--- a/beamerthemeplainculight.sty Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,101 +0,0 @@
-%%\Providespackage{beamerthemeplainculight}[2003/11/07 ver 0.93]
-\NeedsTeXFormat{LaTeX2e}[1995/12/01]
-
-% Copyright 2003 by Till Tantau <tantau@cs.tu-berlin.de>.
-%
-% This program can be redistributed and/or modified under the terms
-% of the LaTeX Project Public License Distributed from CTAN
-% archives in directory macros/latex/base/lppl.txt.
-
-\newcommand{\slidecaption}{}
-
-\mode<presentation>
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-% comic fonts fonts
-\DeclareFontFamily{T1}{comic}{}%
-\DeclareFontShape{T1}{comic}{m}{n}{<->s*[.9]comic8t}{}%
-\DeclareFontShape{T1}{comic}{m}{it}{<->s*[.9]comic8t}{}%
-\DeclareFontShape{T1}{comic}{m}{sc}{<->s*[.9]comic8t}{}%
-\DeclareFontShape{T1}{comic}{b}{n}{<->s*[.9]comicbd8t}{}%
-\DeclareFontShape{T1}{comic}{b}{it}{<->s*[.9]comicbd8t}{}%
-\DeclareFontShape{T1}{comic}{m}{sl}{<->ssub * comic/m/it}{}%
-\DeclareFontShape{T1}{comic}{b}{sc}{<->sub * comic/m/sc}{}%
-\DeclareFontShape{T1}{comic}{b}{sl}{<->ssub * comic/b/it}{}%
-\DeclareFontShape{T1}{comic}{bx}{n}{<->ssub * comic/b/n}{}%
-\DeclareFontShape{T1}{comic}{bx}{it}{<->ssub * comic/b/it}{}%
-\DeclareFontShape{T1}{comic}{bx}{sc}{<->sub * comic/m/sc}{}%
-\DeclareFontShape{T1}{comic}{bx}{sl}{<->ssub * comic/b/it}{}%
-%
-\renewcommand{\rmdefault}{comic}%
-\renewcommand{\sfdefault}{comic}%
-\renewcommand{\mathfamilydefault}{cmr}% mathfont should be still the old one
-%
-\DeclareMathVersion{bold}% mathfont needs to be bold
-\DeclareSymbolFont{operators}{OT1}{cmr}{b}{n}%
-\SetSymbolFont{operators}{bold}{OT1}{cmr}{b}{n}%
-\DeclareSymbolFont{letters}{OML}{cmm}{b}{it}%
-\SetSymbolFont{letters}{bold}{OML}{cmm}{b}{it}%
-\DeclareSymbolFont{symbols}{OMS}{cmsy}{b}{n}%
-\SetSymbolFont{symbols}{bold}{OMS}{cmsy}{b}{n}%
-\DeclareSymbolFont{largesymbols}{OMX}{cmex}{b}{n}%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-% Frametitles
-\setbeamerfont{frametitle}{size={\LARGE}}
-\setbeamerfont{frametitle}{family={\usefont{T1}{ptm}{b}{n}}}
-\setbeamercolor{frametitle}{fg=ProcessBlue,bg=white}
-
-\setbeamertemplate{frametitle}{%
-\vskip 2mm % distance from the top margin
-\hskip -3mm % distance from left margin
-\vbox{%
-\begin{minipage}{1.05\textwidth}%
-\centering%
-\insertframetitle%
-\end{minipage}}%
-}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-% Foot
-%
-\setbeamertemplate{navigation symbols}{}
-\usefoottemplate{%
-\vbox{%
- \tinyline{%
- \tiny\hfill\textcolor{gray!50}{\slidecaption{} --
- p.~\insertframenumber/\inserttotalframenumber}}}%
-}
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\beamertemplateballitem
-\setlength\leftmargini{2mm}
-\setlength\leftmarginii{0.6cm}
-\setlength\leftmarginiii{1.5cm}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-% blocks
-%\definecolor{cream}{rgb}{1,1,.65}
-\definecolor{cream}{rgb}{1,1,.8}
-\setbeamerfont{block title}{size=\normalsize}
-\setbeamercolor{block title}{fg=black,bg=cream}
-\setbeamercolor{block body}{fg=black,bg=cream}
-
-\setbeamertemplate{blocks}[rounded][shadow=true]
-
-\setbeamercolor{boxcolor}{fg=black,bg=cream}
-
-\mode
-<all>
-
-
-
-
-
-
--- a/fib.while Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,15 +0,0 @@
-/* Fibonacci Program
- input: n
-*/
-
-n := 19;
-minus1 := 0;
-minus2 := 1;
-while n > 0 do {
- temp := minus2;
- minus2 := minus1 + minus2;
- minus1 := temp;
- n := n - 1
-};
-write minus2
-
Binary file hw/hw01.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw01.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,42 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+
+\begin{document}
+
+\section*{Homework 1}
+
+\begin{enumerate}
+\item {\bf (Optional)} If you want to run the code presented
+in the lectures, install the
+Scala programming language available (for free) from
+\begin{center}
+\url{http://www.scala-lang.org}
+\end{center}
+
+\item {\bf (Optional)} Have a look at the crawler programs.
+Can you find a usage for them in your daily programming life?
+
+\item In the context of the AFL-course, what is meant by the term \emph{language}?
+
+\item Give the definition for regular expressions. What is the meaning of a
+regular expression?
+
+\item Assume the concatenation operation of two strings is written as $s_1 @ s_2$.
+Define the operation of \emph{concatenating} two sets of strings.
+
+\item How is the power of a language defined? (Hint: There are two rules, one for $\_\!\_^0$ and
+one for $\_\!\_^{n+1}$.)
+
+\item Given the regular expressions $r_1 = \epsilon$ and $r_2 = \varnothing$ and $r_3 = a$.
+How many strings can the regular expressions $r_1^*$, $r_2^*$ and $r_3^*$ each match?
+
+\end{enumerate}
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/hw02.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw02.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,36 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+
+\begin{document}
+
+\section*{Homework 2}
+
+\begin{enumerate}
+\item Give regular expressions for (a) decimal numbers and for (b) binary numbers.
+(Hint: Observe that the empty string is not a number. Also observe that leading 0s
+are normally not written.)
+
+\item Decide whether the following two regular expressions are equivalent $(\epsilon + a)^* \equiv^? a^*$ and
+$(a \cdot b)^* \cdot a \equiv^? a \cdot (b \cdot a)^*$.
+
+\item Given the regular expression $r = (a \cdot b + b)^*$. Compute what the derivative of $r$ is with respect to
+$a$ and $b$. Is $r$ nullable?
+
+\item What is a regular language?
+
+\item Prove that for all regular expressions $r$ we have
+\begin{center}
+$\text{nullable}(r)$ \quad if and only if \quad $\texttt{""} \in L(r)$
+\end{center}
+
+\end{enumerate}
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/hw03.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw03.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,49 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+
+\begin{document}
+
+\section*{Homework 3}
+
+\begin{enumerate}
+\item Assume you have an alphabet consisting of the letters $a$, $b$ and $c$ only.
+(a) Find a regular expression that recognises the two strings $ab$ and $ac$. (b)
+Find a regular expression that matches all strings \emph{except} these two strings.
+Note, you can only use regular expressions of the form
+\begin{center}
+$r ::= \varnothing \;|\; \epsilon \;|\; c \;|\; r_1 + r_2 \;|\; r_1 \cdot r_2 \;|\; r^*$
+\end{center}
+
+\item Define the function $zeroable$ which takes a regular expression as argument
+and returns a boolean.\footnote{In an earlier version there was an error.} The
+function should satisfy the following property:
+\begin{center}
+$zeroable(r)$ \;if and only if\; $L(r) = \varnothing$
+\end{center}
+
+\item Define the tokens and regular expressions for a language
+consisting of numbers, left-parenthesis (, right-parenthesis ),
+identifiers and the operations $+$, $-$ and $*$. Can the following strings
+in this language be lexed?
+
+\begin{itemize}
+\item \texttt{"}$(a + 3) * b$\texttt{"}
+\item \texttt{"}$)()++ -33$\texttt{"}
+\item \texttt{"}$(a / 3) * 3$\texttt{"}
+\end{itemize}
+
+
+In case they can, can you give the corresponding token sequences.
+\end{enumerate}
+
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/hw04.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw04.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,109 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+\section*{Homework 4}
+
+\begin{enumerate}
+\item Why is every finite set of strings a regular language?
+
+\item What is the language recognised by the regular expressions $(\varnothing^*)^*$.
+
+\item If a regular expression $r$ does not contain any occurrence of $\varnothing$
+is it possible for $L(r)$ to be empty?
+
+\item Assume that $s^{-1}$ stands for the operation of reversing a
+string $s$. Given the following \emph{reversing} function on regular
+expressions
+
+\begin{center}
+\begin{tabular}{r@{\hspace{1mm}}c@{\hspace{1mm}}l}
+$rev(\varnothing)$ & $\dn$ & $\varnothing$\\
+$rev(\epsilon)$ & $\dn$ & $\epsilon$\\
+$rev(c)$ & $\dn$ & $c$\\
+$rev(r_1 + r_2)$ & $\dn$ & $rev(r_1) + rev(r_2)$\\
+$rev(r_1 \cdot r_2)$ & $\dn$ & $rev(r_2) \cdot rev(r_1)$\\
+$rev(r^*)$ & $\dn$ & $rev(r)^*$\\
+\end{tabular}
+\end{center}
+
+
+and the set
+
+\begin{center}
+$Rev\,A \dn \{s^{-1} \;|\; s \in A\}$
+\end{center}
+
+prove whether
+
+\begin{center}
+$L(rev(r)) = Rev (L(r))$
+\end{center}
+
+holds.
+
+\item Give a regular expression over the alphabet $\{a,b\}$ recognising all strings
+that do not contain any substring $bb$ and end in $a$.
+
+\item Assume the delimiters for comments are \texttt{$\slash$*} and \texttt{*$\slash$}.
+Give a regular expression that can recognise comments
+of the form
+
+\begin{center}
+\texttt{$\slash$*~\ldots{}~*$\slash$}
+\end{center}
+
+where the three dots stand for arbitrary characters, but not comment delimiters.
+(Hint: You can assume you are already given a regular expression written \texttt{ALL},
+that can recognise any character, and a regular expression \texttt{NOT} that recognises
+the complement of a regular expression.)
+
+\item Given the alphabet $\{a,b\}$. Draw the automaton that has two states, say $q_0$ and $q_1$.
+The starting state is $q_0$ and the final state is $q_1$. The transition
+function is given by
+
+\begin{center}
+\begin{tabular}{l}
+$(q_0, a) \rightarrow q_0$\\
+$(q_0, b) \rightarrow q_1$\\
+$(q_1, b) \rightarrow q_1$
+\end{tabular}
+\end{center}
+
+What is the languages recognised by this automaton?
+
+\item Give a deterministic finite automaton that can recognise
+the language $L(a^*\cdot b\cdot b^*)$.
+
+
+\item (Optional) The tokenizer in \texttt{regexp3.scala} takes as
+argument a string and a list of rules. The result is a list of tokens. Improve this tokenizer so
+that it filters out all comments and whitespace from the result.
+
+\item (Optional) Modify the tokenizer in \texttt{regexp2.scala} so that it
+implements the \texttt{findAll} function. This function takes a regular
+expressions and a string, and returns all substrings in this string that
+match the regular expression.
+\end{enumerate}
+
+% explain what is a context-free grammar and the language it generates
+%
+%
+% Define the language L(M) accepted by a deterministic finite automaton M.
+%
+%
+% does (a + b)*b+ and (a*b+) + (b*b+) define the same language
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/hw05.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw05.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,116 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+\usepackage{tikz}
+\usetikzlibrary{automata}
+
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+\section*{Homework 5}
+
+\begin{enumerate}
+\item Define the following regular expressions
+
+\begin{center}
+\begin{tabular}{ll}
+$r^+$ & (one or more matches)\\
+$r^?$ & (zero or one match)\\
+$r^{\{n\}}$ & (exactly $n$ matches)\\
+$r^{\{m, n\}}$ & (at least $m$ and maximal $n$ matches, with the\\
+& \phantom{(}assumption $m \le n$)\\
+\end{tabular}
+\end{center}
+
+in terms of the usual regular expressions
+
+\begin{center}
+$r ::= \varnothing \;|\; \epsilon \;|\; c \;|\; r_1 + r_2 \;|\; r_1 \cdot r_2 \;|\; r^*$
+\end{center}
+
+\item Given a deterministic finite automata $A(Q, q_0, F, \delta)$,
+define which language is recognised by this automaton.
+
+\item Given the following deterministic finite automata over the alphabet
+$\{a, b\}$, find an automaton that recognises the complement language.
+(Hint: Recall that for the algorithm from the lectures, the automaton needs to be
+in completed form, that is have a transition for every letter from the alphabet.)
+
+\begin{center}
+\begin{tikzpicture}[scale=3, line width=0.7mm]
+ \node[state, initial] (q0) at ( 0,1) {$q_0$};
+ \node[state, accepting] (q1) at ( 1,1) {$q_1$};
+ \path[->] (q0) edge node[above] {$a$} (q1)
+ (q1) edge [loop right] node {$b$} ()
+ ;
+\end{tikzpicture}
+\end{center}
+
+\item Given the following deterministic finite automaton
+
+\begin{center}
+\begin{tikzpicture}[scale=3, line width=0.7mm]
+ \node[state, initial] (q0) at ( 0,1) {$q_0$};
+ \node[state,accepting] (q1) at ( 1,1) {$q_1$};
+ \node[state, accepting] (q2) at ( 2,1) {$q_2$};
+ \path[->] (q0) edge node[above] {$b$} (q1)
+ (q1) edge [loop above] node[above] {$a$} ()
+ (q2) edge [loop above] node[above] {$a, b$} ()
+ (q1) edge node[above] {$b$} (q2)
+ (q0) edge[bend right] node[below] {$a$} (q2)
+ ;
+\end{tikzpicture}
+\end{center}
+find the corresponding minimal automaton. State clearly which nodes
+can be merged.
+
+\item Given the following non-deterministic finite automaton over the alphabet $\{a, b\}$,
+find a deterministic finite automaton that recognises the same language:
+
+\begin{center}
+\begin{tikzpicture}[scale=3, line width=0.7mm]
+ \node[state, initial] (q0) at ( 0,1) {$q_0$};
+ \node[state] (q1) at ( 1,1) {$q_1$};
+ \node[state, accepting] (q2) at ( 2,1) {$q_2$};
+ \path[->] (q0) edge node[above] {$a$} (q1)
+ (q0) edge [loop above] node[above] {$b$} ()
+ (q0) edge [loop below] node[below] {$a$} ()
+ (q1) edge node[above] {$a$} (q2)
+ ;
+\end{tikzpicture}
+\end{center}
+
+\item
+Given the following finite deterministic automaton over the alphabet $\{a, b\}$:
+
+\begin{center}
+\begin{tikzpicture}[scale=2, line width=0.5mm]
+ \node[state, initial, accepting] (q0) at ( 0,1) {$q_0$};
+ \node[state, accepting] (q1) at ( 1,1) {$q_1$};
+ \node[state] (q2) at ( 2,1) {$q_2$};
+ \path[->] (q0) edge[bend left] node[above] {$a$} (q1)
+ (q1) edge[bend left] node[above] {$b$} (q0)
+ (q2) edge[bend left=50] node[below] {$b$} (q0)
+ (q1) edge node[above] {$a$} (q2)
+ (q2) edge [loop right] node {$a$} ()
+ (q0) edge [loop below] node {$b$} ()
+ ;
+\end{tikzpicture}
+\end{center}
+
+Give a regular expression that can recognise the same language as
+this automaton. (Hint: If you use Brzozwski's method, you can assume
+Arden's lemma which states that an equation of the form $q = q\cdot r + s$
+has the unique solution $q = s \cdot r^*$.)\
+\end{enumerate}
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/hw06.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw06.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,72 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+\usepackage{tikz}
+\usetikzlibrary{automata}
+
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+\section*{Homework 6}
+
+\begin{enumerate}
+\item (i) Give the regular expressions for lexing a language
+consisting of whitespaces, identifiers (some letters followed by digits), numbers,
+operations \texttt{=}, \texttt{<} and \texttt{>}, and the keywords
+\texttt{if}, \texttt{then} and \texttt{else}.
+(ii) Decide whether the following strings
+can be lexed in this language?
+
+\begin{enumerate}
+\item \texttt{"if y4 = 3 then 1 else 3"}
+\item \texttt{"if33 ifif then then23 else else 32"}
+\item \texttt{"if x4x < 33 then 1 else 3"}
+\end{enumerate}
+
+In case they can, give the corresponding token sequences. (Hint:
+Observe the maximal munch rule and priorities of your regular
+expressions that make the process of lexing unambiguous.)
+
+\item Suppose the grammar
+
+\begin{center}
+\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $F \;|\; F \cdot * \cdot F \;|\; F \cdot \backslash \cdot F$\\
+$F$ & $\rightarrow$ & $T \;|\; T \cdot \texttt{+} \cdot T \;|\; T \cdot \texttt{-} \cdot T$\\
+$T$ & $\rightarrow$ & $num \;|\; \texttt{(} \cdot E \cdot \texttt{)}$\\
+\end{tabular}
+\end{center}
+
+where $E$, $F$ and $T$ are non-terminals, $E$ is the starting symbol of the grammar, and $num$ stands for
+a number token. Give a parse tree for the string \texttt{(3+3)+(2*3)}.
+
+\item Define what it means for a grammar to be ambiguous. Give an example of
+an ambiguous grammar.
+
+\item Suppose boolean expressions are built up from
+
+\begin{center}
+\begin{tabular}{ll}
+1.) & tokens for \texttt{true} and \texttt{false},\\
+2.) & the infix operations \texttt{$\wedge$} and \texttt{$\vee$},\\
+3.) & the prefix operation $\neg$, and\\
+4.) & can be enclosed in parentheses.
+\end{tabular}
+\end{center}
+
+(i) Give a grammar that can recognise such boolean expressions
+and (ii) give a sample string involving all rules given in 1.-4.~that
+can be parsed by this grammar.
+
+
+\end{enumerate}
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/hw07.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw07.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,75 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+\usepackage{tikz}
+\usetikzlibrary{automata}
+
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+\section*{Homework 7}
+
+\begin{enumerate}
+\item Suppose the following finite deterministic automaton over the alphabet $\{0, 1\}$.
+
+\begin{center}
+\begin{tikzpicture}[scale=2, line width=0.5mm]
+ \node[state, initial, accepting] (q0) at ( 0,1) {$q_0$};
+ \node[state, accepting] (q1) at ( 1,1) {$q_1$};
+ \node[state] (q2) at ( 2,1) {$q_2$};
+ \path[->] (q0) edge[bend left] node[above] {$0$} (q1)
+ (q1) edge[bend left] node[above] {$1$} (q0)
+ (q2) edge[bend left=50] node[below] {$1$} (q0)
+ (q1) edge node[above] {$0$} (q2)
+ (q2) edge [loop right] node {$0$} ()
+ (q0) edge [loop below] node {$1$} ()
+ ;
+\end{tikzpicture}
+\end{center}
+
+Give a regular expression that can recognise the same language as
+this automaton. (Hint: If you use Brzozwski's method, you can assume
+Arden's lemma which states that an equation of the form $q = q\cdot r + s$
+has the unique solution $q = s \cdot r^*$.)
+
+\item Consider the following grammar
+
+\begin{center}
+\begin{tabular}{l}
+$S \rightarrow N\cdot P$\\
+$P \rightarrow V\cdot N$\\
+$N \rightarrow N\cdot N$\\
+$N \rightarrow A \cdot N$\\
+$N \rightarrow \texttt{student} \;|\; \texttt{trainer} \;|\; \texttt{team} \;|\; \texttt{trains}$\\
+$V \rightarrow \texttt{trains} \;|\; \texttt{team}$\\
+$A \rightarrow \texttt{The} \;|\; \texttt{the}$\\
+\end{tabular}
+\end{center}
+
+where $S$ is the start symbol and $S$, $P$, $N$, $V$ and $A$ are non-terminals.
+Using the CYK-algorithm, check whether or not the following string can be parsed
+by the grammar:
+
+\begin{center}
+\texttt{The trainer trains the student team}
+\end{center}
+
+\item {\bf (Optional)} The task is to match strings where the letters are in alphabetical order---for example,
+\texttt{abcfjz} would pass, but \texttt{acb} would not. Whitespace should be ignored---for example
+\texttt{ab c d} should pass. The point is to try to get the regular expression as short as possible!
+See:
+
+\begin{center}
+\url{http://callumacrae.github.com/regex-tuesday/challenge11.html}
+\end{center}
+\end{enumerate}
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/hw08.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/hw08.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,52 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+\usepackage{tikz}
+\usetikzlibrary{automata}
+
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+\section*{Homework 8}
+
+\begin{enumerate}
+\item Suppose the following grammar for the WHILE-language:
+
+\begin{center}
+\begin{tabular}{lcl}
+$Stmt$ & $\rightarrow$ & $\text{skip}$\\
+ & $|$ & $Id := AExp$\\
+ & $|$ & $\text{if}\; B\!Exp \;\text{then}\; Block \;\text{else}\; Block$\\
+ & $|$ & $\text{while}\; B\!Exp \;\text{do}\; Block$\medskip\\
+$Stmts$ & $\rightarrow$ & $Stmt \;\text{;}\; Stmts$\\
+ & $|$ & $Stmt$\medskip\\
+$Block$ & $\rightarrow$ & $\{ Stmts \}$\\
+ & $|$ & $Stmt$\medskip\\
+$AExp$ & $\rightarrow$ & $AExp + AExp$\\
+ & $|$ & $AExp * AExp$\\
+ & $|$ & $( AExp )$\\
+ & $|$ & $Num$\\
+ & $|$ & $Id$\medskip\\
+$BExp$ & $\rightarrow$ & $AExp = AExp$\\
+ & $|$ & $AExp \not= AExp$\\
+ & $|$ & $\text{false}$\\
+ & $|$ & $\text{true}$\\
+
+\end{tabular}
+\end{center}
+
+Transform this grammar into Chomsky normalform.
+
+\item Write a program in the WHILE-language that calculates the factorial function.
+
+\end{enumerate}
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw/proof.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/hw/proof.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,210 @@
+\documentclass{article}
+\usepackage{charter}
+\usepackage{hyperref}
+\usepackage{amssymb}
+\usepackage{amsmath}
+
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+\begin{document}
+
+\section*{Proof}
+
+Recall the definitions for regular expressions and the language associated with a regular expression:
+
+\begin{center}
+\begin{tabular}{c}
+\begin{tabular}[t]{rcl}
+ $r$ & $::=$ & $\varnothing$ \\
+ & $\mid$ & $\epsilon$ \\
+ & $\mid$ & $c$ \\
+ & $\mid$ & $r_1 \cdot r_2$ \\
+ & $\mid$ & $r_1 + r_2$ \\
+ & $\mid$ & $r^*$ \\
+ \end{tabular}\hspace{10mm}
+\begin{tabular}[t]{r@{\hspace{1mm}}c@{\hspace{1mm}}l}
+$L(\varnothing)$ & $\dn$ & $\varnothing$ \\
+$L(\epsilon)$ & $\dn$ & $\{\texttt{""}\}$ \\
+$L(c)$ & $\dn$ & $\{\texttt{"}c\texttt{"}\}$ \\
+$L(r_1 \cdot r_2)$ & $\dn$ & $L(r_1) \,@\, L(r_2)$ \\
+$L(r_1 + r_2)$ & $\dn$ & $L(r_1) \cup L(r_2)$ \\
+ $L(r^*)$ & $\dn$ & $\bigcup_{n\ge 0} L(r)^n$ \\
+ \end{tabular}
+\end{tabular}
+\end{center}
+
+\noindent
+We also defined the notion of a derivative of a regular expression (the derivative with respect to a character):
+
+\begin{center}
+\begin{tabular}{lcl}
+ $der\, c\, (\varnothing)$ & $\dn$ & $\varnothing$ \\
+ $der\, c\, (\epsilon)$ & $\dn$ & $\varnothing$ \\
+ $der\, c\, (d)$ & $\dn$ & if $c = d$ then $\epsilon$ else $\varnothing$\\
+ $der\, c\, (r_1 + r_2)$ & $\dn$ & $(der\, c\, r_1) + (der\, c\, r_2)$ \\
+ $der\, c\, (r_1 \cdot r_2)$ & $\dn$ & if $nullable(r_1)$\\
+ & & then $((der\, c\, r_1) \cdot r_2) + (der\, c\, r_2)$\\
+ & & else $(der\, c\, r_1) \cdot r_2$\\
+ $der\, c\, (r^*)$ & $\dn$ & $(der\, c\, r) \cdot (r^*)$\\
+ \end{tabular}
+\end{center}
+
+\noindent
+With our definition of regular expressions comes an induction principle. Given a property $P$ over
+regular expressions. We can establish that $\forall r.\; P(r)$ holds, provided we can show the following:
+
+\begin{enumerate}
+\item $P(\varnothing)$, $P(\epsilon)$ and $P(c)$ all hold,
+\item $P(r_1 + r_2)$ holds under the induction hypotheses that
+$P(r_1)$ and $P(r_2)$ hold,
+\item $P(r_1 \cdot r_2)$ holds under the induction hypotheses that
+$P(r_1)$ and $P(r_2)$ hold, and
+\item $P(r^*)$ holds under the induction hypothesis that $P(r)$ holds.
+\end{enumerate}
+
+\noindent
+Let us try out an induction proof. Recall the definition
+
+\begin{center}
+$Der\, c\, A \dn \{ s\;\mid\; c\!::\!s \in A\}$
+\end{center}
+
+\noindent
+whereby $A$ is a set of strings. We like to prove
+
+\begin{center}
+\begin{tabular}{l}
+$P(r) \dn $ \hspace{4mm} $L(der\,c\,r) = Der\,c\,(L(r))$
+\end{tabular}
+\end{center}
+
+\noindent
+by induction over the regular expression $r$.
+
+
+\newpage
+\noindent
+{\bf Proof}
+
+\noindent
+According to 1.~above we need to prove $P(\varnothing)$, $P(\epsilon)$ and $P(d)$. Lets do this in turn.
+
+\begin{itemize}
+\item First Case: $P(\varnothing)$ is $L(der\,c\,\varnothing) = Der\,c\,(L(\varnothing))$ (a). We have $der\,c\,\varnothing = \varnothing$
+and $L(\varnothing) = \varnothing$. We also have $Der\,c\,\varnothing = \varnothing$. Hence we have $\varnothing = \varnothing$ in (a).
+
+\item Second Case: $P(\epsilon)$ is $L(der\,c\,\epsilon) = Der\,c\,(L(\epsilon))$ (b). We have $der\,c\,\epsilon = \varnothing$,
+$L(\varnothing) = \varnothing$ and $L(\epsilon) = \{\texttt{""}\}$. We also have $Der\,c\,\{\texttt{""}\} = \varnothing$. Hence we have
+$\varnothing = \varnothing$ in (b).
+
+\item Third Case: $P(d)$ is $L(der\,c\,d) = Der\,c\,(L(d))$ (c). We need to treat the cases $d = c$ and $d \not= c$.
+
+$d = c$: We have $der\,c\,c = \epsilon$ and $L(\epsilon) = \{\texttt{""}\}$.
+We also have $L(c) = \{\texttt{"}c\texttt{"}\}$ and $Der\,c\,\{\texttt{"}c\texttt{"}\} = \{\texttt{""}\}$. Hence we have
+$\{\texttt{""}\} = \{\texttt{""}\}$ in (c).
+
+$d \not=c$: We have $der\,c\,d = \varnothing$.
+We also have $Der\,c\,\{\texttt{"}d\texttt{"}\} = \varnothing$. Hence we have
+$\varnothing = \varnothing$ in (c).
+\end{itemize}
+
+\noindent
+These were the easy base cases. Now come the inductive cases.
+
+\begin{itemize}
+\item Fourth Case: $P(r_1 + r_2)$ is $L(der\,c\,(r_1 + r_2)) = Der\,c\,(L(r_1 + r_2))$ (d). This is what we have to show.
+We can assume already:
+
+\begin{center}
+\begin{tabular}{ll}
+$P(r_1)$: & $L(der\,c\,r_1) = Der\,c\,(L(r_1))$ (I)\\
+$P(r_2)$: & $L(der\,c\,r_2) = Der\,c\,(L(r_2))$ (II)
+\end{tabular}
+\end{center}
+
+We have that $der\,c\,(r_1 + r_2) = (der\,c\,r_1) + (der\,c\,r_2)$ and also $L((der\,c\,r_1) + (der\,c\,r_2)) = L(der\,c\,r_1) \cup L(der\,c\,r_2)$.
+By (I) and (II) we know that the left-hand side is $Der\,c\,(L(r_1)) \cup Der\,c\,(L(r_2))$. You need to ponder a bit, but you should see
+that
+
+\begin{center}
+$Der\,c(A \cup B) = (Der\,c\,A) \cup (Der\,c\,B)$
+\end{center}
+
+holds for every set of strings $A$ and $B$. That means the right-hand side of (d) is also $Der\,c\,(L(r_1)) \cup Der\,c\,(L(r_2))$,
+because $L(r_1 + r_2) = L(r_1) \cup L(r_2)$. And we are done with the fourth case.
+
+\item Fifth Case: $P(r_1 \cdot r_2)$ is $L(der\,c\,(r_1 \cdot r_2)) = Der\,c\,(L(r_1 \cdot r_2))$ (e). We can assume already:
+
+\begin{center}
+\begin{tabular}{ll}
+$P(r_1)$: & $L(der\,c\,r_1) = Der\,c\,(L(r_1))$ (I)\\
+$P(r_2)$: & $L(der\,c\,r_2) = Der\,c\,(L(r_2))$ (II)
+\end{tabular}
+\end{center}
+
+Let us first consider the case where $nullable(r_1)$ holds. Then
+
+\[
+der\,c\,(r_1 \cdot r_2) = ((der\,c\,r_1) \cdot r_2) + (der\,c\,r_2).
+\]
+
+The corresponding language of the right-hand side is
+
+\[
+(L(der\,c\,r_1) \,@\, L(r_2)) \cup L(der\,c\,r_2).
+\]
+
+By the induction hypotheses (I) and (II), this is equal to
+
+\[
+(Der\,c\,(L(r_1)) \,@\, L(r_2)) \cup (Der\,c\,(L(r_2)).\;\;(**)
+\]
+
+We also know that $L(r_1 \cdot r_2) = L(r_1) \,@\,L(r_2)$. We have to know what
+$Der\,c\,(L(r_1) \,@\,L(r_2))$ is.
+
+Let us analyse what
+$Der\,c\,(A \,@\, B)$ is for arbitrary sets of strings $A$ and $B$. If $A$ does \emph{not}
+contain the empty string, then every string in $A\,@\,B$ is of the form $s_1 \,@\, s_2$ where
+$s_1 \in A$ and $s_2 \in B$. So if $s_1$ starts with $c$ then we just have to remove it. Consequently,
+$Der\,c\,(A \,@\, B) = (Der\,c\,(A)) \,@\, B$. This case does not apply here though, because we already
+proved that if $r_1$ is nullable, then $L(r_1)$ contains the empty string. In this case, every string
+in $A\,@\,B$ is either of the form $s_1 \,@\, s_2$, with $s_1 \in A$ and $s_2 \in B$, or
+$s_3$ with $s_3 \in B$. This means $Der\,c\,(A \,@\, B) = ((Der\,c\,(A)) \,@\, B) \cup Der\,c\,B$.
+But this proves that (**) is $Der\,c\,(L(r_1) \,@\, L(r_2))$.
+
+Similarly in the case where $r_1$ is \emph{not} nullable.
+
+\item Sixth Case: $P(r^*)$ is $L(der\,c\,(r^*)) = Der\,c\,L(r^*)$. We can assume already:
+
+\begin{center}
+\begin{tabular}{ll}
+$P(r)$: & $L(der\,c\,r) = Der\,c\,(L(r))$ (I)
+\end{tabular}
+\end{center}
+
+We have $der\,c\,(r^*) = der\,c\,r\cdot r^*$. Which means $L(der\,c\,(r^*)) = L(der\,c\,r\cdot r^*)$ and
+further $L(der\,c\,r) \,@\, L(r^*)$. By induction hypothesis (I) we know that is equal to
+$(Der\,c\,L(r)) \,@\, L(r^*)$. (*)
+
+\end{itemize}
+
+
+
+
+Let us now analyse $Der\,c\,L(r^*)$, which is equal to $Der\,c\,((L(r))^*)$. Now $(L(r))^*$ is defined
+as $\bigcup_{n \ge 0} L(r)$. We can write this as $L(r)^0 \cup \bigcup_{n \ge 1} L(r)$, where we just
+separated the first union and then let the ``big-union'' start from $1$. Form this we can already infer
+
+\begin{center}
+$Der\,c\,(L(r^*)) = Der\,c\,(L(r)^0 \cup \bigcup_{n \ge 1} L(r)) = (Der\,c\,L(r)^0) \cup Der\,c\,(\bigcup_{n \ge 1} L(r))$
+\end{center}
+
+The first union ``disappears'' since $Der\,c\,(L(r)^0) = \varnothing$.
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
Binary file hw01.pdf has changed
--- a/hw01.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,42 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-
-\begin{document}
-
-\section*{Homework 1}
-
-\begin{enumerate}
-\item {\bf (Optional)} If you want to run the code presented
-in the lectures, install the
-Scala programming language available (for free) from
-\begin{center}
-\url{http://www.scala-lang.org}
-\end{center}
-
-\item {\bf (Optional)} Have a look at the crawler programs.
-Can you find a usage for them in your daily programming life?
-
-\item In the context of the AFL-course, what is meant by the term \emph{language}?
-
-\item Give the definition for regular expressions. What is the meaning of a
-regular expression?
-
-\item Assume the concatenation operation of two strings is written as $s_1 @ s_2$.
-Define the operation of \emph{concatenating} two sets of strings.
-
-\item How is the power of a language defined? (Hint: There are two rules, one for $\_\!\_^0$ and
-one for $\_\!\_^{n+1}$.)
-
-\item Given the regular expressions $r_1 = \epsilon$ and $r_2 = \varnothing$ and $r_3 = a$.
-How many strings can the regular expressions $r_1^*$, $r_2^*$ and $r_3^*$ each match?
-
-\end{enumerate}
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
Binary file hw02.pdf has changed
--- a/hw02.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,36 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-\usepackage{amsmath}
-
-\begin{document}
-
-\section*{Homework 2}
-
-\begin{enumerate}
-\item Give regular expressions for (a) decimal numbers and for (b) binary numbers.
-(Hint: Observe that the empty string is not a number. Also observe that leading 0s
-are normally not written.)
-
-\item Decide whether the following two regular expressions are equivalent $(\epsilon + a)^* \equiv^? a^*$ and
-$(a \cdot b)^* \cdot a \equiv^? a \cdot (b \cdot a)^*$.
-
-\item Given the regular expression $r = (a \cdot b + b)^*$. Compute what the derivative of $r$ is with respect to
-$a$ and $b$. Is $r$ nullable?
-
-\item What is a regular language?
-
-\item Prove that for all regular expressions $r$ we have
-\begin{center}
-$\text{nullable}(r)$ \quad if and only if \quad $\texttt{""} \in L(r)$
-\end{center}
-
-\end{enumerate}
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
Binary file hw03.pdf has changed
--- a/hw03.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,49 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-\usepackage{amsmath}
-
-\begin{document}
-
-\section*{Homework 3}
-
-\begin{enumerate}
-\item Assume you have an alphabet consisting of the letters $a$, $b$ and $c$ only.
-(a) Find a regular expression that recognises the two strings $ab$ and $ac$. (b)
-Find a regular expression that matches all strings \emph{except} these two strings.
-Note, you can only use regular expressions of the form
-\begin{center}
-$r ::= \varnothing \;|\; \epsilon \;|\; c \;|\; r_1 + r_2 \;|\; r_1 \cdot r_2 \;|\; r^*$
-\end{center}
-
-\item Define the function $zeroable$ which takes a regular expression as argument
-and returns a boolean.\footnote{In an earlier version there was an error.} The
-function should satisfy the following property:
-\begin{center}
-$zeroable(r)$ \;if and only if\; $L(r) = \varnothing$
-\end{center}
-
-\item Define the tokens and regular expressions for a language
-consisting of numbers, left-parenthesis (, right-parenthesis ),
-identifiers and the operations $+$, $-$ and $*$. Can the following strings
-in this language be lexed?
-
-\begin{itemize}
-\item \texttt{"}$(a + 3) * b$\texttt{"}
-\item \texttt{"}$)()++ -33$\texttt{"}
-\item \texttt{"}$(a / 3) * 3$\texttt{"}
-\end{itemize}
-
-
-In case they can, can you give the corresponding token sequences.
-\end{enumerate}
-
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
Binary file hw04.pdf has changed
--- a/hw04.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,109 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-\usepackage{amsmath}
-
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-\section*{Homework 4}
-
-\begin{enumerate}
-\item Why is every finite set of strings a regular language?
-
-\item What is the language recognised by the regular expressions $(\varnothing^*)^*$.
-
-\item If a regular expression $r$ does not contain any occurrence of $\varnothing$
-is it possible for $L(r)$ to be empty?
-
-\item Assume that $s^{-1}$ stands for the operation of reversing a
-string $s$. Given the following \emph{reversing} function on regular
-expressions
-
-\begin{center}
-\begin{tabular}{r@{\hspace{1mm}}c@{\hspace{1mm}}l}
-$rev(\varnothing)$ & $\dn$ & $\varnothing$\\
-$rev(\epsilon)$ & $\dn$ & $\epsilon$\\
-$rev(c)$ & $\dn$ & $c$\\
-$rev(r_1 + r_2)$ & $\dn$ & $rev(r_1) + rev(r_2)$\\
-$rev(r_1 \cdot r_2)$ & $\dn$ & $rev(r_2) \cdot rev(r_1)$\\
-$rev(r^*)$ & $\dn$ & $rev(r)^*$\\
-\end{tabular}
-\end{center}
-
-
-and the set
-
-\begin{center}
-$Rev\,A \dn \{s^{-1} \;|\; s \in A\}$
-\end{center}
-
-prove whether
-
-\begin{center}
-$L(rev(r)) = Rev (L(r))$
-\end{center}
-
-holds.
-
-\item Give a regular expression over the alphabet $\{a,b\}$ recognising all strings
-that do not contain any substring $bb$ and end in $a$.
-
-\item Assume the delimiters for comments are \texttt{$\slash$*} and \texttt{*$\slash$}.
-Give a regular expression that can recognise comments
-of the form
-
-\begin{center}
-\texttt{$\slash$*~\ldots{}~*$\slash$}
-\end{center}
-
-where the three dots stand for arbitrary characters, but not comment delimiters.
-(Hint: You can assume you are already given a regular expression written \texttt{ALL},
-that can recognise any character, and a regular expression \texttt{NOT} that recognises
-the complement of a regular expression.)
-
-\item Given the alphabet $\{a,b\}$. Draw the automaton that has two states, say $q_0$ and $q_1$.
-The starting state is $q_0$ and the final state is $q_1$. The transition
-function is given by
-
-\begin{center}
-\begin{tabular}{l}
-$(q_0, a) \rightarrow q_0$\\
-$(q_0, b) \rightarrow q_1$\\
-$(q_1, b) \rightarrow q_1$
-\end{tabular}
-\end{center}
-
-What is the languages recognised by this automaton?
-
-\item Give a deterministic finite automaton that can recognise
-the language $L(a^*\cdot b\cdot b^*)$.
-
-
-\item (Optional) The tokenizer in \texttt{regexp3.scala} takes as
-argument a string and a list of rules. The result is a list of tokens. Improve this tokenizer so
-that it filters out all comments and whitespace from the result.
-
-\item (Optional) Modify the tokenizer in \texttt{regexp2.scala} so that it
-implements the \texttt{findAll} function. This function takes a regular
-expressions and a string, and returns all substrings in this string that
-match the regular expression.
-\end{enumerate}
-
-% explain what is a context-free grammar and the language it generates
-%
-%
-% Define the language L(M) accepted by a deterministic finite automaton M.
-%
-%
-% does (a + b)*b+ and (a*b+) + (b*b+) define the same language
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
Binary file hw05.pdf has changed
Binary file hw06.pdf has changed
--- a/hw06.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,72 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-\usepackage{amsmath}
-\usepackage{tikz}
-\usetikzlibrary{automata}
-
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-\section*{Homework 6}
-
-\begin{enumerate}
-\item (i) Give the regular expressions for lexing a language
-consisting of whitespaces, identifiers (some letters followed by digits), numbers,
-operations \texttt{=}, \texttt{<} and \texttt{>}, and the keywords
-\texttt{if}, \texttt{then} and \texttt{else}.
-(ii) Decide whether the following strings
-can be lexed in this language?
-
-\begin{enumerate}
-\item \texttt{"if y4 = 3 then 1 else 3"}
-\item \texttt{"if33 ifif then then23 else else 32"}
-\item \texttt{"if x4x < 33 then 1 else 3"}
-\end{enumerate}
-
-In case they can, give the corresponding token sequences. (Hint:
-Observe the maximal munch rule and priorities of your regular
-expressions that make the process of lexing unambiguous.)
-
-\item Suppose the grammar
-
-\begin{center}
-\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $F \;|\; F \cdot * \cdot F \;|\; F \cdot \backslash \cdot F$\\
-$F$ & $\rightarrow$ & $T \;|\; T \cdot \texttt{+} \cdot T \;|\; T \cdot \texttt{-} \cdot T$\\
-$T$ & $\rightarrow$ & $num \;|\; \texttt{(} \cdot E \cdot \texttt{)}$\\
-\end{tabular}
-\end{center}
-
-where $E$, $F$ and $T$ are non-terminals, $E$ is the starting symbol of the grammar, and $num$ stands for
-a number token. Give a parse tree for the string \texttt{(3+3)+(2*3)}.
-
-\item Define what it means for a grammar to be ambiguous. Give an example of
-an ambiguous grammar.
-
-\item Suppose boolean expressions are built up from
-
-\begin{center}
-\begin{tabular}{ll}
-1.) & tokens for \texttt{true} and \texttt{false},\\
-2.) & the infix operations \texttt{$\wedge$} and \texttt{$\vee$},\\
-3.) & the prefix operation $\neg$, and\\
-4.) & can be enclosed in parentheses.
-\end{tabular}
-\end{center}
-
-(i) Give a grammar that can recognise such boolean expressions
-and (ii) give a sample string involving all rules given in 1.-4.~that
-can be parsed by this grammar.
-
-
-\end{enumerate}
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
Binary file hw07.pdf has changed
--- a/hw07.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,75 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-\usepackage{amsmath}
-\usepackage{tikz}
-\usetikzlibrary{automata}
-
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-\section*{Homework 7}
-
-\begin{enumerate}
-\item Suppose the following finite deterministic automaton over the alphabet $\{0, 1\}$.
-
-\begin{center}
-\begin{tikzpicture}[scale=2, line width=0.5mm]
- \node[state, initial, accepting] (q0) at ( 0,1) {$q_0$};
- \node[state, accepting] (q1) at ( 1,1) {$q_1$};
- \node[state] (q2) at ( 2,1) {$q_2$};
- \path[->] (q0) edge[bend left] node[above] {$0$} (q1)
- (q1) edge[bend left] node[above] {$1$} (q0)
- (q2) edge[bend left=50] node[below] {$1$} (q0)
- (q1) edge node[above] {$0$} (q2)
- (q2) edge [loop right] node {$0$} ()
- (q0) edge [loop below] node {$1$} ()
- ;
-\end{tikzpicture}
-\end{center}
-
-Give a regular expression that can recognise the same language as
-this automaton. (Hint: If you use Brzozwski's method, you can assume
-Arden's lemma which states that an equation of the form $q = q\cdot r + s$
-has the unique solution $q = s \cdot r^*$.)
-
-\item Consider the following grammar
-
-\begin{center}
-\begin{tabular}{l}
-$S \rightarrow N\cdot P$\\
-$P \rightarrow V\cdot N$\\
-$N \rightarrow N\cdot N$\\
-$N \rightarrow A \cdot N$\\
-$N \rightarrow \texttt{student} \;|\; \texttt{trainer} \;|\; \texttt{team} \;|\; \texttt{trains}$\\
-$V \rightarrow \texttt{trains} \;|\; \texttt{team}$\\
-$A \rightarrow \texttt{The} \;|\; \texttt{the}$\\
-\end{tabular}
-\end{center}
-
-where $S$ is the start symbol and $S$, $P$, $N$, $V$ and $A$ are non-terminals.
-Using the CYK-algorithm, check whether or not the following string can be parsed
-by the grammar:
-
-\begin{center}
-\texttt{The trainer trains the student team}
-\end{center}
-
-\item {\bf (Optional)} The task is to match strings where the letters are in alphabetical order---for example,
-\texttt{abcfjz} would pass, but \texttt{acb} would not. Whitespace should be ignored---for example
-\texttt{ab c d} should pass. The point is to try to get the regular expression as short as possible!
-See:
-
-\begin{center}
-\url{http://callumacrae.github.com/regex-tuesday/challenge11.html}
-\end{center}
-\end{enumerate}
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
Binary file hw08.pdf has changed
--- a/hw08.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,52 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-\usepackage{amsmath}
-\usepackage{tikz}
-\usetikzlibrary{automata}
-
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-\section*{Homework 8}
-
-\begin{enumerate}
-\item Suppose the following grammar for the WHILE-language:
-
-\begin{center}
-\begin{tabular}{lcl}
-$Stmt$ & $\rightarrow$ & $\text{skip}$\\
- & $|$ & $Id := AExp$\\
- & $|$ & $\text{if}\; B\!Exp \;\text{then}\; Block \;\text{else}\; Block$\\
- & $|$ & $\text{while}\; B\!Exp \;\text{do}\; Block$\medskip\\
-$Stmts$ & $\rightarrow$ & $Stmt \;\text{;}\; Stmts$\\
- & $|$ & $Stmt$\medskip\\
-$Block$ & $\rightarrow$ & $\{ Stmts \}$\\
- & $|$ & $Stmt$\medskip\\
-$AExp$ & $\rightarrow$ & $AExp + AExp$\\
- & $|$ & $AExp * AExp$\\
- & $|$ & $( AExp )$\\
- & $|$ & $Num$\\
- & $|$ & $Id$\medskip\\
-$BExp$ & $\rightarrow$ & $AExp = AExp$\\
- & $|$ & $AExp \not= AExp$\\
- & $|$ & $\text{false}$\\
- & $|$ & $\text{true}$\\
-
-\end{tabular}
-\end{center}
-
-Transform this grammar into Chomsky normalform.
-
-\item Write a program in the WHILE-language that calculates the factorial function.
-
-\end{enumerate}
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/LOOP.j Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,90 @@
+
+.class public LOOP.LOOP
+.super java/lang/Object
+
+.method public <init>()V
+ aload_0
+ invokenonvirtual java/lang/Object/<init>()V
+ return
+.end method
+
+.method public static write(I)V
+ .limit locals 5
+ .limit stack 5
+ iload 0
+ getstatic java/lang/System/out Ljava/io/PrintStream;
+ swap
+ invokevirtual java/io/PrintStream/println(I)V
+ return
+.end method
+
+
+.method public static main([Ljava/lang/String;)V
+ .limit locals 200
+ .limit stack 200
+
+ldc 750000
+istore 0
+iload 0
+istore 1
+iload 0
+istore 2
+iload 0
+istore 3
+
+Loop_begin_48:
+
+ldc 0
+iload 1
+if_icmpge Loop_end_49
+
+Loop_begin_50:
+
+ldc 0
+iload 2
+if_icmpge Loop_end_51
+
+Loop_begin_52:
+
+ldc 0
+iload 3
+if_icmpge Loop_end_53
+iload 3
+ldc 1
+isub
+istore 3
+goto Loop_begin_52
+
+Loop_end_53:
+
+iload 0
+istore 3
+iload 2
+ldc 1
+isub
+istore 2
+goto Loop_begin_50
+
+Loop_end_51:
+
+iload 0
+istore 2
+iload 1
+ldc 1
+isub
+istore 1
+goto Loop_begin_48
+
+Loop_end_49:
+
+iload 1
+invokestatic LOOP/LOOP/write(I)V
+iload 2
+invokestatic LOOP/LOOP/write(I)V
+iload 3
+invokestatic LOOP/LOOP/write(I)V
+
+
+ return
+
+.end method
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/S_grammar-token.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,47 @@
+//:load matcher.scala
+//:load parser3.scala
+
+abstract class Token
+case object T_ONE extends Token
+
+val lexing_rules : List[Rule[Token]] =
+ List(("1", (s: List[Char]) => T_ONE))
+
+val T = Tokenizer(lexing_rules)
+
+case class TokParser(tok: Token) extends Parser[List[Token], Token] {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((t, ts))
+ case _ => Set ()
+ }
+}
+implicit def token2tokparser(t: Token) = TokParser(t)
+
+case object EmpParser extends Parser[List[Token], String] {
+ def parse(ts: List[Token]) = Set(("", ts))
+}
+
+
+lazy val Su: Parser[List[Token], String] =
+ (T_ONE ~ Su) ==> { case (x, y) => "1" + y} || EmpParser
+
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+def test(i: Int) = {
+ val result = Su.parse_all(T.fromString("1" * i))
+ //print(result.size + " ")
+}
+
+
+for (i <- 1 to 1000 by 50) {
+ print(i + " ")
+ print("%.5f".format(time_needed(1, test(i))))
+ print("\n")
+}
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/S_grammar.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,52 @@
+//:load parser3.scala
+
+case class StringParser(s: String) extends Parser[String, String] {
+ def parse(ts: String) = {
+ if (s.length <= ts.length && ts.startsWith(s)) Set((s, ts.drop(s.length)))
+ else Set()
+ }
+}
+
+implicit def string2parser(s: String) = StringParser(s)
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+// unambiguous grammar
+
+lazy val U: Parser[String, String] =
+ ("1" ~ U) ==> { case (x, y) => "1" + y} || ""
+
+def test1(i: Int) = {
+ val result = U.parse_all("1" * i)
+ //print(result.size + " ")
+}
+
+for (i <- 1 to 1000 by 50) {
+ print(i + " ")
+ print("%.5f".format(time_needed(1, test1(i))))
+ print("\n")
+}
+
+
+
+// ambiguous grammar
+// n = 16 -> over 35 million parse trees
+
+lazy val S: Parser[String, String] =
+ ("1" ~ S ~ S) ==> { case ((x, y), z) => "1" + y + z} || ""
+
+def test2(i: Int) = {
+ val result = S.parse_all("1" * i)
+ print(result.size + " ")
+}
+
+for (i <- 1 to 30) {
+ print(i + " ")
+ print("%.5f".format(time_needed(1, test2(i))))
+ print("\n")
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/Term_grammar.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,62 @@
+//:load matcher.scala
+//:load parser3.scala
+
+// some regular expressions
+val LETTER = RANGE("abcdefghijklmnopqrstuvwxyz")
+val ID = PLUS(LETTER)
+
+val DIGIT = RANGE("0123456789")
+val NONZERODIGIT = RANGE("123456789")
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+
+val LPAREN = CHAR('(')
+val RPAREN = CHAR(')')
+
+val WHITESPACE = PLUS(RANGE(" \n"))
+val OPS = RANGE("+-*")
+
+// for classifying the strings that have been lexed
+abstract class Token
+
+case object T_WHITESPACE extends Token
+case class T_NUM(s: String) extends Token
+case class T_OP(s: String) extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+
+
+// lexing rules for arithmetic expressions
+val lexing_rules: List[Rule[Token]]=
+ List((NUMBER, (s) => T_NUM(s.mkString)),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (OPS, (s) => T_OP(s.mkString)))
+
+val Tk = Tokenizer(lexing_rules, List(T_WHITESPACE))
+
+
+case class TokParser(tok: Token) extends Parser[List[Token], Token] {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((t, ts))
+ case _ => Set ()
+ }
+}
+implicit def token2tparser(t: Token) = TokParser(t)
+
+case object NumParser extends Parser[List[Token], Int] {
+ def parse(ts: List[Token]) = ts match {
+ case T_NUM(s)::ts => Set((s.toInt, ts))
+ case _ => Set ()
+ }
+}
+
+lazy val E: Parser[List[Token], Int] = (T ~ T_OP("+") ~ E) ==> { case ((x, y), z) => x + z } || T
+lazy val T: Parser[List[Token], Int] = (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => x * z } || F
+lazy val F: Parser[List[Token], Int] = (T_LPAREN ~> E <~ T_RPAREN) || NumParser
+
+println(E.parse_all(Tk.fromString("1 + 2 + 3")))
+println(E.parse_all(Tk.fromString("1 + 2 * 3")))
+println(E.parse_all(Tk.fromString("(1 + 2) * 3")))
+println(E.parse_all(Tk.fromString("(14 + 2) * (3 + 2)")))
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app0.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,6 @@
+import io.Source
+
+def get_page(url: String) : String = {
+ Source.fromURL(url).take(10000).mkString
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app1.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,12 @@
+def get_page(url: String) : String = {
+ try {
+ Source.fromURL(url).take(10000).mkString
+ }
+ catch {
+ case e => {
+ println(" Problem with: " + url)
+ ""
+ }
+ }
+}
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app2.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,16 @@
+val http_pattern = """\"https?://[^\"]*\"""".r
+
+def unquote(s: String) = s.drop(1).dropRight(1)
+
+def get_all_URLs(page: String) : Set[String] = {
+ (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+}
+
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ else {
+ println("Visiting: " + n + " " + url)
+ for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
+ }
+}
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app3.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,10 @@
+val my_urls = """urbanc""".r
+
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ else if (my_urls.findFirstIn(url) == None) ()
+ else {
+ println("Visiting: " + n + " " + url)
+ for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
+ }
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app4.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,14 @@
+val http_pattern = """\"https?://[^\"]*\"""".r
+val my_urls = """urbanc""".r
+val email_pattern =
+ """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
+
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ else {
+ println("Visiting: " + n + " " + url)
+ val page = get_page(url)
+ println(email_pattern.findAllIn(page).mkString("\n"))
+ for (u <- get_all_URLs(page)) crawl(u, n - 1)
+ }
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app5.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,8 @@
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app51.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,8 @@
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app6.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,11 @@
+def deriv (r: Rexp, c: Char) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(deriv(r1, c), deriv(r2, c))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(deriv(r1, c), r2), deriv(r2, c))
+ else SEQ(deriv(r1, c), r2)
+ case STAR(r) => SEQ(deriv(r, c), STAR(r))
+}
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app7.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,16 @@
+abstract class Parser[I, T] {
+ def parse(ts: I): Set[(T, I)]
+
+ def parse_all(ts: I) : Set[T] =
+ for ((head, tail) <- parse(ts); if (tail.isEmpty))
+ yield head
+
+ def || (right : => Parser[I, T]) : Parser[I, T] =
+ new AltParser(this, right)
+ def ==>[S] (f: => T => S) : Parser [I, S] =
+ new FunParser(this, f)
+ def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] =
+ new SeqParser(this, right)
+}
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app8.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,23 @@
+class SeqParser[I, T, S](p: => Parser[I, T],
+ q: => Parser[I, S])
+ extends Parser[I, (T, S)] {
+ def parse(sb: I) =
+ for ((head1, tail1) <- p.parse(sb);
+ (head2, tail2) <- q.parse(tail1))
+ yield ((head1, head2), tail2)
+}
+
+class AltParser[I, T](p: => Parser[I, T],
+ q: => Parser[I, T])
+ extends Parser[I, T] {
+ def parse(sb: I) = p.parse(sb) ++ q.parse(sb)
+}
+
+class FunParser[I, T, S](p: => Parser[I, T], f: T => S)
+ extends Parser[I, S] {
+ def parse(sb: I) =
+ for ((head, tail) <- p.parse(sb))
+ yield (f(head), tail)
+}
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/app9.while Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,15 @@
+/* Fibonacci Program
+ input: n
+ */
+
+n := 19;
+minus1 := 0;
+minus2 := 1;
+while n > 0 do {
+ temp := minus2;
+ minus2 := minus1 + minus2;
+ minus1 := temp;
+ n := n - 1
+};
+write minus2
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/automata.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,106 @@
+
+// a class for deterministic finite automata,
+// the type of states is kept polymorphic
+
+case class Automaton[A](start: A, states: Set[A], delta: Map[(A, Char), A], fins: Set[A]) {
+
+ // the transition function lifted to list of characters
+ def deltas(q: A, cs: List[Char]) : Either[A, String] =
+ if (states.contains(q)) cs match {
+ case Nil => Left(q)
+ case c::cs =>
+ if (delta.isDefinedAt(q, c)) deltas(delta(q, c), cs)
+ else Right(q + " does not have a transition for " + c)
+ }
+ else Right(q + " is not a state of the automaton")
+
+ // wether a string is accepted by the automaton
+ def accepts(s: String) = deltas(start, s.toList) match {
+ case Left(q) => fins.contains(q)
+ case _ => false
+ }
+}
+
+
+// translating a regular expression into a finite
+// automaton
+
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+
+implicit def string2rexp(s : String) = {
+ def chars2rexp (cs: List[Char]) : Rexp = cs match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::cs => SEQ(CHAR(c), chars2rexp(cs))
+ }
+ chars2rexp(s.toList)
+}
+
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+}
+
+def der (r: Rexp, c: Char) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(r1, c), der(r2, c))
+ case SEQ(r1, r2) => if (nullable(r1)) ALT(SEQ(der(r1, c), r2), der(r2, c))
+ else SEQ(der(r1, c), r2)
+ case STAR(r) => SEQ(der(r, c), STAR(r))
+}
+
+
+// Here we construct an automaton whose
+// states are regular expressions
+type State = Rexp
+type States = Set[State]
+type Transition = Map[(State, Char), State]
+
+// we use as an alphabet all lowercase letters
+val alphabet = "abcdefghijklmnopqrstuvwxyz".toSet
+
+def goto(q: State, c: Char, qs: States, delta: Transition) : (States, Transition) = {
+ val q_der : State = der(q, c)
+ if (qs.contains(q_der)) (qs, delta + ((q, c) -> q))
+ else explore(qs + q_der, delta + ((q, c) -> q_der), q_der)
+}
+
+def explore (qs: States, delta: Transition, q: State) : (States, Transition) =
+ alphabet.foldRight[(States, Transition)] (qs, delta) ((c, qsd) => goto(q, c, qsd._1, qsd._2))
+
+
+def mk_automaton (r: Rexp) : Automaton[Rexp] = {
+ val (qs, delta) = explore(Set(r), Map(), r);
+ val fins = for (q <- qs if nullable(q)) yield q;
+ Automaton[Rexp](r, qs, delta, fins)
+}
+
+val A = mk_automaton(ALT("ab","ac"))
+
+A.start
+A.states.toList.length
+
+println(A.accepts("bd"))
+println(A.accepts("ab"))
+println(A.accepts("ac"))
+
+val r1 = STAR(ALT("a","b"))
+val r2 = SEQ("b","b")
+val r3 = SEQ(SEQ(SEQ(r1, r2), r1), "a")
+val B = mk_automaton(r3)
+
+B.start
+B.states.toList.length
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/automata1.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,95 @@
+
+// a class for deterministic finite automata,
+// the type of states is kept polymorphic
+
+case class Automaton[A](start: A, states: Set[A], delta: Map[(A, Char), A], fins: Set[A]) {
+
+ // the transition function lifted to list of characters
+ def deltas(q: A, cs: List[Char]) : A =
+ if (states.contains(q)) cs match {
+ case Nil => q
+ case c::cs =>
+ if (delta.isDefinedAt(q, c)) deltas(delta(q, c), cs)
+ else throw new RuntimeException(q + " does not have a transition for " + c)
+ }
+ else throw new RuntimeException(q + " is not a state of the automaton")
+
+ // wether a string is accepted by the automaton
+ def accepts(s: String) =
+ try {
+ fins.contains(deltas(start, s.toList))
+ } catch {
+ case e:RuntimeException => false
+ }
+}
+
+
+
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+
+implicit def string2rexp(s : String) = {
+ def chars2rexp (cs: List[Char]) : Rexp = cs match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::cs => SEQ(CHAR(c), chars2rexp(cs))
+ }
+ chars2rexp(s.toList)
+}
+
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+}
+
+def der (r: Rexp, c: Char) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(r1, c), der(r2, c))
+ case SEQ(r1, r2) => if (nullable(r1)) ALT(SEQ(der(r1, c), r2), der(r2, c))
+ else SEQ(der(r1, c), r2)
+ case STAR(r) => SEQ(der(r, c), STAR(r))
+}
+
+
+// Here we construct an automaton whose
+// states are regular expressions
+type State = Rexp
+type States = Set[State]
+type Transition = Map[(State, Char), State]
+
+def goto(q: State, c: Char, qs: States, delta: Transition) : (States, Transition) = {
+ val qc : State = der(q, c)
+ if (qs.contains(qc)) (qs, delta + ((q, c) -> q))
+ else explore(qs + qc, delta + ((q, c) -> qc), qc)
+}
+
+// we use as alphabet all lowercase letters
+val alphabet = "abcdefghijklmnopqrstuvwxyz".toSet
+
+def explore (qs: States, delta: Transition, q: State) : (States, Transition) =
+ alphabet.foldRight[(States, Transition)] (qs, delta) ((c, qsd) => goto(q, c, qsd._1, qsd._2))
+
+
+def mk_automaton (r: Rexp) : Automaton[Rexp] = {
+ val (qs, delta) = explore(Set(r), Map(), r);
+ val fins = for (q <- qs if nullable(q)) yield q;
+ Automaton[Rexp](r, qs, delta, fins)
+}
+
+val A = mk_automaton(ALT("ab","ac"))
+
+println(A.accepts("bd"))
+println(A.accepts("ab"))
+println(A.accepts("ac"))
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/compile.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,326 @@
+// A parser and evaluator for teh while language
+//
+import matcher._
+import parser._
+
+// some regular expressions
+val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
+val DIGIT = RANGE("0123456789")
+val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
+val NUM = PLUS(DIGIT)
+val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false", "write")
+val SEMI: Rexp = ";"
+val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
+val WHITESPACE = PLUS(RANGE(" \n"))
+val RPAREN: Rexp = ")"
+val LPAREN: Rexp = "("
+val BEGIN: Rexp = "{"
+val END: Rexp = "}"
+val COMMENT = SEQS("/*", NOT(SEQS(STAR(ALLC), "*/", STAR(ALLC))), "*/")
+
+// tokens for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case object T_COMMENT extends Token
+case object T_SEMI extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case object T_BEGIN extends Token
+case object T_END extends Token
+case class T_ID(s: String) extends Token
+case class T_OP(s: String) extends Token
+case class T_NUM(s: String) extends Token
+case class T_KWD(s: String) extends Token
+
+val lexing_rules: List[(Rexp, List[Char] => Token)] =
+ List((KEYWORD, (s) => T_KWD(s.mkString)),
+ (ID, (s) => T_ID(s.mkString)),
+ (OP, (s) => T_OP(s.mkString)),
+ (NUM, (s) => T_NUM(s.mkString)),
+ (SEMI, (s) => T_SEMI),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (BEGIN, (s) => T_BEGIN),
+ (END, (s) => T_END),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (COMMENT, (s) => T_COMMENT))
+
+// the tokenizer
+val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE, T_COMMENT))
+
+// the abstract syntax trees
+abstract class Stmt
+abstract class AExp
+abstract class BExp
+type Block = List[Stmt]
+case object Skip extends Stmt
+case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
+case class While(b: BExp, bl: Block) extends Stmt
+case class Assign(s: String, a: AExp) extends Stmt
+case class Write(s: String) extends Stmt
+
+case class Var(s: String) extends AExp
+case class Num(i: Int) extends AExp
+case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
+
+case object True extends BExp
+case object False extends BExp
+case class Relop(o: String, a1: AExp, a2: AExp) extends BExp
+
+// atomic parsers
+case class TokParser(tok: Token) extends Parser[List[Token], Token] {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((t, ts))
+ case _ => Set ()
+ }
+}
+implicit def token2tparser(t: Token) = TokParser(t)
+
+case object NumParser extends Parser[List[Token], Int] {
+ def parse(ts: List[Token]) = ts match {
+ case T_NUM(s)::ts => Set((s.toInt, ts))
+ case _ => Set ()
+ }
+}
+
+case object IdParser extends Parser[List[Token], String] {
+ def parse(ts: List[Token]) = ts match {
+ case T_ID(s)::ts => Set((s, ts))
+ case _ => Set ()
+ }
+}
+
+
+// arithmetic expressions
+lazy val AExp: Parser[List[Token], AExp] =
+ (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
+ (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
+lazy val T: Parser[List[Token], AExp] =
+ (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
+lazy val F: Parser[List[Token], AExp] =
+ (T_LPAREN ~> AExp <~ T_RPAREN) ||
+ IdParser ==> Var ||
+ NumParser ==> Num
+
+// boolean expressions
+lazy val BExp: Parser[List[Token], BExp] =
+ (T_KWD("true") ==> ((_) => True: BExp)) ||
+ (T_KWD("false") ==> ((_) => False: BExp)) ||
+ (T_LPAREN ~> BExp <~ T_RPAREN) ||
+ (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Relop("=", x, z): BExp } ||
+ (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Relop("!=", x, z): BExp } ||
+ (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Relop("<", x, z): BExp } ||
+ (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Relop("<", z, x): BExp }
+
+lazy val Stmt: Parser[List[Token], Stmt] =
+ (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
+ (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
+ (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
+ { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
+ (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) } ||
+ (T_KWD("write") ~ IdParser) ==> { case (x, y) => Write(y) }
+
+lazy val Stmts: Parser[List[Token], Block] =
+ (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
+ (Stmt ==> ((s) => List(s) : Block))
+
+lazy val Block: Parser[List[Token], Block] =
+ (T_BEGIN ~> Stmts <~ T_END) ||
+ (Stmt ==> ((s) => List(s)))
+
+// compiler
+val beginning = """
+.class public XXX.XXX
+.super java/lang/Object
+
+.method public <init>()V
+ aload_0
+ invokenonvirtual java/lang/Object/<init>()V
+ return
+.end method
+
+.method public static write(I)V
+ .limit locals 5
+ .limit stack 5
+ iload 0
+ getstatic java/lang/System/out Ljava/io/PrintStream;
+ swap
+ invokevirtual java/io/PrintStream/println(I)V
+ return
+.end method
+
+
+.method public static main([Ljava/lang/String;)V
+ .limit locals 200
+ .limit stack 200
+
+"""
+
+val ending = """
+
+ return
+
+.end method
+"""
+
+// for generating new labels
+var counter = -1
+
+def Fresh(x: String) = {
+ counter += 1
+ x ++ "_" ++ counter.toString()
+}
+
+type Env = Map[String, String]
+type Instrs = List[String]
+
+def compile_aexp(a: AExp, env : Env) : Instrs = a match {
+ case Num(i) => List("ldc " + i.toString + "\n")
+ case Var(s) => List("iload " + env(s) + "\n")
+ case Aop("+", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("iadd\n")
+ case Aop("-", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("isub\n")
+ case Aop("*", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("imul\n")
+}
+
+def compile_bexp(b: BExp, env : Env, jmp: String) : Instrs = b match {
+ case True => Nil
+ case False => List("goto " + jmp + "\n")
+ case Relop("=", a1, a2) =>
+ compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpne " + jmp + "\n")
+ case Relop("!=", a1, a2) =>
+ compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpeq " + jmp + "\n")
+ case Relop("<", a1, a2) =>
+ compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpge " + jmp + "\n")
+}
+
+
+def compile_stmt(s: Stmt, env: Env) : (Instrs, Env) = s match {
+ case Skip => (Nil, env)
+ case Assign(x, a) => {
+ val index = if (env.isDefinedAt(x)) env(x) else env.keys.size.toString
+ (compile_aexp(a, env) ++
+ List("istore " + index + "\n"), env + (x -> index))
+ }
+ case If(b, bl1, bl2) => {
+ val if_else = Fresh("If_else")
+ val if_end = Fresh("If_end")
+ val (instrs1, env1) = compile_bl(bl1, env)
+ val (instrs2, env2) = compile_bl(bl2, env1)
+ (compile_bexp(b, env, if_else) ++
+ instrs1 ++
+ List("goto " + if_end + "\n") ++
+ List("\n" + if_else + ":\n\n") ++
+ instrs2 ++
+ List("\n" + if_end + ":\n\n"), env2)
+ }
+ case While(b, bl) => {
+ val loop_begin = Fresh("Loop_begin")
+ val loop_end = Fresh("Loop_end")
+ val (instrs1, env1) = compile_bl(bl, env)
+ (List("\n" + loop_begin + ":\n\n") ++
+ compile_bexp(b, env, loop_end) ++
+ instrs1 ++
+ List("goto " + loop_begin + "\n") ++
+ List("\n" + loop_end + ":\n\n"), env1)
+ }
+ case Write(x) =>
+ (List("iload " + env(x) + "\n" + "invokestatic XXX/XXX/write(I)V\n"), env)
+}
+
+def compile_bl(bl: Block, env: Env) : (Instrs, Env) = bl match {
+ case Nil => (Nil, env)
+ case s::bl => {
+ val (instrs1, env1) = compile_stmt(s, env)
+ val (instrs2, env2) = compile_bl(bl, env1)
+ (instrs1 ++ instrs2, env2)
+ }
+}
+
+def compile(input: String) : String = {
+ val class_name = input.split('.')(0)
+ val tks = Tok.fromFile(input)
+ val ast = Stmts.parse_single(tks)
+ val instructions = compile_bl(ast, Map.empty)._1
+ (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
+}
+
+
+def compile_to(input: String, output: String) = {
+ val fw = new java.io.FileWriter(output)
+ fw.write(compile(input))
+ fw.close()
+}
+
+//
+val tks = Tok.fromString("x := x + 1")
+val ast = Stmt.parse_single(tks)
+println(compile_stmt(ast, Map("x" -> "n"))._1.mkString)
+
+
+
+//examples
+
+compile_to("loops.while", "loops.j")
+//compile_to("fib.while", "fib.j")
+
+
+// testing cases for time measurements
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+// for testing
+import scala.sys.process._
+
+val test_prog = """
+start := XXX;
+x := start;
+y := start;
+z := start;
+while 0 < x do {
+ while 0 < y do {
+ while 0 < z do {
+ z := z - 1
+ };
+ z := start;
+ y := y - 1
+ };
+ y := start;
+ x := x - 1
+};
+write x;
+write y;
+write z
+"""
+
+
+def compile_test(n: Int) : Unit = {
+ val class_name = "LOOP"
+ val tks = Tok.fromString(test_prog.replaceAllLiterally("XXX", n.toString))
+ val ast = Stmts.parse_single(tks)
+ val instructions = compile_bl(ast, Map.empty)._1
+ val assembly = (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
+ val fw = new java.io.FileWriter(class_name + ".j")
+ fw.write(assembly)
+ fw.close()
+ val test = ("java -jar jvm/jasmin-2.4/jasmin.jar " + class_name + ".j").!!
+ println(n + " " + time_needed(2, ("java " + class_name + "/" + class_name).!!))
+}
+
+List(1, 5000, 10000, 50000, 100000, 250000, 500000, 750000, 1000000).map(compile_test(_))
+
+
+
+// Javabyte code assmbler
+//
+// java -jar jvm/jasmin-2.4/jasmin.jar loops.j
+
+
+
+
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/crawler.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,144 @@
+import io.Source
+import scala.util.matching.Regex
+
+// gets the first ~10K of a page
+def get_page(url: String) : String = {
+ try {
+ Source.fromURL(url).take(10000).mkString
+ }
+ catch {
+ case e => {
+ println(" Problem with: " + url)
+ ""
+ }
+ }
+}
+
+// non-existing page -> returns the empty string
+get_page("""http://www.foobar.com""")
+
+
+// staring URL for the crawler
+val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
+
+// starts with an "
+// then either http or https
+// then ://
+// then any character that is not "
+// finally "
+val http_pattern = """\"((?:http|https)://(?:[^\"])*)\"""".r
+val http_pattern = """\"(https?://[^\"]*)\"""".r
+
+def unquote(s: String) = s.drop(1).dropRight(1)
+
+def get_all_URLs(page: String) : Set[String] = {
+ (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+}
+
+// get all urls in startURL
+get_all_URLs(get_page(startURL))
+
+// number of all urls in startURL
+get_all_URLs(get_page(startURL)).toList.length
+
+
+// naive version - seraches until a given depth
+// visits pages potentially more than once
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ else {
+ println("Visiting: " + n + " " + url)
+ for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
+ }
+}
+
+crawl(startURL, 2)
+
+
+//breadth-first version without visiting
+//pages twice
+def bf_crawl(todo: Set[String], visited: Set[String], n: Int) : Unit = {
+ if (n == 0) ()
+ else {
+ val new_todo = todo.flatMap {
+ url => {
+ if (visited.contains(url)) Set[String]()
+ else {
+ println("Visiting: " + n + " " + url)
+ get_all_URLs(get_page(url))
+ }
+ }
+ }
+ bf_crawl(new_todo, visited union todo, n - 1)
+ }
+}
+
+bf_crawl(Set(startURL1), Set(), 2)
+
+
+//breadth-first version without visiting
+//pages twice and only in "my" domain
+val my_pattern = """urbanc""".r
+
+// breadth first search avoiding double searches
+def bf_crawl2(todo: Set[String], visited: Set[String], n: Int) : Unit = {
+ if (n == 0) ()
+ else {
+ val new_todo = todo.flatMap {
+ url => {
+ if (visited.contains(url)) Set[String]()
+ else if (my_pattern.findFirstIn(url) == None) Set[String]()
+ else {
+ println("Visiting: " + n + " " + url);
+ get_all_URLs(get_page(url))
+ }
+ }
+ }
+ bf_crawl2(new_todo, visited union todo, n - 1)
+ }
+}
+
+bf_crawl2(Set(startURL1), Set(), 5)
+
+// email harvester
+// from
+// http://net.tutsplus.com/tutorials/other/8-regular-expressions-you-should-know/
+
+val email_pattern = """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
+
+def bf_crawl3(todo: Set[String], visited: Set[String], n: Int) : Unit = {
+ if (n == 0) ()
+ else {
+ val new_todo = todo.flatMap {
+ url => {
+ if (visited.contains(url)) Set[String]()
+ else {
+ println("Visiting: " + n + " " + url);
+ val page = get_page(url)
+ println(email_pattern.findAllIn(page).mkString("\n"))
+ get_all_URLs(get_page(url))
+ }
+ }
+ }
+ bf_crawl3(new_todo, visited union todo, n - 1)
+ }
+}
+
+bf_crawl3(Set(startURL1), Set(), 3)
+
+
+// depth-first version does not work,
+// because it might visit pages at depth 1
+// while it still wants to visit them at
+// depth 2
+var visited = Set("")
+
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ else if (visited.contains(url)) () //println("Already visited: " + n + " " + url)
+ else {
+ println("Visiting: " + n + " " + url);
+ visited += url
+ for (u <- getAllURLs(getURLpage(url))) crawl(u, n - 1);
+ }
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/crawler1.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,45 @@
+import io.Source
+import scala.util.matching.Regex
+
+// gets the first ~10K of a page
+def get_page(url: String) : String = {
+ try {
+ Source.fromURL(url).take(10000).mkString
+ }
+ catch {
+ case e => {
+ println(" Problem with: " + url)
+ ""
+ }
+ }
+}
+
+
+// regex for URLs
+val http_pattern = """\"https?://[^\"]*\"""".r
+
+def unquote(s: String) = s.drop(1).dropRight(1)
+
+def get_all_URLs(page: String) : Set[String] = {
+ (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+}
+
+// naive version - seraches until a given depth
+// visits pages potentially more than once
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ else {
+ println("Visiting: " + n + " " + url)
+ for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
+ }
+}
+
+// staring URL for the crawler
+val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
+//val startURL = """http://www.inf.kcl.ac.uk/staff/mml/"""
+
+
+// call on the command line
+crawl(startURL, 2)
+
+crawl("""http://www.dcs.kcl.ac.uk/staff/urbanc/msc-projects-12.html""", 2)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/crawler2.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,44 @@
+import io.Source
+import scala.util.matching.Regex
+
+// gets the first ~10K of a page
+def get_page(url: String) : String = {
+ try {
+ Source.fromURL(url).take(10000).mkString
+ }
+ catch {
+ case e => {
+ println(" Problem with: " + url)
+ ""
+ }
+ }
+}
+
+// staring URL for the crawler
+val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
+
+// regex for URLs
+val http_pattern = """\"https?://[^\"]*\"""".r
+val my_urls = """urbanc""".r
+
+def unquote(s: String) = s.drop(1).dropRight(1)
+
+def get_all_URLs(page: String) : Set[String] = {
+ (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+}
+
+// naive version - seraches until a given depth
+// visits pages potentially more than once
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ else if (my_urls.findFirstIn(url) == None) ()
+ else {
+ println("Visiting: " + n + " " + url)
+ for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
+ }
+}
+
+// can now deal with depth 3
+// start on command line
+crawl(startURL, 4)
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/crawler3.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,49 @@
+import io.Source
+import scala.util.matching.Regex
+
+// gets the first ~10K of a page
+def get_page(url: String) : String = {
+ try {
+ Source.fromURL(url).take(10000).mkString
+ }
+ catch {
+ case e => {
+ println(" Problem with: " + url)
+ ""
+ }
+ }
+}
+
+// staring URL for the crawler
+val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
+
+// regex for URLs
+val http_pattern = """\"https?://[^\"]*\"""".r
+val my_urls = """urbanc""".r
+val email_pattern = """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
+
+// http://net.tutsplus.com/tutorials/other/8-regular-expressions-you-should-know/
+
+def unquote(s: String) = s.drop(1).dropRight(1)
+
+def get_all_URLs(page: String) : Set[String] = {
+ (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+}
+
+// naive version - seraches until a given depth
+// visits pages potentially more than once
+def crawl(url: String, n: Int) : Unit = {
+ if (n == 0) ()
+ //else if (my_urls.findFirstIn(url) == None) ()
+ else {
+ println("Visiting: " + n + " " + url)
+ val page = get_page(url)
+ println(email_pattern.findAllIn(page).mkString("\n"))
+ for (u <- get_all_URLs(page)) crawl(u, n - 1)
+ }
+}
+
+// can now deal with depth 3
+// start on command line
+crawl(startURL, 3)
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/fib.j Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,60 @@
+
+.class public fib.fib
+.super java/lang/Object
+
+.method public <init>()V
+ aload_0
+ invokenonvirtual java/lang/Object/<init>()V
+ return
+.end method
+
+.method public static write(I)V
+ .limit locals 5
+ .limit stack 5
+ iload 0
+ getstatic java/lang/System/out Ljava/io/PrintStream;
+ swap
+ invokevirtual java/io/PrintStream/println(I)V
+ return
+.end method
+
+
+.method public static main([Ljava/lang/String;)V
+ .limit locals 200
+ .limit stack 200
+
+ldc 19
+istore 0
+ldc 0
+istore 1
+ldc 1
+istore 2
+
+Loop_begin_0:
+
+ldc 0
+iload 0
+if_icmpge Loop_end_1
+iload 2
+istore 3
+iload 1
+iload 2
+iadd
+istore 2
+iload 3
+istore 1
+iload 0
+ldc 1
+isub
+istore 0
+goto Loop_begin_0
+
+Loop_end_1:
+
+iload 2
+invokestatic fib/fib/write(I)V
+
+
+ return
+
+.end method
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/fib.while Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,15 @@
+/* Fibonacci Program
+ input: n
+*/
+
+n := 19;
+minus1 := 0;
+minus2 := 1;
+while n > 0 do {
+ temp := minus2;
+ minus2 := minus1 + minus2;
+ minus1 := temp;
+ n := n - 1
+};
+write minus2
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/html.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,99 @@
+
+//:load matcher.scala
+
+// some regular expressions
+val SYM = RANGE("""ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz.,!?-{[()]}':;%0123456789""")
+val WORD = PLUS(SYM)
+
+val BTAG = SEQS("<", WORD, ">")
+val ETAG = SEQS("</", WORD, ">")
+
+val WHITESPACE = PLUS(RANGE(" \n"))
+
+// for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case class T_WORD(s: String) extends Token
+case class T_ETAG(s: String) extends Token
+case class T_BTAG(s: String) extends Token
+case class T_NT(s: String, rhs: List[Token]) extends Token
+
+val lexing_rules: List[Rule[Token]] =
+ List((BTAG, (s) => T_BTAG(s.mkString)),
+ (ETAG, (s) => T_ETAG(s.mkString)),
+ (WORD, (s) => T_WORD(s.mkString)),
+ (WHITESPACE, (s) => T_WHITESPACE))
+
+// the tokenizer
+val T = Tokenizer(lexing_rules)
+
+// width for printing
+val WIDTH = 60
+
+
+def interpret(ts: List[Token], c: Int, ctr: List[String]) : Unit= ts match {
+ case Nil => println(Console.RESET)
+ case T_WHITESPACE::rest => print(Console.RESET + " "); interpret(rest, c + 1, ctr)
+ case T_WORD(s)::rest => {
+ val newstr = Console.RESET + ctr.reverse.mkString + s
+ if (c + s.length < WIDTH) {
+ print(newstr);
+ interpret(rest, c + s.length, ctr)
+ }
+ else {
+ print("\n" + newstr)
+ interpret(rest, s.length, ctr)
+ }
+ }
+ case T_BTAG("<p>")::rest => print("\n"); interpret(rest, 0, ctr)
+ case T_ETAG("</p>")::rest => print("\n"); interpret(rest, 0, ctr)
+ case T_BTAG("<b>")::rest => interpret(rest, c, Console.BOLD :: ctr)
+ case T_BTAG("<a>")::rest => interpret(rest, c, Console.UNDERLINED :: ctr)
+ case T_BTAG("<cyan>")::rest => interpret(rest, c, Console.CYAN :: ctr)
+ case T_BTAG("<red>")::rest => interpret(rest, c, Console.RED :: ctr)
+ case T_BTAG("<blink>")::rest => interpret(rest, c, Console.BLINK :: ctr)
+ case T_ETAG(_)::rest => interpret(rest, c, ctr.tail)
+ case _::rest => interpret(rest, c, ctr)
+}
+
+val test_string = """
+<b>MSc Projects</b>
+
+<p>
+start of paragraph. <cyan> a <red>cyan</red> word</cyan> normal again something longer.
+</p>
+
+
+ <p><b>Description:</b>
+ <a>Regular expressions</a> are extremely useful for many text-processing tasks such as finding patterns in texts,
+ lexing programs, syntax highlighting and so on. Given that regular expressions were
+ introduced in 1950 by <a>Stephen Kleene</a>, you might think
+ regular expressions have since been studied and implemented to death. But you would definitely be mistaken: in fact they are still
+ an active research area. For example
+ <a>this paper</a>
+ about regular expression matching and partial derivatives was presented this summer at the international
+ PPDP'12 conference. The task in this project is to implement the results from this paper.</p>
+
+ <p>The background for this project is that some regular expressions are
+ <a>evil</a>
+ and can stab you in the back; according to
+ this <a>blog post</a>.
+ For example, if you use in <a>Python</a> or
+ in <a>Ruby</a> (probably also in other mainstream programming languages) the
+ innocently looking regular expression a?{28}a{28} and match it, say, against the string
+ <red>aaaaaaaaaa<cyan>aaaaaaa</cyan>aaaaaaaaaaa</red> (that is 28 as), you will soon notice that your CPU usage goes to 100%. In fact,
+ Python and Ruby need approximately 30 seconds of hard work for matching this string. You can try it for yourself:
+ <a>re.py</a> (Python version) and
+ <a>re.rb</a>
+ (Ruby version). You can imagine an attacker
+ mounting a nice <a>DoS attack</a> against
+ your program if it contains such an evil regular expression. Actually
+ <a>Scala</a> (and also Java) are almost immune from such
+ attacks as they can deal with strings of up to 4,300 as in less than a second. But if you scale
+ the regular expression and string further to, say, 4,600 as, then you get a
+ StackOverflowError
+ potentially crashing your program.
+ </p>
+"""
+
+interpret(T.fromString(test_string), 0, Nil)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/html1.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,75 @@
+
+
+//:load matcher.scala
+
+
+// some regular expressions
+val LETTER = RANGE("""ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz.,!?-{[()]}':;%""")
+val DIGIT = RANGE("0123456789")
+val NONZERODIGIT = RANGE("123456789")
+
+val NAME = ALT(PLUS(LETTER), SEQS(PLUS(LETTER),"=", PLUS(LETTER)))
+val BTAG = SEQS("<", NAME, ">")
+val ETAG = SEQS("</", PLUS(LETTER), ">")
+
+val WORD = PLUS(ALT(LETTER, DIGIT))
+val WHITESPACE = PLUS(RANGE(" \n"))
+
+// for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case class T_WORD(s: String) extends Token
+case class T_ETAG(s: String) extends Token
+case class T_BTAG(s: String) extends Token
+case class T_NT(s: String, rhs: List[Token]) extends Token
+
+def tokenizer(rs: List[Rule[Token]], s: String) : List[Token] =
+ tokenize(rs, s.toList)
+
+
+
+// lexing rules for arithmetic expressions
+val lexing_rules: List[Rule[Token]]=
+ List((BTAG, (s) => T_BTAG(s.mkString)),
+ (ETAG, (s) => T_ETAG(s.mkString)),
+ (WORD, (s) => T_WORD(s.mkString)),
+ (WHITESPACE, (s) => T_WHITESPACE))
+
+val ts = tokenize_file(lexing_rules, "test.html")
+
+
+val WIDTH = 60
+
+def is_tag(t: Token) = t match {
+ case T_BTAG(_) => true
+ case T_ETAG(_) => true
+ case _ => false
+}
+
+def interpret(ts: List[Token], c: Int, ctr: List[String]) : Unit= ts match {
+ case Nil => println(Console.RESET)
+ case T_WHITESPACE::rest => print(" "); interpret(rest, c + 1, ctr)
+ case T_WORD(s)::rest => {
+ val newc = c + s.length
+ val newstr = Console.RESET + ctr.reverse.mkString + s
+ if (newc < WIDTH) {
+ print(newstr);
+ interpret(rest, newc, ctr)
+ }
+ else {
+ print("\n" + newstr)
+ interpret(rest, s.length, ctr)
+ }
+ }
+ case T_BTAG("<p>")::rest => print("\n"); interpret(rest, 0, ctr)
+ case T_ETAG("</p>")::rest => print("\n"); interpret(rest, 0, ctr)
+ case T_BTAG("<b>")::rest => interpret(rest, c, Console.BOLD :: ctr)
+ case T_BTAG("<A>")::rest => interpret(rest, c, Console.UNDERLINED :: ctr)
+ case T_BTAG("<cyan>")::rest => interpret(rest, c, Console.CYAN :: ctr)
+ case T_BTAG("<red>")::rest => interpret(rest, c, Console.RED :: ctr)
+ case T_BTAG("<blink>")::rest => interpret(rest, c, Console.BLINK :: ctr)
+ case T_ETAG(_)::rest => interpret(rest, c, ctr.tail)
+ case _::rest => interpret(rest, c, ctr)
+}
+
+interpret(ts, 0, Nil)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/i.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,492 @@
+
+// regular expressions including NOT
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case object ALLC extends Rexp // recognises any character
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp // negation of a regular expression
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case ALLC => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression
+// cannot recognise more
+def no_more (r: Rexp) : Boolean = r match {
+ case NULL => true
+ case EMPTY => false
+ case ALLC => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => no_more(r1) && no_more(r2)
+ case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
+ case STAR(_) => false
+ case NOT(r) => !(no_more(r))
+}
+
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case ALLC => EMPTY
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+}
+
+// regular expression for specifying
+// ranges of characters
+def Range(s : List[Char]) : Rexp = s match {
+ case Nil => NULL
+ case c::Nil => CHAR(c)
+ case c::s => ALT(CHAR(c), Range(s))
+}
+def RANGE(s: String) = Range(s.toList)
+
+
+// one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+// many alternatives
+def Alts(rs: List[Rexp]) : Rexp = rs match {
+ case Nil => NULL
+ case r::Nil => r
+ case r::rs => ALT(r, Alts(rs))
+}
+def ALTS(rs: Rexp*) = Alts(rs.toList)
+
+// repetitions
+def Seqs(rs: List[Rexp]) : Rexp = rs match {
+ case Nil => NULL
+ case r::Nil => r
+ case r::rs => SEQ(r, Seqs(rs))
+}
+def SEQS(rs: Rexp*) = Seqs(rs.toList)
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+type Rule[T] = (Rexp, List[Char] => T)
+
+case class Tokenizer[T](rules: List[Rule[T]], excl: List[T] = Nil) {
+
+ def munch(r: Rexp, action: List[Char] => T, s: List[Char], t: List[Char]) : Option[(List[Char], T)] =
+ s match {
+ case Nil if (nullable(r)) => Some(Nil, action(t))
+ case Nil => None
+ case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, action(t))
+ case c::s if (no_more(der (c, r))) => None
+ case c::s => munch(der (c, r), action, s, t ::: List(c))
+ }
+
+ def one_token(s: List[Char]) : Either[(List[Char], T), String] = {
+ val somes = rules.map { (r) => munch(r._1, r._2, s, Nil) }.flatten
+ if (somes == Nil) Right(s.mkString)
+ else Left(somes sortBy (_._1.length) head)
+ }
+
+ def tokenize(cs: List[Char]) : List[T] = cs match {
+ case Nil => Nil
+ case _ => one_token(cs) match {
+ case Left((rest, token)) => token :: tokenize(rest)
+ case Right(s) => { println("Cannot tokenize: \"" + s + "\""); Nil }
+ }
+ }
+
+ def fromString(s: String) : List[T] =
+ tokenize(s.toList).filterNot(excl.contains(_))
+
+ def fromFile(name: String) : List[T] =
+ fromString(io.Source.fromFile(name).mkString)
+
+}
+
+
+// parser combinators with input type I and return type T
+
+abstract class Parser[I <% Seq[_], T] {
+ def parse(ts: I): Set[(T, I)]
+
+ def parse_all(ts: I) : Set[T] =
+ for ((head, tail) <- parse(ts); if (tail.isEmpty)) yield head
+
+ def parse_single(ts: I) : T = parse_all(ts).toList match {
+ case t::Nil => t
+ case _ => { println ("Parse Error") ; sys.exit(-1) }
+ }
+
+ def || (right : => Parser[I, T]) : Parser[I, T] = new AltParser(this, right)
+ def ==>[S] (f: => T => S) : Parser [I, S] = new FunParser(this, f)
+ def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] = new SeqParser(this, right)
+ def ~>[S] (right : => Parser[I, S]) : Parser[I, S] = this ~ right ==> (_._2)
+ def <~[S] (right : => Parser[I, S]) : Parser[I, T] = this ~ right ==> (_._1)
+}
+
+class SeqParser[I <% Seq[_], T, S](p: => Parser[I, T], q: => Parser[I, S]) extends Parser[I, (T, S)] {
+ def parse(sb: I) =
+ for ((head1, tail1) <- p.parse(sb);
+ (head2, tail2) <- q.parse(tail1)) yield ((head1, head2), tail2)
+}
+
+class AltParser[I <% Seq[_], T](p: => Parser[I, T], q: => Parser[I, T]) extends Parser[I, T] {
+ def parse(sb: I) = p.parse(sb) ++ q.parse(sb)
+}
+
+class FunParser[I <% Seq[_], T, S](p: => Parser[I, T], f: T => S) extends Parser[I, S] {
+ def parse(sb: I) =
+ for ((head, tail) <- p.parse(sb)) yield (f(head), tail)
+}
+
+
+// A parser and evaluator for teh while language
+//
+//:load matcher.scala
+//:load parser3.scala
+
+// some regular expressions
+val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
+val DIGIT = RANGE("0123456789")
+val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
+val NUM = PLUS(DIGIT)
+val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false", "write")
+val SEMI: Rexp = ";"
+val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
+val WHITESPACE = PLUS(RANGE(" \n"))
+val RPAREN: Rexp = ")"
+val LPAREN: Rexp = "("
+val BEGIN: Rexp = "{"
+val END: Rexp = "}"
+val COMMENT = SEQS("/*", NOT(SEQS(STAR(ALLC), "*/", STAR(ALLC))), "*/")
+
+// tokens for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case object T_COMMENT extends Token
+case object T_SEMI extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case object T_BEGIN extends Token
+case object T_END extends Token
+case class T_ID(s: String) extends Token
+case class T_OP(s: String) extends Token
+case class T_NUM(s: String) extends Token
+case class T_KWD(s: String) extends Token
+
+val lexing_rules: List[Rule[Token]] =
+ List((KEYWORD, (s) => T_KWD(s.mkString)),
+ (ID, (s) => T_ID(s.mkString)),
+ (OP, (s) => T_OP(s.mkString)),
+ (NUM, (s) => T_NUM(s.mkString)),
+ (SEMI, (s) => T_SEMI),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (BEGIN, (s) => T_BEGIN),
+ (END, (s) => T_END),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (COMMENT, (s) => T_COMMENT))
+
+// the tokenizer
+val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE, T_COMMENT))
+
+// the abstract syntax trees
+abstract class Stmt
+abstract class AExp
+abstract class BExp
+type Block = List[Stmt]
+case object Skip extends Stmt
+case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
+case class While(b: BExp, bl: Block) extends Stmt
+case class Assign(s: String, a: AExp) extends Stmt
+case class Write(s: String) extends Stmt
+
+case class Var(s: String) extends AExp
+case class Num(i: Int) extends AExp
+case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
+
+case object True extends BExp
+case object False extends BExp
+case class Relop(o: String, a1: AExp, a2: AExp) extends BExp
+
+// atomic parsers
+case class TokParser(tok: Token) extends Parser[List[Token], Token] {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((t, ts))
+ case _ => Set ()
+ }
+}
+implicit def token2tparser(t: Token) = TokParser(t)
+
+case object NumParser extends Parser[List[Token], Int] {
+ def parse(ts: List[Token]) = ts match {
+ case T_NUM(s)::ts => Set((s.toInt, ts))
+ case _ => Set ()
+ }
+}
+
+case object IdParser extends Parser[List[Token], String] {
+ def parse(ts: List[Token]) = ts match {
+ case T_ID(s)::ts => Set((s, ts))
+ case _ => Set ()
+ }
+}
+
+
+// arithmetic expressions
+lazy val AExp: Parser[List[Token], AExp] =
+ (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
+ (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
+lazy val T: Parser[List[Token], AExp] =
+ (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
+lazy val F: Parser[List[Token], AExp] =
+ (T_LPAREN ~> AExp <~ T_RPAREN) ||
+ IdParser ==> Var ||
+ NumParser ==> Num
+
+// boolean expressions
+lazy val BExp: Parser[List[Token], BExp] =
+ (T_KWD("true") ==> ((_) => True: BExp)) ||
+ (T_KWD("false") ==> ((_) => False: BExp)) ||
+ (T_LPAREN ~> BExp <~ T_RPAREN) ||
+ (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Relop("=", x, z): BExp } ||
+ (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Relop("!=", x, z): BExp } ||
+ (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Relop("<", x, z): BExp } ||
+ (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Relop("<", z, x): BExp }
+
+lazy val Stmt: Parser[List[Token], Stmt] =
+ (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
+ (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
+ (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
+ { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
+ (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) } ||
+ (T_KWD("write") ~ IdParser) ==> { case (x, y) => Write(y) }
+
+lazy val Stmts: Parser[List[Token], Block] =
+ (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
+ (Stmt ==> ((s) => List(s) : Block))
+
+lazy val Block: Parser[List[Token], Block] =
+ (T_BEGIN ~> Stmts <~ T_END) ||
+ (Stmt ==> ((s) => List(s)))
+
+// compiler
+val beginning = """
+.class public XXX.XXX
+.super java/lang/Object
+
+.method public <init>()V
+ aload_0
+ invokenonvirtual java/lang/Object/<init>()V
+ return
+.end method
+
+.method public static write(I)V
+ .limit locals 5
+ .limit stack 5
+ iload 0
+ getstatic java/lang/System/out Ljava/io/PrintStream;
+ swap
+ invokevirtual java/io/PrintStream/println(I)V
+ return
+.end method
+
+
+.method public static main([Ljava/lang/String;)V
+ .limit locals 200
+ .limit stack 200
+
+"""
+
+val ending = """
+
+ return
+
+.end method
+"""
+
+// for generating new labels
+var counter = -1
+
+def Fresh(x: String) = {
+ counter += 1
+ x ++ "_" ++ counter.toString()
+}
+
+type Env = Map[String, String]
+type Instrs = List[String]
+
+def compile_aexp(a: AExp, env : Env) : Instrs = a match {
+ case Num(i) => List("ldc " + i.toString + "\n")
+ case Var(s) => List("iload " + env(s) + "\n")
+ case Aop("+", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("iadd\n")
+ case Aop("-", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("isub\n")
+ case Aop("*", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("imul\n")
+}
+
+def compile_bexp(b: BExp, env : Env, jmp: String) : Instrs = b match {
+ case True => Nil
+ case False => List("goto " + jmp + "\n")
+ case Relop("=", a1, a2) =>
+ compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpne " + jmp + "\n")
+ case Relop("!=", a1, a2) =>
+ compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpeq " + jmp + "\n")
+ case Relop("<", a1, a2) =>
+ compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpge " + jmp + "\n")
+}
+
+
+def compile_stmt(s: Stmt, env: Env) : (Instrs, Env) = s match {
+ case Skip => (Nil, env)
+ case Assign(x, a) => {
+ val index = if (env.isDefinedAt(x)) env(x) else env.keys.size.toString
+ (compile_aexp(a, env) ++
+ List("istore " + index + "\n"), env + (x -> index))
+ }
+ case If(b, bl1, bl2) => {
+ val if_else = Fresh("If_else")
+ val if_end = Fresh("If_end")
+ val (instrs1, env1) = compile_bl(bl1, env)
+ val (instrs2, env2) = compile_bl(bl2, env1)
+ (compile_bexp(b, env, if_else) ++
+ instrs1 ++
+ List("goto " + if_end + "\n") ++
+ List("\n" + if_else + ":\n\n") ++
+ instrs2 ++
+ List("\n" + if_end + ":\n\n"), env2)
+ }
+ case While(b, bl) => {
+ val loop_begin = Fresh("Loop_begin")
+ val loop_end = Fresh("Loop_end")
+ val (instrs1, env1) = compile_bl(bl, env)
+ (List("\n" + loop_begin + ":\n\n") ++
+ compile_bexp(b, env, loop_end) ++
+ instrs1 ++
+ List("goto " + loop_begin + "\n") ++
+ List("\n" + loop_end + ":\n\n"), env1)
+ }
+ case Write(x) =>
+ (List("iload " + env(x) + "\n" + "invokestatic XXX/XXX/write(I)V\n"), env)
+}
+
+def compile_bl(bl: Block, env: Env) : (Instrs, Env) = bl match {
+ case Nil => (Nil, env)
+ case s::bl => {
+ val (instrs1, env1) = compile_stmt(s, env)
+ val (instrs2, env2) = compile_bl(bl, env1)
+ (instrs1 ++ instrs2, env2)
+ }
+}
+
+def compile(input: String) : String = {
+ val class_name = input.split('.')(0)
+ val tks = Tok.fromFile(input)
+ val ast = Stmts.parse_single(tks)
+ val instructions = compile_bl(ast, Map.empty)._1
+ (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
+}
+
+
+def compile_to(input: String, output: String) = {
+ val fw = new java.io.FileWriter(output)
+ fw.write(compile(input))
+ fw.close()
+}
+
+//
+val tks = Tok.fromString("x := x + 1")
+val ast = Stmt.parse_single(tks)
+println(compile_stmt(ast, Map("x" -> "n"))._1.mkString)
+
+
+
+//examples
+
+compile_to("loops.while", "loops.j")
+//compile_to("fib.while", "fib.j")
+
+
+// testing cases for time measurements
+/*
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+// for testing
+import scala.sys.process._
+
+val test_prog = """
+start := XXX;
+x := start;
+y := start;
+z := start;
+while 0 < x do {
+ while 0 < y do {
+ while 0 < z do {
+ z := z - 1
+ };
+ z := start;
+ y := y - 1
+ };
+ y := start;
+ x := x - 1
+};
+write x;
+write y;
+write z
+"""
+
+
+def compile_test(n: Int) : Unit = {
+ val class_name = "LOOP"
+ val tks = Tok.fromString(test_prog.replaceAllLiterally("XXX", n.toString))
+ val ast = Stmts.parse_single(tks)
+ val instructions = compile_bl(ast, Map.empty)._1
+ val assembly = (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
+ val fw = new java.io.FileWriter(class_name + ".j")
+ fw.write(assembly)
+ fw.close()
+ val test = ("java -jar jvm/jasmin-2.4/jasmin.jar " + class_name + ".j").!!
+ println(n + " " + time_needed(2, ("java " + class_name + "/" + class_name).!!))
+}
+
+List(1, 5000, 10000, 50000, 100000, 250000, 500000, 750000, 1000000).map(compile_test(_))
+
+
+
+// javabyte code assmbler
+//
+// java -jar jvm/jasmin-2.4/jasmin.jar loops.j
+
+*/
+
+
+
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/loops.j Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,90 @@
+
+.class public loops.loops
+.super java/lang/Object
+
+.method public <init>()V
+ aload_0
+ invokenonvirtual java/lang/Object/<init>()V
+ return
+.end method
+
+.method public static write(I)V
+ .limit locals 5
+ .limit stack 5
+ iload 0
+ getstatic java/lang/System/out Ljava/io/PrintStream;
+ swap
+ invokevirtual java/io/PrintStream/println(I)V
+ return
+.end method
+
+
+.method public static main([Ljava/lang/String;)V
+ .limit locals 200
+ .limit stack 200
+
+ldc 1000
+istore 0
+iload 0
+istore 1
+iload 0
+istore 2
+iload 0
+istore 3
+
+Loop_begin_0:
+
+ldc 0
+iload 1
+if_icmpge Loop_end_1
+
+Loop_begin_2:
+
+ldc 0
+iload 2
+if_icmpge Loop_end_3
+
+Loop_begin_4:
+
+ldc 0
+iload 3
+if_icmpge Loop_end_5
+iload 3
+ldc 1
+isub
+istore 3
+goto Loop_begin_4
+
+Loop_end_5:
+
+iload 0
+istore 3
+iload 2
+ldc 1
+isub
+istore 2
+goto Loop_begin_2
+
+Loop_end_3:
+
+iload 0
+istore 2
+iload 1
+ldc 1
+isub
+istore 1
+goto Loop_begin_0
+
+Loop_end_1:
+
+iload 1
+invokestatic loops/loops/write(I)V
+iload 2
+invokestatic loops/loops/write(I)V
+iload 3
+invokestatic loops/loops/write(I)V
+
+
+ return
+
+.end method
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/loops.while Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,18 @@
+start := 1000;
+x := start;
+y := start;
+z := start;
+while 0 < x do {
+ while 0 < y do {
+ while 0 < z do {
+ z := z - 1
+ };
+ z := start;
+ y := y - 1
+ };
+ y := start;
+ x := x - 1
+};
+write x;
+write y;
+write z
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/matcher.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,130 @@
+package object matcher {
+
+// regular expressions
+// including constructors for NOT and ALLC
+sealed abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case object ALLC extends Rexp // recognises any character
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp // negation of a regular expression
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case ALLC => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression
+// cannot recognise more
+def no_more (r: Rexp) : Boolean = r match {
+ case NULL => true
+ case EMPTY => false
+ case ALLC => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => no_more(r1) && no_more(r2)
+ case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
+ case STAR(_) => false
+ case NOT(r) => !(no_more(r))
+}
+
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case ALLC => EMPTY
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+}
+
+// main class for the tokenizer
+case class Tokenizer[T](rules: List[(Rexp, List[Char] => T)], excl: List[T] = Nil) {
+
+def munch(r: Rexp, action: List[Char] => T, s: List[Char], t: List[Char]) : Option[(List[Char], T)] =
+ s match {
+ case Nil if (nullable(r)) => Some(Nil, action(t))
+ case Nil => None
+ case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, action(t))
+ case c::s if (no_more(der (c, r))) => None
+ case c::s => munch(der (c, r), action, s, t ::: List(c))
+ }
+
+def one_token(s: List[Char]) : Either[(List[Char], T), String] = {
+ val somes = rules.map { (r) => munch(r._1, r._2, s, Nil) }.flatten
+ if (somes == Nil) Right(s.mkString)
+ else Left(somes sortBy (_._1.length) head)
+}
+
+def tokenize(cs: List[Char]) : List[T] = cs match {
+ case Nil => Nil
+ case _ => one_token(cs) match {
+ case Left((rest, token)) => token :: tokenize(rest)
+ case Right(s) => { println("Cannot tokenize: \"" + s + "\""); Nil }
+ }
+}
+
+def fromString(s: String) : List[T] =
+ tokenize(s.toList).filterNot(excl.contains(_))
+
+def fromFile(name: String) : List[T] =
+ fromString(io.Source.fromFile(name).mkString)
+
+}
+
+
+// regular expression for specifying
+// ranges of characters
+def Range(s : List[Char]) : Rexp = s match {
+ case Nil => NULL
+ case c::Nil => CHAR(c)
+ case c::s => ALT(CHAR(c), Range(s))
+}
+def RANGE(s: String) = Range(s.toList)
+
+
+// one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+// many alternatives
+def Alts(rs: List[Rexp]) : Rexp = rs match {
+ case Nil => NULL
+ case r::Nil => r
+ case r::rs => ALT(r, Alts(rs))
+}
+def ALTS(rs: Rexp*) = Alts(rs.toList)
+
+// repetitions
+def Seqs(rs: List[Rexp]) : Rexp = rs match {
+ case Nil => NULL
+ case r::Nil => r
+ case r::rs => SEQ(r, Seqs(rs))
+}
+def SEQS(rs: Rexp*) = Seqs(rs.toList)
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/mllex.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,109 @@
+:load matcher.scala
+
+
+// some regular expressions
+val KEYWORDS = ALTS(List("#", "(", ")", ",", "->", "...", ":", ":>", ";", "=",
+ "=>", "[", "]", "_", "{", "|", "}", "abstype", "and", "andalso", "as",
+ "case", "datatype", "do", "else", "end", "eqtype", "exception", "fn",
+ "fun", "functor", "handle", "if", "in", "include", "infix", "infixr",
+ "let", "local", "nonfix", "of", "op", "open", "orelse", "raise", "rec",
+ "sharing", "sig", "signature", "struct", "structure", "then", "type",
+ "val", "where", "while", "with", "withtype"))
+
+val DIGITS = RANGE("0123456789")
+val NONZERODIGITS = RANGE("123456789")
+
+val POSITIVES = ALT(SEQ(NONZERODIGITS, STAR(DIGITS)), "0")
+val INTEGERS = ALT(SEQ("~", POSITIVES), POSITIVES)
+
+val ALL = ALTS(KEYWORDS, INTEGERS)
+
+val COMMENT = SEQS("/*", NOT(SEGS(STAR(ALL), "*/", STAR(ALL))), "*/")
+
+
+
+val LPAREN = CHAR('(')
+val RPAREN = CHAR(')')
+val WHITESPACE = PLUS(RANGE(" \n".toList))
+val OPS = RANGE("+-*".toList)
+
+// for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case object T_NUM extends Token
+case class T_OP(s: String) extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case class T_NT(s: String, rhs: List[Token]) extends Token
+
+def tokenizer(rs: List[Rule[Token]], s: String) : List[Token] =
+ tokenize(rs, s.toList).filterNot(_ match {
+ case T_WHITESPACE => true
+ case _ => false
+ })
+
+
+
+// lexing rules for arithmetic expressions
+val lexing_rules: List[Rule[Token]]=
+ List((NUMBER, (s) => T_NUM),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (OPS, (s) => T_OP(s.mkString)))
+
+tokenize_file(Nil, "nominal_library.ML")
+
+
+
+
+type Grammar = List[(String, List[Token])]
+
+// grammar for arithmetic expressions
+val grammar =
+ List ("E" -> List(T_NUM),
+ "E" -> List(T_NT("E", Nil), T_OP("+"), T_NT("E", Nil)),
+ "E" -> List(T_NT("E", Nil), T_OP("-"), T_NT("E", Nil)),
+ "E" -> List(T_NT("E", Nil), T_OP("*"), T_NT("E", Nil)),
+ "E" -> List(T_LPAREN, T_NT("E", Nil), T_RPAREN))
+
+def startsWith[A](ts1: List[A], ts2: List[A]) : Boolean = (ts1, ts2) match {
+ case (_, Nil) => true
+ case (T_NT(e, _)::ts1,T_NT(f, _)::ts2) => (e == f) && startsWith(ts1, ts2)
+ case (t1::ts1, t2::ts2) => (t1 == t2) && startsWith(ts1, ts2)
+ case _ => false
+}
+
+def chop[A](ts1: List[A], prefix: List[A], ts2: List[A]) : Option[(List[A], List[A])] =
+ ts1 match {
+ case Nil => None
+ case t::ts =>
+ if (startsWith(ts1, prefix)) Some(ts2.reverse, ts1.drop(prefix.length))
+ else chop(ts, prefix, t::ts2)
+ }
+
+// examples
+chop(List(1,2,3,4,5,6,7,8,9), List(4,5), Nil)
+chop(List(1,2,3,4,5,6,7,8,9), List(3,5), Nil)
+
+def replace[A](ts: List[A], out: List[A], in: List [A]) =
+ chop(ts, out, Nil) match {
+ case None => None
+ case Some((before, after)) => Some(before ::: in ::: after)
+ }
+
+def parse1(g: Grammar, ts: List[Token]) : Boolean = ts match {
+ case List(T_NT("E", tree)) => { println(tree); true }
+ case _ => {
+ val tss = for ((lhs, rhs) <- g) yield replace(ts, rhs, List(T_NT(lhs, rhs)))
+ tss.flatten.exists(parse1(g, _))
+ }
+}
+
+
+println() ; parse1(grammar, tokenizer(lexing_rules, "2 + 3 * 4 + 1"))
+println() ; parse1(grammar, tokenizer(lexing_rules, "(2 + 3) * (4 + 1)"))
+println() ; parse1(grammar, tokenizer(lexing_rules, "(2 + 3) * 4 (4 + 1)"))
+
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/parser1.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,88 @@
+// A naive bottom-up parser with backtracking
+//
+// Needs:
+// :load matcher.scala
+
+// some regular expressions
+val DIGIT = RANGE("0123456789")
+val NONZERODIGIT = RANGE("123456789")
+
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+val LPAREN = CHAR('(')
+val RPAREN = CHAR(')')
+val WHITESPACE = PLUS(RANGE(" \n"))
+val OPS = RANGE("+-*")
+
+// for classifying the strings that have been recognised
+
+abstract class Token
+case object T_WHITESPACE extends Token
+case object T_NUM extends Token
+case class T_OP(s: String) extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case class NT(s: String) extends Token
+
+// lexing rules for arithmetic expressions
+val lexing_rules: List[Rule[Token]]=
+ List((NUMBER, (s) => T_NUM),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (OPS, (s) => T_OP(s.mkString)))
+
+// the tokenizer
+val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
+
+type Grammar = List[(String, List[Token])]
+
+// grammar for arithmetic expressions
+val grammar =
+ List ("F" -> List(T_NUM),
+ "E" -> List(T_NUM),
+ "E" -> List(NT("E"), T_OP("+"), NT("E")),
+ "E" -> List(NT("E"), T_OP("-"), NT("E")),
+ "E" -> List(NT("E"), T_OP("*"), NT("E")),
+ "E" -> List(T_LPAREN, NT("E"), T_RPAREN))
+
+
+def chop[A](ts1: List[A], prefix: List[A], ts2: List[A]) : Option[(List[A], List[A])] =
+ ts1 match {
+ case Nil => None
+ case t::ts =>
+ if (ts1.startsWith(prefix)) Some(ts2.reverse, ts1.drop(prefix.length))
+ else chop(ts, prefix, t::ts2)
+ }
+
+// examples for chop
+chop(List(1,2,3,4,5,6,7,8,9), List(4,5), Nil)
+chop(List(1,2,3,4,5,6,7,8,9), List(3,5), Nil)
+
+def replace[A](ts: List[A], out: List[A], in: List [A]) =
+ chop(ts, out, Nil) match {
+ case None => None
+ case Some((before, after)) => Some(before ::: in ::: after)
+ }
+
+def parse(g: Grammar, ts: List[Token]) : Boolean = {
+ println(ts)
+ if (ts == List(NT("E"))) true
+ else {
+ val tss = for ((lhs, rhs) <- g) yield replace(ts, rhs, List(NT(lhs)))
+ tss.flatten.exists(parse(g, _))
+ }
+}
+
+def parser(g: Grammar, s: String) = {
+ println("\n")
+ parse(g, Tok.fromString(s))
+}
+
+
+
+parser(grammar, "2 + 3 * 4 + 1")
+parser(grammar, "(2 + 3) * (4 + 1)")
+parser(grammar, "(2 + 3) * 4 (4 + 1)")
+
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/parser2.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,139 @@
+// A naive version of parser combinators producing parse trees
+//
+// Needs
+// :load matcher.scala
+
+// some regular expressions
+val LETTER = RANGE("abcdefghijklmnopqrstuvwxyz")
+val ID = PLUS(LETTER)
+
+val DIGIT = RANGE("0123456789")
+val NONZERODIGIT = RANGE("123456789")
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+
+val LPAREN = CHAR('(')
+val RPAREN = CHAR(')')
+
+val WHITESPACE = PLUS(RANGE(" \n"))
+val OPS = RANGE("+-*")
+
+// for classifying the strings that have been recognised
+abstract class Token
+
+case object T_WHITESPACE extends Token
+case class T_NUM(s: String) extends Token
+case class T_ID(s: String) extends Token
+case class T_OP(s: String) extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case object T_IF extends Token
+case object T_THEN extends Token
+case object T_ELSE extends Token
+
+// lexing rules for arithmetic expressions
+val lexing_rules: List[Rule[Token]]=
+ List(("if", (s) => T_IF),
+ ("then", (s) => T_THEN),
+ ("else", (s) => T_ELSE),
+ (NUMBER, (s) => T_NUM(s.mkString)),
+ (ID, (s) => T_ID(s.mkString)),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (OPS, (s) => T_OP(s.mkString)))
+
+val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
+
+
+// parse trees
+abstract class ParseTree
+case class Leaf(t: Token) extends ParseTree
+case class Branch(pts: List[ParseTree]) extends ParseTree
+
+def combine(pt1: ParseTree, pt2: ParseTree) = pt1 match {
+ case Leaf(t) => Branch(List(Leaf(t), pt2))
+ case Branch(pts) => Branch(pts ++ List(pt2))
+}
+
+// parser combinators
+abstract class Parser {
+ def parse(ts: List[Token]): Set[(ParseTree, List[Token])]
+
+ def parse_all(ts: List[Token]) : Set[ParseTree] =
+ for ((head, tail) <- parse(ts); if (tail == Nil)) yield head
+
+ def || (right : => Parser) : Parser = new AltParser(this, right)
+ def ~ (right : => Parser) : Parser = new SeqParser(this, right)
+}
+
+class AltParser(p: => Parser, q: => Parser) extends Parser {
+ def parse (ts: List[Token]) = p.parse(ts) ++ q.parse(ts)
+}
+
+class SeqParser(p: => Parser, q: => Parser) extends Parser {
+ def parse(ts: List[Token]) =
+ for ((head1, tail1) <- p.parse(ts);
+ (head2, tail2) <- q.parse(tail1)) yield (combine(head1, head2), tail2)
+}
+
+class ListParser(ps: => List[Parser]) extends Parser {
+ def parse(ts: List[Token]) = ps match {
+ case Nil => Set()
+ case p::Nil => p.parse(ts)
+ case p::ps =>
+ for ((head1, tail1) <- p.parse(ts);
+ (head2, tail2) <- new ListParser(ps).parse(tail1)) yield (Branch(List(head1, head2)), tail2)
+ }
+}
+
+case class TokParser(tok: Token) extends Parser {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((Leaf(t), ts))
+ case _ => Set ()
+ }
+}
+
+implicit def token2tparser(t: Token) = TokParser(t)
+
+case object IdParser extends Parser {
+ def parse(ts: List[Token]) = ts match {
+ case T_ID(s)::ts => Set((Leaf(T_ID(s)), ts))
+ case _ => Set ()
+ }
+}
+
+case object NumParser extends Parser {
+ def parse(ts: List[Token]) = ts match {
+ case T_NUM(s)::ts => Set((Leaf(T_NUM(s)), ts))
+ case _ => Set ()
+ }
+}
+
+lazy val E: Parser = (T ~ T_OP("+") ~ E) || T // start symbol
+lazy val T: Parser = (F ~ T_OP("*") ~ T) || F
+lazy val F: Parser = (T_LPAREN ~ E ~ T_RPAREN) || NumParser
+
+println(Tok.fromString("1 + 2 + 3"))
+println(E.parse_all(Tok.fromString("1 + 2 + 3")))
+
+def eval(t: ParseTree) : Int = t match {
+ case Leaf(T_NUM(n)) => n.toInt
+ case Branch(List(t1, Leaf(T_OP("+")), t2)) => eval(t1) + eval(t2)
+ case Branch(List(t1, Leaf(T_OP("*")), t2)) => eval(t1) * eval(t2)
+ case Branch(List(Leaf(T_LPAREN), t, Leaf(T_RPAREN))) => eval(t)
+}
+
+(E.parse_all(Tok.fromString("1 + 2 + 3"))).map(eval(_))
+(E.parse_all(Tok.fromString("1 + 2 * 3"))).map(eval(_))
+
+lazy val EXPR: Parser =
+ new ListParser(List(T_IF, EXPR, T_THEN, EXPR)) ||
+ new ListParser(List(T_IF, EXPR, T_THEN, EXPR, T_ELSE, EXPR)) ||
+ IdParser
+
+println(EXPR.parse_all(Tok.fromString("if a then b else c")))
+println(EXPR.parse_all(Tok.fromString("if a then if x then y else c")))
+
+
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/parser2a.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,105 @@
+// Parser combinators including semantic actions
+// parses lists of tokens
+//
+// Needs
+// :load matcher.scala
+
+// some regular expressions
+val LETTER = RANGE("abcdefghijklmnopqrstuvwxyz")
+val ID = PLUS(LETTER)
+
+val DIGIT = RANGE("0123456789")
+val NONZERODIGIT = RANGE("123456789")
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+
+val LPAREN = CHAR('(')
+val RPAREN = CHAR(')')
+
+val WHITESPACE = PLUS(RANGE(" \n"))
+val OPS = RANGE("+-*")
+
+// for classifying the strings that have been recognised
+abstract class Token
+
+case object T_WHITESPACE extends Token
+case class T_NUM(s: String) extends Token
+case class T_ID(s: String) extends Token
+case class T_OP(s: String) extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case object T_IF extends Token
+case object T_THEN extends Token
+case object T_ELSE extends Token
+
+// lexing rules for arithmetic expressions
+val lexing_rules: List[Rule[Token]]=
+ List(("if", (s) => T_IF),
+ ("then", (s) => T_THEN),
+ ("else", (s) => T_ELSE),
+ (NUMBER, (s) => T_NUM(s.mkString)),
+ (ID, (s) => T_ID(s.mkString)),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (OPS, (s) => T_OP(s.mkString)))
+
+val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
+
+// parser combinators with return type T
+abstract class Parser[T] {
+ def parse(ts: List[Token]): Set[(T, List[Token])]
+
+ def parse_all(ts: List[Token]) : Set[T] =
+ for ((head, tail) <- parse(ts); if (tail == Nil)) yield head
+
+ def || (right : => Parser[T]) : Parser[T] = new AltParser(this, right)
+ def ==>[S] (f: => T => S) : Parser [S] = new FunParser(this, f)
+ def ~[S] (right : => Parser[S]) : Parser[(T, S)] = new SeqParser(this, right)
+ def ~>[S] (right : => Parser[S]) : Parser[S] = this ~ right ==> (x => x._2)
+ def <~[S] (right : => Parser[S]) : Parser[T] = this ~ right ==> (x => x._1)
+
+}
+
+class SeqParser[T, S](p: => Parser[T], q: => Parser[S]) extends Parser[(T, S)] {
+ def parse(sb: List[Token]) =
+ for ((head1, tail1) <- p.parse(sb);
+ (head2, tail2) <- q.parse(tail1)) yield ((head1, head2), tail2)
+}
+
+class AltParser[T](p: => Parser[T], q: => Parser[T]) extends Parser[T] {
+ def parse (sb: List[Token]) = p.parse(sb) ++ q.parse(sb)
+}
+
+class FunParser[T, S](p: => Parser[T], f: T => S) extends Parser[S] {
+ def parse (sb: List[Token]) =
+ for ((head, tail) <- p.parse(sb)) yield (f(head), tail)
+}
+
+
+case class TokParser(tok: Token) extends Parser[Token] {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((t, ts))
+ case _ => Set ()
+ }
+}
+
+implicit def token2tparser(t: Token) = TokParser(t)
+
+case object NumParser extends Parser[Int] {
+ def parse(ts: List[Token]) = ts match {
+ case T_NUM(s)::ts => Set((s.toInt, ts))
+ case _ => Set ()
+ }
+}
+
+lazy val E: Parser[Int] = (T ~ T_OP("+") ~ E) ==> { case ((x, y), z) => x + z } || T
+lazy val T: Parser[Int] = (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => x * z } || F
+lazy val F: Parser[Int] = (T_LPAREN ~> E <~ T_RPAREN) || NumParser
+
+println(E.parse_all(Tok.fromString("1 + 2 + 3")))
+println(E.parse_all(Tok.fromString("1 + 2 * 3")))
+println(E.parse_all(Tok.fromString("(1 + 2) * 3")))
+
+// Excercise: implement minus
+println(E.parse_all(Tok.fromString("(1 - 2) * 3")))
+println(E.parse_all(Tok.fromString("(1 + 2) * - 3")))
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/parser3.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,41 @@
+package object parser {
+
+// parser combinators
+// with input type I and return type T
+//
+// needs to be compiled with scalac parser3.scala
+
+abstract class Parser[I <% Seq[_], T] {
+ def parse(ts: I): Set[(T, I)]
+
+ def parse_all(ts: I) : Set[T] =
+ for ((head, tail) <- parse(ts); if (tail.isEmpty)) yield head
+
+ def parse_single(ts: I) : T = parse_all(ts).toList match {
+ case t::Nil => t
+ case _ => { println ("Parse Error") ; sys.exit(-1) }
+ }
+
+ def || (right : => Parser[I, T]) : Parser[I, T] = new AltParser(this, right)
+ def ==>[S] (f: => T => S) : Parser [I, S] = new FunParser(this, f)
+ def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] = new SeqParser(this, right)
+ def ~>[S] (right : => Parser[I, S]) : Parser[I, S] = this ~ right ==> (_._2)
+ def <~[S] (right : => Parser[I, S]) : Parser[I, T] = this ~ right ==> (_._1)
+}
+
+class SeqParser[I <% Seq[_], T, S](p: => Parser[I, T], q: => Parser[I, S]) extends Parser[I, (T, S)] {
+ def parse(sb: I) =
+ for ((head1, tail1) <- p.parse(sb);
+ (head2, tail2) <- q.parse(tail1)) yield ((head1, head2), tail2)
+}
+
+class AltParser[I <% Seq[_], T](p: => Parser[I, T], q: => Parser[I, T]) extends Parser[I, T] {
+ def parse(sb: I) = p.parse(sb) ++ q.parse(sb)
+}
+
+class FunParser[I <% Seq[_], T, S](p: => Parser[I, T], f: T => S) extends Parser[I, S] {
+ def parse(sb: I) =
+ for ((head, tail) <- p.parse(sb)) yield (f(head), tail)
+}
+
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/parser4.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,82 @@
+
+// parser combinators with input type I and return type T
+
+case class SubString(s: String, l: Int, h: Int) {
+ def low = l
+ def high = h
+ def length = h - l
+ def substring(l: Int = l, h: Int = h) = s.slice(l, h)
+ def set(low: Int = l, high: Int = h) = SubString(s, low, high)
+
+}
+
+type Ctxt = List[(String, SubString)]
+
+abstract class Parser[T] {
+
+ def parse(ts: SubString, ctxt: Ctxt): Set[(T, SubString)]
+
+ def parse_all(s: String) : Set[T] =
+ for ((head, tail) <- parse(SubString(s, 0, s.length), Nil); if (tail.substring() == "")) yield head
+
+ def || (right : => Parser[T]) : Parser[T] = new AltParser(this, right)
+ def ==>[S] (f: => T => S) : Parser [S] = new FunParser(this, f)
+ def ~[S] (right : => Parser[S]) : Parser[(T, S)] = new SeqParser(this, right)
+}
+
+class SeqParser[T, S](p: => Parser[T], q: => Parser[S]) extends Parser[(T, S)] {
+ def parse(sb: SubString, ctxt: Ctxt) =
+ for ((head1, tail1) <- p.parse(sb, ctxt);
+ (head2, tail2) <- q.parse(tail1, ctxt)) yield ((head1, head2), tail2)
+}
+
+class AltParser[T](p: => Parser[T], q: => Parser[T]) extends Parser[T] {
+ def parse(sb: SubString, ctxt: Ctxt) = p.parse(sb, ctxt) ++ q.parse(sb, ctxt)
+}
+
+class FunParser[T, S](p: => Parser[T], f: T => S) extends Parser[S] {
+ def parse(sb: SubString, ctxt: Ctxt) =
+ for ((head, tail) <- p.parse(sb, ctxt)) yield (f(head), tail)
+}
+
+case class SubStringParser(s: String) extends Parser[SubString] {
+ val n = s.length
+ def parse(sb: SubString, ctxt: Ctxt) = {
+ if (n <= sb.length && sb.substring(sb.low, sb.low + n) == s)
+ Set((sb.set(high = sb.low + n), sb.set(low = sb.low + n)))
+ else Set()
+ }
+}
+
+implicit def string2parser(s: String) = SubStringParser(s) ==> (_.substring())
+
+class IgnLst[T](p: => Parser[T]) extends Parser[T] {
+ def parse(sb: SubString, ctxt: Ctxt) = {
+ if (sb.length == 0) Set()
+ else for ((head, tail) <- p.parse(sb.set(high = sb.high - 1), ctxt))
+ yield (head, tail.set(high = tail.high + 1))
+ }
+}
+
+class CHECK[T](nt: String, p: => Parser[T]) extends Parser[T] {
+ def parse(sb: SubString, ctxt: Ctxt) = {
+ val should_trim = ctxt.contains (nt, sb)
+ if (should_trim && sb.length == 0) Set()
+ else if (should_trim) new IgnLst(p).parse(sb, (nt, sb)::ctxt)
+ else p.parse(sb, (nt, sb)::ctxt)
+ }
+}
+
+// ambigous grammar
+lazy val E: Parser[Int] =
+ new CHECK("E", (E ~ "+" ~ E) ==> { case ((x, y), z) => x + z} ||
+ (E ~ "*" ~ E) ==> { case ((x, y), z) => x * z} ||
+ ("(" ~ E ~ ")") ==> { case ((x, y), z) => y} ||
+ "0" ==> { (s) => 0 } ||
+ "1" ==> { (s) => 1 } ||
+ "2" ==> { (s) => 2 } ||
+ "3" ==> { (s) => 3 })
+
+println(E.parse_all("1+2*3+3"))
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/parser5.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,113 @@
+val DIGIT = RANGE("0123456789")
+val NONZERODIGIT = RANGE("123456789")
+
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+val LPAREN = CHAR('(')
+val RPAREN = CHAR(')')
+val WHITESPACE = PLUS(RANGE(" \n"))
+val OPS = RANGE("+-*")
+
+// for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case class T_NUM(s: String) extends Token
+case class T_OP(s: String) extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+
+val lexing_rules: List[Rule[Token]]=
+ List((NUMBER, (s) => T_NUM(s.mkString)),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (OPS, (s) => T_OP(s.mkString)))
+
+val Tk = Tokenizer(lexing_rules, List(T_WHITESPACE))
+
+
+// parser combinators with input type I and return type T
+// and memoisation
+
+case class SubList[T](s: List[T], l: Int, h: Int) {
+ def low = l
+ def high = h
+ def length = h - l
+ def sublist(l: Int = l, h: Int = h) = s.slice(l, h)
+ def set(low: Int = l, high: Int = h) = SubList(s, low, high)
+}
+
+type Ctxt[T] = List[(String, SubList[T])]
+
+abstract class Parser[I, T] {
+
+ def parse(ts: SubList[I], ctxt: Ctxt[I]): Set[(T, SubList[I])]
+
+ def parse_all(s: List[I]) : Set[T] =
+ for ((head, tail) <- parse(SubList(s, 0, s.length), Nil); if (tail.sublist() == Nil)) yield head
+
+ def || (right : => Parser[I, T]) : Parser[I, T] = new AltParser(this, right)
+ def ==>[S] (f: => T => S) : Parser [I, S] = new FunParser(this, f)
+ def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] = new SeqParser(this, right)
+ def ~>[S] (right : => Parser[I, S]) : Parser[I, S] = this ~ right ==> (_._2)
+ def <~[S] (right : => Parser[I, S]) : Parser[I, T] = this ~ right ==> (_._1)
+}
+
+class SeqParser[I, T, S](p: => Parser[I, T], q: => Parser[I, S]) extends Parser[I, (T, S)] {
+ def parse(sb: SubList[I], ctxt: Ctxt[I]) =
+ for ((head1, tail1) <- p.parse(sb, ctxt);
+ (head2, tail2) <- q.parse(tail1, ctxt)) yield ((head1, head2), tail2)
+}
+
+class AltParser[I, T](p: => Parser[I, T], q: => Parser[I, T]) extends Parser[I, T] {
+ def parse(sb: SubList[I], ctxt: Ctxt[I]) = p.parse(sb, ctxt) ++ q.parse(sb, ctxt)
+}
+
+class FunParser[I, T, S](p: => Parser[I, T], f: T => S) extends Parser[I, S] {
+ def parse(sb: SubList[I], ctxt: Ctxt[I]) =
+ for ((head, tail) <- p.parse(sb, ctxt)) yield (f(head), tail)
+}
+
+case object NumParser extends Parser[Token, Int] {
+ def parse(sb: SubList[Token], ctxt: Ctxt[Token]) = {
+ if (0 < sb.length) sb.sublist(sb.low, sb.low + 1) match {
+ case T_NUM(i)::Nil => Set((i.toInt, sb.set(low = sb.low + 1)))
+ case _ => Set()
+ }
+ else Set()
+ }
+}
+
+case class TokParser(t: Token) extends Parser[Token, Token] {
+ def parse(sb: SubList[Token], ctxt: Ctxt[Token]) = {
+ if (0 < sb.length && sb.sublist(sb.low, sb.low + 1) == List(t)) Set((t, sb.set(low = sb.low + 1)))
+ else Set()
+ }
+}
+
+implicit def token2tparser(t: Token) = TokParser(t)
+
+class IgnLst[I, T](p: => Parser[I, T]) extends Parser[I, T] {
+ def parse(sb: SubList[I], ctxt: Ctxt[I]) = {
+ if (sb.length == 0) Set()
+ else for ((head, tail) <- p.parse(sb.set(high = sb.high - 1), ctxt))
+ yield (head, tail.set(high = tail.high + 1))
+ }
+}
+
+class CHECK[I, T](nt: String, p: => Parser[I, T]) extends Parser[I, T] {
+ def parse(sb: SubList[I], ctxt: Ctxt[I]) = {
+ val should_trim = ctxt.contains (nt, sb)
+ if (should_trim && sb.length == 0) Set()
+ else if (should_trim) new IgnLst(p).parse(sb, (nt, sb)::ctxt)
+ else p.parse(sb, (nt, sb)::ctxt)
+ }
+}
+
+lazy val E: Parser[Token, Int] =
+ new CHECK("E", (E ~ T_OP("+") ~ E) ==> { case ((x, y), z) => x + z} ||
+ (E ~ T_OP("*") ~ E) ==> { case ((x, y), z) => x * z} ||
+ (T_LPAREN ~ E ~ T_RPAREN) ==> { case ((x, y), z) => y} ||
+ NumParser)
+
+println(E.parse_all(Tk.fromString("1 + 2 * 3")))
+println(E.parse_all(Tk.fromString("(1 + 2) * 3")))
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re-alt.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,115 @@
+trait RegExp {
+ def nullable: Boolean
+ def derive(c: Char): RegExp
+}
+
+case object Empty extends RegExp {
+ def nullable = false
+ def derive(c: Char) = Empty
+}
+
+case object Eps extends RegExp {
+ def nullable = true
+ def derive(c: Char) = Empty
+}
+
+case class Str(s: String) extends RegExp {
+ def nullable = s.isEmpty
+ def derive(c: Char) =
+ if (s.isEmpty || s.head != c) Empty
+ else Str(s.tail)
+}
+
+case class Cat(r: RegExp, s: RegExp) extends RegExp {
+ def nullable = r.nullable && s.nullable
+ def derive(c: Char) =
+ if (r.nullable) Or(Cat(r.derive(c), s), s.derive(c))
+ else Cat(r.derive(c), s)
+}
+
+case class Star(r: RegExp) extends RegExp {
+ def nullable = true
+ def derive(c: Char) = Cat(r.derive(c), this)
+}
+
+case class Or(r: RegExp, s: RegExp) extends RegExp {
+ def nullable = r.nullable || s.nullable
+ def derive(c: Char) = Or(r.derive(c), s.derive(c))
+}
+
+case class And(r: RegExp, s: RegExp) extends RegExp {
+ def nullable = r.nullable && s.nullable
+ def derive(c: Char) = And(r.derive(c), s.derive(c))
+}
+
+case class Not(r: RegExp) extends RegExp {
+ def nullable = !r.nullable
+ def derive(c: Char) = Not(r.derive(c))
+}
+
+
+
+
+object Matcher {
+ def matches(r: RegExp, s: String): Boolean = {
+ if (s.isEmpty) r.nullable
+ else matches(r.derive(s.head), s.tail)
+ }
+}
+
+
+object Pimps {
+ implicit def string2RegExp(s: String) = Str(s)
+
+ implicit def regExpOps(r: RegExp) = new {
+ def | (s: RegExp) = Or(r, s)
+ def & (s: RegExp) = And(r, s)
+ def % = Star(r)
+ def %(n: Int) = rep(r, n)
+ def ? = Or(Eps, r)
+ def ! = Not(r)
+ def ++ (s: RegExp) = Cat(r, s)
+ def ~ (s: String) = Matcher.matches(r, s)
+ }
+
+ implicit def stringOps(s: String) = new {
+ def | (r: RegExp) = Or(s, r)
+ def | (r: String) = Or(s, r)
+ def & (r: RegExp) = And(s, r)
+ def & (r: String) = And(s, r)
+ def % = Star(s)
+ def % (n: Int) = rep(Str(s), n)
+ def ? = Or(Eps, s)
+ def ! = Not(s)
+ def ++ (r: RegExp) = Cat(s, r)
+ def ++ (r: String) = Cat(s, r)
+ def ~ (t: String) = Matcher.matches(s, t)
+ }
+
+ def rep(r: RegExp, n: Int): RegExp =
+ if (n <= 0) Star(r)
+ else Cat(r, rep(r, n - 1))
+}
+
+
+object Test {
+ import Pimps._
+
+ val digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
+ val int = ("+" | "-").? ++ digit.%(1)
+ val real = ("+" | "-").? ++ digit.%(1) ++ ("." ++ digit.%(1)).? ++ (("e" | "E") ++ ("+" | "-").? ++ digit.%(1)).?
+
+ def main(args: Array[String]) {
+ val ints = List("0", "-4534", "+049", "99")
+ val reals = List("0.9", "-12.8", "+91.0", "9e12", "+9.21E-12", "-512E+01")
+ val errs = List("", "-", "+", "+-1", "-+2", "2-")
+
+ ints.foreach(s => assert(int ~ s))
+ reals.foreach(s => assert(!(int ~ s)))
+ errs.foreach(s => assert(!(int ~ s)))
+
+ ints.foreach(s => assert(real ~ s))
+ reals.foreach(s => assert(real ~ s))
+ errs.foreach(s => assert(!(real ~ s)))
+ }
+}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re-internal.rb Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,22 @@
+# provided by Daniel Baldwin
+
+nums = (1..100)
+
+#iterate through the nums 1-100
+nums.each do |i|
+
+ start_time = Time.now
+ string = "a" * i
+
+ #create a new regular expression based on current value of i
+ re = Regexp.new(/((a?){#{i}})(a{#{i}})/)
+
+ re.match(string)
+ #if re.match(string)
+ # puts "matched string a * #{i} with regex #{re}"
+ #else
+ # puts "unmatched string a * #{i} with regex #{re}"
+ #end
+
+ puts "#{i} %.5f" % (Time.now - start_time)
+end
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re-internal.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,17 @@
+
+// measures the time a function needs
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+
+for (i <- 1 to 10001 by 300) {
+ val re = ("((a?){" + i + "})(a{" + i + "})")
+ println(i + " " + "%.5f".format(time_needed(1, ("a" * i).matches(re))))
+}
+
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re.py Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,12 @@
+#!/usr/bin/env python
+import re
+import sys
+
+cn = sys.argv[1]
+
+r1 = '((a?){%s})' % cn
+r2 = 'a{%s}' % cn
+
+m = re.match(r1 + r2 , "a" * int(cn))
+
+print m.group(0)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,123 @@
+
+// regular expressions including NOT
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp
+
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression
+// cannot recognise more
+def no_more (r: Rexp) : Boolean = r match {
+ case NULL => true
+ case EMPTY => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => no_more(r1) && no_more(r2)
+ case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
+ case STAR(_) => false
+ case NOT(r) => !(no_more(r))
+}
+
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+}
+
+
+// regular expression for specifying
+// ranges of characters
+def RANGE(s : List[Char]) : Rexp = s match {
+ case Nil => NULL
+ case c::Nil => CHAR(c)
+ case c::s => ALT(CHAR(c), RANGE(s))
+}
+
+//one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+
+//some regular expressions
+val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
+val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
+val LETTER = ALT(LOWERCASE, UPPERCASE)
+val DIGIT = RANGE("0123456789".toList)
+val NONZERODIGIT = RANGE("123456789".toList)
+
+val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGIT)))
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+val WHITESPACE = RANGE(" \n".toList)
+val WHITESPACES = PLUS(WHITESPACE)
+
+val ALL = ALT(ALT(LETTER, DIGIT), WHITESPACE)
+val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
+
+
+// an example list of regular expressions
+val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, WHITESPACES, COMMENT)
+
+
+def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
+
+def munch(r: Rexp, s: List[Char], t: List[Char]) : Option[(List[Char], List[Char])] =
+ s match {
+ case Nil if (nullable(r)) => Some(Nil, t)
+ case Nil => None
+ case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, t)
+ case c::s if (no_more(der (c, r))) => None
+ case c::s => munch(der (c, r), s, t ::: List(c))
+ }
+
+def one_string (regs: List[Rexp], s: List[Char]) : (List[Char], List[Char]) = {
+ val somes = regs.map { munch(_, s, Nil) } .flatten
+ if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
+}
+
+def tokenize (regs: List[Rexp], s: List[Char]) : List[String] = s match {
+ case Nil => Nil
+ case _ => one_string(regs, s) match {
+ case (rest, s) => s.mkString :: tokenize(regs, rest)
+ }
+}
+
+//examples
+println(tokenize(regs, "if true then then 42 else +".toList))
+println(tokenize(regs, "if+true+then+then+42+else +".toList))
+println(tokenize(regs, "ifff if 34 34".toList))
+println(tokenize(regs, "/*ifff if */ hhjj /*34 */".toList))
+println(tokenize(regs, "/* if true then */ then 42 else +".toList))
+//println(tokenize(regs, "ifff $ if 34".toList)) // causes an error because of the symbol $
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re0.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,117 @@
+import scala.annotation.tailrec
+
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case object ALLCHAR extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class STR(s: String) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp
+case class REP(r: Rexp, n: Int) extends Rexp
+
+// some convenience for typing in regular expressions
+implicit def string2rexp(s : String) : Rexp = STR(s)
+
+implicit def RexpOps(r: Rexp) = new {
+ def | (s: Rexp) = ALT(r, s)
+ def % = STAR(r)
+ def %(n: Int) = REP(r, n)
+ def %%(n: Int) = SEQ(REP(r, n), STAR(r))
+ def ? = ALT(EMPTY, r)
+ def unary_! = NOT(r)
+ def ~ (s: Rexp) = SEQ(r, s)
+}
+
+implicit def stringOps(s: String) = new {
+ def | (r: Rexp) = ALT(s, r)
+ def | (r: String) = ALT(s, r)
+ def % = STAR(s)
+ def %(n: Int) = REP(s, n)
+ def %%(n: Int) = SEQ(REP(s, n), STAR(s))
+ def ? = ALT(EMPTY, s)
+ def unary_! = NOT(s)
+ def ~ (r: Rexp) = SEQ(s, r)
+ def ~ (r: String) = SEQ(s, r)
+}
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case ALLCHAR => false
+ case CHAR(_) => false
+ case STR(s) => s.isEmpty
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+ case REP(r, i) => if (i == 0) true else nullable(r)
+}
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case ALLCHAR => EMPTY
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case STR(s) => if (s.isEmpty || s.head != c) NULL else STR(s.tail)
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+ case REP(r, i) =>
+ if (i == 0) NULL else SEQ(der(c, r), REP(r, i - 1))
+}
+
+// derivative w.r.t. a string (iterates der)
+@tailrec
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r))
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+//examples
+val digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
+val int = ("+" | "-").? ~ digit.%%(1)
+val real = ("+" | "-").? ~ digit.%%(1) ~ ("." ~ digit.%%(1)).? ~ (("e" | "E") ~ ("+" | "-").? ~ digit.%%(1)).?
+
+val ints = List("0", "-4534", "+049", "99")
+val reals = List("0.9", "-12.8", "+91.0", "9e12", "+9.21E-12", "-512E+01")
+val errs = List("", "-", "+", "+-1", "-+2", "2-")
+
+ints.map(s => matcher(int, s))
+reals.map(s => matcher(int, s))
+errs.map(s => matcher(int, s))
+
+ints.map(s => matcher(real, s))
+reals.map(s => matcher(real, s))
+errs.map(s => matcher(real, s))
+
+
+
+def RTEST(n: Int) = ("a".? %(n)) ~ ("a" %(n))
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+for (i <- 1 to 12000 by 500) {
+ println(i + ": " + "%.5f".format(time_needed(1, matcher(RTEST(i), "a" * i))))
+}
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re1.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,80 @@
+
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+}
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+}
+
+// derivative w.r.t. a string (iterates der)
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r))
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+//example
+//val r = STAR(ALT(SEQ(CHAR('a'), CHAR('b')), CHAR('b')))
+//der('b', r)
+//der('b', r)
+
+//one or zero
+def OPT(r: Rexp) = ALT(r, EMPTY)
+
+//n-times
+def NTIMES(r: Rexp, n: Int) : Rexp = n match {
+ case 0 => EMPTY
+ case 1 => r
+ case n => SEQ(r, NTIMES(r, n - 1))
+}
+
+def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+for (i <- 1 to 29) {
+ println(i + ": " + "%.5f".format(time_needed(1, matcher(RTEST(i), "a" * i))))
+}
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re2.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,100 @@
+
+abstract class Rexp {
+ def simp : Rexp = this
+}
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp {
+ override def simp = (r1.simp, r2.simp) match {
+ case (NULL, r) => r
+ case (r, NULL) => r
+ case (r, EMPTY) => if (nullable(r)) r else ALT(r, EMPTY)
+ case (EMPTY, r) => if (nullable(r)) r else ALT(r, EMPTY)
+ case (r1, r2) => if (r1 == r2) r1 else ALT(r1, r2)
+ }
+}
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp {
+ override def simp = (r1.simp, r2.simp) match {
+ case (NULL, _) => NULL
+ case (_, NULL) => NULL
+ case (EMPTY, r) => r
+ case (r, EMPTY) => r
+ case (r1, r2) => SEQ(r1, r2)
+ }
+}
+case class STAR(r: Rexp) extends Rexp {
+ override def simp = r.simp match {
+ case NULL => EMPTY
+ case EMPTY => EMPTY
+ case r => STAR(r)
+ }
+}
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+}
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+}
+
+// derivative w.r.t. a string (iterates der)
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r).simp)
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+
+//one or zero
+def OPT(r: Rexp) = ALT(r, EMPTY)
+
+//n-times
+def NTIMES(r: Rexp, n: Int) : Rexp = n match {
+ case 0 => EMPTY
+ case 1 => r
+ case n => SEQ(r, NTIMES(r, n - 1))
+}
+
+def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+for (i <- 1 to 100) {
+ println(i + ": " + "%.5f".format(time_needed(1, matcher(RTEST(i), "a" * i))))
+}
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re3.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,106 @@
+
+abstract class Rexp {
+ def simp : Rexp = this
+}
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp {
+ override def simp = (r1.simp, r2.simp) match {
+ case (NULL, r) => r
+ case (r, NULL) => r
+ case (r, EMPTY) => if (nullable(r)) r else ALT(r, EMPTY)
+ case (EMPTY, r) => if (nullable(r)) r else ALT(r, EMPTY)
+ case (r1, r2) => if (r1 == r2) r1 else ALT(r1, r2)
+ }
+}
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp {
+ override def simp = (r1.simp, r2.simp) match {
+ case (NULL, _) => NULL
+ case (_, NULL) => NULL
+ case (EMPTY, r) => r
+ case (r, EMPTY) => r
+ case (r1, r2) => SEQ(r1, r2)
+ }
+}
+case class STAR(r: Rexp) extends Rexp {
+ override def simp = r.simp match {
+ case NULL => EMPTY
+ case EMPTY => EMPTY
+ case r => STAR(r)
+ }
+}
+case class NTIMES(r: Rexp, n: Int) extends Rexp {
+ override def simp = if (n == 0) EMPTY else
+ r.simp match {
+ case NULL => NULL
+ case EMPTY => EMPTY
+ case r => NTIMES(r, n)
+ }
+}
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NTIMES(r, i) => if (i == 0) true else nullable(r)
+}
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NTIMES(r, i) =>
+ if (i == 0) NULL else SEQ(der(c, r), NTIMES(r, i - 1))
+}
+
+// derivative w.r.t. a string (iterates der)
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r).simp)
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+
+
+//one or zero
+def OPT(r: Rexp) = ALT(r, EMPTY)
+
+def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+
+for (i <- 1 to 11001 by 500) {
+ println(i + " " + + " " + time_needed(1, matcher(RTEST(i), "a" * i)))
+}
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/re4.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,101 @@
+import scala.annotation.tailrec
+abstract class Rexp {
+ def simp : Rexp = this
+}
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp {
+ override def simp = (r1.simp, r2.simp) match {
+ case (NULL, r) => r
+ case (r, NULL) => r
+ case (r, EMPTY) => if (nullable(r)) r else ALT(r, EMPTY)
+ case (EMPTY, r) => if (nullable(r)) r else ALT(r, EMPTY)
+ case (r1, r2) => ALT(r1, r2)
+ }
+}
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp {
+ override def simp = (r1.simp, r2.simp) match {
+ case (NULL, _) => NULL
+ case (_, NULL) => NULL
+ case (EMPTY, r) => r
+ case (r, EMPTY) => r
+ case (r1, r2) => SEQ(r1, r2)
+ }
+}
+case class STAR(r: Rexp) extends Rexp
+case class NTIMES(r: Rexp, n: Int) extends Rexp
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NTIMES(r, i) => if (i == 0) false else nullable(r)
+}
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NTIMES(r, i) =>
+ if (i == 0) NULL else SEQ(der(c, r), NTIMES(r, i - 1))
+}
+
+// derivative w.r.t. a string (iterates der)
+@tailrec
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r).simp)
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+
+
+//one or zero
+def OPT(r: Rexp) = ALT(r, EMPTY)
+
+//n-times
+/*def NTIMES(r: Rexp, n: Int) : Rexp = n match {
+ case 0 => NULL
+ case 1 => r
+ case n => SEQ(r, NTIMES(r, n - 1))
+}*/
+
+def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+
+for (i <- 1 to 13001 by 500) {
+ println(i + " " + time_needed(1, matcher(RTEST(i), "a" * i)))
+}
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/regexp.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,106 @@
+// regular expressions
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// for example
+println(STAR("abc"))
+
+// produces STAR(SEQ(CHAR(a),SEQ(CHAR(b),SEQ(CHAR(c),EMPTY))))
+
+
+
+// a simple-minded regular expression matcher:
+// it loops for examples like STAR(EMPTY) with
+// strings this regular expression does not match
+
+def smatchers(rs: List[Rexp], s: List[Char]) : Boolean = (rs, s) match {
+ case (NULL::rs, s) => false
+ case (EMPTY::rs, s) => smatchers(rs, s)
+ case (CHAR(c)::rs, Nil) => false
+ case (CHAR(c)::rs, d::s) => (c ==d) && smatchers(rs, s)
+ case (ALT(r1, r2)::rs, s) => smatchers(r1::rs, s) || smatchers(r2::rs, s)
+ case (SEQ(r1, r2)::rs, s) => smatchers(r1::r2::rs, s)
+ case (STAR(r)::rs, s) => smatchers(rs, s) || smatchers(r::STAR(r)::rs, s)
+ case (Nil, s) => s == Nil
+}
+
+def smatcher(r: Rexp, s: String) = smatchers(List(r), s.toList)
+
+// regular expression: a
+println(smatcher(CHAR('a'), "ab"))
+
+// regular expression: a + (b o c)
+println(smatcher(ALT(CHAR('a'), SEQ(CHAR('b'), CHAR('c'))), "ab"))
+
+// regular expression: a + (b o c)
+println(smatcher(ALT(CHAR('a'), SEQ(CHAR('b'), CHAR('c'))), "bc"))
+
+// loops for regular expression epsilon*
+//println(smatcher(STAR(EMPTY), "a"))
+
+
+
+// Regular expression matcher that works properly
+//================================================
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+}
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+}
+
+// derivative w.r.t. a string (iterates der)
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r))
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+
+//examples
+
+println(matcher(SEQ(STAR("a"), STAR("b")), "bbaaa"))
+println(matcher(ALT(STAR("a"), STAR("b")), ""))
+println(matcher("abc", ""))
+println(matcher(STAR(ALT(EMPTY, "a")), ""))
+println(matcher(STAR(EMPTY), "a"))
+println(matcher("cab","cab"))
+println(matcher(STAR("a"),"aaa"))
+println(matcher("cab" ,"cab"))
+println(matcher(STAR("a"),"aaa"))
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/regexp2.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,123 @@
+
+// regular expressions including NOT
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp
+
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression
+// cannot recognise more
+def no_more (r: Rexp) : Boolean = r match {
+ case NULL => true
+ case EMPTY => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => no_more(r1) && no_more(r2)
+ case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
+ case STAR(_) => false
+ case NOT(r) => !(no_more(r))
+}
+
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+}
+
+
+// regular expression for specifying
+// ranges of characters
+def RANGE(s : List[Char]) : Rexp = s match {
+ case Nil => NULL
+ case c::Nil => CHAR(c)
+ case c::s => ALT(CHAR(c), RANGE(s))
+}
+
+//one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+
+//some regular expressions
+val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
+val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
+val LETTER = ALT(LOWERCASE, UPPERCASE)
+val DIGIT = RANGE("0123456789".toList)
+val NONZERODIGIT = RANGE("123456789".toList)
+
+val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGIT)))
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+val WHITESPACE = RANGE(" \n".toList)
+val WHITESPACES = PLUS(WHITESPACE)
+
+val ALL = ALT(ALT(LETTER, DIGIT), WHITESPACE)
+val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
+
+
+// an example list of regular expressions
+val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, WHITESPACES, COMMENT)
+
+
+def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
+
+def munch(r: Rexp, s: List[Char], t: List[Char]) : Option[(List[Char], List[Char])] =
+ s match {
+ case Nil if (nullable(r)) => Some(Nil, t)
+ case Nil => None
+ case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, t)
+ case c::s if (no_more(der (c, r))) => None
+ case c::s => munch(der (c, r), s, t ::: List(c))
+ }
+
+def one_string (regs: List[Rexp], s: List[Char]) : (List[Char], List[Char]) = {
+ val somes = regs.map { munch(_, s, Nil) } .flatten
+ if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
+}
+
+def tokenize (regs: List[Rexp], s: List[Char]) : List[String] = s match {
+ case Nil => Nil
+ case _ => one_string(regs, s) match {
+ case (rest, s) => s.mkString :: tokenize(regs, rest)
+ }
+}
+
+//examples
+println(tokenize(regs, "if true then then 42 else +".toList))
+println(tokenize(regs, "if+true+then+then+42+else +".toList))
+println(tokenize(regs, "ifff if 34 34".toList))
+println(tokenize(regs, "/*ifff if */ hhjj /*34 */".toList))
+println(tokenize(regs, "/* if true then */ then 42 else +".toList))
+//println(tokenize(regs, "ifff $ if 34".toList)) // causes an error because of the symbol $
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/regexp3.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,141 @@
+
+// regular expressions including NOT
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp
+
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression
+// cannot recognise more
+def no_more (r: Rexp) : Boolean = r match {
+ case NULL => true
+ case EMPTY => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => no_more(r1) && no_more(r2)
+ case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
+ case STAR(_) => false
+ case NOT(r) => !(no_more(r))
+}
+
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+}
+
+// regular expression for specifying
+// ranges of characters
+def RANGE(s : List[Char]) : Rexp = s match {
+ case Nil => NULL
+ case c::Nil => CHAR(c)
+ case c::s => ALT(CHAR(c), RANGE(s))
+}
+
+// one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+// some regular expressions
+val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
+val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
+val LETTER = ALT(LOWERCASE, UPPERCASE)
+val DIGIT = RANGE("0123456789".toList)
+val NONZERODIGIT = RANGE("123456789".toList)
+
+val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGIT)))
+val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
+val WHITESPACE = RANGE(" \n".toList)
+val WHITESPACES = PLUS(WHITESPACE)
+
+val ALL = ALT(ALT(LETTER, DIGIT), WHITESPACE)
+val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
+
+
+// for classifying the strings that have been recognised
+abstract class Token
+
+case object T_WHITESPACE extends Token
+case object T_COMMENT extends Token
+case class T_IDENT(s: String) extends Token
+case class T_OP(s: String) extends Token
+case class T_NUM(n: Int) extends Token
+case class T_KEYWORD(s: String) extends Token
+
+
+// an example list of syntactic rules
+type Rule = (Rexp, List[Char] => Token)
+
+val rules: List[Rule]=
+ List(("if", (s) => T_KEYWORD(s.mkString)),
+ ("then", (s) => T_KEYWORD(s.mkString)),
+ ("else", (s) => T_KEYWORD(s.mkString)),
+ ("+", (s) => T_OP(s.mkString)),
+ (IDENT, (s) => T_IDENT(s.mkString)),
+ (NUMBER, (s) => T_NUM(s.mkString.toInt)),
+ (WHITESPACES, (s) => T_WHITESPACE),
+ (COMMENT, (s) => T_COMMENT))
+
+
+def error (s: String) = throw new IllegalArgumentException ("Cannot tokenize: " + s)
+
+def munch(r: Rexp, action: List[Char] => Token, s: List[Char], t: List[Char]) : Option[(List[Char], Token)] =
+ s match {
+ case Nil if (nullable(r)) => Some(Nil, action(t))
+ case Nil => None
+ case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, action(t))
+ case c::s if (no_more(der (c, r))) => None
+ case c::s => munch(der (c, r), action, s, t ::: List(c))
+ }
+
+def one_token (rs: List[Rule], s: List[Char]) : (List[Char], Token) = {
+ val somes = rs.map { (r) => munch(r._1, r._2, s, Nil) } .flatten
+ if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
+}
+
+def tokenize (rs: List[Rule], s: List[Char]) : List[Token] = s match {
+ case Nil => Nil
+ case _ => one_token(rs, s) match {
+ case (rest, token) => token :: tokenize(rs, rest)
+ }
+}
+
+//examples
+println(tokenize(rules, "if true then then 42 else +".toList))
+println(tokenize(rules, "if+true+then+then+42+else +".toList))
+println(tokenize(rules, "ifff if 34 34".toList))
+println(tokenize(rules, "/*ifff if */ hhjj /*34 */".toList))
+println(tokenize(rules, "/* if true then */ then 42 else +".toList))
+//println(tokenize(rules, "ifff $ if 34".toList)) // causes an error because of the symbol $
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/regexp4.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,168 @@
+// regular expressions
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp
+
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression
+// recognises nothing
+def zeroable (r: Rexp) : Boolean = r match {
+ case NULL => true
+ case EMPTY => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => zeroable(r1) && zeroable(r2)
+ case SEQ(r1, r2) => zeroable(r1) || zeroable(r2)
+ case STAR(_) => false
+ case NOT(r) => !(zeroable(r))
+}
+
+def starts_with (r: Rexp, c: Char) : Boolean = r match {
+ case NULL => false
+ case EMPTY => false
+ case CHAR(d) => (c == d)
+ case ALT(r1, r2) => starts_with(r1, c) || starts_with(r2, c)
+ case SEQ(r1, r2) => if (nullable(r1)) (starts_with(r1, c) || starts_with(r2, c))
+ else starts_with(r1, c)
+ case STAR(r) => starts_with(r, c)
+ case NOT(r) => !(starts_with(r, c))
+}
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+}
+
+// derivative w.r.t. a string (iterates der)
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r))
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+
+// regular expression for specifying
+// ranges of characters
+def RANGE(s : List[Char]) : Rexp = s match {
+ case Nil => NULL
+ case c::Nil => CHAR(c)
+ case c::s => ALT(CHAR(c), RANGE(s))
+}
+
+//one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+
+//some regular expressions
+val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
+val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
+val LETTER = ALT(LOWERCASE, UPPERCASE)
+val DIGITS = RANGE("0123456789".toList)
+val NONZERODIGITS = RANGE("123456789".toList)
+
+val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGITS)))
+val NUMBER = ALT(SEQ(NONZERODIGITS, STAR(DIGITS)), "0")
+val WHITESPACE = RANGE(" \n".toList)
+val SYMBOLS = RANGE("/*".toList)
+
+val ALL = ALT(ALT(ALT(LETTER, DIGITS), WHITESPACE), SYMBOLS)
+
+val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
+
+println(matcher(NUMBER, "0"))
+println(matcher(NUMBER, "01"))
+println(matcher(NUMBER, "123450"))
+
+println(matcher(SEQ(STAR("a"), STAR("b")), "bbaaa"))
+println(matcher(ALT(STAR("a"), STAR("b")), ""))
+println(matcher("abc", ""))
+println(matcher(STAR(ALT(EMPTY, "a")), ""))
+println(matcher(STAR(EMPTY), "a"))
+println(matcher("cab","cab"))
+println(matcher(STAR("a"),"aaa"))
+println(matcher("cab" ,"cab"))
+println(matcher(STAR("a"),"aaa"))
+
+println(matcher(COMMENT, "/* */"))
+println(matcher(COMMENT, "/* foobar comment */"))
+println(matcher(COMMENT, "/* test */ test */"))
+
+// an example list of regular expressions
+val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, COMMENT, WHITESPACE)
+
+
+def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
+
+def munch(r: Rexp, s: List[Char], t: List[Char]) : Option[(List[Char], List[Char])] =
+ if (zeroable(r)) None else s match {
+ case Nil => if (nullable(r)) Some(Nil, t) else None
+ case c::s if (zeroable(der (c, r)) && nullable(r)) => Some(c::s, t)
+ //case c::s if (zeroable(der (c, r))) => None
+ case c::s => munch(der (c, r), s, t ::: List(c))
+}
+
+
+def lex_one (regs: List[Rexp], s: List[Char]) : (List[Char], List[Char]) = {
+ val somes = regs.map { munch(_, s, Nil) } .flatten
+ if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
+}
+
+def lex_all (regs: List[Rexp], s: List[Char]) : List[String] = s match {
+ case Nil => Nil
+ case _ => lex_one(regs, s) match {
+ case (rest, s) => s.mkString :: lex_all(regs, rest)
+ }
+}
+
+
+
+starts_with(der('/', COMMENT), '*')
+
+munch(COMMENT, "/*ifff if 34 */".toList, Nil)
+val COMMENT2 = NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))
+
+der('a', COMMENT2)
+zeroable(der('a', COMMENT2))
+
+matcher(COMMENT2, "ifff if 34")
+munch(COMMENT2, "ifff if 34".toList, Nil)
+starts_with(COMMENT2, 'i')
+lex_all(regs, "ifff if 34".toList)
+lex_all(regs, "ifff $ if 34".toList)
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/regexp5.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,177 @@
+// regular expressions
+abstract class Rexp
+
+case object NULL extends Rexp
+case object EMPTY extends Rexp
+case class CHAR(c: Char) extends Rexp
+case class ALT(r1: Rexp, r2: Rexp) extends Rexp
+case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
+case class STAR(r: Rexp) extends Rexp
+case class NOT(r: Rexp) extends Rexp
+
+
+// some convenience for typing in regular expressions
+def charlist2rexp(s : List[Char]) : Rexp = s match {
+ case Nil => EMPTY
+ case c::Nil => CHAR(c)
+ case c::s => SEQ(CHAR(c), charlist2rexp(s))
+}
+implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
+
+
+// nullable function: tests whether the regular
+// expression can recognise the empty string
+def nullable (r: Rexp) : Boolean = r match {
+ case NULL => false
+ case EMPTY => true
+ case CHAR(_) => false
+ case ALT(r1, r2) => nullable(r1) || nullable(r2)
+ case SEQ(r1, r2) => nullable(r1) && nullable(r2)
+ case STAR(_) => true
+ case NOT(r) => !(nullable(r))
+}
+
+// tests whether a regular expression
+// recognises nothing
+def zeroable (r: Rexp) : Boolean = r match {
+ case NULL => true
+ case EMPTY => false
+ case CHAR(_) => false
+ case ALT(r1, r2) => zeroable(r1) && zeroable(r2)
+ case SEQ(r1, r2) => if (nullable(r1)) (zeroable(r1) && zeroable(r2)) else zeroable(r1)
+ //zeroable(r1) || zeroable(r2)
+ case STAR(_) => false
+ case NOT(r) => !(zeroable(r))
+}
+
+
+// derivative of a regular expression w.r.t. a character
+def der (c: Char, r: Rexp) : Rexp = r match {
+ case NULL => NULL
+ case EMPTY => NULL
+ case CHAR(d) => if (c == d) EMPTY else NULL
+ case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
+ case SEQ(r1, r2) =>
+ if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
+ else SEQ(der(c, r1), r2)
+ case STAR(r) => SEQ(der(c, r), STAR(r))
+ case NOT(r) => NOT(der (c, r))
+}
+
+// derivative w.r.t. a string (iterates der)
+def ders (s: List[Char], r: Rexp) : Rexp = s match {
+ case Nil => r
+ case c::s => ders(s, der(c, r))
+}
+
+// main matcher function
+def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
+
+
+// regular expression for specifying
+// ranges of characters
+def RANGE(s : List[Char]) : Rexp = s match {
+ case Nil => NULL
+ case c::Nil => CHAR(c)
+ case c::s => ALT(CHAR(c), RANGE(s))
+}
+
+//one or more
+def PLUS(r: Rexp) = SEQ(r, STAR(r))
+
+
+//some regular expressions
+val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
+val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
+val LETTER = ALT(LOWERCASE, UPPERCASE)
+val DIGITS = RANGE("0123456789".toList)
+val NONZERODIGITS = RANGE("123456789".toList)
+
+val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGITS)))
+val NUMBER = ALT(SEQ(NONZERODIGITS, STAR(DIGITS)), "0")
+val WHITESPACE = RANGE(" \n".toList)
+
+val ALL = ALT(ALT(LETTER, DIGITS), WHITESPACE)
+
+val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
+
+println(matcher(NUMBER, "0"))
+println(matcher(NUMBER, "01"))
+println(matcher(NUMBER, "123450"))
+
+println(matcher(SEQ(STAR("a"), STAR("b")), "bbaaa"))
+println(matcher(ALT(STAR("a"), STAR("b")), ""))
+println(matcher("abc", ""))
+println(matcher(STAR(ALT(EMPTY, "a")), ""))
+println(matcher(STAR(EMPTY), "a"))
+println(matcher("cab","cab"))
+println(matcher(STAR("a"),"aaa"))
+println(matcher("cab" ,"cab"))
+println(matcher(STAR("a"),"aaa"))
+
+println(matcher(COMMENT, "/* */"))
+println(matcher(COMMENT, "/* 34 */"))
+println(matcher(COMMENT, "/* foobar comment */"))
+println(matcher(COMMENT, "/* test */ test */"))
+
+// an example list of regular expressions
+
+abstract class Token
+
+case object T_WHITESPACE extends Token
+case object T_COMMENT extends Token
+case class T_IDENT(s: String) extends Token
+case class T_OP(s: String) extends Token
+case class T_NUM(n: Int) extends Token
+case class T_KEYWORD(s: String) extends Token
+
+val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, WHITESPACE)
+
+type Rule = (Rexp, List[Char] => Token)
+
+val rules: List[Rule]=
+ List(("if", (s) => T_KEYWORD(s.mkString)),
+ ("then", (s) => T_KEYWORD(s.mkString)),
+ ("else", (s) => T_KEYWORD(s.mkString)),
+ ("+", (s) => T_OP(s.mkString)),
+ (IDENT, (s) => T_IDENT(s.mkString)),
+ (NUMBER, (s) => T_NUM(s.mkString.toInt)),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (COMMENT, (s) => T_COMMENT))
+
+
+def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
+
+def munch(r: Rexp, action: List[Char] => Token, s: List[Char], t: List[Char]) : Option[(List[Char], Token)] =
+{ println("string " + s)
+ println(" rexp " + r)
+ s match {
+ case Nil if (nullable(r)) => Some(Nil, action(t))
+ case Nil => { println("1"); None }
+ case c::s if (zeroable(der (c, r)) && nullable(r)) => Some(c::s, action(t))
+ case c::s if (zeroable(der (c, r))) => { println("2"); None }
+ case c::s => munch(der (c, r), action, s, t ::: List(c))
+ }
+}
+
+def lex_one (rs: List[Rule], s: List[Char]) : (List[Char], Token) = {
+ val somes = rs.map { (r) => munch(r._1, r._2, s, Nil) } .flatten
+ if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
+}
+
+def lex_all (rs: List[Rule], s: List[Char]) : List[Token] = s match {
+ case Nil => Nil
+ case _ => lex_one(rs, s) match {
+ case (rest, t) => t :: lex_all(rs, rest)
+ }
+}
+
+
+
+println(matcher(COMMENT, "/*ifff if 34 34*/"))
+rules.map { (r) => munch(r._1, r._2, "/*ifff if 34 34*/ ".toList, Nil) }
+println(lex_all(rules, "ifff if 34 34".toList))
+println(lex_all(rules, " /*ifff if 34 34*/ ".toList))
+println(lex_all(rules, "ifff $ if 34".toList))
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/scraper.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,57 @@
+import java.io.OutputStreamWriter
+import java.net.URL
+import scala.io.Source.fromInputStream
+
+val url = new URL("http://www.envir.gov.cn/eng/airep/index.asp")
+
+//connect to url
+val conn = url.openConnection
+conn.setRequestProperty("User-Agent", "")
+conn.setDoOutput(true)
+conn.connect
+
+//sending data
+val wr = new OutputStreamWriter(conn.getOutputStream())
+//wr.write("Fdate=2012-9-24&Tdate=2012-09-25")
+//wr.write("Fdate=2012-9-18&Tdate=2012-09-25")
+wr.write("Fdate=2001-5-18&Tdate=2012-09-25")
+wr.flush
+wr.close
+
+//receiving data
+val page = fromInputStream(conn.getInputStream).getLines.mkString("\n")
+
+//println(page)
+
+// regular expression . excludes newlines,
+// therefore we have to use [\S\s]
+val regex1 = """<tr align="center">[\S\s]*?</tr>""".r
+val rows = regex1.findAllIn(page).toList
+
+//print(rows)
+
+val regex2 = """<td align="center">([\S\s]*?)</td>""".r
+
+def aux(s: String) : Array[String] = {
+ for (m <- regex2.findAllIn(s).toArray) yield m match {
+ case regex2(value) => value.trim
+ }
+}
+
+val data = rows.map { aux }
+
+def compare(i: Int)(e: Array[String], f: Array[String]) = e(i).toInt < f(i).toInt
+
+//day with highest particle pollution (PM_10)
+data.sortWith(compare(1)).last
+
+//day with highest sulfur dioxide (SO_2)
+data.sortWith(compare(2)).last
+
+//day with highest nitro dioxide (NO_2)
+data.sortWith(compare(3)).last
+
+//days with highest PM_10
+val groups = data.groupBy(_(1).toInt)
+val max_key = groups.keySet.max
+groups(max_key)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/while.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,231 @@
+// A parser and evaluator for teh while language
+//
+import matcher._
+import parser._
+
+
+// some regular expressions
+val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
+val DIGIT = RANGE("0123456789")
+val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
+val NUM = PLUS(DIGIT)
+val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false")
+val SEMI: Rexp = ";"
+val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
+val WHITESPACE = PLUS(RANGE(" \n"))
+val RPAREN: Rexp = ")"
+val LPAREN: Rexp = "("
+val BEGIN: Rexp = "{"
+val END: Rexp = "}"
+
+// tokens for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case object T_SEMI extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case object T_BEGIN extends Token
+case object T_END extends Token
+case class T_ID(s: String) extends Token
+case class T_OP(s: String) extends Token
+case class T_NUM(s: String) extends Token
+case class T_KWD(s: String) extends Token
+
+val lexing_rules: List[(Rexp, List[Char] => Token)] =
+ List((KEYWORD, (s) => T_KWD(s.mkString)),
+ (ID, (s) => T_ID(s.mkString)),
+ (OP, (s) => T_OP(s.mkString)),
+ (NUM, (s) => T_NUM(s.mkString)),
+ (SEMI, (s) => T_SEMI),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (BEGIN, (s) => T_BEGIN),
+ (END, (s) => T_END),
+ (WHITESPACE, (s) => T_WHITESPACE))
+
+// the tokenizer
+val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
+
+// the abstract syntax trees
+abstract class Stmt
+abstract class AExp
+abstract class BExp
+type Block = List[Stmt]
+case object Skip extends Stmt
+case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
+case class While(b: BExp, bl: Block) extends Stmt
+case class Assign(s: String, a: AExp) extends Stmt
+
+case class Var(s: String) extends AExp
+case class Num(i: Int) extends AExp
+case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
+
+case object True extends BExp
+case object False extends BExp
+case class Bop(o: String, a1: AExp, a2: AExp) extends BExp
+
+// atomic parsers
+case class TokParser(tok: Token) extends Parser[List[Token], Token] {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((t, ts))
+ case _ => Set ()
+ }
+}
+implicit def token2tparser(t: Token) = TokParser(t)
+
+case object NumParser extends Parser[List[Token], Int] {
+ def parse(ts: List[Token]) = ts match {
+ case T_NUM(s)::ts => Set((s.toInt, ts))
+ case _ => Set ()
+ }
+}
+
+case object IdParser extends Parser[List[Token], String] {
+ def parse(ts: List[Token]) = ts match {
+ case T_ID(s)::ts => Set((s, ts))
+ case _ => Set ()
+ }
+}
+
+
+// arithmetic expressions
+lazy val AExp: Parser[List[Token], AExp] =
+ (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
+ (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
+lazy val T: Parser[List[Token], AExp] =
+ (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
+lazy val F: Parser[List[Token], AExp] =
+ (T_LPAREN ~> AExp <~ T_RPAREN) ||
+ IdParser ==> Var ||
+ NumParser ==> Num
+
+// boolean expressions
+lazy val BExp: Parser[List[Token], BExp] =
+ (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Bop("=", x, z): BExp } ||
+ (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Bop("!=", x, z): BExp } ||
+ (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Bop("<", x, z): BExp } ||
+ (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Bop(">", x, z): BExp } ||
+ (T_KWD("true") ==> ((_) => True)) ||
+ (T_KWD("false") ==> ((_) => False: BExp))
+
+lazy val Stmt: Parser[List[Token], Stmt] =
+ (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
+ (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
+ (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
+ { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
+ (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) }
+
+lazy val Stmts: Parser[List[Token], Block] =
+ (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
+ (Stmt ==> ((s) => List(s) : Block))
+
+lazy val Block: Parser[List[Token], Block] =
+ (T_BEGIN ~> Stmts <~ T_END) ||
+ (Stmt ==> ((s) => List(s)))
+
+
+// examples
+val p1 = "x := 5"
+val p1_toks = Tok.fromString(p1)
+val p1_ast = Block.parse_all(p1_toks)
+println(p1_toks)
+println(p1_ast)
+
+val p1a = "{ x := 5; y := 8}"
+val p1a_toks = Tok.fromString(p1a)
+val p1a_ast = Block.parse_all(p1a_toks)
+println(p1a_ast)
+
+val p2 = "5 = 6"
+val p2_toks = Tok.fromString(p2)
+val p2_ast = BExp.parse_all(p2_toks)
+println(p2_ast)
+
+val p2a = "true"
+val p2a_toks = Tok.fromString(p2a)
+val p2a_ast = BExp.parse_all(p2a_toks)
+println(p2a_ast)
+
+val p3 = "if true then skip else skip"
+val p3_toks = Tok.fromString(p3)
+val p3_ast = Stmt.parse_all(p3_toks)
+println(p3_ast)
+
+val p3a = "if true then x := 5 else x := 10"
+val p3a_toks = Tok.fromString(p3a)
+val p3a_ast = Stmt.parse_all(p3a_toks)
+println(p3a_ast)
+
+val p3b = "if false then x := 5 else x := 10"
+val p3b_toks = Tok.fromString(p3b)
+val p3b_ast = Stmt.parse_all(p3b_toks)
+println(p3b_ast)
+
+// multiplication
+val p4 = """{ x := 5;
+ y := 4;
+ r := 0;
+ while y > 0 do {
+ r := r + x;
+ y := y - 1
+ }
+ }"""
+val p4_toks = Tok.fromString(p4)
+val p4_ast = Block.parse_all(p4_toks)
+println(p4_ast)
+
+val p5 = """
+ n := 9;
+ minus1 := 0;
+ minus2 := 1;
+ temp := 0;
+ while n > 0 do {
+ temp := minus2;
+ minus2 := minus1 + minus2;
+ minus1 := temp;
+ n := n - 1
+ };
+ fib_res := minus2
+"""
+val p5_toks = Tok.fromString(p5)
+val p5_ast = Stmts.parse_all(p5_toks)
+
+// interpreter
+type Env = Map[String, Int]
+
+def eval_bexp(b: BExp, env: Env) : Boolean = b match {
+ case True => true
+ case False => false
+ case Bop("=", a1, a2) => eval_aexp(a1, env) == eval_aexp(a2, env)
+ case Bop("!=", a1, a2) => !(eval_aexp(a1, env) == eval_aexp(a2, env))
+ case Bop(">", a1, a2) => eval_aexp(a1, env) > eval_aexp(a2, env)
+ case Bop("<", a1, a2) => eval_aexp(a1, env) < eval_aexp(a2, env)
+}
+
+def eval_aexp(a: AExp, env : Env) : Int = a match {
+ case Num(i) => i
+ case Var(s) => env(s)
+ case Aop("+", a1, a2) => eval_aexp(a1, env) + eval_aexp(a2, env)
+ case Aop("-", a1, a2) => eval_aexp(a1, env) - eval_aexp(a2, env)
+ case Aop("*", a1, a2) => eval_aexp(a1, env) * eval_aexp(a2, env)
+}
+
+def eval_stmt(s: Stmt, env: Env) : Env = s match {
+ case Skip => env
+ case Assign(x, a) => env + (x -> eval_aexp(a, env))
+ case If(b, bl1, bl2) => if (eval_bexp(b, env)) eval_bl(bl1, env) else eval_bl(bl2, env)
+ case While(b, bl) =>
+ if (eval_bexp(b, env)) eval_stmt(While(b, bl), eval_bl(bl, env))
+ else env
+}
+
+def eval_bl(bl: Block, env: Env) : Env = bl match {
+ case Nil => env
+ case s::bl => eval_bl(bl, eval_stmt(s, env))
+}
+
+//examples
+println(eval_stmt(p3a_ast.head, Map.empty))
+println(eval_stmt(p3b_ast.head, Map.empty))
+println(eval_bl(p4_ast.head, Map.empty))
+println(eval_bl(p5_ast.head, Map.empty))
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/progs/while1.scala Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,220 @@
+// A parser and evaluator for the WHILE language
+//
+import matcher._
+import parser._
+
+
+// some regular expressions
+val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
+val DIGIT = RANGE("0123456789")
+val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
+val NUM = PLUS(DIGIT)
+val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false", "write")
+val SEMI: Rexp = ";"
+val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
+val WHITESPACE = PLUS(RANGE(" \n"))
+val RPAREN: Rexp = ")"
+val LPAREN: Rexp = "("
+val BEGIN: Rexp = "{"
+val END: Rexp = "}"
+val COMMENT = SEQS("/*", NOT(SEQS(STAR(ALLC), "*/", STAR(ALLC))), "*/")
+
+// tokens for classifying the strings that have been recognised
+abstract class Token
+case object T_WHITESPACE extends Token
+case object T_COMMENT extends Token
+case object T_SEMI extends Token
+case object T_LPAREN extends Token
+case object T_RPAREN extends Token
+case object T_BEGIN extends Token
+case object T_END extends Token
+case class T_ID(s: String) extends Token
+case class T_OP(s: String) extends Token
+case class T_NUM(s: String) extends Token
+case class T_KWD(s: String) extends Token
+
+val lexing_rules: List[(Rexp, List[Char] => Token)] =
+ List((KEYWORD, (s) => T_KWD(s.mkString)),
+ (ID, (s) => T_ID(s.mkString)),
+ (OP, (s) => T_OP(s.mkString)),
+ (NUM, (s) => T_NUM(s.mkString)),
+ (SEMI, (s) => T_SEMI),
+ (LPAREN, (s) => T_LPAREN),
+ (RPAREN, (s) => T_RPAREN),
+ (BEGIN, (s) => T_BEGIN),
+ (END, (s) => T_END),
+ (WHITESPACE, (s) => T_WHITESPACE),
+ (COMMENT, (s) => T_COMMENT))
+
+// the tokenizer
+val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE, T_COMMENT))
+
+// the abstract syntax trees
+abstract class Stmt
+abstract class AExp
+abstract class BExp
+type Block = List[Stmt]
+case object Skip extends Stmt
+case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
+case class While(b: BExp, bl: Block) extends Stmt
+case class Assign(s: String, a: AExp) extends Stmt
+case class Write(s: String) extends Stmt
+
+case class Var(s: String) extends AExp
+case class Num(i: Int) extends AExp
+case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
+
+case object True extends BExp
+case object False extends BExp
+case class Bop(o: String, a1: AExp, a2: AExp) extends BExp
+
+// atomic parsers
+case class TokParser(tok: Token) extends Parser[List[Token], Token] {
+ def parse(ts: List[Token]) = ts match {
+ case t::ts if (t == tok) => Set((t, ts))
+ case _ => Set ()
+ }
+}
+implicit def token2tparser(t: Token) = TokParser(t)
+
+case object NumParser extends Parser[List[Token], Int] {
+ def parse(ts: List[Token]) = ts match {
+ case T_NUM(s)::ts => Set((s.toInt, ts))
+ case _ => Set ()
+ }
+}
+
+case object IdParser extends Parser[List[Token], String] {
+ def parse(ts: List[Token]) = ts match {
+ case T_ID(s)::ts => Set((s, ts))
+ case _ => Set ()
+ }
+}
+
+
+// arithmetic expressions
+lazy val AExp: Parser[List[Token], AExp] =
+ (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
+ (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
+lazy val T: Parser[List[Token], AExp] =
+ (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
+lazy val F: Parser[List[Token], AExp] =
+ (T_LPAREN ~> AExp <~ T_RPAREN) ||
+ IdParser ==> Var ||
+ NumParser ==> Num
+
+// boolean expressions
+lazy val BExp: Parser[List[Token], BExp] =
+ (T_KWD("true") ==> ((_) => True: BExp)) ||
+ (T_KWD("false") ==> ((_) => False: BExp)) ||
+ (T_LPAREN ~> BExp <~ T_RPAREN) ||
+ (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Bop("=", x, z): BExp } ||
+ (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Bop("!=", x, z): BExp } ||
+ (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Bop("<", x, z): BExp } ||
+ (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Bop("<", z, x): BExp }
+
+lazy val Stmt: Parser[List[Token], Stmt] =
+ (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
+ (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
+ (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
+ { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
+ (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) } ||
+ (T_KWD("write") ~ IdParser) ==> { case (x, y) => Write(y) }
+
+lazy val Stmts: Parser[List[Token], Block] =
+ (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
+ (Stmt ==> ((s) => List(s) : Block))
+
+lazy val Block: Parser[List[Token], Block] =
+ (T_BEGIN ~> Stmts <~ T_END) ||
+ (Stmt ==> ((s) => List(s)))
+
+// interpreter
+type Env = Map[String, Int]
+
+def eval_bexp(b: BExp, env: Env) : Boolean = b match {
+ case True => true
+ case False => false
+ case Bop("=", a1, a2) => eval_aexp(a1, env) == eval_aexp(a2, env)
+ case Bop("!=", a1, a2) => !(eval_aexp(a1, env) == eval_aexp(a2, env))
+ case Bop("<", a1, a2) => eval_aexp(a1, env) < eval_aexp(a2, env)
+}
+
+def eval_aexp(a: AExp, env : Env) : Int = a match {
+ case Num(i) => i
+ case Var(s) => env(s)
+ case Aop("+", a1, a2) => eval_aexp(a1, env) + eval_aexp(a2, env)
+ case Aop("-", a1, a2) => eval_aexp(a1, env) - eval_aexp(a2, env)
+ case Aop("*", a1, a2) => eval_aexp(a1, env) * eval_aexp(a2, env)
+}
+
+def eval_stmt(s: Stmt, env: Env) : Env = s match {
+ case Skip => env
+ case Assign(x, a) => env + (x -> eval_aexp(a, env))
+ case If(b, bl1, bl2) => if (eval_bexp(b, env)) eval_bl(bl1, env) else eval_bl(bl2, env)
+ case While(b, bl) =>
+ if (eval_bexp(b, env)) eval_stmt(While(b, bl), eval_bl(bl, env))
+ else env
+ case Write(x) => { println(env(x)); env }
+}
+
+def eval_bl(bl: Block, env: Env) : Env = bl match {
+ case Nil => env
+ case s::bl => eval_bl(bl, eval_stmt(s, env))
+}
+
+def eval_prog(name: String) : Env = {
+ val tks = Tok.fromFile(name)
+ val ast = Stmts.parse_single(tks)
+ eval_bl(ast, Map.empty)
+}
+
+
+//examples
+
+//eval_prog("loops.while")
+eval_prog("fib.while")
+
+
+def time_needed[T](i: Int, code: => T) = {
+ val start = System.nanoTime()
+ for (j <- 1 to i) code
+ val end = System.nanoTime()
+ (end - start)/(i * 1.0e9)
+}
+
+
+val test_prog = """
+start := XXX;
+x := start;
+y := start;
+z := start;
+while 0 < x do {
+ while 0 < y do {
+ while 0 < z do {
+ z := z - 1
+ };
+ z := start;
+ y := y - 1
+ };
+ y := start;
+ x := x - 1
+}
+"""
+
+
+
+def eval_test(n: Int) : Unit = {
+ val tks = Tok.fromString(test_prog.replaceAllLiterally("XXX", n.toString))
+ val ast = Stmts.parse_single(tks)
+ println(n + " " + time_needed(2, eval_bl(ast, Map.empty)))
+}
+
+List(1, 200, 400, 600, 800, 1000, 1200, 1400, 1600).map(eval_test(_))
+
+
+
+
+
+
+
Binary file proof.pdf has changed
--- a/proof.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,210 +0,0 @@
-\documentclass{article}
-\usepackage{charter}
-\usepackage{hyperref}
-\usepackage{amssymb}
-\usepackage{amsmath}
-
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-\begin{document}
-
-\section*{Proof}
-
-Recall the definitions for regular expressions and the language associated with a regular expression:
-
-\begin{center}
-\begin{tabular}{c}
-\begin{tabular}[t]{rcl}
- $r$ & $::=$ & $\varnothing$ \\
- & $\mid$ & $\epsilon$ \\
- & $\mid$ & $c$ \\
- & $\mid$ & $r_1 \cdot r_2$ \\
- & $\mid$ & $r_1 + r_2$ \\
- & $\mid$ & $r^*$ \\
- \end{tabular}\hspace{10mm}
-\begin{tabular}[t]{r@{\hspace{1mm}}c@{\hspace{1mm}}l}
-$L(\varnothing)$ & $\dn$ & $\varnothing$ \\
-$L(\epsilon)$ & $\dn$ & $\{\texttt{""}\}$ \\
-$L(c)$ & $\dn$ & $\{\texttt{"}c\texttt{"}\}$ \\
-$L(r_1 \cdot r_2)$ & $\dn$ & $L(r_1) \,@\, L(r_2)$ \\
-$L(r_1 + r_2)$ & $\dn$ & $L(r_1) \cup L(r_2)$ \\
- $L(r^*)$ & $\dn$ & $\bigcup_{n\ge 0} L(r)^n$ \\
- \end{tabular}
-\end{tabular}
-\end{center}
-
-\noindent
-We also defined the notion of a derivative of a regular expression (the derivative with respect to a character):
-
-\begin{center}
-\begin{tabular}{lcl}
- $der\, c\, (\varnothing)$ & $\dn$ & $\varnothing$ \\
- $der\, c\, (\epsilon)$ & $\dn$ & $\varnothing$ \\
- $der\, c\, (d)$ & $\dn$ & if $c = d$ then $\epsilon$ else $\varnothing$\\
- $der\, c\, (r_1 + r_2)$ & $\dn$ & $(der\, c\, r_1) + (der\, c\, r_2)$ \\
- $der\, c\, (r_1 \cdot r_2)$ & $\dn$ & if $nullable(r_1)$\\
- & & then $((der\, c\, r_1) \cdot r_2) + (der\, c\, r_2)$\\
- & & else $(der\, c\, r_1) \cdot r_2$\\
- $der\, c\, (r^*)$ & $\dn$ & $(der\, c\, r) \cdot (r^*)$\\
- \end{tabular}
-\end{center}
-
-\noindent
-With our definition of regular expressions comes an induction principle. Given a property $P$ over
-regular expressions. We can establish that $\forall r.\; P(r)$ holds, provided we can show the following:
-
-\begin{enumerate}
-\item $P(\varnothing)$, $P(\epsilon)$ and $P(c)$ all hold,
-\item $P(r_1 + r_2)$ holds under the induction hypotheses that
-$P(r_1)$ and $P(r_2)$ hold,
-\item $P(r_1 \cdot r_2)$ holds under the induction hypotheses that
-$P(r_1)$ and $P(r_2)$ hold, and
-\item $P(r^*)$ holds under the induction hypothesis that $P(r)$ holds.
-\end{enumerate}
-
-\noindent
-Let us try out an induction proof. Recall the definition
-
-\begin{center}
-$Der\, c\, A \dn \{ s\;\mid\; c\!::\!s \in A\}$
-\end{center}
-
-\noindent
-whereby $A$ is a set of strings. We like to prove
-
-\begin{center}
-\begin{tabular}{l}
-$P(r) \dn $ \hspace{4mm} $L(der\,c\,r) = Der\,c\,(L(r))$
-\end{tabular}
-\end{center}
-
-\noindent
-by induction over the regular expression $r$.
-
-
-\newpage
-\noindent
-{\bf Proof}
-
-\noindent
-According to 1.~above we need to prove $P(\varnothing)$, $P(\epsilon)$ and $P(d)$. Lets do this in turn.
-
-\begin{itemize}
-\item First Case: $P(\varnothing)$ is $L(der\,c\,\varnothing) = Der\,c\,(L(\varnothing))$ (a). We have $der\,c\,\varnothing = \varnothing$
-and $L(\varnothing) = \varnothing$. We also have $Der\,c\,\varnothing = \varnothing$. Hence we have $\varnothing = \varnothing$ in (a).
-
-\item Second Case: $P(\epsilon)$ is $L(der\,c\,\epsilon) = Der\,c\,(L(\epsilon))$ (b). We have $der\,c\,\epsilon = \varnothing$,
-$L(\varnothing) = \varnothing$ and $L(\epsilon) = \{\texttt{""}\}$. We also have $Der\,c\,\{\texttt{""}\} = \varnothing$. Hence we have
-$\varnothing = \varnothing$ in (b).
-
-\item Third Case: $P(d)$ is $L(der\,c\,d) = Der\,c\,(L(d))$ (c). We need to treat the cases $d = c$ and $d \not= c$.
-
-$d = c$: We have $der\,c\,c = \epsilon$ and $L(\epsilon) = \{\texttt{""}\}$.
-We also have $L(c) = \{\texttt{"}c\texttt{"}\}$ and $Der\,c\,\{\texttt{"}c\texttt{"}\} = \{\texttt{""}\}$. Hence we have
-$\{\texttt{""}\} = \{\texttt{""}\}$ in (c).
-
-$d \not=c$: We have $der\,c\,d = \varnothing$.
-We also have $Der\,c\,\{\texttt{"}d\texttt{"}\} = \varnothing$. Hence we have
-$\varnothing = \varnothing$ in (c).
-\end{itemize}
-
-\noindent
-These were the easy base cases. Now come the inductive cases.
-
-\begin{itemize}
-\item Fourth Case: $P(r_1 + r_2)$ is $L(der\,c\,(r_1 + r_2)) = Der\,c\,(L(r_1 + r_2))$ (d). This is what we have to show.
-We can assume already:
-
-\begin{center}
-\begin{tabular}{ll}
-$P(r_1)$: & $L(der\,c\,r_1) = Der\,c\,(L(r_1))$ (I)\\
-$P(r_2)$: & $L(der\,c\,r_2) = Der\,c\,(L(r_2))$ (II)
-\end{tabular}
-\end{center}
-
-We have that $der\,c\,(r_1 + r_2) = (der\,c\,r_1) + (der\,c\,r_2)$ and also $L((der\,c\,r_1) + (der\,c\,r_2)) = L(der\,c\,r_1) \cup L(der\,c\,r_2)$.
-By (I) and (II) we know that the left-hand side is $Der\,c\,(L(r_1)) \cup Der\,c\,(L(r_2))$. You need to ponder a bit, but you should see
-that
-
-\begin{center}
-$Der\,c(A \cup B) = (Der\,c\,A) \cup (Der\,c\,B)$
-\end{center}
-
-holds for every set of strings $A$ and $B$. That means the right-hand side of (d) is also $Der\,c\,(L(r_1)) \cup Der\,c\,(L(r_2))$,
-because $L(r_1 + r_2) = L(r_1) \cup L(r_2)$. And we are done with the fourth case.
-
-\item Fifth Case: $P(r_1 \cdot r_2)$ is $L(der\,c\,(r_1 \cdot r_2)) = Der\,c\,(L(r_1 \cdot r_2))$ (e). We can assume already:
-
-\begin{center}
-\begin{tabular}{ll}
-$P(r_1)$: & $L(der\,c\,r_1) = Der\,c\,(L(r_1))$ (I)\\
-$P(r_2)$: & $L(der\,c\,r_2) = Der\,c\,(L(r_2))$ (II)
-\end{tabular}
-\end{center}
-
-Let us first consider the case where $nullable(r_1)$ holds. Then
-
-\[
-der\,c\,(r_1 \cdot r_2) = ((der\,c\,r_1) \cdot r_2) + (der\,c\,r_2).
-\]
-
-The corresponding language of the right-hand side is
-
-\[
-(L(der\,c\,r_1) \,@\, L(r_2)) \cup L(der\,c\,r_2).
-\]
-
-By the induction hypotheses (I) and (II), this is equal to
-
-\[
-(Der\,c\,(L(r_1)) \,@\, L(r_2)) \cup (Der\,c\,(L(r_2)).\;\;(**)
-\]
-
-We also know that $L(r_1 \cdot r_2) = L(r_1) \,@\,L(r_2)$. We have to know what
-$Der\,c\,(L(r_1) \,@\,L(r_2))$ is.
-
-Let us analyse what
-$Der\,c\,(A \,@\, B)$ is for arbitrary sets of strings $A$ and $B$. If $A$ does \emph{not}
-contain the empty string, then every string in $A\,@\,B$ is of the form $s_1 \,@\, s_2$ where
-$s_1 \in A$ and $s_2 \in B$. So if $s_1$ starts with $c$ then we just have to remove it. Consequently,
-$Der\,c\,(A \,@\, B) = (Der\,c\,(A)) \,@\, B$. This case does not apply here though, because we already
-proved that if $r_1$ is nullable, then $L(r_1)$ contains the empty string. In this case, every string
-in $A\,@\,B$ is either of the form $s_1 \,@\, s_2$, with $s_1 \in A$ and $s_2 \in B$, or
-$s_3$ with $s_3 \in B$. This means $Der\,c\,(A \,@\, B) = ((Der\,c\,(A)) \,@\, B) \cup Der\,c\,B$.
-But this proves that (**) is $Der\,c\,(L(r_1) \,@\, L(r_2))$.
-
-Similarly in the case where $r_1$ is \emph{not} nullable.
-
-\item Sixth Case: $P(r^*)$ is $L(der\,c\,(r^*)) = Der\,c\,L(r^*)$. We can assume already:
-
-\begin{center}
-\begin{tabular}{ll}
-$P(r)$: & $L(der\,c\,r) = Der\,c\,(L(r))$ (I)
-\end{tabular}
-\end{center}
-
-We have $der\,c\,(r^*) = der\,c\,r\cdot r^*$. Which means $L(der\,c\,(r^*)) = L(der\,c\,r\cdot r^*)$ and
-further $L(der\,c\,r) \,@\, L(r^*)$. By induction hypothesis (I) we know that is equal to
-$(Der\,c\,L(r)) \,@\, L(r^*)$. (*)
-
-\end{itemize}
-
-
-
-
-Let us now analyse $Der\,c\,L(r^*)$, which is equal to $Der\,c\,((L(r))^*)$. Now $(L(r))^*$ is defined
-as $\bigcup_{n \ge 0} L(r)$. We can write this as $L(r)^0 \cup \bigcup_{n \ge 1} L(r)$, where we just
-separated the first union and then let the ``big-union'' start from $1$. Form this we can already infer
-
-\begin{center}
-$Der\,c\,(L(r^*)) = Der\,c\,(L(r)^0 \cup \bigcup_{n \ge 1} L(r)) = (Der\,c\,L(r)^0) \cup Der\,c\,(\bigcup_{n \ge 1} L(r))$
-\end{center}
-
-The first union ``disappears'' since $Der\,c\,(L(r)^0) = \varnothing$.
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
--- a/re-internal.rb Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,22 +0,0 @@
-# provided by Daniel Baldwin
-
-nums = (1..100)
-
-#iterate through the nums 1-100
-nums.each do |i|
-
- start_time = Time.now
- string = "a" * i
-
- #create a new regular expression based on current value of i
- re = Regexp.new(/((a?){#{i}})(a{#{i}})/)
-
- re.match(string)
- #if re.match(string)
- # puts "matched string a * #{i} with regex #{re}"
- #else
- # puts "unmatched string a * #{i} with regex #{re}"
- #end
-
- puts "#{i} %.5f" % (Time.now - start_time)
-end
--- a/re.py Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,12 +0,0 @@
-#!/usr/bin/env python
-import re
-import sys
-
-cn = sys.argv[1]
-
-r1 = '((a?){%s})' % cn
-r2 = 'a{%s}' % cn
-
-m = re.match(r1 + r2 , "a" * int(cn))
-
-print m.group(0)
--- a/scala/S_grammar-token.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,47 +0,0 @@
-//:load matcher.scala
-//:load parser3.scala
-
-abstract class Token
-case object T_ONE extends Token
-
-val lexing_rules : List[Rule[Token]] =
- List(("1", (s: List[Char]) => T_ONE))
-
-val T = Tokenizer(lexing_rules)
-
-case class TokParser(tok: Token) extends Parser[List[Token], Token] {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((t, ts))
- case _ => Set ()
- }
-}
-implicit def token2tokparser(t: Token) = TokParser(t)
-
-case object EmpParser extends Parser[List[Token], String] {
- def parse(ts: List[Token]) = Set(("", ts))
-}
-
-
-lazy val Su: Parser[List[Token], String] =
- (T_ONE ~ Su) ==> { case (x, y) => "1" + y} || EmpParser
-
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-def test(i: Int) = {
- val result = Su.parse_all(T.fromString("1" * i))
- //print(result.size + " ")
-}
-
-
-for (i <- 1 to 1000 by 50) {
- print(i + " ")
- print("%.5f".format(time_needed(1, test(i))))
- print("\n")
-}
-
--- a/scala/S_grammar.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,52 +0,0 @@
-//:load parser3.scala
-
-case class StringParser(s: String) extends Parser[String, String] {
- def parse(ts: String) = {
- if (s.length <= ts.length && ts.startsWith(s)) Set((s, ts.drop(s.length)))
- else Set()
- }
-}
-
-implicit def string2parser(s: String) = StringParser(s)
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-// unambiguous grammar
-
-lazy val U: Parser[String, String] =
- ("1" ~ U) ==> { case (x, y) => "1" + y} || ""
-
-def test1(i: Int) = {
- val result = U.parse_all("1" * i)
- //print(result.size + " ")
-}
-
-for (i <- 1 to 1000 by 50) {
- print(i + " ")
- print("%.5f".format(time_needed(1, test1(i))))
- print("\n")
-}
-
-
-
-// ambiguous grammar
-// n = 16 -> over 35 million parse trees
-
-lazy val S: Parser[String, String] =
- ("1" ~ S ~ S) ==> { case ((x, y), z) => "1" + y + z} || ""
-
-def test2(i: Int) = {
- val result = S.parse_all("1" * i)
- print(result.size + " ")
-}
-
-for (i <- 1 to 30) {
- print(i + " ")
- print("%.5f".format(time_needed(1, test2(i))))
- print("\n")
-}
--- a/scala/Term_grammar.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,62 +0,0 @@
-//:load matcher.scala
-//:load parser3.scala
-
-// some regular expressions
-val LETTER = RANGE("abcdefghijklmnopqrstuvwxyz")
-val ID = PLUS(LETTER)
-
-val DIGIT = RANGE("0123456789")
-val NONZERODIGIT = RANGE("123456789")
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-
-val LPAREN = CHAR('(')
-val RPAREN = CHAR(')')
-
-val WHITESPACE = PLUS(RANGE(" \n"))
-val OPS = RANGE("+-*")
-
-// for classifying the strings that have been lexed
-abstract class Token
-
-case object T_WHITESPACE extends Token
-case class T_NUM(s: String) extends Token
-case class T_OP(s: String) extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-
-
-// lexing rules for arithmetic expressions
-val lexing_rules: List[Rule[Token]]=
- List((NUMBER, (s) => T_NUM(s.mkString)),
- (WHITESPACE, (s) => T_WHITESPACE),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (OPS, (s) => T_OP(s.mkString)))
-
-val Tk = Tokenizer(lexing_rules, List(T_WHITESPACE))
-
-
-case class TokParser(tok: Token) extends Parser[List[Token], Token] {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((t, ts))
- case _ => Set ()
- }
-}
-implicit def token2tparser(t: Token) = TokParser(t)
-
-case object NumParser extends Parser[List[Token], Int] {
- def parse(ts: List[Token]) = ts match {
- case T_NUM(s)::ts => Set((s.toInt, ts))
- case _ => Set ()
- }
-}
-
-lazy val E: Parser[List[Token], Int] = (T ~ T_OP("+") ~ E) ==> { case ((x, y), z) => x + z } || T
-lazy val T: Parser[List[Token], Int] = (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => x * z } || F
-lazy val F: Parser[List[Token], Int] = (T_LPAREN ~> E <~ T_RPAREN) || NumParser
-
-println(E.parse_all(Tk.fromString("1 + 2 + 3")))
-println(E.parse_all(Tk.fromString("1 + 2 * 3")))
-println(E.parse_all(Tk.fromString("(1 + 2) * 3")))
-println(E.parse_all(Tk.fromString("(14 + 2) * (3 + 2)")))
-
--- a/scala/app0.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,6 +0,0 @@
-import io.Source
-
-def get_page(url: String) : String = {
- Source.fromURL(url).take(10000).mkString
-
-
--- a/scala/app1.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,12 +0,0 @@
-def get_page(url: String) : String = {
- try {
- Source.fromURL(url).take(10000).mkString
- }
- catch {
- case e => {
- println(" Problem with: " + url)
- ""
- }
- }
-}
-
--- a/scala/app2.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,16 +0,0 @@
-val http_pattern = """\"https?://[^\"]*\"""".r
-
-def unquote(s: String) = s.drop(1).dropRight(1)
-
-def get_all_URLs(page: String) : Set[String] = {
- (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
-}
-
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- else {
- println("Visiting: " + n + " " + url)
- for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
- }
-}
-
--- a/scala/app3.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,10 +0,0 @@
-val my_urls = """urbanc""".r
-
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- else if (my_urls.findFirstIn(url) == None) ()
- else {
- println("Visiting: " + n + " " + url)
- for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
- }
-}
--- a/scala/app4.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,14 +0,0 @@
-val http_pattern = """\"https?://[^\"]*\"""".r
-val my_urls = """urbanc""".r
-val email_pattern =
- """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
-
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- else {
- println("Visiting: " + n + " " + url)
- val page = get_page(url)
- println(email_pattern.findAllIn(page).mkString("\n"))
- for (u <- get_all_URLs(page)) crawl(u, n - 1)
- }
-}
--- a/scala/app5.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,8 +0,0 @@
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
-}
--- a/scala/app51.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,8 +0,0 @@
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
--- a/scala/app6.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,11 +0,0 @@
-def deriv (r: Rexp, c: Char) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(deriv(r1, c), deriv(r2, c))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(deriv(r1, c), r2), deriv(r2, c))
- else SEQ(deriv(r1, c), r2)
- case STAR(r) => SEQ(deriv(r, c), STAR(r))
-}
-
--- a/scala/app7.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,16 +0,0 @@
-abstract class Parser[I, T] {
- def parse(ts: I): Set[(T, I)]
-
- def parse_all(ts: I) : Set[T] =
- for ((head, tail) <- parse(ts); if (tail.isEmpty))
- yield head
-
- def || (right : => Parser[I, T]) : Parser[I, T] =
- new AltParser(this, right)
- def ==>[S] (f: => T => S) : Parser [I, S] =
- new FunParser(this, f)
- def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] =
- new SeqParser(this, right)
-}
-
-
--- a/scala/app8.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,23 +0,0 @@
-class SeqParser[I, T, S](p: => Parser[I, T],
- q: => Parser[I, S])
- extends Parser[I, (T, S)] {
- def parse(sb: I) =
- for ((head1, tail1) <- p.parse(sb);
- (head2, tail2) <- q.parse(tail1))
- yield ((head1, head2), tail2)
-}
-
-class AltParser[I, T](p: => Parser[I, T],
- q: => Parser[I, T])
- extends Parser[I, T] {
- def parse(sb: I) = p.parse(sb) ++ q.parse(sb)
-}
-
-class FunParser[I, T, S](p: => Parser[I, T], f: T => S)
- extends Parser[I, S] {
- def parse(sb: I) =
- for ((head, tail) <- p.parse(sb))
- yield (f(head), tail)
-}
-
-
--- a/scala/automata.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,106 +0,0 @@
-
-// a class for deterministic finite automata,
-// the type of states is kept polymorphic
-
-case class Automaton[A](start: A, states: Set[A], delta: Map[(A, Char), A], fins: Set[A]) {
-
- // the transition function lifted to list of characters
- def deltas(q: A, cs: List[Char]) : Either[A, String] =
- if (states.contains(q)) cs match {
- case Nil => Left(q)
- case c::cs =>
- if (delta.isDefinedAt(q, c)) deltas(delta(q, c), cs)
- else Right(q + " does not have a transition for " + c)
- }
- else Right(q + " is not a state of the automaton")
-
- // wether a string is accepted by the automaton
- def accepts(s: String) = deltas(start, s.toList) match {
- case Left(q) => fins.contains(q)
- case _ => false
- }
-}
-
-
-// translating a regular expression into a finite
-// automaton
-
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-
-implicit def string2rexp(s : String) = {
- def chars2rexp (cs: List[Char]) : Rexp = cs match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::cs => SEQ(CHAR(c), chars2rexp(cs))
- }
- chars2rexp(s.toList)
-}
-
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
-}
-
-def der (r: Rexp, c: Char) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(r1, c), der(r2, c))
- case SEQ(r1, r2) => if (nullable(r1)) ALT(SEQ(der(r1, c), r2), der(r2, c))
- else SEQ(der(r1, c), r2)
- case STAR(r) => SEQ(der(r, c), STAR(r))
-}
-
-
-// Here we construct an automaton whose
-// states are regular expressions
-type State = Rexp
-type States = Set[State]
-type Transition = Map[(State, Char), State]
-
-// we use as an alphabet all lowercase letters
-val alphabet = "abcdefghijklmnopqrstuvwxyz".toSet
-
-def goto(q: State, c: Char, qs: States, delta: Transition) : (States, Transition) = {
- val q_der : State = der(q, c)
- if (qs.contains(q_der)) (qs, delta + ((q, c) -> q))
- else explore(qs + q_der, delta + ((q, c) -> q_der), q_der)
-}
-
-def explore (qs: States, delta: Transition, q: State) : (States, Transition) =
- alphabet.foldRight[(States, Transition)] (qs, delta) ((c, qsd) => goto(q, c, qsd._1, qsd._2))
-
-
-def mk_automaton (r: Rexp) : Automaton[Rexp] = {
- val (qs, delta) = explore(Set(r), Map(), r);
- val fins = for (q <- qs if nullable(q)) yield q;
- Automaton[Rexp](r, qs, delta, fins)
-}
-
-val A = mk_automaton(ALT("ab","ac"))
-
-A.start
-A.states.toList.length
-
-println(A.accepts("bd"))
-println(A.accepts("ab"))
-println(A.accepts("ac"))
-
-val r1 = STAR(ALT("a","b"))
-val r2 = SEQ("b","b")
-val r3 = SEQ(SEQ(SEQ(r1, r2), r1), "a")
-val B = mk_automaton(r3)
-
-B.start
-B.states.toList.length
--- a/scala/automata1.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,95 +0,0 @@
-
-// a class for deterministic finite automata,
-// the type of states is kept polymorphic
-
-case class Automaton[A](start: A, states: Set[A], delta: Map[(A, Char), A], fins: Set[A]) {
-
- // the transition function lifted to list of characters
- def deltas(q: A, cs: List[Char]) : A =
- if (states.contains(q)) cs match {
- case Nil => q
- case c::cs =>
- if (delta.isDefinedAt(q, c)) deltas(delta(q, c), cs)
- else throw new RuntimeException(q + " does not have a transition for " + c)
- }
- else throw new RuntimeException(q + " is not a state of the automaton")
-
- // wether a string is accepted by the automaton
- def accepts(s: String) =
- try {
- fins.contains(deltas(start, s.toList))
- } catch {
- case e:RuntimeException => false
- }
-}
-
-
-
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-
-implicit def string2rexp(s : String) = {
- def chars2rexp (cs: List[Char]) : Rexp = cs match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::cs => SEQ(CHAR(c), chars2rexp(cs))
- }
- chars2rexp(s.toList)
-}
-
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
-}
-
-def der (r: Rexp, c: Char) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(r1, c), der(r2, c))
- case SEQ(r1, r2) => if (nullable(r1)) ALT(SEQ(der(r1, c), r2), der(r2, c))
- else SEQ(der(r1, c), r2)
- case STAR(r) => SEQ(der(r, c), STAR(r))
-}
-
-
-// Here we construct an automaton whose
-// states are regular expressions
-type State = Rexp
-type States = Set[State]
-type Transition = Map[(State, Char), State]
-
-def goto(q: State, c: Char, qs: States, delta: Transition) : (States, Transition) = {
- val qc : State = der(q, c)
- if (qs.contains(qc)) (qs, delta + ((q, c) -> q))
- else explore(qs + qc, delta + ((q, c) -> qc), qc)
-}
-
-// we use as alphabet all lowercase letters
-val alphabet = "abcdefghijklmnopqrstuvwxyz".toSet
-
-def explore (qs: States, delta: Transition, q: State) : (States, Transition) =
- alphabet.foldRight[(States, Transition)] (qs, delta) ((c, qsd) => goto(q, c, qsd._1, qsd._2))
-
-
-def mk_automaton (r: Rexp) : Automaton[Rexp] = {
- val (qs, delta) = explore(Set(r), Map(), r);
- val fins = for (q <- qs if nullable(q)) yield q;
- Automaton[Rexp](r, qs, delta, fins)
-}
-
-val A = mk_automaton(ALT("ab","ac"))
-
-println(A.accepts("bd"))
-println(A.accepts("ab"))
-println(A.accepts("ac"))
--- a/scala/compile.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,326 +0,0 @@
-// A parser and evaluator for teh while language
-//
-import matcher._
-import parser._
-
-// some regular expressions
-val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
-val DIGIT = RANGE("0123456789")
-val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
-val NUM = PLUS(DIGIT)
-val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false", "write")
-val SEMI: Rexp = ";"
-val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
-val WHITESPACE = PLUS(RANGE(" \n"))
-val RPAREN: Rexp = ")"
-val LPAREN: Rexp = "("
-val BEGIN: Rexp = "{"
-val END: Rexp = "}"
-val COMMENT = SEQS("/*", NOT(SEQS(STAR(ALLC), "*/", STAR(ALLC))), "*/")
-
-// tokens for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case object T_COMMENT extends Token
-case object T_SEMI extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case object T_BEGIN extends Token
-case object T_END extends Token
-case class T_ID(s: String) extends Token
-case class T_OP(s: String) extends Token
-case class T_NUM(s: String) extends Token
-case class T_KWD(s: String) extends Token
-
-val lexing_rules: List[(Rexp, List[Char] => Token)] =
- List((KEYWORD, (s) => T_KWD(s.mkString)),
- (ID, (s) => T_ID(s.mkString)),
- (OP, (s) => T_OP(s.mkString)),
- (NUM, (s) => T_NUM(s.mkString)),
- (SEMI, (s) => T_SEMI),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (BEGIN, (s) => T_BEGIN),
- (END, (s) => T_END),
- (WHITESPACE, (s) => T_WHITESPACE),
- (COMMENT, (s) => T_COMMENT))
-
-// the tokenizer
-val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE, T_COMMENT))
-
-// the abstract syntax trees
-abstract class Stmt
-abstract class AExp
-abstract class BExp
-type Block = List[Stmt]
-case object Skip extends Stmt
-case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
-case class While(b: BExp, bl: Block) extends Stmt
-case class Assign(s: String, a: AExp) extends Stmt
-case class Write(s: String) extends Stmt
-
-case class Var(s: String) extends AExp
-case class Num(i: Int) extends AExp
-case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
-
-case object True extends BExp
-case object False extends BExp
-case class Relop(o: String, a1: AExp, a2: AExp) extends BExp
-
-// atomic parsers
-case class TokParser(tok: Token) extends Parser[List[Token], Token] {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((t, ts))
- case _ => Set ()
- }
-}
-implicit def token2tparser(t: Token) = TokParser(t)
-
-case object NumParser extends Parser[List[Token], Int] {
- def parse(ts: List[Token]) = ts match {
- case T_NUM(s)::ts => Set((s.toInt, ts))
- case _ => Set ()
- }
-}
-
-case object IdParser extends Parser[List[Token], String] {
- def parse(ts: List[Token]) = ts match {
- case T_ID(s)::ts => Set((s, ts))
- case _ => Set ()
- }
-}
-
-
-// arithmetic expressions
-lazy val AExp: Parser[List[Token], AExp] =
- (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
- (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
-lazy val T: Parser[List[Token], AExp] =
- (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
-lazy val F: Parser[List[Token], AExp] =
- (T_LPAREN ~> AExp <~ T_RPAREN) ||
- IdParser ==> Var ||
- NumParser ==> Num
-
-// boolean expressions
-lazy val BExp: Parser[List[Token], BExp] =
- (T_KWD("true") ==> ((_) => True: BExp)) ||
- (T_KWD("false") ==> ((_) => False: BExp)) ||
- (T_LPAREN ~> BExp <~ T_RPAREN) ||
- (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Relop("=", x, z): BExp } ||
- (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Relop("!=", x, z): BExp } ||
- (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Relop("<", x, z): BExp } ||
- (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Relop("<", z, x): BExp }
-
-lazy val Stmt: Parser[List[Token], Stmt] =
- (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
- (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
- (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
- { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
- (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) } ||
- (T_KWD("write") ~ IdParser) ==> { case (x, y) => Write(y) }
-
-lazy val Stmts: Parser[List[Token], Block] =
- (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
- (Stmt ==> ((s) => List(s) : Block))
-
-lazy val Block: Parser[List[Token], Block] =
- (T_BEGIN ~> Stmts <~ T_END) ||
- (Stmt ==> ((s) => List(s)))
-
-// compiler
-val beginning = """
-.class public XXX.XXX
-.super java/lang/Object
-
-.method public <init>()V
- aload_0
- invokenonvirtual java/lang/Object/<init>()V
- return
-.end method
-
-.method public static write(I)V
- .limit locals 5
- .limit stack 5
- iload 0
- getstatic java/lang/System/out Ljava/io/PrintStream;
- swap
- invokevirtual java/io/PrintStream/println(I)V
- return
-.end method
-
-
-.method public static main([Ljava/lang/String;)V
- .limit locals 200
- .limit stack 200
-
-"""
-
-val ending = """
-
- return
-
-.end method
-"""
-
-// for generating new labels
-var counter = -1
-
-def Fresh(x: String) = {
- counter += 1
- x ++ "_" ++ counter.toString()
-}
-
-type Env = Map[String, String]
-type Instrs = List[String]
-
-def compile_aexp(a: AExp, env : Env) : Instrs = a match {
- case Num(i) => List("ldc " + i.toString + "\n")
- case Var(s) => List("iload " + env(s) + "\n")
- case Aop("+", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("iadd\n")
- case Aop("-", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("isub\n")
- case Aop("*", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("imul\n")
-}
-
-def compile_bexp(b: BExp, env : Env, jmp: String) : Instrs = b match {
- case True => Nil
- case False => List("goto " + jmp + "\n")
- case Relop("=", a1, a2) =>
- compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpne " + jmp + "\n")
- case Relop("!=", a1, a2) =>
- compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpeq " + jmp + "\n")
- case Relop("<", a1, a2) =>
- compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpge " + jmp + "\n")
-}
-
-
-def compile_stmt(s: Stmt, env: Env) : (Instrs, Env) = s match {
- case Skip => (Nil, env)
- case Assign(x, a) => {
- val index = if (env.isDefinedAt(x)) env(x) else env.keys.size.toString
- (compile_aexp(a, env) ++
- List("istore " + index + "\n"), env + (x -> index))
- }
- case If(b, bl1, bl2) => {
- val if_else = Fresh("If_else")
- val if_end = Fresh("If_end")
- val (instrs1, env1) = compile_bl(bl1, env)
- val (instrs2, env2) = compile_bl(bl2, env1)
- (compile_bexp(b, env, if_else) ++
- instrs1 ++
- List("goto " + if_end + "\n") ++
- List("\n" + if_else + ":\n\n") ++
- instrs2 ++
- List("\n" + if_end + ":\n\n"), env2)
- }
- case While(b, bl) => {
- val loop_begin = Fresh("Loop_begin")
- val loop_end = Fresh("Loop_end")
- val (instrs1, env1) = compile_bl(bl, env)
- (List("\n" + loop_begin + ":\n\n") ++
- compile_bexp(b, env, loop_end) ++
- instrs1 ++
- List("goto " + loop_begin + "\n") ++
- List("\n" + loop_end + ":\n\n"), env1)
- }
- case Write(x) =>
- (List("iload " + env(x) + "\n" + "invokestatic XXX/XXX/write(I)V\n"), env)
-}
-
-def compile_bl(bl: Block, env: Env) : (Instrs, Env) = bl match {
- case Nil => (Nil, env)
- case s::bl => {
- val (instrs1, env1) = compile_stmt(s, env)
- val (instrs2, env2) = compile_bl(bl, env1)
- (instrs1 ++ instrs2, env2)
- }
-}
-
-def compile(input: String) : String = {
- val class_name = input.split('.')(0)
- val tks = Tok.fromFile(input)
- val ast = Stmts.parse_single(tks)
- val instructions = compile_bl(ast, Map.empty)._1
- (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
-}
-
-
-def compile_to(input: String, output: String) = {
- val fw = new java.io.FileWriter(output)
- fw.write(compile(input))
- fw.close()
-}
-
-//
-val tks = Tok.fromString("x := x + 1")
-val ast = Stmt.parse_single(tks)
-println(compile_stmt(ast, Map("x" -> "n"))._1.mkString)
-
-
-
-//examples
-
-compile_to("loops.while", "loops.j")
-//compile_to("fib.while", "fib.j")
-
-
-// testing cases for time measurements
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-// for testing
-import scala.sys.process._
-
-val test_prog = """
-start := XXX;
-x := start;
-y := start;
-z := start;
-while 0 < x do {
- while 0 < y do {
- while 0 < z do {
- z := z - 1
- };
- z := start;
- y := y - 1
- };
- y := start;
- x := x - 1
-};
-write x;
-write y;
-write z
-"""
-
-
-def compile_test(n: Int) : Unit = {
- val class_name = "LOOP"
- val tks = Tok.fromString(test_prog.replaceAllLiterally("XXX", n.toString))
- val ast = Stmts.parse_single(tks)
- val instructions = compile_bl(ast, Map.empty)._1
- val assembly = (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
- val fw = new java.io.FileWriter(class_name + ".j")
- fw.write(assembly)
- fw.close()
- val test = ("java -jar jvm/jasmin-2.4/jasmin.jar " + class_name + ".j").!!
- println(n + " " + time_needed(2, ("java " + class_name + "/" + class_name).!!))
-}
-
-List(1, 5000, 10000, 50000, 100000, 250000, 500000, 750000, 1000000).map(compile_test(_))
-
-
-
-// Javabyte code assmbler
-//
-// java -jar jvm/jasmin-2.4/jasmin.jar loops.j
-
-
-
-
-
-
--- a/scala/crawler.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,144 +0,0 @@
-import io.Source
-import scala.util.matching.Regex
-
-// gets the first ~10K of a page
-def get_page(url: String) : String = {
- try {
- Source.fromURL(url).take(10000).mkString
- }
- catch {
- case e => {
- println(" Problem with: " + url)
- ""
- }
- }
-}
-
-// non-existing page -> returns the empty string
-get_page("""http://www.foobar.com""")
-
-
-// staring URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
-
-// starts with an "
-// then either http or https
-// then ://
-// then any character that is not "
-// finally "
-val http_pattern = """\"((?:http|https)://(?:[^\"])*)\"""".r
-val http_pattern = """\"(https?://[^\"]*)\"""".r
-
-def unquote(s: String) = s.drop(1).dropRight(1)
-
-def get_all_URLs(page: String) : Set[String] = {
- (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
-}
-
-// get all urls in startURL
-get_all_URLs(get_page(startURL))
-
-// number of all urls in startURL
-get_all_URLs(get_page(startURL)).toList.length
-
-
-// naive version - seraches until a given depth
-// visits pages potentially more than once
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- else {
- println("Visiting: " + n + " " + url)
- for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
- }
-}
-
-crawl(startURL, 2)
-
-
-//breadth-first version without visiting
-//pages twice
-def bf_crawl(todo: Set[String], visited: Set[String], n: Int) : Unit = {
- if (n == 0) ()
- else {
- val new_todo = todo.flatMap {
- url => {
- if (visited.contains(url)) Set[String]()
- else {
- println("Visiting: " + n + " " + url)
- get_all_URLs(get_page(url))
- }
- }
- }
- bf_crawl(new_todo, visited union todo, n - 1)
- }
-}
-
-bf_crawl(Set(startURL1), Set(), 2)
-
-
-//breadth-first version without visiting
-//pages twice and only in "my" domain
-val my_pattern = """urbanc""".r
-
-// breadth first search avoiding double searches
-def bf_crawl2(todo: Set[String], visited: Set[String], n: Int) : Unit = {
- if (n == 0) ()
- else {
- val new_todo = todo.flatMap {
- url => {
- if (visited.contains(url)) Set[String]()
- else if (my_pattern.findFirstIn(url) == None) Set[String]()
- else {
- println("Visiting: " + n + " " + url);
- get_all_URLs(get_page(url))
- }
- }
- }
- bf_crawl2(new_todo, visited union todo, n - 1)
- }
-}
-
-bf_crawl2(Set(startURL1), Set(), 5)
-
-// email harvester
-// from
-// http://net.tutsplus.com/tutorials/other/8-regular-expressions-you-should-know/
-
-val email_pattern = """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
-
-def bf_crawl3(todo: Set[String], visited: Set[String], n: Int) : Unit = {
- if (n == 0) ()
- else {
- val new_todo = todo.flatMap {
- url => {
- if (visited.contains(url)) Set[String]()
- else {
- println("Visiting: " + n + " " + url);
- val page = get_page(url)
- println(email_pattern.findAllIn(page).mkString("\n"))
- get_all_URLs(get_page(url))
- }
- }
- }
- bf_crawl3(new_todo, visited union todo, n - 1)
- }
-}
-
-bf_crawl3(Set(startURL1), Set(), 3)
-
-
-// depth-first version does not work,
-// because it might visit pages at depth 1
-// while it still wants to visit them at
-// depth 2
-var visited = Set("")
-
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- else if (visited.contains(url)) () //println("Already visited: " + n + " " + url)
- else {
- println("Visiting: " + n + " " + url);
- visited += url
- for (u <- getAllURLs(getURLpage(url))) crawl(u, n - 1);
- }
-}
--- a/scala/crawler1.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,45 +0,0 @@
-import io.Source
-import scala.util.matching.Regex
-
-// gets the first ~10K of a page
-def get_page(url: String) : String = {
- try {
- Source.fromURL(url).take(10000).mkString
- }
- catch {
- case e => {
- println(" Problem with: " + url)
- ""
- }
- }
-}
-
-
-// regex for URLs
-val http_pattern = """\"https?://[^\"]*\"""".r
-
-def unquote(s: String) = s.drop(1).dropRight(1)
-
-def get_all_URLs(page: String) : Set[String] = {
- (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
-}
-
-// naive version - seraches until a given depth
-// visits pages potentially more than once
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- else {
- println("Visiting: " + n + " " + url)
- for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
- }
-}
-
-// staring URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
-//val startURL = """http://www.inf.kcl.ac.uk/staff/mml/"""
-
-
-// call on the command line
-crawl(startURL, 2)
-
-crawl("""http://www.dcs.kcl.ac.uk/staff/urbanc/msc-projects-12.html""", 2)
--- a/scala/crawler2.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,44 +0,0 @@
-import io.Source
-import scala.util.matching.Regex
-
-// gets the first ~10K of a page
-def get_page(url: String) : String = {
- try {
- Source.fromURL(url).take(10000).mkString
- }
- catch {
- case e => {
- println(" Problem with: " + url)
- ""
- }
- }
-}
-
-// staring URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
-
-// regex for URLs
-val http_pattern = """\"https?://[^\"]*\"""".r
-val my_urls = """urbanc""".r
-
-def unquote(s: String) = s.drop(1).dropRight(1)
-
-def get_all_URLs(page: String) : Set[String] = {
- (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
-}
-
-// naive version - seraches until a given depth
-// visits pages potentially more than once
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- else if (my_urls.findFirstIn(url) == None) ()
- else {
- println("Visiting: " + n + " " + url)
- for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
- }
-}
-
-// can now deal with depth 3
-// start on command line
-crawl(startURL, 4)
-
--- a/scala/crawler3.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,49 +0,0 @@
-import io.Source
-import scala.util.matching.Regex
-
-// gets the first ~10K of a page
-def get_page(url: String) : String = {
- try {
- Source.fromURL(url).take(10000).mkString
- }
- catch {
- case e => {
- println(" Problem with: " + url)
- ""
- }
- }
-}
-
-// staring URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
-
-// regex for URLs
-val http_pattern = """\"https?://[^\"]*\"""".r
-val my_urls = """urbanc""".r
-val email_pattern = """([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z\.]{2,6})""".r
-
-// http://net.tutsplus.com/tutorials/other/8-regular-expressions-you-should-know/
-
-def unquote(s: String) = s.drop(1).dropRight(1)
-
-def get_all_URLs(page: String) : Set[String] = {
- (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
-}
-
-// naive version - seraches until a given depth
-// visits pages potentially more than once
-def crawl(url: String, n: Int) : Unit = {
- if (n == 0) ()
- //else if (my_urls.findFirstIn(url) == None) ()
- else {
- println("Visiting: " + n + " " + url)
- val page = get_page(url)
- println(email_pattern.findAllIn(page).mkString("\n"))
- for (u <- get_all_URLs(page)) crawl(u, n - 1)
- }
-}
-
-// can now deal with depth 3
-// start on command line
-crawl(startURL, 3)
-
--- a/scala/html.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,99 +0,0 @@
-
-//:load matcher.scala
-
-// some regular expressions
-val SYM = RANGE("""ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz.,!?-{[()]}':;%0123456789""")
-val WORD = PLUS(SYM)
-
-val BTAG = SEQS("<", WORD, ">")
-val ETAG = SEQS("</", WORD, ">")
-
-val WHITESPACE = PLUS(RANGE(" \n"))
-
-// for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case class T_WORD(s: String) extends Token
-case class T_ETAG(s: String) extends Token
-case class T_BTAG(s: String) extends Token
-case class T_NT(s: String, rhs: List[Token]) extends Token
-
-val lexing_rules: List[Rule[Token]] =
- List((BTAG, (s) => T_BTAG(s.mkString)),
- (ETAG, (s) => T_ETAG(s.mkString)),
- (WORD, (s) => T_WORD(s.mkString)),
- (WHITESPACE, (s) => T_WHITESPACE))
-
-// the tokenizer
-val T = Tokenizer(lexing_rules)
-
-// width for printing
-val WIDTH = 60
-
-
-def interpret(ts: List[Token], c: Int, ctr: List[String]) : Unit= ts match {
- case Nil => println(Console.RESET)
- case T_WHITESPACE::rest => print(Console.RESET + " "); interpret(rest, c + 1, ctr)
- case T_WORD(s)::rest => {
- val newstr = Console.RESET + ctr.reverse.mkString + s
- if (c + s.length < WIDTH) {
- print(newstr);
- interpret(rest, c + s.length, ctr)
- }
- else {
- print("\n" + newstr)
- interpret(rest, s.length, ctr)
- }
- }
- case T_BTAG("<p>")::rest => print("\n"); interpret(rest, 0, ctr)
- case T_ETAG("</p>")::rest => print("\n"); interpret(rest, 0, ctr)
- case T_BTAG("<b>")::rest => interpret(rest, c, Console.BOLD :: ctr)
- case T_BTAG("<a>")::rest => interpret(rest, c, Console.UNDERLINED :: ctr)
- case T_BTAG("<cyan>")::rest => interpret(rest, c, Console.CYAN :: ctr)
- case T_BTAG("<red>")::rest => interpret(rest, c, Console.RED :: ctr)
- case T_BTAG("<blink>")::rest => interpret(rest, c, Console.BLINK :: ctr)
- case T_ETAG(_)::rest => interpret(rest, c, ctr.tail)
- case _::rest => interpret(rest, c, ctr)
-}
-
-val test_string = """
-<b>MSc Projects</b>
-
-<p>
-start of paragraph. <cyan> a <red>cyan</red> word</cyan> normal again something longer.
-</p>
-
-
- <p><b>Description:</b>
- <a>Regular expressions</a> are extremely useful for many text-processing tasks such as finding patterns in texts,
- lexing programs, syntax highlighting and so on. Given that regular expressions were
- introduced in 1950 by <a>Stephen Kleene</a>, you might think
- regular expressions have since been studied and implemented to death. But you would definitely be mistaken: in fact they are still
- an active research area. For example
- <a>this paper</a>
- about regular expression matching and partial derivatives was presented this summer at the international
- PPDP'12 conference. The task in this project is to implement the results from this paper.</p>
-
- <p>The background for this project is that some regular expressions are
- <a>evil</a>
- and can stab you in the back; according to
- this <a>blog post</a>.
- For example, if you use in <a>Python</a> or
- in <a>Ruby</a> (probably also in other mainstream programming languages) the
- innocently looking regular expression a?{28}a{28} and match it, say, against the string
- <red>aaaaaaaaaa<cyan>aaaaaaa</cyan>aaaaaaaaaaa</red> (that is 28 as), you will soon notice that your CPU usage goes to 100%. In fact,
- Python and Ruby need approximately 30 seconds of hard work for matching this string. You can try it for yourself:
- <a>re.py</a> (Python version) and
- <a>re.rb</a>
- (Ruby version). You can imagine an attacker
- mounting a nice <a>DoS attack</a> against
- your program if it contains such an evil regular expression. Actually
- <a>Scala</a> (and also Java) are almost immune from such
- attacks as they can deal with strings of up to 4,300 as in less than a second. But if you scale
- the regular expression and string further to, say, 4,600 as, then you get a
- StackOverflowError
- potentially crashing your program.
- </p>
-"""
-
-interpret(T.fromString(test_string), 0, Nil)
--- a/scala/html1.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,75 +0,0 @@
-
-
-//:load matcher.scala
-
-
-// some regular expressions
-val LETTER = RANGE("""ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz.,!?-{[()]}':;%""")
-val DIGIT = RANGE("0123456789")
-val NONZERODIGIT = RANGE("123456789")
-
-val NAME = ALT(PLUS(LETTER), SEQS(PLUS(LETTER),"=", PLUS(LETTER)))
-val BTAG = SEQS("<", NAME, ">")
-val ETAG = SEQS("</", PLUS(LETTER), ">")
-
-val WORD = PLUS(ALT(LETTER, DIGIT))
-val WHITESPACE = PLUS(RANGE(" \n"))
-
-// for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case class T_WORD(s: String) extends Token
-case class T_ETAG(s: String) extends Token
-case class T_BTAG(s: String) extends Token
-case class T_NT(s: String, rhs: List[Token]) extends Token
-
-def tokenizer(rs: List[Rule[Token]], s: String) : List[Token] =
- tokenize(rs, s.toList)
-
-
-
-// lexing rules for arithmetic expressions
-val lexing_rules: List[Rule[Token]]=
- List((BTAG, (s) => T_BTAG(s.mkString)),
- (ETAG, (s) => T_ETAG(s.mkString)),
- (WORD, (s) => T_WORD(s.mkString)),
- (WHITESPACE, (s) => T_WHITESPACE))
-
-val ts = tokenize_file(lexing_rules, "test.html")
-
-
-val WIDTH = 60
-
-def is_tag(t: Token) = t match {
- case T_BTAG(_) => true
- case T_ETAG(_) => true
- case _ => false
-}
-
-def interpret(ts: List[Token], c: Int, ctr: List[String]) : Unit= ts match {
- case Nil => println(Console.RESET)
- case T_WHITESPACE::rest => print(" "); interpret(rest, c + 1, ctr)
- case T_WORD(s)::rest => {
- val newc = c + s.length
- val newstr = Console.RESET + ctr.reverse.mkString + s
- if (newc < WIDTH) {
- print(newstr);
- interpret(rest, newc, ctr)
- }
- else {
- print("\n" + newstr)
- interpret(rest, s.length, ctr)
- }
- }
- case T_BTAG("<p>")::rest => print("\n"); interpret(rest, 0, ctr)
- case T_ETAG("</p>")::rest => print("\n"); interpret(rest, 0, ctr)
- case T_BTAG("<b>")::rest => interpret(rest, c, Console.BOLD :: ctr)
- case T_BTAG("<A>")::rest => interpret(rest, c, Console.UNDERLINED :: ctr)
- case T_BTAG("<cyan>")::rest => interpret(rest, c, Console.CYAN :: ctr)
- case T_BTAG("<red>")::rest => interpret(rest, c, Console.RED :: ctr)
- case T_BTAG("<blink>")::rest => interpret(rest, c, Console.BLINK :: ctr)
- case T_ETAG(_)::rest => interpret(rest, c, ctr.tail)
- case _::rest => interpret(rest, c, ctr)
-}
-
-interpret(ts, 0, Nil)
--- a/scala/i.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,492 +0,0 @@
-
-// regular expressions including NOT
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case object ALLC extends Rexp // recognises any character
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp // negation of a regular expression
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case ALLC => false
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
-}
-
-// tests whether a regular expression
-// cannot recognise more
-def no_more (r: Rexp) : Boolean = r match {
- case NULL => true
- case EMPTY => false
- case ALLC => false
- case CHAR(_) => false
- case ALT(r1, r2) => no_more(r1) && no_more(r2)
- case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
- case STAR(_) => false
- case NOT(r) => !(no_more(r))
-}
-
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case ALLC => EMPTY
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
-}
-
-// regular expression for specifying
-// ranges of characters
-def Range(s : List[Char]) : Rexp = s match {
- case Nil => NULL
- case c::Nil => CHAR(c)
- case c::s => ALT(CHAR(c), Range(s))
-}
-def RANGE(s: String) = Range(s.toList)
-
-
-// one or more
-def PLUS(r: Rexp) = SEQ(r, STAR(r))
-
-// many alternatives
-def Alts(rs: List[Rexp]) : Rexp = rs match {
- case Nil => NULL
- case r::Nil => r
- case r::rs => ALT(r, Alts(rs))
-}
-def ALTS(rs: Rexp*) = Alts(rs.toList)
-
-// repetitions
-def Seqs(rs: List[Rexp]) : Rexp = rs match {
- case Nil => NULL
- case r::Nil => r
- case r::rs => SEQ(r, Seqs(rs))
-}
-def SEQS(rs: Rexp*) = Seqs(rs.toList)
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-type Rule[T] = (Rexp, List[Char] => T)
-
-case class Tokenizer[T](rules: List[Rule[T]], excl: List[T] = Nil) {
-
- def munch(r: Rexp, action: List[Char] => T, s: List[Char], t: List[Char]) : Option[(List[Char], T)] =
- s match {
- case Nil if (nullable(r)) => Some(Nil, action(t))
- case Nil => None
- case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, action(t))
- case c::s if (no_more(der (c, r))) => None
- case c::s => munch(der (c, r), action, s, t ::: List(c))
- }
-
- def one_token(s: List[Char]) : Either[(List[Char], T), String] = {
- val somes = rules.map { (r) => munch(r._1, r._2, s, Nil) }.flatten
- if (somes == Nil) Right(s.mkString)
- else Left(somes sortBy (_._1.length) head)
- }
-
- def tokenize(cs: List[Char]) : List[T] = cs match {
- case Nil => Nil
- case _ => one_token(cs) match {
- case Left((rest, token)) => token :: tokenize(rest)
- case Right(s) => { println("Cannot tokenize: \"" + s + "\""); Nil }
- }
- }
-
- def fromString(s: String) : List[T] =
- tokenize(s.toList).filterNot(excl.contains(_))
-
- def fromFile(name: String) : List[T] =
- fromString(io.Source.fromFile(name).mkString)
-
-}
-
-
-// parser combinators with input type I and return type T
-
-abstract class Parser[I <% Seq[_], T] {
- def parse(ts: I): Set[(T, I)]
-
- def parse_all(ts: I) : Set[T] =
- for ((head, tail) <- parse(ts); if (tail.isEmpty)) yield head
-
- def parse_single(ts: I) : T = parse_all(ts).toList match {
- case t::Nil => t
- case _ => { println ("Parse Error") ; sys.exit(-1) }
- }
-
- def || (right : => Parser[I, T]) : Parser[I, T] = new AltParser(this, right)
- def ==>[S] (f: => T => S) : Parser [I, S] = new FunParser(this, f)
- def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] = new SeqParser(this, right)
- def ~>[S] (right : => Parser[I, S]) : Parser[I, S] = this ~ right ==> (_._2)
- def <~[S] (right : => Parser[I, S]) : Parser[I, T] = this ~ right ==> (_._1)
-}
-
-class SeqParser[I <% Seq[_], T, S](p: => Parser[I, T], q: => Parser[I, S]) extends Parser[I, (T, S)] {
- def parse(sb: I) =
- for ((head1, tail1) <- p.parse(sb);
- (head2, tail2) <- q.parse(tail1)) yield ((head1, head2), tail2)
-}
-
-class AltParser[I <% Seq[_], T](p: => Parser[I, T], q: => Parser[I, T]) extends Parser[I, T] {
- def parse(sb: I) = p.parse(sb) ++ q.parse(sb)
-}
-
-class FunParser[I <% Seq[_], T, S](p: => Parser[I, T], f: T => S) extends Parser[I, S] {
- def parse(sb: I) =
- for ((head, tail) <- p.parse(sb)) yield (f(head), tail)
-}
-
-
-// A parser and evaluator for teh while language
-//
-//:load matcher.scala
-//:load parser3.scala
-
-// some regular expressions
-val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
-val DIGIT = RANGE("0123456789")
-val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
-val NUM = PLUS(DIGIT)
-val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false", "write")
-val SEMI: Rexp = ";"
-val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
-val WHITESPACE = PLUS(RANGE(" \n"))
-val RPAREN: Rexp = ")"
-val LPAREN: Rexp = "("
-val BEGIN: Rexp = "{"
-val END: Rexp = "}"
-val COMMENT = SEQS("/*", NOT(SEQS(STAR(ALLC), "*/", STAR(ALLC))), "*/")
-
-// tokens for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case object T_COMMENT extends Token
-case object T_SEMI extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case object T_BEGIN extends Token
-case object T_END extends Token
-case class T_ID(s: String) extends Token
-case class T_OP(s: String) extends Token
-case class T_NUM(s: String) extends Token
-case class T_KWD(s: String) extends Token
-
-val lexing_rules: List[Rule[Token]] =
- List((KEYWORD, (s) => T_KWD(s.mkString)),
- (ID, (s) => T_ID(s.mkString)),
- (OP, (s) => T_OP(s.mkString)),
- (NUM, (s) => T_NUM(s.mkString)),
- (SEMI, (s) => T_SEMI),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (BEGIN, (s) => T_BEGIN),
- (END, (s) => T_END),
- (WHITESPACE, (s) => T_WHITESPACE),
- (COMMENT, (s) => T_COMMENT))
-
-// the tokenizer
-val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE, T_COMMENT))
-
-// the abstract syntax trees
-abstract class Stmt
-abstract class AExp
-abstract class BExp
-type Block = List[Stmt]
-case object Skip extends Stmt
-case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
-case class While(b: BExp, bl: Block) extends Stmt
-case class Assign(s: String, a: AExp) extends Stmt
-case class Write(s: String) extends Stmt
-
-case class Var(s: String) extends AExp
-case class Num(i: Int) extends AExp
-case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
-
-case object True extends BExp
-case object False extends BExp
-case class Relop(o: String, a1: AExp, a2: AExp) extends BExp
-
-// atomic parsers
-case class TokParser(tok: Token) extends Parser[List[Token], Token] {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((t, ts))
- case _ => Set ()
- }
-}
-implicit def token2tparser(t: Token) = TokParser(t)
-
-case object NumParser extends Parser[List[Token], Int] {
- def parse(ts: List[Token]) = ts match {
- case T_NUM(s)::ts => Set((s.toInt, ts))
- case _ => Set ()
- }
-}
-
-case object IdParser extends Parser[List[Token], String] {
- def parse(ts: List[Token]) = ts match {
- case T_ID(s)::ts => Set((s, ts))
- case _ => Set ()
- }
-}
-
-
-// arithmetic expressions
-lazy val AExp: Parser[List[Token], AExp] =
- (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
- (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
-lazy val T: Parser[List[Token], AExp] =
- (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
-lazy val F: Parser[List[Token], AExp] =
- (T_LPAREN ~> AExp <~ T_RPAREN) ||
- IdParser ==> Var ||
- NumParser ==> Num
-
-// boolean expressions
-lazy val BExp: Parser[List[Token], BExp] =
- (T_KWD("true") ==> ((_) => True: BExp)) ||
- (T_KWD("false") ==> ((_) => False: BExp)) ||
- (T_LPAREN ~> BExp <~ T_RPAREN) ||
- (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Relop("=", x, z): BExp } ||
- (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Relop("!=", x, z): BExp } ||
- (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Relop("<", x, z): BExp } ||
- (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Relop("<", z, x): BExp }
-
-lazy val Stmt: Parser[List[Token], Stmt] =
- (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
- (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
- (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
- { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
- (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) } ||
- (T_KWD("write") ~ IdParser) ==> { case (x, y) => Write(y) }
-
-lazy val Stmts: Parser[List[Token], Block] =
- (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
- (Stmt ==> ((s) => List(s) : Block))
-
-lazy val Block: Parser[List[Token], Block] =
- (T_BEGIN ~> Stmts <~ T_END) ||
- (Stmt ==> ((s) => List(s)))
-
-// compiler
-val beginning = """
-.class public XXX.XXX
-.super java/lang/Object
-
-.method public <init>()V
- aload_0
- invokenonvirtual java/lang/Object/<init>()V
- return
-.end method
-
-.method public static write(I)V
- .limit locals 5
- .limit stack 5
- iload 0
- getstatic java/lang/System/out Ljava/io/PrintStream;
- swap
- invokevirtual java/io/PrintStream/println(I)V
- return
-.end method
-
-
-.method public static main([Ljava/lang/String;)V
- .limit locals 200
- .limit stack 200
-
-"""
-
-val ending = """
-
- return
-
-.end method
-"""
-
-// for generating new labels
-var counter = -1
-
-def Fresh(x: String) = {
- counter += 1
- x ++ "_" ++ counter.toString()
-}
-
-type Env = Map[String, String]
-type Instrs = List[String]
-
-def compile_aexp(a: AExp, env : Env) : Instrs = a match {
- case Num(i) => List("ldc " + i.toString + "\n")
- case Var(s) => List("iload " + env(s) + "\n")
- case Aop("+", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("iadd\n")
- case Aop("-", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("isub\n")
- case Aop("*", a1, a2) => compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("imul\n")
-}
-
-def compile_bexp(b: BExp, env : Env, jmp: String) : Instrs = b match {
- case True => Nil
- case False => List("goto " + jmp + "\n")
- case Relop("=", a1, a2) =>
- compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpne " + jmp + "\n")
- case Relop("!=", a1, a2) =>
- compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpeq " + jmp + "\n")
- case Relop("<", a1, a2) =>
- compile_aexp(a1, env) ++ compile_aexp(a2, env) ++ List("if_icmpge " + jmp + "\n")
-}
-
-
-def compile_stmt(s: Stmt, env: Env) : (Instrs, Env) = s match {
- case Skip => (Nil, env)
- case Assign(x, a) => {
- val index = if (env.isDefinedAt(x)) env(x) else env.keys.size.toString
- (compile_aexp(a, env) ++
- List("istore " + index + "\n"), env + (x -> index))
- }
- case If(b, bl1, bl2) => {
- val if_else = Fresh("If_else")
- val if_end = Fresh("If_end")
- val (instrs1, env1) = compile_bl(bl1, env)
- val (instrs2, env2) = compile_bl(bl2, env1)
- (compile_bexp(b, env, if_else) ++
- instrs1 ++
- List("goto " + if_end + "\n") ++
- List("\n" + if_else + ":\n\n") ++
- instrs2 ++
- List("\n" + if_end + ":\n\n"), env2)
- }
- case While(b, bl) => {
- val loop_begin = Fresh("Loop_begin")
- val loop_end = Fresh("Loop_end")
- val (instrs1, env1) = compile_bl(bl, env)
- (List("\n" + loop_begin + ":\n\n") ++
- compile_bexp(b, env, loop_end) ++
- instrs1 ++
- List("goto " + loop_begin + "\n") ++
- List("\n" + loop_end + ":\n\n"), env1)
- }
- case Write(x) =>
- (List("iload " + env(x) + "\n" + "invokestatic XXX/XXX/write(I)V\n"), env)
-}
-
-def compile_bl(bl: Block, env: Env) : (Instrs, Env) = bl match {
- case Nil => (Nil, env)
- case s::bl => {
- val (instrs1, env1) = compile_stmt(s, env)
- val (instrs2, env2) = compile_bl(bl, env1)
- (instrs1 ++ instrs2, env2)
- }
-}
-
-def compile(input: String) : String = {
- val class_name = input.split('.')(0)
- val tks = Tok.fromFile(input)
- val ast = Stmts.parse_single(tks)
- val instructions = compile_bl(ast, Map.empty)._1
- (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
-}
-
-
-def compile_to(input: String, output: String) = {
- val fw = new java.io.FileWriter(output)
- fw.write(compile(input))
- fw.close()
-}
-
-//
-val tks = Tok.fromString("x := x + 1")
-val ast = Stmt.parse_single(tks)
-println(compile_stmt(ast, Map("x" -> "n"))._1.mkString)
-
-
-
-//examples
-
-compile_to("loops.while", "loops.j")
-//compile_to("fib.while", "fib.j")
-
-
-// testing cases for time measurements
-/*
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-// for testing
-import scala.sys.process._
-
-val test_prog = """
-start := XXX;
-x := start;
-y := start;
-z := start;
-while 0 < x do {
- while 0 < y do {
- while 0 < z do {
- z := z - 1
- };
- z := start;
- y := y - 1
- };
- y := start;
- x := x - 1
-};
-write x;
-write y;
-write z
-"""
-
-
-def compile_test(n: Int) : Unit = {
- val class_name = "LOOP"
- val tks = Tok.fromString(test_prog.replaceAllLiterally("XXX", n.toString))
- val ast = Stmts.parse_single(tks)
- val instructions = compile_bl(ast, Map.empty)._1
- val assembly = (beginning ++ instructions.mkString ++ ending).replaceAllLiterally("XXX", class_name)
- val fw = new java.io.FileWriter(class_name + ".j")
- fw.write(assembly)
- fw.close()
- val test = ("java -jar jvm/jasmin-2.4/jasmin.jar " + class_name + ".j").!!
- println(n + " " + time_needed(2, ("java " + class_name + "/" + class_name).!!))
-}
-
-List(1, 5000, 10000, 50000, 100000, 250000, 500000, 750000, 1000000).map(compile_test(_))
-
-
-
-// javabyte code assmbler
-//
-// java -jar jvm/jasmin-2.4/jasmin.jar loops.j
-
-*/
-
-
-
-
-
--- a/scala/matcher.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,130 +0,0 @@
-package object matcher {
-
-// regular expressions
-// including constructors for NOT and ALLC
-sealed abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case object ALLC extends Rexp // recognises any character
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp // negation of a regular expression
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case ALLC => false
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
-}
-
-// tests whether a regular expression
-// cannot recognise more
-def no_more (r: Rexp) : Boolean = r match {
- case NULL => true
- case EMPTY => false
- case ALLC => false
- case CHAR(_) => false
- case ALT(r1, r2) => no_more(r1) && no_more(r2)
- case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
- case STAR(_) => false
- case NOT(r) => !(no_more(r))
-}
-
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case ALLC => EMPTY
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
-}
-
-// main class for the tokenizer
-case class Tokenizer[T](rules: List[(Rexp, List[Char] => T)], excl: List[T] = Nil) {
-
-def munch(r: Rexp, action: List[Char] => T, s: List[Char], t: List[Char]) : Option[(List[Char], T)] =
- s match {
- case Nil if (nullable(r)) => Some(Nil, action(t))
- case Nil => None
- case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, action(t))
- case c::s if (no_more(der (c, r))) => None
- case c::s => munch(der (c, r), action, s, t ::: List(c))
- }
-
-def one_token(s: List[Char]) : Either[(List[Char], T), String] = {
- val somes = rules.map { (r) => munch(r._1, r._2, s, Nil) }.flatten
- if (somes == Nil) Right(s.mkString)
- else Left(somes sortBy (_._1.length) head)
-}
-
-def tokenize(cs: List[Char]) : List[T] = cs match {
- case Nil => Nil
- case _ => one_token(cs) match {
- case Left((rest, token)) => token :: tokenize(rest)
- case Right(s) => { println("Cannot tokenize: \"" + s + "\""); Nil }
- }
-}
-
-def fromString(s: String) : List[T] =
- tokenize(s.toList).filterNot(excl.contains(_))
-
-def fromFile(name: String) : List[T] =
- fromString(io.Source.fromFile(name).mkString)
-
-}
-
-
-// regular expression for specifying
-// ranges of characters
-def Range(s : List[Char]) : Rexp = s match {
- case Nil => NULL
- case c::Nil => CHAR(c)
- case c::s => ALT(CHAR(c), Range(s))
-}
-def RANGE(s: String) = Range(s.toList)
-
-
-// one or more
-def PLUS(r: Rexp) = SEQ(r, STAR(r))
-
-// many alternatives
-def Alts(rs: List[Rexp]) : Rexp = rs match {
- case Nil => NULL
- case r::Nil => r
- case r::rs => ALT(r, Alts(rs))
-}
-def ALTS(rs: Rexp*) = Alts(rs.toList)
-
-// repetitions
-def Seqs(rs: List[Rexp]) : Rexp = rs match {
- case Nil => NULL
- case r::Nil => r
- case r::rs => SEQ(r, Seqs(rs))
-}
-def SEQS(rs: Rexp*) = Seqs(rs.toList)
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-}
--- a/scala/mllex.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,109 +0,0 @@
-:load matcher.scala
-
-
-// some regular expressions
-val KEYWORDS = ALTS(List("#", "(", ")", ",", "->", "...", ":", ":>", ";", "=",
- "=>", "[", "]", "_", "{", "|", "}", "abstype", "and", "andalso", "as",
- "case", "datatype", "do", "else", "end", "eqtype", "exception", "fn",
- "fun", "functor", "handle", "if", "in", "include", "infix", "infixr",
- "let", "local", "nonfix", "of", "op", "open", "orelse", "raise", "rec",
- "sharing", "sig", "signature", "struct", "structure", "then", "type",
- "val", "where", "while", "with", "withtype"))
-
-val DIGITS = RANGE("0123456789")
-val NONZERODIGITS = RANGE("123456789")
-
-val POSITIVES = ALT(SEQ(NONZERODIGITS, STAR(DIGITS)), "0")
-val INTEGERS = ALT(SEQ("~", POSITIVES), POSITIVES)
-
-val ALL = ALTS(KEYWORDS, INTEGERS)
-
-val COMMENT = SEQS("/*", NOT(SEGS(STAR(ALL), "*/", STAR(ALL))), "*/")
-
-
-
-val LPAREN = CHAR('(')
-val RPAREN = CHAR(')')
-val WHITESPACE = PLUS(RANGE(" \n".toList))
-val OPS = RANGE("+-*".toList)
-
-// for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case object T_NUM extends Token
-case class T_OP(s: String) extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case class T_NT(s: String, rhs: List[Token]) extends Token
-
-def tokenizer(rs: List[Rule[Token]], s: String) : List[Token] =
- tokenize(rs, s.toList).filterNot(_ match {
- case T_WHITESPACE => true
- case _ => false
- })
-
-
-
-// lexing rules for arithmetic expressions
-val lexing_rules: List[Rule[Token]]=
- List((NUMBER, (s) => T_NUM),
- (WHITESPACE, (s) => T_WHITESPACE),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (OPS, (s) => T_OP(s.mkString)))
-
-tokenize_file(Nil, "nominal_library.ML")
-
-
-
-
-type Grammar = List[(String, List[Token])]
-
-// grammar for arithmetic expressions
-val grammar =
- List ("E" -> List(T_NUM),
- "E" -> List(T_NT("E", Nil), T_OP("+"), T_NT("E", Nil)),
- "E" -> List(T_NT("E", Nil), T_OP("-"), T_NT("E", Nil)),
- "E" -> List(T_NT("E", Nil), T_OP("*"), T_NT("E", Nil)),
- "E" -> List(T_LPAREN, T_NT("E", Nil), T_RPAREN))
-
-def startsWith[A](ts1: List[A], ts2: List[A]) : Boolean = (ts1, ts2) match {
- case (_, Nil) => true
- case (T_NT(e, _)::ts1,T_NT(f, _)::ts2) => (e == f) && startsWith(ts1, ts2)
- case (t1::ts1, t2::ts2) => (t1 == t2) && startsWith(ts1, ts2)
- case _ => false
-}
-
-def chop[A](ts1: List[A], prefix: List[A], ts2: List[A]) : Option[(List[A], List[A])] =
- ts1 match {
- case Nil => None
- case t::ts =>
- if (startsWith(ts1, prefix)) Some(ts2.reverse, ts1.drop(prefix.length))
- else chop(ts, prefix, t::ts2)
- }
-
-// examples
-chop(List(1,2,3,4,5,6,7,8,9), List(4,5), Nil)
-chop(List(1,2,3,4,5,6,7,8,9), List(3,5), Nil)
-
-def replace[A](ts: List[A], out: List[A], in: List [A]) =
- chop(ts, out, Nil) match {
- case None => None
- case Some((before, after)) => Some(before ::: in ::: after)
- }
-
-def parse1(g: Grammar, ts: List[Token]) : Boolean = ts match {
- case List(T_NT("E", tree)) => { println(tree); true }
- case _ => {
- val tss = for ((lhs, rhs) <- g) yield replace(ts, rhs, List(T_NT(lhs, rhs)))
- tss.flatten.exists(parse1(g, _))
- }
-}
-
-
-println() ; parse1(grammar, tokenizer(lexing_rules, "2 + 3 * 4 + 1"))
-println() ; parse1(grammar, tokenizer(lexing_rules, "(2 + 3) * (4 + 1)"))
-println() ; parse1(grammar, tokenizer(lexing_rules, "(2 + 3) * 4 (4 + 1)"))
-
-
-
--- a/scala/parser1.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,88 +0,0 @@
-// A naive bottom-up parser with backtracking
-//
-// Needs:
-// :load matcher.scala
-
-// some regular expressions
-val DIGIT = RANGE("0123456789")
-val NONZERODIGIT = RANGE("123456789")
-
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-val LPAREN = CHAR('(')
-val RPAREN = CHAR(')')
-val WHITESPACE = PLUS(RANGE(" \n"))
-val OPS = RANGE("+-*")
-
-// for classifying the strings that have been recognised
-
-abstract class Token
-case object T_WHITESPACE extends Token
-case object T_NUM extends Token
-case class T_OP(s: String) extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case class NT(s: String) extends Token
-
-// lexing rules for arithmetic expressions
-val lexing_rules: List[Rule[Token]]=
- List((NUMBER, (s) => T_NUM),
- (WHITESPACE, (s) => T_WHITESPACE),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (OPS, (s) => T_OP(s.mkString)))
-
-// the tokenizer
-val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
-
-type Grammar = List[(String, List[Token])]
-
-// grammar for arithmetic expressions
-val grammar =
- List ("F" -> List(T_NUM),
- "E" -> List(T_NUM),
- "E" -> List(NT("E"), T_OP("+"), NT("E")),
- "E" -> List(NT("E"), T_OP("-"), NT("E")),
- "E" -> List(NT("E"), T_OP("*"), NT("E")),
- "E" -> List(T_LPAREN, NT("E"), T_RPAREN))
-
-
-def chop[A](ts1: List[A], prefix: List[A], ts2: List[A]) : Option[(List[A], List[A])] =
- ts1 match {
- case Nil => None
- case t::ts =>
- if (ts1.startsWith(prefix)) Some(ts2.reverse, ts1.drop(prefix.length))
- else chop(ts, prefix, t::ts2)
- }
-
-// examples for chop
-chop(List(1,2,3,4,5,6,7,8,9), List(4,5), Nil)
-chop(List(1,2,3,4,5,6,7,8,9), List(3,5), Nil)
-
-def replace[A](ts: List[A], out: List[A], in: List [A]) =
- chop(ts, out, Nil) match {
- case None => None
- case Some((before, after)) => Some(before ::: in ::: after)
- }
-
-def parse(g: Grammar, ts: List[Token]) : Boolean = {
- println(ts)
- if (ts == List(NT("E"))) true
- else {
- val tss = for ((lhs, rhs) <- g) yield replace(ts, rhs, List(NT(lhs)))
- tss.flatten.exists(parse(g, _))
- }
-}
-
-def parser(g: Grammar, s: String) = {
- println("\n")
- parse(g, Tok.fromString(s))
-}
-
-
-
-parser(grammar, "2 + 3 * 4 + 1")
-parser(grammar, "(2 + 3) * (4 + 1)")
-parser(grammar, "(2 + 3) * 4 (4 + 1)")
-
-
-
--- a/scala/parser2.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,139 +0,0 @@
-// A naive version of parser combinators producing parse trees
-//
-// Needs
-// :load matcher.scala
-
-// some regular expressions
-val LETTER = RANGE("abcdefghijklmnopqrstuvwxyz")
-val ID = PLUS(LETTER)
-
-val DIGIT = RANGE("0123456789")
-val NONZERODIGIT = RANGE("123456789")
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-
-val LPAREN = CHAR('(')
-val RPAREN = CHAR(')')
-
-val WHITESPACE = PLUS(RANGE(" \n"))
-val OPS = RANGE("+-*")
-
-// for classifying the strings that have been recognised
-abstract class Token
-
-case object T_WHITESPACE extends Token
-case class T_NUM(s: String) extends Token
-case class T_ID(s: String) extends Token
-case class T_OP(s: String) extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case object T_IF extends Token
-case object T_THEN extends Token
-case object T_ELSE extends Token
-
-// lexing rules for arithmetic expressions
-val lexing_rules: List[Rule[Token]]=
- List(("if", (s) => T_IF),
- ("then", (s) => T_THEN),
- ("else", (s) => T_ELSE),
- (NUMBER, (s) => T_NUM(s.mkString)),
- (ID, (s) => T_ID(s.mkString)),
- (WHITESPACE, (s) => T_WHITESPACE),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (OPS, (s) => T_OP(s.mkString)))
-
-val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
-
-
-// parse trees
-abstract class ParseTree
-case class Leaf(t: Token) extends ParseTree
-case class Branch(pts: List[ParseTree]) extends ParseTree
-
-def combine(pt1: ParseTree, pt2: ParseTree) = pt1 match {
- case Leaf(t) => Branch(List(Leaf(t), pt2))
- case Branch(pts) => Branch(pts ++ List(pt2))
-}
-
-// parser combinators
-abstract class Parser {
- def parse(ts: List[Token]): Set[(ParseTree, List[Token])]
-
- def parse_all(ts: List[Token]) : Set[ParseTree] =
- for ((head, tail) <- parse(ts); if (tail == Nil)) yield head
-
- def || (right : => Parser) : Parser = new AltParser(this, right)
- def ~ (right : => Parser) : Parser = new SeqParser(this, right)
-}
-
-class AltParser(p: => Parser, q: => Parser) extends Parser {
- def parse (ts: List[Token]) = p.parse(ts) ++ q.parse(ts)
-}
-
-class SeqParser(p: => Parser, q: => Parser) extends Parser {
- def parse(ts: List[Token]) =
- for ((head1, tail1) <- p.parse(ts);
- (head2, tail2) <- q.parse(tail1)) yield (combine(head1, head2), tail2)
-}
-
-class ListParser(ps: => List[Parser]) extends Parser {
- def parse(ts: List[Token]) = ps match {
- case Nil => Set()
- case p::Nil => p.parse(ts)
- case p::ps =>
- for ((head1, tail1) <- p.parse(ts);
- (head2, tail2) <- new ListParser(ps).parse(tail1)) yield (Branch(List(head1, head2)), tail2)
- }
-}
-
-case class TokParser(tok: Token) extends Parser {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((Leaf(t), ts))
- case _ => Set ()
- }
-}
-
-implicit def token2tparser(t: Token) = TokParser(t)
-
-case object IdParser extends Parser {
- def parse(ts: List[Token]) = ts match {
- case T_ID(s)::ts => Set((Leaf(T_ID(s)), ts))
- case _ => Set ()
- }
-}
-
-case object NumParser extends Parser {
- def parse(ts: List[Token]) = ts match {
- case T_NUM(s)::ts => Set((Leaf(T_NUM(s)), ts))
- case _ => Set ()
- }
-}
-
-lazy val E: Parser = (T ~ T_OP("+") ~ E) || T // start symbol
-lazy val T: Parser = (F ~ T_OP("*") ~ T) || F
-lazy val F: Parser = (T_LPAREN ~ E ~ T_RPAREN) || NumParser
-
-println(Tok.fromString("1 + 2 + 3"))
-println(E.parse_all(Tok.fromString("1 + 2 + 3")))
-
-def eval(t: ParseTree) : Int = t match {
- case Leaf(T_NUM(n)) => n.toInt
- case Branch(List(t1, Leaf(T_OP("+")), t2)) => eval(t1) + eval(t2)
- case Branch(List(t1, Leaf(T_OP("*")), t2)) => eval(t1) * eval(t2)
- case Branch(List(Leaf(T_LPAREN), t, Leaf(T_RPAREN))) => eval(t)
-}
-
-(E.parse_all(Tok.fromString("1 + 2 + 3"))).map(eval(_))
-(E.parse_all(Tok.fromString("1 + 2 * 3"))).map(eval(_))
-
-lazy val EXPR: Parser =
- new ListParser(List(T_IF, EXPR, T_THEN, EXPR)) ||
- new ListParser(List(T_IF, EXPR, T_THEN, EXPR, T_ELSE, EXPR)) ||
- IdParser
-
-println(EXPR.parse_all(Tok.fromString("if a then b else c")))
-println(EXPR.parse_all(Tok.fromString("if a then if x then y else c")))
-
-
-
-
--- a/scala/parser2a.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,105 +0,0 @@
-// Parser combinators including semantic actions
-// parses lists of tokens
-//
-// Needs
-// :load matcher.scala
-
-// some regular expressions
-val LETTER = RANGE("abcdefghijklmnopqrstuvwxyz")
-val ID = PLUS(LETTER)
-
-val DIGIT = RANGE("0123456789")
-val NONZERODIGIT = RANGE("123456789")
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-
-val LPAREN = CHAR('(')
-val RPAREN = CHAR(')')
-
-val WHITESPACE = PLUS(RANGE(" \n"))
-val OPS = RANGE("+-*")
-
-// for classifying the strings that have been recognised
-abstract class Token
-
-case object T_WHITESPACE extends Token
-case class T_NUM(s: String) extends Token
-case class T_ID(s: String) extends Token
-case class T_OP(s: String) extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case object T_IF extends Token
-case object T_THEN extends Token
-case object T_ELSE extends Token
-
-// lexing rules for arithmetic expressions
-val lexing_rules: List[Rule[Token]]=
- List(("if", (s) => T_IF),
- ("then", (s) => T_THEN),
- ("else", (s) => T_ELSE),
- (NUMBER, (s) => T_NUM(s.mkString)),
- (ID, (s) => T_ID(s.mkString)),
- (WHITESPACE, (s) => T_WHITESPACE),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (OPS, (s) => T_OP(s.mkString)))
-
-val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
-
-// parser combinators with return type T
-abstract class Parser[T] {
- def parse(ts: List[Token]): Set[(T, List[Token])]
-
- def parse_all(ts: List[Token]) : Set[T] =
- for ((head, tail) <- parse(ts); if (tail == Nil)) yield head
-
- def || (right : => Parser[T]) : Parser[T] = new AltParser(this, right)
- def ==>[S] (f: => T => S) : Parser [S] = new FunParser(this, f)
- def ~[S] (right : => Parser[S]) : Parser[(T, S)] = new SeqParser(this, right)
- def ~>[S] (right : => Parser[S]) : Parser[S] = this ~ right ==> (x => x._2)
- def <~[S] (right : => Parser[S]) : Parser[T] = this ~ right ==> (x => x._1)
-
-}
-
-class SeqParser[T, S](p: => Parser[T], q: => Parser[S]) extends Parser[(T, S)] {
- def parse(sb: List[Token]) =
- for ((head1, tail1) <- p.parse(sb);
- (head2, tail2) <- q.parse(tail1)) yield ((head1, head2), tail2)
-}
-
-class AltParser[T](p: => Parser[T], q: => Parser[T]) extends Parser[T] {
- def parse (sb: List[Token]) = p.parse(sb) ++ q.parse(sb)
-}
-
-class FunParser[T, S](p: => Parser[T], f: T => S) extends Parser[S] {
- def parse (sb: List[Token]) =
- for ((head, tail) <- p.parse(sb)) yield (f(head), tail)
-}
-
-
-case class TokParser(tok: Token) extends Parser[Token] {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((t, ts))
- case _ => Set ()
- }
-}
-
-implicit def token2tparser(t: Token) = TokParser(t)
-
-case object NumParser extends Parser[Int] {
- def parse(ts: List[Token]) = ts match {
- case T_NUM(s)::ts => Set((s.toInt, ts))
- case _ => Set ()
- }
-}
-
-lazy val E: Parser[Int] = (T ~ T_OP("+") ~ E) ==> { case ((x, y), z) => x + z } || T
-lazy val T: Parser[Int] = (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => x * z } || F
-lazy val F: Parser[Int] = (T_LPAREN ~> E <~ T_RPAREN) || NumParser
-
-println(E.parse_all(Tok.fromString("1 + 2 + 3")))
-println(E.parse_all(Tok.fromString("1 + 2 * 3")))
-println(E.parse_all(Tok.fromString("(1 + 2) * 3")))
-
-// Excercise: implement minus
-println(E.parse_all(Tok.fromString("(1 - 2) * 3")))
-println(E.parse_all(Tok.fromString("(1 + 2) * - 3")))
--- a/scala/parser3.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,41 +0,0 @@
-package object parser {
-
-// parser combinators
-// with input type I and return type T
-//
-// needs to be compiled with scalac parser3.scala
-
-abstract class Parser[I <% Seq[_], T] {
- def parse(ts: I): Set[(T, I)]
-
- def parse_all(ts: I) : Set[T] =
- for ((head, tail) <- parse(ts); if (tail.isEmpty)) yield head
-
- def parse_single(ts: I) : T = parse_all(ts).toList match {
- case t::Nil => t
- case _ => { println ("Parse Error") ; sys.exit(-1) }
- }
-
- def || (right : => Parser[I, T]) : Parser[I, T] = new AltParser(this, right)
- def ==>[S] (f: => T => S) : Parser [I, S] = new FunParser(this, f)
- def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] = new SeqParser(this, right)
- def ~>[S] (right : => Parser[I, S]) : Parser[I, S] = this ~ right ==> (_._2)
- def <~[S] (right : => Parser[I, S]) : Parser[I, T] = this ~ right ==> (_._1)
-}
-
-class SeqParser[I <% Seq[_], T, S](p: => Parser[I, T], q: => Parser[I, S]) extends Parser[I, (T, S)] {
- def parse(sb: I) =
- for ((head1, tail1) <- p.parse(sb);
- (head2, tail2) <- q.parse(tail1)) yield ((head1, head2), tail2)
-}
-
-class AltParser[I <% Seq[_], T](p: => Parser[I, T], q: => Parser[I, T]) extends Parser[I, T] {
- def parse(sb: I) = p.parse(sb) ++ q.parse(sb)
-}
-
-class FunParser[I <% Seq[_], T, S](p: => Parser[I, T], f: T => S) extends Parser[I, S] {
- def parse(sb: I) =
- for ((head, tail) <- p.parse(sb)) yield (f(head), tail)
-}
-
-}
--- a/scala/parser4.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,82 +0,0 @@
-
-// parser combinators with input type I and return type T
-
-case class SubString(s: String, l: Int, h: Int) {
- def low = l
- def high = h
- def length = h - l
- def substring(l: Int = l, h: Int = h) = s.slice(l, h)
- def set(low: Int = l, high: Int = h) = SubString(s, low, high)
-
-}
-
-type Ctxt = List[(String, SubString)]
-
-abstract class Parser[T] {
-
- def parse(ts: SubString, ctxt: Ctxt): Set[(T, SubString)]
-
- def parse_all(s: String) : Set[T] =
- for ((head, tail) <- parse(SubString(s, 0, s.length), Nil); if (tail.substring() == "")) yield head
-
- def || (right : => Parser[T]) : Parser[T] = new AltParser(this, right)
- def ==>[S] (f: => T => S) : Parser [S] = new FunParser(this, f)
- def ~[S] (right : => Parser[S]) : Parser[(T, S)] = new SeqParser(this, right)
-}
-
-class SeqParser[T, S](p: => Parser[T], q: => Parser[S]) extends Parser[(T, S)] {
- def parse(sb: SubString, ctxt: Ctxt) =
- for ((head1, tail1) <- p.parse(sb, ctxt);
- (head2, tail2) <- q.parse(tail1, ctxt)) yield ((head1, head2), tail2)
-}
-
-class AltParser[T](p: => Parser[T], q: => Parser[T]) extends Parser[T] {
- def parse(sb: SubString, ctxt: Ctxt) = p.parse(sb, ctxt) ++ q.parse(sb, ctxt)
-}
-
-class FunParser[T, S](p: => Parser[T], f: T => S) extends Parser[S] {
- def parse(sb: SubString, ctxt: Ctxt) =
- for ((head, tail) <- p.parse(sb, ctxt)) yield (f(head), tail)
-}
-
-case class SubStringParser(s: String) extends Parser[SubString] {
- val n = s.length
- def parse(sb: SubString, ctxt: Ctxt) = {
- if (n <= sb.length && sb.substring(sb.low, sb.low + n) == s)
- Set((sb.set(high = sb.low + n), sb.set(low = sb.low + n)))
- else Set()
- }
-}
-
-implicit def string2parser(s: String) = SubStringParser(s) ==> (_.substring())
-
-class IgnLst[T](p: => Parser[T]) extends Parser[T] {
- def parse(sb: SubString, ctxt: Ctxt) = {
- if (sb.length == 0) Set()
- else for ((head, tail) <- p.parse(sb.set(high = sb.high - 1), ctxt))
- yield (head, tail.set(high = tail.high + 1))
- }
-}
-
-class CHECK[T](nt: String, p: => Parser[T]) extends Parser[T] {
- def parse(sb: SubString, ctxt: Ctxt) = {
- val should_trim = ctxt.contains (nt, sb)
- if (should_trim && sb.length == 0) Set()
- else if (should_trim) new IgnLst(p).parse(sb, (nt, sb)::ctxt)
- else p.parse(sb, (nt, sb)::ctxt)
- }
-}
-
-// ambigous grammar
-lazy val E: Parser[Int] =
- new CHECK("E", (E ~ "+" ~ E) ==> { case ((x, y), z) => x + z} ||
- (E ~ "*" ~ E) ==> { case ((x, y), z) => x * z} ||
- ("(" ~ E ~ ")") ==> { case ((x, y), z) => y} ||
- "0" ==> { (s) => 0 } ||
- "1" ==> { (s) => 1 } ||
- "2" ==> { (s) => 2 } ||
- "3" ==> { (s) => 3 })
-
-println(E.parse_all("1+2*3+3"))
-
-
--- a/scala/parser5.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,113 +0,0 @@
-val DIGIT = RANGE("0123456789")
-val NONZERODIGIT = RANGE("123456789")
-
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-val LPAREN = CHAR('(')
-val RPAREN = CHAR(')')
-val WHITESPACE = PLUS(RANGE(" \n"))
-val OPS = RANGE("+-*")
-
-// for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case class T_NUM(s: String) extends Token
-case class T_OP(s: String) extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-
-val lexing_rules: List[Rule[Token]]=
- List((NUMBER, (s) => T_NUM(s.mkString)),
- (WHITESPACE, (s) => T_WHITESPACE),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (OPS, (s) => T_OP(s.mkString)))
-
-val Tk = Tokenizer(lexing_rules, List(T_WHITESPACE))
-
-
-// parser combinators with input type I and return type T
-// and memoisation
-
-case class SubList[T](s: List[T], l: Int, h: Int) {
- def low = l
- def high = h
- def length = h - l
- def sublist(l: Int = l, h: Int = h) = s.slice(l, h)
- def set(low: Int = l, high: Int = h) = SubList(s, low, high)
-}
-
-type Ctxt[T] = List[(String, SubList[T])]
-
-abstract class Parser[I, T] {
-
- def parse(ts: SubList[I], ctxt: Ctxt[I]): Set[(T, SubList[I])]
-
- def parse_all(s: List[I]) : Set[T] =
- for ((head, tail) <- parse(SubList(s, 0, s.length), Nil); if (tail.sublist() == Nil)) yield head
-
- def || (right : => Parser[I, T]) : Parser[I, T] = new AltParser(this, right)
- def ==>[S] (f: => T => S) : Parser [I, S] = new FunParser(this, f)
- def ~[S] (right : => Parser[I, S]) : Parser[I, (T, S)] = new SeqParser(this, right)
- def ~>[S] (right : => Parser[I, S]) : Parser[I, S] = this ~ right ==> (_._2)
- def <~[S] (right : => Parser[I, S]) : Parser[I, T] = this ~ right ==> (_._1)
-}
-
-class SeqParser[I, T, S](p: => Parser[I, T], q: => Parser[I, S]) extends Parser[I, (T, S)] {
- def parse(sb: SubList[I], ctxt: Ctxt[I]) =
- for ((head1, tail1) <- p.parse(sb, ctxt);
- (head2, tail2) <- q.parse(tail1, ctxt)) yield ((head1, head2), tail2)
-}
-
-class AltParser[I, T](p: => Parser[I, T], q: => Parser[I, T]) extends Parser[I, T] {
- def parse(sb: SubList[I], ctxt: Ctxt[I]) = p.parse(sb, ctxt) ++ q.parse(sb, ctxt)
-}
-
-class FunParser[I, T, S](p: => Parser[I, T], f: T => S) extends Parser[I, S] {
- def parse(sb: SubList[I], ctxt: Ctxt[I]) =
- for ((head, tail) <- p.parse(sb, ctxt)) yield (f(head), tail)
-}
-
-case object NumParser extends Parser[Token, Int] {
- def parse(sb: SubList[Token], ctxt: Ctxt[Token]) = {
- if (0 < sb.length) sb.sublist(sb.low, sb.low + 1) match {
- case T_NUM(i)::Nil => Set((i.toInt, sb.set(low = sb.low + 1)))
- case _ => Set()
- }
- else Set()
- }
-}
-
-case class TokParser(t: Token) extends Parser[Token, Token] {
- def parse(sb: SubList[Token], ctxt: Ctxt[Token]) = {
- if (0 < sb.length && sb.sublist(sb.low, sb.low + 1) == List(t)) Set((t, sb.set(low = sb.low + 1)))
- else Set()
- }
-}
-
-implicit def token2tparser(t: Token) = TokParser(t)
-
-class IgnLst[I, T](p: => Parser[I, T]) extends Parser[I, T] {
- def parse(sb: SubList[I], ctxt: Ctxt[I]) = {
- if (sb.length == 0) Set()
- else for ((head, tail) <- p.parse(sb.set(high = sb.high - 1), ctxt))
- yield (head, tail.set(high = tail.high + 1))
- }
-}
-
-class CHECK[I, T](nt: String, p: => Parser[I, T]) extends Parser[I, T] {
- def parse(sb: SubList[I], ctxt: Ctxt[I]) = {
- val should_trim = ctxt.contains (nt, sb)
- if (should_trim && sb.length == 0) Set()
- else if (should_trim) new IgnLst(p).parse(sb, (nt, sb)::ctxt)
- else p.parse(sb, (nt, sb)::ctxt)
- }
-}
-
-lazy val E: Parser[Token, Int] =
- new CHECK("E", (E ~ T_OP("+") ~ E) ==> { case ((x, y), z) => x + z} ||
- (E ~ T_OP("*") ~ E) ==> { case ((x, y), z) => x * z} ||
- (T_LPAREN ~ E ~ T_RPAREN) ==> { case ((x, y), z) => y} ||
- NumParser)
-
-println(E.parse_all(Tk.fromString("1 + 2 * 3")))
-println(E.parse_all(Tk.fromString("(1 + 2) * 3")))
--- a/scala/re-alt.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,115 +0,0 @@
-trait RegExp {
- def nullable: Boolean
- def derive(c: Char): RegExp
-}
-
-case object Empty extends RegExp {
- def nullable = false
- def derive(c: Char) = Empty
-}
-
-case object Eps extends RegExp {
- def nullable = true
- def derive(c: Char) = Empty
-}
-
-case class Str(s: String) extends RegExp {
- def nullable = s.isEmpty
- def derive(c: Char) =
- if (s.isEmpty || s.head != c) Empty
- else Str(s.tail)
-}
-
-case class Cat(r: RegExp, s: RegExp) extends RegExp {
- def nullable = r.nullable && s.nullable
- def derive(c: Char) =
- if (r.nullable) Or(Cat(r.derive(c), s), s.derive(c))
- else Cat(r.derive(c), s)
-}
-
-case class Star(r: RegExp) extends RegExp {
- def nullable = true
- def derive(c: Char) = Cat(r.derive(c), this)
-}
-
-case class Or(r: RegExp, s: RegExp) extends RegExp {
- def nullable = r.nullable || s.nullable
- def derive(c: Char) = Or(r.derive(c), s.derive(c))
-}
-
-case class And(r: RegExp, s: RegExp) extends RegExp {
- def nullable = r.nullable && s.nullable
- def derive(c: Char) = And(r.derive(c), s.derive(c))
-}
-
-case class Not(r: RegExp) extends RegExp {
- def nullable = !r.nullable
- def derive(c: Char) = Not(r.derive(c))
-}
-
-
-
-
-object Matcher {
- def matches(r: RegExp, s: String): Boolean = {
- if (s.isEmpty) r.nullable
- else matches(r.derive(s.head), s.tail)
- }
-}
-
-
-object Pimps {
- implicit def string2RegExp(s: String) = Str(s)
-
- implicit def regExpOps(r: RegExp) = new {
- def | (s: RegExp) = Or(r, s)
- def & (s: RegExp) = And(r, s)
- def % = Star(r)
- def %(n: Int) = rep(r, n)
- def ? = Or(Eps, r)
- def ! = Not(r)
- def ++ (s: RegExp) = Cat(r, s)
- def ~ (s: String) = Matcher.matches(r, s)
- }
-
- implicit def stringOps(s: String) = new {
- def | (r: RegExp) = Or(s, r)
- def | (r: String) = Or(s, r)
- def & (r: RegExp) = And(s, r)
- def & (r: String) = And(s, r)
- def % = Star(s)
- def % (n: Int) = rep(Str(s), n)
- def ? = Or(Eps, s)
- def ! = Not(s)
- def ++ (r: RegExp) = Cat(s, r)
- def ++ (r: String) = Cat(s, r)
- def ~ (t: String) = Matcher.matches(s, t)
- }
-
- def rep(r: RegExp, n: Int): RegExp =
- if (n <= 0) Star(r)
- else Cat(r, rep(r, n - 1))
-}
-
-
-object Test {
- import Pimps._
-
- val digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
- val int = ("+" | "-").? ++ digit.%(1)
- val real = ("+" | "-").? ++ digit.%(1) ++ ("." ++ digit.%(1)).? ++ (("e" | "E") ++ ("+" | "-").? ++ digit.%(1)).?
-
- def main(args: Array[String]) {
- val ints = List("0", "-4534", "+049", "99")
- val reals = List("0.9", "-12.8", "+91.0", "9e12", "+9.21E-12", "-512E+01")
- val errs = List("", "-", "+", "+-1", "-+2", "2-")
-
- ints.foreach(s => assert(int ~ s))
- reals.foreach(s => assert(!(int ~ s)))
- errs.foreach(s => assert(!(int ~ s)))
-
- ints.foreach(s => assert(real ~ s))
- reals.foreach(s => assert(real ~ s))
- errs.foreach(s => assert(!(real ~ s)))
- }
-}
--- a/scala/re-internal.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,17 +0,0 @@
-
-// measures the time a function needs
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-
-for (i <- 1 to 10001 by 300) {
- val re = ("((a?){" + i + "})(a{" + i + "})")
- println(i + " " + "%.5f".format(time_needed(1, ("a" * i).matches(re))))
-}
-
-
-
--- a/scala/re.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,123 +0,0 @@
-
-// regular expressions including NOT
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp
-
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
-}
-
-// tests whether a regular expression
-// cannot recognise more
-def no_more (r: Rexp) : Boolean = r match {
- case NULL => true
- case EMPTY => false
- case CHAR(_) => false
- case ALT(r1, r2) => no_more(r1) && no_more(r2)
- case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
- case STAR(_) => false
- case NOT(r) => !(no_more(r))
-}
-
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
-}
-
-
-// regular expression for specifying
-// ranges of characters
-def RANGE(s : List[Char]) : Rexp = s match {
- case Nil => NULL
- case c::Nil => CHAR(c)
- case c::s => ALT(CHAR(c), RANGE(s))
-}
-
-//one or more
-def PLUS(r: Rexp) = SEQ(r, STAR(r))
-
-
-//some regular expressions
-val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
-val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
-val LETTER = ALT(LOWERCASE, UPPERCASE)
-val DIGIT = RANGE("0123456789".toList)
-val NONZERODIGIT = RANGE("123456789".toList)
-
-val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGIT)))
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-val WHITESPACE = RANGE(" \n".toList)
-val WHITESPACES = PLUS(WHITESPACE)
-
-val ALL = ALT(ALT(LETTER, DIGIT), WHITESPACE)
-val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
-
-
-// an example list of regular expressions
-val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, WHITESPACES, COMMENT)
-
-
-def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
-
-def munch(r: Rexp, s: List[Char], t: List[Char]) : Option[(List[Char], List[Char])] =
- s match {
- case Nil if (nullable(r)) => Some(Nil, t)
- case Nil => None
- case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, t)
- case c::s if (no_more(der (c, r))) => None
- case c::s => munch(der (c, r), s, t ::: List(c))
- }
-
-def one_string (regs: List[Rexp], s: List[Char]) : (List[Char], List[Char]) = {
- val somes = regs.map { munch(_, s, Nil) } .flatten
- if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
-}
-
-def tokenize (regs: List[Rexp], s: List[Char]) : List[String] = s match {
- case Nil => Nil
- case _ => one_string(regs, s) match {
- case (rest, s) => s.mkString :: tokenize(regs, rest)
- }
-}
-
-//examples
-println(tokenize(regs, "if true then then 42 else +".toList))
-println(tokenize(regs, "if+true+then+then+42+else +".toList))
-println(tokenize(regs, "ifff if 34 34".toList))
-println(tokenize(regs, "/*ifff if */ hhjj /*34 */".toList))
-println(tokenize(regs, "/* if true then */ then 42 else +".toList))
-//println(tokenize(regs, "ifff $ if 34".toList)) // causes an error because of the symbol $
--- a/scala/re0.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,117 +0,0 @@
-import scala.annotation.tailrec
-
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case object ALLCHAR extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class STR(s: String) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp
-case class REP(r: Rexp, n: Int) extends Rexp
-
-// some convenience for typing in regular expressions
-implicit def string2rexp(s : String) : Rexp = STR(s)
-
-implicit def RexpOps(r: Rexp) = new {
- def | (s: Rexp) = ALT(r, s)
- def % = STAR(r)
- def %(n: Int) = REP(r, n)
- def %%(n: Int) = SEQ(REP(r, n), STAR(r))
- def ? = ALT(EMPTY, r)
- def unary_! = NOT(r)
- def ~ (s: Rexp) = SEQ(r, s)
-}
-
-implicit def stringOps(s: String) = new {
- def | (r: Rexp) = ALT(s, r)
- def | (r: String) = ALT(s, r)
- def % = STAR(s)
- def %(n: Int) = REP(s, n)
- def %%(n: Int) = SEQ(REP(s, n), STAR(s))
- def ? = ALT(EMPTY, s)
- def unary_! = NOT(s)
- def ~ (r: Rexp) = SEQ(s, r)
- def ~ (r: String) = SEQ(s, r)
-}
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case ALLCHAR => false
- case CHAR(_) => false
- case STR(s) => s.isEmpty
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
- case REP(r, i) => if (i == 0) true else nullable(r)
-}
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case ALLCHAR => EMPTY
- case CHAR(d) => if (c == d) EMPTY else NULL
- case STR(s) => if (s.isEmpty || s.head != c) NULL else STR(s.tail)
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
- case REP(r, i) =>
- if (i == 0) NULL else SEQ(der(c, r), REP(r, i - 1))
-}
-
-// derivative w.r.t. a string (iterates der)
-@tailrec
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r))
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-//examples
-val digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
-val int = ("+" | "-").? ~ digit.%%(1)
-val real = ("+" | "-").? ~ digit.%%(1) ~ ("." ~ digit.%%(1)).? ~ (("e" | "E") ~ ("+" | "-").? ~ digit.%%(1)).?
-
-val ints = List("0", "-4534", "+049", "99")
-val reals = List("0.9", "-12.8", "+91.0", "9e12", "+9.21E-12", "-512E+01")
-val errs = List("", "-", "+", "+-1", "-+2", "2-")
-
-ints.map(s => matcher(int, s))
-reals.map(s => matcher(int, s))
-errs.map(s => matcher(int, s))
-
-ints.map(s => matcher(real, s))
-reals.map(s => matcher(real, s))
-errs.map(s => matcher(real, s))
-
-
-
-def RTEST(n: Int) = ("a".? %(n)) ~ ("a" %(n))
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-for (i <- 1 to 12000 by 500) {
- println(i + ": " + "%.5f".format(time_needed(1, matcher(RTEST(i), "a" * i))))
-}
-
-
--- a/scala/re1.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,80 +0,0 @@
-
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
-}
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
-}
-
-// derivative w.r.t. a string (iterates der)
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r))
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-//example
-//val r = STAR(ALT(SEQ(CHAR('a'), CHAR('b')), CHAR('b')))
-//der('b', r)
-//der('b', r)
-
-//one or zero
-def OPT(r: Rexp) = ALT(r, EMPTY)
-
-//n-times
-def NTIMES(r: Rexp, n: Int) : Rexp = n match {
- case 0 => EMPTY
- case 1 => r
- case n => SEQ(r, NTIMES(r, n - 1))
-}
-
-def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-for (i <- 1 to 29) {
- println(i + ": " + "%.5f".format(time_needed(1, matcher(RTEST(i), "a" * i))))
-}
-
-
--- a/scala/re2.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,100 +0,0 @@
-
-abstract class Rexp {
- def simp : Rexp = this
-}
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp {
- override def simp = (r1.simp, r2.simp) match {
- case (NULL, r) => r
- case (r, NULL) => r
- case (r, EMPTY) => if (nullable(r)) r else ALT(r, EMPTY)
- case (EMPTY, r) => if (nullable(r)) r else ALT(r, EMPTY)
- case (r1, r2) => if (r1 == r2) r1 else ALT(r1, r2)
- }
-}
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp {
- override def simp = (r1.simp, r2.simp) match {
- case (NULL, _) => NULL
- case (_, NULL) => NULL
- case (EMPTY, r) => r
- case (r, EMPTY) => r
- case (r1, r2) => SEQ(r1, r2)
- }
-}
-case class STAR(r: Rexp) extends Rexp {
- override def simp = r.simp match {
- case NULL => EMPTY
- case EMPTY => EMPTY
- case r => STAR(r)
- }
-}
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
-}
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
-}
-
-// derivative w.r.t. a string (iterates der)
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r).simp)
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-
-//one or zero
-def OPT(r: Rexp) = ALT(r, EMPTY)
-
-//n-times
-def NTIMES(r: Rexp, n: Int) : Rexp = n match {
- case 0 => EMPTY
- case 1 => r
- case n => SEQ(r, NTIMES(r, n - 1))
-}
-
-def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-for (i <- 1 to 100) {
- println(i + ": " + "%.5f".format(time_needed(1, matcher(RTEST(i), "a" * i))))
-}
-
-
--- a/scala/re3.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,106 +0,0 @@
-
-abstract class Rexp {
- def simp : Rexp = this
-}
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp {
- override def simp = (r1.simp, r2.simp) match {
- case (NULL, r) => r
- case (r, NULL) => r
- case (r, EMPTY) => if (nullable(r)) r else ALT(r, EMPTY)
- case (EMPTY, r) => if (nullable(r)) r else ALT(r, EMPTY)
- case (r1, r2) => if (r1 == r2) r1 else ALT(r1, r2)
- }
-}
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp {
- override def simp = (r1.simp, r2.simp) match {
- case (NULL, _) => NULL
- case (_, NULL) => NULL
- case (EMPTY, r) => r
- case (r, EMPTY) => r
- case (r1, r2) => SEQ(r1, r2)
- }
-}
-case class STAR(r: Rexp) extends Rexp {
- override def simp = r.simp match {
- case NULL => EMPTY
- case EMPTY => EMPTY
- case r => STAR(r)
- }
-}
-case class NTIMES(r: Rexp, n: Int) extends Rexp {
- override def simp = if (n == 0) EMPTY else
- r.simp match {
- case NULL => NULL
- case EMPTY => EMPTY
- case r => NTIMES(r, n)
- }
-}
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NTIMES(r, i) => if (i == 0) true else nullable(r)
-}
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NTIMES(r, i) =>
- if (i == 0) NULL else SEQ(der(c, r), NTIMES(r, i - 1))
-}
-
-// derivative w.r.t. a string (iterates der)
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r).simp)
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-
-
-//one or zero
-def OPT(r: Rexp) = ALT(r, EMPTY)
-
-def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-
-for (i <- 1 to 11001 by 500) {
- println(i + " " + + " " + time_needed(1, matcher(RTEST(i), "a" * i)))
-}
-
-
--- a/scala/re4.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,101 +0,0 @@
-import scala.annotation.tailrec
-abstract class Rexp {
- def simp : Rexp = this
-}
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp {
- override def simp = (r1.simp, r2.simp) match {
- case (NULL, r) => r
- case (r, NULL) => r
- case (r, EMPTY) => if (nullable(r)) r else ALT(r, EMPTY)
- case (EMPTY, r) => if (nullable(r)) r else ALT(r, EMPTY)
- case (r1, r2) => ALT(r1, r2)
- }
-}
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp {
- override def simp = (r1.simp, r2.simp) match {
- case (NULL, _) => NULL
- case (_, NULL) => NULL
- case (EMPTY, r) => r
- case (r, EMPTY) => r
- case (r1, r2) => SEQ(r1, r2)
- }
-}
-case class STAR(r: Rexp) extends Rexp
-case class NTIMES(r: Rexp, n: Int) extends Rexp
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NTIMES(r, i) => if (i == 0) false else nullable(r)
-}
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NTIMES(r, i) =>
- if (i == 0) NULL else SEQ(der(c, r), NTIMES(r, i - 1))
-}
-
-// derivative w.r.t. a string (iterates der)
-@tailrec
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r).simp)
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-
-
-//one or zero
-def OPT(r: Rexp) = ALT(r, EMPTY)
-
-//n-times
-/*def NTIMES(r: Rexp, n: Int) : Rexp = n match {
- case 0 => NULL
- case 1 => r
- case n => SEQ(r, NTIMES(r, n - 1))
-}*/
-
-def RTEST(n: Int) = SEQ(NTIMES(OPT("a"), n), NTIMES("a", n))
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-
-for (i <- 1 to 13001 by 500) {
- println(i + " " + time_needed(1, matcher(RTEST(i), "a" * i)))
-}
-
-
--- a/scala/regexp.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,106 +0,0 @@
-// regular expressions
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// for example
-println(STAR("abc"))
-
-// produces STAR(SEQ(CHAR(a),SEQ(CHAR(b),SEQ(CHAR(c),EMPTY))))
-
-
-
-// a simple-minded regular expression matcher:
-// it loops for examples like STAR(EMPTY) with
-// strings this regular expression does not match
-
-def smatchers(rs: List[Rexp], s: List[Char]) : Boolean = (rs, s) match {
- case (NULL::rs, s) => false
- case (EMPTY::rs, s) => smatchers(rs, s)
- case (CHAR(c)::rs, Nil) => false
- case (CHAR(c)::rs, d::s) => (c ==d) && smatchers(rs, s)
- case (ALT(r1, r2)::rs, s) => smatchers(r1::rs, s) || smatchers(r2::rs, s)
- case (SEQ(r1, r2)::rs, s) => smatchers(r1::r2::rs, s)
- case (STAR(r)::rs, s) => smatchers(rs, s) || smatchers(r::STAR(r)::rs, s)
- case (Nil, s) => s == Nil
-}
-
-def smatcher(r: Rexp, s: String) = smatchers(List(r), s.toList)
-
-// regular expression: a
-println(smatcher(CHAR('a'), "ab"))
-
-// regular expression: a + (b o c)
-println(smatcher(ALT(CHAR('a'), SEQ(CHAR('b'), CHAR('c'))), "ab"))
-
-// regular expression: a + (b o c)
-println(smatcher(ALT(CHAR('a'), SEQ(CHAR('b'), CHAR('c'))), "bc"))
-
-// loops for regular expression epsilon*
-//println(smatcher(STAR(EMPTY), "a"))
-
-
-
-// Regular expression matcher that works properly
-//================================================
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
-}
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
-}
-
-// derivative w.r.t. a string (iterates der)
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r))
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-
-//examples
-
-println(matcher(SEQ(STAR("a"), STAR("b")), "bbaaa"))
-println(matcher(ALT(STAR("a"), STAR("b")), ""))
-println(matcher("abc", ""))
-println(matcher(STAR(ALT(EMPTY, "a")), ""))
-println(matcher(STAR(EMPTY), "a"))
-println(matcher("cab","cab"))
-println(matcher(STAR("a"),"aaa"))
-println(matcher("cab" ,"cab"))
-println(matcher(STAR("a"),"aaa"))
-
-
--- a/scala/regexp2.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,123 +0,0 @@
-
-// regular expressions including NOT
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp
-
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
-}
-
-// tests whether a regular expression
-// cannot recognise more
-def no_more (r: Rexp) : Boolean = r match {
- case NULL => true
- case EMPTY => false
- case CHAR(_) => false
- case ALT(r1, r2) => no_more(r1) && no_more(r2)
- case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
- case STAR(_) => false
- case NOT(r) => !(no_more(r))
-}
-
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
-}
-
-
-// regular expression for specifying
-// ranges of characters
-def RANGE(s : List[Char]) : Rexp = s match {
- case Nil => NULL
- case c::Nil => CHAR(c)
- case c::s => ALT(CHAR(c), RANGE(s))
-}
-
-//one or more
-def PLUS(r: Rexp) = SEQ(r, STAR(r))
-
-
-//some regular expressions
-val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
-val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
-val LETTER = ALT(LOWERCASE, UPPERCASE)
-val DIGIT = RANGE("0123456789".toList)
-val NONZERODIGIT = RANGE("123456789".toList)
-
-val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGIT)))
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-val WHITESPACE = RANGE(" \n".toList)
-val WHITESPACES = PLUS(WHITESPACE)
-
-val ALL = ALT(ALT(LETTER, DIGIT), WHITESPACE)
-val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
-
-
-// an example list of regular expressions
-val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, WHITESPACES, COMMENT)
-
-
-def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
-
-def munch(r: Rexp, s: List[Char], t: List[Char]) : Option[(List[Char], List[Char])] =
- s match {
- case Nil if (nullable(r)) => Some(Nil, t)
- case Nil => None
- case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, t)
- case c::s if (no_more(der (c, r))) => None
- case c::s => munch(der (c, r), s, t ::: List(c))
- }
-
-def one_string (regs: List[Rexp], s: List[Char]) : (List[Char], List[Char]) = {
- val somes = regs.map { munch(_, s, Nil) } .flatten
- if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
-}
-
-def tokenize (regs: List[Rexp], s: List[Char]) : List[String] = s match {
- case Nil => Nil
- case _ => one_string(regs, s) match {
- case (rest, s) => s.mkString :: tokenize(regs, rest)
- }
-}
-
-//examples
-println(tokenize(regs, "if true then then 42 else +".toList))
-println(tokenize(regs, "if+true+then+then+42+else +".toList))
-println(tokenize(regs, "ifff if 34 34".toList))
-println(tokenize(regs, "/*ifff if */ hhjj /*34 */".toList))
-println(tokenize(regs, "/* if true then */ then 42 else +".toList))
-//println(tokenize(regs, "ifff $ if 34".toList)) // causes an error because of the symbol $
--- a/scala/regexp3.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,141 +0,0 @@
-
-// regular expressions including NOT
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp
-
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
-}
-
-// tests whether a regular expression
-// cannot recognise more
-def no_more (r: Rexp) : Boolean = r match {
- case NULL => true
- case EMPTY => false
- case CHAR(_) => false
- case ALT(r1, r2) => no_more(r1) && no_more(r2)
- case SEQ(r1, r2) => if (nullable(r1)) (no_more(r1) && no_more(r2)) else no_more(r1)
- case STAR(_) => false
- case NOT(r) => !(no_more(r))
-}
-
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
-}
-
-// regular expression for specifying
-// ranges of characters
-def RANGE(s : List[Char]) : Rexp = s match {
- case Nil => NULL
- case c::Nil => CHAR(c)
- case c::s => ALT(CHAR(c), RANGE(s))
-}
-
-// one or more
-def PLUS(r: Rexp) = SEQ(r, STAR(r))
-
-// some regular expressions
-val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
-val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
-val LETTER = ALT(LOWERCASE, UPPERCASE)
-val DIGIT = RANGE("0123456789".toList)
-val NONZERODIGIT = RANGE("123456789".toList)
-
-val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGIT)))
-val NUMBER = ALT(SEQ(NONZERODIGIT, STAR(DIGIT)), "0")
-val WHITESPACE = RANGE(" \n".toList)
-val WHITESPACES = PLUS(WHITESPACE)
-
-val ALL = ALT(ALT(LETTER, DIGIT), WHITESPACE)
-val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
-
-
-// for classifying the strings that have been recognised
-abstract class Token
-
-case object T_WHITESPACE extends Token
-case object T_COMMENT extends Token
-case class T_IDENT(s: String) extends Token
-case class T_OP(s: String) extends Token
-case class T_NUM(n: Int) extends Token
-case class T_KEYWORD(s: String) extends Token
-
-
-// an example list of syntactic rules
-type Rule = (Rexp, List[Char] => Token)
-
-val rules: List[Rule]=
- List(("if", (s) => T_KEYWORD(s.mkString)),
- ("then", (s) => T_KEYWORD(s.mkString)),
- ("else", (s) => T_KEYWORD(s.mkString)),
- ("+", (s) => T_OP(s.mkString)),
- (IDENT, (s) => T_IDENT(s.mkString)),
- (NUMBER, (s) => T_NUM(s.mkString.toInt)),
- (WHITESPACES, (s) => T_WHITESPACE),
- (COMMENT, (s) => T_COMMENT))
-
-
-def error (s: String) = throw new IllegalArgumentException ("Cannot tokenize: " + s)
-
-def munch(r: Rexp, action: List[Char] => Token, s: List[Char], t: List[Char]) : Option[(List[Char], Token)] =
- s match {
- case Nil if (nullable(r)) => Some(Nil, action(t))
- case Nil => None
- case c::s if (no_more(der (c, r)) && nullable(r)) => Some(c::s, action(t))
- case c::s if (no_more(der (c, r))) => None
- case c::s => munch(der (c, r), action, s, t ::: List(c))
- }
-
-def one_token (rs: List[Rule], s: List[Char]) : (List[Char], Token) = {
- val somes = rs.map { (r) => munch(r._1, r._2, s, Nil) } .flatten
- if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
-}
-
-def tokenize (rs: List[Rule], s: List[Char]) : List[Token] = s match {
- case Nil => Nil
- case _ => one_token(rs, s) match {
- case (rest, token) => token :: tokenize(rs, rest)
- }
-}
-
-//examples
-println(tokenize(rules, "if true then then 42 else +".toList))
-println(tokenize(rules, "if+true+then+then+42+else +".toList))
-println(tokenize(rules, "ifff if 34 34".toList))
-println(tokenize(rules, "/*ifff if */ hhjj /*34 */".toList))
-println(tokenize(rules, "/* if true then */ then 42 else +".toList))
-//println(tokenize(rules, "ifff $ if 34".toList)) // causes an error because of the symbol $
--- a/scala/regexp4.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,168 +0,0 @@
-// regular expressions
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp
-
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
-}
-
-// tests whether a regular expression
-// recognises nothing
-def zeroable (r: Rexp) : Boolean = r match {
- case NULL => true
- case EMPTY => false
- case CHAR(_) => false
- case ALT(r1, r2) => zeroable(r1) && zeroable(r2)
- case SEQ(r1, r2) => zeroable(r1) || zeroable(r2)
- case STAR(_) => false
- case NOT(r) => !(zeroable(r))
-}
-
-def starts_with (r: Rexp, c: Char) : Boolean = r match {
- case NULL => false
- case EMPTY => false
- case CHAR(d) => (c == d)
- case ALT(r1, r2) => starts_with(r1, c) || starts_with(r2, c)
- case SEQ(r1, r2) => if (nullable(r1)) (starts_with(r1, c) || starts_with(r2, c))
- else starts_with(r1, c)
- case STAR(r) => starts_with(r, c)
- case NOT(r) => !(starts_with(r, c))
-}
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
-}
-
-// derivative w.r.t. a string (iterates der)
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r))
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-
-// regular expression for specifying
-// ranges of characters
-def RANGE(s : List[Char]) : Rexp = s match {
- case Nil => NULL
- case c::Nil => CHAR(c)
- case c::s => ALT(CHAR(c), RANGE(s))
-}
-
-//one or more
-def PLUS(r: Rexp) = SEQ(r, STAR(r))
-
-
-//some regular expressions
-val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
-val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
-val LETTER = ALT(LOWERCASE, UPPERCASE)
-val DIGITS = RANGE("0123456789".toList)
-val NONZERODIGITS = RANGE("123456789".toList)
-
-val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGITS)))
-val NUMBER = ALT(SEQ(NONZERODIGITS, STAR(DIGITS)), "0")
-val WHITESPACE = RANGE(" \n".toList)
-val SYMBOLS = RANGE("/*".toList)
-
-val ALL = ALT(ALT(ALT(LETTER, DIGITS), WHITESPACE), SYMBOLS)
-
-val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
-
-println(matcher(NUMBER, "0"))
-println(matcher(NUMBER, "01"))
-println(matcher(NUMBER, "123450"))
-
-println(matcher(SEQ(STAR("a"), STAR("b")), "bbaaa"))
-println(matcher(ALT(STAR("a"), STAR("b")), ""))
-println(matcher("abc", ""))
-println(matcher(STAR(ALT(EMPTY, "a")), ""))
-println(matcher(STAR(EMPTY), "a"))
-println(matcher("cab","cab"))
-println(matcher(STAR("a"),"aaa"))
-println(matcher("cab" ,"cab"))
-println(matcher(STAR("a"),"aaa"))
-
-println(matcher(COMMENT, "/* */"))
-println(matcher(COMMENT, "/* foobar comment */"))
-println(matcher(COMMENT, "/* test */ test */"))
-
-// an example list of regular expressions
-val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, COMMENT, WHITESPACE)
-
-
-def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
-
-def munch(r: Rexp, s: List[Char], t: List[Char]) : Option[(List[Char], List[Char])] =
- if (zeroable(r)) None else s match {
- case Nil => if (nullable(r)) Some(Nil, t) else None
- case c::s if (zeroable(der (c, r)) && nullable(r)) => Some(c::s, t)
- //case c::s if (zeroable(der (c, r))) => None
- case c::s => munch(der (c, r), s, t ::: List(c))
-}
-
-
-def lex_one (regs: List[Rexp], s: List[Char]) : (List[Char], List[Char]) = {
- val somes = regs.map { munch(_, s, Nil) } .flatten
- if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
-}
-
-def lex_all (regs: List[Rexp], s: List[Char]) : List[String] = s match {
- case Nil => Nil
- case _ => lex_one(regs, s) match {
- case (rest, s) => s.mkString :: lex_all(regs, rest)
- }
-}
-
-
-
-starts_with(der('/', COMMENT), '*')
-
-munch(COMMENT, "/*ifff if 34 */".toList, Nil)
-val COMMENT2 = NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))
-
-der('a', COMMENT2)
-zeroable(der('a', COMMENT2))
-
-matcher(COMMENT2, "ifff if 34")
-munch(COMMENT2, "ifff if 34".toList, Nil)
-starts_with(COMMENT2, 'i')
-lex_all(regs, "ifff if 34".toList)
-lex_all(regs, "ifff $ if 34".toList)
-
--- a/scala/regexp5.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,177 +0,0 @@
-// regular expressions
-abstract class Rexp
-
-case object NULL extends Rexp
-case object EMPTY extends Rexp
-case class CHAR(c: Char) extends Rexp
-case class ALT(r1: Rexp, r2: Rexp) extends Rexp
-case class SEQ(r1: Rexp, r2: Rexp) extends Rexp
-case class STAR(r: Rexp) extends Rexp
-case class NOT(r: Rexp) extends Rexp
-
-
-// some convenience for typing in regular expressions
-def charlist2rexp(s : List[Char]) : Rexp = s match {
- case Nil => EMPTY
- case c::Nil => CHAR(c)
- case c::s => SEQ(CHAR(c), charlist2rexp(s))
-}
-implicit def string2rexp(s : String) : Rexp = charlist2rexp(s.toList)
-
-
-// nullable function: tests whether the regular
-// expression can recognise the empty string
-def nullable (r: Rexp) : Boolean = r match {
- case NULL => false
- case EMPTY => true
- case CHAR(_) => false
- case ALT(r1, r2) => nullable(r1) || nullable(r2)
- case SEQ(r1, r2) => nullable(r1) && nullable(r2)
- case STAR(_) => true
- case NOT(r) => !(nullable(r))
-}
-
-// tests whether a regular expression
-// recognises nothing
-def zeroable (r: Rexp) : Boolean = r match {
- case NULL => true
- case EMPTY => false
- case CHAR(_) => false
- case ALT(r1, r2) => zeroable(r1) && zeroable(r2)
- case SEQ(r1, r2) => if (nullable(r1)) (zeroable(r1) && zeroable(r2)) else zeroable(r1)
- //zeroable(r1) || zeroable(r2)
- case STAR(_) => false
- case NOT(r) => !(zeroable(r))
-}
-
-
-// derivative of a regular expression w.r.t. a character
-def der (c: Char, r: Rexp) : Rexp = r match {
- case NULL => NULL
- case EMPTY => NULL
- case CHAR(d) => if (c == d) EMPTY else NULL
- case ALT(r1, r2) => ALT(der(c, r1), der(c, r2))
- case SEQ(r1, r2) =>
- if (nullable(r1)) ALT(SEQ(der(c, r1), r2), der(c, r2))
- else SEQ(der(c, r1), r2)
- case STAR(r) => SEQ(der(c, r), STAR(r))
- case NOT(r) => NOT(der (c, r))
-}
-
-// derivative w.r.t. a string (iterates der)
-def ders (s: List[Char], r: Rexp) : Rexp = s match {
- case Nil => r
- case c::s => ders(s, der(c, r))
-}
-
-// main matcher function
-def matcher(r: Rexp, s: String) : Boolean = nullable(ders(s.toList, r))
-
-
-// regular expression for specifying
-// ranges of characters
-def RANGE(s : List[Char]) : Rexp = s match {
- case Nil => NULL
- case c::Nil => CHAR(c)
- case c::s => ALT(CHAR(c), RANGE(s))
-}
-
-//one or more
-def PLUS(r: Rexp) = SEQ(r, STAR(r))
-
-
-//some regular expressions
-val LOWERCASE = RANGE("abcdefghijklmnopqrstuvwxyz".toList)
-val UPPERCASE = RANGE("ABCDEFGHIJKLMNOPQRSTUVWXYZ".toList)
-val LETTER = ALT(LOWERCASE, UPPERCASE)
-val DIGITS = RANGE("0123456789".toList)
-val NONZERODIGITS = RANGE("123456789".toList)
-
-val IDENT = SEQ(LETTER, STAR(ALT(LETTER,DIGITS)))
-val NUMBER = ALT(SEQ(NONZERODIGITS, STAR(DIGITS)), "0")
-val WHITESPACE = RANGE(" \n".toList)
-
-val ALL = ALT(ALT(LETTER, DIGITS), WHITESPACE)
-
-val COMMENT = SEQ(SEQ("/*", NOT(SEQ(SEQ(STAR(ALL), "*/"), STAR(ALL)))), "*/")
-
-println(matcher(NUMBER, "0"))
-println(matcher(NUMBER, "01"))
-println(matcher(NUMBER, "123450"))
-
-println(matcher(SEQ(STAR("a"), STAR("b")), "bbaaa"))
-println(matcher(ALT(STAR("a"), STAR("b")), ""))
-println(matcher("abc", ""))
-println(matcher(STAR(ALT(EMPTY, "a")), ""))
-println(matcher(STAR(EMPTY), "a"))
-println(matcher("cab","cab"))
-println(matcher(STAR("a"),"aaa"))
-println(matcher("cab" ,"cab"))
-println(matcher(STAR("a"),"aaa"))
-
-println(matcher(COMMENT, "/* */"))
-println(matcher(COMMENT, "/* 34 */"))
-println(matcher(COMMENT, "/* foobar comment */"))
-println(matcher(COMMENT, "/* test */ test */"))
-
-// an example list of regular expressions
-
-abstract class Token
-
-case object T_WHITESPACE extends Token
-case object T_COMMENT extends Token
-case class T_IDENT(s: String) extends Token
-case class T_OP(s: String) extends Token
-case class T_NUM(n: Int) extends Token
-case class T_KEYWORD(s: String) extends Token
-
-val regs: List[Rexp]= List("if", "then", "else", "+", IDENT, NUMBER, WHITESPACE)
-
-type Rule = (Rexp, List[Char] => Token)
-
-val rules: List[Rule]=
- List(("if", (s) => T_KEYWORD(s.mkString)),
- ("then", (s) => T_KEYWORD(s.mkString)),
- ("else", (s) => T_KEYWORD(s.mkString)),
- ("+", (s) => T_OP(s.mkString)),
- (IDENT, (s) => T_IDENT(s.mkString)),
- (NUMBER, (s) => T_NUM(s.mkString.toInt)),
- (WHITESPACE, (s) => T_WHITESPACE),
- (COMMENT, (s) => T_COMMENT))
-
-
-def error (s: String) = throw new IllegalArgumentException ("Could not lex " + s)
-
-def munch(r: Rexp, action: List[Char] => Token, s: List[Char], t: List[Char]) : Option[(List[Char], Token)] =
-{ println("string " + s)
- println(" rexp " + r)
- s match {
- case Nil if (nullable(r)) => Some(Nil, action(t))
- case Nil => { println("1"); None }
- case c::s if (zeroable(der (c, r)) && nullable(r)) => Some(c::s, action(t))
- case c::s if (zeroable(der (c, r))) => { println("2"); None }
- case c::s => munch(der (c, r), action, s, t ::: List(c))
- }
-}
-
-def lex_one (rs: List[Rule], s: List[Char]) : (List[Char], Token) = {
- val somes = rs.map { (r) => munch(r._1, r._2, s, Nil) } .flatten
- if (somes == Nil) error(s.mkString) else (somes sortBy (_._1.length) head)
-}
-
-def lex_all (rs: List[Rule], s: List[Char]) : List[Token] = s match {
- case Nil => Nil
- case _ => lex_one(rs, s) match {
- case (rest, t) => t :: lex_all(rs, rest)
- }
-}
-
-
-
-println(matcher(COMMENT, "/*ifff if 34 34*/"))
-rules.map { (r) => munch(r._1, r._2, "/*ifff if 34 34*/ ".toList, Nil) }
-println(lex_all(rules, "ifff if 34 34".toList))
-println(lex_all(rules, " /*ifff if 34 34*/ ".toList))
-println(lex_all(rules, "ifff $ if 34".toList))
-
-
--- a/scala/scraper.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,57 +0,0 @@
-import java.io.OutputStreamWriter
-import java.net.URL
-import scala.io.Source.fromInputStream
-
-val url = new URL("http://www.envir.gov.cn/eng/airep/index.asp")
-
-//connect to url
-val conn = url.openConnection
-conn.setRequestProperty("User-Agent", "")
-conn.setDoOutput(true)
-conn.connect
-
-//sending data
-val wr = new OutputStreamWriter(conn.getOutputStream())
-//wr.write("Fdate=2012-9-24&Tdate=2012-09-25")
-//wr.write("Fdate=2012-9-18&Tdate=2012-09-25")
-wr.write("Fdate=2001-5-18&Tdate=2012-09-25")
-wr.flush
-wr.close
-
-//receiving data
-val page = fromInputStream(conn.getInputStream).getLines.mkString("\n")
-
-//println(page)
-
-// regular expression . excludes newlines,
-// therefore we have to use [\S\s]
-val regex1 = """<tr align="center">[\S\s]*?</tr>""".r
-val rows = regex1.findAllIn(page).toList
-
-//print(rows)
-
-val regex2 = """<td align="center">([\S\s]*?)</td>""".r
-
-def aux(s: String) : Array[String] = {
- for (m <- regex2.findAllIn(s).toArray) yield m match {
- case regex2(value) => value.trim
- }
-}
-
-val data = rows.map { aux }
-
-def compare(i: Int)(e: Array[String], f: Array[String]) = e(i).toInt < f(i).toInt
-
-//day with highest particle pollution (PM_10)
-data.sortWith(compare(1)).last
-
-//day with highest sulfur dioxide (SO_2)
-data.sortWith(compare(2)).last
-
-//day with highest nitro dioxide (NO_2)
-data.sortWith(compare(3)).last
-
-//days with highest PM_10
-val groups = data.groupBy(_(1).toInt)
-val max_key = groups.keySet.max
-groups(max_key)
--- a/scala/while.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,231 +0,0 @@
-// A parser and evaluator for teh while language
-//
-import matcher._
-import parser._
-
-
-// some regular expressions
-val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
-val DIGIT = RANGE("0123456789")
-val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
-val NUM = PLUS(DIGIT)
-val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false")
-val SEMI: Rexp = ";"
-val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
-val WHITESPACE = PLUS(RANGE(" \n"))
-val RPAREN: Rexp = ")"
-val LPAREN: Rexp = "("
-val BEGIN: Rexp = "{"
-val END: Rexp = "}"
-
-// tokens for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case object T_SEMI extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case object T_BEGIN extends Token
-case object T_END extends Token
-case class T_ID(s: String) extends Token
-case class T_OP(s: String) extends Token
-case class T_NUM(s: String) extends Token
-case class T_KWD(s: String) extends Token
-
-val lexing_rules: List[(Rexp, List[Char] => Token)] =
- List((KEYWORD, (s) => T_KWD(s.mkString)),
- (ID, (s) => T_ID(s.mkString)),
- (OP, (s) => T_OP(s.mkString)),
- (NUM, (s) => T_NUM(s.mkString)),
- (SEMI, (s) => T_SEMI),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (BEGIN, (s) => T_BEGIN),
- (END, (s) => T_END),
- (WHITESPACE, (s) => T_WHITESPACE))
-
-// the tokenizer
-val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE))
-
-// the abstract syntax trees
-abstract class Stmt
-abstract class AExp
-abstract class BExp
-type Block = List[Stmt]
-case object Skip extends Stmt
-case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
-case class While(b: BExp, bl: Block) extends Stmt
-case class Assign(s: String, a: AExp) extends Stmt
-
-case class Var(s: String) extends AExp
-case class Num(i: Int) extends AExp
-case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
-
-case object True extends BExp
-case object False extends BExp
-case class Bop(o: String, a1: AExp, a2: AExp) extends BExp
-
-// atomic parsers
-case class TokParser(tok: Token) extends Parser[List[Token], Token] {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((t, ts))
- case _ => Set ()
- }
-}
-implicit def token2tparser(t: Token) = TokParser(t)
-
-case object NumParser extends Parser[List[Token], Int] {
- def parse(ts: List[Token]) = ts match {
- case T_NUM(s)::ts => Set((s.toInt, ts))
- case _ => Set ()
- }
-}
-
-case object IdParser extends Parser[List[Token], String] {
- def parse(ts: List[Token]) = ts match {
- case T_ID(s)::ts => Set((s, ts))
- case _ => Set ()
- }
-}
-
-
-// arithmetic expressions
-lazy val AExp: Parser[List[Token], AExp] =
- (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
- (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
-lazy val T: Parser[List[Token], AExp] =
- (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
-lazy val F: Parser[List[Token], AExp] =
- (T_LPAREN ~> AExp <~ T_RPAREN) ||
- IdParser ==> Var ||
- NumParser ==> Num
-
-// boolean expressions
-lazy val BExp: Parser[List[Token], BExp] =
- (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Bop("=", x, z): BExp } ||
- (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Bop("!=", x, z): BExp } ||
- (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Bop("<", x, z): BExp } ||
- (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Bop(">", x, z): BExp } ||
- (T_KWD("true") ==> ((_) => True)) ||
- (T_KWD("false") ==> ((_) => False: BExp))
-
-lazy val Stmt: Parser[List[Token], Stmt] =
- (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
- (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
- (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
- { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
- (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) }
-
-lazy val Stmts: Parser[List[Token], Block] =
- (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
- (Stmt ==> ((s) => List(s) : Block))
-
-lazy val Block: Parser[List[Token], Block] =
- (T_BEGIN ~> Stmts <~ T_END) ||
- (Stmt ==> ((s) => List(s)))
-
-
-// examples
-val p1 = "x := 5"
-val p1_toks = Tok.fromString(p1)
-val p1_ast = Block.parse_all(p1_toks)
-println(p1_toks)
-println(p1_ast)
-
-val p1a = "{ x := 5; y := 8}"
-val p1a_toks = Tok.fromString(p1a)
-val p1a_ast = Block.parse_all(p1a_toks)
-println(p1a_ast)
-
-val p2 = "5 = 6"
-val p2_toks = Tok.fromString(p2)
-val p2_ast = BExp.parse_all(p2_toks)
-println(p2_ast)
-
-val p2a = "true"
-val p2a_toks = Tok.fromString(p2a)
-val p2a_ast = BExp.parse_all(p2a_toks)
-println(p2a_ast)
-
-val p3 = "if true then skip else skip"
-val p3_toks = Tok.fromString(p3)
-val p3_ast = Stmt.parse_all(p3_toks)
-println(p3_ast)
-
-val p3a = "if true then x := 5 else x := 10"
-val p3a_toks = Tok.fromString(p3a)
-val p3a_ast = Stmt.parse_all(p3a_toks)
-println(p3a_ast)
-
-val p3b = "if false then x := 5 else x := 10"
-val p3b_toks = Tok.fromString(p3b)
-val p3b_ast = Stmt.parse_all(p3b_toks)
-println(p3b_ast)
-
-// multiplication
-val p4 = """{ x := 5;
- y := 4;
- r := 0;
- while y > 0 do {
- r := r + x;
- y := y - 1
- }
- }"""
-val p4_toks = Tok.fromString(p4)
-val p4_ast = Block.parse_all(p4_toks)
-println(p4_ast)
-
-val p5 = """
- n := 9;
- minus1 := 0;
- minus2 := 1;
- temp := 0;
- while n > 0 do {
- temp := minus2;
- minus2 := minus1 + minus2;
- minus1 := temp;
- n := n - 1
- };
- fib_res := minus2
-"""
-val p5_toks = Tok.fromString(p5)
-val p5_ast = Stmts.parse_all(p5_toks)
-
-// interpreter
-type Env = Map[String, Int]
-
-def eval_bexp(b: BExp, env: Env) : Boolean = b match {
- case True => true
- case False => false
- case Bop("=", a1, a2) => eval_aexp(a1, env) == eval_aexp(a2, env)
- case Bop("!=", a1, a2) => !(eval_aexp(a1, env) == eval_aexp(a2, env))
- case Bop(">", a1, a2) => eval_aexp(a1, env) > eval_aexp(a2, env)
- case Bop("<", a1, a2) => eval_aexp(a1, env) < eval_aexp(a2, env)
-}
-
-def eval_aexp(a: AExp, env : Env) : Int = a match {
- case Num(i) => i
- case Var(s) => env(s)
- case Aop("+", a1, a2) => eval_aexp(a1, env) + eval_aexp(a2, env)
- case Aop("-", a1, a2) => eval_aexp(a1, env) - eval_aexp(a2, env)
- case Aop("*", a1, a2) => eval_aexp(a1, env) * eval_aexp(a2, env)
-}
-
-def eval_stmt(s: Stmt, env: Env) : Env = s match {
- case Skip => env
- case Assign(x, a) => env + (x -> eval_aexp(a, env))
- case If(b, bl1, bl2) => if (eval_bexp(b, env)) eval_bl(bl1, env) else eval_bl(bl2, env)
- case While(b, bl) =>
- if (eval_bexp(b, env)) eval_stmt(While(b, bl), eval_bl(bl, env))
- else env
-}
-
-def eval_bl(bl: Block, env: Env) : Env = bl match {
- case Nil => env
- case s::bl => eval_bl(bl, eval_stmt(s, env))
-}
-
-//examples
-println(eval_stmt(p3a_ast.head, Map.empty))
-println(eval_stmt(p3b_ast.head, Map.empty))
-println(eval_bl(p4_ast.head, Map.empty))
-println(eval_bl(p5_ast.head, Map.empty))
--- a/scala/while1.scala Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,220 +0,0 @@
-// A parser and evaluator for the WHILE language
-//
-import matcher._
-import parser._
-
-
-// some regular expressions
-val SYM = RANGE("ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz_")
-val DIGIT = RANGE("0123456789")
-val ID = SEQ(SYM, STAR(ALT(SYM, DIGIT)))
-val NUM = PLUS(DIGIT)
-val KEYWORD = ALTS("skip", "while", "do", "if", "then", "else", "true", "false", "write")
-val SEMI: Rexp = ";"
-val OP: Rexp = ALTS(":=", "=", "-", "+", "*", "!=", "<", ">")
-val WHITESPACE = PLUS(RANGE(" \n"))
-val RPAREN: Rexp = ")"
-val LPAREN: Rexp = "("
-val BEGIN: Rexp = "{"
-val END: Rexp = "}"
-val COMMENT = SEQS("/*", NOT(SEQS(STAR(ALLC), "*/", STAR(ALLC))), "*/")
-
-// tokens for classifying the strings that have been recognised
-abstract class Token
-case object T_WHITESPACE extends Token
-case object T_COMMENT extends Token
-case object T_SEMI extends Token
-case object T_LPAREN extends Token
-case object T_RPAREN extends Token
-case object T_BEGIN extends Token
-case object T_END extends Token
-case class T_ID(s: String) extends Token
-case class T_OP(s: String) extends Token
-case class T_NUM(s: String) extends Token
-case class T_KWD(s: String) extends Token
-
-val lexing_rules: List[(Rexp, List[Char] => Token)] =
- List((KEYWORD, (s) => T_KWD(s.mkString)),
- (ID, (s) => T_ID(s.mkString)),
- (OP, (s) => T_OP(s.mkString)),
- (NUM, (s) => T_NUM(s.mkString)),
- (SEMI, (s) => T_SEMI),
- (LPAREN, (s) => T_LPAREN),
- (RPAREN, (s) => T_RPAREN),
- (BEGIN, (s) => T_BEGIN),
- (END, (s) => T_END),
- (WHITESPACE, (s) => T_WHITESPACE),
- (COMMENT, (s) => T_COMMENT))
-
-// the tokenizer
-val Tok = Tokenizer(lexing_rules, List(T_WHITESPACE, T_COMMENT))
-
-// the abstract syntax trees
-abstract class Stmt
-abstract class AExp
-abstract class BExp
-type Block = List[Stmt]
-case object Skip extends Stmt
-case class If(a: BExp, bl1: Block, bl2: Block) extends Stmt
-case class While(b: BExp, bl: Block) extends Stmt
-case class Assign(s: String, a: AExp) extends Stmt
-case class Write(s: String) extends Stmt
-
-case class Var(s: String) extends AExp
-case class Num(i: Int) extends AExp
-case class Aop(o: String, a1: AExp, a2: AExp) extends AExp
-
-case object True extends BExp
-case object False extends BExp
-case class Bop(o: String, a1: AExp, a2: AExp) extends BExp
-
-// atomic parsers
-case class TokParser(tok: Token) extends Parser[List[Token], Token] {
- def parse(ts: List[Token]) = ts match {
- case t::ts if (t == tok) => Set((t, ts))
- case _ => Set ()
- }
-}
-implicit def token2tparser(t: Token) = TokParser(t)
-
-case object NumParser extends Parser[List[Token], Int] {
- def parse(ts: List[Token]) = ts match {
- case T_NUM(s)::ts => Set((s.toInt, ts))
- case _ => Set ()
- }
-}
-
-case object IdParser extends Parser[List[Token], String] {
- def parse(ts: List[Token]) = ts match {
- case T_ID(s)::ts => Set((s, ts))
- case _ => Set ()
- }
-}
-
-
-// arithmetic expressions
-lazy val AExp: Parser[List[Token], AExp] =
- (T ~ T_OP("+") ~ AExp) ==> { case ((x, y), z) => Aop("+", x, z): AExp } ||
- (T ~ T_OP("-") ~ AExp) ==> { case ((x, y), z) => Aop("-", x, z): AExp } || T
-lazy val T: Parser[List[Token], AExp] =
- (F ~ T_OP("*") ~ T) ==> { case ((x, y), z) => Aop("*", x, z): AExp } || F
-lazy val F: Parser[List[Token], AExp] =
- (T_LPAREN ~> AExp <~ T_RPAREN) ||
- IdParser ==> Var ||
- NumParser ==> Num
-
-// boolean expressions
-lazy val BExp: Parser[List[Token], BExp] =
- (T_KWD("true") ==> ((_) => True: BExp)) ||
- (T_KWD("false") ==> ((_) => False: BExp)) ||
- (T_LPAREN ~> BExp <~ T_RPAREN) ||
- (AExp ~ T_OP("=") ~ AExp) ==> { case ((x, y), z) => Bop("=", x, z): BExp } ||
- (AExp ~ T_OP("!=") ~ AExp) ==> { case ((x, y), z) => Bop("!=", x, z): BExp } ||
- (AExp ~ T_OP("<") ~ AExp) ==> { case ((x, y), z) => Bop("<", x, z): BExp } ||
- (AExp ~ T_OP(">") ~ AExp) ==> { case ((x, y), z) => Bop("<", z, x): BExp }
-
-lazy val Stmt: Parser[List[Token], Stmt] =
- (T_KWD("skip") ==> ((_) => Skip: Stmt)) ||
- (IdParser ~ T_OP(":=") ~ AExp) ==> { case ((x, y), z) => Assign(x, z): Stmt } ||
- (T_KWD("if") ~ BExp ~ T_KWD("then") ~ Block ~ T_KWD("else") ~ Block) ==>
- { case (((((x,y),z),u),v),w) => If(y, u, w): Stmt } ||
- (T_KWD("while") ~ BExp ~ T_KWD("do") ~ Block) ==> { case (((x, y), z), w) => While(y, w) } ||
- (T_KWD("write") ~ IdParser) ==> { case (x, y) => Write(y) }
-
-lazy val Stmts: Parser[List[Token], Block] =
- (Stmt ~ T_SEMI ~ Stmts) ==> { case ((x, y), z) => x :: z : Block } ||
- (Stmt ==> ((s) => List(s) : Block))
-
-lazy val Block: Parser[List[Token], Block] =
- (T_BEGIN ~> Stmts <~ T_END) ||
- (Stmt ==> ((s) => List(s)))
-
-// interpreter
-type Env = Map[String, Int]
-
-def eval_bexp(b: BExp, env: Env) : Boolean = b match {
- case True => true
- case False => false
- case Bop("=", a1, a2) => eval_aexp(a1, env) == eval_aexp(a2, env)
- case Bop("!=", a1, a2) => !(eval_aexp(a1, env) == eval_aexp(a2, env))
- case Bop("<", a1, a2) => eval_aexp(a1, env) < eval_aexp(a2, env)
-}
-
-def eval_aexp(a: AExp, env : Env) : Int = a match {
- case Num(i) => i
- case Var(s) => env(s)
- case Aop("+", a1, a2) => eval_aexp(a1, env) + eval_aexp(a2, env)
- case Aop("-", a1, a2) => eval_aexp(a1, env) - eval_aexp(a2, env)
- case Aop("*", a1, a2) => eval_aexp(a1, env) * eval_aexp(a2, env)
-}
-
-def eval_stmt(s: Stmt, env: Env) : Env = s match {
- case Skip => env
- case Assign(x, a) => env + (x -> eval_aexp(a, env))
- case If(b, bl1, bl2) => if (eval_bexp(b, env)) eval_bl(bl1, env) else eval_bl(bl2, env)
- case While(b, bl) =>
- if (eval_bexp(b, env)) eval_stmt(While(b, bl), eval_bl(bl, env))
- else env
- case Write(x) => { println(env(x)); env }
-}
-
-def eval_bl(bl: Block, env: Env) : Env = bl match {
- case Nil => env
- case s::bl => eval_bl(bl, eval_stmt(s, env))
-}
-
-def eval_prog(name: String) : Env = {
- val tks = Tok.fromFile(name)
- val ast = Stmts.parse_single(tks)
- eval_bl(ast, Map.empty)
-}
-
-
-//examples
-
-//eval_prog("loops.while")
-eval_prog("fib.while")
-
-
-def time_needed[T](i: Int, code: => T) = {
- val start = System.nanoTime()
- for (j <- 1 to i) code
- val end = System.nanoTime()
- (end - start)/(i * 1.0e9)
-}
-
-
-val test_prog = """
-start := XXX;
-x := start;
-y := start;
-z := start;
-while 0 < x do {
- while 0 < y do {
- while 0 < z do {
- z := z - 1
- };
- z := start;
- y := y - 1
- };
- y := start;
- x := x - 1
-}
-"""
-
-
-
-def eval_test(n: Int) : Unit = {
- val tks = Tok.fromString(test_prog.replaceAllLiterally("XXX", n.toString))
- val ast = Stmts.parse_single(tks)
- println(n + " " + time_needed(2, eval_bl(ast, Map.empty)))
-}
-
-List(1, 200, 400, 600, 800, 1000, 1200, 1400, 1600).map(eval_test(_))
-
-
-
-
-
-
-
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/beamerthemeplainculight.sty Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,101 @@
+%%\Providespackage{beamerthemeplainculight}[2003/11/07 ver 0.93]
+\NeedsTeXFormat{LaTeX2e}[1995/12/01]
+
+% Copyright 2003 by Till Tantau <tantau@cs.tu-berlin.de>.
+%
+% This program can be redistributed and/or modified under the terms
+% of the LaTeX Project Public License Distributed from CTAN
+% archives in directory macros/latex/base/lppl.txt.
+
+\newcommand{\slidecaption}{}
+
+\mode<presentation>
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% comic fonts fonts
+\DeclareFontFamily{T1}{comic}{}%
+\DeclareFontShape{T1}{comic}{m}{n}{<->s*[.9]comic8t}{}%
+\DeclareFontShape{T1}{comic}{m}{it}{<->s*[.9]comic8t}{}%
+\DeclareFontShape{T1}{comic}{m}{sc}{<->s*[.9]comic8t}{}%
+\DeclareFontShape{T1}{comic}{b}{n}{<->s*[.9]comicbd8t}{}%
+\DeclareFontShape{T1}{comic}{b}{it}{<->s*[.9]comicbd8t}{}%
+\DeclareFontShape{T1}{comic}{m}{sl}{<->ssub * comic/m/it}{}%
+\DeclareFontShape{T1}{comic}{b}{sc}{<->sub * comic/m/sc}{}%
+\DeclareFontShape{T1}{comic}{b}{sl}{<->ssub * comic/b/it}{}%
+\DeclareFontShape{T1}{comic}{bx}{n}{<->ssub * comic/b/n}{}%
+\DeclareFontShape{T1}{comic}{bx}{it}{<->ssub * comic/b/it}{}%
+\DeclareFontShape{T1}{comic}{bx}{sc}{<->sub * comic/m/sc}{}%
+\DeclareFontShape{T1}{comic}{bx}{sl}{<->ssub * comic/b/it}{}%
+%
+\renewcommand{\rmdefault}{comic}%
+\renewcommand{\sfdefault}{comic}%
+\renewcommand{\mathfamilydefault}{cmr}% mathfont should be still the old one
+%
+\DeclareMathVersion{bold}% mathfont needs to be bold
+\DeclareSymbolFont{operators}{OT1}{cmr}{b}{n}%
+\SetSymbolFont{operators}{bold}{OT1}{cmr}{b}{n}%
+\DeclareSymbolFont{letters}{OML}{cmm}{b}{it}%
+\SetSymbolFont{letters}{bold}{OML}{cmm}{b}{it}%
+\DeclareSymbolFont{symbols}{OMS}{cmsy}{b}{n}%
+\SetSymbolFont{symbols}{bold}{OMS}{cmsy}{b}{n}%
+\DeclareSymbolFont{largesymbols}{OMX}{cmex}{b}{n}%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% Frametitles
+\setbeamerfont{frametitle}{size={\LARGE}}
+\setbeamerfont{frametitle}{family={\usefont{T1}{ptm}{b}{n}}}
+\setbeamercolor{frametitle}{fg=ProcessBlue,bg=white}
+
+\setbeamertemplate{frametitle}{%
+\vskip 2mm % distance from the top margin
+\hskip -3mm % distance from left margin
+\vbox{%
+\begin{minipage}{1.05\textwidth}%
+\centering%
+\insertframetitle%
+\end{minipage}}%
+}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% Foot
+%
+\setbeamertemplate{navigation symbols}{}
+\usefoottemplate{%
+\vbox{%
+ \tinyline{%
+ \tiny\hfill\textcolor{gray!50}{\slidecaption{} --
+ p.~\insertframenumber/\inserttotalframenumber}}}%
+}
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\beamertemplateballitem
+\setlength\leftmargini{2mm}
+\setlength\leftmarginii{0.6cm}
+\setlength\leftmarginiii{1.5cm}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% blocks
+%\definecolor{cream}{rgb}{1,1,.65}
+\definecolor{cream}{rgb}{1,1,.8}
+\setbeamerfont{block title}{size=\normalsize}
+\setbeamercolor{block title}{fg=black,bg=cream}
+\setbeamercolor{block body}{fg=black,bg=cream}
+
+\setbeamertemplate{blocks}[rounded][shadow=true]
+
+\setbeamercolor{boxcolor}{fg=black,bg=cream}
+
+\mode
+<all>
+
+
+
+
+
+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/compiled.data Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,13 @@
+%% LaTeX2e file `compiled.data'
+%% generated by the `filecontents' environment
+%% from source `slides09' on 2012/11/28.
+%%
+%1 0.234146
+%5000 0.227539
+%10000 0.280748
+50000 1.087897
+100000 3.713165
+250000 21.6624545
+500000 85.872613
+750000 203.6408015
+1000000 345.736574
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/compiled2.data Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,11 @@
+%% LaTeX2e file `compiled2.data'
+%% generated by the `filecontents' environment
+%% from source `slides09' on 2012/11/28.
+%%
+200 0.222058
+400 0.215204
+600 0.202031
+800 0.21986
+1000 0.205934
+1200 0.1981615
+1400 0.207116
Binary file slides/getting-info-from-the-internet.jpg has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/interpreted.data Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,13 @@
+%% LaTeX2e file `interpreted.data'
+%% generated by the `filecontents' environment
+%% from source `slides09' on 2012/11/28.
+%%
+%1 0.00503
+200 1.005863
+400 7.8296765
+500 15.43106
+600 27.2321885
+800 65.249271
+1000 135.4493445
+1200 232.134097
+1400 382.527227
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/interpreted2.data Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,12 @@
+%% LaTeX2e file `interpreted2.data'
+%% generated by the `filecontents' environment
+%% from source `slides09' on 2012/11/28.
+%%
+%1 0.00503
+200 1.005863
+400 7.8296765
+600 27.2321885
+800 65.249271
+1000 135.4493445
+1200 232.134097
+1400 382.527227
Binary file slides/slides01.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides01.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,483 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 01, King's College London, 26.~September 2012}
+
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (1)\\[-3mm]
+ \end{tabular}}
+
+ \begin{center}
+ \includegraphics[scale=0.3]{pics/ante1.jpg}\hspace{5mm}
+ \includegraphics[scale=0.31]{pics/ante2.jpg}\\
+ \footnotesize\textcolor{gray}{Antikythera automaton, 100 BC (Archimedes?)}
+ \end{center}
+
+\normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{textblock}{1}(2,5)
+\begin{tabular}{c}
+\includegraphics[scale=0.15]{pics/servers.png}\\[-2mm]
+\small Server
+\end{tabular}
+\end{textblock}
+
+\begin{textblock}{1}(5.6,4)
+ \begin{tikzpicture}[scale=1.1]
+ \draw[white] (0,1) node (X) {};
+ \draw[white] (2,1) node (Y) {};
+ \draw[white] (0,0) node (X1) {};
+ \draw[white] (2,0) node (Y1) {};
+ \draw[white] (0,-1) node (X2) {};
+ \draw[white] (2,-1) node (Y2) {};
+ \draw[red, <-, line width = 2mm] (X) -- (Y);
+ \node [inner sep=5pt,label=above:\textcolor{black}{GET request}] at ($ (X)!.5!(Y) $) {};
+ \draw[red, ->, line width = 2mm] (X1) -- (Y1);
+ \node [inner sep=5pt,label=above:\textcolor{black}{webpage}] at ($ (X1)!.5!(Y1) $) {};
+ \draw[red, <-, line width = 2mm] (X2) -- (Y2);
+ \node [inner sep=7pt,label=above:\textcolor{black}{POST data}] at ($ (X2)!.5!(Y2) $) {};
+ \end{tikzpicture}
+\end{textblock}
+
+
+\begin{textblock}{1}(9,5.5)
+\begin{tabular}{c}
+\includegraphics[scale=0.15]{pics/laptop.png}\\[-2mm]
+\small Browser
+\end{tabular}
+\end{textblock}
+
+\only<2>{
+\begin{textblock}{10}(2,13.5)
+\begin{itemize}
+\item programming languages, compilers
+\end{itemize}
+\end{textblock}}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+transforming strings into structured data\\[10mm]
+
+{\LARGE\bf Lexing}\medskip\\
+\hspace{5mm}(recognising ``words'')\\[6mm]
+
+{\LARGE\bf Parsing}\medskip\\
+\hspace{5mm}(recognising ``sentences'')
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+The subject is quite old:
+
+\begin{itemize}
+\item Turing Machines, 1936
+\item first compiler for COBOL, 1957 (Grace Hopper)
+\item but surprisingly research papers are still published now
+\end{itemize}
+
+\begin{flushright}
+\includegraphics[scale=0.3]{pics/hopper.jpg}\\
+\footnotesize\textcolor{gray}{Grace Hopper}
+\end{flushright}
+
+{\footnotesize\textcolor{gray}{(she made it to David Letterman's Tonight Show, \url{http://www.youtube.com/watch?v=aZOxtURhfEU})}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}This Course\end{tabular}}
+
+\begin{itemize}
+\item the ultimate goal is to implement a small web-browser (really small one)\bigskip
+\end{itemize}
+
+Let's start with:
+
+\begin{itemize}
+\item a web-crawler
+\item an email harvester
+\item a web-scraper
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}A Web-Crawler\end{tabular}}
+
+\mbox{}\\[10mm]
+
+\begin{enumerate}
+\item given an URL, read the corresponding webpage
+\item extract all links from it
+\item call the web-crawler again for all these links
+\end{enumerate}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}A Web-Crawler\end{tabular}}
+
+\mbox{}\\[10mm]
+
+
+\begin{enumerate}
+\item given an URL, read the corresponding webpage
+\item if not possible print, out a problem
+\item if possible, extract all links from it
+\item call the web-crawler again for all these links
+\end{enumerate}\bigskip\pause
+
+\small (we need a bound for the number of recursive calls)
+
+\small (the purpose is to check all links on my own webpage)
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Scala\end{tabular}}
+
+\footnotesize a simple Scala function for reading webpages\\[-3mm]
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app0.scala}}}\pause
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinline{get_page("""http://www.inf.kcl.ac.uk/staff/urbanc/""")}}}\pause\bigskip
+
+
+\footnotesize slightly more complicated for handling errors properly:\\[-3mm]
+
+\footnotesize
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app1.scala}}}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}A Regular Expression\end{tabular}}
+
+\begin{itemize}
+\item \ldots{} is a pattern or template for specifying strings
+\end{itemize}\bigskip
+
+\begin{center}
+\only<1>{{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
+\texttt{"https?://[$\hat{\hspace{2mm}}$"]*"}}}%
+\only<2>{{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
+\texttt{"""\textbackslash{}"https?://[$\hat{\hspace{2mm}}$\textbackslash{}"]*\textbackslash{}"""".r}}}
+\end{center}\bigskip\bigskip
+
+matches for example\\
+\;{\lstset{language=Scala}\fontsize{12}{14}\selectfont\bf
+\texttt{"http://www.foobar.com"}}\\
+\;{\lstset{language=Scala}\fontsize{12}{14}\selectfont\bf
+\texttt{"https://www.tls.org"}}\\
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
+\texttt{rexp.findAllIn(string)}}\medskip
+
+returns a list of all (sub)strings that match the regular expression\bigskip\bigskip
+
+{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
+\texttt{rexp.findFirstIn(string)}}\medskip
+
+returns either {\bf\texttt{None}} if no (sub)string matches
+or {\bf\texttt{Some(s)}} with the first (sub)string
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app2.scala}}}\medskip
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{crawl(some\_start\_URL, 2)}}\
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\footnotesize
+a version that only ``crawls'' links in my domain:
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app3.scala}}}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\footnotesize
+a little email ``harvester'':
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app4.scala}}}\bigskip
+
+\tiny
+\textcolor{gray}{\url{http://net.tutsplus.com/tutorials/other/8-regular-expressions-you-should-know/}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
+
+Their inductive definition:\medskip
+
+\begin{textblock}{6}(2,5)
+ \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
+ \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
+ & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
+ & \bl{$\mid$} & \bl{c} & character\\
+ & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
+ & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
+ & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
+ \end{tabular}
+ \end{textblock}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
+
+\small
+In Scala:
+
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app51.scala}}}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Meaning of a\\[-2mm] Regular Expression\end{tabular}}
+
+\begin{textblock}{15}(1,4)
+ \begin{tabular}{@ {}rcl}
+ \bl{$L$($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$}\\
+ \bl{$L$($\epsilon$)} & \bl{$\dn$} & \bl{$\{$""$\}$}\\
+ \bl{$L$(c)} & \bl{$\dn$} & \bl{$\{$"c"$\}$}\\
+ \bl{$L$(r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{$L$(r$_1$) $\cup$ $L$(r$_2$)}\\
+ \bl{$L$(r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{$\{$ s$_1$ @ s$_2$ $|$ s$_1$ $\in$ $L$(r$_1$) $\wedge$ s$_2$ $\in$
+ $L$(r$_2$) $\}$}\\
+ \bl{$L$(r$^*$)} & \bl{$\dn$} & \onslide<4->{\bl{$\bigcup_{n \ge 0}$ $L$(r)$^n$}}\\
+ \end{tabular}\bigskip
+
+\onslide<2->{
+\hspace{5mm}\bl{$L$(r)$^0$ $\;\dn\;$ $\{$""$\}$}\\
+\bl{$L$(r)$^{n+1}$ $\;\dn\;$ $L$(r) @ $L$(r)$^n$}\hspace{9mm}\onslide<3->{\small\textcolor{gray}{(append on sets)}\\
+\small\hspace{5cm}\textcolor{gray}{$\{$ s$_1$ @ s$_2$ $|$ s$_1$ $\in$ $L$(r) $\wedge$ s$_2$ $\in$
+ $L$(r)$^n$ $\}$}}
+}
+ \end{textblock}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Meaning of Matching\end{tabular}}
+
+\large
+a regular expression \bl{r} matches a string \bl{s} is defined as
+
+\begin{center}
+\bl{s $\in$ $L$(r)}\\
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}This Course\end{tabular}}
+
+We will have a look at:
+
+\begin{itemize}
+\item regular expressions / regular expression matching
+\item automata
+\item the Myhill-Nerode theorem
+\item parsing
+\item grammars
+\item a small interpreter / web browser
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Exam\end{tabular}}
+
+\begin{itemize}
+\item The question ``Is this relevant for the exam?'' is not appreciated!\bigskip\\
+
+Whatever is in the homework sheets (and is not marked ``optional'') is relevant for the
+exam.\\ No code needs to be written in the exam.
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides02.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides02.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,494 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 02, King's College London, 3.~October 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (2)\\[3mm]
+ \end{tabular}}
+
+ %\begin{center}
+ %\includegraphics[scale=0.3]{pics/ante1.jpg}\hspace{5mm}
+ %\includegraphics[scale=0.31]{pics/ante2.jpg}\\
+ %\footnotesize\textcolor{gray}{Antikythera automaton, 100 BC (Archimedes?)}
+ %\end{center}
+
+\normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Languages\end{tabular}}
+
+A \alert{language} is a set of strings.\bigskip
+
+A \alert{regular expression} specifies a set of strings or language.
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
+
+Their inductive definition:
+
+
+\begin{textblock}{6}(2,5)
+ \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
+ \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
+ & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
+ & \bl{$\mid$} & \bl{c} & character\\
+ & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
+ & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
+ & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
+ \end{tabular}
+ \end{textblock}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
+
+Their implementation in Scala:
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app51.scala}}}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Meaning of a\\[-2mm] Regular Expression\end{tabular}}
+
+\begin{textblock}{15}(1,4)
+ \begin{tabular}{@ {}rcl}
+ \bl{$L$($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$}\\
+ \bl{$L$($\epsilon$)} & \bl{$\dn$} & \bl{$\{$""$\}$}\\
+ \bl{$L$(c)} & \bl{$\dn$} & \bl{$\{$"c"$\}$}\\
+ \bl{$L$(r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{$L$(r$_1$) $\cup$ $L$(r$_2$)}\\
+ \bl{$L$(r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{$L$(r$_1$) @ $L$(r$_2$)}\\
+ \bl{$L$(r$^*$)} & \bl{$\dn$} & \bl{$\bigcup_{n \ge 0}$ $L$(r)$^n$}\\
+ \end{tabular}\bigskip
+
+\hspace{5mm}\textcolor{gray}{$L$(r)$^0$ $\;\dn\;$ $\{$""$\}$}\\
+\textcolor{gray}{$L$(r)$^{n+1}$ $\;\dn\;$ $L$(r) @ $L$(r)$^n$}
+\end{textblock}
+
+\only<2->{
+\begin{textblock}{5}(11,5)
+\textcolor{gray}{\small
+A @ B\\
+\ldots you take out every string from A and
+concatenate it with every string in B
+}
+\end{textblock}}
+
+\only<3->{
+\begin{textblock}{6}(9,12)\small
+\bl{$L$} is a function from regular expressions to sets of strings\\
+\bl{$L$ : Rexp $\Rightarrow$ Set[String]}
+\end{textblock}}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\large
+\begin{center}
+What is \bl{$L$(a$^*$)}?
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+\newcommand{\YES}{\textcolor{gray}{yes}}
+\newcommand{\NO}{\textcolor{gray}{no}}
+\newcommand{\FORALLR}{\textcolor{gray}{$\forall$ r.}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Reg Exp Equivalences\end{tabular}}
+
+\begin{center}
+\begin{tabular}{l@ {\hspace{7mm}}rcl@ {\hspace{7mm}}l}
+&\bl{(a + b) + c} & \bl{$\equiv^?$} & \bl{a + (b + c)} & \onslide<2->{\YES}\\
+&\bl{a + a} & \bl{$\equiv^?$} & \bl{a} & \onslide<3->{\YES}\\
+&\bl{(a $\cdot$ b) $\cdot$ c} & \bl{$\equiv^?$} & \bl{a $\cdot$ (b $\cdot$ c)} & \onslide<4->{\YES}\\
+&\bl{a $\cdot$ a} & \bl{$\equiv^?$} & \bl{a} & \onslide<5->{\NO}\\
+&\bl{$\epsilon^*$} & \bl{$\equiv^?$} & \bl{$\epsilon$} & \onslide<6->{\YES}\\
+&\bl{$\varnothing^*$} & \bl{$\equiv^?$} & \bl{$\varnothing$} & \onslide<7->{\NO}\\
+\FORALLR &\bl{r $\cdot$ $\epsilon$} & \bl{$\equiv^?$} & \bl{r} & \onslide<8->{\YES}\\
+\FORALLR &\bl{r + $\epsilon$} & \bl{$\equiv^?$} & \bl{r} & \onslide<9->{\NO}\\
+\FORALLR &\bl{r + $\varnothing$} & \bl{$\equiv^?$} & \bl{r} & \onslide<10->{\YES}\\
+\FORALLR &\bl{r $\cdot$ $\varnothing$} & \bl{$\equiv^?$} & \bl{r} & \onslide<11->{\NO}\\
+&\bl{c $\cdot$ (a + b)} & \bl{$\equiv^?$} & \bl{(c $\cdot$ a) + (c $\cdot$ b)} & \onslide<12->{\YES}\\
+&\bl{a$^*$} & \bl{$\equiv^?$} & \bl{$\epsilon$ + (a $\cdot$ a$^*$)} & \onslide<13->{\YES}
+\end{tabular}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Meaning of Matching\end{tabular}}
+
+\large
+a regular expression \bl{r} matches a string \bl{s} is defined as
+
+\begin{center}
+\bl{s $\in$ $L$(r)}\\
+\end{center}\bigskip\bigskip\pause
+
+\small
+if \bl{r$_1$ $\equiv$ r$_2$}, then \bl{$s$ $\in$ $L$(r$_1$)} iff \bl{$s$ $\in$ $L$(r$_2$)}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}A Matching Algorithm\end{tabular}}
+
+\begin{itemize}
+\item given a regular expression \bl{r} and a string \bl{s}, say yes or no for whether
+\begin{center}
+\bl{s $\in$ $L$(r)}
+\end{center}
+or not.\bigskip\bigskip\pause
+\end{itemize}\pause
+
+\small
+\begin{itemize}
+\item Identifiers (strings of letters or digits, starting with a letter)
+\item Integers (a non-empty sequence of digits)
+\item Keywords (else, if, while, \ldots)
+\item White space (a non-empty sequence of blanks, newlines and tabs)
+\end{itemize}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}A Matching Algorithm\end{tabular}}
+
+\small
+whether a regular expression matches the empty string:\medskip
+
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app5.scala}}}
+
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Derivative of a Rexp\end{tabular}}
+
+\large
+If \bl{r} matches the string \bl{c::s}, what is a regular expression that matches \bl{s}?\bigskip\bigskip\bigskip\bigskip
+
+\small
+\bl{der c r} gives the answer
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Derivative of a Rexp (2)\end{tabular}}
+
+\begin{center}
+\begin{tabular}{@ {}l@ {\hspace{2mm}}c@ {\hspace{2mm}}l@ {\hspace{-10mm}}l@ {}}
+ \bl{der c ($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
+ \bl{der c ($\epsilon$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
+ \bl{der c (d)} & \bl{$\dn$} & \bl{if c $=$ d then $\epsilon$ else $\varnothing$} & \\
+ \bl{der c (r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{(der c r$_1$) + (der c r$_2$)} & \\
+ \bl{der c (r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{if nullable r$_1$}\\
+ & & \bl{then ((der c r$_1$) $\cdot$ r$_2$) + (der c r$_2$)}\\
+ & & \bl{else (der c r$_1$) $\cdot$ r$_2$}\\
+ \bl{der c (r$^*$)} & \bl{$\dn$} & \bl{(der c r) $\cdot$ (r$^*$)} &\smallskip\\\pause
+
+ \bl{ders [] r} & \bl{$\dn$} & \bl{r} & \\
+ \bl{ders (c::s) r} & \bl{$\dn$} & \bl{ders s (der c r)} & \\
+ \end{tabular}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Derivative\end{tabular}}
+
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app6.scala}}}
+
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Rexp Matcher\end{tabular}}
+
+
+{\lstset{language=Scala}\fontsize{8}{10}\selectfont
+\texttt{\lstinputlisting{app7.scala}}}
+
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Proofs about Rexp\end{tabular}}
+
+Remember their inductive definition:\\[5cm]
+
+\begin{textblock}{6}(5,5)
+ \begin{tabular}{@ {}rrl}
+ \bl{r} & \bl{$::=$} & \bl{$\varnothing$}\\
+ & \bl{$\mid$} & \bl{$\epsilon$} \\
+ & \bl{$\mid$} & \bl{c} \\
+ & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$}\\
+ & \bl{$\mid$} & \bl{r$_1$ + r$_2$} \\
+ & \bl{$\mid$} & \bl{r$^*$} \\
+ \end{tabular}
+ \end{textblock}
+
+If we want to prove something, say a property \bl{$P$(r)}, for all regular expressions \bl{r} then \ldots
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Proofs about Rexp (2)\end{tabular}}
+
+\begin{itemize}
+\item \bl{$P$} holds for \bl{$\varnothing$}, \bl{$\epsilon$} and \bl{c}\bigskip
+\item \bl{$P$} holds for \bl{r$_1$ + r$_2$} under the assumption that \bl{$P$} already
+holds for \bl{r$_1$} and \bl{r$_2$}.\bigskip
+\item \bl{$P$} holds for \bl{r$_1$ $\cdot$ r$_2$} under the assumption that \bl{$P$} already
+holds for \bl{r$_1$} and \bl{r$_2$}.
+\item \bl{$P$} holds for \bl{r$^*$} under the assumption that \bl{$P$} already
+holds for \bl{r}.
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Proofs about Rexp (3)\end{tabular}}
+
+Assume \bl{$P(r)$} is the property:
+
+\begin{center}
+\bl{nullable(r)} if and only if \bl{"" $\in$ $L$(r)}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Proofs about Strings\end{tabular}}
+
+If we want to prove something, say a property \bl{$P$(s)}, for all strings \bl{s} then \ldots\bigskip
+
+\begin{itemize}
+\item \bl{$P$} holds for the empty string, and\medskip
+\item \bl{$P$} holds for the string \bl{c::s} under the assumption that \bl{$P$}
+already holds for \bl{s}
+\end{itemize}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Proofs about Strings (2)\end{tabular}}
+
+Let \bl{Der c A} be the set defined as
+
+\begin{center}
+\bl{Der c A $\dn$ $\{$ s $|$ c::s $\in$ A$\}$ }
+\end{center}
+
+Assume that \bl{$L$(der c r) = Der c ($L$(r))}. Prove that
+
+\begin{center}
+\bl{matcher(r, s) if and only if s $\in$ $L$(r)}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Regular Languages\end{tabular}}
+
+A language (set of strings) is \alert{regular} iff there exists
+a regular expression that recognises all its strings.
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Automata\end{tabular}}
+
+A deterministic finite automaton consists of:
+
+\begin{itemize}
+\item a set of states
+\item one of these states is the start state
+\item some states are accepting states, and
+\item there is transition function\medskip
+
+\small
+which takes a state as argument and a character and produces a new state\smallskip\\
+this function might not always be defined
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides03.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides03.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,386 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 03, King's College London, 10.~October 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (3)\\[3mm]
+ \end{tabular}}
+
+ %\begin{center}
+ %\includegraphics[scale=0.3]{pics/ante1.jpg}\hspace{5mm}
+ %\includegraphics[scale=0.31]{pics/ante2.jpg}\\
+ %\footnotesize\textcolor{gray}{Antikythera automaton, 100 BC (Archimedes?)}
+ %\end{center}
+
+\normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ & \alert{\bf (I have put a temporary link in there.)}\\
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Last Week\end{tabular}}
+
+Last week I showed you
+
+\begin{itemize}
+\item one simple-minded regular expression matcher (which however does not work in all cases), and\bigskip
+\item one which works provably in all cases
+
+\begin{center}
+\bl{matcher r s} \;\;if and only if \;\; \bl{s $\in$ $L$(r)}
+\end{center}
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Derivative of a Rexp\end{tabular}}
+
+\begin{center}
+\begin{tabular}{@ {}l@ {\hspace{2mm}}c@ {\hspace{2mm}}l@ {\hspace{-10mm}}l@ {}}
+ \bl{der c ($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
+ \bl{der c ($\epsilon$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
+ \bl{der c (d)} & \bl{$\dn$} & \bl{if c $=$ d then $\epsilon$ else $\varnothing$} & \\
+ \bl{der c (r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{(der c r$_1$) + (der c r$_2$)} & \\
+ \bl{der c (r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{if nullable r$_1$}\\
+ & & \bl{then ((der c r$_1$) $\cdot$ r$_2$) + (der c r$_2$)}\\
+ & & \bl{else (der c r$_1$) $\cdot$ r$_2$}\\
+ \bl{der c (r$^*$)} & \bl{$\dn$} & \bl{(der c r) $\cdot$ (r$^*$)}\\
+ \end{tabular}
+\end{center}
+
+``the regular expression after \bl{c} has been recognised''
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+For this we defined the set \bl{Der c A} as
+
+\begin{center}
+\bl{Der c A $\dn$ $\{$ s $|$ c::s $\in$ A$\}$ }
+\end{center}
+
+which is called the semantic derivative of a set
+and proved
+
+\begin{center}
+\bl{$L$(der c r) $=$ Der c ($L$(r))}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}The Idea of the Algorithm\end{tabular}}
+
+If we want to recognise the string \bl{abc} with regular expression \bl{r}
+then\medskip
+
+\begin{enumerate}
+\item \bl{Der a ($L$(r))}\pause
+\item \bl{Der b (Der a ($L$(r)))}
+\item \bl{Der c (Der b (Der a ($L$(r))))}\pause
+\item finally we test whether the empty string is in set\pause\medskip
+\end{enumerate}
+
+The matching algorithm works similarly, just over regular expression than sets.
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Input: string \bl{abc} and regular expression \bl{r}
+
+\begin{enumerate}
+\item \bl{der a r}
+\item \bl{der b (der a r)}
+\item \bl{der c (der b (der a r))}\pause
+\item finally check whether the latter regular expression can match the empty string
+\end{enumerate}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+We need to prove
+
+\begin{center}
+\bl{$L$(der c r) $=$ Der c ($L$(r))}
+\end{center}
+
+by induction on the regular expression.
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Proofs about Rexp\end{tabular}}
+
+\begin{itemize}
+\item \bl{$P$} holds for \bl{$\varnothing$}, \bl{$\epsilon$} and \bl{c}\bigskip
+\item \bl{$P$} holds for \bl{r$_1$ + r$_2$} under the assumption that \bl{$P$} already
+holds for \bl{r$_1$} and \bl{r$_2$}.\bigskip
+\item \bl{$P$} holds for \bl{r$_1$ $\cdot$ r$_2$} under the assumption that \bl{$P$} already
+holds for \bl{r$_1$} and \bl{r$_2$}.
+\item \bl{$P$} holds for \bl{r$^*$} under the assumption that \bl{$P$} already
+holds for \bl{r}.
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Proofs about Natural Numbers\\ and Strings\end{tabular}}
+
+\begin{itemize}
+\item \bl{$P$} holds for \bl{$0$} and
+\item \bl{$P$} holds for \bl{$n + 1$} under the assumption that \bl{$P$} already
+holds for \bl{$n$}
+\end{itemize}\bigskip
+
+\begin{itemize}
+\item \bl{$P$} holds for \bl{\texttt{""}} and
+\item \bl{$P$} holds for \bl{$c\!::\!s$} under the assumption that \bl{$P$} already
+holds for \bl{$s$}
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
+
+\begin{center}
+ \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
+ \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
+ & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
+ & \bl{$\mid$} & \bl{c} & character\\
+ & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
+ & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
+ & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
+ \end{tabular}\bigskip\pause
+ \end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Languages\end{tabular}}
+
+A \alert{language} is a set of strings.\bigskip
+
+A \alert{regular expression} specifies a set of strings or language.\bigskip
+
+A language is \alert{regular} iff there exists
+a regular expression that recognises all its strings.\bigskip\bigskip\pause
+
+\textcolor{gray}{not all languages are regular, e.g.~\bl{a$^n$b$^n$}.}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
+
+\begin{center}
+ \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
+ \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
+ & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
+ & \bl{$\mid$} & \bl{c} & character\\
+ & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
+ & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
+ & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
+ \end{tabular}\bigskip
+ \end{center}
+
+How about ranges \bl{[a-z]}, \bl{r$^\text{+}$} and \bl{!r}?
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Negation of Regular Expr's\end{tabular}}
+
+\begin{itemize}
+\item \bl{!r} \hspace{6mm} (everything that \bl{r} cannot recognise)\medskip
+\item \bl{$L$(!r) $\dn$ UNIV - $L$(r)}\medskip
+\item \bl{nullable (!r) $\dn$ not (nullable(r))}\medskip
+\item \bl{der\,c\,(!r) $\dn$ !(der\,c\,r)}
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Regular Exp's for Lexing\end{tabular}}
+
+Lexing separates strings into ``words'' / components.
+
+\begin{itemize}
+\item Identifiers (non-empty strings of letters or digits, starting with a letter)
+\item Numbers (non-empty sequences of digits omitting leading zeros)
+\item Keywords (else, if, while, \ldots)
+\item White space (a non-empty sequence of blanks, newlines and tabs)
+\item Comments
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Automata\end{tabular}}
+
+A deterministic finite automaton consists of:
+
+\begin{itemize}
+\item a set of states
+\item one of these states is the start state
+\item some states are accepting states, and
+\item there is transition function\medskip
+
+\small
+which takes a state as argument and a character and produces a new state\smallskip\\
+this function might not always be defined
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides04.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides04.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,612 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 04, King's College London, 17.~October 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (4)\\[3mm]
+ \end{tabular}}
+
+ \normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Last Week\end{tabular}}
+
+Last week I showed you\bigskip
+
+\begin{itemize}
+\item a tokenizer taking a list of regular expressions\bigskip
+
+\item tokenization identifies lexeme in an input stream of characters (or string)
+and cathegorizes them into tokens
+
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Two Rules\end{tabular}}
+
+\begin{itemize}
+\item Longest match rule (maximal munch rule): The
+longest initial substring matched by any regular expression is taken
+as next token.\bigskip
+
+\item Rule priority:
+For a particular longest initial substring, the first regular
+expression that can match determines the token.
+
+\end{itemize}
+
+%\url{http://www.technologyreview.com/tr10/?year=2011}
+
+%finite deterministic automata/ nondeterministic automaton
+
+%\item problem with infix operations, for example i-12
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\mode<presentation>{
+\begin{frame}[t]
+
+\begin{center}
+\texttt{"if true then then 42 else +"}
+\end{center}
+
+
+\begin{tabular}{@{}l}
+KEYWORD: \\
+\hspace{5mm}\texttt{"if"}, \texttt{"then"}, \texttt{"else"},\\
+WHITESPACE:\\
+\hspace{5mm}\texttt{" "}, \texttt{"$\backslash$n"},\\
+IDENT:\\
+\hspace{5mm}LETTER $\cdot$ (LETTER + DIGIT + \texttt{"\_"})$^*$\\
+NUM:\\
+\hspace{5mm}(NONZERODIGIT $\cdot$ DIGIT$^*$) + \texttt{"0"}\\
+OP:\\
+\hspace{5mm}\texttt{"+"}\\
+COMMENT:\\
+\hspace{5mm}\texttt{"$\slash$*"} $\cdot$ (ALL$^*$ $\cdot$ \texttt{"*$\slash$"} $\cdot$ ALL$^*$) $\cdot$ \texttt{"*$\slash$"}
+\end{tabular}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+
+\begin{center}
+\texttt{"if true then then 42 else +"}
+\end{center}
+
+\only<1>{
+\small\begin{tabular}{l}
+KEYWORD(if),\\
+WHITESPACE,\\
+IDENT(true),\\
+WHITESPACE,\\
+KEYWORD(then),\\
+WHITESPACE,\\
+KEYWORD(then),\\
+WHITESPACE,\\
+NUM(42),\\
+WHITESPACE,\\
+KEYWORD(else),\\
+WHITESPACE,\\
+OP(+)
+\end{tabular}}
+
+\only<2>{
+\small\begin{tabular}{l}
+KEYWORD(if),\\
+IDENT(true),\\
+KEYWORD(then),\\
+KEYWORD(then),\\
+NUM(42),\\
+KEYWORD(else),\\
+OP(+)
+\end{tabular}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+
+There is one small problem with the tokenizer. How should we
+tokenize:
+
+\begin{center}
+\texttt{"x - 3"}
+\end{center}
+
+\begin{tabular}{@{}l}
+OP:\\
+\hspace{5mm}\texttt{"+"}, \texttt{"-"}\\
+NUM:\\
+\hspace{5mm}(NONZERODIGIT $\cdot$ DIGIT$^*$) + \texttt{"0"}\\
+NUMBER:\\
+\hspace{5mm}NUM + (\texttt{"-"} $\cdot$ NUM)\\
+\end{tabular}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Negation\end{tabular}}
+
+Assume you have an alphabet consisting of the letters \bl{a}, \bl{b} and \bl{c} only.
+Find a regular expression that matches all strings \emph{except} \bl{ab}, \bl{ac} and \bl{cba}.
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Deterministic Finite Automata\end{tabular}}
+
+A deterministic finite automaton consists of:
+
+\begin{itemize}
+\item a finite set of states
+\item one of these states is the start state
+\item some states are accepting states, and
+\item there is transition function\medskip
+
+\small
+which takes a state and a character as arguments and produces a new state\smallskip\\
+this function might not always be defined everywhere
+\end{itemize}
+
+\begin{center}
+\bl{$A(Q, q_0, F, \delta)$}
+\end{center}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\includegraphics[scale=0.7]{pics/ch3.jpg}
+\end{center}\pause
+
+\begin{itemize}
+\item start can be an accepting state
+\item it is possible that there is no accepting state
+\item all states might be accepting (but does not necessarily mean all strings are accepted)
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\includegraphics[scale=0.7]{pics/ch3.jpg}
+\end{center}
+
+for this automaton \bl{$\delta$} is the function\\
+
+\begin{center}
+\begin{tabular}{lll}
+\bl{(q$_0$, a) $\rightarrow$ q$_1$} & \bl{(q$_1$, a) $\rightarrow$ q$_4$} & \bl{(q$_4$, a) $\rightarrow$ q$_4$}\\
+\bl{(q$_0$, b) $\rightarrow$ q$_2$} & \bl{(q$_1$, b) $\rightarrow$ q$_2$} & \bl{(q$_4$, b) $\rightarrow$ q$_4$}\\
+\end{tabular}\ldots
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Accepting a String\end{tabular}}
+
+Given
+
+\begin{center}
+\bl{$A(Q, q_0, F, \delta)$}
+\end{center}
+
+you can define
+
+\begin{center}
+\begin{tabular}{l}
+\bl{$\hat{\delta}(q, \texttt{""}) = q$}\\
+\bl{$\hat{\delta}(q, c::s) = \hat{\delta}(\delta(q, c), s)$}\\
+\end{tabular}
+\end{center}\pause
+
+Whether a string \bl{$s$} is accepted by \bl{$A$}?
+
+\begin{center}
+\hspace{5mm}\bl{$\hat{\delta}(q_0, s) \in F$}
+\end{center}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Non-Deterministic\\[-1mm] Finite Automata\end{tabular}}
+
+A non-deterministic finite automaton consists again of:
+
+\begin{itemize}
+\item a finite set of states
+\item one of these states is the start state
+\item some states are accepting states, and
+\item there is transition \alert{relation}\medskip
+\end{itemize}
+
+
+\begin{center}
+\begin{tabular}{c}
+\bl{(q$_1$, a) $\rightarrow$ q$_2$}\\
+\bl{(q$_1$, a) $\rightarrow$ q$_3$}\\
+\end{tabular}
+\hspace{10mm}
+\begin{tabular}{c}
+\bl{(q$_1$, $\epsilon$) $\rightarrow$ q$_2$}\\
+\end{tabular}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\includegraphics[scale=0.7]{pics/ch5.jpg}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\begin{tabular}[b]{ll}
+\bl{$\varnothing$} & \includegraphics[scale=0.7]{pics/NULL.jpg}\\\\
+\bl{$\epsilon$} & \includegraphics[scale=0.7]{pics/epsilon.jpg}\\\\
+\bl{c} & \includegraphics[scale=0.7]{pics/char.jpg}\\
+\end{tabular}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\begin{tabular}[t]{ll}
+\bl{r$_1$ $\cdot$ r$_2$} & \includegraphics[scale=0.6]{pics/seq.jpg}\\\\
+\end{tabular}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\begin{tabular}[t]{ll}
+\bl{r$_1$ + r$_2$} & \includegraphics[scale=0.7]{pics/alt.jpg}\\\\
+\end{tabular}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\begin{tabular}[b]{ll}
+\bl{r$^*$} & \includegraphics[scale=0.7]{pics/star.jpg}\\
+\end{tabular}
+\end{center}\pause\bigskip
+
+Why can't we just have an epsilon transition from the accepting states to the starting state?
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Subset Construction\end{tabular}}
+
+
+\begin{textblock}{5}(1,2.5)
+\includegraphics[scale=0.5]{pics/ch5.jpg}
+\end{textblock}
+
+\begin{textblock}{11}(6.5,4.5)
+\begin{tabular}{r|cl}
+& a & b\\
+\hline
+$\varnothing$ \onslide<2>{\textcolor{white}{*}} & $\varnothing$ & $\varnothing$\\
+$\{0\}$ \onslide<2>{\textcolor{white}{*}} & $\{0,1,2\}$ & $\{2\}$\\
+$\{1\}$ \onslide<2>{\textcolor{white}{*}} &$\{1\}$ & $\varnothing$\\
+$\{2\}$ \onslide<2>{*} & $\varnothing$ &$\{2\}$\\
+$\{0,1\}$ \onslide<2>{\textcolor{white}{*}} &$\{0,1,2\}$ &$\{2\}$\\
+$\{0,2\}$ \onslide<2>{*}&$\{0,1,2\}$ &$\{2\}$\\
+$\{1,2\}$ \onslide<2>{*}& $\{1\}$ & $\{2\}$\\
+\onslide<2>{s:} $\{0,1,2\}$ \onslide<2>{*}&$\{0,1,2\}$ &$\{2\}$\\
+\end{tabular}
+\end{textblock}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Regular Languages\end{tabular}}
+
+A language is \alert{regular} iff there exists
+a regular expression that recognises all its strings.\bigskip\medskip
+
+or equivalently\bigskip\medskip
+
+A language is \alert{regular} iff there exists
+a deterministic finite automaton that recognises all its strings.\bigskip\pause
+
+Why is every finite set of strings a regular language?
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\includegraphics[scale=0.5]{pics/ch3.jpg}
+\end{center}
+
+\begin{center}
+\includegraphics[scale=0.5]{pics/ch4.jpg}\\
+minimal automaton
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{enumerate}
+\item Take all pairs \bl{(q, p)} with \bl{q $\not=$ p}
+\item Mark all pairs that accepting and non-accepting states
+\item For all unmarked pairs \bl{(q, p)} and all characters \bl{c} tests wether
+\begin{center}
+\bl{($\delta$(q,c), $\delta$(p,c))}
+\end{center}
+are marked. If yes, then also mark \bl{(q, p)}
+\item Repeat last step until no chance.
+\item All unmarked pairs can be merged.
+\end{enumerate}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Given the function
+
+\begin{center}
+\bl{\begin{tabular}{r@{\hspace{1mm}}c@{\hspace{1mm}}l}
+$rev(\varnothing)$ & $\dn$ & $\varnothing$\\
+$rev(\epsilon)$ & $\dn$ & $\epsilon$\\
+$rev(c)$ & $\dn$ & $c$\\
+$rev(r_1 + r_2)$ & $\dn$ & $rev(r_1) + rev(r_2)$\\
+$rev(r_1 \cdot r_2)$ & $\dn$ & $rev(r_2) \cdot rev(r_1)$\\
+$rev(r^*)$ & $\dn$ & $rev(r)^*$\\
+\end{tabular}}
+\end{center}
+
+
+and the set
+
+\begin{center}
+\bl{$Rev\,A \dn \{s^{-1} \;|\; s \in A\}$}
+\end{center}
+
+prove whether
+
+\begin{center}
+\bl{$L(rev(r)) = Rev (L(r))$}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{itemize}
+\item The star-case in our proof about the matcher needs the following lemma
+\begin{center}
+\bl{Der\,c\,A$^*$ $=$ (Der c A)\,@\, A$^*$}
+\end{center}
+\end{itemize}\bigskip\bigskip
+
+\begin{itemize}
+\item If \bl{\texttt{""} $\in$ A}, then\\ \bl{Der\,c\,(A @ B) $=$ (Der\,c\,A) @ B $\cup$ (Der\,c\,B)}\medskip
+\item If \bl{\texttt{""} $\not\in$ A}, then\\ \bl{Der\,c\,(A @ B) $=$ (Der\,c\,A) @ B}
+
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{itemize}
+\item Assuming you have the alphabet \bl{\{a, b, c\}}\bigskip
+\item Give a regular expression that can recognise all strings that have at least one \bl{b}.
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+``I hate coding. I do not want to look at code.''
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides05.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides05.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,504 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 05, King's College London, 24.~October 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (5)\\[3mm]
+ \end{tabular}}
+
+ \normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Deterministic Finite Automata\end{tabular}}
+
+A DFA \bl{$A(Q, q_0, F, \delta)$} consists of:
+
+\begin{itemize}
+\item a finite set of states \bl{$Q$}
+\item one of these states is the start state \bl{$q_0$}
+\item some states are accepting states \bl{$F$}
+\item a transition function \bl{$\delta$}
+\end{itemize}\pause
+
+\onslide<2->{
+\begin{center}
+\begin{tabular}{l}
+\bl{$\hat{\delta}(q, \texttt{""}) = q$}\\
+\bl{$\hat{\delta}(q, c\!::\!s) = \hat{\delta}(\delta(q, c), s)$}
+\end{tabular}
+\end{center}}
+
+\only<3,4>{
+\begin{center}
+\begin{tikzpicture}[scale=2, line width=0.5mm]
+ \node[state, initial] (q02) at ( 0,1) {$q_{0}$};
+ \node[state] (q13) at ( 1,1) {$q_{1}$};
+ \node[state, accepting] (q4) at ( 2,1) {$q_2$};
+ \path[->] (q02) edge[bend left] node[above] {$a$} (q13)
+ (q13) edge[bend left] node[below] {$b$} (q02)
+ (q13) edge node[above] {$a$} (q4)
+ (q02) edge [loop below] node {$b$} ()
+ (q4) edge [loop right] node {$a, b$} ()
+ ;
+\end{tikzpicture}
+\end{center}}%
+%
+\only<5>{
+\begin{center}
+\bl{$L(A) \dn \{ s \;|\; \hat{\delta}(q_0, s) \in F\}$}
+\end{center}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Non-Deterministic\\[-1mm] Finite Automata\end{tabular}}
+
+An NFA \bl{$A(Q, q_0, F, \delta)$} consists again of:
+
+\begin{itemize}
+\item a finite set of states
+\item one of these states is the start state
+\item some states are accepting states
+\item a transition \alert{relation}\medskip
+\end{itemize}
+
+
+\begin{center}
+\begin{tabular}{c}
+\bl{(q$_1$, a) $\rightarrow$ q$_2$}\\
+\bl{(q$_1$, a) $\rightarrow$ q$_3$}\\
+\end{tabular}
+\hspace{10mm}
+\begin{tabular}{c}
+\bl{(q$_1$, $\epsilon$) $\rightarrow$ q$_2$}\\
+\end{tabular}
+\end{center}\pause\medskip
+
+A string \bl{s} is accepted by an NFA, if there is a ``lucky'' sequence to an accepting state.
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Last Week\end{tabular}}
+
+Last week I showed you\bigskip
+
+\begin{itemize}
+\item an algorithm for automata minimisation
+
+\item an algorithm for transforming a regular expression into an NFA
+
+\item an algorithm for transforming an NFA into a DFA (subset construction)
+
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}This Week\end{tabular}}
+
+Go over the algorithms again, but with two new things and \ldots\medskip
+
+\begin{itemize}
+\item with the example: what is the regular expression that accepts every string, except those ending
+in \bl{aa}?\medskip
+
+\item Go over the proof for \bl{$L(rev(r)) = Rev(L(r))$}.\medskip
+
+\item Anything else so far.
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Proofs By Induction\end{tabular}}
+
+\begin{itemize}
+\item \bl{$P$} holds for \bl{$\varnothing$}, \bl{$\epsilon$} and \bl{c}\bigskip
+\item \bl{$P$} holds for \bl{r$_1$ + r$_2$} under the assumption that \bl{$P$} already
+holds for \bl{r$_1$} and \bl{r$_2$}.\bigskip
+\item \bl{$P$} holds for \bl{r$_1$ $\cdot$ r$_2$} under the assumption that \bl{$P$} already
+holds for \bl{r$_1$} and \bl{r$_2$}.
+\item \bl{$P$} holds for \bl{r$^*$} under the assumption that \bl{$P$} already
+holds for \bl{r}.
+\end{itemize}
+
+\begin{center}
+\bl{$P(r):\;\;L(rev(r)) = Rev(L(r))$}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+
+What is the regular expression that accepts every string, except those ending
+in \bl{aa}?\pause\bigskip
+
+\begin{center}
+\begin{tabular}{l}
+\bl{(a + b)$^*$ba}\\
+\bl{(a + b)$^*$ab}\\
+\bl{(a + b)$^*$bb}\\\pause
+\bl{a}\\
+\bl{\texttt{""}}
+\end{tabular}
+\end{center}\pause
+
+What are the strings to be avoided?\pause\medskip
+
+\begin{center}
+\bl{(a + b)$^*$aa}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+
+An NFA for \bl{(a + b)$^*$aa}
+
+\begin{center}
+\begin{tikzpicture}[scale=2, line width=0.5mm]
+ \node[state, initial] (q0) at ( 0,1) {$q_0$};
+ \node[state] (q1) at ( 1,1) {$q_1$};
+ \node[state, accepting] (q2) at ( 2,1) {$q_2$};
+ \path[->] (q0) edge node[above] {$a$} (q1)
+ (q1) edge node[above] {$a$} (q2)
+ (q0) edge [loop below] node {$a$} ()
+ (q0) edge [loop above] node {$b$} ()
+ ;
+\end{tikzpicture}
+\end{center}\pause
+
+Minimisation for DFAs\\
+Subset Construction for NFAs
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}DFA Minimisation\end{tabular}}
+
+
+\begin{enumerate}
+\item Take all pairs \bl{(q, p)} with \bl{q $\not=$ p}
+\item Mark all pairs that accepting and non-accepting states
+\item For all unmarked pairs \bl{(q, p)} and all characters \bl{c} tests wether
+\begin{center}
+\bl{($\delta$(q,c), $\delta$(p,c))}
+\end{center}
+are marked. If yes, then also mark \bl{(q, p)}.
+\item Repeat last step until nothing changed.
+\item All unmarked pairs can be merged.
+\end{enumerate}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Minimal DFA \only<1>{\bl{(a + b)$^*$aa}}\only<2->{\alert{not} \bl{(a + b)$^*$aa}}
+
+\begin{center}
+\begin{tikzpicture}[scale=2, line width=0.5mm]
+ \only<1>{\node[state, initial] (q0) at ( 0,1) {$q_0$};}
+ \only<2->{\node[state, initial,accepting] (q0) at ( 0,1) {$q_0$};}
+ \only<1>{\node[state] (q1) at ( 1,1) {$q_1$};}
+ \only<2->{\node[state,accepting] (q1) at ( 1,1) {$q_1$};}
+ \only<1>{\node[state, accepting] (q2) at ( 2,1) {$q_2$};}
+ \only<2->{\node[state] (q2) at ( 2,1) {$q_2$};}
+ \path[->] (q0) edge[bend left] node[above] {$a$} (q1)
+ (q1) edge[bend left] node[above] {$b$} (q0)
+ (q2) edge[bend left=50] node[below] {$b$} (q0)
+ (q1) edge node[above] {$a$} (q2)
+ (q2) edge [loop right] node {$a$} ()
+ (q0) edge [loop below] node {$b$} ()
+ ;
+\end{tikzpicture}
+\end{center}
+
+\onslide<3>{How to get from a DFA to a regular expression?}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\begin{tikzpicture}[scale=2, line width=0.5mm]
+ \only<1->{\node[state, initial] (q0) at ( 0,1) {$q_0$};}
+ \only<1->{\node[state] (q1) at ( 1,1) {$q_1$};}
+ \only<1->{\node[state] (q2) at ( 2,1) {$q_2$};}
+ \path[->] (q0) edge[bend left] node[above] {$a$} (q1)
+ (q1) edge[bend left] node[above] {$b$} (q0)
+ (q2) edge[bend left=50] node[below] {$b$} (q0)
+ (q1) edge node[above] {$a$} (q2)
+ (q2) edge [loop right] node {$a$} ()
+ (q0) edge [loop below] node {$b$} ()
+ ;
+\end{tikzpicture}
+\end{center}\pause\bigskip
+
+\onslide<2->{
+\begin{center}
+\begin{tabular}{r@ {\hspace{2mm}}c@ {\hspace{2mm}}l}
+\bl{$q_0$} & \bl{$=$} & \bl{$2\, q_0 + 3 \,q_1 + 4\, q_2$}\\
+\bl{$q_1$} & \bl{$=$} & \bl{$2 \,q_0 + 3\, q_1 + 1\, q_2$}\\
+\bl{$q_2$} & \bl{$=$} & \bl{$1\, q_0 + 5\, q_1 + 2\, q_2$}\\
+
+\end{tabular}
+\end{center}
+}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\begin{tikzpicture}[scale=2, line width=0.5mm]
+ \only<1->{\node[state, initial] (q0) at ( 0,1) {$q_0$};}
+ \only<1->{\node[state] (q1) at ( 1,1) {$q_1$};}
+ \only<1->{\node[state] (q2) at ( 2,1) {$q_2$};}
+ \path[->] (q0) edge[bend left] node[above] {$a$} (q1)
+ (q1) edge[bend left] node[above] {$b$} (q0)
+ (q2) edge[bend left=50] node[below] {$b$} (q0)
+ (q1) edge node[above] {$a$} (q2)
+ (q2) edge [loop right] node {$a$} ()
+ (q0) edge [loop below] node {$b$} ()
+ ;
+\end{tikzpicture}
+\end{center}\bigskip
+
+\onslide<2->{
+\begin{center}
+\begin{tabular}{r@ {\hspace{2mm}}c@ {\hspace{2mm}}l}
+\bl{$q_0$} & \bl{$=$} & \bl{$\epsilon + q_0\,b + q_1\,b + q_2\,b$}\\
+\bl{$q_1$} & \bl{$=$} & \bl{$q_0\,a$}\\
+\bl{$q_2$} & \bl{$=$} & \bl{$q_1\,a + q_2\,a$}\\
+
+\end{tabular}
+\end{center}
+}
+
+\onslide<3->{
+Arden's Lemma:
+\begin{center}
+If \bl{$q = q\,r + s$}\; then\; \bl{$q = s\, r^*$}
+\end{center}
+}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Algorithms on Automata\end{tabular}}
+
+
+\begin{itemize}
+\item Reg $\rightarrow$ NFA: Thompson-McNaughton-Yamada method\medskip
+\item NFA $\rightarrow$ DFA: Subset Construction\medskip
+\item DFA $\rightarrow$ Reg: Brzozowski's Algebraic Method\medskip
+\item DFA minimisation: Hopcrofts Algorithm\medskip
+\item complement DFA
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\newcommand{\qq}{\mbox{\texttt{"}}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Grammars\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $F + (F \cdot \qq*\qq \cdot F) + (F \cdot \qq\backslash\qq \cdot F)$\\
+$F$ & $\rightarrow$ & $T + (T \cdot \qq\texttt{+}\qq \cdot T) + (T \cdot \qq\texttt{-}\qq \cdot T)$\\
+$T$ & $\rightarrow$ & $num + (\qq\texttt{(}\qq \cdot E \cdot \qq\texttt{)}\qq)$\\
+\end{tabular}}
+\end{center}
+
+\bl{$E$}, \bl{$F$} and \bl{$T$} are non-terminals\\
+\bl{$E$} is start symbol\\
+\bl{$num$}, \bl{(}, \bl{)}, \bl{+} \ldots are terminals\bigskip\\
+
+
+\bl{\texttt{(2*3)+(3+4)}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $F + (F \cdot \qq*\qq \cdot F) + (F \cdot \qq\backslash\qq \cdot F)$\\
+$F$ & $\rightarrow$ & $T + (T \cdot \qq\texttt{+}\qq \cdot T) + (T \cdot \qq\texttt{-}\qq \cdot T)$\\
+$T$ & $\rightarrow$ & $num + (\qq\texttt{(}\qq \cdot E \cdot \qq\texttt{)}\qq)$\\
+\end{tabular}}
+\end{center}
+
+\begin{center}
+\begin{tikzpicture}[level distance=8mm, blue]
+ \node {E}
+ child {node {F}
+ child {node {T}
+ child {node {\qq(\qq\,E\,\qq)\qq}
+ child {node{F \qq*\qq{} F}
+ child {node {T} child {node {2}}}
+ child {node {T} child {node {3}}}
+ }
+ }
+ }
+ child {node {\qq+\qq}}
+ child {node {T}
+ child {node {\qq(\qq\,E\,\qq)\qq}
+ child {node {F}
+ child {node {T \qq+\qq{} T}
+ child {node {3}}
+ child {node {4}}
+ }
+ }}
+ }};
+\end{tikzpicture}
+\end{center}
+
+\begin{textblock}{5}(1, 5)
+\bl{\texttt{(2*3)+(3+4)}}
+\end{textblock}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides06.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides06.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,579 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usetikzlibrary{plotmarks}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 06, King's College London, 31.~October 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+
+% The data files, written on the first run.
+\begin{filecontents}{re-python.data}
+1 0.029
+5 0.029
+10 0.029
+15 0.032
+16 0.042
+17 0.042
+18 0.055
+19 0.084
+20 0.136
+21 0.248
+22 0.464
+23 0.899
+24 1.773
+25 3.505
+26 6.993
+27 14.503
+28 29.307
+#29 58.886
+\end{filecontents}
+
+\begin{filecontents}{re1.data}
+1 0.00179
+2 0.00011
+3 0.00014
+4 0.00026
+5 0.00050
+6 0.00095
+7 0.00190
+8 0.00287
+9 0.00779
+10 0.01399
+11 0.01894
+12 0.03666
+13 0.07994
+14 0.08944
+15 0.02377
+16 0.07392
+17 0.22798
+18 0.65310
+19 2.11360
+20 6.31606
+21 21.46013
+\end{filecontents}
+
+\begin{filecontents}{re2.data}
+1 0.00240
+2 0.00013
+3 0.00020
+4 0.00030
+5 0.00049
+6 0.00083
+7 0.00146
+8 0.00228
+9 0.00351
+10 0.00640
+11 0.01217
+12 0.02565
+13 0.01382
+14 0.02423
+15 0.05065
+16 0.06522
+17 0.02140
+18 0.05176
+19 0.18254
+20 0.51898
+21 1.39631
+22 2.69501
+23 8.07952
+\end{filecontents}
+
+\begin{filecontents}{re-internal.data}
+1 0.00069
+301 0.00700
+601 0.00297
+901 0.00470
+1201 0.01301
+1501 0.01175
+1801 0.01761
+2101 0.01787
+2401 0.02717
+2701 0.03932
+3001 0.03470
+3301 0.04349
+3601 0.05411
+3901 0.06181
+4201 0.07119
+4501 0.08578
+\end{filecontents}
+
+\begin{filecontents}{re3.data}
+1 0.001605
+501 0.131066
+1001 0.057885
+1501 0.136875
+2001 0.176238
+2501 0.254363
+3001 0.37262
+3501 0.500946
+4001 0.638384
+4501 0.816605
+5001 1.00491
+5501 1.232505
+6001 1.525672
+6501 1.757502
+7001 2.092784
+7501 2.429224
+8001 2.803037
+8501 3.463045
+9001 3.609
+9501 4.081504
+10001 4.54569
+\end{filecontents}
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (6)\\[3mm]
+ \end{tabular}}
+
+ \normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+``I hate coding. I do not want to look at code.''
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+``I am appalled. You do not show code anymore.''
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}ReDoS\end{tabular}}
+
+\begin{itemize}
+\item \alert{R}egular \alert{e}xpression \alert{D}enial \alert{o}f \alert{S}ervice\bigskip
+\item ``Regular Expressions Will Stab You in the Back''\bigskip
+\item Evil regular expressions\medskip
+\begin{itemize}
+\item \bl{$(a?\{n\})a\{n\}$}
+\item \bl{$(a^+)^+$}
+\item \bl{$([a-zA-Z]^+)^*$}
+\item \bl{$(a + aa)^+$}
+\item \bl{$(a + a?)^+$}
+\end{itemize}
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Regexp Matching\end{tabular}}
+
+Given a regular expression
+
+\begin{enumerate}
+\item you might convert it into a DFA (subset construction)
+\item you might try all possible paths in an NFA via backtracking
+\item you might try all paths in an NFA in parallel
+\item you might try to convert the DFA ``lazily''
+\end{enumerate}\bigskip
+
+Often No~2 is implemented (sometimes there are even good reasons for doing this).
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}\bl{$(a?\{n\})a\{n\}$} in Python\end{tabular}}
+
+\begin{tikzpicture}[y=.2cm, x=.3cm]
+ %axis
+ \draw (0,0) -- coordinate (x axis mid) (30,0);
+ \draw (0,0) -- coordinate (y axis mid) (0,30);
+ %ticks
+ \foreach \x in {0,5,...,30}
+ \draw (\x,1pt) -- (\x,-3pt)
+ node[anchor=north] {\x};
+ \foreach \y in {0,5,...,30}
+ \draw (1pt,\y) -- (-3pt,\y)
+ node[anchor=east] {\y};
+ %labels
+ \node[below=0.6cm] at (x axis mid) {\bl{a}s};
+ \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
+
+ %plots
+ \draw[color=blue] plot[mark=*, mark options={fill=white}]
+ file {re-python.data};
+ \only<2->{
+ \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
+ file {re1.data};}
+ \only<3->{
+ \draw[color=green] plot[mark=square*, mark options={fill=white} ]
+ file {re2.data};}
+
+ %legend
+ \begin{scope}[shift={(4,20)}]
+ \draw[color=blue] (0,0) --
+ plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Python};
+ \only<2->{\draw[yshift=\baselineskip, color=red] (0,0) --
+ plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala V1};}
+ \only<3->{
+ \draw[yshift=2\baselineskip, color=green] (0,0) --
+ plot[mark=square*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala V2 with simplifications};}
+ \end{scope}
+\end{tikzpicture}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+
+\begin{tikzpicture}[y=.7cm, x=.0009cm]
+ %axis
+ \draw (0,0) -- coordinate (x axis mid) (10000,0);
+ \draw (0,0) -- coordinate (y axis mid) (0,6);
+ %ticks
+ \foreach \x in {0,2000,...,10000}
+ \draw (\x,1pt) -- (\x,-3pt)
+ node[anchor=north] {\x};
+ \foreach \y in {0,1,...,6}
+ \draw (1pt,\y) -- (-3pt,\y)
+ node[anchor=east] {\y};
+ %labels
+ \node[below=0.6cm] at (x axis mid) {\bl{a}s};
+ \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
+
+ %plots
+ \draw[color=blue] plot[mark=*, mark options={fill=white}]
+ file {re-internal.data};
+ \only<2->{
+ \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
+ file {re3.data};}
+
+ %legend
+ \begin{scope}[shift={(2000,4)}]
+ \draw[color=blue] (0,0) --
+ plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala Internal};
+ \only<2->{
+ \draw[yshift=\baselineskip, color=red] (0,0) --
+ plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala V3 with explicit $\_\{\_\}$};}
+ \end{scope}
+\end{tikzpicture}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+\newcommand{\qq}{\mbox{\texttt{"}}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Grammars\end{tabular}}
+
+A (context-free) grammar \bl{$G$} consists of
+
+\begin{itemize}
+\item a finite set of nonterminal symbols (upper case)
+\item a finite terminal symbols or tokens (lower case)
+\item a start symbol (which must be a nonterminal)
+\item a set of rules
+\begin{center}
+\bl{$A \rightarrow \text{rhs}$}
+\end{center}
+
+where \bl{rhs} are sequences involving terminals and nonterminals.\medskip\pause
+
+We can also allow rules
+\begin{center}
+\bl{$A \rightarrow \text{rhs}_1 | \text{rhs}_2 | \ldots$}
+\end{center}
+\end{itemize}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Palindromes\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$S$ & $\rightarrow$ & $\epsilon$ \\
+$S$ & $\rightarrow$ & $a\cdot S\cdot a$ \\
+$S$ & $\rightarrow$ & $b\cdot S\cdot b$ \\
+\end{tabular}}
+\end{center}\pause
+
+or
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$S$ & $\rightarrow$ & $\epsilon \;|\; a\cdot S\cdot a \;|\;b\cdot S\cdot b$ \\
+\end{tabular}}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Arithmetic Expressions\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $num\_token$ \\
+$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
+$E$ & $\rightarrow$ & $( \cdot E \cdot )$
+\end{tabular}}
+\end{center}\pause
+
+\bl{\texttt{1 + 2 * 3 + 4}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Parse Trees\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $F \;|\; F \cdot * \cdot F$\\
+$F$ & $\rightarrow$ & $T \;|\; T \cdot + \cdot T \;|\; T \cdot - \cdot T$\\
+$T$ & $\rightarrow$ & $num\_token \;|\; ( \cdot E \cdot )$\\
+\end{tabular}}
+\end{center}
+
+\begin{center}
+\begin{tikzpicture}[level distance=8mm, blue]
+ \node {$E$}
+ child {node {$F$}
+ child {node {$T$}
+ child {node {(\,$E$\,)}
+ child {node{$F$ *{} $F$}
+ child {node {$T$} child {node {2}}}
+ child {node {$T$} child {node {3}}}
+ }
+ }
+ }
+ child {node {+}}
+ child {node {$T$}
+ child {node {(\,$E$\,)}
+ child {node {$F$}
+ child {node {$T$ +{} $T$}
+ child {node {3}}
+ child {node {4}}
+ }
+ }}
+ }};
+\end{tikzpicture}
+\end{center}
+
+\begin{textblock}{5}(1, 6.5)
+\bl{\texttt{(2*3)+(3+4)}}
+\end{textblock}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Ambiguous Grammars\end{tabular}}
+
+A grammar is \alert{ambiguous} if there is a string that has at least parse trees.
+
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $num\_token$ \\
+$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
+$E$ & $\rightarrow$ & $( \cdot E \cdot )$
+\end{tabular}}
+\end{center}
+
+\bl{\texttt{1 + 2 * 3 + 4}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Chomsky Normal Form\end{tabular}}
+
+All rules must be of the form
+
+\begin{center}
+\bl{$A \rightarrow a$}
+\end{center}
+
+or
+
+\begin{center}
+\bl{$A \rightarrow B\cdot C$}
+\end{center}
+
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}CYK Algorithm\end{tabular}}
+
+
+\begin{center}
+\bl{\begin{tabular}{@ {}lcl}
+$S$ & $\rightarrow$ & $N\cdot P$ \\
+$P$ & $\rightarrow$ & $V\cdot N$ \\
+$N$ & $\rightarrow$ & $N\cdot N$ \\
+$N$ & $\rightarrow$ & $\texttt{students} \;|\; \texttt{Jeff} \;|\; \texttt{geometry} \;|\; \texttt{trains} $ \\
+$V$ & $\rightarrow$ & $\texttt{trains}$
+\end{tabular}}
+\end{center}
+
+\bl{\texttt{Jeff trains geometry students}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}CYK Algorithm\end{tabular}}
+
+
+\begin{itemize}
+\item runtime is \bl{$O(n^3)$}\bigskip
+\item grammars need to be transferred into CNF
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides07.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides07.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,542 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usetikzlibrary{plotmarks}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 07, King's College London, 14.~November 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+
+% The data files, written on the first run.
+\begin{filecontents}{re-python.data}
+1 0.029
+5 0.029
+10 0.029
+15 0.032
+16 0.042
+17 0.042
+18 0.055
+19 0.084
+20 0.136
+21 0.248
+22 0.464
+23 0.899
+24 1.773
+25 3.505
+26 6.993
+27 14.503
+28 29.307
+#29 58.886
+\end{filecontents}
+
+\begin{filecontents}{re-ruby.data}
+1 0.00006
+2 0.00003
+3 0.00001
+4 0.00001
+5 0.00001
+6 0.00002
+7 0.00002
+8 0.00004
+9 0.00007
+10 0.00013
+11 0.00026
+12 0.00055
+13 0.00106
+14 0.00196
+15 0.00378
+16 0.00764
+17 0.01606
+18 0.03094
+19 0.06508
+20 0.12420
+21 0.25393
+22 0.51449
+23 1.02174
+24 2.05998
+25 4.22514
+26 8.42479
+27 16.88678
+28 34.79653
+\end{filecontents}
+
+\begin{filecontents}{re1.data}
+1 0.00179
+2 0.00011
+3 0.00014
+4 0.00026
+5 0.00050
+6 0.00095
+7 0.00190
+8 0.00287
+9 0.00779
+10 0.01399
+11 0.01894
+12 0.03666
+13 0.07994
+14 0.08944
+15 0.02377
+16 0.07392
+17 0.22798
+18 0.65310
+19 2.11360
+20 6.31606
+21 21.46013
+\end{filecontents}
+
+\begin{filecontents}{re2.data}
+1 0.00240
+2 0.00013
+3 0.00020
+4 0.00030
+5 0.00049
+6 0.00083
+7 0.00146
+8 0.00228
+9 0.00351
+10 0.00640
+11 0.01217
+12 0.02565
+13 0.01382
+14 0.02423
+15 0.05065
+16 0.06522
+17 0.02140
+18 0.05176
+19 0.18254
+20 0.51898
+21 1.39631
+22 2.69501
+23 8.07952
+\end{filecontents}
+
+\begin{filecontents}{re-internal.data}
+1 0.00069
+301 0.00700
+601 0.00297
+901 0.00470
+1201 0.01301
+1501 0.01175
+1801 0.01761
+2101 0.01787
+2401 0.02717
+2701 0.03932
+3001 0.03470
+3301 0.04349
+3601 0.05411
+3901 0.06181
+4201 0.07119
+4501 0.08578
+\end{filecontents}
+
+\begin{filecontents}{re3.data}
+1 0.001605
+501 0.131066
+1001 0.057885
+1501 0.136875
+2001 0.176238
+2501 0.254363
+3001 0.37262
+3501 0.500946
+4001 0.638384
+4501 0.816605
+5001 1.00491
+5501 1.232505
+6001 1.525672
+6501 1.757502
+7001 2.092784
+7501 2.429224
+8001 2.803037
+8501 3.463045
+9001 3.609
+9501 4.081504
+10001 4.54569
+\end{filecontents}
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (7)\\[3mm]
+ \end{tabular}}
+
+ \normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}\bl{$(a?\{n\})a\{n\}$}\end{tabular}}
+
+\mbox{}\\[-13mm]
+
+\begin{tikzpicture}[y=.2cm, x=.3cm]
+ %axis
+ \draw (0,0) -- coordinate (x axis mid) (30,0);
+ \draw (0,0) -- coordinate (y axis mid) (0,30);
+ %ticks
+ \foreach \x in {0,5,...,30}
+ \draw (\x,1pt) -- (\x,-3pt)
+ node[anchor=north] {\x};
+ \foreach \y in {0,5,...,30}
+ \draw (1pt,\y) -- (-3pt,\y)
+ node[anchor=east] {\y};
+ %labels
+ \node[below=0.6cm] at (x axis mid) {\bl{a}s};
+ \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
+
+ %plots
+ \draw[color=blue] plot[mark=*, mark options={fill=white}]
+ file {re-python.data};
+ \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
+ file {re1.data};
+ \draw[color=green] plot[mark=square*, mark options={fill=white} ]
+ file {re2.data};
+ \draw[color=brown] plot[mark=pentagon*, mark options={fill=white} ]
+ file {re-ruby.data};
+
+ %legend
+ \begin{scope}[shift={(4,20)}]
+ \draw[color=blue] (0,0) --
+ plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Python};
+ \draw[yshift=-\baselineskip, color=brown] (0,0) --
+ plot[mark=pentagon*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Ruby (Daniel Baldwin)};
+ \draw[yshift=\baselineskip, color=red] (0,0) --
+ plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala V1};
+ \draw[yshift=2\baselineskip, color=green] (0,0) --
+ plot[mark=square*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala V2 with simplifications};
+ \end{scope}
+\end{tikzpicture}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+
+\begin{tikzpicture}[y=.7cm, x=.0009cm]
+ %axis
+ \draw (0,0) -- coordinate (x axis mid) (10000,0);
+ \draw (0,0) -- coordinate (y axis mid) (0,6);
+ %ticks
+ \foreach \x in {0,2000,...,10000}
+ \draw (\x,1pt) -- (\x,-3pt)
+ node[anchor=north] {\x};
+ \foreach \y in {0,1,...,6}
+ \draw (1pt,\y) -- (-3pt,\y)
+ node[anchor=east] {\y};
+ %labels
+ \node[below=0.6cm] at (x axis mid) {\bl{a}s};
+ \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
+
+ %plots
+ \draw[color=blue] plot[mark=*, mark options={fill=white}]
+ file {re-internal.data};
+ \only<1->{
+ \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
+ file {re3.data};}
+
+ %legend
+ \begin{scope}[shift={(2000,4)}]
+ \draw[color=blue] (0,0) --
+ plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala Internal};
+ \only<1->{
+ \draw[yshift=\baselineskip, color=red] (0,0) --
+ plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small Scala V3 with explicit $\_\{\_\}$};}
+ \end{scope}
+\end{tikzpicture}
+
+\begin{center}
+\begin{tabular}{@ {}l@ {\hspace{2mm}}c@ {\hspace{2mm}}l@ {\hspace{-10mm}}l@ {}}
+ \\[-8mm]
+ \bl{der c (r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{if nullable r$_1$}\\
+ & & \bl{then ((der c r$_1$) $\cdot$ r$_2$) + (der c r$_2$)}\\
+ & & \bl{else (der c r$_1$) $\cdot$ r$_2$}\\
+ \bl{der c (r$\{n\}$)} & \bl{$\dn$} & \bl{if $n = 0$ then $\varnothing$}\\
+ & & \bl{else (der c r) $\cdot$ r$\{n - 1\}$}
+ \end{tabular}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+\newcommand{\qq}{\mbox{\texttt{"}}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}CFGs\end{tabular}}
+
+A \alert{context-free} grammar (CFG) \bl{$G$} consists of:
+
+\begin{itemize}
+\item a finite set of nonterminal symbols (upper case)
+\item a finite terminal symbols or tokens (lower case)
+\item a start symbol (which must be a nonterminal)
+\item a set of rules
+\begin{center}
+\bl{$A \rightarrow \text{rhs}$}
+\end{center}
+
+where \bl{rhs} are sequences involving terminals and nonterminals (can also be empty).\medskip\pause
+
+We can also allow rules
+\begin{center}
+\bl{$A \rightarrow \text{rhs}_1 | \text{rhs}_2 | \ldots$}
+\end{center}
+\end{itemize}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}A CFG Derivation\end{tabular}}
+
+\begin{enumerate}
+\item Begin with a string with only the start symbol \bl{$S$}\bigskip
+\item Replace any non-terminal \bl{$X$} in the string by the
right-hand side of some production \bl{$X \rightarrow \text{rhs}$}\bigskip
+\item Repeat 2 until there are no non-terminals
+\end{enumerate}
+
+\begin{center}
+\bl{$S \rightarrow \ldots \rightarrow \ldots \rightarrow \ldots \rightarrow \ldots $}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Language of a CFG\end{tabular}}
+
+Let \bl{$G$} be a context-free grammar with start symbol \bl{$S$}.
+Then the language \bl{$L(G)$} is:
+
+\begin{center}
+\bl{$\{c_1\ldots c_n \;|\; \forall i.\; c_i \in T \wedge S \rightarrow^* c_1\ldots c_n \}$}
+\end{center}\pause
+
+\begin{itemize}
+\item Terminals are so-called because there are no rules for replacing them
+\item Once generated, terminals are ``permanent''
+\item Terminals ought to be tokens of the language (at least in this course)
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Arithmetic Expressions\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $num\_token$ \\
+$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
+$E$ & $\rightarrow$ & $( \cdot E \cdot )$
+\end{tabular}}
+\end{center}\pause\bigskip
+
+A CFG is \alert{left-recursive} if it has a nonterminal \bl{$E$} such
+that \bl{$E \rightarrow^+ E\cdot \ldots$}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Parse Trees\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $F \;|\; F \cdot * \cdot F$\\
+$F$ & $\rightarrow$ & $T \;|\; T \cdot + \cdot T \;|\; T \cdot - \cdot T$\\
+$T$ & $\rightarrow$ & $num\_token \;|\; ( \cdot E \cdot )$\\
+\end{tabular}}
+\end{center}
+
+\begin{center}
+\begin{tikzpicture}[level distance=8mm, blue]
+ \node {$E$}
+ child {node {$F$}
+ child {node {$T$}
+ child {node {(\,$E$\,)}
+ child {node{$F$ *{} $F$}
+ child {node {$T$} child {node {2}}}
+ child {node {$T$} child {node {3}}}
+ }
+ }
+ }
+ child {node {+}}
+ child {node {$T$}
+ child {node {(\,$E$\,)}
+ child {node {$F$}
+ child {node {$T$ +{} $T$}
+ child {node {3}}
+ child {node {4}}
+ }
+ }}
+ }};
+\end{tikzpicture}
+\end{center}
+
+\begin{textblock}{5}(1, 6.5)
+\bl{\texttt{(2*3)+(3+4)}}
+\end{textblock}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Ambiguous Grammars\end{tabular}}
+
+A CFG is \alert{ambiguous} if there is a string that has at least parse trees.
+
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & $num\_token$ \\
+$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
+$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
+$E$ & $\rightarrow$ & $( \cdot E \cdot )$
+\end{tabular}}
+\end{center}
+
+\bl{\texttt{1 + 2 * 3 + 4}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Dangling Else\end{tabular}}
+
+Another ambiguous grammar:\bigskip
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$E$ & $\rightarrow$ & if $E$ then $E$\\
+ & $|$ & if $E$ then $E$ else $E$ \\
+ & $|$ & id
+\end{tabular}}
+\end{center}\bigskip
+
+\bl{\texttt{if a then if x then y else c}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides08.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides08.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,676 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usetikzlibrary{plotmarks}
+\usepackage{graphicx}
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 08, King's College London, 21.~November 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+
+% The data files, written on the first run.
+\begin{filecontents}{s-grammar1.data}
+1 0.01152
+51 0.07973
+101 0.09726
+151 0.09320
+201 0.10010
+251 0.16997
+301 0.26662
+351 0.46118
+401 0.62516
+451 0.87247
+501 1.16334
+551 1.71152
+601 2.10958
+651 2.44360
+701 2.98488
+751 3.50326
+801 4.11036
+851 4.93394
+901 5.77465
+951 7.39123
+\end{filecontents}
+
+\begin{filecontents}{s-grammar2.data}
+1 0.01280
+2 0.00064
+3 0.00173
+4 0.00355
+5 0.00965
+6 0.02674
+7 0.06953
+8 0.11166
+9 0.18707
+10 0.09189
+11 0.12724
+12 0.24337
+13 0.59304
+14 1.53594
+15 4.01195
+16 10.73582
+17 29.51587
+#18 73.14163
+\end{filecontents}
+
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (8)\\[3mm]
+ \end{tabular}}
+
+ \normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ \end{tabular}
+ \end{center}
+
+
+\end{frame}}
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Building a ``Web Browser''\end{tabular}}
+
+Using a lexer: assume the following regular expressions
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$SY\!M$ & $\dn$ & $(\text{a}..\text{zA}..\text{Z0}..\text{9}..)$\\
+$W\!O\!RD$ & $\dn$ & $SY\!M^+$\\
+$BT\!AG$ & $\dn$ & $<\!W\!O\!RD\!>$\\
+$ET\!AG$ & $\dn$ & $<\!/W\!O\!RD\!>$\\
+$W\!HIT\!E$ & $\dn$ & $\texttt{" "} + \texttt{"}\slash{}n\texttt{"}$\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Interpreting a List of Tokens\end{tabular}}
+
+\begin{itemize}
+\item the text should be formatted consistently up to a specified width, say 60 characters
+\item potential linebreaks are inserted by the formatter (not the input)
+\item repeated whitespaces are ``condensed'' to a single whitepace
+\item \bl{$<\!p\!>$} \bl{$<\!\slash{}p\!>$} start/end paragraph
+\item \bl{$<\!b\!>$} \bl{$<\!\slash{}b\!>$} start/end bold
+\item \bl{$<\!red\!>$} \bl{$<\!\slash{}red\!>$} start/end red (cyan, etc)
+
+
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Interpreting a List of Tokens\end{tabular}}
+
+The lexer cannot prevent errors like
+
+\begin{center}
+\bl{$<\!b\!>$} \ldots \bl{$<\!p\!>$} \ldots \bl{$<\!\slash{}b\!>$} \ldots \bl{$<\!\slash{}p\!>$}
+\end{center}
+
+or
+
+\begin{center}
+\bl{$<\!\slash{}b\!>$} \ldots \bl{$<\!b\!>$}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Parser Combinators\end{tabular}}
+
+Parser combinators: \bigskip
+
+\begin{minipage}{1.1\textwidth}
+\begin{center}
+\mbox{}\hspace{-12mm}\mbox{}$\underbrace{\text{list of tokens}}_{\text{input}}$ \bl{$\Rightarrow$}
+$\underbrace{\text{set of (parsed input, unparsed input)}}_{\text{output}}$
+\end{center}
+\end{minipage}\bigskip
+
+\begin{itemize}
+\item sequencing
+\item alternative
+\item semantic action
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Alternative parser (code \bl{$p\;||\;q$})\bigskip
+
+\begin{itemize}
+\item apply \bl{$p$} and also \bl{$q$}; then combine the outputs
+\end{itemize}
+
+\begin{center}
+\large \bl{$p(\text{input}) \cup q(\text{input})$}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Sequence parser (code \bl{$p\sim q$})\bigskip
+
+\begin{itemize}
+\item apply first \bl{$p$} producing a set of pairs
+\item then apply \bl{$q$} to the unparsed parts
+\item then combine the results:\\ \mbox{}\;\;((output$_1$, output$_2$), unparsed part)
+\end{itemize}
+
+\begin{center}
+\begin{tabular}{l}
+\large \bl{$\{((o_1, o_2), u_2) \;|\;$}\\[2mm]
+\large\mbox{}\hspace{15mm} \bl{$(o_1, u_1) \in p(\text{input}) \wedge$}\\[2mm]
+\large\mbox{}\hspace{15mm} \bl{$(o_2, u_2) \in q(u_1)\}$}
+\end{tabular}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Function parser (code \bl{$p \Longrightarrow f$})\bigskip
+
+\begin{itemize}
+\item apply \bl{$p$} producing a set of pairs
+\item then apply the function \bl{$f$} to each first component
+\end{itemize}
+
+\begin{center}
+\begin{tabular}{l}
+\large \bl{$\{(f(o_1), u_1) \;|\; (o_1, u_1) \in p(\text{input})\}$}
+\end{tabular}
+\end{center}\bigskip\bigskip\pause
+
+\bl{$f$} is the semantic action (``what to do with the parsed input'')
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Token parser:\bigskip
+
+\begin{itemize}
+\item if the input is
+
+\begin{center}
+\large \bl{$tok_1:: tok_2 :: \ldots :: tok_n$}
+\end{center}
+
+then return
+
+\begin{center}
+\large \bl{$\{(tok_1,\; tok_2 :: \ldots :: tok_n)\}$}
+\end{center}
+
+or
+
+\begin{center}
+\large \bl{$\{\}$}
+\end{center}
+
+if \bl{$tok_1$} is not the right token we are looking for
+\end{itemize}
+
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Number-Token parser:\bigskip
+
+\begin{itemize}
+\item if the input is
+
+\begin{center}
+\large \bl{$num\_tok(42):: tok_2 :: \ldots :: tok_n$}
+\end{center}
+
+then return
+
+\begin{center}
+\large \bl{$\{(42,\; tok_2 :: \ldots :: tok_n)\}$}
+\end{center}
+
+or
+
+\begin{center}
+\large \bl{$\{\}$}
+\end{center}
+
+if \bl{$tok_1$} is not the right token we are looking for
+\end{itemize}\pause
+
+\begin{center}
+list of tokens \bl{$\Rightarrow$} set of (\alert{int}, list of tokens)
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{itemize}
+\item if the input is
+
+\begin{center}
+\begin{tabular}{l}
+\large \bl{$num\_tok(42)::$}\\
+\hspace{7mm}\large \bl{$num\_tok(3) ::$}\\
+\hspace{14mm}\large \bl{$tok_3 :: \ldots :: tok_n$}
+\end{tabular}
+\end{center}
+
+and the parser is
+
+\begin{center}
+\bl{$ntp \sim ntp$}
+\end{center}
+
+the successful output will be
+
+\begin{center}
+\large \bl{$\{((42, 3),\; tok_2 :: \ldots :: tok_n)\}$}
+\end{center}\pause
+
+Now we can form
+\begin{center}
+\bl{$(ntp \sim ntp) \Longrightarrow f$}
+\end{center}
+
+where \bl{$f$} is the semantic action (``what to do with the pair'')
+
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Semantic Actions\end{tabular}}
+
+Addition
+
+\begin{center}
+\bl{$T \sim + \sim E \Longrightarrow \underbrace{f((x,y), z) \Rightarrow x + z}_{\text{semantic action}}$}
+\end{center}\pause
+
+Multiplication
+
+\begin{center}
+\bl{$F \sim * \sim T \Longrightarrow f((x,y), z) \Rightarrow x * z$}
+\end{center}\pause
+
+Parenthesis
+
+\begin{center}
+\bl{$\text{(} \sim E \sim \text{)} \Longrightarrow f((x,y), z) \Rightarrow y$}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Types of Parsers\end{tabular}}
+
+\begin{itemize}
+\item {\bf Sequencing}: if \bl{$p$} returns results of type \bl{$T$}, and \bl{$q$} results of type \bl{$S$},
+then \bl{$p \sim q$} returns results of type
+
+\begin{center}
+\bl{$T \times S$}
+\end{center}\pause
+
+\item {\bf Alternative}: if \bl{$p$} returns results of type \bl{$T$} then \bl{$q$} \alert{must} also have results of type \bl{$T$},
+and \bl{$p \;||\; q$} returns results of type
+
+\begin{center}
+\bl{$T$}
+\end{center}\pause
+
+\item {\bf Semantic Action}: if \bl{$p$} returns results of type \bl{$T$} and \bl{$f$} is a function from
+\bl{$T$} to \bl{$S$}, then
+\bl{$p \Longrightarrow f$} returns results of type
+
+\begin{center}
+\bl{$S$}
+\end{center}
+
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Input Types of Parsers\end{tabular}}
+
+\begin{itemize}
+\item input: \alert{list of tokens}
+\item output: set of (output\_type, \alert{list of tokens})
+\end{itemize}\bigskip\pause
+
+actually it can be any input type as long as it is a kind of sequence
+(for example a string)
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Scannerless Parsers\end{tabular}}
+
+\begin{itemize}
+\item input: \alert{string}
+\item output: set of (output\_type, \alert{string})
+\end{itemize}\bigskip
+
+but lexers are better when whitespaces or comments need to be filtered out
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Successful Parses\end{tabular}}
+
+\begin{itemize}
+\item input: string
+\item output: \alert{set of} (output\_type, string)
+\end{itemize}\bigskip
+
+a parse is successful whenever the input has been
+fully ``consumed'' (that is the second component is empty)
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+{\lstset{language=Scala}\fontsize{10}{12}\selectfont
+\texttt{\lstinputlisting{app7.scala}}}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+{\lstset{language=Scala}\fontsize{10}{12}\selectfont
+\texttt{\lstinputlisting{app7.scala}}}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+{\lstset{language=Scala}\fontsize{10}{12}\selectfont
+\texttt{\lstinputlisting{app8.scala}}}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Two Grammars\end{tabular}}
+
+Which languages are recognised by the following two grammars?
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$S$ & $\rightarrow$ & $1 \cdot S \cdot S$\\
+ & $|$ & $\epsilon$
+\end{tabular}}
+\end{center}\bigskip
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$U$ & $\rightarrow$ & $1 \cdot U$\\
+ & $|$ & $\epsilon$
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Ambiguous Grammars\end{tabular}}
+
+\mbox{}\\[-25mm]\mbox{}
+
+\begin{center}
+\begin{tikzpicture}[y=.2cm, x=.009cm]
+ %axis
+ \draw (0,0) -- coordinate (x axis mid) (1000,0);
+ \draw (0,0) -- coordinate (y axis mid) (0,30);
+ %ticks
+ \foreach \x in {0, 20, 100, 200,...,1000}
+ \draw (\x,1pt) -- (\x,-3pt)
+ node[anchor=north] {\small \x};
+ \foreach \y in {0,5,...,30}
+ \draw (1pt,\y) -- (-3pt,\y)
+ node[anchor=east] {\small\y};
+ %labels
+ \node[below=0.6cm] at (x axis mid) {\bl{1}s};
+ \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
+
+ %plots
+ \draw[color=blue] plot[mark=*, mark options={fill=white}]
+ file {s-grammar1.data};
+ \only<2->{\draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
+ file {s-grammar2.data};}
+ %legend
+ \begin{scope}[shift={(400,20)}]
+ \draw[color=blue] (0,0) --
+ plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small unambiguous};
+ \only<2->{\draw[yshift=\baselineskip, color=red] (0,0) --
+ plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
+ node[right]{\small ambiguous};}
+ \end{scope}
+\end{tikzpicture}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}What about Left-Recursion?\end{tabular}}
+
+\begin{itemize}
+\item we record when we recursively called a parser\bigskip
+\item whenever the is a recursion, the parser must have consumed something --- so
+we can decrease the input string/list of token by one (at the end)
+\end{itemize}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}While-Language\end{tabular}}
+
+
+\begin{center}
+\bl{\begin{tabular}{@{}lcl@{}}
+$Stmt$ & $\rightarrow$ & $\text{skip}$\\
+ & $|$ & $Id := AExp$\\
+ & $|$ & $\text{if}\; B\!Exp \;\text{then}\; Block \;\text{else}\; Block$\\
+ & $|$ & $\text{while}\; B\!Exp \;\text{do}\; Block$\medskip\\
+$Stmts$ & $\rightarrow$ & $Stmt \;\text{;}\; Stmts$\\
+ & $|$ & $Stmt$\medskip\\
+$Block$ & $\rightarrow$ & $\{ Stmts \}$\\
+ & $|$ & $Stmt$\medskip\\
+$AExp$ & $\rightarrow$ & \ldots\\
+$BExp$ & $\rightarrow$ & \ldots\\
+\end{tabular}}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}An Interpreter\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{l}
+$\{$\\
+\;\;$x := 5 \text{;}$\\
+\;\;$y := x * 3\text{;}$\\
+\;\;$y := x * 4\text{;}$\\
+\;\;$x := u * 3$\\
+$\}$
+\end{tabular}}
+\end{center}
+
+\begin{itemize}
+\item the interpreter has to record the value of \bl{$x$} before assigning a value to \bl{$y$}\pause
+\item \bl{\text{eval}(stmt, env)}
+\end{itemize}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides09.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides09.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,853 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usetikzlibrary{plotmarks}
+\usepackage{graphicx}
+\usepackage{pgfplots}
+
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{while}{
+ morekeywords={if,then,else,while,do,true,false,write},
+ otherkeywords={=,!=,:=,<,>,;},
+ sensitive=true,
+ morecomment=[n]{/*}{*/},
+}
+
+
+\lstset{language=While,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 09, King's College London, 28.~November 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+
+% The data files, written on the first run.
+\begin{filecontents}{compiled.data}
+%1 0.234146
+%5000 0.227539
+%10000 0.280748
+50000 1.087897
+100000 3.713165
+250000 21.6624545
+500000 85.872613
+750000 203.6408015
+1000000 345.736574
+\end{filecontents}
+
+\begin{filecontents}{interpreted.data}
+%1 0.00503
+200 1.005863
+400 7.8296765
+500 15.43106
+600 27.2321885
+800 65.249271
+1000 135.4493445
+1200 232.134097
+1400 382.527227
+\end{filecontents}
+
+\begin{filecontents}{interpreted2.data}
+%1 0.00503
+200 1.005863
+400 7.8296765
+600 27.2321885
+800 65.249271
+1000 135.4493445
+1200 232.134097
+1400 382.527227
+\end{filecontents}
+
+\begin{filecontents}{compiled2.data}
+200 0.222058
+400 0.215204
+600 0.202031
+800 0.21986
+1000 0.205934
+1200 0.1981615
+1400 0.207116
+\end{filecontents}
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (9)\\[3mm]
+ \end{tabular}}
+
+ \normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ \end{tabular}
+ \end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+Imagine the following situation: You talk to somebody
+and you find out that she/he has implemented a compiler.\smallskip
+
+What is your reaction? Check all that apply.\bigskip\pause
+
+ \begin{itemize}
+ \item[$\Box$] You think she/he is God
+ \item[$\Box$] \"Uberhacker
+ \item[$\Box$] superhuman
+ \item[$\Box$] wizard
+ \item[$\Box$] supremo
+ \end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}While-Language\end{tabular}}
+
+
+\begin{center}
+\bl{\begin{tabular}{@{}lcl@{}}
+$Stmt$ & $\rightarrow$ & $\text{skip}$\\
+ & $|$ & $Id := AExp$\\
+ & $|$ & $\text{if}\; B\!Exp \;\text{then}\; Block \;\text{else}\; Block$\\
+ & $|$ & $\text{while}\; B\!Exp \;\text{do}\; Block$\\
+ & $|$ & $\alert{\text{write}\; Id}$\medskip\\
+$Stmts$ & $\rightarrow$ & $Stmt \;\text{;}\; Stmts$\\
+ & $|$ & $Stmt$\medskip\\
+$Block$ & $\rightarrow$ & $\{ Stmts \}$\\
+ & $|$ & $Stmt$\medskip\\
+$AExp$ & $\rightarrow$ & \ldots\\
+$BExp$ & $\rightarrow$ & \ldots\\
+\end{tabular}}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Fibonacci Numbers\end{tabular}}
+
+\mbox{}\\[-18mm]\mbox{}
+
+{\lstset{language=While}\fontsize{10}{12}\selectfont
+\texttt{\lstinputlisting{fib.while}}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Interpreter\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{@{}lcl@{}}
+$\text{eval}(n, E)$ & $\dn$ & $n$\\
+$\text{eval}(x, E)$ & $\dn$ & $E(x)$ \;\;\;\textcolor{black}{lookup \bl{$x$} in \bl{$E$}}\\
+$\text{eval}(a_1 + a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) + \text{eval}(a_2, E)$\\
+$\text{eval}(a_1 - a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) - \text{eval}(a_2, E)$\\
+$\text{eval}(a_1 * a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) * \text{eval}(a_2, E)$\bigskip\\
+$\text{eval}(a_1 = a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) = \text{eval}(a_2, E)$\\
+$\text{eval}(a_1\,!\!= a_2, E)$ & $\dn$ & $\neg(\text{eval}(a_1, E) = \text{eval}(a_2, E))$\\
+$\text{eval}(a_1 < a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) < \text{eval}(a_2, E)$\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Interpreter (2)\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{@{}lcl@{}}
+$\text{eval}(\text{skip}, E)$ & $\dn$ & $E$\\
+$\text{eval}(x:=a, E)$ & $\dn$ & \bl{$E(x \mapsto \text{eval}(a, E))$}\\
+\multicolumn{3}{@{}l@{}}{$\text{eval}(\text{if}\;b\;\text{then}\;cs_1\;\text{else}\;cs_2 , E) \dn$}\\
+\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{if}\;\text{eval}(b,E)\;\text{then}\;
+\text{eval}(cs_1,E)$}\\
+\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\phantom{\text{if}\;\text{eval}(b,E)\;}\text{else}\;\text{eval}(cs_2,E)$}\\
+\multicolumn{3}{@{}l@{}}{$\text{eval}(\text{while}\;b\;\text{do}\;cs, E) \dn$}\\
+\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{if}\;\text{eval}(b,E)$}\\
+\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{then}\;
+\text{eval}(\text{while}\;b\;\text{do}\;cs, \text{eval}(cs,E))$}\\
+\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{else}\; E$}\\
+$\text{eval}(\text{write}\; x, E)$ & $\dn$ & $\{\;\text{println}(E(x))\; ;\;E\;\}$\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Test Program\end{tabular}}
+
+\mbox{}\\[-18mm]\mbox{}
+
+{\lstset{language=While}\fontsize{10}{12}\selectfont
+\texttt{\lstinputlisting{loops.while}}}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Interpreted Code\end{tabular}}
+
+\begin{center}
+\begin{tikzpicture}
+\begin{axis}[axis x line=bottom, axis y line=left, xlabel=n, ylabel=secs, legend style=small]
+\addplot+[smooth] file {interpreted.data};
+\end{axis}
+\end{tikzpicture}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Java Virtual Machine\end{tabular}}
+
+\begin{itemize}
+\item introduced in 1995
+\item is a stack-based VM (like Postscript, CLR of .Net)
+\item contains a JIT compiler
+\item many languages take advantage of JVM's infrastructure (JRE)
+\item is garbage collected $\Rightarrow$ no buffer overflows
+\item some languages compiled to the JVM: Scala, Clojure\ldots
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
+
+{\Large\bl{1 + 2}}
+
+\begin{center}
+\bl{\begin{tabular}{l}
+ldc 1\\
+ldc 2\\
+iadd\\
+\end{tabular}}
+\end{center}\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
+
+{\Large\bl{1 + 2 + 3}}
+
+\begin{center}
+\bl{\begin{tabular}{l}
+ldc 1\\
+ldc 2\\
+iadd\\
+ldc 3\\
+iadd\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
+
+{\Large\bl{1 + (2 + 3)}}
+
+\begin{center}
+\bl{\begin{tabular}{l}
+ldc 1\\
+ldc 2\\
+ldc 3\\
+iadd\\
+iadd\\
+\end{tabular}}
+\end{center}\bigskip\pause
+\vfill
+
+\bl{dadd, fadd, ladd, \ldots}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{@{}lcl@{}}
+$\text{compile}(n)$ & $\dn$ & $\text{ldc}\;n$\\
+$\text{compile}(a_1 + a_2)$ & $\dn$\\
+\multicolumn{3}{l}{$\qquad\text{compile}(a_1) \;@\;\text{compile}(a_2)\;@\; \text{iadd}$}\smallskip\\
+$\text{compile}(a_1 - a_2)$ & $\dn$\\
+\multicolumn{3}{l}{$\qquad\text{compile}(a_1) \;@\; \text{compile}(a_2)\;@\; \text{isub}$}\smallskip\\
+$\text{compile}(a_1 * a_2)$ & $\dn$\\
+\multicolumn{3}{l}{$\qquad\text{compile}(a_1) \;@\; \text{compile}(a_2)\;@\; \text{imul}$}\smallskip\\
+\end{tabular}}
+\end{center}\pause
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
+
+{\Large\bl{1 + 2 * 3 + (4 - 3)}}
+
+\begin{center}
+\bl{\begin{tabular}{l}
+ldc 1\\
+ldc 2\\
+ldc 3\\
+imul\\
+ldc 4\\
+ldc 3\\
+isub\\
+iadd\\
+iadd\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Variables\end{tabular}}
+
+{\Large\bl{$x := 5 + y * 2$}}\bigskip\pause
+
+\begin{itemize}
+\item lookup: \bl{$\text{iload}\; index$}
+\item store: \bl{$\text{istore}\; index$}
+\end{itemize}\bigskip\pause
+
+while compilating we have to maintain a map between our identifiers and the
+Java bytecode indices
+
+\begin{center}
+\bl{$\text{compile}(a, E)$}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
+
+\begin{center}
+\bl{\begin{tabular}{@{}lcl@{}}
+$\text{compile}(n, E)$ & $\dn$ & $\text{ldc}\;n$\\
+$\text{compile}(a_1 + a_2, E)$ & $\dn$\\
+\multicolumn{3}{l}{$\qquad\text{compile}(a_1, E) \;@\;\text{compile}(a_2. E)\;@\; \text{iadd}$}\smallskip\\
+$\text{compile}(a_1 - a_2, E)$ & $\dn$\\
+\multicolumn{3}{l}{$\qquad\text{compile}(a_1, E) \;@\; \text{compile}(a_2, E)\;@\; \text{isub}$}\smallskip\\
+$\text{compile}(a_1 * a_2, E)$ & $\dn$\\
+\multicolumn{3}{l}{$\qquad\text{compile}(a_1, E) \;@\; \text{compile}(a_2, E)\;@\; \text{imul}$}\bigskip\\
+$\text{compile}(x, E)$ & $\dn$ & $\text{iload}\;E(x)$\\
+\end{tabular}}
+\end{center}\pause
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling Statements\end{tabular}}
+
+We return a list of instructions and an environment for the variables
+
+\begin{center}
+\bl{\begin{tabular}{@{}l@{\hspace{1mm}}c@{\hspace{1mm}}l@{}}
+$\text{compile}(\text{skip}, E)$ & $\dn$ & $(N\!il, E)$\bigskip\\
+$\text{compile}(x := a, E)$ & $\dn$\\
+\multicolumn{3}{l}{$(\text{compile}(a, E) \;@\;\text{istore}\;index, E(x\mapsto index))$}\\
+\end{tabular}}
+\end{center}\medskip
+
+where \bl{$index$} is \bl{$E(x)$} if it is already defined, or if it is not then the largest index not yet seen
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
+
+{\Large\bl{$x := x + 1$}}
+
+\begin{center}
+\bl{\begin{tabular}{l}
+iload $n_x$\\
+ldc 1\\
+iadd\\
+istore $n_x$\\
+\end{tabular}}
+\end{center}
+
+where \bl{$n_x$} is the index corresponding to the variable \bl{$x$}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling Ifs\end{tabular}}
+
+{\Large\bl{$\text{if}\;b\;\text{else}\;cs_1\;\text{then}\;cs_2$}}\bigskip\bigskip
+
+\onslide<2->{Case }\only<2>{{\bf True}:}\only<3>{{\bf False}:}
+
+\begin{center}
+\begin{tikzpicture}[node distance=2mm and 4mm,
+ block/.style={rectangle, minimum size=1cm, draw=black, line width=1mm},
+ point/.style={rectangle, inner sep=0mm, minimum size=0mm, fill=red},
+ skip loop/.style={red, line width=1mm, to path={-- ++(0,-10mm) -| (\tikztotarget)}}]
+\node (A1) [point] {};
+\node (b) [block, right=of A1] {code of \bl{$b$}};
+\node (A2) [point, right=of b] {};
+\node (cs1) [block, right=of A2] {code of \bl{$cs_1$}};
+\node (A3) [point, right=of cs1] {};
+\node (cs2) [block, right=of A3] {code of \bl{$cs_2$}};
+\node (A4) [point, right=of cs2] {};
+
+\only<2>{
+\draw (A1) edge [->, red, line width=1mm] (b);
+\draw (b) edge [->, red, line width=1mm] (cs1);
+\draw (cs1) edge [->, red, line width=1mm] (A3);
+\draw (A3) edge [->,skip loop] (A4);
+\node [below=of cs2] {\raisebox{-5mm}{\small{}jump}};}
+\only<3>{
+\draw (A1) edge [->, red, line width=1mm] (b);
+\draw (b) edge [->, red, line width=1mm] (A2);
+\draw (A2) edge [skip loop] (A3);
+\draw (A3) edge [->, red, line width=1mm] (cs2);
+\draw (cs2) edge [->,red, line width=1mm] (A4);
+\node [below=of cs1] {\raisebox{-5mm}{\small{}conditional jump}};}
+\end{tikzpicture}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Conditional Jumps\end{tabular}}
+
+\begin{minipage}{1.1\textwidth}
+\begin{itemize}
+\item \bl{if\_icmpeq $label$} if two ints are equal, then jump\medskip
+\item \bl{if\_icmpne $label$} if two ints aren't equal, then jump\medskip
+\item \bl{if\_icmpge $label$} if one int is greater or equal then another, then jump
+\item[]\ldots
+\end{itemize}
+\end{minipage}\pause
+
+
+\begin{center}
+\bl{\begin{tabular}{l}
+$L_1$:\\
+\hspace{5mm}if\_icmpeq\;$L_2$\\
+\hspace{5mm}iload 1\\
+\hspace{5mm}ldc 1\\
+\hspace{5mm}iadd\\
+\hspace{5mm}if\_icmpeq\;$L_1$\\
+$L_2$:
+\end{tabular}}
+\end{center}
+
+\begin{textblock}{3.5}(11,12)
+\only<3>{labels must be unique}
+\end{textblock}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling BExps\end{tabular}}
+
+{\Large\bl{$a_1 = a_2$}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$\text{compile}(a_1 = a_2, E, lab)$ & $\dn$\\
+\multicolumn{3}{l}{$\quad\text{compile}(a_1, E) \;@\;\text{compile}(a_2, E)\;@\; \text{if\_icmpne}\;lab$}
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling Ifs\end{tabular}}
+
+{\Large\bl{if $b$ then $cs_1$ else $cs_2$}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$\text{compile}(\text{if}\;b\;\text{then}\; cs_1\;\text{else}\; cs_2, E)$ & $\dn$\\
+\multicolumn{3}{l}{$\quad l_{ifelse}\;$ \textcolor{black}{(fresh label)}}\\
+\multicolumn{3}{l}{$\quad l_{ifend}\;$ \textcolor{black}{(fresh label)}}\\
+\multicolumn{3}{l}{$\quad (is_1, E') = \text{compile}(cs_1, E)$}\\
+\multicolumn{3}{l}{$\quad (is_2, E'') = \text{compile}(cs_2, E')$}\\
+\multicolumn{3}{l}{$\quad(\text{compile}(b, E, l_{ifelse})$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\;is_1$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\; \text{goto}\;l_{ifend}$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\;l_{ifelse}:$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\;is_2$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\;l_{ifend}:, E'')$}\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling Whiles\end{tabular}}
+
+{\Large\bl{$\text{while}\;b\;\text{do}\;cs$}}\bigskip\bigskip
+
+\onslide<2->{Case }\only<2>{{\bf True}:}\only<3>{{\bf False}:}
+
+\begin{center}
+\begin{tikzpicture}[node distance=2mm and 4mm,
+ block/.style={rectangle, minimum size=1cm, draw=black, line width=1mm},
+ point/.style={rectangle, inner sep=0mm, minimum size=0mm, fill=red},
+ skip loop/.style={red, line width=1mm, to path={-- ++(0,-10mm) -| (\tikztotarget)}}]
+\node (A0) [point, left=of A1] {};
+\node (A1) [point] {};
+\node (b) [block, right=of A1] {code of \bl{$b$}};
+\node (A2) [point, right=of b] {};
+\node (cs1) [block, right=of A2] {code of \bl{$cs$}};
+\node (A3) [point, right=of cs1] {};
+\node (A4) [point, right=of A3] {};
+
+\only<2>{
+\draw (A0) edge [->, red, line width=1mm] (b);
+\draw (b) edge [->, red, line width=1mm] (cs1);
+\draw (cs1) edge [->, red, line width=1mm] (A3);
+\draw (A3) edge [->,skip loop] (A1);}
+\only<3>{
+\draw (A0) edge [->, red, line width=1mm] (b);
+\draw (b) edge [->, red, line width=1mm] (A2);
+\draw (A2) edge [skip loop] (A3);
+\draw (A3) edge [->, red, line width=1mm] (A4);}
+\end{tikzpicture}
+\end{center}
+
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling Whiles\end{tabular}}
+
+{\Large\bl{while $b$ do $cs$}}
+
+\begin{center}
+\bl{\begin{tabular}{lcl}
+$\text{compile}(\text{while}\; b\; \text{do} \;cs, E)$ & $\dn$\\
+\multicolumn{3}{l}{$\quad l_{wbegin}\;$ \textcolor{black}{(fresh label)}}\\
+\multicolumn{3}{l}{$\quad l_{wend}\;$ \textcolor{black}{(fresh label)}}\\
+\multicolumn{3}{l}{$\quad (is, E') = \text{compile}(cs_1, E)$}\\
+\multicolumn{3}{l}{$\quad(l_{wbegin}:$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\;\text{compile}(b, E, l_{wend})$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\;is$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\; \text{goto}\;l_{wbegin}$}\\
+\multicolumn{3}{l}{$\quad\phantom{(}@\;l_{wend}:, E')$}\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiling Writes\end{tabular}}
+
+{\Large\bl{write $x$}}
+
+\begin{center}
+\small\bl{\begin{tabular}{l}
+.method public static write(I)V\hspace{1cm}\textcolor{black}{(library function)}\\
+\;\; .limit locals 5 \\
+\;\; .limit stack 5 \\
+\;\; iload 0 \\
+\;\; getstatic java/lang/System/out Ljava/io/PrintStream;\\
+\;\; swap \\
+\;\; invokevirtual java/io/PrintStream/println(I)V \\
+\;\; return \\
+.end method\bigskip\bigskip\\
+%
+\normalsize
+iload $E(x)$\\
+invokestatic write(I)V\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\begin{center}
+\small\bl{\begin{tabular}{l}
+.class public XXX.XXX\\
+.super java/lang/Object\\
+\\
+.method public <init>()V\\
+\;\; aload\_0\\
+\;\; invokenonvirtual java/lang/Object/<init>()V\\
+ \;\; return\\
+.end method\\
+\\
+.method public static main([Ljava/lang/String;)V\\
+\;\; .limit locals 200\\
+\;\; .limit stack 200\\
+\\
+ \textcolor{black}{(here comes the compiled code)}\\
+\\
+\;\; return\\
+.end method\\
+\end{tabular}}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}Next Compiler Phases\end{tabular}}
+
+\begin{itemize}
+\item assembly $\Rightarrow$ byte code (class file)
+\item labels $\Rightarrow$ absolute or relative jumps\bigskip\bigskip
+\item \texttt{javap} is a disassembler for class files
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiled Code\end{tabular}}
+
+\begin{center}
+\begin{tikzpicture}
+\begin{axis}[axis x line=bottom, axis y line=left, xlabel=n, ylabel=secs, legend style=small]
+\addplot+[smooth] file {compiled.data};
+\end{axis}
+\end{tikzpicture}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiled vs.~Interpreted Code\end{tabular}}
+
+\begin{center}
+\begin{tikzpicture}
+\begin{loglogaxis}[axis x line=bottom, axis y line=left, xlabel=n, ylabel=secs, legend style=small]
+\addplot+[smooth] file {interpreted.data};
+\addplot+[smooth] file {compiled.data};
+\end{loglogaxis}
+\end{tikzpicture}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}Compiled vs.~Interpreted Code\end{tabular}}
+
+\begin{center}
+\begin{tikzpicture}
+\begin{axis}[axis x line=bottom, axis y line=left, ylabel=secs,
+ xlabel=n,
+ enlargelimits=0.05,
+ ybar interval=0.7, legend style=small]
+\addplot file {interpreted2.data};
+\addplot file {compiled2.data};
+%\legend{interpreted, compiled}
+\end{axis}
+\end{tikzpicture}
+\end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[t]
+\frametitle{\begin{tabular}{c}What Next\end{tabular}}
+
+\begin{itemize}
+\item register spilling
+\item dead code removal
+\item loop optimisations
+\item instruction selection
+\item type checking
+\item concurrency
+\item fuzzy testing
+\item verification\bigskip\\
+
+\item GCC, LLVM, tracing JITs
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides/slides10.pdf has changed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/slides/slides10.tex Sat Jun 15 09:23:18 2013 -0400
@@ -0,0 +1,383 @@
+\documentclass[dvipsnames,14pt,t]{beamer}
+\usepackage{beamerthemeplainculight}
+\usepackage[T1]{fontenc}
+\usepackage[latin1]{inputenc}
+\usepackage{mathpartir}
+\usepackage[absolute,overlay]{textpos}
+\usepackage{ifthen}
+\usepackage{tikz}
+\usepackage{pgf}
+\usepackage{calc}
+\usepackage{ulem}
+\usepackage{courier}
+\usepackage{listings}
+\renewcommand{\uline}[1]{#1}
+\usetikzlibrary{arrows}
+\usetikzlibrary{automata}
+\usetikzlibrary{shapes}
+\usetikzlibrary{shadows}
+\usetikzlibrary{positioning}
+\usetikzlibrary{calc}
+\usetikzlibrary{plotmarks}
+\usepackage{graphicx}
+\usepackage{pgfplots}
+
+
+\definecolor{javared}{rgb}{0.6,0,0} % for strings
+\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
+\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
+\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
+
+\lstset{language=Java,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{scala}{
+ morekeywords={abstract,case,catch,class,def,%
+ do,else,extends,false,final,finally,%
+ for,if,implicit,import,match,mixin,%
+ new,null,object,override,package,%
+ private,protected,requires,return,sealed,%
+ super,this,throw,trait,true,try,%
+ type,val,var,while,with,yield},
+ otherkeywords={=>,<-,<\%,<:,>:,\#,@},
+ sensitive=true,
+ morecomment=[l]{//},
+ morecomment=[n]{/*}{*/},
+ morestring=[b]",
+ morestring=[b]',
+ morestring=[b]"""
+}
+
+
+\lstset{language=Scala,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+\lstdefinelanguage{while}{
+ morekeywords={if,then,else,while,do,true,false,write},
+ otherkeywords={=,!=,:=,<,>,;},
+ sensitive=true,
+ morecomment=[n]{/*}{*/},
+}
+
+
+\lstset{language=While,
+ basicstyle=\ttfamily,
+ keywordstyle=\color{javapurple}\bfseries,
+ stringstyle=\color{javagreen},
+ commentstyle=\color{javagreen},
+ morecomment=[s][\color{javadocblue}]{/**}{*/},
+ numbers=left,
+ numberstyle=\tiny\color{black},
+ stepnumber=1,
+ numbersep=10pt,
+ tabsize=2,
+ showspaces=false,
+ showstringspaces=false}
+
+
+% beamer stuff
+\renewcommand{\slidecaption}{AFL 10, King's College London, 5.~December 2012}
+\newcommand{\bl}[1]{\textcolor{blue}{#1}}
+\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
+
+
+% The data files, written on the first run.
+\begin{filecontents}{compiled.data}
+%1 0.234146
+%5000 0.227539
+%10000 0.280748
+50000 1.087897
+100000 3.713165
+250000 21.6624545
+500000 85.872613
+750000 203.6408015
+1000000 345.736574
+\end{filecontents}
+
+\begin{filecontents}{interpreted.data}
+%1 0.00503
+200 1.005863
+400 7.8296765
+500 15.43106
+600 27.2321885
+800 65.249271
+1000 135.4493445
+1200 232.134097
+1400 382.527227
+\end{filecontents}
+
+\begin{filecontents}{interpreted2.data}
+%1 0.00503
+200 1.005863
+400 7.8296765
+600 27.2321885
+800 65.249271
+1000 135.4493445
+1200 232.134097
+1400 382.527227
+\end{filecontents}
+
+\begin{filecontents}{compiled2.data}
+200 0.222058
+400 0.215204
+600 0.202031
+800 0.21986
+1000 0.205934
+1200 0.1981615
+1400 0.207116
+\end{filecontents}
+
+\begin{document}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}<1>[t]
+\frametitle{%
+ \begin{tabular}{@ {}c@ {}}
+ \\[-3mm]
+ \LARGE Automata and \\[-2mm]
+ \LARGE Formal Languages (10)\\[3mm]
+ \end{tabular}}
+
+ \normalsize
+ \begin{center}
+ \begin{tabular}{ll}
+ Email: & christian.urban at kcl.ac.uk\\
+ Of$\!$fice: & S1.27 (1st floor Strand Building)\\
+ Slides: & KEATS (also home work is there)\\
+ \end{tabular}
+ \end{center}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\Large\bf
+There are more problems, than there are programs.\bigskip\bigskip\pause\\
+
+There must be a problem for which there is no program.
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Revision: Proofs}
+
+\begin{center}
+\includegraphics[scale=0.4]{river-stones.jpg}
+\end{center}
+
+\end{frame}}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Subsets}
+
+\Large
+\bl{$A \subseteq B$}\bigskip\bigskip\\
+
+\bl{$\forall e.\; e \in A \Rightarrow e \in B$}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Subsets}
+
+\Large
+\bl{$A \subseteq B$} and \bl{$B \subseteq A$}\bigskip
+
+then \bl{$A = B$}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Injective Function}
+
+\Large
+\bl{f} is an injective function iff \bigskip
+
+\bl{$\forall x y.\; f(x) = f(y) \Rightarrow x = y$}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Cardinality}
+
+\Large
+\bl{$|A|$} $\dn$ ``how many elements''\bigskip\\
+
+\bl{$A \subseteq B \Rightarrow |A| \leq |B|$}\bigskip\\\pause
+
+if there is an injective function \bl{$f: A \rightarrow B$} then \bl{$|A| \leq |B|$}\
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Natural Numbers}
+
+\Large
+\bl{$\mathbb{N}$} \bl{$\dn$} \bl{$\{0, 1, 2, 3, .......\}$}\bigskip\pause
+
+\bl{$A$} is \alert{countable} iff \bl{$|A| \leq |\mathbb{N}|$}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{First Question}
+
+\Large
+\bl{$|\mathbb{N} - \{0\}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\bigskip
+
+\normalsize
+\bl{$\geq$} or \bl{$\leq$} or \bl{$=$}
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\Large
+\bl{$|\mathbb{N} - \{0, 1\}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\pause
+
+\bl{$|\mathbb{N} - \mathbb{O}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\bigskip
+
+\normalsize
+\bl{$\mathbb{O}$} $\dn$ odd numbers\quad \bl{$\{1,3,5......\}$}\\ \pause
+\bl{$\mathbb{E}$} $\dn$ even numbers\quad \bl{$\{0,2,4......\}$}\\
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\Large
+\bl{$|\mathbb{N} \cup \mathbb{-N}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\bigskip
+
+
+\normalsize
+\bl{$\mathbb{\phantom{-}N}$} $\dn$ positive numbers\quad \bl{$\{0,1,2,3,......\}$}\\
+\bl{$\mathbb{-N}$} $\dn$ negative numbers\quad \bl{$\{0,-1,-2,-3,......\}$}\\
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+
+\Large
+\bl{$A$} is \alert{countable} if there exists an injective \bl{$f : A \rightarrow \mathbb{N}$}\bigskip
+
+\bl{$A$} is \alert{uncountable} if there does not exist an injective \bl{$f : A \rightarrow \mathbb{N}$}\bigskip\bigskip
+
+
+countable: \bl{$|A| \leq |\mathbb{N}|$}\\
+uncountable: \bl{$|A| > |\mathbb{N}|$}\pause\bigskip
+
+
+Does there exist such an \bl{$A$} ?
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Halting Problem}
+
+\large
+Assume a program \bl{$H$} that decides for all programs \bl{$A$} and all
+input data \bl{$D$} whether\bigskip
+
+\begin{itemize}
+\item \bl{$H(A, D) \dn 1$} iff \bl{$A(D)$} terminates
+\item \bl{$H(A, D) \dn 0$} otherwise
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Halting Problem (2)}
+
+\large
+Given such a program \bl{$H$} define the following program \bl{$C$}:
+for all programs \bl{$A$}\bigskip
+
+\begin{itemize}
+\item \bl{$C(A) \dn 0$} iff \bl{$H(A, A) = 0$}
+\item \bl{$C(A) \dn$ loops} otherwise
+\end{itemize}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{Contradiction}
+
+
+\bl{$H(C, C)$} is either \bl{$0$} or \bl{$1$}.
+
+\begin{itemize}
+\item \bl{$H(C, C) = 1$} $\stackrel{\text{def}\,H}{\Rightarrow}$ \bl{$C(C)\downarrow$} $\stackrel{\text{def}\,C}{\Rightarrow}$ \bl{$H(C, C)=0$}
+\item \bl{$H(C, C) = 0$} $\stackrel{\text{def}\,H}{\Rightarrow}$ \bl{$C(C)$} loops $\stackrel{\text{def}\,C}{\Rightarrow}$\\
+\hspace{7cm}\bl{$H(C, C)=1$}
+\end{itemize}
+
+Contradiction in both cases. So \bl{$H$} cannot exist.
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\end{document}
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-master: t
+%%% End:
+
Binary file slides01.pdf has changed
--- a/slides01.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,483 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 01, King's College London, 26.~September 2012}
-
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (1)\\[-3mm]
- \end{tabular}}
-
- \begin{center}
- \includegraphics[scale=0.3]{pics/ante1.jpg}\hspace{5mm}
- \includegraphics[scale=0.31]{pics/ante2.jpg}\\
- \footnotesize\textcolor{gray}{Antikythera automaton, 100 BC (Archimedes?)}
- \end{center}
-
-\normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{textblock}{1}(2,5)
-\begin{tabular}{c}
-\includegraphics[scale=0.15]{pics/servers.png}\\[-2mm]
-\small Server
-\end{tabular}
-\end{textblock}
-
-\begin{textblock}{1}(5.6,4)
- \begin{tikzpicture}[scale=1.1]
- \draw[white] (0,1) node (X) {};
- \draw[white] (2,1) node (Y) {};
- \draw[white] (0,0) node (X1) {};
- \draw[white] (2,0) node (Y1) {};
- \draw[white] (0,-1) node (X2) {};
- \draw[white] (2,-1) node (Y2) {};
- \draw[red, <-, line width = 2mm] (X) -- (Y);
- \node [inner sep=5pt,label=above:\textcolor{black}{GET request}] at ($ (X)!.5!(Y) $) {};
- \draw[red, ->, line width = 2mm] (X1) -- (Y1);
- \node [inner sep=5pt,label=above:\textcolor{black}{webpage}] at ($ (X1)!.5!(Y1) $) {};
- \draw[red, <-, line width = 2mm] (X2) -- (Y2);
- \node [inner sep=7pt,label=above:\textcolor{black}{POST data}] at ($ (X2)!.5!(Y2) $) {};
- \end{tikzpicture}
-\end{textblock}
-
-
-\begin{textblock}{1}(9,5.5)
-\begin{tabular}{c}
-\includegraphics[scale=0.15]{pics/laptop.png}\\[-2mm]
-\small Browser
-\end{tabular}
-\end{textblock}
-
-\only<2>{
-\begin{textblock}{10}(2,13.5)
-\begin{itemize}
-\item programming languages, compilers
-\end{itemize}
-\end{textblock}}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-transforming strings into structured data\\[10mm]
-
-{\LARGE\bf Lexing}\medskip\\
-\hspace{5mm}(recognising ``words'')\\[6mm]
-
-{\LARGE\bf Parsing}\medskip\\
-\hspace{5mm}(recognising ``sentences'')
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-The subject is quite old:
-
-\begin{itemize}
-\item Turing Machines, 1936
-\item first compiler for COBOL, 1957 (Grace Hopper)
-\item but surprisingly research papers are still published now
-\end{itemize}
-
-\begin{flushright}
-\includegraphics[scale=0.3]{pics/hopper.jpg}\\
-\footnotesize\textcolor{gray}{Grace Hopper}
-\end{flushright}
-
-{\footnotesize\textcolor{gray}{(she made it to David Letterman's Tonight Show, \url{http://www.youtube.com/watch?v=aZOxtURhfEU})}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}This Course\end{tabular}}
-
-\begin{itemize}
-\item the ultimate goal is to implement a small web-browser (really small one)\bigskip
-\end{itemize}
-
-Let's start with:
-
-\begin{itemize}
-\item a web-crawler
-\item an email harvester
-\item a web-scraper
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}A Web-Crawler\end{tabular}}
-
-\mbox{}\\[10mm]
-
-\begin{enumerate}
-\item given an URL, read the corresponding webpage
-\item extract all links from it
-\item call the web-crawler again for all these links
-\end{enumerate}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}A Web-Crawler\end{tabular}}
-
-\mbox{}\\[10mm]
-
-
-\begin{enumerate}
-\item given an URL, read the corresponding webpage
-\item if not possible print, out a problem
-\item if possible, extract all links from it
-\item call the web-crawler again for all these links
-\end{enumerate}\bigskip\pause
-
-\small (we need a bound for the number of recursive calls)
-
-\small (the purpose is to check all links on my own webpage)
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Scala\end{tabular}}
-
-\footnotesize a simple Scala function for reading webpages\\[-3mm]
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app0.scala}}}\pause
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinline{get_page("""http://www.inf.kcl.ac.uk/staff/urbanc/""")}}}\pause\bigskip
-
-
-\footnotesize slightly more complicated for handling errors properly:\\[-3mm]
-
-\footnotesize
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app1.scala}}}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}A Regular Expression\end{tabular}}
-
-\begin{itemize}
-\item \ldots{} is a pattern or template for specifying strings
-\end{itemize}\bigskip
-
-\begin{center}
-\only<1>{{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
-\texttt{"https?://[$\hat{\hspace{2mm}}$"]*"}}}%
-\only<2>{{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
-\texttt{"""\textbackslash{}"https?://[$\hat{\hspace{2mm}}$\textbackslash{}"]*\textbackslash{}"""".r}}}
-\end{center}\bigskip\bigskip
-
-matches for example\\
-\;{\lstset{language=Scala}\fontsize{12}{14}\selectfont\bf
-\texttt{"http://www.foobar.com"}}\\
-\;{\lstset{language=Scala}\fontsize{12}{14}\selectfont\bf
-\texttt{"https://www.tls.org"}}\\
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
-\texttt{rexp.findAllIn(string)}}\medskip
-
-returns a list of all (sub)strings that match the regular expression\bigskip\bigskip
-
-{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf
-\texttt{rexp.findFirstIn(string)}}\medskip
-
-returns either {\bf\texttt{None}} if no (sub)string matches
-or {\bf\texttt{Some(s)}} with the first (sub)string
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app2.scala}}}\medskip
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{crawl(some\_start\_URL, 2)}}\
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\footnotesize
-a version that only ``crawls'' links in my domain:
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app3.scala}}}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\footnotesize
-a little email ``harvester'':
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app4.scala}}}\bigskip
-
-\tiny
-\textcolor{gray}{\url{http://net.tutsplus.com/tutorials/other/8-regular-expressions-you-should-know/}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
-
-Their inductive definition:\medskip
-
-\begin{textblock}{6}(2,5)
- \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
- \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
- & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
- & \bl{$\mid$} & \bl{c} & character\\
- & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
- & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
- & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
- \end{tabular}
- \end{textblock}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
-
-\small
-In Scala:
-
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app51.scala}}}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Meaning of a\\[-2mm] Regular Expression\end{tabular}}
-
-\begin{textblock}{15}(1,4)
- \begin{tabular}{@ {}rcl}
- \bl{$L$($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$}\\
- \bl{$L$($\epsilon$)} & \bl{$\dn$} & \bl{$\{$""$\}$}\\
- \bl{$L$(c)} & \bl{$\dn$} & \bl{$\{$"c"$\}$}\\
- \bl{$L$(r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{$L$(r$_1$) $\cup$ $L$(r$_2$)}\\
- \bl{$L$(r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{$\{$ s$_1$ @ s$_2$ $|$ s$_1$ $\in$ $L$(r$_1$) $\wedge$ s$_2$ $\in$
- $L$(r$_2$) $\}$}\\
- \bl{$L$(r$^*$)} & \bl{$\dn$} & \onslide<4->{\bl{$\bigcup_{n \ge 0}$ $L$(r)$^n$}}\\
- \end{tabular}\bigskip
-
-\onslide<2->{
-\hspace{5mm}\bl{$L$(r)$^0$ $\;\dn\;$ $\{$""$\}$}\\
-\bl{$L$(r)$^{n+1}$ $\;\dn\;$ $L$(r) @ $L$(r)$^n$}\hspace{9mm}\onslide<3->{\small\textcolor{gray}{(append on sets)}\\
-\small\hspace{5cm}\textcolor{gray}{$\{$ s$_1$ @ s$_2$ $|$ s$_1$ $\in$ $L$(r) $\wedge$ s$_2$ $\in$
- $L$(r)$^n$ $\}$}}
-}
- \end{textblock}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Meaning of Matching\end{tabular}}
-
-\large
-a regular expression \bl{r} matches a string \bl{s} is defined as
-
-\begin{center}
-\bl{s $\in$ $L$(r)}\\
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}This Course\end{tabular}}
-
-We will have a look at:
-
-\begin{itemize}
-\item regular expressions / regular expression matching
-\item automata
-\item the Myhill-Nerode theorem
-\item parsing
-\item grammars
-\item a small interpreter / web browser
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Exam\end{tabular}}
-
-\begin{itemize}
-\item The question ``Is this relevant for the exam?'' is not appreciated!\bigskip\\
-
-Whatever is in the homework sheets (and is not marked ``optional'') is relevant for the
-exam.\\ No code needs to be written in the exam.
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides02.pdf has changed
--- a/slides02.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,494 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 02, King's College London, 3.~October 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (2)\\[3mm]
- \end{tabular}}
-
- %\begin{center}
- %\includegraphics[scale=0.3]{pics/ante1.jpg}\hspace{5mm}
- %\includegraphics[scale=0.31]{pics/ante2.jpg}\\
- %\footnotesize\textcolor{gray}{Antikythera automaton, 100 BC (Archimedes?)}
- %\end{center}
-
-\normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Languages\end{tabular}}
-
-A \alert{language} is a set of strings.\bigskip
-
-A \alert{regular expression} specifies a set of strings or language.
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
-
-Their inductive definition:
-
-
-\begin{textblock}{6}(2,5)
- \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
- \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
- & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
- & \bl{$\mid$} & \bl{c} & character\\
- & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
- & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
- & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
- \end{tabular}
- \end{textblock}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
-
-Their implementation in Scala:
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app51.scala}}}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Meaning of a\\[-2mm] Regular Expression\end{tabular}}
-
-\begin{textblock}{15}(1,4)
- \begin{tabular}{@ {}rcl}
- \bl{$L$($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$}\\
- \bl{$L$($\epsilon$)} & \bl{$\dn$} & \bl{$\{$""$\}$}\\
- \bl{$L$(c)} & \bl{$\dn$} & \bl{$\{$"c"$\}$}\\
- \bl{$L$(r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{$L$(r$_1$) $\cup$ $L$(r$_2$)}\\
- \bl{$L$(r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{$L$(r$_1$) @ $L$(r$_2$)}\\
- \bl{$L$(r$^*$)} & \bl{$\dn$} & \bl{$\bigcup_{n \ge 0}$ $L$(r)$^n$}\\
- \end{tabular}\bigskip
-
-\hspace{5mm}\textcolor{gray}{$L$(r)$^0$ $\;\dn\;$ $\{$""$\}$}\\
-\textcolor{gray}{$L$(r)$^{n+1}$ $\;\dn\;$ $L$(r) @ $L$(r)$^n$}
-\end{textblock}
-
-\only<2->{
-\begin{textblock}{5}(11,5)
-\textcolor{gray}{\small
-A @ B\\
-\ldots you take out every string from A and
-concatenate it with every string in B
-}
-\end{textblock}}
-
-\only<3->{
-\begin{textblock}{6}(9,12)\small
-\bl{$L$} is a function from regular expressions to sets of strings\\
-\bl{$L$ : Rexp $\Rightarrow$ Set[String]}
-\end{textblock}}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\large
-\begin{center}
-What is \bl{$L$(a$^*$)}?
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-\newcommand{\YES}{\textcolor{gray}{yes}}
-\newcommand{\NO}{\textcolor{gray}{no}}
-\newcommand{\FORALLR}{\textcolor{gray}{$\forall$ r.}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Reg Exp Equivalences\end{tabular}}
-
-\begin{center}
-\begin{tabular}{l@ {\hspace{7mm}}rcl@ {\hspace{7mm}}l}
-&\bl{(a + b) + c} & \bl{$\equiv^?$} & \bl{a + (b + c)} & \onslide<2->{\YES}\\
-&\bl{a + a} & \bl{$\equiv^?$} & \bl{a} & \onslide<3->{\YES}\\
-&\bl{(a $\cdot$ b) $\cdot$ c} & \bl{$\equiv^?$} & \bl{a $\cdot$ (b $\cdot$ c)} & \onslide<4->{\YES}\\
-&\bl{a $\cdot$ a} & \bl{$\equiv^?$} & \bl{a} & \onslide<5->{\NO}\\
-&\bl{$\epsilon^*$} & \bl{$\equiv^?$} & \bl{$\epsilon$} & \onslide<6->{\YES}\\
-&\bl{$\varnothing^*$} & \bl{$\equiv^?$} & \bl{$\varnothing$} & \onslide<7->{\NO}\\
-\FORALLR &\bl{r $\cdot$ $\epsilon$} & \bl{$\equiv^?$} & \bl{r} & \onslide<8->{\YES}\\
-\FORALLR &\bl{r + $\epsilon$} & \bl{$\equiv^?$} & \bl{r} & \onslide<9->{\NO}\\
-\FORALLR &\bl{r + $\varnothing$} & \bl{$\equiv^?$} & \bl{r} & \onslide<10->{\YES}\\
-\FORALLR &\bl{r $\cdot$ $\varnothing$} & \bl{$\equiv^?$} & \bl{r} & \onslide<11->{\NO}\\
-&\bl{c $\cdot$ (a + b)} & \bl{$\equiv^?$} & \bl{(c $\cdot$ a) + (c $\cdot$ b)} & \onslide<12->{\YES}\\
-&\bl{a$^*$} & \bl{$\equiv^?$} & \bl{$\epsilon$ + (a $\cdot$ a$^*$)} & \onslide<13->{\YES}
-\end{tabular}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Meaning of Matching\end{tabular}}
-
-\large
-a regular expression \bl{r} matches a string \bl{s} is defined as
-
-\begin{center}
-\bl{s $\in$ $L$(r)}\\
-\end{center}\bigskip\bigskip\pause
-
-\small
-if \bl{r$_1$ $\equiv$ r$_2$}, then \bl{$s$ $\in$ $L$(r$_1$)} iff \bl{$s$ $\in$ $L$(r$_2$)}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}A Matching Algorithm\end{tabular}}
-
-\begin{itemize}
-\item given a regular expression \bl{r} and a string \bl{s}, say yes or no for whether
-\begin{center}
-\bl{s $\in$ $L$(r)}
-\end{center}
-or not.\bigskip\bigskip\pause
-\end{itemize}\pause
-
-\small
-\begin{itemize}
-\item Identifiers (strings of letters or digits, starting with a letter)
-\item Integers (a non-empty sequence of digits)
-\item Keywords (else, if, while, \ldots)
-\item White space (a non-empty sequence of blanks, newlines and tabs)
-\end{itemize}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}A Matching Algorithm\end{tabular}}
-
-\small
-whether a regular expression matches the empty string:\medskip
-
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app5.scala}}}
-
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Derivative of a Rexp\end{tabular}}
-
-\large
-If \bl{r} matches the string \bl{c::s}, what is a regular expression that matches \bl{s}?\bigskip\bigskip\bigskip\bigskip
-
-\small
-\bl{der c r} gives the answer
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Derivative of a Rexp (2)\end{tabular}}
-
-\begin{center}
-\begin{tabular}{@ {}l@ {\hspace{2mm}}c@ {\hspace{2mm}}l@ {\hspace{-10mm}}l@ {}}
- \bl{der c ($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
- \bl{der c ($\epsilon$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
- \bl{der c (d)} & \bl{$\dn$} & \bl{if c $=$ d then $\epsilon$ else $\varnothing$} & \\
- \bl{der c (r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{(der c r$_1$) + (der c r$_2$)} & \\
- \bl{der c (r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{if nullable r$_1$}\\
- & & \bl{then ((der c r$_1$) $\cdot$ r$_2$) + (der c r$_2$)}\\
- & & \bl{else (der c r$_1$) $\cdot$ r$_2$}\\
- \bl{der c (r$^*$)} & \bl{$\dn$} & \bl{(der c r) $\cdot$ (r$^*$)} &\smallskip\\\pause
-
- \bl{ders [] r} & \bl{$\dn$} & \bl{r} & \\
- \bl{ders (c::s) r} & \bl{$\dn$} & \bl{ders s (der c r)} & \\
- \end{tabular}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Derivative\end{tabular}}
-
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app6.scala}}}
-
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Rexp Matcher\end{tabular}}
-
-
-{\lstset{language=Scala}\fontsize{8}{10}\selectfont
-\texttt{\lstinputlisting{app7.scala}}}
-
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Proofs about Rexp\end{tabular}}
-
-Remember their inductive definition:\\[5cm]
-
-\begin{textblock}{6}(5,5)
- \begin{tabular}{@ {}rrl}
- \bl{r} & \bl{$::=$} & \bl{$\varnothing$}\\
- & \bl{$\mid$} & \bl{$\epsilon$} \\
- & \bl{$\mid$} & \bl{c} \\
- & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$}\\
- & \bl{$\mid$} & \bl{r$_1$ + r$_2$} \\
- & \bl{$\mid$} & \bl{r$^*$} \\
- \end{tabular}
- \end{textblock}
-
-If we want to prove something, say a property \bl{$P$(r)}, for all regular expressions \bl{r} then \ldots
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Proofs about Rexp (2)\end{tabular}}
-
-\begin{itemize}
-\item \bl{$P$} holds for \bl{$\varnothing$}, \bl{$\epsilon$} and \bl{c}\bigskip
-\item \bl{$P$} holds for \bl{r$_1$ + r$_2$} under the assumption that \bl{$P$} already
-holds for \bl{r$_1$} and \bl{r$_2$}.\bigskip
-\item \bl{$P$} holds for \bl{r$_1$ $\cdot$ r$_2$} under the assumption that \bl{$P$} already
-holds for \bl{r$_1$} and \bl{r$_2$}.
-\item \bl{$P$} holds for \bl{r$^*$} under the assumption that \bl{$P$} already
-holds for \bl{r}.
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Proofs about Rexp (3)\end{tabular}}
-
-Assume \bl{$P(r)$} is the property:
-
-\begin{center}
-\bl{nullable(r)} if and only if \bl{"" $\in$ $L$(r)}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Proofs about Strings\end{tabular}}
-
-If we want to prove something, say a property \bl{$P$(s)}, for all strings \bl{s} then \ldots\bigskip
-
-\begin{itemize}
-\item \bl{$P$} holds for the empty string, and\medskip
-\item \bl{$P$} holds for the string \bl{c::s} under the assumption that \bl{$P$}
-already holds for \bl{s}
-\end{itemize}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Proofs about Strings (2)\end{tabular}}
-
-Let \bl{Der c A} be the set defined as
-
-\begin{center}
-\bl{Der c A $\dn$ $\{$ s $|$ c::s $\in$ A$\}$ }
-\end{center}
-
-Assume that \bl{$L$(der c r) = Der c ($L$(r))}. Prove that
-
-\begin{center}
-\bl{matcher(r, s) if and only if s $\in$ $L$(r)}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Regular Languages\end{tabular}}
-
-A language (set of strings) is \alert{regular} iff there exists
-a regular expression that recognises all its strings.
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Automata\end{tabular}}
-
-A deterministic finite automaton consists of:
-
-\begin{itemize}
-\item a set of states
-\item one of these states is the start state
-\item some states are accepting states, and
-\item there is transition function\medskip
-
-\small
-which takes a state as argument and a character and produces a new state\smallskip\\
-this function might not always be defined
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides03.pdf has changed
--- a/slides03.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,386 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 03, King's College London, 10.~October 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (3)\\[3mm]
- \end{tabular}}
-
- %\begin{center}
- %\includegraphics[scale=0.3]{pics/ante1.jpg}\hspace{5mm}
- %\includegraphics[scale=0.31]{pics/ante2.jpg}\\
- %\footnotesize\textcolor{gray}{Antikythera automaton, 100 BC (Archimedes?)}
- %\end{center}
-
-\normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- & \alert{\bf (I have put a temporary link in there.)}\\
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Last Week\end{tabular}}
-
-Last week I showed you
-
-\begin{itemize}
-\item one simple-minded regular expression matcher (which however does not work in all cases), and\bigskip
-\item one which works provably in all cases
-
-\begin{center}
-\bl{matcher r s} \;\;if and only if \;\; \bl{s $\in$ $L$(r)}
-\end{center}
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Derivative of a Rexp\end{tabular}}
-
-\begin{center}
-\begin{tabular}{@ {}l@ {\hspace{2mm}}c@ {\hspace{2mm}}l@ {\hspace{-10mm}}l@ {}}
- \bl{der c ($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
- \bl{der c ($\epsilon$)} & \bl{$\dn$} & \bl{$\varnothing$} & \\
- \bl{der c (d)} & \bl{$\dn$} & \bl{if c $=$ d then $\epsilon$ else $\varnothing$} & \\
- \bl{der c (r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{(der c r$_1$) + (der c r$_2$)} & \\
- \bl{der c (r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{if nullable r$_1$}\\
- & & \bl{then ((der c r$_1$) $\cdot$ r$_2$) + (der c r$_2$)}\\
- & & \bl{else (der c r$_1$) $\cdot$ r$_2$}\\
- \bl{der c (r$^*$)} & \bl{$\dn$} & \bl{(der c r) $\cdot$ (r$^*$)}\\
- \end{tabular}
-\end{center}
-
-``the regular expression after \bl{c} has been recognised''
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-For this we defined the set \bl{Der c A} as
-
-\begin{center}
-\bl{Der c A $\dn$ $\{$ s $|$ c::s $\in$ A$\}$ }
-\end{center}
-
-which is called the semantic derivative of a set
-and proved
-
-\begin{center}
-\bl{$L$(der c r) $=$ Der c ($L$(r))}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}The Idea of the Algorithm\end{tabular}}
-
-If we want to recognise the string \bl{abc} with regular expression \bl{r}
-then\medskip
-
-\begin{enumerate}
-\item \bl{Der a ($L$(r))}\pause
-\item \bl{Der b (Der a ($L$(r)))}
-\item \bl{Der c (Der b (Der a ($L$(r))))}\pause
-\item finally we test whether the empty string is in set\pause\medskip
-\end{enumerate}
-
-The matching algorithm works similarly, just over regular expression than sets.
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Input: string \bl{abc} and regular expression \bl{r}
-
-\begin{enumerate}
-\item \bl{der a r}
-\item \bl{der b (der a r)}
-\item \bl{der c (der b (der a r))}\pause
-\item finally check whether the latter regular expression can match the empty string
-\end{enumerate}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-We need to prove
-
-\begin{center}
-\bl{$L$(der c r) $=$ Der c ($L$(r))}
-\end{center}
-
-by induction on the regular expression.
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Proofs about Rexp\end{tabular}}
-
-\begin{itemize}
-\item \bl{$P$} holds for \bl{$\varnothing$}, \bl{$\epsilon$} and \bl{c}\bigskip
-\item \bl{$P$} holds for \bl{r$_1$ + r$_2$} under the assumption that \bl{$P$} already
-holds for \bl{r$_1$} and \bl{r$_2$}.\bigskip
-\item \bl{$P$} holds for \bl{r$_1$ $\cdot$ r$_2$} under the assumption that \bl{$P$} already
-holds for \bl{r$_1$} and \bl{r$_2$}.
-\item \bl{$P$} holds for \bl{r$^*$} under the assumption that \bl{$P$} already
-holds for \bl{r}.
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Proofs about Natural Numbers\\ and Strings\end{tabular}}
-
-\begin{itemize}
-\item \bl{$P$} holds for \bl{$0$} and
-\item \bl{$P$} holds for \bl{$n + 1$} under the assumption that \bl{$P$} already
-holds for \bl{$n$}
-\end{itemize}\bigskip
-
-\begin{itemize}
-\item \bl{$P$} holds for \bl{\texttt{""}} and
-\item \bl{$P$} holds for \bl{$c\!::\!s$} under the assumption that \bl{$P$} already
-holds for \bl{$s$}
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
-
-\begin{center}
- \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
- \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
- & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
- & \bl{$\mid$} & \bl{c} & character\\
- & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
- & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
- & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
- \end{tabular}\bigskip\pause
- \end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Languages\end{tabular}}
-
-A \alert{language} is a set of strings.\bigskip
-
-A \alert{regular expression} specifies a set of strings or language.\bigskip
-
-A language is \alert{regular} iff there exists
-a regular expression that recognises all its strings.\bigskip\bigskip\pause
-
-\textcolor{gray}{not all languages are regular, e.g.~\bl{a$^n$b$^n$}.}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}}
-
-\begin{center}
- \begin{tabular}{@ {}rrl@ {\hspace{13mm}}l}
- \bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\
- & \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\
- & \bl{$\mid$} & \bl{c} & character\\
- & \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\
- & \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\
- & \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\
- \end{tabular}\bigskip
- \end{center}
-
-How about ranges \bl{[a-z]}, \bl{r$^\text{+}$} and \bl{!r}?
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Negation of Regular Expr's\end{tabular}}
-
-\begin{itemize}
-\item \bl{!r} \hspace{6mm} (everything that \bl{r} cannot recognise)\medskip
-\item \bl{$L$(!r) $\dn$ UNIV - $L$(r)}\medskip
-\item \bl{nullable (!r) $\dn$ not (nullable(r))}\medskip
-\item \bl{der\,c\,(!r) $\dn$ !(der\,c\,r)}
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Regular Exp's for Lexing\end{tabular}}
-
-Lexing separates strings into ``words'' / components.
-
-\begin{itemize}
-\item Identifiers (non-empty strings of letters or digits, starting with a letter)
-\item Numbers (non-empty sequences of digits omitting leading zeros)
-\item Keywords (else, if, while, \ldots)
-\item White space (a non-empty sequence of blanks, newlines and tabs)
-\item Comments
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Automata\end{tabular}}
-
-A deterministic finite automaton consists of:
-
-\begin{itemize}
-\item a set of states
-\item one of these states is the start state
-\item some states are accepting states, and
-\item there is transition function\medskip
-
-\small
-which takes a state as argument and a character and produces a new state\smallskip\\
-this function might not always be defined
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides04.pdf has changed
--- a/slides04.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,612 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 04, King's College London, 17.~October 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (4)\\[3mm]
- \end{tabular}}
-
- \normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Last Week\end{tabular}}
-
-Last week I showed you\bigskip
-
-\begin{itemize}
-\item a tokenizer taking a list of regular expressions\bigskip
-
-\item tokenization identifies lexeme in an input stream of characters (or string)
-and cathegorizes them into tokens
-
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Two Rules\end{tabular}}
-
-\begin{itemize}
-\item Longest match rule (maximal munch rule): The
-longest initial substring matched by any regular expression is taken
-as next token.\bigskip
-
-\item Rule priority:
-For a particular longest initial substring, the first regular
-expression that can match determines the token.
-
-\end{itemize}
-
-%\url{http://www.technologyreview.com/tr10/?year=2011}
-
-%finite deterministic automata/ nondeterministic automaton
-
-%\item problem with infix operations, for example i-12
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\mode<presentation>{
-\begin{frame}[t]
-
-\begin{center}
-\texttt{"if true then then 42 else +"}
-\end{center}
-
-
-\begin{tabular}{@{}l}
-KEYWORD: \\
-\hspace{5mm}\texttt{"if"}, \texttt{"then"}, \texttt{"else"},\\
-WHITESPACE:\\
-\hspace{5mm}\texttt{" "}, \texttt{"$\backslash$n"},\\
-IDENT:\\
-\hspace{5mm}LETTER $\cdot$ (LETTER + DIGIT + \texttt{"\_"})$^*$\\
-NUM:\\
-\hspace{5mm}(NONZERODIGIT $\cdot$ DIGIT$^*$) + \texttt{"0"}\\
-OP:\\
-\hspace{5mm}\texttt{"+"}\\
-COMMENT:\\
-\hspace{5mm}\texttt{"$\slash$*"} $\cdot$ (ALL$^*$ $\cdot$ \texttt{"*$\slash$"} $\cdot$ ALL$^*$) $\cdot$ \texttt{"*$\slash$"}
-\end{tabular}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-
-\begin{center}
-\texttt{"if true then then 42 else +"}
-\end{center}
-
-\only<1>{
-\small\begin{tabular}{l}
-KEYWORD(if),\\
-WHITESPACE,\\
-IDENT(true),\\
-WHITESPACE,\\
-KEYWORD(then),\\
-WHITESPACE,\\
-KEYWORD(then),\\
-WHITESPACE,\\
-NUM(42),\\
-WHITESPACE,\\
-KEYWORD(else),\\
-WHITESPACE,\\
-OP(+)
-\end{tabular}}
-
-\only<2>{
-\small\begin{tabular}{l}
-KEYWORD(if),\\
-IDENT(true),\\
-KEYWORD(then),\\
-KEYWORD(then),\\
-NUM(42),\\
-KEYWORD(else),\\
-OP(+)
-\end{tabular}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-
-There is one small problem with the tokenizer. How should we
-tokenize:
-
-\begin{center}
-\texttt{"x - 3"}
-\end{center}
-
-\begin{tabular}{@{}l}
-OP:\\
-\hspace{5mm}\texttt{"+"}, \texttt{"-"}\\
-NUM:\\
-\hspace{5mm}(NONZERODIGIT $\cdot$ DIGIT$^*$) + \texttt{"0"}\\
-NUMBER:\\
-\hspace{5mm}NUM + (\texttt{"-"} $\cdot$ NUM)\\
-\end{tabular}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Negation\end{tabular}}
-
-Assume you have an alphabet consisting of the letters \bl{a}, \bl{b} and \bl{c} only.
-Find a regular expression that matches all strings \emph{except} \bl{ab}, \bl{ac} and \bl{cba}.
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Deterministic Finite Automata\end{tabular}}
-
-A deterministic finite automaton consists of:
-
-\begin{itemize}
-\item a finite set of states
-\item one of these states is the start state
-\item some states are accepting states, and
-\item there is transition function\medskip
-
-\small
-which takes a state and a character as arguments and produces a new state\smallskip\\
-this function might not always be defined everywhere
-\end{itemize}
-
-\begin{center}
-\bl{$A(Q, q_0, F, \delta)$}
-\end{center}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\includegraphics[scale=0.7]{pics/ch3.jpg}
-\end{center}\pause
-
-\begin{itemize}
-\item start can be an accepting state
-\item it is possible that there is no accepting state
-\item all states might be accepting (but does not necessarily mean all strings are accepted)
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\includegraphics[scale=0.7]{pics/ch3.jpg}
-\end{center}
-
-for this automaton \bl{$\delta$} is the function\\
-
-\begin{center}
-\begin{tabular}{lll}
-\bl{(q$_0$, a) $\rightarrow$ q$_1$} & \bl{(q$_1$, a) $\rightarrow$ q$_4$} & \bl{(q$_4$, a) $\rightarrow$ q$_4$}\\
-\bl{(q$_0$, b) $\rightarrow$ q$_2$} & \bl{(q$_1$, b) $\rightarrow$ q$_2$} & \bl{(q$_4$, b) $\rightarrow$ q$_4$}\\
-\end{tabular}\ldots
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Accepting a String\end{tabular}}
-
-Given
-
-\begin{center}
-\bl{$A(Q, q_0, F, \delta)$}
-\end{center}
-
-you can define
-
-\begin{center}
-\begin{tabular}{l}
-\bl{$\hat{\delta}(q, \texttt{""}) = q$}\\
-\bl{$\hat{\delta}(q, c::s) = \hat{\delta}(\delta(q, c), s)$}\\
-\end{tabular}
-\end{center}\pause
-
-Whether a string \bl{$s$} is accepted by \bl{$A$}?
-
-\begin{center}
-\hspace{5mm}\bl{$\hat{\delta}(q_0, s) \in F$}
-\end{center}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Non-Deterministic\\[-1mm] Finite Automata\end{tabular}}
-
-A non-deterministic finite automaton consists again of:
-
-\begin{itemize}
-\item a finite set of states
-\item one of these states is the start state
-\item some states are accepting states, and
-\item there is transition \alert{relation}\medskip
-\end{itemize}
-
-
-\begin{center}
-\begin{tabular}{c}
-\bl{(q$_1$, a) $\rightarrow$ q$_2$}\\
-\bl{(q$_1$, a) $\rightarrow$ q$_3$}\\
-\end{tabular}
-\hspace{10mm}
-\begin{tabular}{c}
-\bl{(q$_1$, $\epsilon$) $\rightarrow$ q$_2$}\\
-\end{tabular}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\includegraphics[scale=0.7]{pics/ch5.jpg}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\begin{tabular}[b]{ll}
-\bl{$\varnothing$} & \includegraphics[scale=0.7]{pics/NULL.jpg}\\\\
-\bl{$\epsilon$} & \includegraphics[scale=0.7]{pics/epsilon.jpg}\\\\
-\bl{c} & \includegraphics[scale=0.7]{pics/char.jpg}\\
-\end{tabular}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\begin{tabular}[t]{ll}
-\bl{r$_1$ $\cdot$ r$_2$} & \includegraphics[scale=0.6]{pics/seq.jpg}\\\\
-\end{tabular}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\begin{tabular}[t]{ll}
-\bl{r$_1$ + r$_2$} & \includegraphics[scale=0.7]{pics/alt.jpg}\\\\
-\end{tabular}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\begin{tabular}[b]{ll}
-\bl{r$^*$} & \includegraphics[scale=0.7]{pics/star.jpg}\\
-\end{tabular}
-\end{center}\pause\bigskip
-
-Why can't we just have an epsilon transition from the accepting states to the starting state?
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Subset Construction\end{tabular}}
-
-
-\begin{textblock}{5}(1,2.5)
-\includegraphics[scale=0.5]{pics/ch5.jpg}
-\end{textblock}
-
-\begin{textblock}{11}(6.5,4.5)
-\begin{tabular}{r|cl}
-& a & b\\
-\hline
-$\varnothing$ \onslide<2>{\textcolor{white}{*}} & $\varnothing$ & $\varnothing$\\
-$\{0\}$ \onslide<2>{\textcolor{white}{*}} & $\{0,1,2\}$ & $\{2\}$\\
-$\{1\}$ \onslide<2>{\textcolor{white}{*}} &$\{1\}$ & $\varnothing$\\
-$\{2\}$ \onslide<2>{*} & $\varnothing$ &$\{2\}$\\
-$\{0,1\}$ \onslide<2>{\textcolor{white}{*}} &$\{0,1,2\}$ &$\{2\}$\\
-$\{0,2\}$ \onslide<2>{*}&$\{0,1,2\}$ &$\{2\}$\\
-$\{1,2\}$ \onslide<2>{*}& $\{1\}$ & $\{2\}$\\
-\onslide<2>{s:} $\{0,1,2\}$ \onslide<2>{*}&$\{0,1,2\}$ &$\{2\}$\\
-\end{tabular}
-\end{textblock}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Regular Languages\end{tabular}}
-
-A language is \alert{regular} iff there exists
-a regular expression that recognises all its strings.\bigskip\medskip
-
-or equivalently\bigskip\medskip
-
-A language is \alert{regular} iff there exists
-a deterministic finite automaton that recognises all its strings.\bigskip\pause
-
-Why is every finite set of strings a regular language?
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\includegraphics[scale=0.5]{pics/ch3.jpg}
-\end{center}
-
-\begin{center}
-\includegraphics[scale=0.5]{pics/ch4.jpg}\\
-minimal automaton
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{enumerate}
-\item Take all pairs \bl{(q, p)} with \bl{q $\not=$ p}
-\item Mark all pairs that accepting and non-accepting states
-\item For all unmarked pairs \bl{(q, p)} and all characters \bl{c} tests wether
-\begin{center}
-\bl{($\delta$(q,c), $\delta$(p,c))}
-\end{center}
-are marked. If yes, then also mark \bl{(q, p)}
-\item Repeat last step until no chance.
-\item All unmarked pairs can be merged.
-\end{enumerate}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Given the function
-
-\begin{center}
-\bl{\begin{tabular}{r@{\hspace{1mm}}c@{\hspace{1mm}}l}
-$rev(\varnothing)$ & $\dn$ & $\varnothing$\\
-$rev(\epsilon)$ & $\dn$ & $\epsilon$\\
-$rev(c)$ & $\dn$ & $c$\\
-$rev(r_1 + r_2)$ & $\dn$ & $rev(r_1) + rev(r_2)$\\
-$rev(r_1 \cdot r_2)$ & $\dn$ & $rev(r_2) \cdot rev(r_1)$\\
-$rev(r^*)$ & $\dn$ & $rev(r)^*$\\
-\end{tabular}}
-\end{center}
-
-
-and the set
-
-\begin{center}
-\bl{$Rev\,A \dn \{s^{-1} \;|\; s \in A\}$}
-\end{center}
-
-prove whether
-
-\begin{center}
-\bl{$L(rev(r)) = Rev (L(r))$}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{itemize}
-\item The star-case in our proof about the matcher needs the following lemma
-\begin{center}
-\bl{Der\,c\,A$^*$ $=$ (Der c A)\,@\, A$^*$}
-\end{center}
-\end{itemize}\bigskip\bigskip
-
-\begin{itemize}
-\item If \bl{\texttt{""} $\in$ A}, then\\ \bl{Der\,c\,(A @ B) $=$ (Der\,c\,A) @ B $\cup$ (Der\,c\,B)}\medskip
-\item If \bl{\texttt{""} $\not\in$ A}, then\\ \bl{Der\,c\,(A @ B) $=$ (Der\,c\,A) @ B}
-
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{itemize}
-\item Assuming you have the alphabet \bl{\{a, b, c\}}\bigskip
-\item Give a regular expression that can recognise all strings that have at least one \bl{b}.
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-``I hate coding. I do not want to look at code.''
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides05.pdf has changed
--- a/slides05.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,504 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 05, King's College London, 24.~October 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (5)\\[3mm]
- \end{tabular}}
-
- \normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Deterministic Finite Automata\end{tabular}}
-
-A DFA \bl{$A(Q, q_0, F, \delta)$} consists of:
-
-\begin{itemize}
-\item a finite set of states \bl{$Q$}
-\item one of these states is the start state \bl{$q_0$}
-\item some states are accepting states \bl{$F$}
-\item a transition function \bl{$\delta$}
-\end{itemize}\pause
-
-\onslide<2->{
-\begin{center}
-\begin{tabular}{l}
-\bl{$\hat{\delta}(q, \texttt{""}) = q$}\\
-\bl{$\hat{\delta}(q, c\!::\!s) = \hat{\delta}(\delta(q, c), s)$}
-\end{tabular}
-\end{center}}
-
-\only<3,4>{
-\begin{center}
-\begin{tikzpicture}[scale=2, line width=0.5mm]
- \node[state, initial] (q02) at ( 0,1) {$q_{0}$};
- \node[state] (q13) at ( 1,1) {$q_{1}$};
- \node[state, accepting] (q4) at ( 2,1) {$q_2$};
- \path[->] (q02) edge[bend left] node[above] {$a$} (q13)
- (q13) edge[bend left] node[below] {$b$} (q02)
- (q13) edge node[above] {$a$} (q4)
- (q02) edge [loop below] node {$b$} ()
- (q4) edge [loop right] node {$a, b$} ()
- ;
-\end{tikzpicture}
-\end{center}}%
-%
-\only<5>{
-\begin{center}
-\bl{$L(A) \dn \{ s \;|\; \hat{\delta}(q_0, s) \in F\}$}
-\end{center}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Non-Deterministic\\[-1mm] Finite Automata\end{tabular}}
-
-An NFA \bl{$A(Q, q_0, F, \delta)$} consists again of:
-
-\begin{itemize}
-\item a finite set of states
-\item one of these states is the start state
-\item some states are accepting states
-\item a transition \alert{relation}\medskip
-\end{itemize}
-
-
-\begin{center}
-\begin{tabular}{c}
-\bl{(q$_1$, a) $\rightarrow$ q$_2$}\\
-\bl{(q$_1$, a) $\rightarrow$ q$_3$}\\
-\end{tabular}
-\hspace{10mm}
-\begin{tabular}{c}
-\bl{(q$_1$, $\epsilon$) $\rightarrow$ q$_2$}\\
-\end{tabular}
-\end{center}\pause\medskip
-
-A string \bl{s} is accepted by an NFA, if there is a ``lucky'' sequence to an accepting state.
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Last Week\end{tabular}}
-
-Last week I showed you\bigskip
-
-\begin{itemize}
-\item an algorithm for automata minimisation
-
-\item an algorithm for transforming a regular expression into an NFA
-
-\item an algorithm for transforming an NFA into a DFA (subset construction)
-
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}This Week\end{tabular}}
-
-Go over the algorithms again, but with two new things and \ldots\medskip
-
-\begin{itemize}
-\item with the example: what is the regular expression that accepts every string, except those ending
-in \bl{aa}?\medskip
-
-\item Go over the proof for \bl{$L(rev(r)) = Rev(L(r))$}.\medskip
-
-\item Anything else so far.
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Proofs By Induction\end{tabular}}
-
-\begin{itemize}
-\item \bl{$P$} holds for \bl{$\varnothing$}, \bl{$\epsilon$} and \bl{c}\bigskip
-\item \bl{$P$} holds for \bl{r$_1$ + r$_2$} under the assumption that \bl{$P$} already
-holds for \bl{r$_1$} and \bl{r$_2$}.\bigskip
-\item \bl{$P$} holds for \bl{r$_1$ $\cdot$ r$_2$} under the assumption that \bl{$P$} already
-holds for \bl{r$_1$} and \bl{r$_2$}.
-\item \bl{$P$} holds for \bl{r$^*$} under the assumption that \bl{$P$} already
-holds for \bl{r}.
-\end{itemize}
-
-\begin{center}
-\bl{$P(r):\;\;L(rev(r)) = Rev(L(r))$}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-
-What is the regular expression that accepts every string, except those ending
-in \bl{aa}?\pause\bigskip
-
-\begin{center}
-\begin{tabular}{l}
-\bl{(a + b)$^*$ba}\\
-\bl{(a + b)$^*$ab}\\
-\bl{(a + b)$^*$bb}\\\pause
-\bl{a}\\
-\bl{\texttt{""}}
-\end{tabular}
-\end{center}\pause
-
-What are the strings to be avoided?\pause\medskip
-
-\begin{center}
-\bl{(a + b)$^*$aa}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-
-An NFA for \bl{(a + b)$^*$aa}
-
-\begin{center}
-\begin{tikzpicture}[scale=2, line width=0.5mm]
- \node[state, initial] (q0) at ( 0,1) {$q_0$};
- \node[state] (q1) at ( 1,1) {$q_1$};
- \node[state, accepting] (q2) at ( 2,1) {$q_2$};
- \path[->] (q0) edge node[above] {$a$} (q1)
- (q1) edge node[above] {$a$} (q2)
- (q0) edge [loop below] node {$a$} ()
- (q0) edge [loop above] node {$b$} ()
- ;
-\end{tikzpicture}
-\end{center}\pause
-
-Minimisation for DFAs\\
-Subset Construction for NFAs
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}DFA Minimisation\end{tabular}}
-
-
-\begin{enumerate}
-\item Take all pairs \bl{(q, p)} with \bl{q $\not=$ p}
-\item Mark all pairs that accepting and non-accepting states
-\item For all unmarked pairs \bl{(q, p)} and all characters \bl{c} tests wether
-\begin{center}
-\bl{($\delta$(q,c), $\delta$(p,c))}
-\end{center}
-are marked. If yes, then also mark \bl{(q, p)}.
-\item Repeat last step until nothing changed.
-\item All unmarked pairs can be merged.
-\end{enumerate}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Minimal DFA \only<1>{\bl{(a + b)$^*$aa}}\only<2->{\alert{not} \bl{(a + b)$^*$aa}}
-
-\begin{center}
-\begin{tikzpicture}[scale=2, line width=0.5mm]
- \only<1>{\node[state, initial] (q0) at ( 0,1) {$q_0$};}
- \only<2->{\node[state, initial,accepting] (q0) at ( 0,1) {$q_0$};}
- \only<1>{\node[state] (q1) at ( 1,1) {$q_1$};}
- \only<2->{\node[state,accepting] (q1) at ( 1,1) {$q_1$};}
- \only<1>{\node[state, accepting] (q2) at ( 2,1) {$q_2$};}
- \only<2->{\node[state] (q2) at ( 2,1) {$q_2$};}
- \path[->] (q0) edge[bend left] node[above] {$a$} (q1)
- (q1) edge[bend left] node[above] {$b$} (q0)
- (q2) edge[bend left=50] node[below] {$b$} (q0)
- (q1) edge node[above] {$a$} (q2)
- (q2) edge [loop right] node {$a$} ()
- (q0) edge [loop below] node {$b$} ()
- ;
-\end{tikzpicture}
-\end{center}
-
-\onslide<3>{How to get from a DFA to a regular expression?}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\begin{tikzpicture}[scale=2, line width=0.5mm]
- \only<1->{\node[state, initial] (q0) at ( 0,1) {$q_0$};}
- \only<1->{\node[state] (q1) at ( 1,1) {$q_1$};}
- \only<1->{\node[state] (q2) at ( 2,1) {$q_2$};}
- \path[->] (q0) edge[bend left] node[above] {$a$} (q1)
- (q1) edge[bend left] node[above] {$b$} (q0)
- (q2) edge[bend left=50] node[below] {$b$} (q0)
- (q1) edge node[above] {$a$} (q2)
- (q2) edge [loop right] node {$a$} ()
- (q0) edge [loop below] node {$b$} ()
- ;
-\end{tikzpicture}
-\end{center}\pause\bigskip
-
-\onslide<2->{
-\begin{center}
-\begin{tabular}{r@ {\hspace{2mm}}c@ {\hspace{2mm}}l}
-\bl{$q_0$} & \bl{$=$} & \bl{$2\, q_0 + 3 \,q_1 + 4\, q_2$}\\
-\bl{$q_1$} & \bl{$=$} & \bl{$2 \,q_0 + 3\, q_1 + 1\, q_2$}\\
-\bl{$q_2$} & \bl{$=$} & \bl{$1\, q_0 + 5\, q_1 + 2\, q_2$}\\
-
-\end{tabular}
-\end{center}
-}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\begin{tikzpicture}[scale=2, line width=0.5mm]
- \only<1->{\node[state, initial] (q0) at ( 0,1) {$q_0$};}
- \only<1->{\node[state] (q1) at ( 1,1) {$q_1$};}
- \only<1->{\node[state] (q2) at ( 2,1) {$q_2$};}
- \path[->] (q0) edge[bend left] node[above] {$a$} (q1)
- (q1) edge[bend left] node[above] {$b$} (q0)
- (q2) edge[bend left=50] node[below] {$b$} (q0)
- (q1) edge node[above] {$a$} (q2)
- (q2) edge [loop right] node {$a$} ()
- (q0) edge [loop below] node {$b$} ()
- ;
-\end{tikzpicture}
-\end{center}\bigskip
-
-\onslide<2->{
-\begin{center}
-\begin{tabular}{r@ {\hspace{2mm}}c@ {\hspace{2mm}}l}
-\bl{$q_0$} & \bl{$=$} & \bl{$\epsilon + q_0\,b + q_1\,b + q_2\,b$}\\
-\bl{$q_1$} & \bl{$=$} & \bl{$q_0\,a$}\\
-\bl{$q_2$} & \bl{$=$} & \bl{$q_1\,a + q_2\,a$}\\
-
-\end{tabular}
-\end{center}
-}
-
-\onslide<3->{
-Arden's Lemma:
-\begin{center}
-If \bl{$q = q\,r + s$}\; then\; \bl{$q = s\, r^*$}
-\end{center}
-}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Algorithms on Automata\end{tabular}}
-
-
-\begin{itemize}
-\item Reg $\rightarrow$ NFA: Thompson-McNaughton-Yamada method\medskip
-\item NFA $\rightarrow$ DFA: Subset Construction\medskip
-\item DFA $\rightarrow$ Reg: Brzozowski's Algebraic Method\medskip
-\item DFA minimisation: Hopcrofts Algorithm\medskip
-\item complement DFA
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\newcommand{\qq}{\mbox{\texttt{"}}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Grammars\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $F + (F \cdot \qq*\qq \cdot F) + (F \cdot \qq\backslash\qq \cdot F)$\\
-$F$ & $\rightarrow$ & $T + (T \cdot \qq\texttt{+}\qq \cdot T) + (T \cdot \qq\texttt{-}\qq \cdot T)$\\
-$T$ & $\rightarrow$ & $num + (\qq\texttt{(}\qq \cdot E \cdot \qq\texttt{)}\qq)$\\
-\end{tabular}}
-\end{center}
-
-\bl{$E$}, \bl{$F$} and \bl{$T$} are non-terminals\\
-\bl{$E$} is start symbol\\
-\bl{$num$}, \bl{(}, \bl{)}, \bl{+} \ldots are terminals\bigskip\\
-
-
-\bl{\texttt{(2*3)+(3+4)}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $F + (F \cdot \qq*\qq \cdot F) + (F \cdot \qq\backslash\qq \cdot F)$\\
-$F$ & $\rightarrow$ & $T + (T \cdot \qq\texttt{+}\qq \cdot T) + (T \cdot \qq\texttt{-}\qq \cdot T)$\\
-$T$ & $\rightarrow$ & $num + (\qq\texttt{(}\qq \cdot E \cdot \qq\texttt{)}\qq)$\\
-\end{tabular}}
-\end{center}
-
-\begin{center}
-\begin{tikzpicture}[level distance=8mm, blue]
- \node {E}
- child {node {F}
- child {node {T}
- child {node {\qq(\qq\,E\,\qq)\qq}
- child {node{F \qq*\qq{} F}
- child {node {T} child {node {2}}}
- child {node {T} child {node {3}}}
- }
- }
- }
- child {node {\qq+\qq}}
- child {node {T}
- child {node {\qq(\qq\,E\,\qq)\qq}
- child {node {F}
- child {node {T \qq+\qq{} T}
- child {node {3}}
- child {node {4}}
- }
- }}
- }};
-\end{tikzpicture}
-\end{center}
-
-\begin{textblock}{5}(1, 5)
-\bl{\texttt{(2*3)+(3+4)}}
-\end{textblock}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides06.pdf has changed
--- a/slides06.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,579 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usetikzlibrary{plotmarks}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 06, King's College London, 31.~October 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-
-% The data files, written on the first run.
-\begin{filecontents}{re-python.data}
-1 0.029
-5 0.029
-10 0.029
-15 0.032
-16 0.042
-17 0.042
-18 0.055
-19 0.084
-20 0.136
-21 0.248
-22 0.464
-23 0.899
-24 1.773
-25 3.505
-26 6.993
-27 14.503
-28 29.307
-#29 58.886
-\end{filecontents}
-
-\begin{filecontents}{re1.data}
-1 0.00179
-2 0.00011
-3 0.00014
-4 0.00026
-5 0.00050
-6 0.00095
-7 0.00190
-8 0.00287
-9 0.00779
-10 0.01399
-11 0.01894
-12 0.03666
-13 0.07994
-14 0.08944
-15 0.02377
-16 0.07392
-17 0.22798
-18 0.65310
-19 2.11360
-20 6.31606
-21 21.46013
-\end{filecontents}
-
-\begin{filecontents}{re2.data}
-1 0.00240
-2 0.00013
-3 0.00020
-4 0.00030
-5 0.00049
-6 0.00083
-7 0.00146
-8 0.00228
-9 0.00351
-10 0.00640
-11 0.01217
-12 0.02565
-13 0.01382
-14 0.02423
-15 0.05065
-16 0.06522
-17 0.02140
-18 0.05176
-19 0.18254
-20 0.51898
-21 1.39631
-22 2.69501
-23 8.07952
-\end{filecontents}
-
-\begin{filecontents}{re-internal.data}
-1 0.00069
-301 0.00700
-601 0.00297
-901 0.00470
-1201 0.01301
-1501 0.01175
-1801 0.01761
-2101 0.01787
-2401 0.02717
-2701 0.03932
-3001 0.03470
-3301 0.04349
-3601 0.05411
-3901 0.06181
-4201 0.07119
-4501 0.08578
-\end{filecontents}
-
-\begin{filecontents}{re3.data}
-1 0.001605
-501 0.131066
-1001 0.057885
-1501 0.136875
-2001 0.176238
-2501 0.254363
-3001 0.37262
-3501 0.500946
-4001 0.638384
-4501 0.816605
-5001 1.00491
-5501 1.232505
-6001 1.525672
-6501 1.757502
-7001 2.092784
-7501 2.429224
-8001 2.803037
-8501 3.463045
-9001 3.609
-9501 4.081504
-10001 4.54569
-\end{filecontents}
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (6)\\[3mm]
- \end{tabular}}
-
- \normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-``I hate coding. I do not want to look at code.''
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-``I am appalled. You do not show code anymore.''
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}ReDoS\end{tabular}}
-
-\begin{itemize}
-\item \alert{R}egular \alert{e}xpression \alert{D}enial \alert{o}f \alert{S}ervice\bigskip
-\item ``Regular Expressions Will Stab You in the Back''\bigskip
-\item Evil regular expressions\medskip
-\begin{itemize}
-\item \bl{$(a?\{n\})a\{n\}$}
-\item \bl{$(a^+)^+$}
-\item \bl{$([a-zA-Z]^+)^*$}
-\item \bl{$(a + aa)^+$}
-\item \bl{$(a + a?)^+$}
-\end{itemize}
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Regexp Matching\end{tabular}}
-
-Given a regular expression
-
-\begin{enumerate}
-\item you might convert it into a DFA (subset construction)
-\item you might try all possible paths in an NFA via backtracking
-\item you might try all paths in an NFA in parallel
-\item you might try to convert the DFA ``lazily''
-\end{enumerate}\bigskip
-
-Often No~2 is implemented (sometimes there are even good reasons for doing this).
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}\bl{$(a?\{n\})a\{n\}$} in Python\end{tabular}}
-
-\begin{tikzpicture}[y=.2cm, x=.3cm]
- %axis
- \draw (0,0) -- coordinate (x axis mid) (30,0);
- \draw (0,0) -- coordinate (y axis mid) (0,30);
- %ticks
- \foreach \x in {0,5,...,30}
- \draw (\x,1pt) -- (\x,-3pt)
- node[anchor=north] {\x};
- \foreach \y in {0,5,...,30}
- \draw (1pt,\y) -- (-3pt,\y)
- node[anchor=east] {\y};
- %labels
- \node[below=0.6cm] at (x axis mid) {\bl{a}s};
- \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
-
- %plots
- \draw[color=blue] plot[mark=*, mark options={fill=white}]
- file {re-python.data};
- \only<2->{
- \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
- file {re1.data};}
- \only<3->{
- \draw[color=green] plot[mark=square*, mark options={fill=white} ]
- file {re2.data};}
-
- %legend
- \begin{scope}[shift={(4,20)}]
- \draw[color=blue] (0,0) --
- plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Python};
- \only<2->{\draw[yshift=\baselineskip, color=red] (0,0) --
- plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala V1};}
- \only<3->{
- \draw[yshift=2\baselineskip, color=green] (0,0) --
- plot[mark=square*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala V2 with simplifications};}
- \end{scope}
-\end{tikzpicture}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-
-\begin{tikzpicture}[y=.7cm, x=.0009cm]
- %axis
- \draw (0,0) -- coordinate (x axis mid) (10000,0);
- \draw (0,0) -- coordinate (y axis mid) (0,6);
- %ticks
- \foreach \x in {0,2000,...,10000}
- \draw (\x,1pt) -- (\x,-3pt)
- node[anchor=north] {\x};
- \foreach \y in {0,1,...,6}
- \draw (1pt,\y) -- (-3pt,\y)
- node[anchor=east] {\y};
- %labels
- \node[below=0.6cm] at (x axis mid) {\bl{a}s};
- \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
-
- %plots
- \draw[color=blue] plot[mark=*, mark options={fill=white}]
- file {re-internal.data};
- \only<2->{
- \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
- file {re3.data};}
-
- %legend
- \begin{scope}[shift={(2000,4)}]
- \draw[color=blue] (0,0) --
- plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala Internal};
- \only<2->{
- \draw[yshift=\baselineskip, color=red] (0,0) --
- plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala V3 with explicit $\_\{\_\}$};}
- \end{scope}
-\end{tikzpicture}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-\newcommand{\qq}{\mbox{\texttt{"}}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Grammars\end{tabular}}
-
-A (context-free) grammar \bl{$G$} consists of
-
-\begin{itemize}
-\item a finite set of nonterminal symbols (upper case)
-\item a finite terminal symbols or tokens (lower case)
-\item a start symbol (which must be a nonterminal)
-\item a set of rules
-\begin{center}
-\bl{$A \rightarrow \text{rhs}$}
-\end{center}
-
-where \bl{rhs} are sequences involving terminals and nonterminals.\medskip\pause
-
-We can also allow rules
-\begin{center}
-\bl{$A \rightarrow \text{rhs}_1 | \text{rhs}_2 | \ldots$}
-\end{center}
-\end{itemize}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Palindromes\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$S$ & $\rightarrow$ & $\epsilon$ \\
-$S$ & $\rightarrow$ & $a\cdot S\cdot a$ \\
-$S$ & $\rightarrow$ & $b\cdot S\cdot b$ \\
-\end{tabular}}
-\end{center}\pause
-
-or
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$S$ & $\rightarrow$ & $\epsilon \;|\; a\cdot S\cdot a \;|\;b\cdot S\cdot b$ \\
-\end{tabular}}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Arithmetic Expressions\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $num\_token$ \\
-$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
-$E$ & $\rightarrow$ & $( \cdot E \cdot )$
-\end{tabular}}
-\end{center}\pause
-
-\bl{\texttt{1 + 2 * 3 + 4}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Parse Trees\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $F \;|\; F \cdot * \cdot F$\\
-$F$ & $\rightarrow$ & $T \;|\; T \cdot + \cdot T \;|\; T \cdot - \cdot T$\\
-$T$ & $\rightarrow$ & $num\_token \;|\; ( \cdot E \cdot )$\\
-\end{tabular}}
-\end{center}
-
-\begin{center}
-\begin{tikzpicture}[level distance=8mm, blue]
- \node {$E$}
- child {node {$F$}
- child {node {$T$}
- child {node {(\,$E$\,)}
- child {node{$F$ *{} $F$}
- child {node {$T$} child {node {2}}}
- child {node {$T$} child {node {3}}}
- }
- }
- }
- child {node {+}}
- child {node {$T$}
- child {node {(\,$E$\,)}
- child {node {$F$}
- child {node {$T$ +{} $T$}
- child {node {3}}
- child {node {4}}
- }
- }}
- }};
-\end{tikzpicture}
-\end{center}
-
-\begin{textblock}{5}(1, 6.5)
-\bl{\texttt{(2*3)+(3+4)}}
-\end{textblock}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Ambiguous Grammars\end{tabular}}
-
-A grammar is \alert{ambiguous} if there is a string that has at least parse trees.
-
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $num\_token$ \\
-$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
-$E$ & $\rightarrow$ & $( \cdot E \cdot )$
-\end{tabular}}
-\end{center}
-
-\bl{\texttt{1 + 2 * 3 + 4}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Chomsky Normal Form\end{tabular}}
-
-All rules must be of the form
-
-\begin{center}
-\bl{$A \rightarrow a$}
-\end{center}
-
-or
-
-\begin{center}
-\bl{$A \rightarrow B\cdot C$}
-\end{center}
-
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}CYK Algorithm\end{tabular}}
-
-
-\begin{center}
-\bl{\begin{tabular}{@ {}lcl}
-$S$ & $\rightarrow$ & $N\cdot P$ \\
-$P$ & $\rightarrow$ & $V\cdot N$ \\
-$N$ & $\rightarrow$ & $N\cdot N$ \\
-$N$ & $\rightarrow$ & $\texttt{students} \;|\; \texttt{Jeff} \;|\; \texttt{geometry} \;|\; \texttt{trains} $ \\
-$V$ & $\rightarrow$ & $\texttt{trains}$
-\end{tabular}}
-\end{center}
-
-\bl{\texttt{Jeff trains geometry students}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}CYK Algorithm\end{tabular}}
-
-
-\begin{itemize}
-\item runtime is \bl{$O(n^3)$}\bigskip
-\item grammars need to be transferred into CNF
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides07.pdf has changed
--- a/slides07.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,542 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usetikzlibrary{plotmarks}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 07, King's College London, 14.~November 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-
-% The data files, written on the first run.
-\begin{filecontents}{re-python.data}
-1 0.029
-5 0.029
-10 0.029
-15 0.032
-16 0.042
-17 0.042
-18 0.055
-19 0.084
-20 0.136
-21 0.248
-22 0.464
-23 0.899
-24 1.773
-25 3.505
-26 6.993
-27 14.503
-28 29.307
-#29 58.886
-\end{filecontents}
-
-\begin{filecontents}{re-ruby.data}
-1 0.00006
-2 0.00003
-3 0.00001
-4 0.00001
-5 0.00001
-6 0.00002
-7 0.00002
-8 0.00004
-9 0.00007
-10 0.00013
-11 0.00026
-12 0.00055
-13 0.00106
-14 0.00196
-15 0.00378
-16 0.00764
-17 0.01606
-18 0.03094
-19 0.06508
-20 0.12420
-21 0.25393
-22 0.51449
-23 1.02174
-24 2.05998
-25 4.22514
-26 8.42479
-27 16.88678
-28 34.79653
-\end{filecontents}
-
-\begin{filecontents}{re1.data}
-1 0.00179
-2 0.00011
-3 0.00014
-4 0.00026
-5 0.00050
-6 0.00095
-7 0.00190
-8 0.00287
-9 0.00779
-10 0.01399
-11 0.01894
-12 0.03666
-13 0.07994
-14 0.08944
-15 0.02377
-16 0.07392
-17 0.22798
-18 0.65310
-19 2.11360
-20 6.31606
-21 21.46013
-\end{filecontents}
-
-\begin{filecontents}{re2.data}
-1 0.00240
-2 0.00013
-3 0.00020
-4 0.00030
-5 0.00049
-6 0.00083
-7 0.00146
-8 0.00228
-9 0.00351
-10 0.00640
-11 0.01217
-12 0.02565
-13 0.01382
-14 0.02423
-15 0.05065
-16 0.06522
-17 0.02140
-18 0.05176
-19 0.18254
-20 0.51898
-21 1.39631
-22 2.69501
-23 8.07952
-\end{filecontents}
-
-\begin{filecontents}{re-internal.data}
-1 0.00069
-301 0.00700
-601 0.00297
-901 0.00470
-1201 0.01301
-1501 0.01175
-1801 0.01761
-2101 0.01787
-2401 0.02717
-2701 0.03932
-3001 0.03470
-3301 0.04349
-3601 0.05411
-3901 0.06181
-4201 0.07119
-4501 0.08578
-\end{filecontents}
-
-\begin{filecontents}{re3.data}
-1 0.001605
-501 0.131066
-1001 0.057885
-1501 0.136875
-2001 0.176238
-2501 0.254363
-3001 0.37262
-3501 0.500946
-4001 0.638384
-4501 0.816605
-5001 1.00491
-5501 1.232505
-6001 1.525672
-6501 1.757502
-7001 2.092784
-7501 2.429224
-8001 2.803037
-8501 3.463045
-9001 3.609
-9501 4.081504
-10001 4.54569
-\end{filecontents}
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (7)\\[3mm]
- \end{tabular}}
-
- \normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}\bl{$(a?\{n\})a\{n\}$}\end{tabular}}
-
-\mbox{}\\[-13mm]
-
-\begin{tikzpicture}[y=.2cm, x=.3cm]
- %axis
- \draw (0,0) -- coordinate (x axis mid) (30,0);
- \draw (0,0) -- coordinate (y axis mid) (0,30);
- %ticks
- \foreach \x in {0,5,...,30}
- \draw (\x,1pt) -- (\x,-3pt)
- node[anchor=north] {\x};
- \foreach \y in {0,5,...,30}
- \draw (1pt,\y) -- (-3pt,\y)
- node[anchor=east] {\y};
- %labels
- \node[below=0.6cm] at (x axis mid) {\bl{a}s};
- \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
-
- %plots
- \draw[color=blue] plot[mark=*, mark options={fill=white}]
- file {re-python.data};
- \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
- file {re1.data};
- \draw[color=green] plot[mark=square*, mark options={fill=white} ]
- file {re2.data};
- \draw[color=brown] plot[mark=pentagon*, mark options={fill=white} ]
- file {re-ruby.data};
-
- %legend
- \begin{scope}[shift={(4,20)}]
- \draw[color=blue] (0,0) --
- plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Python};
- \draw[yshift=-\baselineskip, color=brown] (0,0) --
- plot[mark=pentagon*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Ruby (Daniel Baldwin)};
- \draw[yshift=\baselineskip, color=red] (0,0) --
- plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala V1};
- \draw[yshift=2\baselineskip, color=green] (0,0) --
- plot[mark=square*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala V2 with simplifications};
- \end{scope}
-\end{tikzpicture}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-
-\begin{tikzpicture}[y=.7cm, x=.0009cm]
- %axis
- \draw (0,0) -- coordinate (x axis mid) (10000,0);
- \draw (0,0) -- coordinate (y axis mid) (0,6);
- %ticks
- \foreach \x in {0,2000,...,10000}
- \draw (\x,1pt) -- (\x,-3pt)
- node[anchor=north] {\x};
- \foreach \y in {0,1,...,6}
- \draw (1pt,\y) -- (-3pt,\y)
- node[anchor=east] {\y};
- %labels
- \node[below=0.6cm] at (x axis mid) {\bl{a}s};
- \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
-
- %plots
- \draw[color=blue] plot[mark=*, mark options={fill=white}]
- file {re-internal.data};
- \only<1->{
- \draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
- file {re3.data};}
-
- %legend
- \begin{scope}[shift={(2000,4)}]
- \draw[color=blue] (0,0) --
- plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala Internal};
- \only<1->{
- \draw[yshift=\baselineskip, color=red] (0,0) --
- plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small Scala V3 with explicit $\_\{\_\}$};}
- \end{scope}
-\end{tikzpicture}
-
-\begin{center}
-\begin{tabular}{@ {}l@ {\hspace{2mm}}c@ {\hspace{2mm}}l@ {\hspace{-10mm}}l@ {}}
- \\[-8mm]
- \bl{der c (r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{if nullable r$_1$}\\
- & & \bl{then ((der c r$_1$) $\cdot$ r$_2$) + (der c r$_2$)}\\
- & & \bl{else (der c r$_1$) $\cdot$ r$_2$}\\
- \bl{der c (r$\{n\}$)} & \bl{$\dn$} & \bl{if $n = 0$ then $\varnothing$}\\
- & & \bl{else (der c r) $\cdot$ r$\{n - 1\}$}
- \end{tabular}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-\newcommand{\qq}{\mbox{\texttt{"}}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}CFGs\end{tabular}}
-
-A \alert{context-free} grammar (CFG) \bl{$G$} consists of:
-
-\begin{itemize}
-\item a finite set of nonterminal symbols (upper case)
-\item a finite terminal symbols or tokens (lower case)
-\item a start symbol (which must be a nonterminal)
-\item a set of rules
-\begin{center}
-\bl{$A \rightarrow \text{rhs}$}
-\end{center}
-
-where \bl{rhs} are sequences involving terminals and nonterminals (can also be empty).\medskip\pause
-
-We can also allow rules
-\begin{center}
-\bl{$A \rightarrow \text{rhs}_1 | \text{rhs}_2 | \ldots$}
-\end{center}
-\end{itemize}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}A CFG Derivation\end{tabular}}
-
-\begin{enumerate}
-\item Begin with a string with only the start symbol \bl{$S$}\bigskip
-\item Replace any non-terminal \bl{$X$} in the string by the
right-hand side of some production \bl{$X \rightarrow \text{rhs}$}\bigskip
-\item Repeat 2 until there are no non-terminals
-\end{enumerate}
-
-\begin{center}
-\bl{$S \rightarrow \ldots \rightarrow \ldots \rightarrow \ldots \rightarrow \ldots $}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Language of a CFG\end{tabular}}
-
-Let \bl{$G$} be a context-free grammar with start symbol \bl{$S$}.
-Then the language \bl{$L(G)$} is:
-
-\begin{center}
-\bl{$\{c_1\ldots c_n \;|\; \forall i.\; c_i \in T \wedge S \rightarrow^* c_1\ldots c_n \}$}
-\end{center}\pause
-
-\begin{itemize}
-\item Terminals are so-called because there are no rules for replacing them
-\item Once generated, terminals are ``permanent''
-\item Terminals ought to be tokens of the language (at least in this course)
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Arithmetic Expressions\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $num\_token$ \\
-$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
-$E$ & $\rightarrow$ & $( \cdot E \cdot )$
-\end{tabular}}
-\end{center}\pause\bigskip
-
-A CFG is \alert{left-recursive} if it has a nonterminal \bl{$E$} such
-that \bl{$E \rightarrow^+ E\cdot \ldots$}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Parse Trees\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $F \;|\; F \cdot * \cdot F$\\
-$F$ & $\rightarrow$ & $T \;|\; T \cdot + \cdot T \;|\; T \cdot - \cdot T$\\
-$T$ & $\rightarrow$ & $num\_token \;|\; ( \cdot E \cdot )$\\
-\end{tabular}}
-\end{center}
-
-\begin{center}
-\begin{tikzpicture}[level distance=8mm, blue]
- \node {$E$}
- child {node {$F$}
- child {node {$T$}
- child {node {(\,$E$\,)}
- child {node{$F$ *{} $F$}
- child {node {$T$} child {node {2}}}
- child {node {$T$} child {node {3}}}
- }
- }
- }
- child {node {+}}
- child {node {$T$}
- child {node {(\,$E$\,)}
- child {node {$F$}
- child {node {$T$ +{} $T$}
- child {node {3}}
- child {node {4}}
- }
- }}
- }};
-\end{tikzpicture}
-\end{center}
-
-\begin{textblock}{5}(1, 6.5)
-\bl{\texttt{(2*3)+(3+4)}}
-\end{textblock}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Ambiguous Grammars\end{tabular}}
-
-A CFG is \alert{ambiguous} if there is a string that has at least parse trees.
-
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & $num\_token$ \\
-$E$ & $\rightarrow$ & $E \cdot + \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot - \cdot E$ \\
-$E$ & $\rightarrow$ & $E \cdot * \cdot E$ \\
-$E$ & $\rightarrow$ & $( \cdot E \cdot )$
-\end{tabular}}
-\end{center}
-
-\bl{\texttt{1 + 2 * 3 + 4}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Dangling Else\end{tabular}}
-
-Another ambiguous grammar:\bigskip
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$E$ & $\rightarrow$ & if $E$ then $E$\\
- & $|$ & if $E$ then $E$ else $E$ \\
- & $|$ & id
-\end{tabular}}
-\end{center}\bigskip
-
-\bl{\texttt{if a then if x then y else c}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides08.pdf has changed
--- a/slides08.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,676 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usetikzlibrary{plotmarks}
-\usepackage{graphicx}
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 08, King's College London, 21.~November 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-
-% The data files, written on the first run.
-\begin{filecontents}{s-grammar1.data}
-1 0.01152
-51 0.07973
-101 0.09726
-151 0.09320
-201 0.10010
-251 0.16997
-301 0.26662
-351 0.46118
-401 0.62516
-451 0.87247
-501 1.16334
-551 1.71152
-601 2.10958
-651 2.44360
-701 2.98488
-751 3.50326
-801 4.11036
-851 4.93394
-901 5.77465
-951 7.39123
-\end{filecontents}
-
-\begin{filecontents}{s-grammar2.data}
-1 0.01280
-2 0.00064
-3 0.00173
-4 0.00355
-5 0.00965
-6 0.02674
-7 0.06953
-8 0.11166
-9 0.18707
-10 0.09189
-11 0.12724
-12 0.24337
-13 0.59304
-14 1.53594
-15 4.01195
-16 10.73582
-17 29.51587
-#18 73.14163
-\end{filecontents}
-
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (8)\\[3mm]
- \end{tabular}}
-
- \normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- \end{tabular}
- \end{center}
-
-
-\end{frame}}
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Building a ``Web Browser''\end{tabular}}
-
-Using a lexer: assume the following regular expressions
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$SY\!M$ & $\dn$ & $(\text{a}..\text{zA}..\text{Z0}..\text{9}..)$\\
-$W\!O\!RD$ & $\dn$ & $SY\!M^+$\\
-$BT\!AG$ & $\dn$ & $<\!W\!O\!RD\!>$\\
-$ET\!AG$ & $\dn$ & $<\!/W\!O\!RD\!>$\\
-$W\!HIT\!E$ & $\dn$ & $\texttt{" "} + \texttt{"}\slash{}n\texttt{"}$\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Interpreting a List of Tokens\end{tabular}}
-
-\begin{itemize}
-\item the text should be formatted consistently up to a specified width, say 60 characters
-\item potential linebreaks are inserted by the formatter (not the input)
-\item repeated whitespaces are ``condensed'' to a single whitepace
-\item \bl{$<\!p\!>$} \bl{$<\!\slash{}p\!>$} start/end paragraph
-\item \bl{$<\!b\!>$} \bl{$<\!\slash{}b\!>$} start/end bold
-\item \bl{$<\!red\!>$} \bl{$<\!\slash{}red\!>$} start/end red (cyan, etc)
-
-
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Interpreting a List of Tokens\end{tabular}}
-
-The lexer cannot prevent errors like
-
-\begin{center}
-\bl{$<\!b\!>$} \ldots \bl{$<\!p\!>$} \ldots \bl{$<\!\slash{}b\!>$} \ldots \bl{$<\!\slash{}p\!>$}
-\end{center}
-
-or
-
-\begin{center}
-\bl{$<\!\slash{}b\!>$} \ldots \bl{$<\!b\!>$}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Parser Combinators\end{tabular}}
-
-Parser combinators: \bigskip
-
-\begin{minipage}{1.1\textwidth}
-\begin{center}
-\mbox{}\hspace{-12mm}\mbox{}$\underbrace{\text{list of tokens}}_{\text{input}}$ \bl{$\Rightarrow$}
-$\underbrace{\text{set of (parsed input, unparsed input)}}_{\text{output}}$
-\end{center}
-\end{minipage}\bigskip
-
-\begin{itemize}
-\item sequencing
-\item alternative
-\item semantic action
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Alternative parser (code \bl{$p\;||\;q$})\bigskip
-
-\begin{itemize}
-\item apply \bl{$p$} and also \bl{$q$}; then combine the outputs
-\end{itemize}
-
-\begin{center}
-\large \bl{$p(\text{input}) \cup q(\text{input})$}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Sequence parser (code \bl{$p\sim q$})\bigskip
-
-\begin{itemize}
-\item apply first \bl{$p$} producing a set of pairs
-\item then apply \bl{$q$} to the unparsed parts
-\item then combine the results:\\ \mbox{}\;\;((output$_1$, output$_2$), unparsed part)
-\end{itemize}
-
-\begin{center}
-\begin{tabular}{l}
-\large \bl{$\{((o_1, o_2), u_2) \;|\;$}\\[2mm]
-\large\mbox{}\hspace{15mm} \bl{$(o_1, u_1) \in p(\text{input}) \wedge$}\\[2mm]
-\large\mbox{}\hspace{15mm} \bl{$(o_2, u_2) \in q(u_1)\}$}
-\end{tabular}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Function parser (code \bl{$p \Longrightarrow f$})\bigskip
-
-\begin{itemize}
-\item apply \bl{$p$} producing a set of pairs
-\item then apply the function \bl{$f$} to each first component
-\end{itemize}
-
-\begin{center}
-\begin{tabular}{l}
-\large \bl{$\{(f(o_1), u_1) \;|\; (o_1, u_1) \in p(\text{input})\}$}
-\end{tabular}
-\end{center}\bigskip\bigskip\pause
-
-\bl{$f$} is the semantic action (``what to do with the parsed input'')
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Token parser:\bigskip
-
-\begin{itemize}
-\item if the input is
-
-\begin{center}
-\large \bl{$tok_1:: tok_2 :: \ldots :: tok_n$}
-\end{center}
-
-then return
-
-\begin{center}
-\large \bl{$\{(tok_1,\; tok_2 :: \ldots :: tok_n)\}$}
-\end{center}
-
-or
-
-\begin{center}
-\large \bl{$\{\}$}
-\end{center}
-
-if \bl{$tok_1$} is not the right token we are looking for
-\end{itemize}
-
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Number-Token parser:\bigskip
-
-\begin{itemize}
-\item if the input is
-
-\begin{center}
-\large \bl{$num\_tok(42):: tok_2 :: \ldots :: tok_n$}
-\end{center}
-
-then return
-
-\begin{center}
-\large \bl{$\{(42,\; tok_2 :: \ldots :: tok_n)\}$}
-\end{center}
-
-or
-
-\begin{center}
-\large \bl{$\{\}$}
-\end{center}
-
-if \bl{$tok_1$} is not the right token we are looking for
-\end{itemize}\pause
-
-\begin{center}
-list of tokens \bl{$\Rightarrow$} set of (\alert{int}, list of tokens)
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{itemize}
-\item if the input is
-
-\begin{center}
-\begin{tabular}{l}
-\large \bl{$num\_tok(42)::$}\\
-\hspace{7mm}\large \bl{$num\_tok(3) ::$}\\
-\hspace{14mm}\large \bl{$tok_3 :: \ldots :: tok_n$}
-\end{tabular}
-\end{center}
-
-and the parser is
-
-\begin{center}
-\bl{$ntp \sim ntp$}
-\end{center}
-
-the successful output will be
-
-\begin{center}
-\large \bl{$\{((42, 3),\; tok_2 :: \ldots :: tok_n)\}$}
-\end{center}\pause
-
-Now we can form
-\begin{center}
-\bl{$(ntp \sim ntp) \Longrightarrow f$}
-\end{center}
-
-where \bl{$f$} is the semantic action (``what to do with the pair'')
-
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Semantic Actions\end{tabular}}
-
-Addition
-
-\begin{center}
-\bl{$T \sim + \sim E \Longrightarrow \underbrace{f((x,y), z) \Rightarrow x + z}_{\text{semantic action}}$}
-\end{center}\pause
-
-Multiplication
-
-\begin{center}
-\bl{$F \sim * \sim T \Longrightarrow f((x,y), z) \Rightarrow x * z$}
-\end{center}\pause
-
-Parenthesis
-
-\begin{center}
-\bl{$\text{(} \sim E \sim \text{)} \Longrightarrow f((x,y), z) \Rightarrow y$}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Types of Parsers\end{tabular}}
-
-\begin{itemize}
-\item {\bf Sequencing}: if \bl{$p$} returns results of type \bl{$T$}, and \bl{$q$} results of type \bl{$S$},
-then \bl{$p \sim q$} returns results of type
-
-\begin{center}
-\bl{$T \times S$}
-\end{center}\pause
-
-\item {\bf Alternative}: if \bl{$p$} returns results of type \bl{$T$} then \bl{$q$} \alert{must} also have results of type \bl{$T$},
-and \bl{$p \;||\; q$} returns results of type
-
-\begin{center}
-\bl{$T$}
-\end{center}\pause
-
-\item {\bf Semantic Action}: if \bl{$p$} returns results of type \bl{$T$} and \bl{$f$} is a function from
-\bl{$T$} to \bl{$S$}, then
-\bl{$p \Longrightarrow f$} returns results of type
-
-\begin{center}
-\bl{$S$}
-\end{center}
-
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Input Types of Parsers\end{tabular}}
-
-\begin{itemize}
-\item input: \alert{list of tokens}
-\item output: set of (output\_type, \alert{list of tokens})
-\end{itemize}\bigskip\pause
-
-actually it can be any input type as long as it is a kind of sequence
-(for example a string)
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Scannerless Parsers\end{tabular}}
-
-\begin{itemize}
-\item input: \alert{string}
-\item output: set of (output\_type, \alert{string})
-\end{itemize}\bigskip
-
-but lexers are better when whitespaces or comments need to be filtered out
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Successful Parses\end{tabular}}
-
-\begin{itemize}
-\item input: string
-\item output: \alert{set of} (output\_type, string)
-\end{itemize}\bigskip
-
-a parse is successful whenever the input has been
-fully ``consumed'' (that is the second component is empty)
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-{\lstset{language=Scala}\fontsize{10}{12}\selectfont
-\texttt{\lstinputlisting{app7.scala}}}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-{\lstset{language=Scala}\fontsize{10}{12}\selectfont
-\texttt{\lstinputlisting{app7.scala}}}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-{\lstset{language=Scala}\fontsize{10}{12}\selectfont
-\texttt{\lstinputlisting{app8.scala}}}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Two Grammars\end{tabular}}
-
-Which languages are recognised by the following two grammars?
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$S$ & $\rightarrow$ & $1 \cdot S \cdot S$\\
- & $|$ & $\epsilon$
-\end{tabular}}
-\end{center}\bigskip
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$U$ & $\rightarrow$ & $1 \cdot U$\\
- & $|$ & $\epsilon$
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Ambiguous Grammars\end{tabular}}
-
-\mbox{}\\[-25mm]\mbox{}
-
-\begin{center}
-\begin{tikzpicture}[y=.2cm, x=.009cm]
- %axis
- \draw (0,0) -- coordinate (x axis mid) (1000,0);
- \draw (0,0) -- coordinate (y axis mid) (0,30);
- %ticks
- \foreach \x in {0, 20, 100, 200,...,1000}
- \draw (\x,1pt) -- (\x,-3pt)
- node[anchor=north] {\small \x};
- \foreach \y in {0,5,...,30}
- \draw (1pt,\y) -- (-3pt,\y)
- node[anchor=east] {\small\y};
- %labels
- \node[below=0.6cm] at (x axis mid) {\bl{1}s};
- \node[rotate=90, left=1.2cm] at (y axis mid) {secs};
-
- %plots
- \draw[color=blue] plot[mark=*, mark options={fill=white}]
- file {s-grammar1.data};
- \only<2->{\draw[color=red] plot[mark=triangle*, mark options={fill=white} ]
- file {s-grammar2.data};}
- %legend
- \begin{scope}[shift={(400,20)}]
- \draw[color=blue] (0,0) --
- plot[mark=*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small unambiguous};
- \only<2->{\draw[yshift=\baselineskip, color=red] (0,0) --
- plot[mark=triangle*, mark options={fill=white}] (0.25,0) -- (0.5,0)
- node[right]{\small ambiguous};}
- \end{scope}
-\end{tikzpicture}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}What about Left-Recursion?\end{tabular}}
-
-\begin{itemize}
-\item we record when we recursively called a parser\bigskip
-\item whenever the is a recursion, the parser must have consumed something --- so
-we can decrease the input string/list of token by one (at the end)
-\end{itemize}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}While-Language\end{tabular}}
-
-
-\begin{center}
-\bl{\begin{tabular}{@{}lcl@{}}
-$Stmt$ & $\rightarrow$ & $\text{skip}$\\
- & $|$ & $Id := AExp$\\
- & $|$ & $\text{if}\; B\!Exp \;\text{then}\; Block \;\text{else}\; Block$\\
- & $|$ & $\text{while}\; B\!Exp \;\text{do}\; Block$\medskip\\
-$Stmts$ & $\rightarrow$ & $Stmt \;\text{;}\; Stmts$\\
- & $|$ & $Stmt$\medskip\\
-$Block$ & $\rightarrow$ & $\{ Stmts \}$\\
- & $|$ & $Stmt$\medskip\\
-$AExp$ & $\rightarrow$ & \ldots\\
-$BExp$ & $\rightarrow$ & \ldots\\
-\end{tabular}}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}An Interpreter\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{l}
-$\{$\\
-\;\;$x := 5 \text{;}$\\
-\;\;$y := x * 3\text{;}$\\
-\;\;$y := x * 4\text{;}$\\
-\;\;$x := u * 3$\\
-$\}$
-\end{tabular}}
-\end{center}
-
-\begin{itemize}
-\item the interpreter has to record the value of \bl{$x$} before assigning a value to \bl{$y$}\pause
-\item \bl{\text{eval}(stmt, env)}
-\end{itemize}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides09.pdf has changed
--- a/slides09.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,853 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usetikzlibrary{plotmarks}
-\usepackage{graphicx}
-\usepackage{pgfplots}
-
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{while}{
- morekeywords={if,then,else,while,do,true,false,write},
- otherkeywords={=,!=,:=,<,>,;},
- sensitive=true,
- morecomment=[n]{/*}{*/},
-}
-
-
-\lstset{language=While,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 09, King's College London, 28.~November 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-
-% The data files, written on the first run.
-\begin{filecontents}{compiled.data}
-%1 0.234146
-%5000 0.227539
-%10000 0.280748
-50000 1.087897
-100000 3.713165
-250000 21.6624545
-500000 85.872613
-750000 203.6408015
-1000000 345.736574
-\end{filecontents}
-
-\begin{filecontents}{interpreted.data}
-%1 0.00503
-200 1.005863
-400 7.8296765
-500 15.43106
-600 27.2321885
-800 65.249271
-1000 135.4493445
-1200 232.134097
-1400 382.527227
-\end{filecontents}
-
-\begin{filecontents}{interpreted2.data}
-%1 0.00503
-200 1.005863
-400 7.8296765
-600 27.2321885
-800 65.249271
-1000 135.4493445
-1200 232.134097
-1400 382.527227
-\end{filecontents}
-
-\begin{filecontents}{compiled2.data}
-200 0.222058
-400 0.215204
-600 0.202031
-800 0.21986
-1000 0.205934
-1200 0.1981615
-1400 0.207116
-\end{filecontents}
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (9)\\[3mm]
- \end{tabular}}
-
- \normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- \end{tabular}
- \end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-Imagine the following situation: You talk to somebody
-and you find out that she/he has implemented a compiler.\smallskip
-
-What is your reaction? Check all that apply.\bigskip\pause
-
- \begin{itemize}
- \item[$\Box$] You think she/he is God
- \item[$\Box$] \"Uberhacker
- \item[$\Box$] superhuman
- \item[$\Box$] wizard
- \item[$\Box$] supremo
- \end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}While-Language\end{tabular}}
-
-
-\begin{center}
-\bl{\begin{tabular}{@{}lcl@{}}
-$Stmt$ & $\rightarrow$ & $\text{skip}$\\
- & $|$ & $Id := AExp$\\
- & $|$ & $\text{if}\; B\!Exp \;\text{then}\; Block \;\text{else}\; Block$\\
- & $|$ & $\text{while}\; B\!Exp \;\text{do}\; Block$\\
- & $|$ & $\alert{\text{write}\; Id}$\medskip\\
-$Stmts$ & $\rightarrow$ & $Stmt \;\text{;}\; Stmts$\\
- & $|$ & $Stmt$\medskip\\
-$Block$ & $\rightarrow$ & $\{ Stmts \}$\\
- & $|$ & $Stmt$\medskip\\
-$AExp$ & $\rightarrow$ & \ldots\\
-$BExp$ & $\rightarrow$ & \ldots\\
-\end{tabular}}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Fibonacci Numbers\end{tabular}}
-
-\mbox{}\\[-18mm]\mbox{}
-
-{\lstset{language=While}\fontsize{10}{12}\selectfont
-\texttt{\lstinputlisting{fib.while}}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Interpreter\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{@{}lcl@{}}
-$\text{eval}(n, E)$ & $\dn$ & $n$\\
-$\text{eval}(x, E)$ & $\dn$ & $E(x)$ \;\;\;\textcolor{black}{lookup \bl{$x$} in \bl{$E$}}\\
-$\text{eval}(a_1 + a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) + \text{eval}(a_2, E)$\\
-$\text{eval}(a_1 - a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) - \text{eval}(a_2, E)$\\
-$\text{eval}(a_1 * a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) * \text{eval}(a_2, E)$\bigskip\\
-$\text{eval}(a_1 = a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) = \text{eval}(a_2, E)$\\
-$\text{eval}(a_1\,!\!= a_2, E)$ & $\dn$ & $\neg(\text{eval}(a_1, E) = \text{eval}(a_2, E))$\\
-$\text{eval}(a_1 < a_2, E)$ & $\dn$ & $\text{eval}(a_1, E) < \text{eval}(a_2, E)$\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Interpreter (2)\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{@{}lcl@{}}
-$\text{eval}(\text{skip}, E)$ & $\dn$ & $E$\\
-$\text{eval}(x:=a, E)$ & $\dn$ & \bl{$E(x \mapsto \text{eval}(a, E))$}\\
-\multicolumn{3}{@{}l@{}}{$\text{eval}(\text{if}\;b\;\text{then}\;cs_1\;\text{else}\;cs_2 , E) \dn$}\\
-\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{if}\;\text{eval}(b,E)\;\text{then}\;
-\text{eval}(cs_1,E)$}\\
-\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\phantom{\text{if}\;\text{eval}(b,E)\;}\text{else}\;\text{eval}(cs_2,E)$}\\
-\multicolumn{3}{@{}l@{}}{$\text{eval}(\text{while}\;b\;\text{do}\;cs, E) \dn$}\\
-\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{if}\;\text{eval}(b,E)$}\\
-\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{then}\;
-\text{eval}(\text{while}\;b\;\text{do}\;cs, \text{eval}(cs,E))$}\\
-\multicolumn{3}{@{}l@{}}{\hspace{2cm}$\text{else}\; E$}\\
-$\text{eval}(\text{write}\; x, E)$ & $\dn$ & $\{\;\text{println}(E(x))\; ;\;E\;\}$\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Test Program\end{tabular}}
-
-\mbox{}\\[-18mm]\mbox{}
-
-{\lstset{language=While}\fontsize{10}{12}\selectfont
-\texttt{\lstinputlisting{loops.while}}}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Interpreted Code\end{tabular}}
-
-\begin{center}
-\begin{tikzpicture}
-\begin{axis}[axis x line=bottom, axis y line=left, xlabel=n, ylabel=secs, legend style=small]
-\addplot+[smooth] file {interpreted.data};
-\end{axis}
-\end{tikzpicture}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Java Virtual Machine\end{tabular}}
-
-\begin{itemize}
-\item introduced in 1995
-\item is a stack-based VM (like Postscript, CLR of .Net)
-\item contains a JIT compiler
-\item many languages take advantage of JVM's infrastructure (JRE)
-\item is garbage collected $\Rightarrow$ no buffer overflows
-\item some languages compiled to the JVM: Scala, Clojure\ldots
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
-
-{\Large\bl{1 + 2}}
-
-\begin{center}
-\bl{\begin{tabular}{l}
-ldc 1\\
-ldc 2\\
-iadd\\
-\end{tabular}}
-\end{center}\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
-
-{\Large\bl{1 + 2 + 3}}
-
-\begin{center}
-\bl{\begin{tabular}{l}
-ldc 1\\
-ldc 2\\
-iadd\\
-ldc 3\\
-iadd\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
-
-{\Large\bl{1 + (2 + 3)}}
-
-\begin{center}
-\bl{\begin{tabular}{l}
-ldc 1\\
-ldc 2\\
-ldc 3\\
-iadd\\
-iadd\\
-\end{tabular}}
-\end{center}\bigskip\pause
-\vfill
-
-\bl{dadd, fadd, ladd, \ldots}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{@{}lcl@{}}
-$\text{compile}(n)$ & $\dn$ & $\text{ldc}\;n$\\
-$\text{compile}(a_1 + a_2)$ & $\dn$\\
-\multicolumn{3}{l}{$\qquad\text{compile}(a_1) \;@\;\text{compile}(a_2)\;@\; \text{iadd}$}\smallskip\\
-$\text{compile}(a_1 - a_2)$ & $\dn$\\
-\multicolumn{3}{l}{$\qquad\text{compile}(a_1) \;@\; \text{compile}(a_2)\;@\; \text{isub}$}\smallskip\\
-$\text{compile}(a_1 * a_2)$ & $\dn$\\
-\multicolumn{3}{l}{$\qquad\text{compile}(a_1) \;@\; \text{compile}(a_2)\;@\; \text{imul}$}\smallskip\\
-\end{tabular}}
-\end{center}\pause
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
-
-{\Large\bl{1 + 2 * 3 + (4 - 3)}}
-
-\begin{center}
-\bl{\begin{tabular}{l}
-ldc 1\\
-ldc 2\\
-ldc 3\\
-imul\\
-ldc 4\\
-ldc 3\\
-isub\\
-iadd\\
-iadd\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Variables\end{tabular}}
-
-{\Large\bl{$x := 5 + y * 2$}}\bigskip\pause
-
-\begin{itemize}
-\item lookup: \bl{$\text{iload}\; index$}
-\item store: \bl{$\text{istore}\; index$}
-\end{itemize}\bigskip\pause
-
-while compilating we have to maintain a map between our identifiers and the
-Java bytecode indices
-
-\begin{center}
-\bl{$\text{compile}(a, E)$}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
-
-\begin{center}
-\bl{\begin{tabular}{@{}lcl@{}}
-$\text{compile}(n, E)$ & $\dn$ & $\text{ldc}\;n$\\
-$\text{compile}(a_1 + a_2, E)$ & $\dn$\\
-\multicolumn{3}{l}{$\qquad\text{compile}(a_1, E) \;@\;\text{compile}(a_2. E)\;@\; \text{iadd}$}\smallskip\\
-$\text{compile}(a_1 - a_2, E)$ & $\dn$\\
-\multicolumn{3}{l}{$\qquad\text{compile}(a_1, E) \;@\; \text{compile}(a_2, E)\;@\; \text{isub}$}\smallskip\\
-$\text{compile}(a_1 * a_2, E)$ & $\dn$\\
-\multicolumn{3}{l}{$\qquad\text{compile}(a_1, E) \;@\; \text{compile}(a_2, E)\;@\; \text{imul}$}\bigskip\\
-$\text{compile}(x, E)$ & $\dn$ & $\text{iload}\;E(x)$\\
-\end{tabular}}
-\end{center}\pause
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling Statements\end{tabular}}
-
-We return a list of instructions and an environment for the variables
-
-\begin{center}
-\bl{\begin{tabular}{@{}l@{\hspace{1mm}}c@{\hspace{1mm}}l@{}}
-$\text{compile}(\text{skip}, E)$ & $\dn$ & $(N\!il, E)$\bigskip\\
-$\text{compile}(x := a, E)$ & $\dn$\\
-\multicolumn{3}{l}{$(\text{compile}(a, E) \;@\;\text{istore}\;index, E(x\mapsto index))$}\\
-\end{tabular}}
-\end{center}\medskip
-
-where \bl{$index$} is \bl{$E(x)$} if it is already defined, or if it is not then the largest index not yet seen
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling AExps\end{tabular}}
-
-{\Large\bl{$x := x + 1$}}
-
-\begin{center}
-\bl{\begin{tabular}{l}
-iload $n_x$\\
-ldc 1\\
-iadd\\
-istore $n_x$\\
-\end{tabular}}
-\end{center}
-
-where \bl{$n_x$} is the index corresponding to the variable \bl{$x$}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling Ifs\end{tabular}}
-
-{\Large\bl{$\text{if}\;b\;\text{else}\;cs_1\;\text{then}\;cs_2$}}\bigskip\bigskip
-
-\onslide<2->{Case }\only<2>{{\bf True}:}\only<3>{{\bf False}:}
-
-\begin{center}
-\begin{tikzpicture}[node distance=2mm and 4mm,
- block/.style={rectangle, minimum size=1cm, draw=black, line width=1mm},
- point/.style={rectangle, inner sep=0mm, minimum size=0mm, fill=red},
- skip loop/.style={red, line width=1mm, to path={-- ++(0,-10mm) -| (\tikztotarget)}}]
-\node (A1) [point] {};
-\node (b) [block, right=of A1] {code of \bl{$b$}};
-\node (A2) [point, right=of b] {};
-\node (cs1) [block, right=of A2] {code of \bl{$cs_1$}};
-\node (A3) [point, right=of cs1] {};
-\node (cs2) [block, right=of A3] {code of \bl{$cs_2$}};
-\node (A4) [point, right=of cs2] {};
-
-\only<2>{
-\draw (A1) edge [->, red, line width=1mm] (b);
-\draw (b) edge [->, red, line width=1mm] (cs1);
-\draw (cs1) edge [->, red, line width=1mm] (A3);
-\draw (A3) edge [->,skip loop] (A4);
-\node [below=of cs2] {\raisebox{-5mm}{\small{}jump}};}
-\only<3>{
-\draw (A1) edge [->, red, line width=1mm] (b);
-\draw (b) edge [->, red, line width=1mm] (A2);
-\draw (A2) edge [skip loop] (A3);
-\draw (A3) edge [->, red, line width=1mm] (cs2);
-\draw (cs2) edge [->,red, line width=1mm] (A4);
-\node [below=of cs1] {\raisebox{-5mm}{\small{}conditional jump}};}
-\end{tikzpicture}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Conditional Jumps\end{tabular}}
-
-\begin{minipage}{1.1\textwidth}
-\begin{itemize}
-\item \bl{if\_icmpeq $label$} if two ints are equal, then jump\medskip
-\item \bl{if\_icmpne $label$} if two ints aren't equal, then jump\medskip
-\item \bl{if\_icmpge $label$} if one int is greater or equal then another, then jump
-\item[]\ldots
-\end{itemize}
-\end{minipage}\pause
-
-
-\begin{center}
-\bl{\begin{tabular}{l}
-$L_1$:\\
-\hspace{5mm}if\_icmpeq\;$L_2$\\
-\hspace{5mm}iload 1\\
-\hspace{5mm}ldc 1\\
-\hspace{5mm}iadd\\
-\hspace{5mm}if\_icmpeq\;$L_1$\\
-$L_2$:
-\end{tabular}}
-\end{center}
-
-\begin{textblock}{3.5}(11,12)
-\only<3>{labels must be unique}
-\end{textblock}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling BExps\end{tabular}}
-
-{\Large\bl{$a_1 = a_2$}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$\text{compile}(a_1 = a_2, E, lab)$ & $\dn$\\
-\multicolumn{3}{l}{$\quad\text{compile}(a_1, E) \;@\;\text{compile}(a_2, E)\;@\; \text{if\_icmpne}\;lab$}
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling Ifs\end{tabular}}
-
-{\Large\bl{if $b$ then $cs_1$ else $cs_2$}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$\text{compile}(\text{if}\;b\;\text{then}\; cs_1\;\text{else}\; cs_2, E)$ & $\dn$\\
-\multicolumn{3}{l}{$\quad l_{ifelse}\;$ \textcolor{black}{(fresh label)}}\\
-\multicolumn{3}{l}{$\quad l_{ifend}\;$ \textcolor{black}{(fresh label)}}\\
-\multicolumn{3}{l}{$\quad (is_1, E') = \text{compile}(cs_1, E)$}\\
-\multicolumn{3}{l}{$\quad (is_2, E'') = \text{compile}(cs_2, E')$}\\
-\multicolumn{3}{l}{$\quad(\text{compile}(b, E, l_{ifelse})$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\;is_1$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\; \text{goto}\;l_{ifend}$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\;l_{ifelse}:$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\;is_2$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\;l_{ifend}:, E'')$}\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling Whiles\end{tabular}}
-
-{\Large\bl{$\text{while}\;b\;\text{do}\;cs$}}\bigskip\bigskip
-
-\onslide<2->{Case }\only<2>{{\bf True}:}\only<3>{{\bf False}:}
-
-\begin{center}
-\begin{tikzpicture}[node distance=2mm and 4mm,
- block/.style={rectangle, minimum size=1cm, draw=black, line width=1mm},
- point/.style={rectangle, inner sep=0mm, minimum size=0mm, fill=red},
- skip loop/.style={red, line width=1mm, to path={-- ++(0,-10mm) -| (\tikztotarget)}}]
-\node (A0) [point, left=of A1] {};
-\node (A1) [point] {};
-\node (b) [block, right=of A1] {code of \bl{$b$}};
-\node (A2) [point, right=of b] {};
-\node (cs1) [block, right=of A2] {code of \bl{$cs$}};
-\node (A3) [point, right=of cs1] {};
-\node (A4) [point, right=of A3] {};
-
-\only<2>{
-\draw (A0) edge [->, red, line width=1mm] (b);
-\draw (b) edge [->, red, line width=1mm] (cs1);
-\draw (cs1) edge [->, red, line width=1mm] (A3);
-\draw (A3) edge [->,skip loop] (A1);}
-\only<3>{
-\draw (A0) edge [->, red, line width=1mm] (b);
-\draw (b) edge [->, red, line width=1mm] (A2);
-\draw (A2) edge [skip loop] (A3);
-\draw (A3) edge [->, red, line width=1mm] (A4);}
-\end{tikzpicture}
-\end{center}
-
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling Whiles\end{tabular}}
-
-{\Large\bl{while $b$ do $cs$}}
-
-\begin{center}
-\bl{\begin{tabular}{lcl}
-$\text{compile}(\text{while}\; b\; \text{do} \;cs, E)$ & $\dn$\\
-\multicolumn{3}{l}{$\quad l_{wbegin}\;$ \textcolor{black}{(fresh label)}}\\
-\multicolumn{3}{l}{$\quad l_{wend}\;$ \textcolor{black}{(fresh label)}}\\
-\multicolumn{3}{l}{$\quad (is, E') = \text{compile}(cs_1, E)$}\\
-\multicolumn{3}{l}{$\quad(l_{wbegin}:$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\;\text{compile}(b, E, l_{wend})$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\;is$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\; \text{goto}\;l_{wbegin}$}\\
-\multicolumn{3}{l}{$\quad\phantom{(}@\;l_{wend}:, E')$}\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiling Writes\end{tabular}}
-
-{\Large\bl{write $x$}}
-
-\begin{center}
-\small\bl{\begin{tabular}{l}
-.method public static write(I)V\hspace{1cm}\textcolor{black}{(library function)}\\
-\;\; .limit locals 5 \\
-\;\; .limit stack 5 \\
-\;\; iload 0 \\
-\;\; getstatic java/lang/System/out Ljava/io/PrintStream;\\
-\;\; swap \\
-\;\; invokevirtual java/io/PrintStream/println(I)V \\
-\;\; return \\
-.end method\bigskip\bigskip\\
-%
-\normalsize
-iload $E(x)$\\
-invokestatic write(I)V\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\begin{center}
-\small\bl{\begin{tabular}{l}
-.class public XXX.XXX\\
-.super java/lang/Object\\
-\\
-.method public <init>()V\\
-\;\; aload\_0\\
-\;\; invokenonvirtual java/lang/Object/<init>()V\\
- \;\; return\\
-.end method\\
-\\
-.method public static main([Ljava/lang/String;)V\\
-\;\; .limit locals 200\\
-\;\; .limit stack 200\\
-\\
- \textcolor{black}{(here comes the compiled code)}\\
-\\
-\;\; return\\
-.end method\\
-\end{tabular}}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{\begin{tabular}{c}Next Compiler Phases\end{tabular}}
-
-\begin{itemize}
-\item assembly $\Rightarrow$ byte code (class file)
-\item labels $\Rightarrow$ absolute or relative jumps\bigskip\bigskip
-\item \texttt{javap} is a disassembler for class files
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiled Code\end{tabular}}
-
-\begin{center}
-\begin{tikzpicture}
-\begin{axis}[axis x line=bottom, axis y line=left, xlabel=n, ylabel=secs, legend style=small]
-\addplot+[smooth] file {compiled.data};
-\end{axis}
-\end{tikzpicture}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiled vs.~Interpreted Code\end{tabular}}
-
-\begin{center}
-\begin{tikzpicture}
-\begin{loglogaxis}[axis x line=bottom, axis y line=left, xlabel=n, ylabel=secs, legend style=small]
-\addplot+[smooth] file {interpreted.data};
-\addplot+[smooth] file {compiled.data};
-\end{loglogaxis}
-\end{tikzpicture}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}Compiled vs.~Interpreted Code\end{tabular}}
-
-\begin{center}
-\begin{tikzpicture}
-\begin{axis}[axis x line=bottom, axis y line=left, ylabel=secs,
- xlabel=n,
- enlargelimits=0.05,
- ybar interval=0.7, legend style=small]
-\addplot file {interpreted2.data};
-\addplot file {compiled2.data};
-%\legend{interpreted, compiled}
-\end{axis}
-\end{tikzpicture}
-\end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[t]
-\frametitle{\begin{tabular}{c}What Next\end{tabular}}
-
-\begin{itemize}
-\item register spilling
-\item dead code removal
-\item loop optimisations
-\item instruction selection
-\item type checking
-\item concurrency
-\item fuzzy testing
-\item verification\bigskip\\
-
-\item GCC, LLVM, tracing JITs
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
Binary file slides10.pdf has changed
--- a/slides10.tex Sat Jun 15 09:11:11 2013 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,383 +0,0 @@
-\documentclass[dvipsnames,14pt,t]{beamer}
-\usepackage{beamerthemeplainculight}
-\usepackage[T1]{fontenc}
-\usepackage[latin1]{inputenc}
-\usepackage{mathpartir}
-\usepackage[absolute,overlay]{textpos}
-\usepackage{ifthen}
-\usepackage{tikz}
-\usepackage{pgf}
-\usepackage{calc}
-\usepackage{ulem}
-\usepackage{courier}
-\usepackage{listings}
-\renewcommand{\uline}[1]{#1}
-\usetikzlibrary{arrows}
-\usetikzlibrary{automata}
-\usetikzlibrary{shapes}
-\usetikzlibrary{shadows}
-\usetikzlibrary{positioning}
-\usetikzlibrary{calc}
-\usetikzlibrary{plotmarks}
-\usepackage{graphicx}
-\usepackage{pgfplots}
-
-
-\definecolor{javared}{rgb}{0.6,0,0} % for strings
-\definecolor{javagreen}{rgb}{0.25,0.5,0.35} % comments
-\definecolor{javapurple}{rgb}{0.5,0,0.35} % keywords
-\definecolor{javadocblue}{rgb}{0.25,0.35,0.75} % javadoc
-
-\lstset{language=Java,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{scala}{
- morekeywords={abstract,case,catch,class,def,%
- do,else,extends,false,final,finally,%
- for,if,implicit,import,match,mixin,%
- new,null,object,override,package,%
- private,protected,requires,return,sealed,%
- super,this,throw,trait,true,try,%
- type,val,var,while,with,yield},
- otherkeywords={=>,<-,<\%,<:,>:,\#,@},
- sensitive=true,
- morecomment=[l]{//},
- morecomment=[n]{/*}{*/},
- morestring=[b]",
- morestring=[b]',
- morestring=[b]"""
-}
-
-
-\lstset{language=Scala,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-\lstdefinelanguage{while}{
- morekeywords={if,then,else,while,do,true,false,write},
- otherkeywords={=,!=,:=,<,>,;},
- sensitive=true,
- morecomment=[n]{/*}{*/},
-}
-
-
-\lstset{language=While,
- basicstyle=\ttfamily,
- keywordstyle=\color{javapurple}\bfseries,
- stringstyle=\color{javagreen},
- commentstyle=\color{javagreen},
- morecomment=[s][\color{javadocblue}]{/**}{*/},
- numbers=left,
- numberstyle=\tiny\color{black},
- stepnumber=1,
- numbersep=10pt,
- tabsize=2,
- showspaces=false,
- showstringspaces=false}
-
-
-% beamer stuff
-\renewcommand{\slidecaption}{AFL 10, King's College London, 5.~December 2012}
-\newcommand{\bl}[1]{\textcolor{blue}{#1}}
-\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions
-
-
-% The data files, written on the first run.
-\begin{filecontents}{compiled.data}
-%1 0.234146
-%5000 0.227539
-%10000 0.280748
-50000 1.087897
-100000 3.713165
-250000 21.6624545
-500000 85.872613
-750000 203.6408015
-1000000 345.736574
-\end{filecontents}
-
-\begin{filecontents}{interpreted.data}
-%1 0.00503
-200 1.005863
-400 7.8296765
-500 15.43106
-600 27.2321885
-800 65.249271
-1000 135.4493445
-1200 232.134097
-1400 382.527227
-\end{filecontents}
-
-\begin{filecontents}{interpreted2.data}
-%1 0.00503
-200 1.005863
-400 7.8296765
-600 27.2321885
-800 65.249271
-1000 135.4493445
-1200 232.134097
-1400 382.527227
-\end{filecontents}
-
-\begin{filecontents}{compiled2.data}
-200 0.222058
-400 0.215204
-600 0.202031
-800 0.21986
-1000 0.205934
-1200 0.1981615
-1400 0.207116
-\end{filecontents}
-
-\begin{document}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}<1>[t]
-\frametitle{%
- \begin{tabular}{@ {}c@ {}}
- \\[-3mm]
- \LARGE Automata and \\[-2mm]
- \LARGE Formal Languages (10)\\[3mm]
- \end{tabular}}
-
- \normalsize
- \begin{center}
- \begin{tabular}{ll}
- Email: & christian.urban at kcl.ac.uk\\
- Of$\!$fice: & S1.27 (1st floor Strand Building)\\
- Slides: & KEATS (also home work is there)\\
- \end{tabular}
- \end{center}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\Large\bf
-There are more problems, than there are programs.\bigskip\bigskip\pause\\
-
-There must be a problem for which there is no program.
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Revision: Proofs}
-
-\begin{center}
-\includegraphics[scale=0.4]{river-stones.jpg}
-\end{center}
-
-\end{frame}}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Subsets}
-
-\Large
-\bl{$A \subseteq B$}\bigskip\bigskip\\
-
-\bl{$\forall e.\; e \in A \Rightarrow e \in B$}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Subsets}
-
-\Large
-\bl{$A \subseteq B$} and \bl{$B \subseteq A$}\bigskip
-
-then \bl{$A = B$}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Injective Function}
-
-\Large
-\bl{f} is an injective function iff \bigskip
-
-\bl{$\forall x y.\; f(x) = f(y) \Rightarrow x = y$}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Cardinality}
-
-\Large
-\bl{$|A|$} $\dn$ ``how many elements''\bigskip\\
-
-\bl{$A \subseteq B \Rightarrow |A| \leq |B|$}\bigskip\\\pause
-
-if there is an injective function \bl{$f: A \rightarrow B$} then \bl{$|A| \leq |B|$}\
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Natural Numbers}
-
-\Large
-\bl{$\mathbb{N}$} \bl{$\dn$} \bl{$\{0, 1, 2, 3, .......\}$}\bigskip\pause
-
-\bl{$A$} is \alert{countable} iff \bl{$|A| \leq |\mathbb{N}|$}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{First Question}
-
-\Large
-\bl{$|\mathbb{N} - \{0\}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\bigskip
-
-\normalsize
-\bl{$\geq$} or \bl{$\leq$} or \bl{$=$}
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\Large
-\bl{$|\mathbb{N} - \{0, 1\}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\pause
-
-\bl{$|\mathbb{N} - \mathbb{O}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\bigskip
-
-\normalsize
-\bl{$\mathbb{O}$} $\dn$ odd numbers\quad \bl{$\{1,3,5......\}$}\\ \pause
-\bl{$\mathbb{E}$} $\dn$ even numbers\quad \bl{$\{0,2,4......\}$}\\
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\Large
-\bl{$|\mathbb{N} \cup \mathbb{-N}| \;\;\;\alert{?}\;\;\; |\mathbb{N}| $}\bigskip\bigskip
-
-
-\normalsize
-\bl{$\mathbb{\phantom{-}N}$} $\dn$ positive numbers\quad \bl{$\{0,1,2,3,......\}$}\\
-\bl{$\mathbb{-N}$} $\dn$ negative numbers\quad \bl{$\{0,-1,-2,-3,......\}$}\\
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-
-\Large
-\bl{$A$} is \alert{countable} if there exists an injective \bl{$f : A \rightarrow \mathbb{N}$}\bigskip
-
-\bl{$A$} is \alert{uncountable} if there does not exist an injective \bl{$f : A \rightarrow \mathbb{N}$}\bigskip\bigskip
-
-
-countable: \bl{$|A| \leq |\mathbb{N}|$}\\
-uncountable: \bl{$|A| > |\mathbb{N}|$}\pause\bigskip
-
-
-Does there exist such an \bl{$A$} ?
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Halting Problem}
-
-\large
-Assume a program \bl{$H$} that decides for all programs \bl{$A$} and all
-input data \bl{$D$} whether\bigskip
-
-\begin{itemize}
-\item \bl{$H(A, D) \dn 1$} iff \bl{$A(D)$} terminates
-\item \bl{$H(A, D) \dn 0$} otherwise
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Halting Problem (2)}
-
-\large
-Given such a program \bl{$H$} define the following program \bl{$C$}:
-for all programs \bl{$A$}\bigskip
-
-\begin{itemize}
-\item \bl{$C(A) \dn 0$} iff \bl{$H(A, A) = 0$}
-\item \bl{$C(A) \dn$ loops} otherwise
-\end{itemize}
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\mode<presentation>{
-\begin{frame}[c]
-\frametitle{Contradiction}
-
-
-\bl{$H(C, C)$} is either \bl{$0$} or \bl{$1$}.
-
-\begin{itemize}
-\item \bl{$H(C, C) = 1$} $\stackrel{\text{def}\,H}{\Rightarrow}$ \bl{$C(C)\downarrow$} $\stackrel{\text{def}\,C}{\Rightarrow}$ \bl{$H(C, C)=0$}
-\item \bl{$H(C, C) = 0$} $\stackrel{\text{def}\,H}{\Rightarrow}$ \bl{$C(C)$} loops $\stackrel{\text{def}\,C}{\Rightarrow}$\\
-\hspace{7cm}\bl{$H(C, C)=1$}
-\end{itemize}
-
-Contradiction in both cases. So \bl{$H$} cannot exist.
-
-\end{frame}}
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\end{document}
-
-%%% Local Variables:
-%%% mode: latex
-%%% TeX-master: t
-%%% End:
-
