author | Christian Urban <christian dot urban at kcl dot ac dot uk> |
Sun, 01 Dec 2013 09:58:41 +0000 | |
changeset 215 | 828303e8e4af |
parent 98 | 1f3d89fe9820 |
child 252 | e8ef8f38ca84 |
permissions | -rw-r--r-- |
95
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
1 |
\documentclass[dvipsnames,14pt,t,xelatex]{beamer} |
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
2 |
\usepackage{beamerthemeplaincu} |
215
828303e8e4af
updated slides
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
98
diff
changeset
|
3 |
\usepackage{fontenc,xltxtra,xunicode} |
95
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
4 |
\defaultfontfeatures{Mapping=tex-text} |
0 | 5 |
\usepackage[absolute,overlay]{textpos} |
6 |
\usepackage{ifthen} |
|
7 |
\usepackage{tikz} |
|
8 |
\usepackage{pgf} |
|
9 |
\usepackage{calc} |
|
10 |
\usepackage{ulem} |
|
11 |
\usepackage{listings} |
|
12 |
\renewcommand{\uline}[1]{#1} |
|
13 |
\usetikzlibrary{arrows} |
|
14 |
\usetikzlibrary{automata} |
|
15 |
\usetikzlibrary{shapes} |
|
16 |
\usetikzlibrary{shadows} |
|
17 |
\usetikzlibrary{positioning} |
|
18 |
\usetikzlibrary{calc} |
|
98
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
19 |
\usetikzlibrary{plotmarks} |
0 | 20 |
\usepackage{graphicx} |
98
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
21 |
\usepackage{pgfplots} |
215
828303e8e4af
updated slides
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
98
diff
changeset
|
22 |
\usepackage{../langs} |
828303e8e4af
updated slides
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
98
diff
changeset
|
23 |
\usepackage{../data} |
0 | 24 |
|
95
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
25 |
\makeatletter |
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
26 |
\lst@CCPutMacro\lst@ProcessOther {"2D}{\lst@ttfamily{-{}}{-{}}} |
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
27 |
\@empty\z@\@empty |
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
28 |
\makeatother |
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
29 |
|
0 | 30 |
% beamer stuff |
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
31 |
\renewcommand{\slidecaption}{AFL 01, King's College London, 25.~September 2013} |
0 | 32 |
|
33 |
||
34 |
\begin{document} |
|
35 |
||
36 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
37 |
\mode<presentation>{ |
|
38 |
\begin{frame}<1>[t] |
|
39 |
\frametitle{% |
|
40 |
\begin{tabular}{@ {}c@ {}} |
|
1 | 41 |
\\[-3mm] |
42 |
\LARGE Automata and \\[-2mm] |
|
43 |
\LARGE Formal Languages (1)\\[-3mm] |
|
0 | 44 |
\end{tabular}} |
45 |
||
46 |
\begin{center} |
|
1 | 47 |
\includegraphics[scale=0.3]{pics/ante1.jpg}\hspace{5mm} |
48 |
\includegraphics[scale=0.31]{pics/ante2.jpg}\\ |
|
49 |
\footnotesize\textcolor{gray}{Antikythera automaton, 100 BC (Archimedes?)} |
|
0 | 50 |
\end{center} |
51 |
||
52 |
\normalsize |
|
53 |
\begin{center} |
|
54 |
\begin{tabular}{ll} |
|
55 |
Email: & christian.urban at kcl.ac.uk\\ |
|
95
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
56 |
Office: & S1.27 (1st floor Strand Building)\\ |
0 | 57 |
Slides: & KEATS |
58 |
\end{tabular} |
|
59 |
\end{center} |
|
60 |
||
61 |
||
62 |
\end{frame}} |
|
63 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
64 |
||
65 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
66 |
\mode<presentation>{ |
|
67 |
\begin{frame}[c] |
|
68 |
||
1 | 69 |
\begin{textblock}{1}(2,5) |
0 | 70 |
\begin{tabular}{c} |
1 | 71 |
\includegraphics[scale=0.15]{pics/servers.png}\\[-2mm] |
72 |
\small Server |
|
0 | 73 |
\end{tabular} |
74 |
\end{textblock} |
|
75 |
||
1 | 76 |
\begin{textblock}{1}(5.6,4) |
77 |
\begin{tikzpicture}[scale=1.1] |
|
78 |
\draw[white] (0,1) node (X) {}; |
|
79 |
\draw[white] (2,1) node (Y) {}; |
|
80 |
\draw[white] (0,0) node (X1) {}; |
|
81 |
\draw[white] (2,0) node (Y1) {}; |
|
82 |
\draw[white] (0,-1) node (X2) {}; |
|
83 |
\draw[white] (2,-1) node (Y2) {}; |
|
84 |
\draw[red, <-, line width = 2mm] (X) -- (Y); |
|
85 |
\node [inner sep=5pt,label=above:\textcolor{black}{GET request}] at ($ (X)!.5!(Y) $) {}; |
|
86 |
\draw[red, ->, line width = 2mm] (X1) -- (Y1); |
|
87 |
\node [inner sep=5pt,label=above:\textcolor{black}{webpage}] at ($ (X1)!.5!(Y1) $) {}; |
|
88 |
\draw[red, <-, line width = 2mm] (X2) -- (Y2); |
|
89 |
\node [inner sep=7pt,label=above:\textcolor{black}{POST data}] at ($ (X2)!.5!(Y2) $) {}; |
|
0 | 90 |
\end{tikzpicture} |
91 |
\end{textblock} |
|
92 |
||
93 |
||
1 | 94 |
\begin{textblock}{1}(9,5.5) |
0 | 95 |
\begin{tabular}{c} |
1 | 96 |
\includegraphics[scale=0.15]{pics/laptop.png}\\[-2mm] |
97 |
\small Browser |
|
0 | 98 |
\end{tabular} |
99 |
\end{textblock} |
|
100 |
||
1 | 101 |
\only<2>{ |
102 |
\begin{textblock}{10}(2,13.5) |
|
0 | 103 |
\begin{itemize} |
1 | 104 |
\item programming languages, compilers |
0 | 105 |
\end{itemize} |
1 | 106 |
\end{textblock}} |
0 | 107 |
|
108 |
||
109 |
\end{frame}} |
|
110 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
111 |
||
112 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
113 |
\mode<presentation>{ |
|
114 |
\begin{frame}[c] |
|
1 | 115 |
|
116 |
transforming strings into structured data\\[10mm] |
|
0 | 117 |
|
1 | 118 |
{\LARGE\bf Lexing}\medskip\\ |
119 |
\hspace{5mm}(recognising ``words'')\\[6mm] |
|
0 | 120 |
|
1 | 121 |
{\LARGE\bf Parsing}\medskip\\ |
122 |
\hspace{5mm}(recognising ``sentences'') |
|
123 |
||
0 | 124 |
\end{frame}} |
1 | 125 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
126 |
||
0 | 127 |
|
128 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
129 |
\mode<presentation>{ |
|
130 |
\begin{frame}[c] |
|
131 |
||
1 | 132 |
The subject is quite old: |
0 | 133 |
|
134 |
\begin{itemize} |
|
1 | 135 |
\item Turing Machines, 1936 |
136 |
\item first compiler for COBOL, 1957 (Grace Hopper) |
|
137 |
\item but surprisingly research papers are still published now |
|
0 | 138 |
\end{itemize} |
139 |
||
1 | 140 |
\begin{flushright} |
141 |
\includegraphics[scale=0.3]{pics/hopper.jpg}\\ |
|
142 |
\footnotesize\textcolor{gray}{Grace Hopper} |
|
143 |
\end{flushright} |
|
144 |
||
145 |
{\footnotesize\textcolor{gray}{(she made it to David Letterman's Tonight Show, \url{http://www.youtube.com/watch?v=aZOxtURhfEU})}} |
|
0 | 146 |
|
1 | 147 |
\end{frame}} |
148 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
149 |
||
150 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
151 |
\mode<presentation>{ |
|
152 |
\begin{frame}[c] |
|
153 |
\frametitle{\begin{tabular}{c}This Course\end{tabular}} |
|
0 | 154 |
|
1 | 155 |
\begin{itemize} |
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
156 |
\item the ultimate goal is to implement a small compiler (a really small one for the JVM)\bigskip |
1 | 157 |
\end{itemize} |
158 |
||
159 |
Let's start with: |
|
160 |
||
161 |
\begin{itemize} |
|
162 |
\item a web-crawler |
|
163 |
\item an email harvester |
|
164 |
\item a web-scraper |
|
165 |
\end{itemize} |
|
166 |
||
98
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
167 |
\begin{textblock}{6}(10,7) |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
168 |
\begin{tikzpicture}[scale=0.38] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
169 |
\begin{axis}[axis x line=bottom, axis y line=left, ylabel=secs, |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
170 |
xlabel=n, |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
171 |
enlargelimits=0.05, |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
172 |
ybar interval=0.7, legend style=small] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
173 |
\addplot file {interpreted2.data}; |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
174 |
\addplot file {compiled2.data}; |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
175 |
%\legend{interpreted, compiled} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
176 |
\end{axis} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
177 |
\end{tikzpicture} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
178 |
\end{textblock} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
179 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
180 |
|
1 | 181 |
\end{frame}} |
182 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
0 | 183 |
|
2 | 184 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
185 |
\mode<presentation>{ |
|
3 | 186 |
\begin{frame}[t] |
13 | 187 |
\frametitle{\begin{tabular}{c}A Web-Crawler\end{tabular}} |
2 | 188 |
|
3 | 189 |
\mbox{}\\[10mm] |
190 |
||
2 | 191 |
\begin{enumerate} |
192 |
\item given an URL, read the corresponding webpage |
|
193 |
\item extract all links from it |
|
194 |
\item call the web-crawler again for all these links |
|
195 |
\end{enumerate} |
|
196 |
||
197 |
\end{frame}} |
|
198 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
199 |
||
200 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
201 |
\mode<presentation>{ |
|
3 | 202 |
\begin{frame}[t] |
13 | 203 |
\frametitle{\begin{tabular}{c}A Web-Crawler\end{tabular}} |
2 | 204 |
|
3 | 205 |
\mbox{}\\[10mm] |
206 |
||
207 |
||
2 | 208 |
\begin{enumerate} |
209 |
\item given an URL, read the corresponding webpage |
|
210 |
\item if not possible print, out a problem |
|
211 |
\item if possible, extract all links from it |
|
212 |
\item call the web-crawler again for all these links |
|
213 |
\end{enumerate}\bigskip\pause |
|
214 |
||
3 | 215 |
\small (we need a bound for the number of recursive calls) |
2 | 216 |
|
217 |
\small (the purpose is to check all links on my own webpage) |
|
218 |
\end{frame}} |
|
219 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
220 |
||
0 | 221 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
222 |
\mode<presentation>{ |
|
223 |
\begin{frame}[c] |
|
1 | 224 |
\frametitle{\begin{tabular}{c}Scala\end{tabular}} |
225 |
||
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
226 |
\small a simple Scala function for reading webpages\\[-3mm] |
0 | 227 |
|
98
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
228 |
\footnotesize |
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
229 |
{\lstset{language=Scala}\texttt{\lstinputlisting{../progs/app0.scala}}}\pause |
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
230 |
{\lstset{language=Scala}\texttt{\lstinline{get_page("""http://www.inf.kcl.ac.uk/staff/urbanc/""")}}}\pause\bigskip |
0 | 231 |
|
3 | 232 |
|
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
233 |
\small slightly more complicated for handling errors properly:\\[-3mm] |
2 | 234 |
|
98
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
235 |
\footnotesize |
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
236 |
{\lstset{language=Scala}\texttt{\lstinputlisting{../progs/app1.scala}}} |
1 | 237 |
|
0 | 238 |
|
239 |
\end{frame}} |
|
240 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
241 |
||
242 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
243 |
\mode<presentation>{ |
|
98
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
244 |
\begin{frame}[c] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
245 |
\frametitle{\begin{tabular}{c}Why Scala?\end{tabular}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
246 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
247 |
\begin{textblock}{6}(1,3) |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
248 |
\begin{tabular}{l} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
249 |
\mbox{}\hspace{-1mm}\includegraphics[scale=0.36]{pics/twitter.png}\\[-1mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
250 |
\includegraphics[scale=0.30]{pics/linked.png}\\ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
251 |
\includegraphics[scale=0.30]{pics/guardian.jpg}\\[-3mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
252 |
\mbox{}\hspace{-2mm}\includegraphics[scale=0.38]{pics/morgan.png}\\[-3mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
253 |
\includegraphics[scale=0.30]{pics/suisse.png}\\ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
254 |
\includegraphics[scale=0.20]{pics/edf.png}\\[-1mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
255 |
\includegraphics[scale=0.08]{pics/novell.png}\\[-1mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
256 |
\includegraphics[scale=0.30]{pics/foursquare.png}\\ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
257 |
\includegraphics[scale=0.30]{pics/hsbc.png}\\ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
258 |
{\large\bf ...} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
259 |
\end{tabular} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
260 |
\end{textblock} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
261 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
262 |
\only<2->{ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
263 |
\begin{textblock}{6}(6,3) |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
264 |
\includegraphics[scale=0.35]{pics/jobgraph.png}\\ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
265 |
\end{textblock}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
266 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
267 |
\only<3->{ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
268 |
\begin{textblock}{6}(7.3,9.2) |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
269 |
\begin{tabular}{l} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
270 |
\footnotesize 2013: 1$\%$\\[-2mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
271 |
\footnotesize 2014: 3$\%$\\[-2mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
272 |
\footnotesize 2015: 9$\%$\\[-2mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
273 |
\footnotesize 2016: 27$\%$\\[-2mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
274 |
\footnotesize 2017: 81$\%$\\[-2mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
275 |
\footnotesize 2018: 243$\%$ \raisebox{-1mm}{\includegraphics[scale=0.02]{pics/smiley.jpg}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
276 |
\end{tabular} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
277 |
\end{textblock}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
278 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
279 |
\only<3->{ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
280 |
\begin{textblock}{6}(6,9.5) |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
281 |
\footnotesize 5 yrs $\begin{cases}\mbox{}\\[1.4cm]\end{cases}$ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
282 |
\end{textblock}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
283 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
284 |
\only<4->{ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
285 |
\begin{textblock}{11}(5,14.1) |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
286 |
\textcolor{gray}{ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
287 |
\footnotesize {\bf in London today:} 1 Scala job for every 30 Java jobs;\\[-2mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
288 |
Scala programmers seem to get up to 20\% better salary} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
289 |
\end{textblock}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
290 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
291 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
292 |
\only<5->{ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
293 |
\begin{textblock}{1}(3,6) |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
294 |
\begin{tikzpicture} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
295 |
\draw (0,0) node[inner sep=2mm,fill=cream, ultra thick, draw=red, rounded corners=2mm] |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
296 |
{\normalsize\color{darkgray} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
297 |
\begin{minipage}{8.5cm}\raggedright\normalsize |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
298 |
Scala is a functional and object-oriented programming language; compiles to the JVM; does not |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
299 |
need null-pointer exceptions; a course on Coursera\\ |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
300 |
\mbox{}\hfill\textcolor{blue}{\url{http://www.scala-lang.org}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
301 |
\end{minipage}}; |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
302 |
\end{tikzpicture} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
303 |
\end{textblock}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
304 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
305 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
306 |
\end{frame}} |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
307 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
308 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
309 |
|
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
310 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
1f3d89fe9820
updated
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
97
diff
changeset
|
311 |
\mode<presentation>{ |
3 | 312 |
\begin{frame}[t] |
313 |
\frametitle{\begin{tabular}{c}A Regular Expression\end{tabular}} |
|
314 |
||
315 |
\begin{itemize} |
|
316 |
\item \ldots{} is a pattern or template for specifying strings |
|
317 |
\end{itemize}\bigskip |
|
318 |
||
319 |
\begin{center} |
|
320 |
\only<1>{{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf |
|
321 |
\texttt{"https?://[$\hat{\hspace{2mm}}$"]*"}}}% |
|
322 |
\only<2>{{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf |
|
323 |
\texttt{"""\textbackslash{}"https?://[$\hat{\hspace{2mm}}$\textbackslash{}"]*\textbackslash{}"""".r}}} |
|
324 |
\end{center}\bigskip\bigskip |
|
325 |
||
326 |
matches for example\\ |
|
327 |
\;{\lstset{language=Scala}\fontsize{12}{14}\selectfont\bf |
|
328 |
\texttt{"http://www.foobar.com"}}\\ |
|
329 |
\;{\lstset{language=Scala}\fontsize{12}{14}\selectfont\bf |
|
330 |
\texttt{"https://www.tls.org"}}\\ |
|
331 |
||
332 |
\end{frame}} |
|
333 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
334 |
||
335 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
336 |
\mode<presentation>{ |
|
0 | 337 |
\begin{frame}[c] |
338 |
||
3 | 339 |
{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf |
340 |
\texttt{rexp.findAllIn(string)}}\medskip |
|
341 |
||
342 |
returns a list of all (sub)strings that match the regular expression\bigskip\bigskip |
|
343 |
||
344 |
{\lstset{language=Scala}\fontsize{18}{19}\selectfont\bf |
|
345 |
\texttt{rexp.findFirstIn(string)}}\medskip |
|
346 |
||
347 |
returns either {\bf\texttt{None}} if no (sub)string matches |
|
348 |
or {\bf\texttt{Some(s)}} with the first (sub)string |
|
0 | 349 |
|
350 |
\end{frame}} |
|
351 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
352 |
||
353 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
354 |
\mode<presentation>{ |
|
355 |
\begin{frame}[c] |
|
356 |
||
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
357 |
\small |
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
358 |
{\lstset{language=Scala}\texttt{\lstinputlisting{../progs/app2.scala}}}\medskip |
0 | 359 |
|
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
360 |
{\lstset{language=Scala}\texttt{crawl(some\_start\_URL, 2)}}\ |
0 | 361 |
|
362 |
\end{frame}} |
|
363 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
364 |
||
365 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
366 |
\mode<presentation>{ |
|
3 | 367 |
\begin{frame}[c] |
0 | 368 |
|
3 | 369 |
\footnotesize |
370 |
a version that only ``crawls'' links in my domain: |
|
0 | 371 |
|
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
372 |
\small |
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
373 |
{\lstset{language=Scala}\texttt{\lstinputlisting{../progs/app3.scala}}} |
0 | 374 |
|
375 |
||
376 |
\end{frame}} |
|
377 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
378 |
||
379 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
380 |
\mode<presentation>{ |
|
381 |
\begin{frame}[c] |
|
3 | 382 |
|
383 |
\footnotesize |
|
384 |
a little email ``harvester'': |
|
385 |
||
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
386 |
\small |
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
387 |
{\lstset{language=Scala}\texttt{\lstinputlisting{../progs/app4.scala}}}\bigskip |
3 | 388 |
|
389 |
\tiny |
|
390 |
\textcolor{gray}{\url{http://net.tutsplus.com/tutorials/other/8-regular-expressions-you-should-know/}} |
|
391 |
||
392 |
\end{frame}} |
|
393 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
394 |
||
395 |
\newcommand{\bl}[1]{\textcolor{blue}{#1}} |
|
396 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
397 |
\mode<presentation>{ |
|
14 | 398 |
\begin{frame}[t] |
3 | 399 |
\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}} |
0 | 400 |
|
14 | 401 |
Their inductive definition:\medskip |
402 |
||
403 |
\begin{textblock}{6}(2,5) |
|
3 | 404 |
\begin{tabular}{@ {}rrl@ {\hspace{13mm}}l} |
405 |
\bl{r} & \bl{$::=$} & \bl{$\varnothing$} & null\\ |
|
5 | 406 |
& \bl{$\mid$} & \bl{$\epsilon$} & empty string / "" / []\\ |
3 | 407 |
& \bl{$\mid$} & \bl{c} & character\\ |
408 |
& \bl{$\mid$} & \bl{r$_1$ $\cdot$ r$_2$} & sequence\\ |
|
409 |
& \bl{$\mid$} & \bl{r$_1$ + r$_2$} & alternative / choice\\ |
|
410 |
& \bl{$\mid$} & \bl{r$^*$} & star (zero or more)\\ |
|
411 |
\end{tabular} |
|
412 |
\end{textblock} |
|
413 |
||
414 |
\end{frame}} |
|
415 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
416 |
||
417 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
418 |
\mode<presentation>{ |
|
419 |
\begin{frame}[t] |
|
420 |
\frametitle{\begin{tabular}{c}Regular Expressions\end{tabular}} |
|
421 |
||
14 | 422 |
\small |
423 |
In Scala: |
|
424 |
||
425 |
||
3 | 426 |
{\lstset{language=Scala}\fontsize{8}{10}\selectfont |
95
dbe49327b6c5
added new stuff
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
93
diff
changeset
|
427 |
\texttt{\lstinputlisting{../progs/app51.scala}}} |
0 | 428 |
|
429 |
||
430 |
\end{frame}} |
|
431 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
432 |
||
3 | 433 |
\newcommand{\dn}{\stackrel{\mbox{\scriptsize def}}{=}}% for definitions |
0 | 434 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
435 |
\mode<presentation>{ |
|
436 |
\begin{frame}[c] |
|
3 | 437 |
\frametitle{\begin{tabular}{c}The Meaning of a\\[-2mm] Regular Expression\end{tabular}} |
0 | 438 |
|
4 | 439 |
\begin{textblock}{15}(1,4) |
3 | 440 |
\begin{tabular}{@ {}rcl} |
441 |
\bl{$L$($\varnothing$)} & \bl{$\dn$} & \bl{$\varnothing$}\\ |
|
442 |
\bl{$L$($\epsilon$)} & \bl{$\dn$} & \bl{$\{$""$\}$}\\ |
|
443 |
\bl{$L$(c)} & \bl{$\dn$} & \bl{$\{$"c"$\}$}\\ |
|
444 |
\bl{$L$(r$_1$ + r$_2$)} & \bl{$\dn$} & \bl{$L$(r$_1$) $\cup$ $L$(r$_2$)}\\ |
|
4 | 445 |
\bl{$L$(r$_1$ $\cdot$ r$_2$)} & \bl{$\dn$} & \bl{$\{$ s$_1$ @ s$_2$ $|$ s$_1$ $\in$ $L$(r$_1$) $\wedge$ s$_2$ $\in$ |
446 |
$L$(r$_2$) $\}$}\\ |
|
5 | 447 |
\bl{$L$(r$^*$)} & \bl{$\dn$} & \onslide<4->{\bl{$\bigcup_{n \ge 0}$ $L$(r)$^n$}}\\ |
4 | 448 |
\end{tabular}\bigskip |
3 | 449 |
|
4 | 450 |
\onslide<2->{ |
451 |
\hspace{5mm}\bl{$L$(r)$^0$ $\;\dn\;$ $\{$""$\}$}\\ |
|
5 | 452 |
\bl{$L$(r)$^{n+1}$ $\;\dn\;$ $L$(r) @ $L$(r)$^n$}\hspace{9mm}\onslide<3->{\small\textcolor{gray}{(append on sets)}\\ |
453 |
\small\hspace{5cm}\textcolor{gray}{$\{$ s$_1$ @ s$_2$ $|$ s$_1$ $\in$ $L$(r) $\wedge$ s$_2$ $\in$ |
|
454 |
$L$(r)$^n$ $\}$}} |
|
4 | 455 |
} |
456 |
\end{textblock} |
|
457 |
||
0 | 458 |
\end{frame}} |
459 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
460 |
||
5 | 461 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
462 |
\mode<presentation>{ |
|
463 |
\begin{frame}[c] |
|
8 | 464 |
\frametitle{\begin{tabular}{c}The Meaning of Matching\end{tabular}} |
5 | 465 |
|
466 |
\large |
|
467 |
a regular expression \bl{r} matches a string \bl{s} is defined as |
|
468 |
||
469 |
\begin{center} |
|
470 |
\bl{s $\in$ $L$(r)}\\ |
|
471 |
\end{center} |
|
472 |
||
473 |
\end{frame}} |
|
474 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
475 |
||
3 | 476 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
477 |
\mode<presentation>{ |
|
478 |
\begin{frame}[c] |
|
479 |
\frametitle{\begin{tabular}{c}This Course\end{tabular}} |
|
480 |
||
7 | 481 |
We will have a look at: |
3 | 482 |
|
483 |
\begin{itemize} |
|
7 | 484 |
\item regular expressions / regular expression matching |
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
485 |
\item derivatives |
3 | 486 |
\item automata |
487 |
\item parsing |
|
488 |
\item grammars |
|
97
60a3ba90dd53
added
Christian Urban <christian dot urban at kcl dot ac dot uk>
parents:
95
diff
changeset
|
489 |
\item a small interpreter / compiler |
3 | 490 |
\end{itemize} |
491 |
||
492 |
\end{frame}} |
|
493 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
494 |
||
0 | 495 |
|
496 |
||
497 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
498 |
\mode<presentation>{ |
|
499 |
\begin{frame}[c] |
|
1 | 500 |
\frametitle{\begin{tabular}{c}Exam\end{tabular}} |
0 | 501 |
|
502 |
\begin{itemize} |
|
7 | 503 |
\item The question ``Is this relevant for the exam?'' is not appreciated!\bigskip\\ |
0 | 504 |
|
14 | 505 |
Whatever is in the homework sheets (and is not marked ``optional'') is relevant for the |
506 |
exam.\\ No code needs to be written in the exam. |
|
0 | 507 |
\end{itemize} |
508 |
||
509 |
\end{frame}} |
|
510 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
|
511 |
||
512 |
||
513 |
\end{document} |
|
514 |
||
515 |
%%% Local Variables: |
|
516 |
%%% mode: latex |
|
517 |
%%% TeX-master: t |
|
518 |
%%% End: |
|
519 |