# HG changeset patch # User Christian Urban # Date 1380279502 -3600 # Node ID db6862f6bf6cd1b071524c91f8733c3f72f31e79 # Parent 95ee5cc5c05dfcf8db272111219009896df4dab6 added diff -r 95ee5cc5c05d -r db6862f6bf6c handouts/ho01.pdf Binary file handouts/ho01.pdf has changed diff -r 95ee5cc5c05d -r db6862f6bf6c handouts/ho01.tex --- a/handouts/ho01.tex Fri Sep 27 11:49:44 2013 +0100 +++ b/handouts/ho01.tex Fri Sep 27 11:58:22 2013 +0100 @@ -298,7 +298,7 @@ {\lstset{language=Scala}\texttt{\lstinputlisting{../progs/crawler2.scala}}} \caption{A version of the web-crawler which only follows links in ``my'' domain---since these are the ones I am interested in to fix. It uses the regular expression {\tt my\_urls} in Line~16. -The main change is in Line~26 where we test whether URL is in our domain or not.} +The main change is in Line~26 where there is a test whether URL is in ``my'' domain or not.} \end{figure} @@ -306,8 +306,7 @@ {\lstset{language=Scala}\texttt{\lstinputlisting{../progs/crawler3.scala}}} \caption{A small email harvester---whenever we download a web-page, we also check whether it contains any email addresses. For this we use the regular expression {\tt email\_pattern} in -Line~17. The main change is in Lines 33 and 34 where we print all email addresses -we can find in a page.} +Line~17. The main change is in Lines 33 and 34 where all email addresses that can be found in a page are printed.} \end{figure} \end{document}