Author: gsingers
Date: Fri Oct 31 10:27:58 2008
New Revision: 709492
URL: http://svn.apache.org/viewvc?rev=709492&view=rev
Log:
download wikipedia sample, same as Lucene contrib/benchmark
Modified:
lucene/mahout/trunk/examples/build.xml
Modified: lucene/mahout/trunk/examples/build.xml
URL:
http://svn.apache.org/viewvc/lucene/mahout/trunk/examples/build.xml?rev=709492&r1=709491&r2=709492&view=diff
==============================================================================
--- lucene/mahout/trunk/examples/build.xml (original)
+++ lucene/mahout/trunk/examples/build.xml Fri Oct 31 10:27:58 2008
@@ -267,9 +267,27 @@
<target name="check-files">
<available file="temp/20news-18828.tar.gz" property="20news-18828.exists"/>
<available file="${working.dir}/20news-18828"
property="20news-18828.expanded"/>
-
+ <available file="temp/enwiki-20070527-pages-articles.xml.bz2"
property="enwiki.exists"/>
+ <available file="temp/enwiki-20070527-pages-articles.xml"
property="enwiki.expanded"/>
+
</target>
+ <target name="enwiki-files" depends="check-files">
+ <mkdir dir="temp"/>
+ <antcall target="get-enwiki"/>
+ <antcall target="expand-enwiki"/>
+ </target>
+
+ <target name="get-enwiki" unless="enwiki.exists">
+ <get
src="http://people.apache.org/~gsingers/wikipedia/enwiki-20070527-pages-articles.xml.bz2"
+ dest="temp/enwiki-20070527-pages-articles.xml.bz2"/>
+ </target>
+
+ <target name="expand-enwiki" unless="enwiki.expanded">
+ <bunzip2 src="temp/enwiki-20070527-pages-articles.xml.bz2"
dest="temp"/>
+ </target>
+
+
<target name="get-20news-18828" unless="20news-18828.exists">
<get
src="http://people.csail.mit.edu/jrennie/20Newsgroups/20news-18828.tar.gz"
dest="temp/20news-18828.tar.gz"/>