Author: andreas
Date: Tue Jun 28 08:55:37 2005
New Revision: 202234
URL: http://svn.apache.org/viewcvs?rev=202234&view=rev
Log:
moving search binaries to search publet
Added:
lenya/trunk/src/publets/search/bin/
lenya/trunk/src/publets/search/bin/crawl_and_index.xml
lenya/trunk/src/publets/search/bin/search.properties
Added: lenya/trunk/src/publets/search/bin/crawl_and_index.xml
URL:
http://svn.apache.org/viewcvs/lenya/trunk/src/publets/search/bin/crawl_and_index.xml?rev=202234&view=auto
==============================================================================
--- lenya/trunk/src/publets/search/bin/crawl_and_index.xml (added)
+++ lenya/trunk/src/publets/search/bin/crawl_and_index.xml Tue Jun 28 08:55:37
2005
@@ -0,0 +1,180 @@
+<?xml version="1.0"?>
+<!--
+ Copyright 1999-2004 The Apache Software Foundation
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- $Id: crawl_and_index.xml 201766 2005-06-25 16:54:42Z gregor $ -->
+
+<project default="main" basedir=".">
+
+
+
+<target name="main" description="main" depends="init">
+ <echo>INFO: webapp.dir=${webapp.dir}</echo>
+</target>
+
+
+
+
+<target name="init">
+ <property file="local.search.properties"/>
+ <property file="search.properties"/>
+
+ <!-- Dummy arguments -->
+ <property name="crawler.xconf"
value="src/webapp/lenya/pubs/default/config/search/crawler.xconf"/>
+ <property name="lucene.xconf"
value="src/webapp/lenya/pubs/default/config/search/lucene-cmfsMatrix.xconf"/>
+ <property name="htdocs.dump.dir"
value="src/webapp/lenya/pubs/default/content/live"/>
+ <property name="file"
value="src/webapp/lenya/pubs/default/content/live/index.xml"/>
+ <property name="index.dir"
value="src/webapp/lenya/pubs/default/work/search/lucene/index/index"/>
+ <property name="search.term" value="Lenya"/>
+ <!-- /Dummy arguments -->
+
+ <property name="web-inf.dir" value="${webapp.dir}/WEB-INF"/>
+
+ <path id="class.path">
+ <pathelement path="${web-inf.dir}/classes"/>
+ <fileset dir="${web-inf.dir}/lib">
+ <include name="**/*.jar"/>
+ </fileset>
+ </path>
+
+ <chmod file="${webapp.dir}/lenya/bin/crawl_and_index.sh" perm="755"/>
+</target>
+
+<target name="crawl" description="Crawl and dump hypertext documents. Usage:
-Dcrawler.xconf=/foo/bar/crawler.xconf (IMPORTANT NOTE: Use an absolute path to
specify the crawler.xconf file" depends="init">
+ <echo>INFO: Crawl and dump hypertext documents (${crawler.xconf})</echo>
+
+ <echo>INFO: Show configuration</echo>
+ <java classname="org.apache.lenya.search.crawler.CrawlerConfiguration">
+ <arg value="${crawler.xconf}"/>
+ <classpath refid="class.path"/>
+ </java>
+
+ <echo>INFO: START crawling ...</echo>
+ <java classname="org.apache.lenya.search.crawler.IterativeHTMLCrawler">
+ <arg value="${crawler.xconf}"/>
+ <classpath refid="class.path"/>
+ </java>
+ <echo>INFO: Crawling finished</echo>
+</target>
+
+
+<target name="index" description="Index hypertext documents. Usage:
-Dlucene.xconf=/foo/bar/lucene.xconf" depends="init">
+ <echo>INFO: Index hypertext documents</echo>
+
+ <echo>INFO: Show configuration</echo>
+ <java classname="org.apache.lenya.lucene.IndexConfiguration">
+ <arg value="${lucene.xconf}"/>
+ <classpath refid="class.path"/>
+ </java>
+
+ <echo>INFO: Create index ...</echo>
+ <java classname="org.apache.lenya.lucene.index.Index">
+ <arg value="${lucene.xconf}"/>
+ <classpath refid="class.path"/>
+ </java>
+ <echo>INFO: Index has been created</echo>
+</target>
+
+<target name="indexOneDocument" description="Index one document. Usage:
-Dlucene.xconf=/foo/bar/lucene.xconf -Dfile=/foo/bar/document" depends="init">
+ <echo>INFO: Index one document</echo>
+
+ <echo>INFO: Show configuration</echo>
+ <java classname="org.apache.lenya.lucene.IndexConfiguration">
+ <arg value="${lucene.xconf}"/>
+ <classpath refid="class.path"/>
+ </java>
+
+ <echo>INFO: Update index for ${file}</echo>
+ <java classname="org.apache.lenya.lucene.index.Index">
+ <arg value="${lucene.xconf}"/>
+ <arg value="${file}"/>
+ <classpath refid="class.path"/>
+ </java>
+ <echo>INFO: Document has been indexed</echo>
+</target>
+
+
+
+<target name="test-index" description="Regression Test of Index"
depends="init">
+ <echo>INFO: Regression Test of Index</echo>
+</target>
+
+<target name="search" description="Search within Index. Usage: -Dindex.dir=...
-Dsearch.term=Lenya" depends="init">
+ <echo>INFO: Search within Index</echo>
+
+ <exec executable="${webapp.dir}/lenya/bin/crawl_and_index.sh">
+ <arg value="search"/>
+ <arg value="${index.dir}"/>
+ <arg value="${search.term}"/>
+ </exec>
+
+<!-- NOTE: problem with modifiers "public static" -->
+<!--
+ <java classname="org.apache.lenya.lucene.SearchFiles">
+ <arg value="${index.dir}"/>
+ <arg value="${search.term}"/>
+ <classpath refid="class.path"/>
+ </java>
+-->
+</target>
+
+<target name="publish-index" description="Publish Index" depends="init">
+ <echo>INFO: Publish Index</echo>
+</target>
+
+<target name="xpdf" description="Extract text from PDF with Xpdf. Usage:
-Dhtdocs.dump.dir=/usr/local/apache/htdocs" depends="init">
+ <echo>INFO: Extract text from PDF with Xpdf (${htdocs.dump.dir})</echo>
+
+ <exec executable="${webapp.dir}/lenya/bin/crawl_and_index.sh">
+ <arg value="xpdf"/>
+ <arg value="${htdocs.dump.dir}"/>
+ </exec>
+</target>
+
+<target name="pdfbox" description="Extract text from PDF with PDFBox"
depends="init">
+ <echo>INFO: Extract text from PDF with PDFBox</echo>
+
+ <echo>FIXME: Not implemented yet</echo>
+<!--
+PDFBOX=$HOME/src/PDFBox-0.5.5
+CLASSPATH=$CLASSPATH:$PDFBOX/classes
+##$JAVA -cp $CLASSPATH org.pdfbox.Main $FILE_PDF $FILE_PDF.txt
+-->
+</target>
+
+<target name="pdfadobe" description="Extract text from PDF via Adobe PDF
Conversion webpage" depends="init">
+ <echo>INFO: Extract text from PDF via Adobe PDF Conversion webpage</echo>
+
+ <echo>INFO:
http://www.adobe.com/products/acrobat/access_simple_form.html</echo>
+</target>
+
+<target name="show-config" description="Show configuration" depends="init">
+ <echo>INFO: Show configuration</echo>
+
+ <echo>INFO: crawler.xconf</echo>
+ <java classname="org.apache.lenya.search.crawler.CrawlerConfiguration">
+ <arg value="${crawler.xconf}"/>
+ <classpath refid="class.path"/>
+ </java>
+
+ <echo>INFO: lucene.xconf</echo>
+ <java classname="org.apache.lenya.lucene.IndexConfiguration">
+ <arg value="${lucene.xconf}"/>
+ <classpath refid="class.path"/>
+ </java>
+</target>
+
+</project>
Added: lenya/trunk/src/publets/search/bin/search.properties
URL:
http://svn.apache.org/viewcvs/lenya/trunk/src/publets/search/bin/search.properties?rev=202234&view=auto
==============================================================================
--- lenya/trunk/src/publets/search/bin/search.properties (added)
+++ lenya/trunk/src/publets/search/bin/search.properties Tue Jun 28 08:55:37
2005
@@ -0,0 +1,19 @@
+# Copyright 1999-2004 The Apache Software Foundation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+webapp.dir=../../
+
+#java.run=/usr/lib/j2sdk1.4/bin/java
+
+#xpdf.bin=/usr/local/xpdf-2.03-linux/pdftotext
|
