mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-21 00:00:13 +02:00
361f05978d
optional content parsers, thread pool configuration ... Please help me testing if everything works correct. *) Migration of yacy seedUpload functionality See: http://www.yacy-forum.de/viewtopic.php?t=256 - new uploaders can now be easily introduced because of a new modulare uploader system - default uploaders are: none, file, ftp - adding optional uploader for scp - each uploader provides its own configuration file that will be included into the settings page using the new template include feature - Each uploader can define its libx dependencies. If not all needed libs are available, the uploader is deactivated automatically. *) Migration of optional parsers See: http://www.yacy-forum.de/viewtopic.php?t=198 - Parsers can now also define there libx dependencies - adding parser for bzip compressed content - adding parser for gzip compressed content - adding parser for zip files - adding parser for tar files - adding parser to detect the mime-type of a file this is needed by the bzip/gzip Parser.java - adding parser for rtf files - removing extra configuration file yacy.parser the list of enabled parsers is now stored in the main config file *) Adding configuration option in the performance dialog to configure See: http://www.yacy-forum.de/viewtopic.php?t=267 - maxActive / maxIdle / minIdle values for httpd-session-threadpool - maxActive / maxIdle / minIdle values for crawler-threadpool *) Changing Crawling Filter behaviour See: http://www.yacy-forum.de/viewtopic.php?p=2631 *) Replacing some hardcoded strings with the proper constants of the httpHeader class *) Adding new libs to libx directory. This libs are - needed by new content parsers - needed by new optional seed uploader - needed by SOAP API (which will be committed later) git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@126 6c8d7289-2bf4-0310-a012-ef5d649a1542
55 lines
2.0 KiB
XML
55 lines
2.0 KiB
XML
<?xml version="1.0"?>
|
|
<project name="YACY - pdfParser" default="dist">
|
|
<description>
|
|
A class to parse pdf documents (application/pdf)
|
|
</description>
|
|
|
|
<property name="parserShortName" value="pdf"/>
|
|
<property name="parserVersion" value="0.1"/>
|
|
|
|
<property name="parserLongName" value="yacyContentParser_${parserShortName}"/>
|
|
<property name="parserArchive" location="${release}/${parserLongName}_${parserVersion}.tgz"/>
|
|
|
|
<target name="compile">
|
|
<echo message="Compiling ${parserLongName} Version ${parserVersion} ..."/>
|
|
<javac srcdir="${src}/de/anomic/plasma/parser/${parserShortName}" destdir="${build}" source="${javacSource}" target="${javacTarget}">
|
|
<classpath>
|
|
<pathelement location="${build}" />
|
|
|
|
<!-- main lib needed to parse pdf files -->
|
|
<pathelement location="${libx}/PDFBox-0.7.1.jar" />
|
|
|
|
<!-- libs needed by the main lib -->
|
|
<pathelement location="${libx}/log4j-1.2.9.jar" />
|
|
</classpath>
|
|
</javac>
|
|
</target>
|
|
|
|
|
|
<target name="zip" depends="compile">
|
|
<echo message="Compressing ${parserLongName} Version ${parserVersion} ..."/>
|
|
<tar destfile="${parserArchive}" compression="gzip">
|
|
<tarfileset dir="${libx}"
|
|
includes="PDFBox-0.7.1.*"
|
|
prefix="libx/"
|
|
dirmode="755" mode="644"/>
|
|
<tarfileset dir="${libx}"
|
|
includes="log4j-1.2.9.*"
|
|
prefix="libx/"
|
|
dirmode="755" mode="644"/>
|
|
<tarfileset dir="${src}/de/anomic/plasma/parser/${parserShortName}"
|
|
prefix="source/de/anomic/plasma/parser/${parserShortName}"
|
|
dirmode="755" mode="644"/>
|
|
<tarfileset dir="${build}/de/anomic/plasma/parser/${parserShortName}"
|
|
prefix="classes/de/anomic/plasma/parser/${parserShortName}"
|
|
dirmode="755" mode="644"/>
|
|
</tar>
|
|
</target>
|
|
|
|
|
|
<target name="dist" depends="compile,zip" description="Compile and zip the parser"/>
|
|
|
|
|
|
</project>
|
|
|