From: <bra...@us...> - 2009-11-06 01:50:37
|
Revision: 2886 http://archive-access.svn.sourceforge.net/archive-access/?rev=2886&view=rev Author: bradtofel Date: 2009-11-06 01:50:20 +0000 (Fri, 06 Nov 2009) Log Message: ----------- REFACTOR: moved main() from ArcIndexer and WarcIndexer into IndexWorker - leaving Modified Paths: -------------- trunk/archive-access/projects/wayback/dist/src/scripts/arc-indexer trunk/archive-access/projects/wayback/dist/src/scripts/warc-indexer Added Paths: ----------- trunk/archive-access/projects/wayback/dist/src/scripts/cdx-indexer Modified: trunk/archive-access/projects/wayback/dist/src/scripts/arc-indexer =================================================================== --- trunk/archive-access/projects/wayback/dist/src/scripts/arc-indexer 2009-11-06 01:49:32 UTC (rev 2885) +++ trunk/archive-access/projects/wayback/dist/src/scripts/arc-indexer 2009-11-06 01:50:20 UTC (rev 2886) @@ -75,7 +75,7 @@ # Main ArcIndexer class. if [ -z "$CLASS_MAIN" ] then - CLASS_MAIN='org.archive.wayback.resourcestore.indexer.ArcIndexer' + CLASS_MAIN='org.archive.wayback.resourcestore.indexer.IndexWorker' fi CLASSPATH=${CP} $JAVACMD ${JAVA_OPTS} $CLASS_MAIN "$@" Added: trunk/archive-access/projects/wayback/dist/src/scripts/cdx-indexer =================================================================== --- trunk/archive-access/projects/wayback/dist/src/scripts/cdx-indexer (rev 0) +++ trunk/archive-access/projects/wayback/dist/src/scripts/cdx-indexer 2009-11-06 01:50:20 UTC (rev 2886) @@ -0,0 +1,82 @@ +#!/usr/bin/env sh +## +## This script creates a CDX file for all ARC files in a directory +## PUTs those CDX files into a remote pipeline, and informs a remote +## LocationDB of the locations of all the ARC files. +## +## Optional environment variables +## +## JAVA_HOME Point at a JDK install to use. +## +## WAYBACK_HOME Pointer to your wayback install. If not present, we +## make an educated guess based of position relative to this +## script. +## +## JAVA_OPTS Java runtime options. Default setting is '-Xmx256m'. +## + +# Resolve links - $0 may be a softlink +PRG="$0" +while [ -h "$PRG" ]; do + ls=`ls -ld "$PRG"` + link=`expr "$ls" : '.*-> \(.*\)$'` + if expr "$link" : '.*/.*' > /dev/null; then + PRG="$link" + else + PRG=`dirname "$PRG"`/"$link" + fi +done +PRGDIR=`dirname "$PRG"` + +# Set WAYBACK_HOME. +if [ -z "$WAYBACK_HOME" ] +then + WAYBACK_HOME=`cd "$PRGDIR/.." ; pwd` +fi + +# Find JAVA_HOME. +if [ -z "$JAVA_HOME" ] +then + JAVA=`which java` + if [ -z "$JAVA" ] + then + echo "Cannot find JAVA. Please set JAVA_HOME or your PATH." + exit 1 + fi + JAVA_BINDIR=`dirname $JAVA` + JAVA_HOME=$JAVA_BINDIR/.. +fi + +if [ -z "$JAVACMD" ] +then + # It may be defined in env - including flags!! + JAVACMD=$JAVA_HOME/bin/java +fi + +# Ignore previous classpath. Build one that contains heritrix jar and content +# of the lib directory into the variable CP. +for jar in `ls $WAYBACK_HOME/lib/*.jar $WAYBACK_HOME/*.jar 2> /dev/null` +do + CP=${CP}:${jar} +done + +# cygwin path translation +if expr `uname` : 'CYGWIN*' > /dev/null; then + CP=`cygpath -p -w "$CP"` + WAYBACK_HOME=`cygpath -p -w "$WAYBACK_HOME"` +fi + +# Make sure of java opts. +if [ -z "$JAVA_OPTS" ] +then + JAVA_OPTS=" -Xmx256m" +fi + +# Main ArcIndexer class. +if [ -z "$CLASS_MAIN" ] +then + CLASS_MAIN='org.archive.wayback.resourcestore.indexer.IndexWorker' +fi + +CLASSPATH=${CP} $JAVACMD ${JAVA_OPTS} $CLASS_MAIN "$@" + Modified: trunk/archive-access/projects/wayback/dist/src/scripts/warc-indexer =================================================================== --- trunk/archive-access/projects/wayback/dist/src/scripts/warc-indexer 2009-11-06 01:49:32 UTC (rev 2885) +++ trunk/archive-access/projects/wayback/dist/src/scripts/warc-indexer 2009-11-06 01:50:20 UTC (rev 2886) @@ -75,7 +75,7 @@ # Main ArcIndexer class. if [ -z "$CLASS_MAIN" ] then - CLASS_MAIN='org.archive.wayback.resourcestore.indexer.WarcIndexer' + CLASS_MAIN='org.archive.wayback.resourcestore.indexer.IndexWorker' fi CLASSPATH=${CP} $JAVACMD ${JAVA_OPTS} $CLASS_MAIN "$@" This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site. |