source: nutchez-0.1/bin/nutch @ 75

#!/bin/bash
# 
# The Nutch command script
#
# Environment Variables
#
#   NUTCH_JAVA_HOME The java implementation to use.  Overrides JAVA_HOME.
#
#   NUTCH_HEAPSIZE  The maximum amount of heap to use, in MB. 
#                   Default is 1000.
#
#   NUTCH_OPTS      Extra Java runtime options.
#
cygwin=false
case "`uname`" in
CYGWIN*) cygwin=true;;
esac

# resolve links - $0 may be a softlink
THIS="$0"
while [ -h "$THIS" ]; do
  ls=`ls -ld "$THIS"`
  link=`expr "$ls" : '.*-> \(.*\)$'`
  if expr "$link" : '.*/.*' > /dev/null; then
    THIS="$link"
  else
    THIS=`dirname "$THIS"`/"$link"
  fi
done

# if no args specified, show usage
if [ $# = 0 ]; then
  echo "Usage: nutch [-core] COMMAND"
  echo "where COMMAND is one of:"
  echo "  crawl             one-step crawler for intranets"
  echo "  readdb            read / dump crawl db"
  echo "  convdb            convert crawl db from pre-0.9 format"
  echo "  mergedb           merge crawldb-s, with optional filtering"
  echo "  readlinkdb        read / dump link db"
  echo "  inject            inject new urls into the database"
  echo "  generate          generate new segments to fetch from crawl db"
  echo "  freegen           generate new segments to fetch from text files"
  echo "  fetch             fetch a segment's pages"
  echo "  parse             parse a segment's pages"
  echo "  readseg           read / dump segment data"
  echo "  mergesegs         merge several segments, with optional filtering and slicing"
  echo "  updatedb          update crawl db from segments after fetching"
  echo "  invertlinks       create a linkdb from parsed segments"
  echo "  mergelinkdb       merge linkdb-s, with optional filtering"
  echo "  index             run the indexer on parsed segments and linkdb"
  echo "  solrindex         run the solr indexer on parsed segments and linkdb"
  echo "  merge             merge several segment indexes"
  echo "  dedup             remove duplicates from a set of segment indexes"
  echo "  solrdedup         remove duplicates from solr"
  echo "  plugin            load a plugin and run one of its classes main()"
  echo "  server            run a search server"
  echo " or"
  echo "  CLASSNAME         run the class named CLASSNAME"
  echo "Most commands print help when invoked w/o parameters."
  echo ""
  echo "Expert: -core option is for developers only. It avoids building the job jar, "
  echo "        instead it simply includes classes compiled with ant compile-core. "
  echo "        NOTE: this works only for jobs executed in 'local' mode"
  exit 1
fi

IS_CORE=0
#check for -core option
if [ "$1" == "-core" ] ; then
  IS_CORE=1
  shift
fi

# get arguments
COMMAND=$1
shift

# some directories
THIS_DIR=`dirname "$THIS"`
NUTCH_HOME=`cd "$THIS_DIR/.." ; pwd`

# some Java parameters
if [ "$NUTCH_JAVA_HOME" != "" ]; then
  #echo "run java in $NUTCH_JAVA_HOME"
  JAVA_HOME=$NUTCH_JAVA_HOME
fi
  
if [ "$JAVA_HOME" = "" ]; then
  echo "Error: JAVA_HOME is not set."
  exit 1
fi

JAVA=$JAVA_HOME/bin/java
JAVA_HEAP_MAX=-Xmx1000m 

# check envvars which might override default args
if [ "$NUTCH_HEAPSIZE" != "" ]; then
  #echo "run with heapsize $NUTCH_HEAPSIZE"
  JAVA_HEAP_MAX="-Xmx""$NUTCH_HEAPSIZE""m"
  #echo $JAVA_HEAP_MAX
fi

# CLASSPATH initially contains $NUTCH_CONF_DIR, or defaults to $NUTCH_HOME/conf
CLASSPATH=${NUTCH_CONF_DIR:=$NUTCH_HOME/conf}

CLASSPATH=${CLASSPATH}:$JAVA_HOME/lib/tools.jar

# so that filenames w/ spaces are handled correctly in loops below
IFS=

# for developers, add plugins, job & test code to CLASSPATH
if [ -d "$NUTCH_HOME/build/plugins" ]; then
  CLASSPATH=${CLASSPATH}:$NUTCH_HOME/build
fi
if [ -d "$NUTCH_HOME/build/test/classes" ]; then
  CLASSPATH=${CLASSPATH}:$NUTCH_HOME/build/test/classes
fi

if [ $IS_CORE == 0 ] 
then
  for f in $NUTCH_HOME/build/nutch-*.job; do
    CLASSPATH=${CLASSPATH}:$f;
  done

  # for releases, add Nutch job to CLASSPATH
  for f in $NUTCH_HOME/nutch-*.job; do
    CLASSPATH=${CLASSPATH}:$f;
  done
else
  CLASSPATH=${CLASSPATH}:$NUTCH_HOME/build/classes
fi

# add plugins to classpath
if [ -d "$NUTCH_HOME/plugins" ]; then
  CLASSPATH=${NUTCH_HOME}:${CLASSPATH}
fi

# add libs to CLASSPATH
for f in $NUTCH_HOME/lib/*.jar; do
  CLASSPATH=${CLASSPATH}:$f;
done

for f in $NUTCH_HOME/lib/jetty-ext/*.jar; do
  CLASSPATH=${CLASSPATH}:$f;
done

# cygwin path translation
if $cygwin; then
  CLASSPATH=`cygpath -p -w "$CLASSPATH"`
fi

# setup 'java.library.path' for native-hadoop code if necessary
JAVA_LIBRARY_PATH=''
if [ -d "${NUTCH_HOME}/build/native" -o -d "${NUTCH_HOME}/lib/native" ]; then
  JAVA_PLATFORM=`CLASSPATH=${CLASSPATH} ${JAVA} org.apache.hadoop.util.PlatformName | sed -e 's/ /_/g'`
  
  if [ -d "$NUTCH_HOME/build/native" ]; then
    JAVA_LIBRARY_PATH=${HADOOP_HOME}/build/native/${JAVA_PLATFORM}/lib
  fi
  
  if [ -d "${NUTCH_HOME}/lib/native" ]; then
    if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
      JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}:${NUTCH_HOME}/lib/native/${JAVA_PLATFORM}
    else
      JAVA_LIBRARY_PATH=${NUTCH_HOME}/lib/native/${JAVA_PLATFORM}
    fi
  fi
fi

if [ $cygwin = true -a "X${JAVA_LIBRARY_PATH}" != "X" ]; then
  JAVA_LIBRARY_PATH=`cygpath -p -w "$JAVA_LIBRARY_PATH"`
fi

# restore ordinary behaviour
unset IFS

# default log directory & file
if [ "$NUTCH_LOG_DIR" = "" ]; then
  NUTCH_LOG_DIR="$NUTCH_HOME/logs"
fi
if [ "$NUTCH_LOGFILE" = "" ]; then
  NUTCH_LOGFILE='hadoop.log'
fi

#Fix log path under cygwin
if $cygwin; then
  NUTCH_LOG_DIR=`cygpath -p -w "$NUTCH_LOG_DIR"`
fi

NUTCH_OPTS="$NUTCH_OPTS -Dhadoop.log.dir=$NUTCH_LOG_DIR"
NUTCH_OPTS="$NUTCH_OPTS -Dhadoop.log.file=$NUTCH_LOGFILE"

if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
  NUTCH_OPTS="$NUTCH_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH"
fi

# figure out which class to run
if [ "$COMMAND" = "crawl" ] ; then
  CLASS=org.apache.nutch.crawl.Crawl
elif [ "$COMMAND" = "inject" ] ; then
  CLASS=org.apache.nutch.crawl.Injector
elif [ "$COMMAND" = "generate" ] ; then
  CLASS=org.apache.nutch.crawl.Generator
elif [ "$COMMAND" = "freegen" ] ; then
  CLASS=org.apache.nutch.tools.FreeGenerator
elif [ "$COMMAND" = "fetch" ] ; then
  CLASS=org.apache.nutch.fetcher.Fetcher
elif [ "$COMMAND" = "fetch2" ] ; then
  CLASS=org.apache.nutch.fetcher.Fetcher2
elif [ "$COMMAND" = "parse" ] ; then
  CLASS=org.apache.nutch.parse.ParseSegment
elif [ "$COMMAND" = "readdb" ] ; then
  CLASS=org.apache.nutch.crawl.CrawlDbReader
elif [ "$COMMAND" = "convdb" ] ; then
  CLASS=org.apache.nutch.tools.compat.CrawlDbConverter
elif [ "$COMMAND" = "mergedb" ] ; then
  CLASS=org.apache.nutch.crawl.CrawlDbMerger
elif [ "$COMMAND" = "readlinkdb" ] ; then
  CLASS=org.apache.nutch.crawl.LinkDbReader
elif [ "$COMMAND" = "readseg" ] ; then
  CLASS=org.apache.nutch.segment.SegmentReader
elif [ "$COMMAND" = "segread" ] ; then
  echo "[DEPRECATED] Command 'segread' is deprecated, use 'readseg' instead."
  CLASS=org.apache.nutch.segment.SegmentReader
elif [ "$COMMAND" = "mergesegs" ] ; then
  CLASS=org.apache.nutch.segment.SegmentMerger
elif [ "$COMMAND" = "updatedb" ] ; then
  CLASS=org.apache.nutch.crawl.CrawlDb
elif [ "$COMMAND" = "invertlinks" ] ; then
  CLASS=org.apache.nutch.crawl.LinkDb
elif [ "$COMMAND" = "mergelinkdb" ] ; then
  CLASS=org.apache.nutch.crawl.LinkDbMerger
elif [ "$COMMAND" = "index" ] ; then
  CLASS=org.apache.nutch.indexer.Indexer
elif [ "$COMMAND" = "solrindex" ] ; then
  CLASS=org.apache.nutch.indexer.solr.SolrIndexer
elif [ "$COMMAND" = "dedup" ] ; then
  CLASS=org.apache.nutch.indexer.DeleteDuplicates
elif [ "$COMMAND" = "solrdedup" ] ; then
  CLASS=org.apache.nutch.indexer.solr.SolrDeleteDuplicates
elif [ "$COMMAND" = "merge" ] ; then
  CLASS=org.apache.nutch.indexer.IndexMerger
elif [ "$COMMAND" = "plugin" ] ; then
  CLASS=org.apache.nutch.plugin.PluginRepository
elif [ "$COMMAND" = "server" ] ; then
  CLASS='org.apache.nutch.searcher.DistributedSearch$Server'
else
  CLASS=$COMMAND
fi

# run it
exec "$JAVA" $JAVA_HEAP_MAX $NUTCH_OPTS -classpath "$CLASSPATH" $CLASS "$@"