Author: drew
Date: Thu Jul 8 12:43:17 2010
New Revision: 961739
URL: http://svn.apache.org/viewvc?rev=961739&view=rev
Log:
MAHOUT-426: improvements to the mahout script
Modified:
mahout/trunk/bin/mahout
Modified: mahout/trunk/bin/mahout
URL:
http://svn.apache.org/viewvc/mahout/trunk/bin/mahout?rev=961739&r1=961738&r2=961739&view=diff
==============================================================================
--- mahout/trunk/bin/mahout (original)
+++ mahout/trunk/bin/mahout Thu Jul 8 12:43:17 2010
@@ -17,6 +17,22 @@
# mappings and the default properties files
# defaults to "$MAHOUT_HOME/conf"
#
+# MAHOUT_LOCAL set to anything other than an empty string to force
+# mahout to run locally even if
+# HADOOP_CONF_DIR and HADOOP_HOME are set
+#
+# MAHOUT_CORE set to anything other than an empty string to force
+# mahout to run in developer 'core' mode, just as if the
+# -core option was presented on the command-line
+# Commane-line Options
+#
+# -core -core is used to switch into 'developer mode' when
+# running mahout locally. If specified, the classes
+# from the 'target/classes' directories in each project
+# are used. Otherwise classes will be retrived from
+# jars in the binary releas collection or *.job files
+# found in build directories. When running on hadoop
+# the job files will always be used.
#
#/**
@@ -54,12 +70,15 @@ while [ -h "$THIS" ]; do
done
IS_CORE=0
-#check for -core option
if [ "$1" == "-core" ] ; then
IS_CORE=1
shift
fi
+if [ "$MAHOUT_CORE" != "" ]; then
+ IS_CORE=1
+fi
+
# some directories
THIS_DIR=`dirname "$THIS"`
MAHOUT_HOME=`cd "$THIS_DIR/.." ; pwd`
@@ -165,18 +184,29 @@ done
if [ "$MAHOUT_JOB" = "" ]; then
for f in $MAHOUT_HOME/mahout-examples-*.job; do
- MAHOUT_JOB=$f
+ if [ -e "$f" ]; then
+ MAHOUT_JOB=$f
+ fi
done
fi
# run it
-if [ "$HADOOP_CONF_DIR" = "" ] || [ "$HADOOP_HOME" = "" ]; then
- echo "no HADOOP_CONF_DIR or HADOOP_HOME set, running locally"
+if [ "$HADOOP_CONF_DIR" = "" ] || [ "$HADOOP_HOME" = "" ] || [ "$MAHOUT_LOCAL"
!= "" ] ; then
+ if [ "$HADOOP_CONF_DIR" = "" ] || [ "$HADOOP_HOME" = "" ] ; then
+ echo "no HADOOP_CONF_DIR or HADOOP_HOME set, running locally"
+ elif [ "$MAHOUT_LOCAL" != "" ] ; then
+ echo "MAHOUT_LOCAL is set, running locally"
+ fi
exec "$JAVA" $JAVA_HEAP_MAX $MAHOUT_OPTS -classpath "$CLASSPATH" $CLASS "$@"
else
echo "running on hadoop, using HADOOP_HOME=$HADOOP_HOME and
HADOOP_CONF_DIR=$HADOOP_CONF_DIR"
+ if [ "$MAHOUT_JOB" = "" ] ; then
+ echo "ERROR: Could not find mahout-examples-*.job in $MAHOUT_HOME or
$MAHOUT_HOME/examples/target, please run 'mvn install' to create the .job file"
+ exit 1
+ else
export HADOOP_CLASSPATH=$MAHOUT_CONF_DIR:${HADOOP_CLASSPATH}
exec "$HADOOP_HOME/bin/hadoop" jar $MAHOUT_JOB $CLASS "$@"
+ fi
fi
