$ cvs -d :pserver:username@cvs.dev.java.net:/cvs login
$ cvs -d :pserver:username@cvs.dev.java.net:/cvs checkout sampo
$ cd sampo/nutch
$ export JAVA_HOME=/usr/java/jdk1.6.0_04
$ export SAMPO_HOME=/var/sampo
$ export NUTCH_HOME=/usr/local/nutch-0.9
$ export PATH=$SAMPO_HOME/bin:$JAVA_HOME/bin:$PATH
$ ant init
$ ant -DSAMPO_HOME=$SAMPO_HOME install
$ cd $NUTCH_HOME
$ mkdir lj
$ vi lj.sh
$ cat lj.sh
#!/bin/sh
L=$SAMPO_HOME/lib
CP=$L/sampo-nutch.jar:$L/hadoop-0.12.2-core.jar:$L/nutch-0.9.jar\
:$L/commons-logging-1.1.1.jar:$L/log4j-1.2.15.jar:$L/commons-io-1.3.2.jar
CN=net.java.sampo.nutch.util.ContentsExtractor
S=`ls -d $1/20* | tail -1`
D=$2
java -classpath $CP $CN $S $D
$ sh lj.sh kazmuzik-segment-20080303 lj
$ |