filterbuilder

HTML Parser is a Java library used to parse HTML in either a linear or nested fashion. Primarily use

#! /bin/sh

if [ -z "$HTMLPARSER_HOME" ] ; then

  ## resolve links - $0 may be a link to the home
  PRG="$0"
  progname=`basename "$0"`
  saveddir=`pwd`

  # need this for relative symlinks
  dirname_prg=`dirname "$PRG"`
  cd "$dirname_prg"
  
  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
  
  HTMLPARSER_HOME=`dirname "$PRG"`/..

  cd "$saveddir"

  # make it fully qualified
  HTMLPARSER_HOME=`cd "$HTMLPARSER_HOME" && pwd`
fi

if [ -z "$JAVACMD" ] ; then 
  if [ -n "$JAVA_HOME"  ] ; then
    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then 
      # IBM's JDK on AIX uses strange locations for the executables
      JAVACMD="$JAVA_HOME/jre/sh/java"
    else
      JAVACMD="$JAVA_HOME/bin/java"
    fi
  else
    JAVACMD=`which java 2> /dev/null `
    if [ -z "$JAVACMD" ] ; then 
        JAVACMD=java
    fi
  fi
fi
 
if [ ! -x "$JAVACMD" ] ; then
  echo "Error: JAVA_HOME is not defined correctly."
  echo "  We cannot execute $JAVACMD"
  exit 1
fi

HTMLPARSER_LIB="${HTMLPARSER_HOME}/lib"

"$JAVACMD" -Xmx256M -classpath "${HTMLPARSER_LIB}/filterbuilder.jar:${HTMLPARSER_LIB}/htmlparser.jar:${HTMLPARSER_LIB}/htmllexer.jar" org.htmlparser.parserapplications.filterbuilder.FilterBuilder "$@"