(brain-dead) shell script using TIKA in server mode to convert a batch of files to plain text

tika2text.sh

#!/bin/bash

# tika2text.sh - given a directory, recursively extract text frome files

# Eric Lease Morgan <[email protected]>
# (c) University of Notre Dame, distributed under a GNU Public License

# March 27, 2017 - a second cut; works with a directory


# configure
HOST='127.0.0.1'
TIKA='/Users/emorgan/desktop/tika.jar'
MODE="--text"
PORT=12345

# get input and sanity check
DIRECTORY=$@
if [[ -z $DIRECTORY ]]; then 
	printf "Usage: $0 <directory>\n"
	exit
fi

# start TIKA
printf "Starting TIKA. Please wait... " 1>&2
java -jar $TIKA $MODE --server -port $PORT &
PID=$!
printf "($PID)\n" 1>&2
sleep 10

# set up the environment; error check
cd "$DIRECTORY"

# process each file in the directory
for FILE in ./*;
do
	# only want files, not directories
	if [[ -f $FILE ]]; then
    	
		# do the work and send it to STDOUT
		nc $HOST $PORT < "$FILE"
	
    fi
done

# stop TIKA
printf "Stopping TIKA ($PID)..." 1>&2
kill $PID
printf "done\n" 1>&2