#!/bin/bash
# Converter script to convert almost everything openoffice can read to txt using the jodconverter
# and the pdf2txt tool
# Because the jodconverter can not convert files formats like ppt, pptx, xls, ods, xlsx to txt directly,
# a conversion to PDF is performed first using the jodconvert. The second step is a conversion from
# PDF to txt using the pdftotxt commandline tool
# usage: all2text.sh <inputfile> <outputfile>
# <inputfile> is a arbitrary file open office can read (with correct file extension!)
# <outputfile> is the filename the result should go to. (txt as file extension)
#
# adapt the settings below to your own needs


echo "Input: $1"

#jodconverter binary cmd
JODCONVERTER_CMD=/opt/jodconverter/lib/jodconverter-cli-2.2.2.jar
#pdf2txt binary cmd (find out your path using the 'which pdftotxt' cmd)
PDF2TXT_CMD=/usr/bin/pdftotext
#your java cmd
JAVA_CMD=/usr/bin/java
#temporary folder for storing the PDF (path without trailing /)(you need to have write access here!)
TMP_FOLDER=/tmp/pdftmp

#extract input name
input_fullfile=$1
input_filename_w_ext=$(basename "$input_fullfile")
input_extension=${input_filename_w_ext##*.}
input_filename_wo_ext=${input_filename_w_ext%.*}

#first conversion to PDF:
tmpfile=$TMP_FOLDER/$input_filename_wo_ext".pdf"
$JAVA_CMD -jar $JODCONVERTER_CMD "$input_fullfile" "$tmpfile"

#second conversion to txt:
$PDF2TXT_CMD "$TMP_FOLDER/$input_filename_wo_ext.pdf" "$2"

#remove tmp file
rm -f $tmpfile