#!/bin/bash                                           
# This is a converter script to convert the content from a zip file to a single txt file.
# All files which extensions are defined in this script get unzipped, converted to text and joined to one single output file
# usage: zip2txt.sh <inputfile> <outputfile>                                                                               

#adapt this:
#Folder where the zip file is unpacked WARNING: DO NOT USE THIS FOLDER FOR ANYTHING ELSE -> all files in there will be converted!
TMPFOLDER="/tmp/zipconverter"         
#File which is used as a temporary storage
#DO NOT PLACE THE TMPFILE INSIDE/BELOW THE TMPFOLDER IF YOU DON'T EXACTLY KNOW WHAT YOUR ARE DOING
TMPFILE="/tmp/zipconverstion.txt"                                                                 
#commands needed for this script                                                                  
UNZIP_CMD="/usr/bin/unzip"                                                                        
FIND_CMD="/usr/bin/find"                                                                          

#extent the extention and command  array for your personal needs
#note: the first parameter of the cmd must be the input, the second is the output filename. e.g. /opt/office2txt.sh <inputfile> <outputfile>
FILEEXT[0]="doc"; CMD[0]="/opt/office2txt.sh"                                                                                          
FILEEXT[1]="pdf"; CMD[1]="/usr/bin/pdftotext"                                                                                          

#IO definitions
zipfile=$1     
outputfile=$2  

#generate filter string from FILEEXT
filter=""                           
for ext in "${FILEEXT[@]}"          
do                                  
  filter="$filter *.$ext"
done

#Unzip only content into TMPFOLDER with known extensions, ignoring case sensitivity of filter "-C",
# The  "-P \n" is needed to tell unzip that we do not have a valid password so it does not ask on stdin
# if a file is encrypted                                                                               
$UNZIP_CMD -o -qq -C -P \n $1$filter -d $TMPFOLDER  

#put all filenames into an array which are inside the TMPFOLDER.
#Whitespaces in filenames are handled correctly (from http://mywiki.wooledge.org/BashFAQ/020)
unset filenames i
while IFS= read -r -d '' file; do
  filenames[i++]=$file
#  echo "File: ${filenames[i-1]}"
done < <($FIND_CMD $TMPFOLDER -type f -print0)

#switch off case sensitivity
shopt -s nocasematch

#convert each file to txt according the command set in CMD
for file in "${filenames[@]}"
do
echo "Working on file: $file"
  #get fileextention
  input_filename_w_ext=$(basename "$file")
  input_extension=${input_filename_w_ext##*.}
  #search extension in FILEEXT array (case insensitive)
  # get length of an array
  tLen=${#FILEEXT[@]}
  extfount=0
  for (( i=0; i<${tLen}; i++ ));
  do
    if [[ ${FILEEXT[$i]} = $input_extension ]]
    then
      rm -f $TMPFILE #make sure it is empty
      #execute conversion cmd
      echo ${CMD[$i]} "$file" "$TMPFILE"
      ${CMD[$i]} "$file" "$TMPFILE"
      #append $TMPFILE to output file $outputfile
      cat $TMPFILE >> $outputfile
      break
    fi
  done
done
#switch on case sensitivity
shopt -u nocasematch

#remove all stuff in the temp folder and the temp file
rm -rf $TMPFOLDER/*
rm -f $TMPFILE