#!/bin/bash

bdir=$1
cd "$bdir"

SAVEIFS=$IFS
IFS=$(echo -en "\n\b")
for bookdir in $(find openbess* -type d);
do
   echo "$bookdir"
   cd "$bookdir"
   n=0
   SAVEIFS=$IFS
   IFS=$(echo -en "\n\b")
   for nfile in $(find *.pdf -type f);
   do
      let "n += 1"
      filedoc="$nfile"
   done
   if [ $n -gt 1 ] || [ $n -lt 1 ]
   then
      echo "ERROR file PDF non unico"
      exit
   fi
   IFS=$SAVEIFS
   cp "$filedoc" doc.pdf
   rm "$filedoc"
   
   docsplit text --pages all --no-ocr --no-clean --output OCR/ doc.pdf
   
   cd OCR
   n=0
   SAVEIFS=$IFS
   IFS=$(echo -en "\n\b")
   for nfile in $(find *.txt -type f);
   do
      numer=${nfile#doc_}
      numero=${numer%\.txt}
      sn=$(printf "%04d" $numero)
      
      tr -d '\f' < "$nfile" > "$sn".txt
      rm "$nfile"
      
      echo "$sn"" DONE"
   done
   IFS=$SAVEIFS
  
   cd ~
   echo "DONE **************************""$bookdir"
done
exit