#!bin/bash
# This script works in its current form, but it's written for files that are named with the pattern pg_1.pdf, without leading zeros. Our files are named with four digits, the leading zeros being present if the page number is less than 1000. 'Need a script that will work with files named with the pattern pg_0001.pdf

a=1 #Sets the starting page equal to 1. 'Could set with user input.
b=$(($a+1))#Sets the next page equal to one more than the starting page.

Filename="pg_"$a".pdf" # This is the filename of the starting page.

until [ $b == 6 ]; do # The number sets the maximum pages to be considered for concatenation. Again, it could be set using user input.

Filename2="pg_"$b".pdf" # This is the filename of the next file to be considered for concatenation to the current file.

x=`pdfgrep -C 0 [0-9]\{7\} $Filename | head -n 1` # pdfgrep with option to capture only zero characters other than the seven digits in the employee ID; this is piped to head in order to get just the first occurrence.
y=`pdfgrep -C 0 [0-9]\{7\} $Filename2 | head -n 1`

if [ "$x" == "$y" ]; then 
    pdfjoin --rotateoversize 'false' $Filename $Filename2 --outfile $Filename # If the employee ID's are equal, then the pdf files are concatenated into a new file, which is given the name of the first file that's added to.
    rm $Filename2 # If the file is concatenated to a previous file, it is removed.
else
Filename=$Filename2 # If no match is found and the file is not concatenated, then advance the current origination file, Filename, to the name of the non-concatenated/non-matching file.

fi

b=$(($b+1)) # Advance the page number of the next file, Filename2.

done
exit