#!/bin/bash
## diff-by-charset -- compares a file to itself, using two specified charset/encodings -- Eugene Reimer 2009-08;
## receives 2 named charsets and one file, compares the file converted from charset1 to utf8, and same file converted from charset2.
##
## USAGE EXAMPLE:
##	diff-by-charset  windows-1252  windows-1251  /pkg/geneweb/gw/lang/lexicon.txt
##
## Copyright © 2009 Eugene Reimer;  can be used, modified, copied, and distributed or sold under the terms of either the LGPL or the GPL (your choice);
## see http://www.gnu.org/licenses for the details of these terms.

[ $# -lt 3 ] && { echo "usage:  diff-by-charset  CHARSET1  CHARSET2  FILE...";  exit 2; }
FROM1=$1; FROM2=$2; shift; shift
for F in "$@";do
  iconv -f $FROM1 -t utf8  $F >/tmp/tmpdiff-from-$FROM1
  iconv -f $FROM2 -t utf8  $F >/tmp/tmpdiff-from-$FROM2
  diff -bBs -U0  /tmp/tmpdiff-from-$FROM1  /tmp/tmpdiff-from-$FROM2
done