#!/usr/bin/perl

# Compares a tokenized view of two RTF files

use strict;
use RTF::Tokenizer;
use Text::Diff;

my $first_file = pretty_print( $ARGV[0] );
my $second_file = pretty_print( $ARGV[1] );

print diff \$first_file, \$second_file;

sub pretty_print {

    my $filename = shift;
    my $output;

    my $tokenizer = RTF::Tokenizer->new( file => $filename );

    while (1) {

        my ( $type, $token, $argument ) = $tokenizer->get_token();

        last if $type eq 'eof';

        $argument =~ s/\n/[n]/g;
        $argument =~ s/\t/[t]/g;
        $argument =~ s/\r/[r]/g;

        $output .= "($type) $token $argument\n";

    }

    return $output;

}

[download]

In reply to RTF diff by sheriff

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.