#!/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;
}
In reply to RTF diff
by sheriff
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|