#!perl use 5.010001; use strict; use warnings; use Log::ger; #use Log::ger::Screen; use Getopt::Long (); use CLI::MetaUtil::Getopt::Long qw(GetOptionsCLIWrapper); our $AUTHORITY = 'cpan:PERLANCAR'; # AUTHORITY our $DATE = '2022-09-08'; # DATE our $DIST = 'App-DiffDocText'; # DIST our $VERSION = '0.004'; # VERSION my @files; Getopt::Long::Configure("gnu_getopt", "no_ignore_case", "pass_through"); my $fail; GetOptionsCLIWrapper( cli => 'diff', add_opts => { '<>' => sub { my $filename = $_[0]; unless (-f $filename) { warn "diff-doc-text: No such file or not a file: '$filename'\n"; $fail++; return; } require App::OfficeUtils; my $res = App::OfficeUtils::officewp2txt( input_file => $filename, fmt => 1, return_output_file => 1, ); my $file; if ($res->[0] == 304) { $file = $_[0]; } elsif ($res->[0] == 200) { $file = $res->[2]; } else { die "Can't convert doc '$_[0]' to text: $res->[0] - $res->[1]"; } push @CLI::MetaUtil::Getopt::Long::cli_argv, $file; }, }, ); exit 1 if $fail; require File::Which; my $diff_cmd = $ENV{DIFF_DOC_TEXT_DIFF_CMD} // $ENV{DIFF_CMD} // (File::Which::which("diffwc") ? "diffwc" : undef) // "diff"; require IPC::System::Options; IPC::System::Options::system( {log=>1}, $diff_cmd, @ARGV, ); # ABSTRACT: Diff the text of two Office word-processor documents (.doc, .docx, .odt, etc) # PODNAME: diff-doc-text __END__ =pod =encoding UTF-8 =head1 NAME diff-doc-text - Diff the text of two Office word-processor documents (.doc, .docx, .odt, etc) =head1 VERSION This document describes version 0.004 of diff-doc-text (from Perl distribution App-DiffDocText), released on 2022-09-08. =head1 SYNOPSIS Use like you would use the Unix command B<diff>: % diff-doc-text [options] <FILE>... =head1 DESCRIPTION This is a wrapper for the Unix command B<diff>. It assumes that each file is an Office word-processor documents (.doc, .docx, .odt, etc) and tries to convert the file to plaintext first. It then passes the converted files to C<diff>. =head1 ENVIRONMENT =head2 DIFF_CMD String. Can be used to set path to diff command. See also L</DIFF_XLS_TEXT_DIFF_CMD> which takes precedence. =head2 DIFF_DOC_TEXT_DIFF_CMD String. Can be used to set path to diff command. The defaultl is L<diffwc> if available in PATH, or C<diff>. Takes precedence over L</DIFF_CMD>. =head1 HOMEPAGE Please visit the project's homepage at L<https://metacpan.org/release/App-DiffDocText>. =head1 SOURCE Source repository is at L<https://github.com/perlancar/perl-App-DiffDocText>. =head1 SEE ALSO Unix command L<diff>. L<App::OfficeUtils> and the included CLI L<doc2txt>. =head1 AUTHOR perlancar <perlancar@cpan.org> =head1 CONTRIBUTING To contribute, you can send patches by email/via RT, or send pull requests on GitHub. Most of the time, you don't need to build the distribution yourself. You can simply modify the code, then test via: % prove -l If you want to build the distribution (e.g. to try to install it locally on your system), you can install L<Dist::Zilla>, L<Dist::Zilla::PluginBundle::Author::PERLANCAR>, L<Pod::Weaver::PluginBundle::Author::PERLANCAR>, and sometimes one or two other Dist::Zilla- and/or Pod::Weaver plugins. Any additional steps required beyond that are considered a bug and can be reported to me. =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2022, 2020 by perlancar <perlancar@cpan.org>. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =head1 BUGS Please report any bugs or feature requests on the bugtracker website L<https://rt.cpan.org/Public/Dist/Display.html?Name=App-DiffDocText> When submitting a bug or request, please include a test-file or a patch to an existing test-file that illustrates the bug or desired feature. =cut