#!perl

use 5.010001;
use strict;
use warnings;
use Log::ger;
#use Log::ger::Screen;

use File::chdir;
use File::Slurper qw(read_binary);
use File::Temp qw(tempdir);
use File::Which qw(which);
use CLI::MetaUtil::Getopt::Long qw(GetOptionsCLIWrapper);
use IPC::System::Options 'system', -log=>1, -die=>1;

our $AUTHORITY = 'cpan:PERLANCAR'; # AUTHORITY
our $DATE = '2022-10-07'; # DATE
our $DIST = 'App-DiffPDFText'; # DIST
our $VERSION = '0.005'; # VERSION

my @files;
Getopt::Long::Configure("gnu_getopt", "no_ignore_case", "pass_through");

my $fail;
my $opt_pages;
my $opt_fmt = 1;

GetOptionsCLIWrapper(
    cli => 'diff',
    add_opts => {
        'pdf-pages=s' => \$opt_pages,
        'pdf-fmt!' => \$opt_fmt,
        '<>' => sub {
            my $filename = $_[0];
            unless (-f $filename) {
                warn "diff-pdf-text: No such file or not a file: '$filename'\n";
                $fail++;
                return;
            }

            require App::PDFUtils;
            my $res = App::PDFUtils::convert_pdf_to_text(
                file => $filename,
                fmt => $opt_fmt,
                return_output_file => 1,
                (defined $opt_pages ? (pages => $opt_pages) : ()),
            );
            my $file;
            if ($res->[0] == 304) {
                $file = $_[0];
            } elsif ($res->[0] == 200) {
                $file = $res->[2];
            } else {
                die "Can't convert PDF '$_[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_PDF_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, "-ruN", @ARGV,
);

# ABSTRACT: Diff the text of two PDF documents
# PODNAME: diff-pdf-text

__END__

=pod

=encoding UTF-8

=head1 NAME

diff-pdf-text - Diff the text of two PDF documents

=head1 VERSION

This document describes version 0.005 of diff-pdf-text (from Perl distribution App-DiffPDFText), released on 2022-10-07.

=head1 SYNOPSIS

Use like you would use the Unix command B<diff>:

 % diff-pdf-text [options] <FILE>...

=head1 DESCRIPTION

This is a wrapper for the Unix command B<diff>. It assumes that each input file
is a PDF file and tries to convert the file to text first using L<App::PDFUtils>
(which in turn uses B<pdftotext> CLI utility). It then passes the converted
text C<< diff -ruN >> command.

=head1 OPTIONS

These are options that are interpreted by B<diff-pdf-text> and not passed to
B<diff>.

B<Please specify these options before file names.>

=over

=item * --pdf-pages

Only diff a range of pages instead of the whole PDF. Example: 1,5-10,15.
Requires B<pdftk> to extract the page range.

=item * --(no-)pdf-fmt

Whether to apply `fmt` formatting to the `pdftotext` output. The default is yes;
use C<--no-pdf-fmt> to disable it.

=back

=head1 ENVIRONMENT

=head2 DEBUG

If set to true, do not cleanup temporary directories.

=head2 DIFF_CMD

String. Can be used to set path to diff command. See also
L</DIFF_PDF_TEXT_DIFF_CMD> which takes precedence.

=head2 DIFF_PDF_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-DiffPDFText>.

=head1 SOURCE

Source repository is at L<https://github.com/perlancar/perl-App-DiffPDFText>.

=head1 SEE ALSO

Unix command L<diff>.

=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 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-DiffPDFText>

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