—#!perl
use
5.010001;
use
strict;
use
warnings;
use
Log::ger;
#use Log::ger::Screen;
use
Getopt::Long ();
our
$AUTHORITY
=
'cpan:PERLANCAR'
;
# AUTHORITY
our
$DATE
=
'2024-09-28'
;
# DATE
our
$DIST
=
'App-PDFUtils'
;
# DIST
our
$VERSION
=
'0.016'
;
# VERSION
my
@files
;
Getopt::Long::Configure(
"gnu_getopt"
,
"no_ignore_case"
,
"pass_through"
);
my
$fail
;
my
(
$opt_pages
,
$opt_raw
);
GetOptionsCLIWrapper(
cli
=>
'less'
,
add_opts
=> {
'pdf-pages=s'
=> \
$opt_pages
,
'pdf-raw'
=> \
$opt_raw
,
'<>'
=>
sub
{
my
$arg
=
shift
;
if
(
$arg
=~ /\A\+/) {
# less command, push to original command's arguments
goto
PUSH;
}
my
$filename
=
$arg
;
unless
(-f
$filename
) {
warn
"less-pdf-text: No such file or not a file: '$filename'\n"
;
$fail
++;
return
;
}
my
$res
= App::PDFUtils::convert_pdf_to_text(
file
=>
$filename
,
fmt
=> 0,
return_output_file
=> 1,
raw
=>
$opt_raw
,
(
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]"
;
}
$arg
=
$file
;
PUSH:
push
@CLI::MetaUtil::Getopt::Long::Complete::cli_argv
,
$arg
;
},
arg_completion
=>
sub
{
my
%args
=
@_
;
Complete::File::complete_file(
filter
=>
sub
{
$_
[0] =~ /\.pdf\z/i },
word
=>
$args
{word});
},
},
);
exit
1
if
$fail
;
require
File::Which;
require
IPC::System::Options;
IPC::System::Options::
system
(
{
log
=>1},
"less"
,
@ARGV
,
);
# ABSTRACT: Less for seeing plaintext of PDF files
# PODNAME: less-pdf-text
__END__
=pod
=encoding UTF-8
=head1 NAME
less-pdf-text - Less for seeing plaintext of PDF files
=head1 VERSION
This document describes version 0.016 of less-pdf-text (from Perl distribution App-PDFUtils), released on 2024-09-28.
=head1 SYNOPSIS
Use like you would use the Unix command B<less>:
% less-pdf-text [options] <PDF_FILE>...
=head1 DESCRIPTION
This is a wrapper for the Unix command B<less>. It assumes that each input file
is a PDF file and tries to convert the file to text first using B<pdftotext> CLI
utility first before passing it to C<less>.
=head1 OPTIONS
These are options that are interpreted by B<less-pdf-text> and not passed to
B<less>.
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 * --pdf-raw
If set, then C<pdftext> command will be run using the C<-raw> option.
=back
=head1 ENVIRONMENT
=head2 DEBUG
If set to true, do not cleanup temporary directories.
=head1 HOMEPAGE
Please visit the project's homepage at L<https://metacpan.org/release/App-PDFUtils>.
=head1 SOURCE
Source repository is at L<https://github.com/perlancar/perl-App-PDFUtils>.
=head1 SEE ALSO
Unix command B<less>.
B<pdftotext> utility.
=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) 2024, 2023, 2022, 2021, 2020, 2017 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-PDFUtils>
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