App-PDFUtils
view release on metacpan or search on metacpan
lib/App/PDFUtils.pm view on Meta::CPAN
'x.element_completion' => [filename => {filter => sub { /\.pdf$/i }}],
},
);
our %argspec0_file = (
file => {
summary => 'Input file',
schema => ['filename*'],
req => 1,
pos => 0,
'x.completion' => [filename => {filter => sub { /\.pdf$/i }}],
},
);
our %argspecopt_quiet = (
quiet => {
schema => ['bool*'],
cmdline_aliases => {q=>{}},
},
);
our %argspecopt1_output = (
output => {
summary => 'Output path',
schema => ['filename*'],
pos => 1,
},
);
our %argspecopt_overwrite = (
overwrite => {
schema => 'bool*',
cmdline_aliases => {O=>{}},
},
);
our %argspecopt_return_output_file = (
return_output_file => {
summary => 'Return the path of output file instead',
schema => 'bool*',
description => <<'MARKDOWN',
This is useful when you do not specify an output file but do not want to show
the converted document to stdout, but instead want to get the path to a
temporary output file.
MARKDOWN
},
);
$SPEC{add_pdf_password} = {
v => 1.1,
summary => 'Password-protect PDF files',
description => <<'MARKDOWN',
This program is a wrapper for <prog:qpdf> to password-protect PDF files
(in-place). This is the counterpart for <prog:remove-pdf-password>. Why use this
wrapper instead of **qpdf** directly? This wrapper offers configuration file
support, where you can put the password(s) you want to use there. The wrapper
also offers multiple file support and additional options, e.g. whether to create
backup.
MARKDOWN
args => {
%argspec0_files,
password => {
schema => ['str*', min_len=>1],
req => 1,
},
backup => {
summary => 'Whether to backup the original file to ORIG~',
schema => 'bool*',
default => 1,
},
# XXX key_length (see qpdf, but when 256 can't be opened by evince)
# XXX other options (see qpdf)
},
deps => {
prog => 'qpdf',
},
links => [
{url => 'prog:remove-pdf-password'},
],
};
sub add_pdf_password {
#require File::Temp;
require IPC::System::Options;
#require Proc::ChildError;
#require Path::Tiny;
my %args = @_;
my $envres = envresmulti();
FILE:
for my $f (@{ $args{files} }) {
unless (-f $f) {
$envres->add_result(404, "File not found", {item_id=>$f});
next FILE;
}
# XXX test that tempfile doesn't yet exist. but actually we can't avoid
# race condition because qpdf is another process
(my $tempf = $f) =~ s/\.pdf$/".tmp_" . int(rand()*900_000 + 100_000) . ".pdf"/ei
or do {
$envres->add_result(412, "Cannot set temporary name for $f");
next FILE;
};
my $decrypted;
my ($stdout, $stderr);
IPC::System::Options::system(
{log => 1, capture_stdout => \$stdout, capture_stderr => \$stderr},
"qpdf", "--encrypt", $args{password}, $args{password}, 128, "--", $f, $tempf);
my $err = $?;# ? Proc::ChildError::explain_child_error() : '';
if ($err && $stderr =~ /: invalid password$/) {
$envres->add_result(412, "File already encrypted", {item_id=>$f});
next FILE;
} elsif ($err) {
$stderr =~ s/\R//g;
$envres->add_result(500, $stderr, {item_id=>$f});
next FILE;
}
BACKUP:
{
last unless $args{backup};
unless (rename $f, "$f~") {
warn "Can't backup original '$f' to '$f~': $!, skipped backup\n";
last;
};
}
unless (rename $tempf, $f) {
$envres->add_result(500, "Can't rename $tempf to $f: $!", {item_id=>$f});
next FILE;
}
$envres->add_result(200, "OK", {item_id=>$f});
}
$envres->as_struct;
}
$SPEC{remove_pdf_password} = {
v => 1.1,
summary => 'Remove password from PDF files',
description => <<'MARKDOWN',
This program is a wrapper for <prog:qpdf> to remove passwords from PDF files
(in-place).
The motivation for this wrapper is the increasing occurence of financial
institutions sending financial statements or documents in the format of
password-protected PDF file. This is annoying when we want to archive the file
or use it in an organization because we have to remember different passwords for
different financial institutions and re-enter the password everytime we want to
use the file. (The banks could've sent the PDF in a password-protected .zip, or
use PGP-encrypted email, but I digress.)
Compared to using **qpdf** directly, this wrapper offers some additional
features/options and convenience, for example: multiple file support, multiple
password matching attempt, configuration file, option whether you want backup,
etc.
You can provide the passwords to be tried in a configuration file,
`~/remove-pdf-password.conf`, e.g.:
passwords = pass1
passwords = pass2
passwords = pass3
or:
passwords = ["pass1", "pass2", "pass3"]
MARKDOWN
args => {
%argspec0_files,
passwords => {
schema => ['array*', of=>['str*', min_len=>1], min_len=>1],
},
backup => {
summary => 'Whether to backup the original file to ORIG~',
schema => 'bool*',
default => 1,
},
},
deps => {
prog => 'qpdf',
},
links => [
{url => 'prog:add-pdf-password'},
],
};
sub remove_pdf_password {
#require File::Temp;
require IPC::System::Options;
#require Proc::ChildError;
#require Path::Tiny;
my %args = @_;
my $envres = envresmulti();
FILE:
for my $f (@{ $args{files} }) {
unless (-f $f) {
$envres->add_result(404, "File not found", {item_id=>$f});
next FILE;
}
# XXX test that tempfile doesn't yet exist. but actually we can't avoid
# race condition because qpdf is another process
(my $tempf = $f) =~ s/\.pdf$/".tmp_" . int(rand()*900_000 + 100_000) . ".pdf"/ei
or do {
$envres->add_result(412, "Cannot set temporary name for $f");
next FILE;
};
my $decrypted;
PASSWORD:
for my $p (@{ $args{passwords} }) {
my ($stdout, $stderr);
IPC::System::Options::system(
{log => 1, fail_log_level => 'info', capture_stdout => \$stdout, capture_stderr => \$stderr},
"qpdf", "--password=$p", "--decrypt", $f, $tempf);
my $err = $?;# ? Proc::ChildError::explain_child_error() : '';
if ($err && $stderr =~ /: invalid password$/) {
#$log->tracef("D1");
unlink $tempf; # just to make sure
next PASSWORD;
} elsif ($err) {
#$log->tracef("D2");
$stderr =~ s/\R//g;
$envres->add_result(500, $stderr, {item_id=>$f});
next FILE;
}
last;
}
unless (-f $tempf) {
$envres->add_result(412, "No passwords can be successfully used on $f", {item_id=>$f});
next FILE;
}
BACKUP:
{
last unless $args{backup};
unless (rename $f, "$f~") {
warn "Can't backup original '$f' to '$f~': $!, skipped backup\n";
last;
};
}
unless (rename $tempf, $f) {
$envres->add_result(500, "Can't rename $tempf to $f: $!", {item_id=>$f});
next FILE;
}
$envres->add_result(200, "OK", {item_id=>$f});
}
$envres->as_struct;
}
$SPEC{pdf_has_password} = {
v => 1.1,
summary => 'Check if PDF file has password',
description => <<'MARKDOWN',
This is a wrapper for `qpdf --check`. The wrapper offers additional options like
`--quiet``.
MARKDOWN
args => {
%argspec0_file,
%argspecopt_quiet,
},
deps => {
prog => 'qpdf',
},
};
sub pdf_has_password {
require IPC::System::Options;
my %args = @_;
my ($stdout, $stderr);
IPC::System::Options::system(
{log => 1, fail_log_level => 'info', capture_stdout => \$stdout, capture_stderr => \$stderr},
"qpdf", "--check", $args{file});
my $has_password;
if ($? && $stderr =~ /: invalid password/) {
$has_password = 1;
} elsif (!$? && $stdout =~ /is not encrypted/) {
$has_password = 0;
}
[200, "OK",
$args{quiet} ? "" : ($has_password ? "PDF has password" : defined($has_password) ? "PDF DOES NOT have password" : "CANNOT determine if PDF has password"),
{
'cmdline.exit_code' => $has_password ? 0 : defined($has_password) ? 1 : 2,
}];
}
$SPEC{convert_pdf_to_text} = {
v => 1.1,
summary => 'Convert PDF file to text',
description => <<'MARKDOWN',
This utility uses one of the following backends:
lib/App/PDFUtils.pm view on Meta::CPAN
1;
# ABSTRACT: Command-line utilities related to PDF files
__END__
=pod
=encoding UTF-8
=head1 NAME
App::PDFUtils - Command-line utilities related to PDF files
=head1 VERSION
This document describes version 0.017 of App::PDFUtils (from Perl distribution App-PDFUtils), released on 2026-02-02.
=head1 SYNOPSIS
=head1 DESCRIPTION
This distribution provides tha following command-line utilities related to PDF
files:
=over
=item 1. L<add-pdf-password>
=item 2. L<compress-pdf>
=item 3. L<grep-from-pdf>
=item 4. L<less-pdf-text>
=item 5. L<pdf-has-password>
=item 6. L<pdfgrep>
=item 7. L<pdfnopass>
=item 8. L<remove-pdf-password>
=back
=head1 FUNCTIONS
=head2 add_pdf_password
Usage:
add_pdf_password(%args) -> [$status_code, $reason, $payload, \%result_meta]
Password-protect PDF files.
This program is a wrapper for L<qpdf> to password-protect PDF files
(in-place). This is the counterpart for L<remove-pdf-password>. Why use this
wrapper instead of B<qpdf> directly? This wrapper offers configuration file
support, where you can put the password(s) you want to use there. The wrapper
also offers multiple file support and additional options, e.g. whether to create
backup.
This function is not exported.
Arguments ('*' denotes required arguments):
=over 4
=item * B<backup> => I<bool> (default: 1)
Whether to backup the original file to ORIG~.
=item * B<files>* => I<array[filename]>
(No description)
=item * B<password>* => I<str>
(No description)
=back
Returns an enveloped result (an array).
First element ($status_code) is an integer containing HTTP-like status code
(200 means OK, 4xx caller error, 5xx function error). Second element
($reason) is a string containing error message, or something like "OK" if status is
200. Third element ($payload) is the actual result, but usually not present when enveloped result is an error response ($status_code is not 2xx). Fourth
element (%result_meta) is called result metadata and is optional, a hash
that contains extra information, much like how HTTP response headers provide additional metadata.
Return value: (any)
=head2 compress_pdf
Usage:
compress_pdf(%args) -> [$status_code, $reason, $payload, \%result_meta]
Make PDF smaller.
This utility is a wrapper for L<gs> (GhostScript) and is equivalent to the
following command:
% gs -sDEVICE=pdfwrite -dCompatibilityLevel=1.4 -dPDFSETTINGS=/screen -dNOPAUSE -dQUIET -dBATCH -sOutputFile=output.pdf input.pdf
This wrapper offers support for multiple files and automatically naming output
C<INPUT.compressed.pdf> by default.
This function is not exported.
Arguments ('*' denotes required arguments):
=over 4
=item * B<files>* => I<array[filename]>
(No description)
=item * B<overwrite> => I<bool>
(No description)
=item * B<setting> => I<str> (default: "ebook")
(No description)
lib/App/PDFUtils.pm view on Meta::CPAN
Usage:
pdf_has_password(%args) -> [$status_code, $reason, $payload, \%result_meta]
Check if PDF file has password.
This is a wrapper for C<qpdf --check>. The wrapper offers additional options like
`--quiet``.
This function is not exported.
Arguments ('*' denotes required arguments):
=over 4
=item * B<file>* => I<filename>
Input file.
=item * B<quiet> => I<bool>
(No description)
=back
Returns an enveloped result (an array).
First element ($status_code) is an integer containing HTTP-like status code
(200 means OK, 4xx caller error, 5xx function error). Second element
($reason) is a string containing error message, or something like "OK" if status is
200. Third element ($payload) is the actual result, but usually not present when enveloped result is an error response ($status_code is not 2xx). Fourth
element (%result_meta) is called result metadata and is optional, a hash
that contains extra information, much like how HTTP response headers provide additional metadata.
Return value: (any)
=head2 remove_pdf_password
Usage:
remove_pdf_password(%args) -> [$status_code, $reason, $payload, \%result_meta]
Remove password from PDF files.
This program is a wrapper for L<qpdf> to remove passwords from PDF files
(in-place).
The motivation for this wrapper is the increasing occurence of financial
institutions sending financial statements or documents in the format of
password-protected PDF file. This is annoying when we want to archive the file
or use it in an organization because we have to remember different passwords for
different financial institutions and re-enter the password everytime we want to
use the file. (The banks could've sent the PDF in a password-protected .zip, or
use PGP-encrypted email, but I digress.)
Compared to using B<qpdf> directly, this wrapper offers some additional
features/options and convenience, for example: multiple file support, multiple
password matching attempt, configuration file, option whether you want backup,
etc.
You can provide the passwords to be tried in a configuration file,
C<~/remove-pdf-password.conf>, e.g.:
passwords = pass1
passwords = pass2
passwords = pass3
or:
passwords = ["pass1", "pass2", "pass3"]
This function is not exported.
Arguments ('*' denotes required arguments):
=over 4
=item * B<backup> => I<bool> (default: 1)
Whether to backup the original file to ORIG~.
=item * B<files>* => I<array[filename]>
(No description)
=item * B<passwords> => I<array[str]>
(No description)
=back
Returns an enveloped result (an array).
First element ($status_code) is an integer containing HTTP-like status code
(200 means OK, 4xx caller error, 5xx function error). Second element
($reason) is a string containing error message, or something like "OK" if status is
200. Third element ($payload) is the actual result, but usually not present when enveloped result is an error response ($status_code is not 2xx). Fourth
element (%result_meta) is called result metadata and is optional, a hash
that contains extra information, much like how HTTP response headers provide additional metadata.
Return value: (any)
=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
L<diff-pdf-text> from L<App::DiffPDFText>.
=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) 2026 by perlancar <perlancar@cpan.org>.
( run in 3.963 seconds using v1.01-cache-2.11-cpan-df04353d9ac )