po4a 0.52-1 / usr / bin / po4a-gettextize

#! /usr/bin/env perl
eval 'exec perl -S $0 ${1+"$@"}'
    if $running_under_some_shell;

# po4a-gettextize -- convert an original file to a PO file
#
# Copyright 2002-2012 by SPI, inc.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms of GPL (see COPYING).

=encoding UTF-8

=head1 NAME

po4a-gettextize - convert an original file (and its translation) to a PO file

=head1 SYNOPSIS

B<po4a-gettextize> B<-f> I<fmt> B<-m> I<master.doc> [B<-l> I<XX.doc>] B<-p> I<XX.po>

(I<XX.po> is the output, all others are inputs)

=head1 DESCRIPTION

The po4a (PO for anything) project goal is to ease translations (and more
interestingly, the maintenance of translations) using gettext tools on
areas where they were not expected like documentation.

The B<po4a-gettextize> script is in charge of converting documentation
files to PO files.  If you start a new translation, B<po4a-gettextize>
will extract the translatable strings from the documentation file and
write a POT file from it.

If you already have a translated file, B<po4a-gettextize> will try to
extract the translations it contains and put them in place in the written
PO file. Be warned that very few intelligence is used in this process: the
Nth string of the translated file is supposed to be the translation of the
Nth string in the original. If it's not the case, you're dead. That's why
it is very important that both files share exactly the same structure.

However, B<po4a-gettextize> will diagnose your death by detecting any
desynchronisation between files, and reporting where they occur. In that
case, you should edit manually the files to solve the reported
disparity. Even if no error were reported, you should check carefully that the
generated PO file is correct (i.e. that each msgstr is the translation of
the associated msgid, and not the one before or after).

Even if the script manages to do its job without any apparent problem, it still
marks all extracted translations as fuzzy, to make sure that the translator
will have a look at them, and detect any remaining problem.

If the master document has non-ASCII characters, the new generated PO file
will be in UTF-8, in order to allow non-standard characters in a culture
independent way. Else (if the master document is completely in ASCII), the
generated PO will use the encoding of the translated input document.

=head1 OPTIONS

=over 4

=item B<-f>, B<--format>

Format of the documentation you want to handle. Use the B<--help-format>
option to see the list of available formats.

=item B<-m>, B<--master>

File containing the master document to translate. You can use this option
multiple times if you want to gettextize multiple documents.

=item B<-M>, B<--master-charset>

Charset of the file containing the document to translate.

=item B<-l>, B<--localized>

File containing the localized (translated) document. If you provided
multiple master files, you may wish to provide multiple localized file by
using this option more than once.

=item B<-L>, B<--localized-charset>

Charset of the file containing the localized document.

=item B<-p>, B<--po>

File where the message catalog should be written. If not given, the message
catalog will be written to the standard output.

=item B<-o>, B<--option>

Extra option(s) to pass to the format plugin. Specify each option in the
'I<name>B<=>I<value>' format. See the documentation of each plugin for more
information about the valid options and their meanings.

=item B<-h>, B<--help>

Show a short help message.

=item B<--help-format>

List the documentation formats understood by po4a.

=item B<-V>, B<--version>

Display the version of the script and exit.

=item B<-v>, B<--verbose>

Increase the verbosity of the program.

=item B<-d>, B<--debug>

Output some debugging information.

=item B<--msgid-bugs-address> I<email@address>

Set the report address for msgid bugs. By default, the created POT files
have no Report-Msgid-Bugs-To fields.

=item B<--copyright-holder> I<string>

Set the copyright holder in the POT header. The default value is
"Free Software Foundation, Inc."

=item B<--package-name> I<string>

Set the package name for the POT header. The default is "PACKAGE".

=item B<--package-version> I<string>

Set the package version for the POT header. The default is "VERSION".

=back

=head1 SEE ALSO

L<po4a-normalize(1)>,
L<po4a-translate(1)>,
L<po4a-updatepo(1)>,
L<po4a(7)>

=head1 AUTHORS

 Denis Barbier <barbier@linuxfr.org>
 Nicolas François <nicolas.francois@centraliens.net>
 Martin Quinson (mquinson#debian.org)

=head1 COPYRIGHT AND LICENSE

Copyright 2002-2012 by SPI, inc.

This program is free software; you may redistribute it and/or modify it
under the terms of GPL (see the COPYING file).

=cut

use 5.006;
use strict;
use warnings;

use Getopt::Long qw(GetOptions);

use Locale::Po4a::Chooser;
use Locale::Po4a::TransTractor;
use Locale::Po4a::Common;

use Pod::Usage qw(pod2usage);

Locale::Po4a::Common::textdomain('po4a');


sub show_version {
    Locale::Po4a::Common::show_version("po4a-gettextize");
    exit 0;
}

my %opts = (
    "verbose"             => 0,
    "debug"               => 0,
    "copyright-holder"    => undef,
    "msgid-bugs-address"  => undef,
    "package-name"        => undef,
    "package-version"     => undef);

my ($pofile)=('-');
my (@masterfile,@locfile,$help_fmt,$help,$type,@options);
my ($mastchar,$locchar);
Getopt::Long::config('bundling', 'no_getopt_compat', 'no_auto_abbrev');
GetOptions(
        'help|h'        => \$help,
        'help-format'   => \$help_fmt,

        'master|m=s'    => \@masterfile,
        'localized|l=s' => \@locfile,
        'po|p=s'        => \$pofile,
        'format|f=s'    => \$type,

        'master-charset|M=s'    => \$mastchar,
        'localized-charset|L=s' => \$locchar,

        'option|o=s'            => \@options,

        'copyright-holder=s'    => \$opts{"copyright-holder"},
        'msgid-bugs-address=s'  => \$opts{"msgid-bugs-address"},
        'package-name=s'        => \$opts{"package-name"},
        'package-version=s'     => \$opts{"package-version"},

        'verbose|v'             => \$opts{"verbose"},
        'debug|d'               => \$opts{"debug"},
        'version|V'             => \&show_version
) or pod2usage();

# Argument check
$help && pod2usage (-verbose => 1, -exitval => 0);
$help_fmt && Locale::Po4a::Chooser::list(0);
pod2usage () if (scalar @ARGV > 1) || (scalar @masterfile < 1);

foreach (@options) {
    if (m/^([^=]*)=(.*)$/) {
        $opts{$1}="$2";
    } else {
        $opts{$_}=1;
    }
}
# Check file existence
foreach my $file (@masterfile, @locfile) {
    $file eq '-' || -e $file || die wrap_msg(gettext("File %s does not exist."), $file);
}

# Declare the TransTractor parsers
my ($mastertt,$transtt)=(Locale::Po4a::Chooser::new($type,%opts),
                         Locale::Po4a::Chooser::new($type,%opts));

# Parse master file forcing conversion to utf if it's not in ascii
foreach my $file (@masterfile) {
    $mastertt->read($file);
}
$mastertt->{TT}{utf_mode} = 1;
if ($mastertt->{TT}{ascii_input}) {
    $mastertt->detected_charset('ascii');
} elsif (defined($mastchar)) {
    $mastertt->detected_charset($mastchar);
    $mastertt->{TT}{po_in}->set_charset($mastchar);
}
$mastertt->parse;


unless (scalar @locfile >= 1) {
  # Ok, outputing the pot extracted from original is enough
  $mastertt->writepo($pofile);
} else {
  # We have to merge two transtractor files

  foreach my $file (@locfile) {
      $transtt->read($file);
  }
  # We force the conversion to utf if the master document wasn't in ascii
  $transtt->{TT}{utf_mode} = !$mastertt->{TT}{ascii_input};
  $transtt->detected_charset($locchar);
  $transtt->{TT}{po_in}->set_charset($locchar);
  $transtt->parse;

  my $mergedpo = Locale::Po4a::Po->gettextize($mastertt->getpoout(),
                                              $transtt->getpoout());

  $mergedpo->write($pofile);
}

__END__