=cut
use strict;
+use warnings;
use Getopt::Long;
+use POSIX;
use Locale::PO;
use TmplTokenizer;
use VerboseWarnings;
use vars qw( $pedantic_p );
use vars qw( %text %translation );
use vars qw( $charset_in $charset_out );
+use vars qw( $disable_fuzzy_p );
use vars qw( $verbose_p );
+use vars qw( $po_mode_p );
###############################################################################
if ($attr->{$a}) {
next if $a eq 'content' && $tag ne 'meta';
next if $a eq 'value' && ($tag ne 'input'
- || (ref $attr->{'type'} && $attr->{'type'}->[1] =~ /^(?:hidden|radio)$/)); # FIXME
+ || (ref $attr->{'type'} && $attr->{'type'}->[1] =~ /^(?:hidden|radio|submit)$/)); # FIXME
my($key, $val, $val_orig, $order) = @{$attr->{$a}}; #FIXME
$val = TmplTokenizer::trim $val;
remember( $s, $val ) if $val =~ /\S/s;
}
}
+ } elsif ($s->has_js_data) {
+ for my $t (@{$s->js_data}) {
+ remember( $s, $t->[3] ) if $t->[0]; # FIXME
+ }
}
}
}
sub generate_strings_list () {
# Emit all extracted strings.
for my $t (string_list) {
- printf OUTPUT "%s\n", $t # unless negligible_p($t);
+ printf OUTPUT "%s\n", $t;
}
}
# We don't emit the Plural-Forms header; it's meaningless for us
my $pot_charset = (defined $charset_out? $charset_out: 'CHARSET');
$pot_charset = TmplTokenizer::charset_canon $pot_charset;
+ # Time stamps aren't exactly right semantically. I don't know how to fix it.
+ my $time = POSIX::strftime('%Y-%m-%d %H:%M%z', localtime(time));
+ my $time_pot = $time;
+ my $time_po = $po_mode_p? $time: 'YEAR-MO-DA HO:MI+ZONE';
print OUTPUT <<EOF;
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR THE PACKAGE'S COPYRIGHT HOLDER
# This file is distributed under the same license as the PACKAGE package.
# FIRST AUTHOR <EMAIL\@ADDRESS>, YEAR.
#
+EOF
+ print OUTPUT <<EOF unless $disable_fuzzy_p;
#, fuzzy
+EOF
+ print OUTPUT <<EOF;
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\\n"
-"POT-Creation-Date: 2004-02-05 20:55-0500\\n"
-"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\\n"
+"POT-Creation-Date: $time_pot\\n"
+"PO-Revision-Date: $time_po\\n"
"Last-Translator: FULL NAME <EMAIL\@ADDRESS>\\n"
"Language-Team: LANGUAGE <LL\@li.org>\\n"
"MIME-Version: 1.0\\n"
EOF
my $directory_re = quotemeta("$directory/");
for my $t (string_list) {
- #next if negligible_p($t);
+ if ($text{$t}->[0]->type == TmplTokenType::TEXT_PARAMETRIZED) {
+ my($token, $n) = ($text{$t}->[0], 0);
+ printf OUTPUT "#. For the first occurrence,\n"
+ if @{$text{$t}} > 1 && $token->parameters_and_fields > 0;
+ for my $param ($token->parameters_and_fields) {
+ $n += 1;
+ my $type = $param->type;
+ my $subtype = ($type == TmplTokenType::TAG
+ && $param->string =~ /^<input\b/is?
+ $param->attributes->{'type'}->[1]: undef);
+ my $fmt = TmplTokenizer::_formalize( $param );
+ $fmt =~ s/^%/%$n\$/;
+ if ($type == TmplTokenType::DIRECTIVE) {
+ $type = $param->string =~ /(TMPL_[A-Z]+)+/is? $1: 'ERROR';
+ my $name = $param->string =~ /\bname=(["']?)([^\s"']+)\1/is?
+ $2: undef;
+ printf OUTPUT "#. %s: %s\n", $fmt,
+ "$type" . (defined $name? " name=$name": '');
+ } else {
+ my $name = $param->attributes->{'name'};
+ my $value = $param->attributes->{'value'}
+ unless $subtype =~ /^(?:text)$/;
+ printf OUTPUT "#. %s: %s\n", $fmt, "type=$subtype"
+ . (defined $name? " name=$name->[1]": '')
+ . (defined $value? " value=$value->[1]": '');
+ }
+ }
+ } elsif ($text{$t}->[0]->type == TmplTokenType::TAG) {
+ my($token) = ($text{$t}->[0]);
+ printf OUTPUT "#. For the first occurrence,\n"
+ if @{$text{$t}} > 1 && $token->parameters_and_fields > 0;
+ if ($token->string =~ /^<meta\b/is) {
+ my $type = $token->attributes->{'http-equiv'}->[1];
+ print OUTPUT "#. META http-equiv=$type\n" if defined $type;
+ } elsif ($token->string =~ /^<([a-z0-9]+)/is) {
+ my $tag = uc($1);
+ my $type = (lc($tag) eq 'input'?
+ $token->attributes->{'type'}: undef);
+ my $name = $token->attributes->{'name'};
+ printf OUTPUT "#. %s\n", $tag
+ . (defined $type? " type=$type->[1]": '')
+ . (defined $name? " name=$name->[1]": '');
+ }
+ } elsif ($text{$t}->[0]->has_js_data) {
+ printf OUTPUT "#. For the first occurrence,\n" if @{$text{$t}} > 1;
+ printf OUTPUT "#. SCRIPT\n";
+ }
my $cformat_p;
for my $token (@{$text{$t}}) {
my $pathname = $token->pathname;
}
# The following assumption is correct; that's what HTML::Template assumes
if (!defined $charset_in) {
- $charset_in = $charset_out = TmplTokenizer::charset_canon 'iso8859-1';
+ $charset_in = $charset_out = TmplTokenizer::charset_canon 'utf-8';
warn "Warning: Can't determine original templates' charset, defaulting to $charset_in\n";
}
}
HTML::Template options:
-a, --extract-all Extract all strings
--pedantic-warnings Issue warnings even for detected problems
- which are likely to be harmless
+ which are likely to be harmless
Output details:
-s, --sort-output generate sorted output
Informative output:
--help Display this help and exit
+
+Try `perldoc $0' for perhaps more information.
EOF
exit($exitcode);
}
'charset=s' => sub { $charset_in = $charset_out = $_[1] }, # INTERNAL
'convert-from=s' => \$convert_from,
'D|directory=s' => \$directory,
+ 'disable-fuzzy' => \$disable_fuzzy_p, # INTERNAL
'f|files-from=s' => \$files_from,
'I|input-charset=s' => \$charset_in, # INTERNAL
'pedantic-warnings|pedantic' => sub { $pedantic_p = 1 },
'O|output-charset=s' => \$charset_out, # INTERNAL
'output|o=s' => \$output,
+ 'po-mode' => \$po_mode_p, # INTERNAL
's|sort-output' => sub { $sort = 's' },
'F|sort-by-file' => sub { $sort = 'F' },
'v|verbose' => \$verbose_p,
open(INPUT, "<$files_from") || die "$files_from: $!\n";
while (<INPUT>) {
chomp;
- my $h = TmplTokenizer->new( "$directory/$_" );
+ my $input = /^\//? $_: "$directory/$_";
+ my $h = TmplTokenizer->new( $input );
$h->set_allow_cformat( 1 );
- VerboseWarnings::set_input_file_name "$directory/$_";
- print STDERR "$0: Processing file \"$directory/$_\"\n" if $verbose_p;
+ VerboseWarnings::set_input_file_name $input;
+ print STDERR "$0: Processing file \"$input\"\n" if $verbose_p;
text_extract( $h );
}
close INPUT;
=item -
-(Future goal)
Translation to non-English-like languages with different word
order: gettext's c-format strings can theoretically be
emulated if we are able to do some analysis on the .tmpl input
=back
-Note that this script is experimental and should still be
-considered unstable.
+This script has already been in use for over a year and should
+be reasonable stable. Nevertheless, it is still somewhat
+experimental and there are still some issues.
Please refer to the explanation in tmpl_process3 for further
details.
If you want to generate GNOME-style POTFILES.in files, such
files (passed to -f) can be generated thus:
- (cd ../.. && find koha-tmpl/opac-tmpl/default/en
+ (cd ../.. && find koha-tmpl/opac-tmpl/default/en \
-name \*.inc -o -name \*.tmpl) > opac/POTFILES.in
- (cd ../.. && find koha-tmpl/intranet-tmpl/default/en
+ (cd ../.. && find koha-tmpl/intranet-tmpl/default/en \
-name \*.inc -o -name \*.tmpl) > intranet/POTFILES.in
This is, however, quite pointless, because the "create" and
"update" actions have already been implemented in tmpl_process3.pl.
+=head2 Strings inside JavaScript
+
+In the SCRIPT elements, the script will attempt to scan for
+_("I<string literal>") patterns, and extract the I<string literal>
+as a translatable string.
+
+Note that the C-like _(...) notation is required.
+
+The JavaScript must actually define a _ function
+so that the code remains correct JavaScript.
+A suitable definition of such a function can be
+
+ function _(s) { return s } // dummy function for gettext
+
=head1 SEE ALSO
-tmpl_process.pl,
+tmpl_process3.pl,
xgettext(1),
Locale::PO(3),
translator_doc.txt
strings inside the generated PO file spuriously moving about
when tmpl_process3.pl calls msgmerge(1) to update the PO file.
+If a Javascript string has leading spaces, it will
+generate strings with spurious leading spaces,
+leading to failure to match the strings when actually generating
+translated files.
+
=cut