=cut
use strict;
+use warnings;
use Getopt::Long;
use POSIX;
use Locale::PO;
my($token, $string) = @_;
# If we determine that the string is negligible, don't bother to remember
unless (string_negligible_p( $string ) || token_negligible_p( $token )) {
- my $key = TmplTokenizer::string_canon( $string );
- $text{$key} = [] unless defined $text{$key};
- push @{$text{$key}}, $token;
+ my $key = TmplTokenizer::string_canon( $string );
+ $text{$key} = [] unless defined $text{$key};
+ push @{$text{$key}}, $token;
}
}
return @t;
}
-###############################################################################
+ ###############################################################################
sub text_extract (*) {
my($h) = @_;
for (;;) {
- my $s = TmplTokenizer::next_token $h;
- last unless defined $s;
- my($kind, $t, $attr) = ($s->type, $s->string, $s->attributes);
- if ($kind eq TmplTokenType::TEXT) {
- remember( $s, $t ) if $t =~ /\S/s;
- } elsif ($kind eq TmplTokenType::TEXT_PARAMETRIZED) {
- remember( $s, $s->form ) if $s->form =~ /\S/s;
- } elsif ($kind eq TmplTokenType::TAG && %$attr) {
- # value [tag=input], meta
- my $tag = lc($1) if $t =~ /^<(\S+)/s;
- for my $a ('alt', 'content', 'title', 'value') {
- if ($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
- my($key, $val, $val_orig, $order) = @{$attr->{$a}}; #FIXME
- $val = TmplTokenizer::trim $val;
- remember( $s, $val ) if $val =~ /\S/s;
- }
- }
- }
+ my $s = TmplTokenizer::next_token $h;
+ last unless defined $s;
+ my($kind, $t, $attr) = ($s->type, $s->string, $s->attributes);
+ if ($kind eq TmplTokenType::TEXT) {
+ remember( $s, $t ) if $t =~ /\S/s;
+ } elsif ($kind eq TmplTokenType::TEXT_PARAMETRIZED) {
+ remember( $s, $s->form ) if $s->form =~ /\S/s;
+ } elsif ($kind eq TmplTokenType::TAG && %$attr) {
+ # value [tag=input], meta
+ my $tag = lc($1) if $t =~ /^<(\S+)/s;
+ for my $a ('alt', 'content', 'title', 'value','label') {
+ if ($attr->{$a}) {
+ next if $a eq 'label' && $tag ne 'optgroup';
+ next if $a eq 'content' && $tag ne 'meta';
+ next if $a eq 'value' && ($tag ne 'input'
+ || (ref $attr->{'type'} && $attr->{'type'}->[1] =~ /^(?:hidden|radio|checkbox)$/)); # 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
+ }
+ }
}
}
. (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;
$pathname =~ s/^$directory_re//os;
+ $pathname =~ s/^.*\/koha-tmpl\/(.*)$/$1/;
printf OUTPUT "#: %s:%d\n", $pathname, $token->line_number
if defined $pathname && defined $token->line_number;
$cformat_p = 1 if $token->type == TmplTokenType::TEXT_PARAMETRIZED;
}
# 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";
}
}
=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.
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