EVOLUTION-MANAGER

Edit File: Messages.pm

# vim: set autoindent shiftwidth=4 tabstop=4:
# $Id$

# This program is free software; you can redistribute it and/or modify it
# under the terms of the GNU Library General Public License as published
# by the Free Software Foundation; either version 2, or (at your option)
# any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# Library General Public License for more details.

# You should have received a copy of the GNU Library General Public 
# License along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, 
# USA.

package Locale::Messages;

use strict;

use vars qw ($package @EXPORT_OK %EXPORT_TAGS @ISA $VERSION);

$VERSION = '1.20';

# Try to load the C version first.
$package = 'gettext_xs';
my $can_xs = 1;
eval <<'EOF';
require Locale::gettext_xs; 
my $version = Locale::gettext_xs::__gettext_xs_version();
die "Version: $version mismatch (1.20 vs. $version)" unless $version eq '1.20';
EOF
if ($@) {
    $package = 'gettext_pp';
	undef $can_xs;
    require Locale::gettext_pp;
}
		
require Exporter;
@ISA = qw (Exporter);
%EXPORT_TAGS = (locale_h => [ qw (gettext
				  dgettext
				  dcgettext
				  ngettext
				  dngettext
				  dcngettext
				  pgettext
				  dpgettext
				  dcpgettext
				  npgettext
				  dnpgettext
				  dcnpgettext
				  textdomain
				  bindtextdomain
				  bind_textdomain_codeset
				  )
			       ],
		 libintl_h => [ qw (LC_CTYPE
				    LC_NUMERIC
				    LC_TIME
				    LC_COLLATE
				    LC_MONETARY
				    LC_MESSAGES
				    LC_ALL)
				],
		 );

@EXPORT_OK = qw (select_package
				 turn_utf_8_on
				 turn_utf_8_off
				 gettext
				 dgettext
				 dcgettext
				 ngettext
				 dngettext
				 dcngettext
				 pgettext
				 dpgettext
				 dcpgettext
				 npgettext
				 dnpgettext
				 dcnpgettext
				 textdomain
				 bindtextdomain
				 bind_textdomain_codeset
				 bind_textdomain_filter
                 nl_putenv
				 LC_CTYPE
				 LC_NUMERIC
				 LC_TIME
				 LC_COLLATE
				 LC_MONETARY
				 LC_MESSAGES
				 LC_ALL);

BEGIN {
	my ($has_encode, $has_bytes);
	
	if ($] >= 5.006) {
		unless (defined $has_encode) {
			eval "require Encode";
			$has_encode = !$@;
		}

unless ($has_encode || defined $has_bytes) {
			eval "use bytes";
			$has_bytes = !$@;
		}
	}

# Turn the UTF-8 flag on or off unconditionally.  The prototypes
	# allow an optional second parameter, so that you can use the
	# functions as callbacks to bind_textdomain_filter.
	if ($has_encode) {
		eval <<'EOF';
sub turn_utf_8_on($;$)
{
	Encode::_utf8_on ($_[0]);
	return $_[0];
}

sub turn_utf_8_off($;$)
{
	Encode::_utf8_off ($_[0]);
	return $_[0];
}

EOF
	} elsif ($has_bytes) {
		eval <<'EOF';
sub turn_utf_8_on($;$)
{
	$_[0] = pack "U0C*", unpack "C*", $_[0];
}

sub turn_utf_8_off($;$)
{
	use bytes;
	$_[0] = join "", split //, $_[0];
}

EOF
	} else {
		eval <<'EOF';
sub turn_utf_8_on($;$)
{
	return $_[0];
}

sub turn_utf_8_off($;$)
{
	return $_[0];
}

EOF
	}
}

# The textdomain could be undef.  We avoid a warning by specifying
# a filter for the undefined textdomain.
my %filters = (
			   undef => \&turn_utf_8_off,
			   );

sub select_package
{
	my ($pkg, $compatibility) = @_;

# Compatibility quirk for a bug pre 1.17:
	if (__PACKAGE__ eq $pkg && defined $compatibility) {
		$pkg = $compatibility;
	}

if (!$can_xs || (defined $pkg && 'gettext_pp' eq $pkg)) {
		require Locale::gettext_pp;
		$package = 'gettext_pp';
	} else {
		eval "require Locale::gettext_xs";
		$package = 'gettext_xs' unless $@;
	}

return $package;
}

sub bind_textdomain_filter($;$$)
{
	my ($textdomain, $coderef, $data) = @_;

$filters{$textdomain} = [ $coderef, $data ];

return 1;
}

sub textdomain(;$)
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::textdomain :
	&Locale::gettext_pp::textdomain;
}

sub bindtextdomain($;$)
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::bindtextdomain :
	&Locale::gettext_pp::bindtextdomain;
}

sub bind_textdomain_codeset($;$)
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::bind_textdomain_codeset :
	&Locale::gettext_pp::bind_textdomain_codeset;
}

sub gettext($)
{
	my $textdomain = textdomain;
	$filters{$textdomain} ||= [ \&turn_utf_8_off ];
	my $cb = $filters{$textdomain};

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::gettext :
		     &Locale::gettext_pp::gettext, $cb->[1]);
}

sub dgettext($$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dgettext :
		     &Locale::gettext_pp::dgettext, $cb->[1]);
}

sub dcgettext($$$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dcgettext :
		     &Locale::gettext_pp::dcgettext, $cb->[1]);
}

sub ngettext($$$)
{
	my $textdomain = textdomain;
	$filters{$textdomain} ||= [ \&turn_utf_8_off ];
	my $cb = $filters{$textdomain};

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::ngettext :
		     &Locale::gettext_pp::ngettext, $cb->[1]);
}

sub dngettext($$$$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dngettext :
		     &Locale::gettext_pp::dngettext, $cb->[1]);
}

sub dcngettext($$$$$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dcngettext :
		     &Locale::gettext_pp::dcngettext, $cb->[1]);
}

###
sub pgettext($$)
{
	my $textdomain = textdomain;
	$filters{$textdomain} ||= [ \&turn_utf_8_off ];
	my $cb = $filters{$textdomain};

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::pgettext :
		     &Locale::gettext_pp::pgettext, $cb->[1]);
}

sub dpgettext($$$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dpgettext :
		     &Locale::gettext_pp::dpgettext, $cb->[1]);
}

sub dcpgettext($$$$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dcpgettext :
		     &Locale::gettext_pp::dcpgettext, $cb->[1]);
}

sub npgettext($$$$)
{
	my $textdomain = textdomain;
	$filters{$textdomain} ||= [ \&turn_utf_8_off ];
	my $cb = $filters{$textdomain};

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::npgettext :
		     &Locale::gettext_pp::npgettext, $cb->[1]);
}

sub dnpgettext($$$$$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dnpgettext :
		     &Locale::gettext_pp::dnpgettext, $cb->[1]);
}

sub dcnpgettext($$$$$$)
{
	my $cb = $filters{$_[0]} ||= [ \&turn_utf_8_off ];

$cb->[0] ('gettext_xs' eq $package ?
		     &Locale::gettext_xs::dcnpgettext :
		     &Locale::gettext_pp::dcnpgettext, $cb->[1]);
}

sub nl_putenv($)
{
    'gettext_xs' eq $package ?
		     &Locale::gettext_xs::nl_putenv :
		     &Locale::gettext_pp::nl_putenv;
}

sub LC_NUMERIC
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::LC_NUMERIC :
	&Locale::gettext_pp::LC_NUMERIC;
}

sub LC_CTYPE
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::LC_CTYPE :
	&Locale::gettext_pp::LC_CTYPE;
}

sub LC_TIME
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::LC_TIME :
	&Locale::gettext_pp::LC_TIME;
}

sub LC_COLLATE
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::LC_COLLATE :
	&Locale::gettext_pp::LC_COLLATE;
}

sub LC_MONETARY
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::LC_MONETARY :
	&Locale::gettext_pp::LC_MONETARY;
}

sub LC_MESSAGES
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::LC_MESSAGES :
	&Locale::gettext_pp::LC_MESSAGES;
}

sub LC_ALL
{
    'gettext_xs' eq $package ?
	&Locale::gettext_xs::LC_ALL :
	&Locale::gettext_pp::LC_ALL;
}

__END__

=head1 NAME

Locale::Messages - Gettext Like Message Retrieval

=head1 SYNOPSIS

use Locale::Messages (:locale_h :libintl_h);

gettext $msgid;
 dgettext $textdomain, $msgid;
 dcgettext $textdomain, $msgid, LC_MESSAGES;
 ngettext $msgid, $msgid_plural, $count;
 dngettext $textdomain, $msgid, $msgid_plural, $count;
 dcngettext $textdomain, $msgid, $msgid_plural, $count, LC_MESSAGES;
 pgettext $msgctxt, $msgid;
 dpgettext $textdomain, $msgctxt, $msgid;
 dcpgettext $textdomain, $msgctxt, $msgid, LC_MESSAGES;
 npgettext $msgctxt, $msgid, $msgid_plural, $count;
 dnpgettext $textdomain, $msgctxt, $msgid, $msgid_plural, $count;
 dcnpgettext $textdomain, $msgctxt, $msgid, $msgid_plural, $count, LC_MESSAGES;
 textdomain $textdomain;
 bindtextdomain $textdomain, $directory;
 bind_textdomain_codeset $textdomain, $encoding;
 bind_textdomain_filter $textdomain, \&filter, $data;
 turn_utf_8_on ($variable);
 turn_utf_8_off ($variable);
 nl_putenv ('OUTPUT_CHARSET=koi8-r');
 my $category = LC_CTYPE;
 my $category = LC_NUMERIC;
 my $category = LC_TIME;
 my $category = LC_COLLATE;
 my $category = LC_MONETARY;
 my $category = LC_MESSAGES;
 my $category = LC_ALL;

=head1 DESCRIPTION

The module B<Locale::Messages> is a wrapper around the interface to
message translation according to the Uniforum approach that is
for example used in GNU gettext and Sun's Solaris.  It is intended
to allow Locale::Messages(3) to switch between different implementations
of the lower level libraries but this is not yet implemented.

Normally you should not use this module directly, but the high
level interface Locale::TextDomain(3) that provides a much simpler
interface.  This description is therefore deliberately kept
brief.  Please refer to the GNU gettext documentation available at
L<http://www.gnu.org/manual/gettext/> for in-depth and background 
information on the topic.

The lower level module Locale::gettext_pp(3) provides the Perl
implementation of gettext() and related functions.

=head1 FUNCTIONS

The module exports by default nothing.  Every function has to be
imported explicitely or via an export tag (L</"EXPORT TAGS">).

=over 4

=item B<gettext MSGID>

Returns the translation for B<MSGID>.  Example:

print gettext "Hello World!\n";

If no translation can be found, the unmodified B<MSGID> is returned,
i. e. the function can I<never> fail, and will I<never> mess up your
original message.

Note for Perl 5.6 and later: The returned string will I<always> have
the UTF-8 flag off by default.  See the documentation for function
bind_textdomain_filter() for a way to change this behavior.

One common mistake is this:

print gettext "Hello $name!";

Perl will interpolate the variable C<$name> I<before> the function
will see the string.  Unless the corresponding message catalog 
contains a message "Hello Tom!", "Hello Dick!" or "Hello Harry!",
no translation will be found.

Using printf() and friends has its own problems:

print sprintf (gettext ("This is the %s %s."), $color, $thing);

(The example is stupid because neither color nor thing will get
translated here ...).

In English the adjective (the color) will precede the noun, many
other languages (for example French or Italian) differ here.  The 
translator of the message may therefore have a hard time to find
a translation that will still work and not sound stupid in the 
target language.  Many C implementations of printf() allow to 
change the order of the arguments, and a French translator could
then say:

"C'est le %$2s %$1s."

Perl printf() implements this feature as of version 5.8 or better.
Consequently you can only use it, if you are sure that your software
will run with Perl 5.8 or a later version.

Another disadvantage of using printf() is its cryptic syntax (maybe
not for you but translators of your software may have their own
opinion).

See the description of the function C<__x()> in Locale::TextDomain(3)
for a much better way to get around this problem.

Non-ASCII message ids ...

You should note that the function (and all other similar functions
in this module) does a bytewise comparison of the B<MSGID> for the
lookup in the translation catalog, no matter whether obscure utf-8
flags are set on it, whether the string looks like utf-8, whether
the utf8(3pm) pragma is used, or whatever other weird method past
or future perl(1) versions invent for guessing character sets of
strings.

Using other than us-ascii characters in Perl source code is a call
for trouble, a compatibility nightmare.  Furthermore, GNU gettext
only lately introduced support for non-ascii character sets in sources,
and support for this feature may not be available everywhere.  If
you absolutely want to use B<MSGID>s in non-ascii character sets,
it is wise to choose utf-8.  This will minimize the risk that perl(1)
itself will mess with the strings, and it will also be a guaranty
that you can later translate your project into arbitrary target
languages.

Other character sets can theoretically work.  Yet, using another
character set in the Perl source code than the one used in your
message catalogs will B<never> work, since the lookup is done bytewise,
and all strings with non-ascii characters will not be found.

Even if you have solved all these problems, there is still one show
stopper left: The gettext runtime API lacks a possibility to specify 
the character set of the source code (including the original strings).
Consequently - in absence of a hint for the input encoding - strings 
without a translation are not subject to output character set conversion.
In other words: If the (non-determinable) output character set differs
from the character set used in the source code, output can be a
mixture of two character sets.  There is no point in trying to address
this problem in the pure Perl version of the gettext functions.  because
breaking compatibilty between the Perl and the C version is a price too
high to pay.

This all boils down to: Only use ASCII characters in your translatable
strings!

=item B<dgettext TEXTDOMAIN, MSGID>

Like gettext(), but retrieves the message for the specified 
B<TEXTDOMAIN> instead of the default domain.  In case you wonder what
a textdomain is, you should really read on with Locale::TextDomain(3).

=item B<dcgettext TEXTDOMAIN, MSGID, CATEGORY>

Like dgettext() but retrieves the message from the specified B<CATEGORY>
instead of the default category C<LC_MESSAGES>.

=item B<ngettext MSGID, MSGID_PLURAL, COUNT>

Retrieves the correct translation for B<COUNT> items.  In legacy software
you will often find something like:

print "$count file(s) deleted.\n";

printf "$count file%s deleted.\n", $count == 1 ? '' : 's';

The first example looks awkward, the second will only work in English
and languages with similar plural rules.  Before ngettext() was introduced,
the best practice for internationalized programs was:

if ($count == 1) {
        print gettext "One file deleted.\n";
    } else {
        printf gettext "%d files deleted.\n";
    }

This is a nuisance for the programmer and often still not sufficient
for an adequate translation.  Many languages have completely different
ideas on numerals.  Some (French, Italian, ...) treat 0 and 1 alike,
others make no distinction at all (Japanese, Korean, Chinese, ...),
others have two or more plural forms (Russian, Latvian, Czech,
Polish, ...).  The solution is:

printf (ngettext ("One file deleted.\n",
                     "%d files deleted.\n",
                     $count), # argument to ngettext!
            $count);          # argument to printf!

In English, or if no translation can be found, the first argument
(B<MSGID>) is picked if C<$count> is one, the second one otherwise.
For other languages, the correct plural form (of 1, 2, 3, 4, ...)
is automatically picked, too.  You don't have to know anything about
the plural rules in the target language, ngettext() will take care
of that.

This is most of the time sufficient but you will have to prove your
creativity in cases like

printf "%d file(s) deleted, and %d file(s) created.\n";

=item B<dngettext TEXTDOMAIN, MSGID, MSGID_PLURAL, COUNT>

Like ngettext() but retrieves the translation from the specified
textdomain instead of the default domain.

=item B<dcngettext TEXTDOMAIN, MSGID, MSGID_PLURAL, COUNT, CATEGORY>

Like dngettext() but retrieves the translation from the specified
category, instead of the default category C<LC_MESSAGES>.

=item B<pgettext MSGCTXT, MSGID>

Returns the translation of MSGID, given the context of MSGCTXT.

Both items are used as a unique key into the message catalog.

This allows the translator to have two entries for words that may
translate to different foreign words based on their context. For
example, the word "View" may be a noun or a verb, which may be
used in a menu as File->View or View->Source.

pgettext "Verb: To View", "View\n";
    pgettext "Noun: A View", "View\n";

The above will both lookup different entries in the message catalog.

A typical usage are GUI programs.  Imagine a program with a main
menu and the notorious "Open" entry in the "File" menu.  Now imagine,
there is another menu entry Preferences->Advanced->Policy where you have 
a choice between the alternatives "Open" and "Closed".  In English, "Open"
is the adequate text at both places.  In other languages, it is very
likely that you need two different translations.  Therefore, you would
now write:

pgettext "File|", "Open";
    pgettext "Preferences|Advanced|Policy", "Open";

In English, or if no translation can be found, the second argument
(MSGID) is returned.