3 * accept-to-gettext.inc -- convert information in 'Accept-*' headers to
4 * gettext language identifiers.
5 * Copyright (c) 2003, Wouter Verhelst <wouter@debian.org>
7 * This program is free software; you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation; either version 2 of the License, or
10 * (at your option) any later version.
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with this program; if not, write to the Free Software
19 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
23 * $locale=al2gt(<array of supported languages/charsets in gettext syntax>,
24 * <MIME type of document>);
25 * setlocale('LC_ALL', $locale); // or 'LC_MESSAGES', or whatever...
29 * $langs=array('nl_BE.ISO-8859-15','nl_BE.UTF-8','en_US.UTF-8','en_GB.UTF-8');
30 * $locale=al2gt($langs, 'text/html');
31 * setlocale('LC_ALL', $locale);
33 * Note that this will send out header information (to be
34 * RFC2616-compliant), so it must be called before anything is sent to
38 * * Charset encodings are written the same way as the Accept-Charset
39 * HTTP header specifies them (RFC2616), except that they're parsed
41 * * Country codes and language codes are the same in both gettext and
42 * the Accept-Language syntax (except for the case differences, which
43 * are dealt with easily). If not, some input may be ignored.
44 * * The provided gettext-strings are fully qualified; i.e., no "en_US";
45 * always "en_US.ISO-8859-15" or "en_US.UTF-8", or whichever has been
46 * used. "en.ISO-8859-15" is OK, though.
47 * * The language is more important than the charset; i.e., if the
50 * Accept-Language: nl-be, nl;q=0.8, en-us;q=0.5, en;q=0.3
51 * Accept-Charset: ISO-8859-15, utf-8;q=0.5
53 * And the supplied parameter contains (amongst others) nl_BE.UTF-8
54 * and nl.ISO-8859-15, then nl_BE.UTF-8 will be picked.
56 * $Log: accept-to-gettext.inc,v $
57 * Revision 1.1.1.1 2003/11/19 19:31:15 wouter
58 * * moved to new CVS repo after death of the old
59 * * Fixed code to apply a default to both Accept-Charset and
60 * Accept-Language if none of those headers are supplied; patch from
61 * Dominic Chambers <dominic@encasa.com>
63 * Revision 1.2 2003/08/14 10:23:59 wouter
64 * Removed little error in Content-Type header syntaxis.
68 /* not really important, this one; perhaps I could've put it inline with
70 function find_match($curlscore,$curcscore,$curgtlang,$langval,$charval,
73 if($curlscore < $langval) {
77 } else if ($curlscore == $langval) {
78 if($curcscore < $charval) {
83 return array($curlscore, $curcscore, $curgtlang);
86 function al2gt($gettextlangs, $mime) {
87 /* default to "everything is acceptable", as RFC2616 specifies */
88 $acceptLang=(($_SERVER["HTTP_ACCEPT_LANGUAGE"] == '') ? '*' :
89 $_SERVER["HTTP_ACCEPT_LANGUAGE"]);
90 $acceptChar=(($_SERVER["HTTP_ACCEPT_CHARSET"] == '') ? '*' :
91 $_SERVER["HTTP_ACCEPT_CHARSET"]);
92 $alparts=@preg_split("/,/",$acceptLang);
93 $acparts=@preg_split("/,/",$acceptChar);
95 /* Parse the contents of the Accept-Language header.*/
96 foreach($alparts as $part) {
98 if(preg_match("/;/", $part)) {
99 $lang=@preg_split("/;/",$part);
100 $score=@preg_split("/=/",$lang[1]);
101 $alscores[$lang[0]]=$score[1];
107 /* Do the same for the Accept-Charset header. */
109 /* RFC2616: ``If no "*" is present in an Accept-Charset field, then
110 * all character sets not explicitly mentioned get a quality value of
111 * 0, except for ISO-8859-1, which gets a quality value of 1 if not
112 * explicitly mentioned.''
114 * Making it 2 for the time being, so that we
115 * can distinguish between "not specified" and "specified as 1" later
117 $acscores["ISO-8859-1"]=2;
119 foreach($acparts as $part) {
121 if(preg_match("/;/", $part)) {
122 $cs=@preg_split("/;/",$part);
123 $score=@preg_split("/=/",$cs[1]);
124 $acscores[strtoupper($cs[0])]=$score[1];
126 $acscores[strtoupper($part)]=1;
129 if($acscores["ISO-8859-1"]==2) {
130 $acscores["ISO-8859-1"]=(isset($acscores["*"])?$acscores["*"]:1);
134 * Loop through the available languages/encodings, and pick the one
135 * with the highest score, excluding the ones with a charset the user
141 foreach($gettextlangs as $gtlang) {
143 $tmp1=preg_replace("/\_/","-",$gtlang);
144 $tmp2=@preg_split("/\./",$tmp1);
145 $allang=strtolower($tmp2[0]);
146 $gtcs=strtoupper($tmp2[1]);
147 $noct=@preg_split("/-/",$allang);
150 array($alscores[$allang], $acscores[$gtcs]),
151 array($alscores[$noct[0]], $acscores[$gtcs]),
152 array($alscores[$allang], $acscores["*"]),
153 array($alscores[$noct[0]], $acscores["*"]),
154 array($alscores["*"], $acscores[$gtcs]),
155 array($alscores["*"], $acscores["*"]));
158 foreach($testvals as $tval) {
159 if(!$found && isset($tval[0]) && isset($tval[1])) {
160 $arr=find_match($curlscore, $curcscore, $curgtlang, $tval[0],
170 /* We must re-parse the gettext-string now, since we may have found it
171 * through a "*" qualifier.*/
173 $gtparts=@preg_split("/\./",$curgtlang);
174 $tmp=strtolower($gtparts[0]);
175 $lang=preg_replace("/\_/", "-", $tmp);
176 $charset=$gtparts[1];
178 header("Content-Language: $lang");
179 header("Content-Type: $mime; charset=$charset");