1 |
<?php |
2 |
/* This file is part of BBClone (A PHP based Web Counter on Steroids) |
3 |
* |
4 |
* SVN FILE $Id$ |
5 |
* |
6 |
* Copyright (C) 2001-2023, the BBClone Team (see doc/authors.txt for details) |
7 |
* |
8 |
* This program is free software: you can redistribute it and/or modify |
9 |
* it under the terms of the GNU General Public License as published by |
10 |
* the Free Software Foundation, either version 3 of the License, or |
11 |
* (at your option) any later version. |
12 |
* |
13 |
* This program is distributed in the hope that it will be useful, |
14 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
15 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
16 |
* GNU General Public License for more details. |
17 |
* |
18 |
* See doc/copying.txt for details |
19 |
*/ |
20 |
|
21 |
////////////////////////////// |
22 |
// Character set conversion // |
23 |
////////////////////////////// |
24 |
|
25 |
function bbc_get_encoding($str) { |
26 |
global $BBC_LANGUAGE; |
27 |
|
28 |
switch ($BBC_LANGUAGE) { |
29 |
case "bg": |
30 |
case "mk": |
31 |
case "ru": |
32 |
case "uk": |
33 |
return mb_detect_encoding($str, "UTF-8, KOI8-R, Windows-1251"); |
34 |
|
35 |
case "ja": |
36 |
return mb_detect_encoding($str, "JIS, UTF-8, EUC-JP, SJIS"); |
37 |
|
38 |
case "ko": |
39 |
return mb_detect_encoding($str, "UTF-8, EUC-KR, ISO-2022-KR"); |
40 |
|
41 |
default: |
42 |
// Note that iso-8859-1 is only a placeholder, the focus lies on detecting UTF-8... |
43 |
return (mb_detect_encoding($str, "UTF-8, iso-8859-1") == "UTF-8") ? "UTF-8" : false; |
44 |
} |
45 |
} |
46 |
|
47 |
function bbc_convert_keys($str, $from, $to) { |
48 |
if (($from !== false) && defined("_BBC_MBSTRING") && preg_match(":iso-8859-|EUC-(JP|KR)|gb2312:", $to) || |
49 |
(!empty($BBC_CUSTOM_CHARSET) && stristr("UTF", $BBC_CUSTOM_CHARSET))) { |
50 |
return mb_convert_encoding($str, $to, $from); |
51 |
} |
52 |
elseif (($from !== false) && defined("_BBC_ICONV")) return iconv($from, $to."//TRANSLIT", $str); |
53 |
elseif (defined("_BBC_RECODE")) return recode_string($to, $str); |
54 |
|
55 |
else return $str; |
56 |
} |
57 |
|
58 |
// Note: Specify $BBC_CUSTOM_CHARSET to overwrite the default character set. |
59 |
function bbc_convert_lang($str, $from, $char) { |
60 |
global $BBC_LANGUAGE; |
61 |
|
62 |
if (!empty($char)) return bbc_convert_keys($str, $from, $char); |
63 |
|
64 |
switch ($BBC_LANGUAGE) { |
65 |
|
66 |
// Cyrillic encodings |
67 |
case "bg": |
68 |
case "mk": |
69 |
case "ru": |
70 |
case "uk": |
71 |
return bbc_convert_keys($str, $from, "Windows-1251"); |
72 |
|
73 |
// Central and East European encodings |
74 |
case "bs": |
75 |
case "cs": |
76 |
case "hu": |
77 |
case "pl": |
78 |
case "ro": |
79 |
case "sk": |
80 |
case "sl": |
81 |
return bbc_convert_keys($str, $from, "iso-8859-2"); |
82 |
|
83 |
// Various encodings |
84 |
case "ar": |
85 |
return bbc_convert_keys($str, $from, "Windows-1256"); |
86 |
|
87 |
case "el": |
88 |
return bbc_convert_keys($str, $from, "iso-8859-7"); |
89 |
|
90 |
case "ja": |
91 |
return bbc_convert_keys($str, $from, "EUC-JP"); |
92 |
|
93 |
case "ko": |
94 |
return bbc_convert_keys($str, $from, "EUC-KR"); |
95 |
|
96 |
case "lt": |
97 |
return bbc_convert_keys($str, $from, "Windows-1257"); |
98 |
|
99 |
case "tr": |
100 |
return bbc_convert_keys($str, $from, "Windows-1254"); |
101 |
|
102 |
case "zh-cn": |
103 |
return bbc_convert_keys($str, $from, "gb2312"); |
104 |
|
105 |
case "zh-tw": |
106 |
return bbc_convert_keys($str, $from, "big5"); |
107 |
|
108 |
// All remaining languages not mentioned anywhere else |
109 |
default: |
110 |
return bbc_convert_keys($str, $from, "iso-8859-15"); |
111 |
} |
112 |
} |
113 |
?> |