summaryrefslogtreecommitdiff
path: root/languages/LanguageUtf8.php
blob: d738624b77b490de3c32adbd78356cdf6cf9d34f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
<?php
/**
  * @package MediaWiki
  * @subpackage Language
  */

if( defined( "MEDIAWIKI" ) ) {

# This file and LanguageLatin1.php may be included from within functions, so
# we need to have global statements

global $wgInputEncoding, $wgOutputEncoding, $wikiUpperChars, $wikiLowerChars;
global $wgDBname, $wgMemc;

$wgInputEncoding    = "UTF-8";
$wgOutputEncoding	= "UTF-8";

if( function_exists( 'mb_strtoupper' ) ) {
	mb_internal_encoding('UTF-8');
} else {
	# Hack our own case conversion routines

	# Loading serialized arrays is faster than parsing code :P
	$wikiUpperChars = $wgMemc->get( $key1 = "$wgDBname:utf8:upper" );
	$wikiLowerChars = $wgMemc->get( $key2 = "$wgDBname:utf8:lower" );

	if(empty( $wikiUpperChars) || empty($wikiLowerChars )) {
		require_once( "includes/Utf8Case.php" );
		$wgMemc->set( $key1, $wikiUpperChars );
		$wgMemc->set( $key2, $wikiLowerChars );
	}
}

/**
 * Base stuff useful to all UTF-8 based language files
 * @package MediaWiki
 */
class LanguageUtf8 extends Language {

	# These functions use mbstring library, if it is loaded
	# or compiled and character mapping arrays otherwise.
	# In case of language-specific character mismatch
	# it should be dealt with in Language classes.

	function ucfirst( $str ) {
		return LanguageUtf8::uc( $str, true );
	}

	function uc( $str, $first = false ) {
		if ( function_exists( 'mb_strtoupper' ) )
			if ( $first )
				if ( LanguageUtf8::isMultibyte( $str ) )
					return mb_strtoupper( mb_substr( $str, 0, 1 ) ) . mb_substr( $str, 1 );
				else
					return ucfirst( $str );
			else
				return LanguageUtf8::isMultibyte( $str ) ? mb_strtoupper( $str ) : strtoupper( $str );
		else
			if ( LanguageUtf8::isMultibyte( $str ) ) {
				global $wikiUpperChars;
				$x = $first ? '^' : '';
				return preg_replace(
					"/$x([a-z]|[\\xc0-\\xff][\\x80-\\xbf]*)/e",
					"strtr( \"\$1\" , \$wikiUpperChars )",
					$str
				);
			} else
				return $first ? ucfirst( $str ) : strtoupper( $str );
	}

	function lcfirst( $str ) {
		return LanguageUtf8::lc( $str, true );
	}

	function lc( $str, $first = false ) {
		if ( function_exists( 'mb_strtolower' ) )
			if ( $first )
				if ( LanguageUtf8::isMultibyte( $str ) )
					return mb_strtolower( mb_substr( $str, 0, 1 ) ) . mb_substr( $str, 1 );
				else
					return strtolower( substr( $str, 0, 1 ) ) . substr( $str, 1 );
			else
				return LanguageUtf8::isMultibyte( $str ) ? mb_strtolower( $str ) : strtolower( $str );
		else
			if ( LanguageUtf8::isMultibyte( $str ) ) {
				global $wikiLowerChars;
				$x = $first ? '^' : '';
				return preg_replace(
					"/$x([A-Z]|[\\xc0-\\xff][\\x80-\\xbf]*)/e",
					"strtr( \"\$1\" , \$wikiLowerChars )",
					$str
				);
			} else
				return $first ? strtolower( substr( $str, 0, 1 ) ) . substr( $str, 1 ) : strtolower( $str );
	}

	function isMultibyte( $str ) {
		return (bool)preg_match( '/^[\x80-\xff]/', $str );
	}

	function stripForSearch( $string ) {
		# MySQL fulltext index doesn't grok utf-8, so we
		# need to fold cases and convert to hex

		# In Language:: it just returns lowercase, maybe
		# all strtolower on stripped output or argument
		# should be removed and all stripForSearch
		# methods adjusted to that.

		wfProfileIn( "LanguageUtf8::stripForSearch" );
		if( function_exists( 'mb_strtolower' ) ) {
			$out = preg_replace(
				"/([\\xc0-\\xff][\\x80-\\xbf]*)/e",
				"'U8' . bin2hex( \"$1\" )",
				mb_strtolower( $string ) );
		} else {
			global $wikiLowerChars;
			$out = preg_replace(
				"/([\\xc0-\\xff][\\x80-\\xbf]*)/e",
				"'U8' . bin2hex( strtr( \"\$1\", \$wikiLowerChars ) )",
				$string );
		}
		wfProfileOut( "LanguageUtf8::stripForSearch" );
		return $out;
	}

	function fallback8bitEncoding() {
		# Windows codepage 1252 is a superset of iso 8859-1
		# override this to use difference source encoding to
		# translate incoming 8-bit URLs.
		return "windows-1252";
	}

	function checkTitleEncoding( $s ) {
		global $wgInputEncoding;

		if( is_array( $s ) ) {
			wfDebugDieBacktrace( 'Given array to checkTitleEncoding.' );
		}
		# Check for non-UTF-8 URLs
		$ishigh = preg_match( '/[\x80-\xff]/', $s);
		if(!$ishigh) return $s;

		$isutf8 = preg_match( '/^([\x00-\x7f]|[\xc0-\xdf][\x80-\xbf]|' .
                '[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xf7][\x80-\xbf]{3})+$/', $s );
		if( $isutf8 ) return $s;

		return $this->iconv( $this->fallback8bitEncoding(), "utf-8", $s );
	}

	function firstChar( $s ) {
		preg_match( '/^([\x00-\x7f]|[\xc0-\xdf][\x80-\xbf]|' .
		'[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xf7][\x80-\xbf]{3})/', $s, $matches);

		return isset( $matches[1] ) ? $matches[1] : "";
	}

	# Crop a string from the beginning or end to a certain number of bytes.
	# (Bytes are used because our storage has limited byte lengths for some
	# columns in the database.) Multibyte charsets will need to make sure that
	# only whole characters are included!
	#
	# $length does not include the optional ellipsis.
	# If $length is negative, snip from the beginning
	function truncate( $string, $length, $ellipsis = "" ) {
		if( $length == 0 ) {
			return $ellipsis;
		}
		if ( strlen( $string ) <= abs( $length ) ) {
			return $string;
		}
		if( $length > 0 ) {
			$string = substr( $string, 0, $length );
			$char = ord( $string[strlen( $string ) - 1] );
			if ($char >= 0xc0) {
				# We got the first byte only of a multibyte char; remove it.
				$string = substr( $string, 0, -1 );
			} elseif( $char >= 0x80 &&
			          preg_match( '/^(.*)(?:[\xe0-\xef][\x80-\xbf]|' .
			                      '[\xf0-\xf7][\x80-\xbf]{1,2})$/', $string, $m ) ) {
			    # We chopped in the middle of a character; remove it
				$string = $m[1];
			}
			return $string . $ellipsis;
		} else {
			$string = substr( $string, $length );
			$char = ord( $string[0] );
			if( $char >= 0x80 && $char < 0xc0 ) {
				# We chopped in the middle of a character; remove the whole thing
				$string = preg_replace( '/^[\x80-\xbf]+/', '', $string );
			}
			return $ellipsis . $string;
		}
	}
}

} # ifdef MEDIAWIKI

?>