/usr/share/mediawiki/includes/libs/StringUtils.php is in mediawiki-classes 1:1.27.4-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 | <?php
/**
* Methods to play with strings.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
* @file
*/
/**
* A collection of static methods to play with strings.
*/
class StringUtils {
/**
* Test whether a string is valid UTF-8.
*
* The function check for invalid byte sequences, overlong encoding but
* not for different normalisations.
*
* @note In MediaWiki 1.21, this function did not provide proper UTF-8 validation.
* In particular, the pure PHP code path did not in fact check for overlong forms.
* Beware of this when backporting code to that version of MediaWiki.
*
* @since 1.21
* @param string $value String to check
* @return bool Whether the given $value is a valid UTF-8 encoded string
*/
static function isUtf8( $value ) {
$value = (string)$value;
// HHVM 3.4 and older come with an outdated version of libmbfl that
// incorrectly allows values above U+10FFFF, so we have to check
// for them separately. (This issue also exists in PHP 5.3 and
// older, which are no longer supported.)
static $newPHP;
if ( $newPHP === null ) {
$newPHP = !mb_check_encoding( "\xf4\x90\x80\x80", 'UTF-8' );
}
return mb_check_encoding( $value, 'UTF-8' ) &&
( $newPHP || preg_match( "/\xf4[\x90-\xbf]|[\xf5-\xff]/S", $value ) === 0 );
}
/**
* Perform an operation equivalent to `preg_replace()`
*
* Matches this code:
*
* preg_replace( "!$startDelim(.*?)$endDelim!", $replace, $subject );
*
* ..except that it's worst-case O(N) instead of O(N^2). Compared to delimiterReplace(), this
* implementation is fast but memory-hungry and inflexible. The memory requirements are such
* that I don't recommend using it on anything but guaranteed small chunks of text.
*
* @param string $startDelim
* @param string $endDelim
* @param string $replace
* @param string $subject
* @return string
*/
static function hungryDelimiterReplace( $startDelim, $endDelim, $replace, $subject ) {
$segments = explode( $startDelim, $subject );
$output = array_shift( $segments );
foreach ( $segments as $s ) {
$endDelimPos = strpos( $s, $endDelim );
if ( $endDelimPos === false ) {
$output .= $startDelim . $s;
} else {
$output .= $replace . substr( $s, $endDelimPos + strlen( $endDelim ) );
}
}
return $output;
}
/**
* Perform an operation equivalent to `preg_replace_callback()`
*
* Matches this code:
*
* preg_replace_callback( "!$startDelim(.*)$endDelim!s$flags", $callback, $subject );
*
* If the start delimiter ends with an initial substring of the end delimiter,
* e.g. in the case of C-style comments, the behavior differs from the model
* regex. In this implementation, the end must share no characters with the
* start, so e.g. `/*\/` is not considered to be both the start and end of a
* comment. `/*\/xy/*\/` is considered to be a single comment with contents `/xy/`.
*
* The implementation of delimiterReplaceCallback() is slower than hungryDelimiterReplace()
* but uses far less memory. The delimiters are literal strings, not regular expressions.
*
* @param string $startDelim Start delimiter
* @param string $endDelim End delimiter
* @param callable $callback Function to call on each match
* @param string $subject
* @param string $flags Regular expression flags
* @throws InvalidArgumentException
* @return string
*/
static function delimiterReplaceCallback( $startDelim, $endDelim, $callback,
$subject, $flags = ''
) {
$inputPos = 0;
$outputPos = 0;
$output = '';
$foundStart = false;
$encStart = preg_quote( $startDelim, '!' );
$encEnd = preg_quote( $endDelim, '!' );
$strcmp = strpos( $flags, 'i' ) === false ? 'strcmp' : 'strcasecmp';
$endLength = strlen( $endDelim );
$m = [];
while ( $inputPos < strlen( $subject ) &&
preg_match( "!($encStart)|($encEnd)!S$flags", $subject, $m, PREG_OFFSET_CAPTURE, $inputPos )
) {
$tokenOffset = $m[0][1];
if ( $m[1][0] != '' ) {
if ( $foundStart &&
$strcmp( $endDelim, substr( $subject, $tokenOffset, $endLength ) ) == 0
) {
# An end match is present at the same location
$tokenType = 'end';
$tokenLength = $endLength;
} else {
$tokenType = 'start';
$tokenLength = strlen( $m[0][0] );
}
} elseif ( $m[2][0] != '' ) {
$tokenType = 'end';
$tokenLength = strlen( $m[0][0] );
} else {
throw new InvalidArgumentException( 'Invalid delimiter given to ' . __METHOD__ );
}
if ( $tokenType == 'start' ) {
# Only move the start position if we haven't already found a start
# This means that START START END matches outer pair
if ( !$foundStart ) {
# Found start
$inputPos = $tokenOffset + $tokenLength;
# Write out the non-matching section
$output .= substr( $subject, $outputPos, $tokenOffset - $outputPos );
$outputPos = $tokenOffset;
$contentPos = $inputPos;
$foundStart = true;
} else {
# Move the input position past the *first character* of START,
# to protect against missing END when it overlaps with START
$inputPos = $tokenOffset + 1;
}
} elseif ( $tokenType == 'end' ) {
if ( $foundStart ) {
# Found match
$output .= call_user_func( $callback, [
substr( $subject, $outputPos, $tokenOffset + $tokenLength - $outputPos ),
substr( $subject, $contentPos, $tokenOffset - $contentPos )
] );
$foundStart = false;
} else {
# Non-matching end, write it out
$output .= substr( $subject, $inputPos, $tokenOffset + $tokenLength - $outputPos );
}
$inputPos = $outputPos = $tokenOffset + $tokenLength;
} else {
throw new InvalidArgumentException( 'Invalid delimiter given to ' . __METHOD__ );
}
}
if ( $outputPos < strlen( $subject ) ) {
$output .= substr( $subject, $outputPos );
}
return $output;
}
/**
* Perform an operation equivalent to `preg_replace()` with flags.
*
* Matches this code:
*
* preg_replace( "!$startDelim(.*)$endDelim!$flags", $replace, $subject );
*
* @param string $startDelim Start delimiter regular expression
* @param string $endDelim End delimiter regular expression
* @param string $replace Replacement string. May contain $1, which will be
* replaced by the text between the delimiters
* @param string $subject String to search
* @param string $flags Regular expression flags
* @return string The string with the matches replaced
*/
static function delimiterReplace( $startDelim, $endDelim, $replace, $subject, $flags = '' ) {
$replacer = new RegexlikeReplacer( $replace );
return self::delimiterReplaceCallback( $startDelim, $endDelim,
$replacer->cb(), $subject, $flags );
}
/**
* More or less "markup-safe" explode()
* Ignores any instances of the separator inside `<...>`
* @param string $separator
* @param string $text
* @return array
*/
static function explodeMarkup( $separator, $text ) {
$placeholder = "\x00";
// Remove placeholder instances
$text = str_replace( $placeholder, '', $text );
// Replace instances of the separator inside HTML-like tags with the placeholder
$replacer = new DoubleReplacer( $separator, $placeholder );
$cleaned = StringUtils::delimiterReplaceCallback( '<', '>', $replacer->cb(), $text );
// Explode, then put the replaced separators back in
$items = explode( $separator, $cleaned );
foreach ( $items as $i => $str ) {
$items[$i] = str_replace( $placeholder, $separator, $str );
}
return $items;
}
/**
* More or less "markup-safe" str_replace()
* Ignores any instances of the separator inside `<...>`
* @param string $search
* @param string $replace
* @param string $text
* @return string
*/
static function replaceMarkup( $search, $replace, $text ) {
$placeholder = "\x00";
// Remove placeholder instances
$text = str_replace( $placeholder, '', $text );
// Replace instances of the separator inside HTML-like tags with the placeholder
$replacer = new DoubleReplacer( $search, $placeholder );
$cleaned = StringUtils::delimiterReplaceCallback( '<', '>', $replacer->cb(), $text );
// Explode, then put the replaced separators back in
$cleaned = str_replace( $search, $replace, $cleaned );
$text = str_replace( $placeholder, $search, $cleaned );
return $text;
}
/**
* Escape a string to make it suitable for inclusion in a preg_replace()
* replacement parameter.
*
* @param string $string
* @return string
*/
static function escapeRegexReplacement( $string ) {
$string = str_replace( '\\', '\\\\', $string );
$string = str_replace( '$', '\\$', $string );
return $string;
}
/**
* Workalike for explode() with limited memory usage.
*
* @param string $separator
* @param string $subject
* @return ArrayIterator|ExplodeIterator
*/
static function explode( $separator, $subject ) {
if ( substr_count( $subject, $separator ) > 1000 ) {
return new ExplodeIterator( $separator, $subject );
} else {
return new ArrayIterator( explode( $separator, $subject ) );
}
}
}
|