includes/Fallback.php

   1 <?php
   2 /**
   3  * Fallback functions for PHP installed without mbstring support.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  */
  22
  23 /**
  24  * Fallback functions for PHP installed without mbstring support
  25  */
  26 class Fallback {
  27
  28         /**
  29          * Fallback implementation for mb_substr, hardcoded to UTF-8.
  30          * Attempts to be at least _moderately_ efficient; best optimized
  31          * for relatively small offset and count values -- about 5x slower
  32          * than native mb_string in my testing.
  33          *
  34          * Larger offsets are still fairly efficient for Latin text, but
  35          * can be up to 100x slower than native if the text is heavily
  36          * multibyte and we have to slog through a few hundred kb.
  37          *
  38          * @param string $str
  39          * @param int $start
  40          * @param string $count
  41          *
  42          * @return string
  43          */
  44         public static function mb_substr( $str, $start, $count = 'end' ) {
  45                 if ( $start != 0 ) {
  46                         $split = self::mb_substr_split_unicode( $str, intval( $start ) );
  47                         $str = substr( $str, $split );
  48                 }
  49
  50                 if ( $count !== 'end' ) {
  51                         $split = self::mb_substr_split_unicode( $str, intval( $count ) );
  52                         $str = substr( $str, 0, $split );
  53                 }
  54
  55                 return $str;
  56         }
  57
  58         /**
  59          * @param string $str
  60          * @param int $splitPos
  61          * @return int
  62          */
  63         public static function mb_substr_split_unicode( $str, $splitPos ) {
  64                 if ( $splitPos == 0 ) {
  65                         return 0;
  66                 }
  67
  68                 $byteLen = strlen( $str );
  69
  70                 if ( $splitPos > 0 ) {
  71                         if ( $splitPos > 256 ) {
  72                                 // Optimize large string offsets by skipping ahead N bytes.
  73                                 // This will cut out most of our slow time on Latin-based text,
  74                                 // and 1/2 to 1/3 on East European and Asian scripts.
  75                                 $bytePos = $splitPos;
  76                                 while ( $bytePos < $byteLen && $str[$bytePos] >= "\x80" && $str[$bytePos] < "\xc0" ) {
  77                                         ++$bytePos;
  78                                 }
  79                                 $charPos = mb_strlen( substr( $str, 0, $bytePos ) );
  80                         } else {
  81                                 $charPos = 0;
  82                                 $bytePos = 0;
  83                         }
  84
  85                         while ( $charPos++ < $splitPos ) {
  86                                 ++$bytePos;
  87                                 // Move past any tail bytes
  88                                 while ( $bytePos < $byteLen && $str[$bytePos] >= "\x80" && $str[$bytePos] < "\xc0" ) {
  89                                         ++$bytePos;
  90                                 }
  91                         }
  92                 } else {
  93                         $splitPosX = $splitPos + 1;
  94                         $charPos = 0; // relative to end of string; we don't care about the actual char position here
  95                         $bytePos = $byteLen;
  96                         while ( $bytePos > 0 && $charPos-- >= $splitPosX ) {
  97                                 --$bytePos;
  98                                 // Move past any tail bytes
  99                                 while ( $bytePos > 0 && $str[$bytePos] >= "\x80" && $str[$bytePos] < "\xc0" ) {
 100                                         --$bytePos;
 101                                 }
 102                         }
 103                 }
 104
 105                 return $bytePos;
 106         }
 107
 108         /**
 109          * Fallback implementation of mb_strlen, hardcoded to UTF-8.
 110          * @param string $str
 111          * @param string $enc Optional encoding; ignored
 112          * @return int
 113          */
 114         public static function mb_strlen( $str, $enc = '' ) {
 115                 $counts = count_chars( $str );
 116                 $total = 0;
 117
 118                 // Count ASCII bytes
 119                 for ( $i = 0; $i < 0x80; $i++ ) {
 120                         $total += $counts[$i];
 121                 }
 122
 123                 // Count multibyte sequence heads
 124                 for ( $i = 0xc0; $i < 0xff; $i++ ) {
 125                         $total += $counts[$i];
 126                 }
 127                 return $total;
 128         }
 129
 130         /**
 131          * Fallback implementation of mb_strpos, hardcoded to UTF-8.
 132          * @param string $haystack
 133          * @param string $needle
 134          * @param string $offset Optional start position
 135          * @param string $encoding Optional encoding; ignored
 136          * @return int
 137          */
 138         public static function mb_strpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
 139                 $needle = preg_quote( $needle, '/' );
 140
 141                 $ar = array();
 142                 preg_match( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
 143
 144                 if ( isset( $ar[0][1] ) ) {
 145                         return $ar[0][1];
 146                 } else {
 147                         return false;
 148                 }
 149         }
 150
 151         /**
 152          * Fallback implementation of mb_strrpos, hardcoded to UTF-8.
 153          * @param string $haystack
 154          * @param string $needle
 155          * @param string $offset Optional start position
 156          * @param string $encoding Optional encoding; ignored
 157          * @return int
 158          */
 159         public static function mb_strrpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
 160                 $needle = preg_quote( $needle, '/' );
 161
 162                 $ar = array();
 163                 preg_match_all( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
 164
 165                 if ( isset( $ar[0] ) && count( $ar[0] ) > 0 &&
 166                         isset( $ar[0][count( $ar[0] ) - 1][1] ) ) {
 167                         return $ar[0][count( $ar[0] ) - 1][1];
 168                 } else {
 169                         return false;
 170                 }
 171         }
 172 }