aboutsummaryrefslogtreecommitdiffstats
path: root/phpBB/includes/utf/utf_tools.php
diff options
context:
space:
mode:
authorNils Adermann <naderman@naderman.de>2010-03-02 01:05:34 +0100
committerNils Adermann <naderman@naderman.de>2010-03-02 01:05:34 +0100
commit517f25353246f06eec7d1fdef90a04119a45bbbf (patch)
tree7837b0e54fcd05f2f49a22a078b0f12cad864b30 /phpBB/includes/utf/utf_tools.php
parent89b37954f994a7cd517553d2d16686f91dcaae72 (diff)
parent7068d8b462e388ea87883c5203a28fa6a8e4b6dc (diff)
downloadforums-517f25353246f06eec7d1fdef90a04119a45bbbf.tar
forums-517f25353246f06eec7d1fdef90a04119a45bbbf.tar.gz
forums-517f25353246f06eec7d1fdef90a04119a45bbbf.tar.bz2
forums-517f25353246f06eec7d1fdef90a04119a45bbbf.tar.xz
forums-517f25353246f06eec7d1fdef90a04119a45bbbf.zip
Merge commit 'release-3.0-B5'
Diffstat (limited to 'phpBB/includes/utf/utf_tools.php')
-rw-r--r--phpBB/includes/utf/utf_tools.php542
1 files changed, 397 insertions, 145 deletions
diff --git a/phpBB/includes/utf/utf_tools.php b/phpBB/includes/utf/utf_tools.php
index 4c6c26909a..f9558c12b4 100644
--- a/phpBB/includes/utf/utf_tools.php
+++ b/phpBB/includes/utf/utf_tools.php
@@ -6,9 +6,6 @@
* @copyright (c) 2006 phpBB Group
* @license http://opensource.org/licenses/gpl-license.php GNU Public License
*
-* @todo make sure the replacements are called correctly
-* already done: strtolower, strtoupper, ucfirst, str_split, strrpos, strlen (hopefully!), strpos, substr, htmlspecialchars
-* remaining: strspn, chr, ord
*/
/**
@@ -18,6 +15,9 @@ if (!defined('IN_PHPBB'))
exit;
}
+// Enforce ASCII only string handling
+setlocale(LC_CTYPE, 'C');
+
/**
* UTF-8 tools
*
@@ -104,6 +104,8 @@ if (!extension_loaded('xml'))
// if mbstring is not loaded, we go into native mode.
if (extension_loaded('mbstring'))
{
+ mb_internal_encoding('UTF-8');
+
/**
* UTF-8 aware alternative to strrpos
* Find position of last occurrence of a char in a string
@@ -305,7 +307,7 @@ else
{
if (!is_int($offset))
{
- trigger_error('utf8_strpos: Offset must be an integer', E_USER_ERROR);
+ trigger_error('utf8_strpos: Offset must be an integer', E_USER_ERROR);
return false;
}
@@ -320,116 +322,6 @@ else
}
}
- $UTF8_UPPER_TO_LOWER = array(
- "\x41" => "\x61", "\x42" => "\x62", "\x43" => "\x63", "\x44" => "\x64",
- "\x45" => "\x65", "\x46" => "\x66", "\x47" => "\x67", "\x48" => "\x68",
- "\x49" => "\x69", "\x4A" => "\x6A", "\x4B" => "\x6B", "\x4C" => "\x6C",
- "\x4D" => "\x6D", "\x4E" => "\x6E", "\x4F" => "\x6F", "\x50" => "\x70",
- "\x51" => "\x71", "\x52" => "\x72", "\x53" => "\x73", "\x54" => "\x74",
- "\x55" => "\x75", "\x56" => "\x76", "\x57" => "\x77", "\x58" => "\x78",
- "\x59" => "\x79", "\x5A" => "\x7A", "\xC3\x80" => "\xC3\xA0", "\xC3\x81" => "\xC3\xA1",
- "\xC3\x82" => "\xC3\xA2", "\xC3\x83" => "\xC3\xA3", "\xC3\x84" => "\xC3\xA4", "\xC3\x85" => "\xC3\xA5",
- "\xC3\x86" => "\xC3\xA6", "\xC3\x87" => "\xC3\xA7", "\xC3\x88" => "\xC3\xA8", "\xC3\x89" => "\xC3\xA9",
- "\xC3\x8A" => "\xC3\xAA", "\xC3\x8B" => "\xC3\xAB", "\xC3\x8C" => "\xC3\xAC", "\xC3\x8D" => "\xC3\xAD",
- "\xC3\x8E" => "\xC3\xAE", "\xC3\x8F" => "\xC3\xAF", "\xC3\x90" => "\xC3\xB0", "\xC3\x91" => "\xC3\xB1",
- "\xC3\x92" => "\xC3\xB2", "\xC3\x93" => "\xC3\xB3", "\xC3\x94" => "\xC3\xB4", "\xC3\x95" => "\xC3\xB5",
- "\xC3\x96" => "\xC3\xB6", "\xC3\x98" => "\xC3\xB8", "\xC3\x99" => "\xC3\xB9", "\xC3\x9A" => "\xC3\xBA",
- "\xC3\x9B" => "\xC3\xBB", "\xC3\x9C" => "\xC3\xBC", "\xC3\x9D" => "\xC3\xBD", "\xC3\x9E" => "\xC3\xBE",
- "\xC4\x80" => "\xC4\x81", "\xC4\x82" => "\xC4\x83", "\xC4\x84" => "\xC4\x85", "\xC4\x86" => "\xC4\x87",
- "\xC4\x88" => "\xC4\x89", "\xC4\x8A" => "\xC4\x8B", "\xC4\x8C" => "\xC4\x8D", "\xC4\x8E" => "\xC4\x8F",
- "\xC4\x90" => "\xC4\x91", "\xC4\x92" => "\xC4\x93", "\xC4\x96" => "\xC4\x97", "\xC4\x98" => "\xC4\x99",
- "\xC4\x9A" => "\xC4\x9B", "\xC4\x9C" => "\xC4\x9D", "\xC4\x9E" => "\xC4\x9F", "\xC4\xA0" => "\xC4\xA1",
- "\xC4\xA2" => "\xC4\xA3", "\xC4\xA4" => "\xC4\xA5", "\xC4\xA6" => "\xC4\xA7", "\xC4\xA8" => "\xC4\xA9",
- "\xC4\xAA" => "\xC4\xAB", "\xC4\xAE" => "\xC4\xAF", "\xC4\xB4" => "\xC4\xB5", "\xC4\xB6" => "\xC4\xB7",
- "\xC4\xB9" => "\xC4\xBA", "\xC4\xBB" => "\xC4\xBC", "\xC4\xBD" => "\xC4\xBE", "\xC5\x81" => "\xC5\x82",
- "\xC5\x83" => "\xC5\x84", "\xC5\x85" => "\xC5\x86", "\xC5\x87" => "\xC5\x88", "\xC5\x8A" => "\xC5\x8B",
- "\xC5\x8C" => "\xC5\x8D", "\xC5\x90" => "\xC5\x91", "\xC5\x94" => "\xC5\x95", "\xC5\x96" => "\xC5\x97",
- "\xC5\x98" => "\xC5\x99", "\xC5\x9A" => "\xC5\x9B", "\xC5\x9C" => "\xC5\x9D", "\xC5\x9E" => "\xC5\x9F",
- "\xC5\xA0" => "\xC5\xA1", "\xC5\xA2" => "\xC5\xA3", "\xC5\xA4" => "\xC5\xA5", "\xC5\xA6" => "\xC5\xA7",
- "\xC5\xA8" => "\xC5\xA9", "\xC5\xAA" => "\xC5\xAB", "\xC5\xAC" => "\xC5\xAD", "\xC5\xAE" => "\xC5\xAF",
- "\xC5\xB0" => "\xC5\xB1", "\xC5\xB2" => "\xC5\xB3", "\xC5\xB4" => "\xC5\xB5", "\xC5\xB6" => "\xC5\xB7",
- "\xC5\xB8" => "\xC3\xBF", "\xC5\xB9" => "\xC5\xBA", "\xC5\xBB" => "\xC5\xBC", "\xC5\xBD" => "\xC5\xBE",
- "\xC6\xA0" => "\xC6\xA1", "\xC6\xAF" => "\xC6\xB0", "\xC8\x98" => "\xC8\x99", "\xC8\x9A" => "\xC8\x9B",
- "\xCE\x86" => "\xCE\xAC", "\xCE\x88" => "\xCE\xAD", "\xCE\x89" => "\xCE\xAE", "\xCE\x8A" => "\xCE\xAF",
- "\xCE\x8C" => "\xCF\x8C", "\xCE\x8E" => "\xCF\x8D", "\xCE\x8F" => "\xCF\x8E", "\xCE\x91" => "\xCE\xB1",
- "\xCE\x92" => "\xCE\xB2", "\xCE\x93" => "\xCE\xB3", "\xCE\x94" => "\xCE\xB4", "\xCE\x95" => "\xCE\xB5",
- "\xCE\x96" => "\xCE\xB6", "\xCE\x97" => "\xCE\xB7", "\xCE\x98" => "\xCE\xB8", "\xCE\x99" => "\xCE\xB9",
- "\xCE\x9A" => "\xCE\xBA", "\xCE\x9B" => "\xCE\xBB", "\xCE\x9C" => "\xCE\xBC", "\xCE\x9D" => "\xCE\xBD",
- "\xCE\x9E" => "\xCE\xBE", "\xCE\x9F" => "\xCE\xBF", "\xCE\xA0" => "\xCF\x80", "\xCE\xA1" => "\xCF\x81",
- "\xCE\xA3" => "\xCF\x83", "\xCE\xA4" => "\xCF\x84", "\xCE\xA5" => "\xCF\x85", "\xCE\xA6" => "\xCF\x86",
- "\xCE\xA7" => "\xCF\x87", "\xCE\xA8" => "\xCF\x88", "\xCE\xA9" => "\xCF\x89", "\xCE\xAA" => "\xCF\x8A",
- "\xCE\xAB" => "\xCF\x8B", "\xD0\x81" => "\xD1\x91", "\xD0\x82" => "\xD1\x92", "\xD0\x83" => "\xD1\x93",
- "\xD0\x84" => "\xD1\x94", "\xD0\x85" => "\xD1\x95", "\xD0\x86" => "\xD1\x96", "\xD0\x87" => "\xD1\x97",
- "\xD0\x88" => "\xD1\x98", "\xD0\x89" => "\xD1\x99", "\xD0\x8A" => "\xD1\x9A", "\xD0\x8B" => "\xD1\x9B",
- "\xD0\x8C" => "\xD1\x9C", "\xD0\x8E" => "\xD1\x9E", "\xD0\x8F" => "\xD1\x9F", "\xD0\x90" => "\xD0\xB0",
- "\xD0\x91" => "\xD0\xB1", "\xD0\x92" => "\xD0\xB2", "\xD0\x93" => "\xD0\xB3", "\xD0\x94" => "\xD0\xB4",
- "\xD0\x95" => "\xD0\xB5", "\xD0\x96" => "\xD0\xB6", "\xD0\x97" => "\xD0\xB7", "\xD0\x98" => "\xD0\xB8",
- "\xD0\x99" => "\xD0\xB9", "\xD0\x9A" => "\xD0\xBA", "\xD0\x9B" => "\xD0\xBB", "\xD0\x9C" => "\xD0\xBC",
- "\xD0\x9D" => "\xD0\xBD", "\xD0\x9E" => "\xD0\xBE", "\xD0\x9F" => "\xD0\xBF", "\xD0\xA0" => "\xD1\x80",
- "\xD0\xA1" => "\xD1\x81", "\xD0\xA2" => "\xD1\x82", "\xD0\xA3" => "\xD1\x83", "\xD0\xA4" => "\xD1\x84",
- "\xD0\xA5" => "\xD1\x85", "\xD0\xA6" => "\xD1\x86", "\xD0\xA7" => "\xD1\x87", "\xD0\xA8" => "\xD1\x88",
- "\xD0\xA9" => "\xD1\x89", "\xD0\xAA" => "\xD1\x8A", "\xD0\xAB" => "\xD1\x8B", "\xD0\xAC" => "\xD1\x8C",
- "\xD0\xAD" => "\xD1\x8D", "\xD0\xAE" => "\xD1\x8E", "\xD0\xAF" => "\xD1\x8F", "\xD2\x90" => "\xD2\x91",
- "\xE1\xB8\x82" => "\xE1\xB8\x83", "\xE1\xB8\x8A" => "\xE1\xB8\x8B", "\xE1\xB8\x9E" => "\xE1\xB8\x9F", "\xE1\xB9\x80" => "\xE1\xB9\x81",
- "\xE1\xB9\x96" => "\xE1\xB9\x97", "\xE1\xB9\xA0" => "\xE1\xB9\xA1", "\xE1\xB9\xAA" => "\xE1\xB9\xAB", "\xE1\xBA\x80" => "\xE1\xBA\x81",
- "\xE1\xBA\x82" => "\xE1\xBA\x83", "\xE1\xBA\x84" => "\xE1\xBA\x85", "\xE1\xBB\xB2" => "\xE1\xBB\xB3"
- );
-
- $UTF8_LOWER_TO_UPPER = array(
- "\x61" => "\x41", "\x62" => "\x42", "\x63" => "\x43", "\x64" => "\x44",
- "\x65" => "\x45", "\x66" => "\x46", "\x67" => "\x47", "\x68" => "\x48",
- "\x69" => "\x49", "\x6A" => "\x4A", "\x6B" => "\x4B", "\x6C" => "\x4C",
- "\x6D" => "\x4D", "\x6E" => "\x4E", "\x6F" => "\x4F", "\x70" => "\x50",
- "\x71" => "\x51", "\x72" => "\x52", "\x73" => "\x53", "\x74" => "\x54",
- "\x75" => "\x55", "\x76" => "\x56", "\x77" => "\x57", "\x78" => "\x58",
- "\x79" => "\x59", "\x7A" => "\x5A", "\xC3\xA0" => "\xC3\x80", "\xC3\xA1" => "\xC3\x81",
- "\xC3\xA2" => "\xC3\x82", "\xC3\xA3" => "\xC3\x83", "\xC3\xA4" => "\xC3\x84", "\xC3\xA5" => "\xC3\x85",
- "\xC3\xA6" => "\xC3\x86", "\xC3\xA7" => "\xC3\x87", "\xC3\xA8" => "\xC3\x88", "\xC3\xA9" => "\xC3\x89",
- "\xC3\xAA" => "\xC3\x8A", "\xC3\xAB" => "\xC3\x8B", "\xC3\xAC" => "\xC3\x8C", "\xC3\xAD" => "\xC3\x8D",
- "\xC3\xAE" => "\xC3\x8E", "\xC3\xAF" => "\xC3\x8F", "\xC3\xB0" => "\xC3\x90", "\xC3\xB1" => "\xC3\x91",
- "\xC3\xB2" => "\xC3\x92", "\xC3\xB3" => "\xC3\x93", "\xC3\xB4" => "\xC3\x94", "\xC3\xB5" => "\xC3\x95",
- "\xC3\xB6" => "\xC3\x96", "\xC3\xB8" => "\xC3\x98", "\xC3\xB9" => "\xC3\x99", "\xC3\xBA" => "\xC3\x9A",
- "\xC3\xBB" => "\xC3\x9B", "\xC3\xBC" => "\xC3\x9C", "\xC3\xBD" => "\xC3\x9D", "\xC3\xBE" => "\xC3\x9E",
- "\xC3\xBF" => "\xC5\xB8", "\xC4\x81" => "\xC4\x80", "\xC4\x83" => "\xC4\x82", "\xC4\x85" => "\xC4\x84",
- "\xC4\x87" => "\xC4\x86", "\xC4\x89" => "\xC4\x88", "\xC4\x8B" => "\xC4\x8A", "\xC4\x8D" => "\xC4\x8C",
- "\xC4\x8F" => "\xC4\x8E", "\xC4\x91" => "\xC4\x90", "\xC4\x93" => "\xC4\x92", "\xC4\x97" => "\xC4\x96",
- "\xC4\x99" => "\xC4\x98", "\xC4\x9B" => "\xC4\x9A", "\xC4\x9D" => "\xC4\x9C", "\xC4\x9F" => "\xC4\x9E",
- "\xC4\xA1" => "\xC4\xA0", "\xC4\xA3" => "\xC4\xA2", "\xC4\xA5" => "\xC4\xA4", "\xC4\xA7" => "\xC4\xA6",
- "\xC4\xA9" => "\xC4\xA8", "\xC4\xAB" => "\xC4\xAA", "\xC4\xAF" => "\xC4\xAE", "\xC4\xB5" => "\xC4\xB4",
- "\xC4\xB7" => "\xC4\xB6", "\xC4\xBA" => "\xC4\xB9", "\xC4\xBC" => "\xC4\xBB", "\xC4\xBE" => "\xC4\xBD",
- "\xC5\x82" => "\xC5\x81", "\xC5\x84" => "\xC5\x83", "\xC5\x86" => "\xC5\x85", "\xC5\x88" => "\xC5\x87",
- "\xC5\x8B" => "\xC5\x8A", "\xC5\x8D" => "\xC5\x8C", "\xC5\x91" => "\xC5\x90", "\xC5\x95" => "\xC5\x94",
- "\xC5\x97" => "\xC5\x96", "\xC5\x99" => "\xC5\x98", "\xC5\x9B" => "\xC5\x9A", "\xC5\x9D" => "\xC5\x9C",
- "\xC5\x9F" => "\xC5\x9E", "\xC5\xA1" => "\xC5\xA0", "\xC5\xA3" => "\xC5\xA2", "\xC5\xA5" => "\xC5\xA4",
- "\xC5\xA7" => "\xC5\xA6", "\xC5\xA9" => "\xC5\xA8", "\xC5\xAB" => "\xC5\xAA", "\xC5\xAD" => "\xC5\xAC",
- "\xC5\xAF" => "\xC5\xAE", "\xC5\xB1" => "\xC5\xB0", "\xC5\xB3" => "\xC5\xB2", "\xC5\xB5" => "\xC5\xB4",
- "\xC5\xB7" => "\xC5\xB6", "\xC5\xBA" => "\xC5\xB9", "\xC5\xBC" => "\xC5\xBB", "\xC5\xBE" => "\xC5\xBD",
- "\xC6\xA1" => "\xC6\xA0", "\xC6\xB0" => "\xC6\xAF", "\xC8\x99" => "\xC8\x98", "\xC8\x9B" => "\xC8\x9A",
- "\xCE\xAC" => "\xCE\x86", "\xCE\xAD" => "\xCE\x88", "\xCE\xAE" => "\xCE\x89", "\xCE\xAF" => "\xCE\x8A",
- "\xCE\xB1" => "\xCE\x91", "\xCE\xB2" => "\xCE\x92", "\xCE\xB3" => "\xCE\x93", "\xCE\xB4" => "\xCE\x94",
- "\xCE\xB5" => "\xCE\x95", "\xCE\xB6" => "\xCE\x96", "\xCE\xB7" => "\xCE\x97", "\xCE\xB8" => "\xCE\x98",
- "\xCE\xB9" => "\xCE\x99", "\xCE\xBA" => "\xCE\x9A", "\xCE\xBB" => "\xCE\x9B", "\xCE\xBC" => "\xCE\x9C",
- "\xCE\xBD" => "\xCE\x9D", "\xCE\xBE" => "\xCE\x9E", "\xCE\xBF" => "\xCE\x9F", "\xCF\x80" => "\xCE\xA0",
- "\xCF\x81" => "\xCE\xA1", "\xCF\x83" => "\xCE\xA3", "\xCF\x84" => "\xCE\xA4", "\xCF\x85" => "\xCE\xA5",
- "\xCF\x86" => "\xCE\xA6", "\xCF\x87" => "\xCE\xA7", "\xCF\x88" => "\xCE\xA8", "\xCF\x89" => "\xCE\xA9",
- "\xCF\x8A" => "\xCE\xAA", "\xCF\x8B" => "\xCE\xAB", "\xCF\x8C" => "\xCE\x8C", "\xCF\x8D" => "\xCE\x8E",
- "\xCF\x8E" => "\xCE\x8F", "\xD0\xB0" => "\xD0\x90", "\xD0\xB1" => "\xD0\x91", "\xD0\xB2" => "\xD0\x92",
- "\xD0\xB3" => "\xD0\x93", "\xD0\xB4" => "\xD0\x94", "\xD0\xB5" => "\xD0\x95", "\xD0\xB6" => "\xD0\x96",
- "\xD0\xB7" => "\xD0\x97", "\xD0\xB8" => "\xD0\x98", "\xD0\xB9" => "\xD0\x99", "\xD0\xBA" => "\xD0\x9A",
- "\xD0\xBB" => "\xD0\x9B", "\xD0\xBC" => "\xD0\x9C", "\xD0\xBD" => "\xD0\x9D", "\xD0\xBE" => "\xD0\x9E",
- "\xD0\xBF" => "\xD0\x9F", "\xD1\x80" => "\xD0\xA0", "\xD1\x81" => "\xD0\xA1", "\xD1\x82" => "\xD0\xA2",
- "\xD1\x83" => "\xD0\xA3", "\xD1\x84" => "\xD0\xA4", "\xD1\x85" => "\xD0\xA5", "\xD1\x86" => "\xD0\xA6",
- "\xD1\x87" => "\xD0\xA7", "\xD1\x88" => "\xD0\xA8", "\xD1\x89" => "\xD0\xA9", "\xD1\x8A" => "\xD0\xAA",
- "\xD1\x8B" => "\xD0\xAB", "\xD1\x8C" => "\xD0\xAC", "\xD1\x8D" => "\xD0\xAD", "\xD1\x8E" => "\xD0\xAE",
- "\xD1\x8F" => "\xD0\xAF", "\xD1\x91" => "\xD0\x81", "\xD1\x92" => "\xD0\x82", "\xD1\x93" => "\xD0\x83",
- "\xD1\x94" => "\xD0\x84", "\xD1\x95" => "\xD0\x85", "\xD1\x96" => "\xD0\x86", "\xD1\x97" => "\xD0\x87",
- "\xD1\x98" => "\xD0\x88", "\xD1\x99" => "\xD0\x89", "\xD1\x9A" => "\xD0\x8A", "\xD1\x9B" => "\xD0\x8B",
- "\xD1\x9C" => "\xD0\x8C", "\xD1\x9E" => "\xD0\x8E", "\xD1\x9F" => "\xD0\x8F", "\xD2\x91" => "\xD2\x90",
- "\xE1\xB8\x83" => "\xE1\xB8\x82", "\xE1\xB8\x8B" => "\xE1\xB8\x8A", "\xE1\xB8\x9F" => "\xE1\xB8\x9E", "\xE1\xB9\x81" => "\xE1\xB9\x80",
- "\xE1\xB9\x97" => "\xE1\xB9\x96", "\xE1\xB9\xA1" => "\xE1\xB9\xA0", "\xE1\xB9\xAB" => "\xE1\xB9\xAA", "\xE1\xBA\x81" => "\xE1\xBA\x80",
- "\xE1\xBA\x83" => "\xE1\xBA\x82", "\xE1\xBA\x85" => "\xE1\xBA\x84", "\xE1\xBB\xB3" => "\xE1\xBB\xB2"
- );
-
/**
* UTF-8 aware alternative to strtolower
* Make a string lowercase
@@ -443,9 +335,56 @@ else
*/
function utf8_strtolower($string)
{
- global $UTF8_UPPER_TO_LOWER;
-
- return strtr($string, $UTF8_UPPER_TO_LOWER);
+ static $UTF8_UPPER_TO_LOWER = array(
+ "\xC3\x80" => "\xC3\xA0", "\xC3\x81" => "\xC3\xA1",
+ "\xC3\x82" => "\xC3\xA2", "\xC3\x83" => "\xC3\xA3", "\xC3\x84" => "\xC3\xA4", "\xC3\x85" => "\xC3\xA5",
+ "\xC3\x86" => "\xC3\xA6", "\xC3\x87" => "\xC3\xA7", "\xC3\x88" => "\xC3\xA8", "\xC3\x89" => "\xC3\xA9",
+ "\xC3\x8A" => "\xC3\xAA", "\xC3\x8B" => "\xC3\xAB", "\xC3\x8C" => "\xC3\xAC", "\xC3\x8D" => "\xC3\xAD",
+ "\xC3\x8E" => "\xC3\xAE", "\xC3\x8F" => "\xC3\xAF", "\xC3\x90" => "\xC3\xB0", "\xC3\x91" => "\xC3\xB1",
+ "\xC3\x92" => "\xC3\xB2", "\xC3\x93" => "\xC3\xB3", "\xC3\x94" => "\xC3\xB4", "\xC3\x95" => "\xC3\xB5",
+ "\xC3\x96" => "\xC3\xB6", "\xC3\x98" => "\xC3\xB8", "\xC3\x99" => "\xC3\xB9", "\xC3\x9A" => "\xC3\xBA",
+ "\xC3\x9B" => "\xC3\xBB", "\xC3\x9C" => "\xC3\xBC", "\xC3\x9D" => "\xC3\xBD", "\xC3\x9E" => "\xC3\xBE",
+ "\xC4\x80" => "\xC4\x81", "\xC4\x82" => "\xC4\x83", "\xC4\x84" => "\xC4\x85", "\xC4\x86" => "\xC4\x87",
+ "\xC4\x88" => "\xC4\x89", "\xC4\x8A" => "\xC4\x8B", "\xC4\x8C" => "\xC4\x8D", "\xC4\x8E" => "\xC4\x8F",
+ "\xC4\x90" => "\xC4\x91", "\xC4\x92" => "\xC4\x93", "\xC4\x96" => "\xC4\x97", "\xC4\x98" => "\xC4\x99",
+ "\xC4\x9A" => "\xC4\x9B", "\xC4\x9C" => "\xC4\x9D", "\xC4\x9E" => "\xC4\x9F", "\xC4\xA0" => "\xC4\xA1",
+ "\xC4\xA2" => "\xC4\xA3", "\xC4\xA4" => "\xC4\xA5", "\xC4\xA6" => "\xC4\xA7", "\xC4\xA8" => "\xC4\xA9",
+ "\xC4\xAA" => "\xC4\xAB", "\xC4\xAE" => "\xC4\xAF", "\xC4\xB4" => "\xC4\xB5", "\xC4\xB6" => "\xC4\xB7",
+ "\xC4\xB9" => "\xC4\xBA", "\xC4\xBB" => "\xC4\xBC", "\xC4\xBD" => "\xC4\xBE", "\xC5\x81" => "\xC5\x82",
+ "\xC5\x83" => "\xC5\x84", "\xC5\x85" => "\xC5\x86", "\xC5\x87" => "\xC5\x88", "\xC5\x8A" => "\xC5\x8B",
+ "\xC5\x8C" => "\xC5\x8D", "\xC5\x90" => "\xC5\x91", "\xC5\x94" => "\xC5\x95", "\xC5\x96" => "\xC5\x97",
+ "\xC5\x98" => "\xC5\x99", "\xC5\x9A" => "\xC5\x9B", "\xC5\x9C" => "\xC5\x9D", "\xC5\x9E" => "\xC5\x9F",
+ "\xC5\xA0" => "\xC5\xA1", "\xC5\xA2" => "\xC5\xA3", "\xC5\xA4" => "\xC5\xA5", "\xC5\xA6" => "\xC5\xA7",
+ "\xC5\xA8" => "\xC5\xA9", "\xC5\xAA" => "\xC5\xAB", "\xC5\xAC" => "\xC5\xAD", "\xC5\xAE" => "\xC5\xAF",
+ "\xC5\xB0" => "\xC5\xB1", "\xC5\xB2" => "\xC5\xB3", "\xC5\xB4" => "\xC5\xB5", "\xC5\xB6" => "\xC5\xB7",
+ "\xC5\xB8" => "\xC3\xBF", "\xC5\xB9" => "\xC5\xBA", "\xC5\xBB" => "\xC5\xBC", "\xC5\xBD" => "\xC5\xBE",
+ "\xC6\xA0" => "\xC6\xA1", "\xC6\xAF" => "\xC6\xB0", "\xC8\x98" => "\xC8\x99", "\xC8\x9A" => "\xC8\x9B",
+ "\xCE\x86" => "\xCE\xAC", "\xCE\x88" => "\xCE\xAD", "\xCE\x89" => "\xCE\xAE", "\xCE\x8A" => "\xCE\xAF",
+ "\xCE\x8C" => "\xCF\x8C", "\xCE\x8E" => "\xCF\x8D", "\xCE\x8F" => "\xCF\x8E", "\xCE\x91" => "\xCE\xB1",
+ "\xCE\x92" => "\xCE\xB2", "\xCE\x93" => "\xCE\xB3", "\xCE\x94" => "\xCE\xB4", "\xCE\x95" => "\xCE\xB5",
+ "\xCE\x96" => "\xCE\xB6", "\xCE\x97" => "\xCE\xB7", "\xCE\x98" => "\xCE\xB8", "\xCE\x99" => "\xCE\xB9",
+ "\xCE\x9A" => "\xCE\xBA", "\xCE\x9B" => "\xCE\xBB", "\xCE\x9C" => "\xCE\xBC", "\xCE\x9D" => "\xCE\xBD",
+ "\xCE\x9E" => "\xCE\xBE", "\xCE\x9F" => "\xCE\xBF", "\xCE\xA0" => "\xCF\x80", "\xCE\xA1" => "\xCF\x81",
+ "\xCE\xA3" => "\xCF\x83", "\xCE\xA4" => "\xCF\x84", "\xCE\xA5" => "\xCF\x85", "\xCE\xA6" => "\xCF\x86",
+ "\xCE\xA7" => "\xCF\x87", "\xCE\xA8" => "\xCF\x88", "\xCE\xA9" => "\xCF\x89", "\xCE\xAA" => "\xCF\x8A",
+ "\xCE\xAB" => "\xCF\x8B", "\xD0\x81" => "\xD1\x91", "\xD0\x82" => "\xD1\x92", "\xD0\x83" => "\xD1\x93",
+ "\xD0\x84" => "\xD1\x94", "\xD0\x85" => "\xD1\x95", "\xD0\x86" => "\xD1\x96", "\xD0\x87" => "\xD1\x97",
+ "\xD0\x88" => "\xD1\x98", "\xD0\x89" => "\xD1\x99", "\xD0\x8A" => "\xD1\x9A", "\xD0\x8B" => "\xD1\x9B",
+ "\xD0\x8C" => "\xD1\x9C", "\xD0\x8E" => "\xD1\x9E", "\xD0\x8F" => "\xD1\x9F", "\xD0\x90" => "\xD0\xB0",
+ "\xD0\x91" => "\xD0\xB1", "\xD0\x92" => "\xD0\xB2", "\xD0\x93" => "\xD0\xB3", "\xD0\x94" => "\xD0\xB4",
+ "\xD0\x95" => "\xD0\xB5", "\xD0\x96" => "\xD0\xB6", "\xD0\x97" => "\xD0\xB7", "\xD0\x98" => "\xD0\xB8",
+ "\xD0\x99" => "\xD0\xB9", "\xD0\x9A" => "\xD0\xBA", "\xD0\x9B" => "\xD0\xBB", "\xD0\x9C" => "\xD0\xBC",
+ "\xD0\x9D" => "\xD0\xBD", "\xD0\x9E" => "\xD0\xBE", "\xD0\x9F" => "\xD0\xBF", "\xD0\xA0" => "\xD1\x80",
+ "\xD0\xA1" => "\xD1\x81", "\xD0\xA2" => "\xD1\x82", "\xD0\xA3" => "\xD1\x83", "\xD0\xA4" => "\xD1\x84",
+ "\xD0\xA5" => "\xD1\x85", "\xD0\xA6" => "\xD1\x86", "\xD0\xA7" => "\xD1\x87", "\xD0\xA8" => "\xD1\x88",
+ "\xD0\xA9" => "\xD1\x89", "\xD0\xAA" => "\xD1\x8A", "\xD0\xAB" => "\xD1\x8B", "\xD0\xAC" => "\xD1\x8C",
+ "\xD0\xAD" => "\xD1\x8D", "\xD0\xAE" => "\xD1\x8E", "\xD0\xAF" => "\xD1\x8F", "\xD2\x90" => "\xD2\x91",
+ "\xE1\xB8\x82" => "\xE1\xB8\x83", "\xE1\xB8\x8A" => "\xE1\xB8\x8B", "\xE1\xB8\x9E" => "\xE1\xB8\x9F", "\xE1\xB9\x80" => "\xE1\xB9\x81",
+ "\xE1\xB9\x96" => "\xE1\xB9\x97", "\xE1\xB9\xA0" => "\xE1\xB9\xA1", "\xE1\xB9\xAA" => "\xE1\xB9\xAB", "\xE1\xBA\x80" => "\xE1\xBA\x81",
+ "\xE1\xBA\x82" => "\xE1\xBA\x83", "\xE1\xBA\x84" => "\xE1\xBA\x85", "\xE1\xBB\xB2" => "\xE1\xBB\xB3"
+ );
+
+ return strtr(strtolower($string), $UTF8_UPPER_TO_LOWER);
}
/**
@@ -461,9 +400,56 @@ else
*/
function utf8_strtoupper($string)
{
- global $UTF8_LOWER_TO_UPPER;
-
- return strtr($string, $UTF8_LOWER_TO_UPPER);
+ static $UTF8_LOWER_TO_UPPER = array(
+ "\xC3\xA0" => "\xC3\x80", "\xC3\xA1" => "\xC3\x81",
+ "\xC3\xA2" => "\xC3\x82", "\xC3\xA3" => "\xC3\x83", "\xC3\xA4" => "\xC3\x84", "\xC3\xA5" => "\xC3\x85",
+ "\xC3\xA6" => "\xC3\x86", "\xC3\xA7" => "\xC3\x87", "\xC3\xA8" => "\xC3\x88", "\xC3\xA9" => "\xC3\x89",
+ "\xC3\xAA" => "\xC3\x8A", "\xC3\xAB" => "\xC3\x8B", "\xC3\xAC" => "\xC3\x8C", "\xC3\xAD" => "\xC3\x8D",
+ "\xC3\xAE" => "\xC3\x8E", "\xC3\xAF" => "\xC3\x8F", "\xC3\xB0" => "\xC3\x90", "\xC3\xB1" => "\xC3\x91",
+ "\xC3\xB2" => "\xC3\x92", "\xC3\xB3" => "\xC3\x93", "\xC3\xB4" => "\xC3\x94", "\xC3\xB5" => "\xC3\x95",
+ "\xC3\xB6" => "\xC3\x96", "\xC3\xB8" => "\xC3\x98", "\xC3\xB9" => "\xC3\x99", "\xC3\xBA" => "\xC3\x9A",
+ "\xC3\xBB" => "\xC3\x9B", "\xC3\xBC" => "\xC3\x9C", "\xC3\xBD" => "\xC3\x9D", "\xC3\xBE" => "\xC3\x9E",
+ "\xC3\xBF" => "\xC5\xB8", "\xC4\x81" => "\xC4\x80", "\xC4\x83" => "\xC4\x82", "\xC4\x85" => "\xC4\x84",
+ "\xC4\x87" => "\xC4\x86", "\xC4\x89" => "\xC4\x88", "\xC4\x8B" => "\xC4\x8A", "\xC4\x8D" => "\xC4\x8C",
+ "\xC4\x8F" => "\xC4\x8E", "\xC4\x91" => "\xC4\x90", "\xC4\x93" => "\xC4\x92", "\xC4\x97" => "\xC4\x96",
+ "\xC4\x99" => "\xC4\x98", "\xC4\x9B" => "\xC4\x9A", "\xC4\x9D" => "\xC4\x9C", "\xC4\x9F" => "\xC4\x9E",
+ "\xC4\xA1" => "\xC4\xA0", "\xC4\xA3" => "\xC4\xA2", "\xC4\xA5" => "\xC4\xA4", "\xC4\xA7" => "\xC4\xA6",
+ "\xC4\xA9" => "\xC4\xA8", "\xC4\xAB" => "\xC4\xAA", "\xC4\xAF" => "\xC4\xAE", "\xC4\xB5" => "\xC4\xB4",
+ "\xC4\xB7" => "\xC4\xB6", "\xC4\xBA" => "\xC4\xB9", "\xC4\xBC" => "\xC4\xBB", "\xC4\xBE" => "\xC4\xBD",
+ "\xC5\x82" => "\xC5\x81", "\xC5\x84" => "\xC5\x83", "\xC5\x86" => "\xC5\x85", "\xC5\x88" => "\xC5\x87",
+ "\xC5\x8B" => "\xC5\x8A", "\xC5\x8D" => "\xC5\x8C", "\xC5\x91" => "\xC5\x90", "\xC5\x95" => "\xC5\x94",
+ "\xC5\x97" => "\xC5\x96", "\xC5\x99" => "\xC5\x98", "\xC5\x9B" => "\xC5\x9A", "\xC5\x9D" => "\xC5\x9C",
+ "\xC5\x9F" => "\xC5\x9E", "\xC5\xA1" => "\xC5\xA0", "\xC5\xA3" => "\xC5\xA2", "\xC5\xA5" => "\xC5\xA4",
+ "\xC5\xA7" => "\xC5\xA6", "\xC5\xA9" => "\xC5\xA8", "\xC5\xAB" => "\xC5\xAA", "\xC5\xAD" => "\xC5\xAC",
+ "\xC5\xAF" => "\xC5\xAE", "\xC5\xB1" => "\xC5\xB0", "\xC5\xB3" => "\xC5\xB2", "\xC5\xB5" => "\xC5\xB4",
+ "\xC5\xB7" => "\xC5\xB6", "\xC5\xBA" => "\xC5\xB9", "\xC5\xBC" => "\xC5\xBB", "\xC5\xBE" => "\xC5\xBD",
+ "\xC6\xA1" => "\xC6\xA0", "\xC6\xB0" => "\xC6\xAF", "\xC8\x99" => "\xC8\x98", "\xC8\x9B" => "\xC8\x9A",
+ "\xCE\xAC" => "\xCE\x86", "\xCE\xAD" => "\xCE\x88", "\xCE\xAE" => "\xCE\x89", "\xCE\xAF" => "\xCE\x8A",
+ "\xCE\xB1" => "\xCE\x91", "\xCE\xB2" => "\xCE\x92", "\xCE\xB3" => "\xCE\x93", "\xCE\xB4" => "\xCE\x94",
+ "\xCE\xB5" => "\xCE\x95", "\xCE\xB6" => "\xCE\x96", "\xCE\xB7" => "\xCE\x97", "\xCE\xB8" => "\xCE\x98",
+ "\xCE\xB9" => "\xCE\x99", "\xCE\xBA" => "\xCE\x9A", "\xCE\xBB" => "\xCE\x9B", "\xCE\xBC" => "\xCE\x9C",
+ "\xCE\xBD" => "\xCE\x9D", "\xCE\xBE" => "\xCE\x9E", "\xCE\xBF" => "\xCE\x9F", "\xCF\x80" => "\xCE\xA0",
+ "\xCF\x81" => "\xCE\xA1", "\xCF\x83" => "\xCE\xA3", "\xCF\x84" => "\xCE\xA4", "\xCF\x85" => "\xCE\xA5",
+ "\xCF\x86" => "\xCE\xA6", "\xCF\x87" => "\xCE\xA7", "\xCF\x88" => "\xCE\xA8", "\xCF\x89" => "\xCE\xA9",
+ "\xCF\x8A" => "\xCE\xAA", "\xCF\x8B" => "\xCE\xAB", "\xCF\x8C" => "\xCE\x8C", "\xCF\x8D" => "\xCE\x8E",
+ "\xCF\x8E" => "\xCE\x8F", "\xD0\xB0" => "\xD0\x90", "\xD0\xB1" => "\xD0\x91", "\xD0\xB2" => "\xD0\x92",
+ "\xD0\xB3" => "\xD0\x93", "\xD0\xB4" => "\xD0\x94", "\xD0\xB5" => "\xD0\x95", "\xD0\xB6" => "\xD0\x96",
+ "\xD0\xB7" => "\xD0\x97", "\xD0\xB8" => "\xD0\x98", "\xD0\xB9" => "\xD0\x99", "\xD0\xBA" => "\xD0\x9A",
+ "\xD0\xBB" => "\xD0\x9B", "\xD0\xBC" => "\xD0\x9C", "\xD0\xBD" => "\xD0\x9D", "\xD0\xBE" => "\xD0\x9E",
+ "\xD0\xBF" => "\xD0\x9F", "\xD1\x80" => "\xD0\xA0", "\xD1\x81" => "\xD0\xA1", "\xD1\x82" => "\xD0\xA2",
+ "\xD1\x83" => "\xD0\xA3", "\xD1\x84" => "\xD0\xA4", "\xD1\x85" => "\xD0\xA5", "\xD1\x86" => "\xD0\xA6",
+ "\xD1\x87" => "\xD0\xA7", "\xD1\x88" => "\xD0\xA8", "\xD1\x89" => "\xD0\xA9", "\xD1\x8A" => "\xD0\xAA",
+ "\xD1\x8B" => "\xD0\xAB", "\xD1\x8C" => "\xD0\xAC", "\xD1\x8D" => "\xD0\xAD", "\xD1\x8E" => "\xD0\xAE",
+ "\xD1\x8F" => "\xD0\xAF", "\xD1\x91" => "\xD0\x81", "\xD1\x92" => "\xD0\x82", "\xD1\x93" => "\xD0\x83",
+ "\xD1\x94" => "\xD0\x84", "\xD1\x95" => "\xD0\x85", "\xD1\x96" => "\xD0\x86", "\xD1\x97" => "\xD0\x87",
+ "\xD1\x98" => "\xD0\x88", "\xD1\x99" => "\xD0\x89", "\xD1\x9A" => "\xD0\x8A", "\xD1\x9B" => "\xD0\x8B",
+ "\xD1\x9C" => "\xD0\x8C", "\xD1\x9E" => "\xD0\x8E", "\xD1\x9F" => "\xD0\x8F", "\xD2\x91" => "\xD2\x90",
+ "\xE1\xB8\x83" => "\xE1\xB8\x82", "\xE1\xB8\x8B" => "\xE1\xB8\x8A", "\xE1\xB8\x9F" => "\xE1\xB8\x9E", "\xE1\xB9\x81" => "\xE1\xB9\x80",
+ "\xE1\xB9\x97" => "\xE1\xB9\x96", "\xE1\xB9\xA1" => "\xE1\xB9\xA0", "\xE1\xB9\xAB" => "\xE1\xB9\xAA", "\xE1\xBA\x81" => "\xE1\xBA\x80",
+ "\xE1\xBA\x83" => "\xE1\xBA\x82", "\xE1\xBA\x85" => "\xE1\xBA\x84", "\xE1\xBB\xB3" => "\xE1\xBB\xB2"
+ );
+
+ return strtr(strtoupper($string), $UTF8_LOWER_TO_UPPER);
}
/**
@@ -594,7 +580,7 @@ else
$ly = (-$length) % 65535;
// negative length requires ... capture everything
- // except a group of -length characters
+ // except a group of -length characters
// anchored at the tail-end of the string
if ($lx)
{
@@ -636,7 +622,7 @@ else
*/
function utf8_str_split($str, $split_len = 1)
{
- if (!preg_match('/^[0-9]+$/', $split_len) || $split_len < 1)
+ if (!is_int($split_len) || $split_len < 1)
{
return false;
}
@@ -659,8 +645,6 @@ function utf8_str_split($str, $split_len = 1)
*/
function utf8_strspn($str, $mask, $start = null, $length = null)
{
- $mask = preg_replace('!([\\\\\\-\\]\\[/^])!', '\\\${1}', $mask);
-
if ($start !== null || $length !== null)
{
$str = utf8_substr($str, $start, $length);
@@ -767,14 +751,140 @@ function utf8_recode($string, $encoding)
trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
}
- global $phpbb_root_path;
+ global $phpbb_root_path, $phpEx;
- if (!file_exists($phpbb_root_path . 'includes/utf/data/'))
+ // iso-8859-* character encoding
+ if (preg_match('/iso[_ -]?8859[_ -]?(\\d+)/', $encoding, $array))
{
- return $string;
+ switch ($array[1])
+ {
+ case '1':
+ case '2':
+ case '4':
+ case '7':
+ case '9':
+ case '15':
+ if (!function_exists('iso_8859_' . $array[1]))
+ {
+ if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx))
+ {
+ trigger_error('Basic reencoder file is missing', E_USER_ERROR);
+ }
+ include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx);
+ }
+ return call_user_func('iso_8859_' . $array[1], $string);
+ break;
+
+ default:
+ trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
+ break;
+ }
+ }
+
+ // CP/WIN character encoding
+ if (preg_match('/(?:cp|windows)[_\- ]?(\\d+)/', $encoding, $array))
+ {
+ switch ($array[1])
+ {
+ case '932':
+ break;
+ case '1250':
+ case '1251':
+ case '1254':
+ case '1255':
+ case '1256':
+ case '1257':
+ case '874':
+ if (!function_exists('cp' . $array[1]))
+ {
+ if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx))
+ {
+ trigger_error('Basic reencoder file is missing', E_USER_ERROR);
+ }
+ include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx);
+ }
+ return call_user_func('cp' . $array[1], $string);
+ break;
+
+ default:
+ trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
+ break;
+ }
+ }
+
+ // TIS-620
+ if (preg_match('/tis[_ -]?620/', $encoding))
+ {
+ if (!function_exists('tis_620'))
+ {
+ if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx))
+ {
+ trigger_error('Basic reencoder file is missing', E_USER_ERROR);
+ }
+ include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx);
+ }
+ return tis_620($string);
+ }
+
+ // SJIS
+ if (preg_match('/sjis(?:[_ -]?win)?|(?:cp|ibm)[_ -]?932|shift[_ -]?jis/', $encoding))
+ {
+ if (!function_exists('sjis'))
+ {
+ if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
+ {
+ trigger_error('CJK reencoder file is missing', E_USER_ERROR);
+ }
+ include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
+ }
+ return sjis($string);
+ }
+
+ // EUC_KR
+ if (preg_match('/euc[_ -]?kr/', $encoding))
+ {
+ if (!function_exists('euc_kr'))
+ {
+ if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
+ {
+ trigger_error('CJK reencoder file is missing', E_USER_ERROR);
+ }
+ include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
+ }
+ return euc_kr($string);
}
- die('Finish me!! ' . basename(__FILE__) . ' at line ' . __LINE__);
+ // BIG-5
+ if (preg_match('/big[_ -]?5/', $encoding))
+ {
+ if (!function_exists('big5'))
+ {
+ if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
+ {
+ trigger_error('CJK reencoder file is missing', E_USER_ERROR);
+ }
+ include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
+ }
+ return big5($string);
+ }
+
+ // GB2312
+ if (preg_match('/gb[_ -]?2312/', $encoding))
+ {
+ if (!function_exists('gb2312'))
+ {
+ if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
+ {
+ trigger_error('CJK reencoder file is missing', E_USER_ERROR);
+ }
+ include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
+ }
+ return gb2312($string);
+ }
+
+ // Trigger an error?! Fow now just give bad data :-(
+ //trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
+ return $string;
}
/**
@@ -993,28 +1103,170 @@ function utf8_clean_string($text)
utf_normalizer::nfc($text);
static $homographs = array(
- // cyrllic
- "\xD0\xB0" => "\x61",
- "\xD0\xB5" => "\x65",
- "\xD0\xBE" => "\x6F",
- "\xD1\x80" => "\x70",
- "\xD1\x81" => "\x63",
- "\xD1\x83" => "\x79",
- "\xD1\x85" => "\x78",
- "\xD1\x95" => "\x73",
- "\xD1\x96" => "\x69",
- "\xD1\x98" => "\x6A",
- "\xD2\xBB" => "\x68",
- // greek
- "\xCE\xB1" => "\x61",
- "\xCE\xBF" => "\x6F",
- // other
- "\xC2\xA1" => "\x69",
+ "\xC2\xA1" => "\x69", // EXCLAMATION MARK, INVERTED => LATIN SMALL LETTER I
+ "\xC2\xAD" => '', // HYPHEN, SOFT => empty string
+ "\xC4\x90" => "\xC3\x90", // LATIN CAPITAL LETTER D WITH STROKE => LATIN CAPITAL LETTER ETH
+ "\xC7\x83" => "\x21", // LATIN LETTER RETROFLEX CLICK => EXCLAMATION MARK
+ "\xC9\x85" => "\xCE\x9B", // LATIN CAPITAL LETTER TURNED V => GREEK CAPITAL LETTER LAMDA
+ "\xC9\x99" => "\xC7\x9D", // LATIN SMALL LETTER SCHWA => LATIN SMALL LETTER TURNED E
+ "\xCA\x99" => "\xD0\xB2", // LATIN LETTER SMALL CAPITAL B => CYRILLIC SMALL LETTER VE
+ "\xCA\x9C" => "\xD0\xBD", // LATIN LETTER SMALL CAPITAL H => CYRILLIC SMALL LETTER EN
+ "\xCE\x91" => "\x41", // GREEK CAPITAL LETTER ALPHA => LATIN CAPITAL LETTER A
+ "\xCE\x92" => "\x42", // GREEK CAPITAL LETTER BETA => LATIN CAPITAL LETTER B
+ "\xCE\x95" => "\x45", // GREEK CAPITAL LETTER EPSILON => LATIN CAPITAL LETTER E
+ "\xCE\x96" => "\x5A", // GREEK CAPITAL LETTER ZETA => LATIN CAPITAL LETTER Z
+ "\xCE\x97" => "\x48", // GREEK CAPITAL LETTER ETA => LATIN CAPITAL LETTER H
+ "\xCE\x99" => "\x49", // GREEK CAPITAL LETTER IOTA => LATIN CAPITAL LETTER I
+ "\xCE\x9A" => "\x4B", // GREEK CAPITAL LETTER KAPPA => LATIN CAPITAL LETTER K
+ "\xCE\x9C" => "\x4D", // GREEK CAPITAL LETTER MU => LATIN CAPITAL LETTER M
+ "\xCE\x9D" => "\x4E", // GREEK CAPITAL LETTER NU => LATIN CAPITAL LETTER N
+ "\xCE\x9F" => "\x4F", // GREEK CAPITAL LETTER OMICRON => LATIN CAPITAL LETTER O
+ "\xCE\xA1" => "\x50", // GREEK CAPITAL LETTER RHO => LATIN CAPITAL LETTER P
+ "\xCE\xA3" => "\xC6\xA9", // GREEK CAPITAL LETTER SIGMA => LATIN CAPITAL LETTER ESH
+ "\xCE\xA4" => "\x54", // GREEK CAPITAL LETTER TAU => LATIN CAPITAL LETTER T
+ "\xCE\xA5" => "\x59", // GREEK CAPITAL LETTER UPSILON => LATIN CAPITAL LETTER Y
+ "\xCE\xA7" => "\x58", // GREEK CAPITAL LETTER CHI => LATIN CAPITAL LETTER X
+ "\xCE\xB1" => "\x61", // GREEK SMALL LETTER ALPHA => LATIN SMALL LETTER A
+ "\xCE\xB5" => "\xC9\x9B", // GREEK SMALL LETTER EPSILON => LATIN SMALL LETTER OPEN E
+ "\xCE\xB9" => "\xC9\xA9", // GREEK SMALL LETTER IOTA => LATIN SMALL LETTER IOTA
+ "\xCE\xBF" => "\x6F", // GREEK SMALL LETTER OMICRON => LATIN SMALL LETTER O
+ "\xCF\xB3" => "\x6A", // GREEK LETTER YOT => LATIN SMALL LETTER J
+ "\xD0\x85" => "\x53", // CYRILLIC CAPITAL LETTER DZE => LATIN CAPITAL LETTER S
+ "\xD0\x88" => "\x4A", // CYRILLIC CAPITAL LETTER JE => LATIN CAPITAL LETTER J
+ "\xD0\x91" => "\xC6\x82", // CYRILLIC CAPITAL LETTER BE => LATIN CAPITAL LETTER B WITH TOPBAR
+ "\xD0\x93" => "\xCE\x93", // CYRILLIC CAPITAL LETTER GHE => GREEK CAPITAL LETTER GAMMA
+ "\xD0\x9F" => "\xCE\xA0", // CYRILLIC CAPITAL LETTER PE => GREEK CAPITAL LETTER PI
+ "\xD0\xA1" => "\x43", // CYRILLIC CAPITAL LETTER ES => LATIN CAPITAL LETTER C
+ "\xD0\xB0" => "\x61", // CYRILLIC SMALL LETTER A => LATIN SMALL LETTER A
+ "\xD0\xB5" => "\x65", // CYRILLIC SMALL LETTER IE => LATIN SMALL LETTER E
+ "\xD0\xBA" => "\xC4\xB8", // CYRILLIC SMALL LETTER KA => LATIN SMALL LETTER KRA
+ "\xD0\xBE" => "\x6F", // CYRILLIC SMALL LETTER O => LATIN SMALL LETTER O
+ "\xD1\x80" => "\x70", // CYRILLIC SMALL LETTER ER => LATIN SMALL LETTER P
+ "\xD1\x81" => "\x63", // CYRILLIC SMALL LETTER ES => LATIN SMALL LETTER C
+ "\xD1\x83" => "\x79", // CYRILLIC SMALL LETTER U => LATIN SMALL LETTER Y
+ "\xD1\x85" => "\x78", // CYRILLIC SMALL LETTER HA => LATIN SMALL LETTER X
+ "\xD1\x95" => "\x73", // CYRILLIC SMALL LETTER DZE => LATIN SMALL LETTER S
+ "\xD1\x96" => "\x69", // CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I => LATIN SMALL LETTER I
+ "\xD1\x98" => "\x6A", // CYRILLIC SMALL LETTER JE => LATIN SMALL LETTER J
+ "\xD2\xBB" => "\x68", // CYRILLIC SMALL LETTER SHHA => LATIN SMALL LETTER H
+ "\xD3\x8F" => "\xC9\xAA", // CYRILLIC SMALL LETTER PALOCHKA => LATIN LETTER SMALL CAPITAL I
+ "\xD3\x94" => "\xC3\x86", // CYRILLIC CAPITAL LIGATURE A IE => LATIN CAPITAL LETTER AE
+ "\xD3\x95" => "\xC3\xA6", // CYRILLIC SMALL LIGATURE A IE => LATIN SMALL LETTER AE
+ "\xD3\x98" => "\xC6\x8E", // CYRILLIC CAPITAL LETTER SCHWA => LATIN CAPITAL LETTER REVERSED E
+ "\xD3\x99" => "\xC7\x9D", // CYRILLIC SMALL LETTER SCHWA => LATIN SMALL LETTER TURNED E
+ "\xD3\xA1" => "\xCA\x92", // CYRILLIC SMALL LETTER ABKHASIAN DZE => LATIN SMALL LETTER EZH
+ "\xD3\xA8" => "\xC6\x9F", // CYRILLIC CAPITAL LETTER BARRED O => LATIN CAPITAL LETTER O WITH MIDDLE TILDE
+ "\xD3\xA9" => "\xC9\xB5", // CYRILLIC SMALL LETTER BARRED O => LATIN SMALL LETTER BARRED O
+ "\xD4\x81" => "\x64", // CYRILLIC SMALL LETTER KOMI DE => LATIN SMALL LETTER D
+ "\xE1\x81\x80" => "\xE1\x80\x9D", // MYANMAR DIGIT ZERO => MYANMAR LETTER WA
+ "\xE1\x9E\xA3" => "\xE1\x9E\xA2", // KHMER INDEPENDENT VOWEL QAQ => KHMER LETTER QA
+ "\xE1\xA1\x95" => "\xE1\xA0\xB5", // MONGOLIAN LETTER TODO YA => MONGOLIAN LETTER JA
+ "\xE1\xA7\x90" => "\xE1\xA6\x9E", // NEW TAI LUE DIGIT ZERO => NEW TAI LUE LETTER LOW VA
+ "\xE1\xAD\x92" => "\xE1\xAC\x8D", // BALINESE DIGIT TWO => BALINESE LETTER LA LENGA
+ "\xE1\xAD\x93" => "\xE1\xAC\x91", // BALINESE DIGIT THREE => BALINESE LETTER OKARA
+ "\xE1\xAD\x98" => "\xE1\xAC\xA8", // BALINESE DIGIT EIGHT => BALINESE LETTER PA KAPAL
+ "\xE1\xAD\x9C" => "\xE1\xAD\x90", // BALINESE WINDU => BALINESE DIGIT ZERO
+ "\xE1\xB4\x8D" => "\xD0\xBC", // LATIN LETTER SMALL CAPITAL M => CYRILLIC SMALL LETTER EM
+ "\xE1\xB4\x9B" => "\xD1\x82", // LATIN LETTER SMALL CAPITAL T => CYRILLIC SMALL LETTER TE
+ "\xE1\xB4\xA6" => "\xD0\xB3", // GREEK LETTER SMALL CAPITAL GAMMA => CYRILLIC SMALL LETTER GHE
+ "\xE1\xB4\xA8" => "\xD0\xBF", // GREEK LETTER SMALL CAPITAL PI => CYRILLIC SMALL LETTER PE
+ "\xE1\xB4\xA9" => "\xE1\xB4\x98", // GREEK LETTER SMALL CAPITAL RHO => LATIN LETTER SMALL CAPITAL P
+ "\xE1\xB4\xAB" => "\xD0\xBB", // CYRILLIC LETTER SMALL CAPITAL EL => CYRILLIC SMALL LETTER EL
+ "\xE2\x8D\xB3" => "\xC9\xA9", // APL FUNCTIONAL SYMBOL IOTA => LATIN SMALL LETTER IOTA
+ "\xE2\x8D\xB4" => "\xCF\x81", // APL FUNCTIONAL SYMBOL RHO => GREEK SMALL LETTER RHO
+ "\xE2\x8D\xB5" => "\xCF\x89", // APL FUNCcTIONAL SYMBOL OMEGA => GREEK SMALL LETTER OMEGA
+ "\xE2\x8D\xBA" => "\xCE\xB1", // APL FUNCTIONAL SYMBOL ALPHA => GREEK SMALL LETTER ALPHA
+ "\xE2\xB1\xA7" => "\xD2\xA2", // LATIN CAPITAL LETTER H WITH DESCENDER => CYRILLIC CAPITAL LETTER EN WITH DESCENDER
+ "\xE2\xB1\xA9" => "\xD2\x9A", // LATIN CAPITAL LETTER K WITH DESCENDER => CYRILLIC CAPITAL LETTER KA WITH DESCENDER
+ "\xF0\x90\x8F\x91" => "\xF0\x90\x8E\x82", // OLD PERSIAN NUMBER ONE => UGARITIC LETTER GAMLA
+ "\xF0\x90\x8F\x93" => "\xF0\x90\x8E\x93", // OLD PERSIAN NUMBER TEN => UGARITIC LETTER AIN
+ "\xF0\x90\x92\xA0" => "\xF0\x90\x92\x86", // OSMANYA DIGIT ZERO => OSMANYA LETTER DEEL
+ "\xF0\x92\x80\xB8" => "\xF0\x90\x8E\x9A", // CUNEIFORM SIGN ASH => UGARITIC LETTER TO
+
+ "\xC2\xA0" => "\x20", // NO-BREAK SPACE
+ "\xE1\x9A\x80" => "\x20", // OGHAM SPACE MARK
+ "\xE2\x80\x80" => "\x20", // EN QUAD
+ "\xE2\x80\x81" => "\x20", // EM QUAD
+ "\xE2\x80\x82" => "\x20", // EN SPACE
+ "\xE2\x80\x83" => "\x20", // EM SPACE
+ "\xE2\x80\x84" => "\x20", // THREE-PER-EM SPACE
+ "\xE2\x80\x85" => "\x20", // FOUR-PER-EM SPACE
+ "\xE2\x80\x86" => "\x20", // SIX-PER-EM SPACE
+ "\xE2\x80\x87" => "\x20", // FIGURE SPACE
+ "\xE2\x80\x88" => "\x20", // PUNCTUATION SPACE
+ "\xE2\x80\x89" => "\x20", // THIN SPACE
+ "\xE2\x80\x8A" => "\x20", // HAIR SPACE
+ "\xE2\x80\xAF" => "\x20", // NARROW NO-BREAK SPACE
+ "\xE2\x81\x9F" => "\x20", // MEDIUM MATHEMATICAL SPACE
+ "\xE3\x80\x80" => "\x20", // IDEOGRAPHIC SPACE
+
+ "\xDB\x9D" => '', // ARABIC END OF AYAH
+ "\xDC\x8F" => '', // SYRIAC ABBREVIATION MARK
+ "\xE1\xA0\x86" => '', // MONGOLIAN TODO SOFT HYPHEN
+ "\xE1\xA0\x8E" => '', // MONGOLIAN VOWEL SEPARATOR
+ "\xE2\x80\x8B" => '', // ZERO WIDTH SPACE
+ "\xE2\x80\x8C" => '', // ZERO WIDTH NON-JOINER
+ "\xE2\x80\x8D" => '', // ZERO WIDTH JOINER
+ "\xE2\x80\xA8" => '', // LINE SEPARATOR
+ "\xE2\x80\xA9" => '', // PARAGRAPH SEPARATOR
+ "\xE2\x81\xA0" => '', // WORD JOINER
+ "\xE2\x81\xA1" => '', // FUNCTION APPLICATION
+ "\xE2\x81\xA2" => '', // INVISIBLE TIMES
+ "\xE2\x81\xA3" => '', // INVISIBLE SEPARATOR
+ "\xE2\x81\xAA" => '', // [CONTROL CHARACTERS]
+ "\xE2\x81\xAB" => '', // [CONTROL CHARACTERS]
+ "\xE2\x81\xAC" => '', // [CONTROL CHARACTERS]
+ "\xE2\x81\xAD" => '', // [CONTROL CHARACTERS]
+ "\xE2\x81\xAE" => '', // [CONTROL CHARACTERS]
+ "\xE2\x81\xAF" => '', // [CONTROL CHARACTERS]
+ "\xEF\xBB\xBF" => '', // ZERO WIDTH NO-BREAK SPACE
+ "\xEF\xBF\xB9" => '', // [CONTROL CHARACTERS]
+ "\xEF\xBF\xBA" => '', // [CONTROL CHARACTERS]
+ "\xEF\xBF\xBB" => '', // [CONTROL CHARACTERS]
+ "\xEF\xBF\xBC" => '', // [CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xB3" => '', // [MUSICAL CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xB4" => '', // [MUSICAL CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xB5" => '', // [MUSICAL CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xB6" => '', // [MUSICAL CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xB7" => '', // [MUSICAL CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xB8" => '', // [MUSICAL CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xB9" => '', // [MUSICAL CONTROL CHARACTERS]
+ "\xF0\x9D\x85\xBA" => '', // [MUSICAL CONTROL CHARACTERS]
);
$text = strtr($text, $homographs);
+ // Other control characters
+ $text = preg_replace('#(?:[\x00-\x1F\x7F]+|(?:\xC2[\x80-\x9F])+)#', '', $text);
+
return $text;
}
+/**
+* A wrapper for htmlspecialchars($value, ENT_COMPAT, 'UTF-8')
+*/
+function utf8_htmlspecialchars(&$value)
+{
+ return htmlspecialchars($value, ENT_COMPAT, 'UTF-8');
+}
+
+/**
+* Trying to convert returned system message to utf8
+*
+* PHP assumes such messages are ISO-8859-1 so we'll do that too
+* and if it breaks messages we'll blame it on them ;-)
+*/
+function utf8_convert_message($message)
+{
+ // First of all check if conversion is neded at all, as there is no point
+ // in converting ASCII messages from ISO-8859-1 to UTF-8
+ if (!preg_match('/[\x80-\xFF]/', $message))
+ {
+ return utf8_htmlspecialchars($message);
+ }
+
+ // else we need to convert some part of the message
+ return utf8_htmlspecialchars(utf8_recode($message, 'ISO-8859-1'));
+}
+
?> \ No newline at end of file