/www/wiki/inc/utf8.php
PHP | 1659 lines | 1001 code | 151 blank | 507 comment | 174 complexity | 1d4742632daf839033c2c80a97c6fbc6 MD5 | raw file
Possible License(s): GPL-2.0
Large files files are truncated, but you can click here to view the full file
- <?php
- /**
- * UTF8 helper functions
- *
- * @license LGPL (http://www.gnu.org/copyleft/lesser.html)
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- /**
- * check for mb_string support
- */
- if(!defined('UTF8_MBSTRING')){
- if(function_exists('mb_substr') && !defined('UTF8_NOMBSTRING')){
- define('UTF8_MBSTRING',1);
- }else{
- define('UTF8_MBSTRING',0);
- }
- }
- if(UTF8_MBSTRING){ mb_internal_encoding('UTF-8'); }
- if(!function_exists('utf8_encodeFN')){
- /**
- * URL-Encode a filename to allow unicodecharacters
- *
- * Slashes are not encoded
- *
- * When the second parameter is true the string will
- * be encoded only if non ASCII characters are detected -
- * This makes it safe to run it multiple times on the
- * same string (default is true)
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see urlencode
- */
- function utf8_encodeFN($file,$safe=true){
- if($safe && preg_match('#^[a-zA-Z0-9/_\-.%]+$#',$file)){
- return $file;
- }
- $file = urlencode($file);
- $file = str_replace('%2F','/',$file);
- return $file;
- }
- }
- if(!function_exists('utf8_decodeFN')){
- /**
- * URL-Decode a filename
- *
- * This is just a wrapper around urldecode
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see urldecode
- */
- function utf8_decodeFN($file){
- $file = urldecode($file);
- return $file;
- }
- }
- if(!function_exists('utf8_isASCII')){
- /**
- * Checks if a string contains 7bit ASCII only
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- function utf8_isASCII($str){
- for($i=0; $i<strlen($str); $i++){
- if(ord($str{$i}) >127) return false;
- }
- return true;
- }
- }
- if(!function_exists('utf8_strip')){
- /**
- * Strips all highbyte chars
- *
- * Returns a pure ASCII7 string
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- function utf8_strip($str){
- $ascii = '';
- for($i=0; $i<strlen($str); $i++){
- if(ord($str{$i}) <128){
- $ascii .= $str{$i};
- }
- }
- return $ascii;
- }
- }
- if(!function_exists('utf8_check')){
- /**
- * Tries to detect if a string is in Unicode encoding
- *
- * @author <bmorel@ssi.fr>
- * @link http://www.php.net/manual/en/function.utf8-encode.php
- */
- function utf8_check($Str) {
- for ($i=0; $i<strlen($Str); $i++) {
- $b = ord($Str[$i]);
- if ($b < 0x80) continue; # 0bbbbbbb
- elseif (($b & 0xE0) == 0xC0) $n=1; # 110bbbbb
- elseif (($b & 0xF0) == 0xE0) $n=2; # 1110bbbb
- elseif (($b & 0xF8) == 0xF0) $n=3; # 11110bbb
- elseif (($b & 0xFC) == 0xF8) $n=4; # 111110bb
- elseif (($b & 0xFE) == 0xFC) $n=5; # 1111110b
- else return false; # Does not match any model
- for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
- if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80))
- return false;
- }
- }
- return true;
- }
- }
- if(!function_exists('utf8_strlen')){
- /**
- * Unicode aware replacement for strlen()
- *
- * utf8_decode() converts characters that are not in ISO-8859-1
- * to '?', which, for the purpose of counting, is alright - It's
- * even faster than mb_strlen.
- *
- * @author <chernyshevsky at hotmail dot com>
- * @see strlen()
- * @see utf8_decode()
- */
- function utf8_strlen($string){
- return strlen(utf8_decode($string));
- }
- }
- if(!function_exists('utf8_substr')){
- /**
- * UTF-8 aware alternative to substr
- *
- * Return part of a string given character offset (and optionally length)
- *
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @author Chris Smith <chris@jalakai.co.uk>
- * @param string
- * @param integer number of UTF-8 characters offset (from left)
- * @param integer (optional) length in UTF-8 characters from offset
- * @return mixed string or false if failure
- */
- function utf8_substr($str, $offset, $length = null) {
- if(UTF8_MBSTRING){
- if( $length === null ){
- return mb_substr($str, $offset);
- }else{
- return mb_substr($str, $offset, $length);
- }
- }
- /*
- * Notes:
- *
- * no mb string support, so we'll use pcre regex's with 'u' flag
- * pcre only supports repetitions of less than 65536, in order to accept up to MAXINT values for
- * offset and length, we'll repeat a group of 65535 characters when needed (ok, up to MAXINT-65536)
- *
- * substr documentation states false can be returned in some cases (e.g. offset > string length)
- * mb_substr never returns false, it will return an empty string instead.
- *
- * calculating the number of characters in the string is a relatively expensive operation, so
- * we only carry it out when necessary. It isn't necessary for +ve offsets and no specified length
- */
- // cast parameters to appropriate types to avoid multiple notices/warnings
- $str = (string)$str; // generates E_NOTICE for PHP4 objects, but not PHP5 objects
- $offset = (int)$offset;
- if (!is_null($length)) $length = (int)$length;
- // handle trivial cases
- if ($length === 0) return '';
- if ($offset < 0 && $length < 0 && $length < $offset) return '';
- $offset_pattern = '';
- $length_pattern = '';
- // normalise -ve offsets (we could use a tail anchored pattern, but they are horribly slow!)
- if ($offset < 0) {
- $strlen = strlen(utf8_decode($str)); // see notes
- $offset = $strlen + $offset;
- if ($offset < 0) $offset = 0;
- }
- // establish a pattern for offset, a non-captured group equal in length to offset
- if ($offset > 0) {
- $Ox = (int)($offset/65535);
- $Oy = $offset%65535;
- if ($Ox) $offset_pattern = '(?:.{65535}){'.$Ox.'}';
- $offset_pattern = '^(?:'.$offset_pattern.'.{'.$Oy.'})';
- } else {
- $offset_pattern = '^'; // offset == 0; just anchor the pattern
- }
- // establish a pattern for length
- if (is_null($length)) {
- $length_pattern = '(.*)$'; // the rest of the string
- } else {
- if (!isset($strlen)) $strlen = strlen(utf8_decode($str)); // see notes
- if ($offset > $strlen) return ''; // another trivial case
- if ($length > 0) {
- $length = min($strlen-$offset, $length); // reduce any length that would go passed the end of the string
- $Lx = (int)($length/65535);
- $Ly = $length%65535;
- // +ve length requires ... a captured group of length characters
- if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
- $length_pattern = '('.$length_pattern.'.{'.$Ly.'})';
- } else if ($length < 0) {
- if ($length < ($offset - $strlen)) return '';
- $Lx = (int)((-$length)/65535);
- $Ly = (-$length)%65535;
- // -ve length requires ... capture everything except a group of -length characters
- // anchored at the tail-end of the string
- if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
- $length_pattern = '(.*)(?:'.$length_pattern.'.{'.$Ly.'})$';
- }
- }
- if (!preg_match('#'.$offset_pattern.$length_pattern.'#us',$str,$match)) return '';
- return $match[1];
- }
- }
- if(!function_exists('utf8_substr_replace')){
- /**
- * Unicode aware replacement for substr_replace()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see substr_replace()
- */
- function utf8_substr_replace($string, $replacement, $start , $length=0 ){
- $ret = '';
- if($start>0) $ret .= utf8_substr($string, 0, $start);
- $ret .= $replacement;
- $ret .= utf8_substr($string, $start+$length);
- return $ret;
- }
- }
- if(!function_exists('utf8_ltrim')){
- /**
- * Unicode aware replacement for ltrim()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see ltrim()
- * @return string
- */
- function utf8_ltrim($str,$charlist=''){
- if($charlist == '') return ltrim($str);
- //quote charlist for use in a characterclass
- $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);
- return preg_replace('/^['.$charlist.']+/u','',$str);
- }
- }
- if(!function_exists('utf8_rtrim')){
- /**
- * Unicode aware replacement for rtrim()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see rtrim()
- * @return string
- */
- function utf8_rtrim($str,$charlist=''){
- if($charlist == '') return rtrim($str);
- //quote charlist for use in a characterclass
- $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);
- return preg_replace('/['.$charlist.']+$/u','',$str);
- }
- }
- if(!function_exists('utf8_trim')){
- /**
- * Unicode aware replacement for trim()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see trim()
- * @return string
- */
- function utf8_trim($str,$charlist='') {
- if($charlist == '') return trim($str);
- return utf8_ltrim(utf8_rtrim($str,$charlist),$charlist);
- }
- }
- if(!function_exists('utf8_strtolower')){
- /**
- * This is a unicode aware replacement for strtolower()
- *
- * Uses mb_string extension if available
- *
- * @author Leo Feyer <leo@typolight.org>
- * @see strtolower()
- * @see utf8_strtoupper()
- */
- function utf8_strtolower($string){
- if(UTF8_MBSTRING) return mb_strtolower($string,'utf-8');
- global $UTF8_UPPER_TO_LOWER;
- return strtr($string,$UTF8_UPPER_TO_LOWER);
- }
- }
- if(!function_exists('utf8_strtoupper')){
- /**
- * This is a unicode aware replacement for strtoupper()
- *
- * Uses mb_string extension if available
- *
- * @author Leo Feyer <leo@typolight.org>
- * @see strtoupper()
- * @see utf8_strtoupper()
- */
- function utf8_strtoupper($string){
- if(UTF8_MBSTRING) return mb_strtoupper($string,'utf-8');
- global $UTF8_LOWER_TO_UPPER;
- return strtr($string,$UTF8_LOWER_TO_UPPER);
- }
- }
- if(!function_exists('utf8_ucfirst')){
- /**
- * UTF-8 aware alternative to ucfirst
- * Make a string's first character uppercase
- *
- * @author Harry Fuecks
- * @param string
- * @return string with first character as upper case (if applicable)
- */
- function utf8_ucfirst($str){
- switch ( utf8_strlen($str) ) {
- case 0:
- return '';
- case 1:
- return utf8_strtoupper($str);
- default:
- preg_match('/^(.{1})(.*)$/us', $str, $matches);
- return utf8_strtoupper($matches[1]).$matches[2];
- }
- }
- }
- if(!function_exists('utf8_ucwords')){
- /**
- * UTF-8 aware alternative to ucwords
- * Uppercase the first character of each word in a string
- *
- * @author Harry Fuecks
- * @param string
- * @return string with first char of each word uppercase
- * @see http://www.php.net/ucwords
- */
- function utf8_ucwords($str) {
- // Note: [\x0c\x09\x0b\x0a\x0d\x20] matches;
- // form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns
- // This corresponds to the definition of a "word" defined at http://www.php.net/ucwords
- $pattern = '/(^|([\x0c\x09\x0b\x0a\x0d\x20]+))([^\x0c\x09\x0b\x0a\x0d\x20]{1})[^\x0c\x09\x0b\x0a\x0d\x20]*/u';
- return preg_replace_callback($pattern, 'utf8_ucwords_callback',$str);
- }
- /**
- * Callback function for preg_replace_callback call in utf8_ucwords
- * You don't need to call this yourself
- *
- * @author Harry Fuecks
- * @param array of matches corresponding to a single word
- * @return string with first char of the word in uppercase
- * @see utf8_ucwords
- * @see utf8_strtoupper
- */
- function utf8_ucwords_callback($matches) {
- $leadingws = $matches[2];
- $ucfirst = utf8_strtoupper($matches[3]);
- $ucword = utf8_substr_replace(ltrim($matches[0]),$ucfirst,0,1);
- return $leadingws . $ucword;
- }
- }
- if(!function_exists('utf8_deaccent')){
- /**
- * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents
- *
- * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1)
- * letters. Default is to deaccent both cases ($case = 0)
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- function utf8_deaccent($string,$case=0){
- if($case <= 0){
- global $UTF8_LOWER_ACCENTS;
- $string = strtr($string,$UTF8_LOWER_ACCENTS);
- }
- if($case >= 0){
- global $UTF8_UPPER_ACCENTS;
- $string = strtr($string,$UTF8_UPPER_ACCENTS);
- }
- return $string;
- }
- }
- if(!function_exists('utf8_romanize')){
- /**
- * Romanize a non-latin string
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- function utf8_romanize($string){
- if(utf8_isASCII($string)) return $string; //nothing to do
- global $UTF8_ROMANIZATION;
- return strtr($string,$UTF8_ROMANIZATION);
- }
- }
- if(!function_exists('utf8_stripspecials')){
- /**
- * Removes special characters (nonalphanumeric) from a UTF-8 string
- *
- * This function adds the controlchars 0x00 to 0x19 to the array of
- * stripped chars (they are not included in $UTF8_SPECIAL_CHARS)
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @param string $string The UTF8 string to strip of special chars
- * @param string $repl Replace special with this string
- * @param string $additional Additional chars to strip (used in regexp char class)
- */
- function utf8_stripspecials($string,$repl='',$additional=''){
- global $UTF8_SPECIAL_CHARS;
- global $UTF8_SPECIAL_CHARS2;
- static $specials = null;
- if(is_null($specials)){
- #$specials = preg_quote(unicode_to_utf8($UTF8_SPECIAL_CHARS), '/');
- $specials = preg_quote($UTF8_SPECIAL_CHARS2, '/');
- }
- return preg_replace('/['.$additional.'\x00-\x19'.$specials.']/u',$repl,$string);
- }
- }
- if(!function_exists('utf8_strpos')){
- /**
- * This is an Unicode aware replacement for strpos
- *
- * @author Leo Feyer <leo@typolight.org>
- * @see strpos()
- * @param string
- * @param string
- * @param integer
- * @return integer
- */
- function utf8_strpos($haystack, $needle, $offset=0){
- $comp = 0;
- $length = null;
- while (is_null($length) || $length < $offset) {
- $pos = strpos($haystack, $needle, $offset + $comp);
- if ($pos === false)
- return false;
- $length = utf8_strlen(substr($haystack, 0, $pos));
- if ($length < $offset)
- $comp = $pos - $length;
- }
- return $length;
- }
- }
- if(!function_exists('utf8_tohtml')){
- /**
- * Encodes UTF-8 characters to HTML entities
- *
- * @author Tom N Harris <tnharris@whoopdedo.org>
- * @author <vpribish at shopping dot com>
- * @link http://www.php.net/manual/en/function.utf8-decode.php
- */
- function utf8_tohtml ($str) {
- $ret = '';
- foreach (utf8_to_unicode($str) as $cp) {
- if ($cp < 0x80)
- $ret .= chr($cp);
- elseif ($cp < 0x100)
- $ret .= "&#$cp;";
- else
- $ret .= '&#x'.dechex($cp).';';
- }
- return $ret;
- }
- }
- if(!function_exists('utf8_unhtml')){
- /**
- * Decodes HTML entities to UTF-8 characters
- *
- * Convert any &#..; entity to a codepoint,
- * The entities flag defaults to only decoding numeric entities.
- * Pass HTML_ENTITIES and named entities, including & < etc.
- * are handled as well. Avoids the problem that would occur if you
- * had to decode "&#38;&amp;#38;"
- *
- * unhtmlspecialchars(utf8_unhtml($s)) -> "&&"
- * utf8_unhtml(unhtmlspecialchars($s)) -> "&&#38;"
- * what it should be -> "&&#38;"
- *
- * @author Tom N Harris <tnharris@whoopdedo.org>
- * @param string $str UTF-8 encoded string
- * @param boolean $entities Flag controlling decoding of named entities.
- * @return UTF-8 encoded string with numeric (and named) entities replaced.
- */
- function utf8_unhtml($str, $entities=null) {
- static $decoder = null;
- if (is_null($decoder))
- $decoder = new utf8_entity_decoder();
- if (is_null($entities))
- return preg_replace_callback('/(&#([Xx])?([0-9A-Za-z]+);)/m',
- 'utf8_decode_numeric', $str);
- else
- return preg_replace_callback('/&(#)?([Xx])?([0-9A-Za-z]+);/m',
- array(&$decoder, 'decode'), $str);
- }
- }
- if(!function_exists('utf8_decode_numeric')){
- function utf8_decode_numeric($ent) {
- switch ($ent[2]) {
- case 'X':
- case 'x':
- $cp = hexdec($ent[3]);
- break;
- default:
- $cp = intval($ent[3]);
- break;
- }
- return unicode_to_utf8(array($cp));
- }
- }
- if(!class_exists('utf8_entity_decoder')){
- class utf8_entity_decoder {
- var $table;
- function utf8_entity_decoder() {
- $table = get_html_translation_table(HTML_ENTITIES);
- $table = array_flip($table);
- $this->table = array_map(array(&$this,'makeutf8'), $table);
- }
- function makeutf8($c) {
- return unicode_to_utf8(array(ord($c)));
- }
- function decode($ent) {
- if ($ent[1] == '#') {
- return utf8_decode_numeric($ent);
- } elseif (array_key_exists($ent[0],$this->table)) {
- return $this->table[$ent[0]];
- } else {
- return $ent[0];
- }
- }
- }
- }
- if(!function_exists('utf8_to_unicode')){
- /**
- * Takes an UTF-8 string and returns an array of ints representing the
- * Unicode characters. Astral planes are supported ie. the ints in the
- * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
- * are not allowed.
- *
- * If $strict is set to true the function returns false if the input
- * string isn't a valid UTF-8 octet sequence and raises a PHP error at
- * level E_USER_WARNING
- *
- * Note: this function has been modified slightly in this library to
- * trigger errors on encountering bad bytes
- *
- * @author <hsivonen@iki.fi>
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @param string UTF-8 encoded string
- * @param boolean Check for invalid sequences?
- * @return mixed array of unicode code points or false if UTF-8 invalid
- * @see unicode_to_utf8
- * @link http://hsivonen.iki.fi/php-utf8/
- * @link http://sourceforge.net/projects/phputf8/
- */
- function utf8_to_unicode($str,$strict=false) {
- $mState = 0; // cached expected number of octets after the current octet
- // until the beginning of the next UTF8 character sequence
- $mUcs4 = 0; // cached Unicode character
- $mBytes = 1; // cached expected number of octets in the current sequence
- $out = array();
- $len = strlen($str);
- for($i = 0; $i < $len; $i++) {
- $in = ord($str{$i});
- if ( $mState == 0) {
- // When mState is zero we expect either a US-ASCII character or a
- // multi-octet sequence.
- if (0 == (0x80 & ($in))) {
- // US-ASCII, pass straight through.
- $out[] = $in;
- $mBytes = 1;
- } else if (0xC0 == (0xE0 & ($in))) {
- // First octet of 2 octet sequence
- $mUcs4 = ($in);
- $mUcs4 = ($mUcs4 & 0x1F) << 6;
- $mState = 1;
- $mBytes = 2;
- } else if (0xE0 == (0xF0 & ($in))) {
- // First octet of 3 octet sequence
- $mUcs4 = ($in);
- $mUcs4 = ($mUcs4 & 0x0F) << 12;
- $mState = 2;
- $mBytes = 3;
- } else if (0xF0 == (0xF8 & ($in))) {
- // First octet of 4 octet sequence
- $mUcs4 = ($in);
- $mUcs4 = ($mUcs4 & 0x07) << 18;
- $mState = 3;
- $mBytes = 4;
- } else if (0xF8 == (0xFC & ($in))) {
- /* First octet of 5 octet sequence.
- *
- * This is illegal because the encoded codepoint must be either
- * (a) not the shortest form or
- * (b) outside the Unicode range of 0-0x10FFFF.
- * Rather than trying to resynchronize, we will carry on until the end
- * of the sequence and let the later error handling code catch it.
- */
- $mUcs4 = ($in);
- $mUcs4 = ($mUcs4 & 0x03) << 24;
- $mState = 4;
- $mBytes = 5;
- } else if (0xFC == (0xFE & ($in))) {
- // First octet of 6 octet sequence, see comments for 5 octet sequence.
- $mUcs4 = ($in);
- $mUcs4 = ($mUcs4 & 1) << 30;
- $mState = 5;
- $mBytes = 6;
- } elseif($strict) {
- /* Current octet is neither in the US-ASCII range nor a legal first
- * octet of a multi-octet sequence.
- */
- trigger_error(
- 'utf8_to_unicode: Illegal sequence identifier '.
- 'in UTF-8 at byte '.$i,
- E_USER_WARNING
- );
- return false;
- }
- } else {
- // When mState is non-zero, we expect a continuation of the multi-octet
- // sequence
- if (0x80 == (0xC0 & ($in))) {
- // Legal continuation.
- $shift = ($mState - 1) * 6;
- $tmp = $in;
- $tmp = ($tmp & 0x0000003F) << $shift;
- $mUcs4 |= $tmp;
- /**
- * End of the multi-octet sequence. mUcs4 now contains the final
- * Unicode codepoint to be output
- */
- if (0 == --$mState) {
- /*
- * Check for illegal sequences and codepoints.
- */
- // From Unicode 3.1, non-shortest form is illegal
- if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
- ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
- ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
- (4 < $mBytes) ||
- // From Unicode 3.2, surrogate characters are illegal
- (($mUcs4 & 0xFFFFF800) == 0xD800) ||
- // Codepoints outside the Unicode range are illegal
- ($mUcs4 > 0x10FFFF)) {
- if($strict){
- trigger_error(
- 'utf8_to_unicode: Illegal sequence or codepoint '.
- 'in UTF-8 at byte '.$i,
- E_USER_WARNING
- );
- return false;
- }
- }
- if (0xFEFF != $mUcs4) {
- // BOM is legal but we don't want to output it
- $out[] = $mUcs4;
- }
- //initialize UTF8 cache
- $mState = 0;
- $mUcs4 = 0;
- $mBytes = 1;
- }
- } elseif($strict) {
- /**
- *((0xC0 & (*in) != 0x80) && (mState != 0))
- * Incomplete multi-octet sequence.
- */
- trigger_error(
- 'utf8_to_unicode: Incomplete multi-octet '.
- ' sequence in UTF-8 at byte '.$i,
- E_USER_WARNING
- );
- return false;
- }
- }
- }
- return $out;
- }
- }
- if(!function_exists('unicode_to_utf8')){
- /**
- * Takes an array of ints representing the Unicode characters and returns
- * a UTF-8 string. Astral planes are supported ie. the ints in the
- * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
- * are not allowed.
- *
- * If $strict is set to true the function returns false if the input
- * array contains ints that represent surrogates or are outside the
- * Unicode range and raises a PHP error at level E_USER_WARNING
- *
- * Note: this function has been modified slightly in this library to use
- * output buffering to concatenate the UTF-8 string (faster) as well as
- * reference the array by it's keys
- *
- * @param array of unicode code points representing a string
- * @param boolean Check for invalid sequences?
- * @return mixed UTF-8 string or false if array contains invalid code points
- * @author <hsivonen@iki.fi>
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @see utf8_to_unicode
- * @link http://hsivonen.iki.fi/php-utf8/
- * @link http://sourceforge.net/projects/phputf8/
- */
- function unicode_to_utf8($arr,$strict=false) {
- if (!is_array($arr)) return '';
- ob_start();
- foreach (array_keys($arr) as $k) {
- # ASCII range (including control chars)
- if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) {
- echo chr($arr[$k]);
- # 2 byte sequence
- } else if ($arr[$k] <= 0x07ff) {
- echo chr(0xc0 | ($arr[$k] >> 6));
- echo chr(0x80 | ($arr[$k] & 0x003f));
- # Byte order mark (skip)
- } else if($arr[$k] == 0xFEFF) {
- // nop -- zap the BOM
- # Test for illegal surrogates
- } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) {
- // found a surrogate
- if($strict){
- trigger_error(
- 'unicode_to_utf8: Illegal surrogate '.
- 'at index: '.$k.', value: '.$arr[$k],
- E_USER_WARNING
- );
- return false;
- }
- # 3 byte sequence
- } else if ($arr[$k] <= 0xffff) {
- echo chr(0xe0 | ($arr[$k] >> 12));
- echo chr(0x80 | (($arr[$k] >> 6) & 0x003f));
- echo chr(0x80 | ($arr[$k] & 0x003f));
- # 4 byte sequence
- } else if ($arr[$k] <= 0x10ffff) {
- echo chr(0xf0 | ($arr[$k] >> 18));
- echo chr(0x80 | (($arr[$k] >> 12) & 0x3f));
- echo chr(0x80 | (($arr[$k] >> 6) & 0x3f));
- echo chr(0x80 | ($arr[$k] & 0x3f));
- } elseif($strict) {
- trigger_error(
- 'unicode_to_utf8: Codepoint out of Unicode range '.
- 'at index: '.$k.', value: '.$arr[$k],
- E_USER_WARNING
- );
- // out of range
- return false;
- }
- }
- $result = ob_get_contents();
- ob_end_clean();
- return $result;
- }
- }
- if(!function_exists('utf8_to_utf16be')){
- /**
- * UTF-8 to UTF-16BE conversion.
- *
- * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
- */
- function utf8_to_utf16be(&$str, $bom = false) {
- $out = $bom ? "\xFE\xFF" : '';
- if(UTF8_MBSTRING) return $out.mb_convert_encoding($str,'UTF-16BE','UTF-8');
- $uni = utf8_to_unicode($str);
- foreach($uni as $cp){
- $out .= pack('n',$cp);
- }
- return $out;
- }
- }
- if(!function_exists('utf16be_to_utf8')){
- /**
- * UTF-8 to UTF-16BE conversion.
- *
- * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
- */
- function utf16be_to_utf8(&$str) {
- $uni = unpack('n*',$str);
- return unicode_to_utf8($uni);
- }
- }
- if(!function_exists('utf8_bad_replace')){
- /**
- * Replace bad bytes with an alternative character
- *
- * ASCII character is recommended for replacement char
- *
- * PCRE Pattern to locate bad bytes in a UTF-8 string
- * Comes from W3 FAQ: Multilingual Forms
- * Note: modified to include full ASCII range including control chars
- *
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @see http://www.w3.org/International/questions/qa-forms-utf-8
- * @param string to search
- * @param string to replace bad bytes with (defaults to '?') - use ASCII
- * @return string
- */
- function utf8_bad_replace($str, $replace = '') {
- $UTF8_BAD =
- '([\x00-\x7F]'. # ASCII (including control chars)
- '|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte
- '|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs
- '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte
- '|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates
- '|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3
- '|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15
- '|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16
- '|(.{1}))'; # invalid byte
- ob_start();
- while (preg_match('/'.$UTF8_BAD.'/S', $str, $matches)) {
- if ( !isset($matches[2])) {
- echo $matches[0];
- } else {
- echo $replace;
- }
- $str = substr($str,strlen($matches[0]));
- }
- $result = ob_get_contents();
- ob_end_clean();
- return $result;
- }
- }
- if(!function_exists('utf8_correctIdx')){
- /**
- * adjust a byte index into a utf8 string to a utf8 character boundary
- *
- * @param $str string utf8 character string
- * @param $i int byte index into $str
- * @param $next bool direction to search for boundary,
- * false = up (current character)
- * true = down (next character)
- *
- * @return int byte index into $str now pointing to a utf8 character boundary
- *
- * @author chris smith <chris@jalakai.co.uk>
- */
- function utf8_correctIdx(&$str,$i,$next=false) {
- if ($i <= 0) return 0;
- $limit = strlen($str);
- if ($i>=$limit) return $limit;
- if ($next) {
- while (($i<$limit) && ((ord($str[$i]) & 0xC0) == 0x80)) $i++;
- } else {
- while ($i && ((ord($str[$i]) & 0xC0) == 0x80)) $i--;
- }
- return $i;
- }
- }
- // only needed if no mb_string available
- if(!UTF8_MBSTRING){
- /**
- * UTF-8 Case lookup table
- *
- * This lookuptable defines the upper case letters to their correspponding
- * lower case letter in UTF-8
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- global $UTF8_LOWER_TO_UPPER;
- if(empty($UTF8_LOWER_TO_UPPER)) $UTF8_LOWER_TO_UPPER = array(
- "z"=>"Z","y"=>"Y","x"=>"X","w"=>"W","v"=>"V","u"=>"U","t"=>"T","s"=>"S","r"=>"R","q"=>"Q",
- "p"=>"P","o"=>"O","n"=>"N","m"=>"M","l"=>"L","k"=>"K","j"=>"J","i"=>"I","h"=>"H","g"=>"G",
- "f"=>"F","e"=>"E","d"=>"D","c"=>"C","b"=>"B","a"=>"A","ῳ"=>"ῼ","ῥ"=>"Ῥ","ῡ"=>"Ῡ","ῑ"=>"Ῑ",
- "ῐ"=>"Ῐ","ῃ"=>"ῌ","ι"=>"Ι","ᾳ"=>"ᾼ","ᾱ"=>"Ᾱ","ᾰ"=>"Ᾰ","ᾧ"=>"ᾯ","ᾦ"=>"ᾮ","ᾥ"=>"ᾭ","ᾤ"=>"ᾬ",
- "ᾣ"=>"ᾫ","ᾢ"=>"ᾪ","ᾡ"=>"ᾩ","ᾗ"=>"ᾟ","ᾖ"=>"ᾞ","ᾕ"=>"ᾝ","ᾔ"=>"ᾜ","ᾓ"=>"ᾛ","ᾒ"=>"ᾚ","ᾑ"=>"ᾙ",
- "ᾐ"=>"ᾘ","ᾇ"=>"ᾏ","ᾆ"=>"ᾎ","ᾅ"=>"ᾍ","ᾄ"=>"ᾌ","ᾃ"=>"ᾋ","ᾂ"=>"ᾊ","ᾁ"=>"ᾉ","ᾀ"=>"ᾈ","ώ"=>"Ώ",
- "ὼ"=>"Ὼ","ύ"=>"Ύ","ὺ"=>"Ὺ","ό"=>"Ό","ὸ"=>"Ὸ","ί"=>"Ί","ὶ"=>"Ὶ","ή"=>"Ή","ὴ"=>"Ὴ","έ"=>"Έ",
- "ὲ"=>"Ὲ","ά"=>"Ά","ὰ"=>"Ὰ","ὧ"=>"Ὧ","ὦ"=>"Ὦ","ὥ"=>"Ὥ","ὤ"=>"Ὤ","ὣ"=>"Ὣ","ὢ"=>"Ὢ","ὡ"=>"Ὡ",
- "ὗ"=>"Ὗ","ὕ"=>"Ὕ","ὓ"=>"Ὓ","ὑ"=>"Ὑ","ὅ"=>"Ὅ","ὄ"=>"Ὄ","ὃ"=>"Ὃ","ὂ"=>"Ὂ","ὁ"=>"Ὁ","ὀ"=>"Ὀ",
- "ἷ"=>"Ἷ","ἶ"=>"Ἶ","ἵ"=>"Ἵ","ἴ"=>"Ἴ","ἳ"=>"Ἳ","ἲ"=>"Ἲ","ἱ"=>"Ἱ","ἰ"=>"Ἰ","ἧ"=>"Ἧ","ἦ"=>"Ἦ",
- "ἥ"=>"Ἥ","ἤ"=>"Ἤ","ἣ"=>"Ἣ","ἢ"=>"Ἢ","ἡ"=>"Ἡ","ἕ"=>"Ἕ","ἔ"=>"Ἔ","ἓ"=>"Ἓ","ἒ"=>"Ἒ","ἑ"=>"Ἑ",
- "ἐ"=>"Ἐ","ἇ"=>"Ἇ","ἆ"=>"Ἆ","ἅ"=>"Ἅ","ἄ"=>"Ἄ","ἃ"=>"Ἃ","ἂ"=>"Ἂ","ἁ"=>"Ἁ","ἀ"=>"Ἀ","ỹ"=>"Ỹ",
- "ỷ"=>"Ỷ","ỵ"=>"Ỵ","ỳ"=>"Ỳ","ự"=>"Ự","ữ"=>"Ữ","ử"=>"Ử","ừ"=>"Ừ","ứ"=>"Ứ","ủ"=>"Ủ","ụ"=>"Ụ",
- "ợ"=>"Ợ","ỡ"=>"Ỡ","ở"=>"Ở","ờ"=>"Ờ","ớ"=>"Ớ","ộ"=>"Ộ","ỗ"=>"Ỗ","ổ"=>"Ổ","ồ"=>"Ồ","ố"=>"Ố",
- "ỏ"=>"Ỏ","ọ"=>"Ọ","ị"=>"Ị","ỉ"=>"Ỉ","ệ"=>"Ệ","ễ"=>"Ễ","ể"=>"Ể","ề"=>"Ề","ế"=>"Ế","ẽ"=>"Ẽ",
- "ẻ"=>"Ẻ","ẹ"=>"Ẹ","ặ"=>"Ặ","ẵ"=>"Ẵ","ẳ"=>"Ẳ","ằ"=>"Ằ","ắ"=>"Ắ","ậ"=>"Ậ","ẫ"=>"Ẫ","ẩ"=>"Ẩ",
- "ầ"=>"Ầ","ấ"=>"Ấ","ả"=>"Ả","ạ"=>"Ạ","ẛ"=>"Ṡ","ẕ"=>"Ẕ","ẓ"=>"Ẓ","ẑ"=>"Ẑ","ẏ"=>"Ẏ","ẍ"=>"Ẍ",
- "ẋ"=>"Ẋ","ẉ"=>"Ẉ","ẇ"=>"Ẇ","ẅ"=>"Ẅ","ẃ"=>"Ẃ","ẁ"=>"Ẁ","ṿ"=>"Ṿ","ṽ"=>"Ṽ","ṻ"=>"Ṻ","ṹ"=>"Ṹ",
- "ṷ"=>"Ṷ","ṵ"=>"Ṵ","ṳ"=>"Ṳ","ṱ"=>"Ṱ","ṯ"=>"Ṯ","ṭ"=>"Ṭ","ṫ"=>"Ṫ","ṩ"=>"Ṩ","ṧ"=>"Ṧ","ṥ"=>"Ṥ",
- "ṣ"=>"Ṣ","ṡ"=>"Ṡ","ṟ"=>"Ṟ","ṝ"=>"Ṝ","ṛ"=>"Ṛ","ṙ"=>"Ṙ","ṗ"=>"Ṗ","ṕ"=>"Ṕ","ṓ"=>"Ṓ","ṑ"=>"Ṑ",
- "ṏ"=>"Ṏ","ṍ"=>"Ṍ","ṋ"=>"Ṋ","ṉ"=>"Ṉ","ṇ"=>"Ṇ","ṅ"=>"Ṅ","ṃ"=>"Ṃ","ṁ"=>"Ṁ","ḿ"=>"Ḿ","ḽ"=>"Ḽ",
- "ḻ"=>"Ḻ","ḹ"=>"Ḹ","ḷ"=>"Ḷ","ḵ"=>"Ḵ","ḳ"=>"Ḳ","ḱ"=>"Ḱ","ḯ"=>"Ḯ","ḭ"=>"Ḭ","ḫ"=>"Ḫ","ḩ"=>"Ḩ",
- "ḧ"=>"Ḧ","ḥ"=>"Ḥ","ḣ"=>"Ḣ","ḡ"=>"Ḡ","ḟ"=>"Ḟ","ḝ"=>"Ḝ","ḛ"=>"Ḛ","ḙ"=>"Ḙ","ḗ"=>"Ḗ","ḕ"=>"Ḕ",
- "ḓ"=>"Ḓ","ḑ"=>"Ḑ","ḏ"=>"Ḏ","ḍ"=>"Ḍ","ḋ"=>"Ḋ","ḉ"=>"Ḉ","ḇ"=>"Ḇ","ḅ"=>"Ḅ","ḃ"=>"Ḃ","ḁ"=>"Ḁ",
- "ֆ"=>"Ֆ","օ"=>"Օ","ք"=>"Ք","փ"=>"Փ","ւ"=>"Ւ","ց"=>"Ց","ր"=>"Ր","տ"=>"Տ","վ"=>"Վ","ս"=>"Ս",
- "ռ"=>"Ռ","ջ"=>"Ջ","պ"=>"Պ","չ"=>"Չ","ո"=>"Ո","շ"=>"Շ","ն"=>"Ն","յ"=>"Յ","մ"=>"Մ","ճ"=>"Ճ",
- "ղ"=>"Ղ","ձ"=>"Ձ","հ"=>"Հ","կ"=>"Կ","ծ"=>"Ծ","խ"=>"Խ","լ"=>"Լ","ի"=>"Ի","ժ"=>"Ժ","թ"=>"Թ",
- "ը"=>"Ը","է"=>"Է","զ"=>"Զ","ե"=>"Ե","դ"=>"Դ","գ"=>"Գ","բ"=>"Բ","ա"=>"Ա","ԏ"=>"Ԏ","ԍ"=>"Ԍ",
- "ԋ"=>"Ԋ","ԉ"=>"Ԉ","ԇ"=>"Ԇ","ԅ"=>"Ԅ","ԃ"=>"Ԃ","ԁ"=>"Ԁ","ӹ"=>"Ӹ","ӵ"=>"Ӵ","ӳ"=>"Ӳ","ӱ"=>"Ӱ",
- "ӯ"=>"Ӯ","ӭ"=>"Ӭ","ӫ"=>"Ӫ","ө"=>"Ө","ӧ"=>"Ӧ","ӥ"=>"Ӥ","ӣ"=>"Ӣ","ӡ"=>"Ӡ","ӟ"=>"Ӟ","ӝ"=>"Ӝ",
- "ӛ"=>"Ӛ","ә"=>"Ә","ӗ"=>"Ӗ","ӕ"=>"Ӕ","ӓ"=>"Ӓ","ӑ"=>"Ӑ","ӎ"=>"Ӎ","ӌ"=>"Ӌ","ӊ"=>"Ӊ","ӈ"=>"Ӈ",
- "ӆ"=>"Ӆ","ӄ"=>"Ӄ","ӂ"=>"Ӂ","ҿ"=>"Ҿ","ҽ"=>"Ҽ","һ"=>"Һ","ҹ"=>"Ҹ","ҷ"=>"Ҷ","ҵ"=>"Ҵ","ҳ"=>"Ҳ",
- "ұ"=>"Ұ","ү"=>"Ү","ҭ"=>"Ҭ","ҫ"=>"Ҫ","ҩ"=>"Ҩ","ҧ"=>"Ҧ","ҥ"=>"Ҥ","ң"=>"Ң","ҡ"=>"Ҡ","ҟ"=>"Ҟ",
- "ҝ"=>"Ҝ","қ"=>"Қ","ҙ"=>"Ҙ","җ"=>"Җ","ҕ"=>"Ҕ","ғ"=>"Ғ","ґ"=>"Ґ","ҏ"=>"Ҏ","ҍ"=>"Ҍ","ҋ"=>"Ҋ",
- "ҁ"=>"Ҁ","ѿ"=>"Ѿ","ѽ"=>"Ѽ","ѻ"=>"Ѻ","ѹ"=>"Ѹ","ѷ"=>"Ѷ","ѵ"=>"Ѵ","ѳ"=>"Ѳ","ѱ"=>"Ѱ","ѯ"=>"Ѯ",
- "ѭ"=>"Ѭ","ѫ"=>"Ѫ","ѩ"=>"Ѩ","ѧ"=>"Ѧ","ѥ"=>"Ѥ","ѣ"=>"Ѣ","ѡ"=>"Ѡ","џ"=>"Џ","ў"=>"Ў","ѝ"=>"Ѝ",
- "ќ"=>"Ќ","ћ"=>"Ћ","њ"=>"Њ","љ"=>"Љ","ј"=>"Ј","ї"=>"Ї","і"=>"І","ѕ"=>"Ѕ","є"=>"Є","ѓ"=>"Ѓ",
- "ђ"=>"Ђ","ё"=>"Ё","ѐ"=>"Ѐ","я"=>"Я","ю"=>"Ю","э"=>"Э","ь"=>"Ь","ы"=>"Ы","ъ"=>"Ъ","щ"=>"Щ",
- "ш"=>"Ш","ч"=>"Ч","ц"=>"Ц","х"=>"Х","ф"=>"Ф","у"=>"У","т"=>"Т","с"=>"С","р"=>"Р","п"=>"П",
- "о"=>"О","н"=>"Н","м"=>"М","л"=>"Л","к"=>"К","й"=>"Й","и"=>"И","з"=>"З","ж"=>"Ж","е"=>"Е",
- "д"=>"Д","г"=>"Г","в"=>"В","б"=>"Б","а"=>"А","ϵ"=>"Ε","ϲ"=>"Σ","ϱ"=>"Ρ","ϰ"=>"Κ","ϯ"=>"Ϯ",
- "ϭ"=>"Ϭ","ϫ"=>"Ϫ","ϩ"=>"Ϩ","ϧ"=>"Ϧ","ϥ"=>"Ϥ","ϣ"=>"Ϣ","ϡ"=>"Ϡ","ϟ"=>"Ϟ","ϝ"=>"Ϝ","ϛ"=>"Ϛ",
- "ϙ"=>"Ϙ","ϖ"=>"Π","ϕ"=>"Φ","ϑ"=>"Θ","ϐ"=>"Β","ώ"=>"Ώ","ύ"=>"Ύ","ό"=>"Ό","ϋ"=>"Ϋ","ϊ"=>"Ϊ",
- "ω"=>"Ω","ψ"=>"Ψ","χ"=>"Χ","φ"=>"Φ","υ"=>"Υ","τ"=>"Τ","σ"=>"Σ","ς"=>"Σ","ρ"=>"Ρ","π"=>"Π",
- "ο"=>"Ο","ξ"=>"Ξ","ν"=>"Ν","μ"=>"Μ","λ"=>"Λ","κ"=>"Κ","ι"=>"Ι","θ"=>"Θ","η"=>"Η","ζ"=>"Ζ",
- "ε"=>"Ε","δ"=>"Δ","γ"=>"Γ","β"=>"Β","α"=>"Α","ί"=>"Ί","ή"=>"Ή","έ"=>"Έ","ά"=>"Ά","ʒ"=>"Ʒ",
- "ʋ"=>"Ʋ","ʊ"=>"Ʊ","ʈ"=>"Ʈ","ʃ"=>"Ʃ","ʀ"=>"Ʀ","ɵ"=>"Ɵ","ɲ"=>"Ɲ","ɯ"=>"Ɯ","ɩ"=>"Ɩ","ɨ"=>"Ɨ",
- "ɣ"=>"Ɣ","ɛ"=>"Ɛ","ə"=>"Ə","ɗ"=>"Ɗ","ɖ"=>"Ɖ","ɔ"=>"Ɔ","ɓ"=>"Ɓ","ȳ"=>"Ȳ","ȱ"=>"Ȱ","ȯ"=>"Ȯ",
- "ȭ"=>"Ȭ","ȫ"=>"Ȫ","ȩ"=>"Ȩ","ȧ"=>"Ȧ","ȥ"=>"Ȥ","ȣ"=>"Ȣ","ȟ"=>"Ȟ","ȝ"=>"Ȝ","ț"=>"Ț","ș"=>"Ș",
- "ȗ"=>"Ȗ","ȕ"=>"Ȕ","ȓ"=>"Ȓ","ȑ"=>"Ȑ","ȏ"=>"Ȏ","ȍ"=>"Ȍ","ȋ"=>"Ȋ","ȉ"=>"Ȉ","ȇ"=>"Ȇ","ȅ"=>"Ȅ",
- "ȃ"=>"Ȃ","ȁ"=>"Ȁ","ǿ"=>"Ǿ","ǽ"=>"Ǽ","ǻ"=>"Ǻ","ǹ"=>"Ǹ","ǵ"=>"Ǵ","dz"=>"Dz","ǯ"=>"Ǯ","ǭ"=>"Ǭ",
- "ǫ"=>"Ǫ","ǩ"=>"Ǩ","ǧ"=>"Ǧ","ǥ"=>"Ǥ","ǣ"=>"Ǣ","ǡ"=>"Ǡ","ǟ"=>"Ǟ","ǝ"=>"Ǝ","ǜ"=>"Ǜ","ǚ"=>"Ǚ",
- "ǘ"=>"Ǘ","ǖ"=>"Ǖ","ǔ"=>"Ǔ","ǒ"=>"Ǒ","ǐ"=>"Ǐ","ǎ"=>"Ǎ","nj"=>"Nj","lj"=>"Lj","dž"=>"Dž","ƿ"=>"Ƿ",
- "ƽ"=>"Ƽ","ƹ"=>"Ƹ","ƶ"=>"Ƶ","ƴ"=>"Ƴ","ư"=>"Ư","ƭ"=>"Ƭ","ƨ"=>"Ƨ","ƥ"=>"Ƥ","ƣ"=>"Ƣ","ơ"=>"Ơ",
- "ƞ"=>"Ƞ","ƙ"=>"Ƙ","ƕ"=>"Ƕ","ƒ"=>"Ƒ","ƌ"=>"Ƌ","ƈ"=>"Ƈ","ƅ"=>"Ƅ","ƃ"=>"Ƃ","ſ"=>"S","ž"=>"Ž",
- "ż"=>"Ż","ź"=>"Ź","ŷ"=>"Ŷ","ŵ"=>"Ŵ","ų"=>"Ų","ű"=>"Ű","ů"=>"Ů","ŭ"=>"Ŭ","ū"=>"Ū","ũ"=>"Ũ",
- "ŧ"=>"Ŧ","ť"=>"Ť","ţ"=>"Ţ","š"=>"Š","ş"=>"Ş","ŝ"=>"Ŝ","ś"=>"Ś","ř"=>"Ř","ŗ"=>"Ŗ","ŕ"=>"Ŕ",
- "œ"=>"Œ","ő"=>"Ő","ŏ"=>"Ŏ","ō"=>"Ō","ŋ"=>"Ŋ","ň"=>"Ň","ņ"=>"Ņ","ń"=>"Ń","ł"=>"Ł","ŀ"=>"Ŀ",
- "ľ"=>"Ľ","ļ"=>"Ļ","ĺ"=>"Ĺ","ķ"=>"Ķ","ĵ"=>"Ĵ","ij"=>"IJ","ı"=>"I","į"=>"Į","ĭ"=>"Ĭ","ī"=>"Ī",
- "ĩ"=>"Ĩ","ħ"=>"Ħ","ĥ"=>"Ĥ","ģ"=>"Ģ","ġ"=>"Ġ","ğ"=>"Ğ","ĝ"=>"Ĝ","ě"=>"Ě","ę"=>"Ę","ė"=>"Ė",
- "ĕ"=>"Ĕ","ē"=>"Ē","đ"=>"Đ","ď"=>"Ď","č"=>"Č","ċ"=>"Ċ","ĉ"=>"Ĉ","ć"=>"Ć","ą"=>"Ą","ă"=>"Ă",
- "ā"=>"Ā","ÿ"=>"Ÿ","þ"=>"Þ","ý"=>"Ý","ü"=>"Ü","û"=>"Û","ú"=>"Ú","ù"=>"Ù","ø"=>"Ø","ö"=>"Ö",
- "õ"=>"Õ","ô"=>"Ô","ó"=>"Ó","ò"=>"Ò","ñ"=>"Ñ","ð"=>"Ð","ï"=>"Ï","î"=>"Î","í"=>"Í","ì"=>"Ì",
- "ë"=>"Ë","ê"=>"Ê","é"=>"É","è"=>"È","ç"=>"Ç","æ"=>"Æ","å"=>"Å","ä"=>"Ä","ã"=>"Ã","â"=>"Â",
- "á"=>"Á","à"=>"À","µ"=>"Μ","z"=>"Z","y"=>"Y","x"=>"X","w"=>"W","v"=>"V","u"=>"U","t"=>"T",
- "s"=>"S","r"=>"R","q"=>"Q","p"=>"P","o"=>"O","n"=>"N","m"=>"M","l"=>"L","k"=>"K","j"=>"J",
- "i"=>"I","h"=>"H","g"=>"G","f"=>"F","e"=>"E","d"=>"D","c"=>"C","b"=>"B","a"=>"A"
- );
- /**
- * UTF-8 Case lookup table
- *
- * This lookuptable defines the lower case letters to their correspponding
- * upper case letter in UTF-8
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- global $UTF8_UPPER_TO_LOWER;
- if(empty($UTF8_UPPER_TO_LOWER)) $UTF8_UPPER_TO_LOWER = array (
- "Z"=>"z","Y"=>"y","X"=>"x","W"=>"w","V"=>"v","U"=>"u","T"=>"t","S"=>"s","R"=>"r","Q"=>"q",
- "P"=>"p","O"=>"o","N"=>"n","M"=>"m","L"=>"l","K"=>"k","J"=>"j","I"=>"i","H"=>"h","G"=>"g",
- "F"=>"f","E"=>"e","D"=>"d","C"=>"c","B"=>"b","A"=>"a","ῼ"=>"ῳ","Ῥ"=>"ῥ","Ῡ"=>"ῡ","Ῑ"=>"ῑ",
- "Ῐ"=>"ῐ","ῌ"=>"ῃ","Ι"=>"ι","ᾼ"=>"ᾳ","Ᾱ"=>"ᾱ","Ᾰ"=>"ᾰ","ᾯ"=>"ᾧ","ᾮ"=>"ᾦ","ᾭ"=>"ᾥ","ᾬ"=>"ᾤ",
- "ᾫ"=>"ᾣ","ᾪ"=>"ᾢ","ᾩ"=>"ᾡ","ᾟ"=>"ᾗ","ᾞ"=>"ᾖ","ᾝ"=>"ᾕ","ᾜ"=>"ᾔ","ᾛ"=>"ᾓ","ᾚ"=>"ᾒ","ᾙ"=>"ᾑ",
- "ᾘ"=>"ᾐ","ᾏ"=>"ᾇ","ᾎ"=>"ᾆ","ᾍ"=>"ᾅ","ᾌ"=>"ᾄ","ᾋ"=>"ᾃ","ᾊ"=>"ᾂ","ᾉ"=>"ᾁ","ᾈ"=>"ᾀ","Ώ"=>"ώ",
- "Ὼ"=>"ὼ","Ύ"=>"ύ","Ὺ"=>"ὺ","Ό"=>"ό","Ὸ"=>"ὸ","Ί"=>"ί","Ὶ"=>"ὶ","Ή"=>"ή","Ὴ"=>"ὴ","Έ"=>"έ",
- "Ὲ"=>"ὲ","Ά"=>"ά","Ὰ"=>"ὰ","Ὧ"=>"ὧ","Ὦ"=>"ὦ","Ὥ"=>"ὥ","Ὤ"=>"ὤ","Ὣ"=>"ὣ","Ὢ"=>"ὢ","Ὡ"=>"ὡ",
- "Ὗ"=>"ὗ","Ὕ"=>"ὕ","Ὓ"=>"ὓ","Ὑ"=>"ὑ","Ὅ"=>"ὅ","Ὄ"=>"ὄ","Ὃ"=>"ὃ","Ὂ"=>"ὂ","Ὁ"=>"ὁ","Ὀ"=>"ὀ",
- "Ἷ"=>"ἷ","Ἶ"=>"ἶ","Ἵ"=>"ἵ","Ἴ"=>"ἴ","Ἳ"=>"ἳ","Ἲ"=>"ἲ","Ἱ"=>"ἱ","Ἰ"=>"ἰ","Ἧ"=>"ἧ","Ἦ"=>"ἦ",
- "Ἥ"=>"ἥ","Ἤ"=>"ἤ","Ἣ"=>"ἣ","Ἢ"=>"ἢ","Ἡ"=>"ἡ","Ἕ"=>"ἕ","Ἔ"=>"ἔ","Ἓ"=>"ἓ","Ἒ"=>"ἒ","Ἑ"=>"ἑ",
- "Ἐ"=>"ἐ","Ἇ"=>"ἇ","Ἆ"=>"ἆ","Ἅ"=>"ἅ","Ἄ"=>"ἄ","Ἃ"=>"ἃ","Ἂ"=>"ἂ","Ἁ"=>"ἁ","Ἀ"=>"ἀ","Ỹ"=>"ỹ",
- "Ỷ"=>"ỷ","Ỵ"=>"ỵ","Ỳ"=>"ỳ","Ự"=>"ự","Ữ"=>"ữ","Ử"=>"ử","Ừ"=>"ừ","Ứ"=>"ứ","Ủ"=>"ủ","Ụ"=>"ụ",
- "Ợ"=>"ợ","Ỡ"=>"ỡ","Ở"=>"ở","Ờ"=>"ờ","Ớ"=>"ớ","Ộ"=>"ộ","Ỗ"=>"ỗ","Ổ"=>"ổ","Ồ"=>"ồ","Ố"=>"ố",
- "Ỏ"=>"ỏ","Ọ"=>"ọ","Ị"=>"ị","Ỉ"=>"ỉ","Ệ"=>"ệ","Ễ"=>"ễ","Ể"=>"ể","Ề"=>"ề","Ế"=>"ế","Ẽ"=>"ẽ",
- "Ẻ"=>"ẻ","Ẹ"=>"ẹ","Ặ"=>"ặ","Ẵ"=>"ẵ","Ẳ"=>"ẳ","Ằ"=>"ằ","Ắ"=>"ắ","Ậ"=>"ậ","Ẫ"=>"ẫ","Ẩ"=>"ẩ",
- "Ầ"=>"ầ","Ấ"=>"ấ","Ả"=>"ả","Ạ"=>"ạ","Ṡ"=>"ẛ","Ẕ"=>"ẕ","Ẓ"=>"ẓ","Ẑ"=>"ẑ","Ẏ"=>"ẏ","Ẍ"=>"ẍ",
- "Ẋ"=>"ẋ","Ẉ"=>"ẉ","Ẇ"=>"ẇ","Ẅ"=>"ẅ","Ẃ"=>"ẃ","Ẁ"=>"ẁ","Ṿ"=>"ṿ","Ṽ"=>"ṽ","Ṻ"=>"ṻ","Ṹ"=>"ṹ",
- "Ṷ"=>"ṷ","Ṵ"=>"ṵ","Ṳ"=>"ṳ","Ṱ"=>"ṱ","Ṯ"=>"ṯ","Ṭ"=>"ṭ","Ṫ"=>"ṫ","Ṩ"=>"ṩ","Ṧ"=>"ṧ","Ṥ"=>"ṥ",
- "Ṣ"=>"ṣ","Ṡ"=>"ṡ","Ṟ"=>"ṟ","Ṝ"=>"ṝ","Ṛ"=>"ṛ","Ṙ"=>"ṙ","Ṗ"=>"ṗ","Ṕ"=>"ṕ","Ṓ"=>"ṓ","Ṑ"=>"ṑ",
- "Ṏ"=>"ṏ","Ṍ"=>"ṍ","Ṋ"=>"ṋ","Ṉ"=>"ṉ","Ṇ"=>"ṇ","Ṅ"=>"ṅ","Ṃ"=>"ṃ","Ṁ"=>"ṁ","Ḿ"=>"ḿ","Ḽ"=>"ḽ",
- "Ḻ"=>"ḻ","Ḹ"=>"ḹ","Ḷ"=>"ḷ","Ḵ"=>"ḵ","Ḳ"=>"ḳ","Ḱ"=>"ḱ","Ḯ"=>"ḯ","Ḭ"=>"ḭ","Ḫ"=>"ḫ","Ḩ"=>"ḩ",
- "Ḧ"=>"ḧ","Ḥ"=>"ḥ","Ḣ"=>"ḣ","Ḡ"=>"ḡ","Ḟ"=>"ḟ","Ḝ"=>"ḝ","Ḛ"=>"ḛ","Ḙ"=>"ḙ","Ḗ"=>"ḗ","Ḕ"=>"ḕ",
- "Ḓ"=>"ḓ","Ḑ"=>"ḑ","Ḏ"=>"ḏ","Ḍ"=>"ḍ","Ḋ"=>"ḋ","Ḉ"=>"ḉ","Ḇ"=>"ḇ","Ḅ"=>"ḅ","Ḃ"=>"ḃ","Ḁ"=>"ḁ",
- "Ֆ"=>"ֆ","Օ"=>"օ","Ք"=>"ք","Փ"=>"փ","Ւ"=>"ւ","Ց"=>"ց","Ր"=>"ր","Տ"=>"տ","Վ"=>"վ","Ս"=>"ս",
- "Ռ"=>"ռ","Ջ"=>"ջ","Պ"=>"պ","Չ"=>"չ","Ո"=>"ո","Շ"=>"շ","Ն"=>"ն","Յ"=>"յ","Մ"=>"մ","Ճ"=>"ճ",
- "Ղ"=>"ղ","Ձ"=>"ձ","Հ"=>"հ","Կ"=>"կ","Ծ"=>"ծ","Խ"=>"խ","Լ"=>"լ","Ի"=>"ի","Ժ"=>"ժ","Թ"=>"թ",
- "Ը"=>"ը","Է"=>"է","Զ"=>"զ","Ե"=>"ե","Դ"=>"դ","Գ"=>"գ","Բ"=>"բ","Ա"=>"ա","Ԏ"=>"ԏ","Ԍ"=>"ԍ",
- "Ԋ"=>"ԋ","Ԉ"=>"ԉ","Ԇ"=>"ԇ","Ԅ"=>"ԅ","Ԃ"=>"ԃ","Ԁ"=>"ԁ","Ӹ"=>"ӹ","Ӵ"=>"ӵ","Ӳ"=>"ӳ","Ӱ"=>"ӱ",
- "Ӯ"=>"ӯ","Ӭ"=>"ӭ","Ӫ"=>"ӫ","Ө"=>"ө","Ӧ"=>"ӧ","Ӥ"=>"ӥ","Ӣ"=>"ӣ","Ӡ"=>"ӡ","Ӟ"=>"ӟ","Ӝ"=>"ӝ",
- "Ӛ"=>"ӛ","Ә"=>"ә","Ӗ"=>"ӗ","Ӕ"=>"ӕ","Ӓ"=>"ӓ","Ӑ"=>"ӑ","Ӎ"=>"ӎ","Ӌ"=>"ӌ","Ӊ"=>"ӊ","Ӈ"=>"ӈ",
- "Ӆ"=>"ӆ","Ӄ"=>"ӄ","Ӂ"=>"ӂ","Ҿ"=>"ҿ","Ҽ"=>"ҽ","Һ"=>"һ","Ҹ"=>"ҹ","Ҷ"=>"ҷ","Ҵ"=>"ҵ","Ҳ"=>"ҳ",
- "Ұ"=>"ұ","Ү"=>"ү","Ҭ"=>"ҭ","Ҫ"=>"ҫ","Ҩ"=>"ҩ","Ҧ"=>"ҧ","Ҥ"=>"ҥ","Ң"=>"ң","Ҡ"=>"ҡ","Ҟ"=>"ҟ",
- "Ҝ"=>"ҝ","Қ"=>"қ","Ҙ"=>"ҙ","Җ"=>"җ","Ҕ"=>"ҕ","Ғ"=>"ғ","Ґ"=>"ґ","Ҏ"=>"ҏ","Ҍ"=>"ҍ","Ҋ"=>"ҋ",
- "Ҁ"=>"ҁ","Ѿ"=>"ѿ","Ѽ"=>"ѽ","Ѻ"=>"ѻ","Ѹ"=>"ѹ","Ѷ"=>"ѷ","Ѵ"=>"ѵ","Ѳ"=>"ѳ","Ѱ"=>"ѱ","Ѯ"=>"ѯ",
- "Ѭ"=>"ѭ","Ѫ"=>"ѫ","Ѩ"=>"ѩ","Ѧ"=>"ѧ","Ѥ"=>"ѥ","Ѣ"=>"ѣ","Ѡ"=>"ѡ","Џ"=>"џ","Ў"=>"ў","Ѝ"=>"ѝ",
- "Ќ"=>"ќ","Ћ"=>"ћ","Њ"=>"њ","Љ"=>"љ","Ј"=>"ј","Ї"=>"ї","І"=>"і","Ѕ"=>"ѕ","Є"=>"є","Ѓ"=>"ѓ",
- "Ђ"=>"ђ","Ё"=>"ё","Ѐ"=>"ѐ","Я"=>"я","Ю"=>"ю","Э"=>"э","Ь"=>"ь","Ы"=>"ы","Ъ"=>"ъ","Щ"=>"щ",
- "Ш"=>"ш","Ч"=>"ч","Ц"=>"ц","Х"=>"х","Ф"=>"ф","У"=>"у","Т"=>"т","С"=>"с","Р"=>"р","П"=>"п",
- "О"=>"о","Н"=>"н","М"=>"м","Л"=>"л","К"=>"к","Й"=>"й","И"=>"и","З"=>"з","Ж"=>"ж","Е"=>"е",
- "Д"=>"д","Г"=>"г","В"=>"в","Б"=>"б","А"=>"а","Ε"=>"ϵ","Σ"=>"ϲ","Ρ"=>"ϱ","Κ"=>"ϰ","Ϯ"=>"ϯ",
- "Ϭ"=>"ϭ","Ϫ"=>"ϫ","Ϩ"=>"ϩ","Ϧ"=>"ϧ","Ϥ"=>"ϥ","Ϣ"=>"ϣ","Ϡ"=>"ϡ","Ϟ"=>"ϟ","Ϝ"=>"ϝ","Ϛ"=>"ϛ",
- "Ϙ"=>"ϙ","Π"=>"ϖ","Φ"=>"ϕ","Θ"=>"ϑ","Β"=>"ϐ","Ώ"=>"ώ","Ύ"=>"ύ","Ό"=>"ό","Ϋ"=>"ϋ","Ϊ"=>"ϊ",
- "Ω"=>"ω","Ψ"=>"ψ","Χ"=>"χ","Φ"=>"φ","Υ"=>"υ","Τ"=>"τ","Σ"=>"σ","Σ"=>"ς","Ρ"=>"ρ","Π"=>"π",
- "Ο"=>"ο","Ξ"=>"ξ","Ν"=>"ν","Μ"=>"μ","Λ"=>"λ","Κ"=>"κ","Ι"=>"ι","Θ"=>"θ","Η"=>"η","Ζ"=>"ζ",
- "Ε"=>"ε","Δ"=>"δ","Γ"=>"γ","Β"=>"β","Α"=>"α","Ί"=>"ί","Ή"=>"ή","Έ"=>"έ","Ά"=>"ά","Ʒ"=>"ʒ",
- "Ʋ"=>"ʋ","Ʊ"=>"ʊ","Ʈ"=>"ʈ","Ʃ"=>"ʃ","Ʀ"=>"ʀ","Ɵ"=>"ɵ","Ɲ"=>"ɲ","Ɯ"=>"ɯ","Ɩ"=>"ɩ","Ɨ"=>"ɨ",
- "Ɣ"=>"ɣ","Ɛ"=>"ɛ","Ə"=>"ə","Ɗ"=>"ɗ","Ɖ"=>"ɖ","Ɔ"=>"ɔ","Ɓ"=>"ɓ","Ȳ"=>"ȳ","Ȱ"=>"ȱ","Ȯ"=>"ȯ",
- "Ȭ"=>"ȭ","Ȫ"=>"ȫ","Ȩ"=>"ȩ","Ȧ"=>"ȧ","Ȥ"=>"ȥ","Ȣ"=>"ȣ","Ȟ"=>"ȟ","Ȝ"=>"ȝ","Ț"=>"ț","Ș"=>"ș",
- "Ȗ"=>"ȗ","Ȕ"=>"ȕ","Ȓ"=>"ȓ","Ȑ"=>"ȑ","Ȏ"=>"ȏ","Ȍ"=>"ȍ","Ȋ"=>"ȋ","Ȉ"=>"ȉ","Ȇ"=>"ȇ","Ȅ"=>"ȅ",
- "Ȃ"=>"ȃ","Ȁ"=>"ȁ","Ǿ"=>"ǿ","Ǽ"=>"ǽ","Ǻ"=>"ǻ","Ǹ"=>"ǹ","Ǵ"=>"ǵ","Dz"=>"dz","Ǯ"=>"ǯ","Ǭ"=>"ǭ",
- "Ǫ"=>"ǫ","Ǩ"=>"ǩ","Ǧ"=>"ǧ","Ǥ"=>"ǥ","Ǣ"=>"ǣ","Ǡ"=>"ǡ","Ǟ"=>"ǟ","Ǝ"=>"ǝ","Ǜ"=>"ǜ","Ǚ"=>"ǚ",
- "Ǘ"=>"ǘ","Ǖ"=>"ǖ","Ǔ"=>"ǔ","Ǒ"=>"ǒ","Ǐ"=>"ǐ","Ǎ"=>"ǎ","Nj"=>"nj","Lj"=>"lj","Dž"=>"dž","Ƿ"=>"ƿ",
- "Ƽ"=>"ƽ","Ƹ"=>"ƹ","Ƶ"=>"ƶ","Ƴ"=>"ƴ","Ư"=>"ư","Ƭ"=>"ƭ","Ƨ"=>"ƨ","Ƥ"=>"ƥ","Ƣ"=>"ƣ","Ơ"=>"ơ",
- "Ƞ"=>"ƞ","Ƙ"=>"ƙ","Ƕ"=>"ƕ","Ƒ"=>"ƒ","Ƌ"=>"ƌ","Ƈ"=>"ƈ","Ƅ"=>"ƅ","Ƃ"=>"ƃ","S"=>"ſ","Ž"=>"ž",
- "Ż"=>"ż","Ź"=>"ź","Ŷ"=>"ŷ","Ŵ"=>"ŵ","Ų"=>"ų","Ű"=>"ű","Ů"=>"ů","Ŭ"=>"ŭ","Ū"=>"ū","Ũ"=>"ũ",
- "Ŧ"=>"ŧ","Ť"=>"ť","Ţ"=>"ţ","Š"=>"š","Ş"=>"ş","Ŝ"=>"ŝ","Ś"=>"ś","Ř"=>"ř","Ŗ"=>"ŗ","Ŕ"=>"ŕ",
- "Œ"=>"œ","Ő"=>"ő","Ŏ"=>"ŏ","Ō"=>"ō","Ŋ"=>"ŋ","Ň"=>"ň","Ņ"=>"ņ","Ń"=>"ń","Ł"=>"ł","Ŀ"=>"ŀ",
- "Ľ"=>"ľ","Ļ"=>"ļ","Ĺ"=>"ĺ","Ķ"=>"ķ","Ĵ"=>"ĵ","IJ"=>"ij","I"=>"ı","Į"=>"į","Ĭ"=>"ĭ","Ī"=>"ī",
- "Ĩ"=>"ĩ","Ħ"=>"ħ","Ĥ"=>"ĥ","Ģ"=>"ģ","Ġ"=>"ġ","Ğ"=>"ğ","Ĝ"=>"ĝ","Ě"=>"ě","Ę"=>"ę","Ė"=>"ė",
- "Ĕ"=>"ĕ","Ē"=>"ē","Đ"=>"đ","Ď"=>"ď","Č"=>"č","Ċ"=>"ċ","Ĉ"=>"ĉ","Ć"=>"ć","Ą"=>"ą","Ă"=>"ă",
- "Ā"=>"ā","Ÿ"=>"ÿ","Þ"=>"þ","Ý"=>"ý","Ü"=>"ü","Û"=>"û","Ú"=>"ú","Ù"=>"ù","Ø"=>"ø","Ö"=>"ö",
- "Õ"=>"õ","Ô"=>"ô","Ó"=>"ó","Ò"=>"ò","Ñ"=>"ñ","Ð"=>"ð","Ï"=>"ï","Î"=>"î","Í"=>"í","Ì"=>"ì",
- "Ë"=>"ë","Ê"=>"ê","É"=>"é","È"=>"è","Ç"=>"ç","Æ"=>"æ","Å"=>"å","Ä"=>"ä","Ã"=>"ã","Â"=>"â",
- "Á"=>"á","À"=>"à","Μ"=>"µ","Z"=>"z","Y"=>"y","X"=>"x","W"=>"w","V"=>"v","U"=>"u","T"=>"t",
- "S"=>"s","R"=>"r","Q"=>"q","P"=>"p","O"=>"o","N"=>"n","M"=>"m","L"=>"l","K"=>"k","J"=>"j",
- "I"=>"i","H"=>"h","G"=>"g","F"=>"f","E"=>"e","D"=>"d","C"=>"c","B"=>"b","A"=>"a"
- );
- }; // end of case lookup tables
- /**
- * UTF-8 lookup table for lower case accented letters
- *
- * This lookuptable defines replacements for accented characters from the ASCII-7
- * range. This are lower case letters only.
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see utf8_deaccent()
- */
- global $UTF8_LOWER_ACCENTS;
- if(empty($UTF8_LOWER_ACCENTS)) $UTF8_LOWER_ACCENTS = array(
- 'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o',
- 'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k',
- 'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o',
- 'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o',
- 'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c',
- 'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't',
- 'ū' => 'u', 'č' => 'c', 'ö' => 'oe', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l',
- 'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z',
- 'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't',
- 'ŗ' => 'r', 'ä' => 'ae', 'í' => 'i', 'ŕ' => 'r',…
Large files files are truncated, but you can click here to view the full file