Recent changes to feature-requests

Use preg_quote() instead?

David Pennington — Fri, 30 Oct 2009 19:01:52 -0000

I'm wondering why some of the functions manually quote meta characters in the regex rather than using preg_quote()?

//quote charlist for use in a characterclass
$charlist = preg_replace('!([\\\\\\-\\]\\[/^])!','\\\${1}',$charlist);

Replacing mb_* functions

David Pennington — Fri, 30 Oct 2009 18:47:43 -0000

After going through this library it seems like it would be easiest to add this code to existing projects by checking for and overriding the mb_* functions as needed. For example, you could do something like this:

if ( extension_loaded('mbstring') == FALSE ) {
include('utf8.php');
}

which would contain all the matching string functions (called utf8_*) defined as mb_* functions for a quick drop in place solution to hosts that don't have mutlibyte string support. Perhaps, I'm missing something - but this would seem to be an easier way to implement this very useful function lib.

Please consider adding utf8_sprintf/utf8_vprintf

aprisobal — Sat, 29 Sep 2007 09:41:36 -0000

function utf8_sprintf($format) {
$argv = func_get_args();
array_shift($argv);
return utf8_vprintf($format, $argv);
}

function utf8_vprintf($format, $arguments) {
if (mb_internal_encoding() != 'UTF-8') {
return vsprintf($format, $arguments);
}
$newargv = array();

preg_match_all("`\%('.+|[0 ]|)([1-9][0-9]*|)s`U", $format, $results, PREG_SET_ORDER);
if (count($results)) {
foreach($results as $result) {
list($string_format, $filler, $size) = $result;
if(strlen($filler) > 1) $filler = substr($filler, 1);
while(count($arguments) && !is_string($arg = array_shift($arguments))) $newargv[] = $arg;
$pos = strpos($format, $string_format);
$format = substr($format, 0, $pos)
. ($size ? str_repeat($filler, $size-strlen($arg)) : '')
. str_replace('%', '%%', $arg)
. substr($format, $pos+strlen($string_format));
}
if (!count($newargv)) {
return $format;
} else {
return vsprintf($format, $newargv);
}
} else {
return vsprintf($format, $arguments);
}
}

Please consider adding utf8_wordwrap

aprisobal — Sat, 29 Sep 2007 09:39:29 -0000

The function is not by me.

/**
* Wordwrap for utf8 encoded strings
* @param string $str
* @param integer $len
* @param string $what
* @return string
* @author Milian Wolff <mail@milianw.de>
*/
function utf8_wordwrap($str, $width, $break=" ", $cut = false){
if(!$cut){
$regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){'.$width.',}\b#U';
} else {
$regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){'.$width.'}#';
}
if(function_exists('mb_strlen')){
$str_len = mb_strlen($str, 'UTF-8');
} else {
$str_len = preg_match_all('/[\x00-\x7F\xC0-\xFD]/', $str, $var_empty);
}
$while_what = ceil($str_len / $width);
$i = 1;
$return = '';
while ($i < $while_what){
if (!preg_match($regexp, $str, $matches)) {
break;
}
$string = $matches[0];
$return .= $string . $break;
$str = substr($str,strlen($string));
$i++;
}
return $return.$str;
}

Please consider adding utf8_html_entity_decode

Kingsquare — Tue, 28 Aug 2007 08:49:11 -0000

Original author can be found here: (akniep at rayo dot info) http://www.php.net/manual/en/function.html-entity-decode.php

function utf8_html_entity_decode($string) {
static $trans_tbl;

// replace numeric entities
$string = preg_replace('~&#x([0-9a-f]+);~ei', 'code2utf(hexdec("\\1"))', $string);
$string = preg_replace('~&#([0-9]+);~e', 'code2utf(\\1)', $string);

// replace literal entities
if (!isset($trans_tbl)) {
$trans_tbl = array();
foreach (get_html_translation_table(HTML_ENTITIES) as $val=>$key)
$trans_tbl[$key] = utf8_encode($val);
}

return strtr($string, $trans_tbl);
}
// Returns the utf string corresponding to the unicode value (from php.net, courtesy - romans@void.lv)

function code2utf($number) {
if ($number < 0) return FALSE;
if ($number < 128) return chr($number);
// Removing / Replacing Windows Illegals Characters
if ($number < 160) {
if ($number==128) $number=8364;
elseif ($number==129) $number=160; // (Rayo:) #129 using no relevant sign, thus, mapped to the saved-space #160
elseif ($number==130) $number=8218;
elseif ($number==131) $number=402;
elseif ($number==132) $number=8222;
elseif ($number==133) $number=8230;
elseif ($number==134) $number=8224;
elseif ($number==135) $number=8225;
elseif ($number==136) $number=710;
elseif ($number==137) $number=8240;
elseif ($number==138) $number=352;
elseif ($number==139) $number=8249;
elseif ($number==140) $number=338;
elseif ($number==141) $number=160; // (Rayo:) #129 using no relevant sign, thus, mapped to the saved-space #160
elseif ($number==142) $number=381;
elseif ($number==143) $number=160; // (Rayo:) #129 using no relevant sign, thus, mapped to the saved-space #160
elseif ($number==144) $number=160; // (Rayo:) #129 using no relevant sign, thus, mapped to the saved-space #160
elseif ($number==145) $number=8216;
elseif ($number==146) $number=8217;
elseif ($number==147) $number=8220;
elseif ($number==148) $number=8221;
elseif ($number==149) $number=8226;
elseif ($number==150) $number=8211;
elseif ($number==151) $number=8212;
elseif ($number==152) $number=732;
elseif ($number==153) $number=8482;
elseif ($number==154) $number=353;
elseif ($number==155) $number=8250;
elseif ($number==156) $number=339;
elseif ($number==157) $number=160; // (Rayo:) #129 using no relevant sign, thus, mapped to the saved-space #160
elseif ($number==158) $number=382;
elseif ($number==159) $number=376;
} //if

if ($number < 2048) return chr(($number >> 6) + 192) . chr(($number & 63) + 128);
if ($number < 65536) return chr(($number >> 12) + 224) . chr((($number >> 6) & 63) + 128) . chr(($number & 63) + 128);
if ($number < 2097152) return chr(($number >> 18) + 240) . chr((($number >> 12) & 63) + 128) . chr((($number >> 6) & 63) + 128) . chr(($number & 63) + 128);

return false;
}