note 93162 added to function.utf8-encode
| From: | squeegee at osu1 dot php dot net | Date: | Wed, 26 Aug 2009 13:20:46 +0000 |
| Subject: | note 93162 added to function.utf8-encode | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-159901@lists.php.net to get a copy of this message | ||
I think this is a reasonable port of Perl's Encoding::FixLatin by Grant McLean, which converts
a string with mixed encodings (ASCII, ISO-8859-1, CP1252, and UTF-8) to UTF-8.
<?php
function init_byte_map(){
global $byte_map;
for($x=128;$x<256;++$x){
$byte_map[chr($x)]=utf8_encode(chr($x));
}
$cp1252_map=array(
"\x80"=>"\xE2\x82\xAC", // EURO SIGN
"\x82" => "\xE2\x80\x9A", // SINGLE LOW-9 QUOTATION MARK
"\x83" => "\xC6\x92", // LATIN SMALL LETTER F WITH HOOK
"\x84" => "\xE2\x80\x9E", // DOUBLE LOW-9 QUOTATION MARK
"\x85" => "\xE2\x80\xA6", // HORIZONTAL ELLIPSIS
"\x86" => "\xE2\x80\xA0", // DAGGER
"\x87" => "\xE2\x80\xA1", // DOUBLE DAGGER
"\x88" => "\xCB\x86", // MODIFIER LETTER CIRCUMFLEX ACCENT
"\x89" => "\xE2\x80\xB0", // PER MILLE SIGN
"\x8A" => "\xC5\xA0", // LATIN CAPITAL LETTER S WITH CARON
"\x8B" => "\xE2\x80\xB9", // SINGLE LEFT-POINTING ANGLE QUOTATION MARK
"\x8C" => "\xC5\x92", // LATIN CAPITAL LIGATURE OE
"\x8E" => "\xC5\xBD", // LATIN CAPITAL LETTER Z WITH CARON
"\x91" => "\xE2\x80\x98", // LEFT SINGLE QUOTATION MARK
"\x92" => "\xE2\x80\x99", // RIGHT SINGLE QUOTATION MARK
"\x93" => "\xE2\x80\x9C", // LEFT DOUBLE QUOTATION MARK
"\x94" => "\xE2\x80\x9D", // RIGHT DOUBLE QUOTATION MARK
"\x95" => "\xE2\x80\xA2", // BULLET
"\x96" => "\xE2\x80\x93", // EN DASH
"\x97" => "\xE2\x80\x94", // EM DASH
"\x98" => "\xCB\x9C", // SMALL TILDE
"\x99" => "\xE2\x84\xA2", // TRADE MARK SIGN
"\x9A" => "\xC5\xA1", // LATIN SMALL LETTER S WITH CARON
"\x9B" => "\xE2\x80\xBA", // SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
"\x9C" => "\xC5\x93", // LATIN SMALL LIGATURE OE
"\x9E" => "\xC5\xBE", // LATIN SMALL LETTER Z WITH CARON
"\x9F" => "\xC5\xB8" // LATIN CAPITAL LETTER Y WITH DIAERESIS
);
foreach($cp1252_map as $k=>$v){
$byte_map[$k]=$v;
}
}
function fix_latin($instr){
if(mb_check_encoding($instr,'UTF-8'))return $instr; // no need for the rest if it's
all valid UTF-8 already
global $nibble_good_chars,$byte_map;
$outstr='';
$char='';
$rest='';
while((strlen($instr))>0){
if(1==preg_match($nibble_good_chars,$input,$match)){
$char=$match[1];
$rest=$match[2];
$outstr.=$char;
}elseif(1==preg_match('@^(.)(.*)$@s',$input,$match)){
$char=$match[1];
$rest=$match[2];
$outstr.=$byte_map[$char];
}
$instr=$rest;
}
return $outstr;
}
$byte_map=array();
init_byte_map();
$ascii_char='[\x00-\x7F]';
$cont_byte='[\x80-\xBF]';
$utf8_2='[\xC0-\xDF]'.$cont_byte;
$utf8_3='[\xE0-\xEF]'.$cont_byte.'{2}';
$utf8_4='[\xF0-\xF7]'.$cont_byte.'{3}';
$utf8_5='[\xF8-\xFB]'.$cont_byte.'{4}';
$nibble_good_chars = "@^($ascii_char+|$utf8_2|$utf8_3|$utf8_4|$utf8_5)(.*)$@s";
?>
Then just call fix_latin wherever you need it.
----
Server IP: 208.69.120.35
Probable Submitter: 72.174.41.7
----
Manual Page -- http://www.php.net/manual/en/function.utf8-encode.php
Edit -- https://master.php.net/note/edit/93162
Del: integrated -- https://master.php.net/note/delete/93162/integrated
Del: useless -- https://master.php.net/note/delete/93162/useless
Del: bad code -- https://master.php.net/note/delete/93162/bad+code
Del: spam -- https://master.php.net/note/delete/93162/spam
Del: non-english -- https://master.php.net/note/delete/93162/non-english
Del: in docs -- https://master.php.net/note/delete/93162/in+docs
Del: other reasons-- https://master.php.net/note/delete/93162
Reject -- https://master.php.net/note/reject/93162
Search -- https://master.php.net/manage/user-notes.php