Takes an UTF-8 string and returns an array of ints representing the Unicode characters. Astral planes are supported i.e. the ints in the output can be > 0xFFFF. Occurrences of the BOM are ignored. Surrogates are not allowed.
$array = UTF8::to_unicode($str);
The Original Code is Mozilla Communicator client code. The Initial Developer of the Original Code is Netscape Communications Corporation. Portions created by the Initial Developer are Copyright (C) 1998 the Initial Developer. Ported to PHP by Henri Sivonen hsivonen@iki.fi, see http://hsivonen.iki.fi/php-utf8/ Slight modifications to fit with phputf8 library by Harry Fuecks hfuecks@gmail.com
array Core_UTF8::to_unicode( string $str )
参数列表
参数 类型 描述 默认值 $strstringUTF-8 encoded string
array unicode code pointsFALSE if the string is invalidpublic static function to_unicode($str)
{
$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;
}
elseif ( 0xC0 == (0xE0 & $in) )
{
// First octet of 2 octet sequence
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 0x1F) << 6;
$mState = 1;
$mBytes = 2;
}
elseif ( 0xE0 == (0xF0 & $in) )
{
// First octet of 3 octet sequence
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 0x0F) << 12;
$mState = 2;
$mBytes = 3;
}
elseif ( 0xF0 == (0xF8 & $in) )
{
// First octet of 4 octet sequence
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 0x07) << 18;
$mState = 3;
$mBytes = 4;
}
elseif ( 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;
}
elseif ( 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;
}
else
{
// 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 == $mBytes) and ($mUcs4 < 0x0080)) or ((3 == $mBytes) and ($mUcs4 < 0x0800)) or ((4 == $mBytes) and ($mUcs4 < 0x10000)) or (4 < $mBytes) or // From Unicode 3.2, surrogate characters are illegal
Ucs4 & 0xFFFFF800) == 0xD800) or // Codepoints outside the Unicode range are illegal
cs4 > 0x10FFFF) )
{
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 UTF-8 cache
$mState = 0;
$mUcs4 = 0;
$mBytes = 1;
}
}
else
{
// ((0xC0 & (*in) != 0x80) AND (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;
}