Source code for file /phputf8/utils/unicode.php
Documentation is available at unicode.php
* @version $Id: unicode.php,v 1.2 2006/02/26 13:20:44 harryf Exp $
* Tools for conversion between UTF-8 and unicode
* 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. All Rights Reserved.
* Ported to PHP by Henri Sivonen (http://hsivonen.iki.fi)
* Slight modifications to fit with phputf8 library by Harry Fuecks (hfuecks gmail com)
* @see http://lxr.mozilla.org/seamonkey/source/intl/uconv/src/nsUTF8ToUnicode.cpp
* @see http://lxr.mozilla.org/seamonkey/source/intl/uconv/src/nsUnicodeToUTF8.cpp
* @see http://hsivonen.iki.fi/php-utf8/
//--------------------------------------------------------------------
* 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
* 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
* @param string UTF-8 encoded string
* @return mixed array of unicode code points or FALSE if UTF-8 invalid
* @see http://hsivonen.iki.fi/php-utf8/
$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
$mBytes =
1; // cached expected number of octets in the current sequence
for($i =
0; $i <
$len; $i++
) {
// When mState is zero we expect either a US-ASCII character or a
if (0 ==
(0x80 & ($in))) {
// US-ASCII, pass straight through.
} else if (0xC0 ==
(0xE0 & ($in))) {
// First octet of 2 octet sequence
$mUcs4 =
($mUcs4 & 0x1F) <<
6;
} else if (0xE0 ==
(0xF0 & ($in))) {
// First octet of 3 octet sequence
$mUcs4 =
($mUcs4 & 0x0F) <<
12;
} else if (0xF0 ==
(0xF8 & ($in))) {
// First octet of 4 octet sequence
$mUcs4 =
($mUcs4 & 0x07) <<
18;
} 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.
$mUcs4 =
($mUcs4 & 0x03) <<
24;
} else if (0xFC ==
(0xFE & ($in))) {
// First octet of 6 octet sequence, see comments for 5 octet sequence.
$mUcs4 =
($mUcs4 & 1) <<
30;
/* Current octet is neither in the US-ASCII range nor a legal first
* octet of a multi-octet sequence.
'utf8_to_unicode: Illegal sequence identifier '.
// When mState is non-zero, we expect a continuation of the multi-octet
if (0x80 ==
(0xC0 & ($in))) {
$shift =
($mState -
1) *
6;
$tmp =
($tmp & 0x0000003F) <<
$shift;
* End of the multi-octet sequence. mUcs4 now contains the final
* Unicode codepoint to be output
* 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)) ||
// From Unicode 3.2, surrogate characters are illegal
(($mUcs4 & 0xFFFFF800) ==
0xD800) ||
// Codepoints outside the Unicode range are illegal
'utf8_to_unicode: Illegal sequence or codepoint '.
// BOM is legal but we don't want to output it
*((0xC0 & (*in) != 0x80) && (mState != 0))
* Incomplete multi-octet sequence.
'utf8_to_unicode: Incomplete multi-octet '.
' sequence in UTF-8 at byte '.
$i,
//--------------------------------------------------------------------
* Takes an array of ints representing the Unicode characters and returns
* a UTF-8 string. Astral planes are supported ie. the ints in the
* input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
* Returns false if the input array contains ints that represent
* surrogates or are outside the Unicode range
* and raises a PHP error at level E_USER_WARNING
* Note: this function has been modified slightly in this library to use
* output buffering to concatenate the UTF-8 string (faster) as well as
* reference the array by it's keys
* @param array of unicode code points representing a string
* @return mixed UTF-8 string or FALSE if array contains invalid code points
* @see http://hsivonen.iki.fi/php-utf8/
# ASCII range (including control chars)
if ( ($arr[$k] >=
0) &&
($arr[$k] <=
0x007f) ) {
} else if ($arr[$k] <=
0x07ff) {
echo
chr(0xc0 |
($arr[$k] >>
6));
echo
chr(0x80 |
($arr[$k] & 0x003f));
} else if($arr[$k] ==
0xFEFF) {
# Test for illegal surrogates
} else if ($arr[$k] >=
0xD800 &&
$arr[$k] <=
0xDFFF) {
'utf8_from_unicode: Illegal surrogate '.
'at index: '.
$k.
', value: '.
$arr[$k],
} else if ($arr[$k] <=
0xffff) {
echo
chr(0xe0 |
($arr[$k] >>
12));
echo
chr(0x80 |
(($arr[$k] >>
6) & 0x003f));
echo
chr(0x80 |
($arr[$k] & 0x003f));
} 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));
'utf8_from_unicode: Codepoint out of Unicode range '.
'at index: '.
$k.
', value: '.
$arr[$k],