3 // warning: this file is encoded in UTF-8!
8 // at some point this should be moved to a .ser file. Another
9 // possible optimization is to give UTF-8 bytes, not Unicode
11 protected static $realCodepointTable = array(
12 0x0D => 0x000A, // LINE FEED (LF)
13 0x80 => 0x20AC, // EURO SIGN ('€')
14 0x81 => 0xFFFD, // REPLACEMENT CHARACTER
15 0x82 => 0x201A, // SINGLE LOW-9 QUOTATION MARK ('‚')
16 0x83 => 0x0192, // LATIN SMALL LETTER F WITH HOOK ('ƒ')
17 0x84 => 0x201E, // DOUBLE LOW-9 QUOTATION MARK ('„')
18 0x85 => 0x2026, // HORIZONTAL ELLIPSIS ('…')
19 0x86 => 0x2020, // DAGGER ('†')
20 0x87 => 0x2021, // DOUBLE DAGGER ('‡')
21 0x88 => 0x02C6, // MODIFIER LETTER CIRCUMFLEX ACCENT ('ˆ')
22 0x89 => 0x2030, // PER MILLE SIGN ('‰')
23 0x8A => 0x0160, // LATIN CAPITAL LETTER S WITH CARON ('Š')
24 0x8B => 0x2039, // SINGLE LEFT-POINTING ANGLE QUOTATION MARK ('‹')
25 0x8C => 0x0152, // LATIN CAPITAL LIGATURE OE ('Œ')
26 0x8D => 0xFFFD, // REPLACEMENT CHARACTER
27 0x8E => 0x017D, // LATIN CAPITAL LETTER Z WITH CARON ('Ž')
28 0x8F => 0xFFFD, // REPLACEMENT CHARACTER
29 0x90 => 0xFFFD, // REPLACEMENT CHARACTER
30 0x91 => 0x2018, // LEFT SINGLE QUOTATION MARK ('‘')
31 0x92 => 0x2019, // RIGHT SINGLE QUOTATION MARK ('’')
32 0x93 => 0x201C, // LEFT DOUBLE QUOTATION MARK ('“')
33 0x94 => 0x201D, // RIGHT DOUBLE QUOTATION MARK ('”')
34 0x95 => 0x2022, // BULLET ('•')
35 0x96 => 0x2013, // EN DASH ('–')
36 0x97 => 0x2014, // EM DASH ('—')
37 0x98 => 0x02DC, // SMALL TILDE ('˜')
38 0x99 => 0x2122, // TRADE MARK SIGN ('™')
39 0x9A => 0x0161, // LATIN SMALL LETTER S WITH CARON ('š')
40 0x9B => 0x203A, // SINGLE RIGHT-POINTING ANGLE QUOTATION MARK ('›')
41 0x9C => 0x0153, // LATIN SMALL LIGATURE OE ('œ')
42 0x9D => 0xFFFD, // REPLACEMENT CHARACTER
43 0x9E => 0x017E, // LATIN SMALL LETTER Z WITH CARON ('ž')
44 0x9F => 0x0178, // LATIN CAPITAL LETTER Y WITH DIAERESIS ('Ÿ')
47 protected static $namedCharacterReferences;
49 protected static $namedCharacterReferenceMaxLength;
52 * Returns the "real" Unicode codepoint of a malformed character
55 public static function getRealCodepoint($ref) {
56 if (!isset(self::$realCodepointTable[$ref])) return false;
57 else return self::$realCodepointTable[$ref];
60 public static function getNamedCharacterReferences() {
61 if (!self::$namedCharacterReferences) {
62 self::$namedCharacterReferences = unserialize(
63 file_get_contents(dirname(__FILE__) . '/named-character-references.ser'));
65 return self::$namedCharacterReferences;
68 public static function getNamedCharacterReferenceMaxLength() {
69 if (!self::$namedCharacterReferenceMaxLength) {
70 $namedCharacterReferences = self::getNamedCharacterReferences();
71 $lengths = array_map('strlen', array_keys($namedCharacterReferences));
72 self::$namedCharacterReferenceMaxLength = max($lengths);
74 return self::$namedCharacterReferenceMaxLength;
79 * Converts a Unicode codepoint to sequence of UTF-8 bytes.
80 * @note Shamelessly stolen from HTML Purifier, which is also
81 * shamelessly stolen from Feyd (which is in public domain).
83 public static function utf8chr($code) {
84 if($code > 0x10FFFF or $code < 0x0 or
85 ($code >= 0xD800 and $code <= 0xDFFF) ) {
86 // bits are set outside the "valid" range as defined
88 return "\xEF\xBF\xBD";
91 $x = $y = $z = $w = 0;
93 // regular ASCII character
96 // set up bits for UTF-8
97 $x = ($code & 0x3F) | 0x80;
99 $y = (($code & 0x7FF) >> 6) | 0xC0;
101 $y = (($code & 0xFC0) >> 6) | 0x80;
102 if($code < 0x10000) {
103 $z = (($code >> 12) & 0x0F) | 0xE0;
105 $z = (($code >> 12) & 0x3F) | 0x80;
106 $w = (($code >> 18) & 0x07) | 0xF0;
110 // set up the actual character
112 if($w) $ret .= chr($w);
113 if($z) $ret .= chr($z);
114 if($y) $ret .= chr($y);