From 42ba96e2de227d3f85b21b20bca2bf3e2caf3852 Mon Sep 17 00:00:00 2001 From: "Edward Z. Yang" Date: Fri, 18 Aug 2006 20:06:40 +0000 Subject: [PATCH] Put in cleanUTF8 function, currently unused but will be adapted for our needs. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@300 48356398-32a2-884e-a903-53898d9a118a --- library/HTMLPurifier/Lexer.php | 139 +++++++++++++++++++++++++++++++++ 1 file changed, 139 insertions(+) diff --git a/library/HTMLPurifier/Lexer.php b/library/HTMLPurifier/Lexer.php index cb4f0fcc..4f35c441 100644 --- a/library/HTMLPurifier/Lexer.php +++ b/library/HTMLPurifier/Lexer.php @@ -306,6 +306,145 @@ class HTMLPurifier_Lexer } } + /** + * Currently converts UTF8 into an array of Unicode codepoints. (changing) + * + * We're going to convert this into a multi-purpose UTF-8 well-formedness + * checker as well as handler for the control characters that are illegal + * in SGML documents. But *after* we draw up some unit-tests. This means + * that the function, in the end, will not return an array of codepoints + * but a valid UTF8 string, with non-SGML codepoints excluded. + * + * @note Just for reference, the non-SGML code points are 0 to 31 and + * 127 to 159, inclusive. + * + * @note The functionality provided by the original function could be + * implemented with iconv using 'UTF-8//IGNORE', mbstring, or + * even the PCRE modifier 'u', these do not allow us to strip + * control characters or disallowed code points, and the latter + * does not allow invalid UTF8 characters to be ignored. + * + * @note Decomposing the string into Unicode code points is necessary + * because SGML disallows the use of specific code points, not + * necessarily bytes. A naive implementation that simply strtr + * disallowed code points as bytes will break other Unicode + * characters in which using such bytes is valid. + * + * @note Code adapted from utf8ToUnicode by Henri Sivonen and + * hsivonen@iki.fi at under the + * LGPL license. + */ + function cleanUTF8($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 (0 == $mState) { + // When mState is zero we expect either a US-ASCII character + // or a multi-octet sequence. + if (0 == (0x80 & ($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; + $mBytes = 6; + } else { + // Current octet is neither in the US-ASCII range nor a + // legal first octet of a multi-octet sequence. + return false; + } + } else { + // When mState is non-zero, we expect a continuation of the + // multi-octet sequence + if (0x80 == (0xC0 & ($in))) { + // Legal continuation. + $shift = ($mState - 1) * 6; + $tmp = $in; + $tmp = ($tmp & 0x0000003F) << $shift; + $mUcs4 |= $tmp; + + if (0 == --$mState) { + // 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)) || + (4 < $mBytes) || + // From Unicode 3.2, surrogate characters = illegal + (($mUcs4 & 0xFFFFF800) == 0xD800) || + // Codepoints outside the Unicode range are illegal + ($mUcs4 > 0x10FFFF) + ) { + return false; + } + if (0xFEFF != $mUcs4) { + // BOM is legal but we don't want to output it + $out[] = $mUcs4; + } + //initialize UTF8 cache + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + } + } else { + // ((0xC0 & (*in) != 0x80) && (mState != 0)) + * + * Incomplete multi-octet sequence. + */ + return false; + } + } + } + return $out; + } + } ?> \ No newline at end of file