htmlpurifier/library/HTMLPurifier/Encoder.php

<?php

require_once 'HTMLPurifier/EntityLookup.php';

/**
 * A UTF-8 specific character encoder that handles cleaning and transforming.
 */
class HTMLPurifier_Encoder
{
    
    /**
     * Cleans a UTF-8 string for well-formedness and SGML validity
     * 
     * It will parse according to UTF-8 and return 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.  However, we allow code points 9, 10
     *       and 13, which are the tab, line feed and carriage return
     *       respectively. 128 and above the code points map to multibyte
     *       UTF-8 representations.
     * 
     * @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 UTF-8 characters to be ignored.  Once
     *       PHP 6 appears all our problems magically disappear.
     * 
     * @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 <http://iki.fi/hsivonen/php-utf8/> under the
     *       LGPL license.  Notes on what changed are inside, but in general,
     *       the original code transformed UTF-8 text into an array of integer
     *       Unicode codepoints. Understandably, transforming that back to
     *       a string would be somewhat expensive, so the function was modded to
     *       directly operate on the string.  However, this discourages code
     *       reuse, and the logic enumerated here would be useful for any
     *       function that needs to be able to understand UTF-8 characters.
     *       As of right now, only smart lossless character encoding converters
     *       would need that, and I'm probably not going to implement them.
     *       Once again, PHP 6 should solve all our problems.
     */
    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
        
        // original code involved an $out that was an array of Unicode
        // codepoints.  Instead of having to convert back into UTF-8, we've
        // decided to directly append valid UTF-8 characters onto a string
        // $out once they're done.  $char accumulates raw bytes, while $mUcs4
        // turns into the Unicode code point, so there's some redundancy.
        
        $out = '';
        $char = '';
        
        $len = strlen($str);
        for($i = 0; $i < $len; $i++) {
            $in = ord($str{$i});
            $char .= $str[$i]; // append byte to char
            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.
                    if (($in <= 31 || $in == 127) && 
                        !($in == 9 || $in == 13 || $in == 10) // save \r\t\n
                    ) {
                        // control characters, remove
                    } else {
                        $out .= $char;
                    }
                    // reset
                    $char = '';
                    $mBytes = 1;
                } elseif (0xC0 == (0xE0 & ($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.
                    $mState = 0;
                    $mUcs4  = 0;
                    $mBytes = 1;
                    $char = '';
                }
            } else {
                // When mState is non-zero, we expect a continuation of the
                // multi-octet sequence
                if (0x80 == (0xC0 & ($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)
                        ) {
                            
                        } elseif (0xFEFF != $mUcs4 && // omit BOM
                            !($mUcs4 >= 128 && $mUcs4 <= 159) // omit non-SGML
                        ) {
                            $out .= $char;
                        }
                        // initialize UTF8 cache (reset)
                        $mState = 0;
                        $mUcs4  = 0;
                        $mBytes = 1;
                        $char = '';
                    }
                } else {
                    // ((0xC0 & (*in) != 0x80) && (mState != 0))
                    // Incomplete multi-octet sequence.
                    // used to result in complete fail, but we'll reset
                    $mState = 0;
                    $mUcs4  = 0;
                    $mBytes = 1;
                    $char ='';
                }
            }
        }
        return $out;
    }
    
    
}

?>