encoder.php

很棒的在线教学系统

                    }
                } 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;
    }
    
    /**
     * Translates a Unicode codepoint into its corresponding UTF-8 character.
     * @static
     * @note Based on Feyd's function at
     *       <http://forums.devnetwork.net/viewtopic.php?p=191404#191404>,
     *       which is in public domain.
     * @note While we're going to do code point parsing anyway, a good
     *       optimization would be to refuse to translate code points that
     *       are non-SGML characters.  However, this could lead to duplication.
     * @note This is very similar to the unichr function in
     *       maintenance/generate-entity-file.php (although this is superior,
     *       due to its sanity checks).
     */
    
    // +----------+----------+----------+----------+
    // | 33222222 | 22221111 | 111111   |          |
    // | 10987654 | 32109876 | 54321098 | 76543210 | bit
    // +----------+----------+----------+----------+
    // |          |          |          | 0xxxxxxx | 1 byte 0x00000000..0x0000007F
    // |          |          | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF
    // |          | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF
    // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF
    // +----------+----------+----------+----------+
    // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
    // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
    // +----------+----------+----------+----------+ 
    
    function unichr($code) {
        if($code > 1114111 or $code < 0 or
          ($code >= 55296 and $code <= 57343) ) {
            // bits are set outside the "valid" range as defined
            // by UNICODE 4.1.0 
            return '';
        }
        
        $x = $y = $z = $w = 0; 
        if ($code < 128) {
            // regular ASCII character
            $x = $code;
        } else {
            // set up bits for UTF-8
            $x = ($code & 63) | 128;
            if ($code < 2048) {
                $y = (($code & 2047) >> 6) | 192;
            } else {
                $y = (($code & 4032) >> 6) | 128;
                if($code < 65536) {
                    $z = (($code >> 12) & 15) | 224;
                } else {
                    $z = (($code >> 12) & 63) | 128;
                    $w = (($code >> 18) & 7)  | 240;
                }
            } 
        }
        // set up the actual character
        $ret = '';
        if($w) $ret .= chr($w);
        if($z) $ret .= chr($z);
        if($y) $ret .= chr($y);
        $ret .= chr($x); 
        
        return $ret;
    }
    
    /**
     * Converts a string to UTF-8 based on configuration.
     * @static
     */
    function convertToUTF8($str, $config, &$context) {
        $encoding = $config->get('Core', 'Encoding');
        if ($encoding === 'utf-8') return $str;
        static $iconv = null;
        if ($iconv === null) $iconv = function_exists('iconv');
        set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
            $str = iconv($encoding, 'utf-8//IGNORE', $str);
            // If the string is bjorked by Shift_JIS or a similar encoding
            // that doesn't support all of ASCII, convert the naughty
            // characters to their true byte-wise ASCII/UTF-8 equivalents.
            $str = strtr($str, HTMLPurifier_Encoder::testEncodingSupportsASCII($encoding));
            restore_error_handler();
            return $str;
        } elseif ($encoding === 'iso-8859-1') {
            $str = utf8_encode($str);
            restore_error_handler();
            return $str;
        }
        trigger_error('Encoding not supported', E_USER_ERROR);
    }
    
    /**
     * Converts a string from UTF-8 based on configuration.
     * @static
     * @note Currently, this is a lossy conversion, with unexpressable
     *       characters being omitted.
     */
    function convertFromUTF8($str, $config, &$context) {
        $encoding = $config->get('Core', 'Encoding');
        if ($encoding === 'utf-8') return $str;
        static $iconv = null;
        if ($iconv === null) $iconv = function_exists('iconv');
        if ($escape = $config->get('Core', 'EscapeNonASCIICharacters')) {
            $str = HTMLPurifier_Encoder::convertToASCIIDumbLossless($str);
        }
        set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
        if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
            // Undo our previous fix in convertToUTF8, otherwise iconv will barf
            $ascii_fix = HTMLPurifier_Encoder::testEncodingSupportsASCII($encoding);
            if (!$escape && !empty($ascii_fix)) {
                $clear_fix = array();
                foreach ($ascii_fix as $utf8 => $native) $clear_fix[$utf8] = '';
                $str = strtr($str, $clear_fix);
            }
            $str = strtr($str, array_flip($ascii_fix));
            // Normal stuff
            $str = iconv('utf-8', $encoding . '//IGNORE', $str);
            restore_error_handler();
            return $str;
        } elseif ($encoding === 'iso-8859-1') {
            $str = utf8_decode($str);
            restore_error_handler();
            return $str;
        }
        trigger_error('Encoding not supported', E_USER_ERROR);
    }
    
    /**
     * Lossless (character-wise) conversion of HTML to ASCII
     * @static
     * @param $str UTF-8 string to be converted to ASCII
     * @returns ASCII encoded string with non-ASCII character entity-ized
     * @warning Adapted from MediaWiki, claiming fair use: this is a common
     *       algorithm. If you disagree with this license fudgery,
     *       implement it yourself.
     * @note Uses decimal numeric entities since they are best supported.
     * @note This is a DUMB function: it has no concept of keeping
     *       character entities that the projected character encoding
     *       can allow. We could possibly implement a smart version
     *       but that would require it to also know which Unicode
     *       codepoints the charset supported (not an easy task).
     * @note Sort of with cleanUTF8() but it assumes that $str is
     *       well-formed UTF-8
     */
    function convertToASCIIDumbLossless($str) {
        $bytesleft = 0;
        $result = '';
        $working = 0;
        $len = strlen($str);
        for( $i = 0; $i < $len; $i++ ) {
            $bytevalue = ord( $str[$i] );
            if( $bytevalue <= 0x7F ) { //0xxx xxxx
                $result .= chr( $bytevalue );
                $bytesleft = 0;
            } elseif( $bytevalue <= 0xBF ) { //10xx xxxx
                $working = $working << 6;
                $working += ($bytevalue & 0x3F);
                $bytesleft--;
                if( $bytesleft <= 0 ) {
                    $result .= "&#" . $working . ";";
                }
            } elseif( $bytevalue <= 0xDF ) { //110x xxxx
                $working = $bytevalue & 0x1F;
                $bytesleft = 1;
            } elseif( $bytevalue <= 0xEF ) { //1110 xxxx
                $working = $bytevalue & 0x0F;
                $bytesleft = 2;
            } else { //1111 0xxx
                $working = $bytevalue & 0x07;
                $bytesleft = 3;
            }
        }
        return $result;
    }
    
    /**
     * This expensive function tests whether or not a given character
     * encoding supports ASCII. 7/8-bit encodings like Shift_JIS will
     * fail this test, and require special processing. Variable width
     * encodings shouldn't ever fail.
     * 
     * @param string $encoding Encoding name to test, as per iconv format
     * @param bool $bypass Whether or not to bypass the precompiled arrays.
     * @return Array of UTF-8 characters to their corresponding ASCII,
     *      which can be used to "undo" any overzealous iconv action.
     */
    function testEncodingSupportsASCII($encoding, $bypass = false) {
        static $encodings = array();
        if (!$bypass) {
            if (isset($encodings[$encoding])) return $encodings[$encoding];
            $lenc = strtolower($encoding);
            switch ($lenc) {
                case 'shift_jis':
                    return array("\xC2\xA5" => '\\', "\xE2\x80\xBE" => '~');
                case 'johab':
                    return array("\xE2\x82\xA9" => '\\');
            }
            if (strpos($lenc, 'iso-8859-') === 0) return array();
        }
        $ret = array();
        set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
        if (iconv('UTF-8', $encoding, 'a') === false) return false;
        for ($i = 0x20; $i <= 0x7E; $i++) { // all printable ASCII chars
            $c = chr($i);
            if (iconv('UTF-8', "$encoding//IGNORE", $c) === '') {
                // Reverse engineer: what's the UTF-8 equiv of this byte
                // sequence? This assumes that there's no variable width
                // encoding that doesn't support ASCII.
                $ret[iconv($encoding, 'UTF-8//IGNORE', $c)] = $c;
            }
        }
        restore_error_handler();
        $encodings[$encoding] = $ret;
        return $ret;
    }
    
    
}