+global\HTML5_Tokenizer::consumeCharacterReference()

Complexity

Conditions	48
Paths	101

Size

Total Lines	243
Code Lines	97

Duplication

Lines	0
Ratio	0 %

<?php
    private function consumeCharacterReference($allowed = false, $inattr = false) {
        // This goes quite far against spec, and is far closer to the Python
        // impl., mainly because we don't do the large unconsuming the spec
        // requires.

        // All consumed characters.
        $chars = $this->stream->char();

        /* This section defines how to consume a character
        reference. This definition is used when parsing character
        references in text and in attributes.

        The behavior depends on the identity of the next character
        (the one immediately after the U+0026 AMPERSAND character): */

        if (
            $chars[0] === "\x09" ||
            $chars[0] === "\x0A" ||
            $chars[0] === "\x0C" ||
            $chars[0] === "\x20" ||
            $chars[0] === '<' ||
            $chars[0] === '&' ||
            $chars === false ||
            $chars[0] === $allowed
        ) {
            /* U+0009 CHARACTER TABULATION
               U+000A LINE FEED (LF)
               U+000C FORM FEED (FF)
               U+0020 SPACE
               U+003C LESS-THAN SIGN
               U+0026 AMPERSAND
               EOF
               The additional allowed character, if there is one
            Not a character reference. No characters are consumed,
            and nothing is returned. (This is not an error, either.) */
            // We already consumed, so unconsume.
            $this->stream->unget();
            return '&';
        } elseif ($chars[0] === '#') {
            /* Consume the U+0023 NUMBER SIGN. */
            // Um, yeah, we already did that.
            /* The behavior further depends on the character after
            the U+0023 NUMBER SIGN: */
            $chars .= $this->stream->char();
            if (isset($chars[1]) && ($chars[1] === 'x' || $chars[1] === 'X')) {
                /* U+0078 LATIN SMALL LETTER X
                   U+0058 LATIN CAPITAL LETTER X */
                /* Consume the X. */
                // Um, yeah, we already did that.
                /* Follow the steps below, but using the range of
                characters U+0030 DIGIT ZERO through to U+0039 DIGIT
                NINE, U+0061 LATIN SMALL LETTER A through to U+0066
                LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER
                A, through to U+0046 LATIN CAPITAL LETTER F (in other
                words, 0123456789, ABCDEF, abcdef). */
                $char_class = self::HEX;
                /* When it comes to interpreting the
                number, interpret it as a hexadecimal number. */
                $hex = true;
            } else {
                /* Anything else */
                // Unconsume because we shouldn't have consumed this.
                $chars = $chars[0];
                $this->stream->unget();
                /* Follow the steps below, but using the range of
                characters U+0030 DIGIT ZERO through to U+0039 DIGIT
                NINE (i.e. just 0123456789). */
                $char_class = self::DIGIT;
                /* When it comes to interpreting the number,
                interpret it as a decimal number. */
                $hex = false;
            }

            /* Consume as many characters as match the range of characters given above. */
            $consumed = $this->stream->charsWhile($char_class);
            if ($consumed === '' || $consumed === false) {
                /* If no characters match the range, then don't consume
                any characters (and unconsume the U+0023 NUMBER SIGN
                character and, if appropriate, the X character). This
                is a parse error; nothing is returned. */
                $this->emitToken(array(
                    'type' => self::PARSEERROR,
                    'data' => 'expected-numeric-entity'
                ));
                return '&' . $chars;
            } else {
                /* Otherwise, if the next character is a U+003B SEMICOLON,
                consume that too. If it isn't, there is a parse error. */
                if ($this->stream->char() !== ';') {
                    $this->stream->unget();
                    $this->emitToken(array(
                        'type' => self::PARSEERROR,
                        'data' => 'numeric-entity-without-semicolon'
                    ));
                }

                /* If one or more characters match the range, then take
                them all and interpret the string of characters as a number
                (either hexadecimal or decimal as appropriate). */
                $codepoint = $hex ? hexdec($consumed) : (int) $consumed;

                /* If that number is one of the numbers in the first column
                of the following table, then this is a parse error. Find the
                row with that number in the first column, and return a
                character token for the Unicode character given in the
                second column of that row. */
                $new_codepoint = HTML5_Data::getRealCodepoint($codepoint);
                if ($new_codepoint) {
                    $this->emitToken(array(
                        'type' => self::PARSEERROR,
                        'data' => 'illegal-windows-1252-entity'
                    ));
                    return HTML5_Data::utf8chr($new_codepoint);
                } else {
                    /* Otherwise, if the number is greater than 0x10FFFF, then 
                     * this is a parse error. Return a U+FFFD REPLACEMENT 
                     * CHARACTER. */
                    if ($codepoint > 0x10FFFF) {
                        $this->emitToken(array(
                            'type' => self::PARSEERROR,
                            'data' => 'overlong-character-entity' // XXX probably not correct
                        ));
                        return "\xEF\xBF\xBD";
                    }
                    /* Otherwise, return a character token for the Unicode 
                     * character whose code point is that number.  If the 
                     * number is in the range 0x0001 to 0x0008,    0x000E to 
                     * 0x001F,  0x007F  to 0x009F, 0xD800 to 0xDFFF, 0xFDD0 to 
                     * 0xFDEF, or is one of 0x000B, 0xFFFE, 0xFFFF, 0x1FFFE, 
                     * 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE, 0x3FFFF, 0x4FFFE, 
                     * 0x4FFFF, 0x5FFFE, 0x5FFFF, 0x6FFFE, 0x6FFFF, 0x7FFFE, 
                     * 0x7FFFF, 0x8FFFE, 0x8FFFF, 0x9FFFE, 0x9FFFF, 0xAFFFE, 
                     * 0xAFFFF, 0xBFFFE, 0xBFFFF, 0xCFFFE, 0xCFFFF, 0xDFFFE, 
                     * 0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE, 0xFFFFF, 0x10FFFE, 
                     * or 0x10FFFF, then this is a parse error. */
                    // && has higher precedence than ||
                    if (
                        $codepoint >= 0x0000 && $codepoint <= 0x0008 ||
                        $codepoint === 0x000B ||
                        $codepoint >= 0x000E && $codepoint <= 0x001F ||
                        $codepoint >= 0x007F && $codepoint <= 0x009F ||
                        $codepoint >= 0xD800 && $codepoint <= 0xDFFF ||
                        $codepoint >= 0xFDD0 && $codepoint <= 0xFDEF ||
                        ($codepoint & 0xFFFE) === 0xFFFE ||
                        $codepoint == 0x10FFFF || $codepoint == 0x10FFFE
                    ) {
                        $this->emitToken(array(
                            'type' => self::PARSEERROR,
                            'data' => 'illegal-codepoint-for-numeric-entity'
                        ));
                    }
                    return HTML5_Data::utf8chr($codepoint);
                }
            }

        } else {
            /* Anything else */

            /* Consume the maximum number of characters possible,
            with the consumed characters matching one of the
            identifiers in the first column of the named character
            references table (in a case-sensitive manner). */
            // What we actually do here is consume as much as we can while it
            // matches the start of one of the identifiers in the first column.

            $refs = HTML5_Data::getNamedCharacterReferences();
            
            // Get the longest string which is the start of an identifier
            // ($chars) as well as the longest identifier which matches ($id)
            // and its codepoint ($codepoint).
            $codepoint = false;
            $char = $chars;
            while ($char !== false && isset($refs[$char])) {
                $refs = $refs[$char];
                if (isset($refs['codepoint'])) {
                    $id = $chars;
                    $codepoint = $refs['codepoint'];
                }
                $chars .= $char = $this->stream->char();
            }
            
            // Unconsume the one character we just took which caused the while
            // statement to fail. This could be anything and could cause state
            // changes (as if it matches the while loop it must be
            // alphanumeric so we can just concat it to whatever we get later).
            $this->stream->unget();
            if ($char !== false) {
                $chars = substr($chars, 0, -1);
            }

            /* If no match can be made, then this is a parse error.
            No characters are consumed, and nothing is returned. */
            if (!$codepoint) {
                $this->emitToken(array(
                    'type' => self::PARSEERROR,
                    'data' => 'expected-named-entity'
                ));
                return '&' . $chars;
            }

            /* If the last character matched is not a U+003B SEMICOLON
            (;), there is a parse error. */
            $semicolon = true;
            if (substr($id, -1) !== ';') {
                $this->emitToken(array(
                    'type' => self::PARSEERROR,
                    'data' => 'named-entity-without-semicolon'
                ));
                $semicolon = false;
            }

            /* If the character reference is being consumed as part of
            an attribute, and the last character matched is not a
            U+003B SEMICOLON (;), and the next character is in the
            range U+0030 DIGIT ZERO to U+0039 DIGIT NINE, U+0041
            LATIN CAPITAL LETTER A to U+005A LATIN CAPITAL LETTER Z,
            or U+0061 LATIN SMALL LETTER A to U+007A LATIN SMALL LETTER Z,
            then, for historical reasons, all the characters that were
            matched after the U+0026 AMPERSAND (&) must be unconsumed,
            and nothing is returned. */
            if ($inattr && !$semicolon) {
                // The next character is either the next character in $chars or in the stream.
                if (strlen($chars) > strlen($id)) {
                    $next = substr($chars, strlen($id), 1);
                } else {
                    $next = $this->stream->char();
                    $this->stream->unget();
                }
                if (
                    '0' <= $next && $next <= '9' ||
                    'A' <= $next && $next <= 'Z' ||
                    'a' <= $next && $next <= 'z'
                ) {
                    return '&' . $chars;
                }
            }

            /* Otherwise, return a character token for the character
            corresponding to the character reference name (as given
            by the second column of the named character references table). */
            return HTML5_Data::utf8chr($codepoint) . substr($chars, strlen($id));
        }
    }