diff options
Diffstat (limited to 'plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser')
12 files changed, 3311 insertions, 0 deletions
diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/CharacterReference.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/CharacterReference.php new file mode 100644 index 000000000..490b5487b --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/CharacterReference.php @@ -0,0 +1,61 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +use Masterminds\HTML5\Entities; + +/** + * Manage entity references. + * + * This is a simple resolver for HTML5 character reference entitites. See Entities for the list of supported entities. + */ +class CharacterReference +{ + protected static $numeric_mask = array( + 0x0, + 0x2FFFF, + 0, + 0xFFFF, + ); + + /** + * Given a name (e.g. 'amp'), lookup the UTF-8 character ('&'). + * + * @param string $name The name to look up. + * + * @return string The character sequence. In UTF-8 this may be more than one byte. + */ + public static function lookupName($name) + { + // Do we really want to return NULL here? or FFFD + return isset(Entities::$byName[$name]) ? Entities::$byName[$name] : null; + } + + /** + * Given a decimal number, return the UTF-8 character. + * + * @param $int + * + * @return false|string|string[]|null + */ + public static function lookupDecimal($int) + { + $entity = '&#' . $int . ';'; + + // UNTESTED: This may fail on some planes. Couldn't find full documentation + // on the value of the mask array. + return mb_decode_numericentity($entity, static::$numeric_mask, 'utf-8'); + } + + /** + * Given a hexidecimal number, return the UTF-8 character. + * + * @param $hexdec + * + * @return false|string|string[]|null + */ + public static function lookupHex($hexdec) + { + return static::lookupDecimal(hexdec($hexdec)); + } +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/DOMTreeBuilder.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/DOMTreeBuilder.php new file mode 100644 index 000000000..293d83e2a --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/DOMTreeBuilder.php @@ -0,0 +1,705 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +use Masterminds\HTML5\Elements; +use Masterminds\HTML5\InstructionProcessor; + +/** + * Create an HTML5 DOM tree from events. + * + * This attempts to create a DOM from events emitted by a parser. This + * attempts (but does not guarantee) to up-convert older HTML documents + * to HTML5. It does this by applying HTML5's rules, but it will not + * change the architecture of the document itself. + * + * Many of the error correction and quirks features suggested in the specification + * are implemented herein; however, not all of them are. Since we do not + * assume a graphical user agent, no presentation-specific logic is conducted + * during tree building. + * + * FIXME: The present tree builder does not exactly follow the state machine rules + * for insert modes as outlined in the HTML5 spec. The processor needs to be + * re-written to accomodate this. See, for example, the Go language HTML5 + * parser. + */ +class DOMTreeBuilder implements EventHandler +{ + /** + * Defined in http://www.w3.org/TR/html51/infrastructure.html#html-namespace-0. + */ + const NAMESPACE_HTML = 'http://www.w3.org/1999/xhtml'; + + const NAMESPACE_MATHML = 'http://www.w3.org/1998/Math/MathML'; + + const NAMESPACE_SVG = 'http://www.w3.org/2000/svg'; + + const NAMESPACE_XLINK = 'http://www.w3.org/1999/xlink'; + + const NAMESPACE_XML = 'http://www.w3.org/XML/1998/namespace'; + + const NAMESPACE_XMLNS = 'http://www.w3.org/2000/xmlns/'; + + const OPT_DISABLE_HTML_NS = 'disable_html_ns'; + + const OPT_TARGET_DOC = 'target_document'; + + const OPT_IMPLICIT_NS = 'implicit_namespaces'; + + /** + * Holds the HTML5 element names that causes a namespace switch. + * + * @var array + */ + protected $nsRoots = array( + 'html' => self::NAMESPACE_HTML, + 'svg' => self::NAMESPACE_SVG, + 'math' => self::NAMESPACE_MATHML, + ); + + /** + * Holds the always available namespaces (which does not require the XMLNS declaration). + * + * @var array + */ + protected $implicitNamespaces = array( + 'xml' => self::NAMESPACE_XML, + 'xmlns' => self::NAMESPACE_XMLNS, + 'xlink' => self::NAMESPACE_XLINK, + ); + + /** + * Holds a stack of currently active namespaces. + * + * @var array + */ + protected $nsStack = array(); + + /** + * Holds the number of namespaces declared by a node. + * + * @var array + */ + protected $pushes = array(); + + /** + * Defined in 8.2.5. + */ + const IM_INITIAL = 0; + + const IM_BEFORE_HTML = 1; + + const IM_BEFORE_HEAD = 2; + + const IM_IN_HEAD = 3; + + const IM_IN_HEAD_NOSCRIPT = 4; + + const IM_AFTER_HEAD = 5; + + const IM_IN_BODY = 6; + + const IM_TEXT = 7; + + const IM_IN_TABLE = 8; + + const IM_IN_TABLE_TEXT = 9; + + const IM_IN_CAPTION = 10; + + const IM_IN_COLUMN_GROUP = 11; + + const IM_IN_TABLE_BODY = 12; + + const IM_IN_ROW = 13; + + const IM_IN_CELL = 14; + + const IM_IN_SELECT = 15; + + const IM_IN_SELECT_IN_TABLE = 16; + + const IM_AFTER_BODY = 17; + + const IM_IN_FRAMESET = 18; + + const IM_AFTER_FRAMESET = 19; + + const IM_AFTER_AFTER_BODY = 20; + + const IM_AFTER_AFTER_FRAMESET = 21; + + const IM_IN_SVG = 22; + + const IM_IN_MATHML = 23; + + protected $options = array(); + + protected $stack = array(); + + protected $current; // Pointer in the tag hierarchy. + protected $rules; + protected $doc; + + protected $frag; + + protected $processor; + + protected $insertMode = 0; + + /** + * Track if we are in an element that allows only inline child nodes. + * + * @var string|null + */ + protected $onlyInline; + + /** + * Quirks mode is enabled by default. + * Any document that is missing the DT will be considered to be in quirks mode. + */ + protected $quirks = true; + + protected $errors = array(); + + public function __construct($isFragment = false, array $options = array()) + { + $this->options = $options; + + if (isset($options[self::OPT_TARGET_DOC])) { + $this->doc = $options[self::OPT_TARGET_DOC]; + } else { + $impl = new \DOMImplementation(); + // XXX: + // Create the doctype. For now, we are always creating HTML5 + // documents, and attempting to up-convert any older DTDs to HTML5. + $dt = $impl->createDocumentType('html'); + // $this->doc = \DOMImplementation::createDocument(NULL, 'html', $dt); + $this->doc = $impl->createDocument(null, '', $dt); + $this->doc->encoding = !empty($options['encoding']) ? $options['encoding'] : 'UTF-8'; + } + + $this->errors = array(); + + $this->current = $this->doc; // ->documentElement; + + // Create a rules engine for tags. + $this->rules = new TreeBuildingRules(); + + $implicitNS = array(); + if (isset($this->options[self::OPT_IMPLICIT_NS])) { + $implicitNS = $this->options[self::OPT_IMPLICIT_NS]; + } elseif (isset($this->options['implicitNamespaces'])) { + $implicitNS = $this->options['implicitNamespaces']; + } + + // Fill $nsStack with the defalut HTML5 namespaces, plus the "implicitNamespaces" array taken form $options + array_unshift($this->nsStack, $implicitNS + array('' => self::NAMESPACE_HTML) + $this->implicitNamespaces); + + if ($isFragment) { + $this->insertMode = static::IM_IN_BODY; + $this->frag = $this->doc->createDocumentFragment(); + $this->current = $this->frag; + } + } + + /** + * Get the document. + */ + public function document() + { + return $this->doc; + } + + /** + * Get the DOM fragment for the body. + * + * This returns a DOMNodeList because a fragment may have zero or more + * DOMNodes at its root. + * + * @see http://www.w3.org/TR/2012/CR-html5-20121217/syntax.html#concept-frag-parse-context + * + * @return \DOMDocumentFragment + */ + public function fragment() + { + return $this->frag; + } + + /** + * Provide an instruction processor. + * + * This is used for handling Processor Instructions as they are + * inserted. If omitted, PI's are inserted directly into the DOM tree. + * + * @param InstructionProcessor $proc + */ + public function setInstructionProcessor(InstructionProcessor $proc) + { + $this->processor = $proc; + } + + public function doctype($name, $idType = 0, $id = null, $quirks = false) + { + // This is used solely for setting quirks mode. Currently we don't + // try to preserve the inbound DT. We convert it to HTML5. + $this->quirks = $quirks; + + if ($this->insertMode > static::IM_INITIAL) { + $this->parseError('Illegal placement of DOCTYPE tag. Ignoring: ' . $name); + + return; + } + + $this->insertMode = static::IM_BEFORE_HTML; + } + + /** + * Process the start tag. + * + * @todo - XMLNS namespace handling (we need to parse, even if it's not valid) + * - XLink, MathML and SVG namespace handling + * - Omission rules: 8.1.2.4 Optional tags + * + * @param string $name + * @param array $attributes + * @param bool $selfClosing + * + * @return int + */ + public function startTag($name, $attributes = array(), $selfClosing = false) + { + $lname = $this->normalizeTagName($name); + + // Make sure we have an html element. + if (!$this->doc->documentElement && 'html' !== $name && !$this->frag) { + $this->startTag('html'); + } + + // Set quirks mode if we're at IM_INITIAL with no doctype. + if ($this->insertMode === static::IM_INITIAL) { + $this->quirks = true; + $this->parseError('No DOCTYPE specified.'); + } + + // SPECIAL TAG HANDLING: + // Spec says do this, and "don't ask." + // find the spec where this is defined... looks problematic + if ('image' === $name && !($this->insertMode === static::IM_IN_SVG || $this->insertMode === static::IM_IN_MATHML)) { + $name = 'img'; + } + + // Autoclose p tags where appropriate. + if ($this->insertMode >= static::IM_IN_BODY && Elements::isA($name, Elements::AUTOCLOSE_P)) { + $this->autoclose('p'); + } + + // Set insert mode: + switch ($name) { + case 'html': + $this->insertMode = static::IM_BEFORE_HEAD; + break; + case 'head': + if ($this->insertMode > static::IM_BEFORE_HEAD) { + $this->parseError('Unexpected head tag outside of head context.'); + } else { + $this->insertMode = static::IM_IN_HEAD; + } + break; + case 'body': + $this->insertMode = static::IM_IN_BODY; + break; + case 'svg': + $this->insertMode = static::IM_IN_SVG; + break; + case 'math': + $this->insertMode = static::IM_IN_MATHML; + break; + case 'noscript': + if ($this->insertMode === static::IM_IN_HEAD) { + $this->insertMode = static::IM_IN_HEAD_NOSCRIPT; + } + break; + } + + // Special case handling for SVG. + if ($this->insertMode === static::IM_IN_SVG) { + $lname = Elements::normalizeSvgElement($lname); + } + + $pushes = 0; + // when we found a tag thats appears inside $nsRoots, we have to switch the defalut namespace + if (isset($this->nsRoots[$lname]) && $this->nsStack[0][''] !== $this->nsRoots[$lname]) { + array_unshift($this->nsStack, array( + '' => $this->nsRoots[$lname], + ) + $this->nsStack[0]); + ++$pushes; + } + $needsWorkaround = false; + if (isset($this->options['xmlNamespaces']) && $this->options['xmlNamespaces']) { + // when xmlNamespaces is true a and we found a 'xmlns' or 'xmlns:*' attribute, we should add a new item to the $nsStack + foreach ($attributes as $aName => $aVal) { + if ('xmlns' === $aName) { + $needsWorkaround = $aVal; + array_unshift($this->nsStack, array( + '' => $aVal, + ) + $this->nsStack[0]); + ++$pushes; + } elseif ('xmlns' === (($pos = strpos($aName, ':')) ? substr($aName, 0, $pos) : '')) { + array_unshift($this->nsStack, array( + substr($aName, $pos + 1) => $aVal, + ) + $this->nsStack[0]); + ++$pushes; + } + } + } + + if ($this->onlyInline && Elements::isA($lname, Elements::BLOCK_TAG)) { + $this->autoclose($this->onlyInline); + $this->onlyInline = null; + } + + try { + $prefix = ($pos = strpos($lname, ':')) ? substr($lname, 0, $pos) : ''; + + if (false !== $needsWorkaround) { + $xml = "<$lname xmlns=\"$needsWorkaround\" " . (strlen($prefix) && isset($this->nsStack[0][$prefix]) ? ("xmlns:$prefix=\"" . $this->nsStack[0][$prefix] . '"') : '') . '/>'; + + $frag = new \DOMDocument('1.0', 'UTF-8'); + $frag->loadXML($xml); + + $ele = $this->doc->importNode($frag->documentElement, true); + } else { + if (!isset($this->nsStack[0][$prefix]) || ('' === $prefix && isset($this->options[self::OPT_DISABLE_HTML_NS]) && $this->options[self::OPT_DISABLE_HTML_NS])) { + $ele = $this->doc->createElement($lname); + } else { + $ele = $this->doc->createElementNS($this->nsStack[0][$prefix], $lname); + } + } + } catch (\DOMException $e) { + $this->parseError("Illegal tag name: <$lname>. Replaced with <invalid>."); + $ele = $this->doc->createElement('invalid'); + } + + if (Elements::isA($lname, Elements::BLOCK_ONLY_INLINE)) { + $this->onlyInline = $lname; + } + + // When we add some namespacess, we have to track them. Later, when "endElement" is invoked, we have to remove them. + // When we are on a void tag, we do not need to care about namesapce nesting. + if ($pushes > 0 && !Elements::isA($name, Elements::VOID_TAG)) { + // PHP tends to free the memory used by DOM, + // to avoid spl_object_hash collisions whe have to avoid garbage collection of $ele storing it into $pushes + // see https://bugs.php.net/bug.php?id=67459 + $this->pushes[spl_object_hash($ele)] = array($pushes, $ele); + } + + foreach ($attributes as $aName => $aVal) { + // xmlns attributes can't be set + if ('xmlns' === $aName) { + continue; + } + + if ($this->insertMode === static::IM_IN_SVG) { + $aName = Elements::normalizeSvgAttribute($aName); + } elseif ($this->insertMode === static::IM_IN_MATHML) { + $aName = Elements::normalizeMathMlAttribute($aName); + } + + $aVal = (string) $aVal; + + try { + $prefix = ($pos = strpos($aName, ':')) ? substr($aName, 0, $pos) : false; + + if ('xmlns' === $prefix) { + $ele->setAttributeNS(self::NAMESPACE_XMLNS, $aName, $aVal); + } elseif (false !== $prefix && isset($this->nsStack[0][$prefix])) { + $ele->setAttributeNS($this->nsStack[0][$prefix], $aName, $aVal); + } else { + $ele->setAttribute($aName, $aVal); + } + } catch (\DOMException $e) { + $this->parseError("Illegal attribute name for tag $name. Ignoring: $aName"); + continue; + } + + // This is necessary on a non-DTD schema, like HTML5. + if ('id' === $aName) { + $ele->setIdAttribute('id', true); + } + } + + if ($this->frag !== $this->current && $this->rules->hasRules($name)) { + // Some elements have special processing rules. Handle those separately. + $this->current = $this->rules->evaluate($ele, $this->current); + } else { + // Otherwise, it's a standard element. + $this->current->appendChild($ele); + + if (!Elements::isA($name, Elements::VOID_TAG)) { + $this->current = $ele; + } + + // Self-closing tags should only be respected on foreign elements + // (and are implied on void elements) + // See: https://www.w3.org/TR/html5/syntax.html#start-tags + if (Elements::isHtml5Element($name)) { + $selfClosing = false; + } + } + + // This is sort of a last-ditch attempt to correct for cases where no head/body + // elements are provided. + if ($this->insertMode <= static::IM_BEFORE_HEAD && 'head' !== $name && 'html' !== $name) { + $this->insertMode = static::IM_IN_BODY; + } + + // When we are on a void tag, we do not need to care about namesapce nesting, + // but we have to remove the namespaces pushed to $nsStack. + if ($pushes > 0 && Elements::isA($name, Elements::VOID_TAG)) { + // remove the namespaced definded by current node + for ($i = 0; $i < $pushes; ++$i) { + array_shift($this->nsStack); + } + } + + if ($selfClosing) { + $this->endTag($name); + } + + // Return the element mask, which the tokenizer can then use to set + // various processing rules. + return Elements::element($name); + } + + public function endTag($name) + { + $lname = $this->normalizeTagName($name); + + // Special case within 12.2.6.4.7: An end tag whose tag name is "br" should be treated as an opening tag + if ('br' === $name) { + $this->parseError('Closing tag encountered for void element br.'); + + $this->startTag('br'); + } + // Ignore closing tags for other unary elements. + elseif (Elements::isA($name, Elements::VOID_TAG)) { + return; + } + + if ($this->insertMode <= static::IM_BEFORE_HTML) { + // 8.2.5.4.2 + if (in_array($name, array( + 'html', + 'br', + 'head', + 'title', + ))) { + $this->startTag('html'); + $this->endTag($name); + $this->insertMode = static::IM_BEFORE_HEAD; + + return; + } + + // Ignore the tag. + $this->parseError('Illegal closing tag at global scope.'); + + return; + } + + // Special case handling for SVG. + if ($this->insertMode === static::IM_IN_SVG) { + $lname = Elements::normalizeSvgElement($lname); + } + + $cid = spl_object_hash($this->current); + + // XXX: HTML has no parent. What do we do, though, + // if this element appears in the wrong place? + if ('html' === $lname) { + return; + } + + // remove the namespaced definded by current node + if (isset($this->pushes[$cid])) { + for ($i = 0; $i < $this->pushes[$cid][0]; ++$i) { + array_shift($this->nsStack); + } + unset($this->pushes[$cid]); + } + + if (!$this->autoclose($lname)) { + $this->parseError('Could not find closing tag for ' . $lname); + } + + switch ($lname) { + case 'head': + $this->insertMode = static::IM_AFTER_HEAD; + break; + case 'body': + $this->insertMode = static::IM_AFTER_BODY; + break; + case 'svg': + case 'mathml': + $this->insertMode = static::IM_IN_BODY; + break; + } + } + + public function comment($cdata) + { + // TODO: Need to handle case where comment appears outside of the HTML tag. + $node = $this->doc->createComment($cdata); + $this->current->appendChild($node); + } + + public function text($data) + { + // XXX: Hmmm.... should we really be this strict? + if ($this->insertMode < static::IM_IN_HEAD) { + // Per '8.2.5.4.3 The "before head" insertion mode' the characters + // " \t\n\r\f" should be ignored but no mention of a parse error. This is + // practical as most documents contain these characters. Other text is not + // expected here so recording a parse error is necessary. + $dataTmp = trim($data, " \t\n\r\f"); + if (!empty($dataTmp)) { + // fprintf(STDOUT, "Unexpected insert mode: %d", $this->insertMode); + $this->parseError('Unexpected text. Ignoring: ' . $dataTmp); + } + + return; + } + // fprintf(STDOUT, "Appending text %s.", $data); + $node = $this->doc->createTextNode($data); + $this->current->appendChild($node); + } + + public function eof() + { + // If the $current isn't the $root, do we need to do anything? + } + + public function parseError($msg, $line = 0, $col = 0) + { + $this->errors[] = sprintf('Line %d, Col %d: %s', $line, $col, $msg); + } + + public function getErrors() + { + return $this->errors; + } + + public function cdata($data) + { + $node = $this->doc->createCDATASection($data); + $this->current->appendChild($node); + } + + public function processingInstruction($name, $data = null) + { + // XXX: Ignore initial XML declaration, per the spec. + if ($this->insertMode === static::IM_INITIAL && 'xml' === strtolower($name)) { + return; + } + + // Important: The processor may modify the current DOM tree however it sees fit. + if ($this->processor instanceof InstructionProcessor) { + $res = $this->processor->process($this->current, $name, $data); + if (!empty($res)) { + $this->current = $res; + } + + return; + } + + // Otherwise, this is just a dumb PI element. + $node = $this->doc->createProcessingInstruction($name, $data); + + $this->current->appendChild($node); + } + + // ========================================================================== + // UTILITIES + // ========================================================================== + + /** + * Apply normalization rules to a tag name. + * See sections 2.9 and 8.1.2. + * + * @param string $tagName + * + * @return string The normalized tag name. + */ + protected function normalizeTagName($tagName) + { + /* + * Section 2.9 suggests that we should not do this. if (strpos($name, ':') !== false) { // We know from the grammar that there must be at least one other // char besides :, since : is not a legal tag start. $parts = explode(':', $name); return array_pop($parts); } + */ + return $tagName; + } + + protected function quirksTreeResolver($name) + { + throw new \Exception('Not implemented.'); + } + + /** + * Automatically climb the tree and close the closest node with the matching $tag. + * + * @param string $tagName + * + * @return bool + */ + protected function autoclose($tagName) + { + $working = $this->current; + do { + if (XML_ELEMENT_NODE !== $working->nodeType) { + return false; + } + if ($working->tagName === $tagName) { + $this->current = $working->parentNode; + + return true; + } + } while ($working = $working->parentNode); + + return false; + } + + /** + * Checks if the given tagname is an ancestor of the present candidate. + * + * If $this->current or anything above $this->current matches the given tag + * name, this returns true. + * + * @param string $tagName + * + * @return bool + */ + protected function isAncestor($tagName) + { + $candidate = $this->current; + while (XML_ELEMENT_NODE === $candidate->nodeType) { + if ($candidate->tagName === $tagName) { + return true; + } + $candidate = $candidate->parentNode; + } + + return false; + } + + /** + * Returns true if the immediate parent element is of the given tagname. + * + * @param string $tagName + * + * @return bool + */ + protected function isParent($tagName) + { + return $this->current->tagName === $tagName; + } +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/EventHandler.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/EventHandler.php new file mode 100644 index 000000000..9893a718b --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/EventHandler.php @@ -0,0 +1,114 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +/** + * Standard events for HTML5. + * + * This is roughly analogous to a SAX2 or expat-style interface. + * However, it is tuned specifically for HTML5, according to section 8 + * of the HTML5 specification. + * + * An event handler receives parser events. For a concrete + * implementation, see DOMTreeBuilder. + * + * Quirks support in the parser is limited to close-in syntax (malformed + * tags or attributes). Higher order syntax and semantic issues with a + * document (e.g. mismatched tags, illegal nesting, etc.) are the + * responsibility of the event handler implementation. + * + * See HTML5 spec section 8.2.4 + */ +interface EventHandler +{ + const DOCTYPE_NONE = 0; + + const DOCTYPE_PUBLIC = 1; + + const DOCTYPE_SYSTEM = 2; + + /** + * A doctype declaration. + * + * @param string $name The name of the root element. + * @param int $idType One of DOCTYPE_NONE, DOCTYPE_PUBLIC, or DOCTYPE_SYSTEM + * @param string $id The identifier. For DOCTYPE_PUBLIC, this is the public ID. If DOCTYPE_SYSTEM, + * then this is a system ID. + * @param bool $quirks Indicates whether the builder should enter quirks mode. + */ + public function doctype($name, $idType = 0, $id = null, $quirks = false); + + /** + * A start tag. + * + * IMPORTANT: The parser watches the return value of this event. If this returns + * an integer, the parser will switch TEXTMODE patters according to the int. + * + * This is how the Tree Builder can tell the Tokenizer when a certain tag should + * cause the parser to go into RAW text mode. + * + * The HTML5 standard requires that the builder is the one that initiates this + * step, and this is the only way short of a circular reference that we can + * do that. + * + * Example: if a startTag even for a `script` name is fired, and the startTag() + * implementation returns Tokenizer::TEXTMODE_RAW, then the tokenizer will + * switch into RAW text mode and consume data until it reaches a closing + * `script` tag. + * + * The textmode is automatically reset to Tokenizer::TEXTMODE_NORMAL when the + * closing tag is encounter. **This behavior may change.** + * + * @param string $name The tag name. + * @param array $attributes An array with all of the tag's attributes. + * @param bool $selfClosing An indicator of whether or not this tag is self-closing (<foo/>). + * + * @return int one of the Tokenizer::TEXTMODE_* constants + */ + public function startTag($name, $attributes = array(), $selfClosing = false); + + /** + * An end-tag. + */ + public function endTag($name); + + /** + * A comment section (unparsed character data). + */ + public function comment($cdata); + + /** + * A unit of parsed character data. + * + * Entities in this text are *already decoded*. + */ + public function text($cdata); + + /** + * Indicates that the document has been entirely processed. + */ + public function eof(); + + /** + * Emitted when the parser encounters an error condition. + */ + public function parseError($msg, $line, $col); + + /** + * A CDATA section. + * + * @param string $data + * The unparsed character data + */ + public function cdata($data); + + /** + * This is a holdover from the XML spec. + * + * While user agents don't get PIs, server-side does. + * + * @param string $name The name of the processor (e.g. 'php'). + * @param string $data The unparsed data. + */ + public function processingInstruction($name, $data = null); +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/FileInputStream.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/FileInputStream.php new file mode 100644 index 000000000..b081ed96b --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/FileInputStream.php @@ -0,0 +1,33 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +/** + * The FileInputStream loads a file to be parsed. + * + * So right now we read files into strings and then process the + * string. We chose to do this largely for the sake of expediency of + * development, and also because we could optimize toward processing + * arbitrarily large chunks of the input. But in the future, we'd + * really like to rewrite this class to efficiently handle lower level + * stream reads (and thus efficiently handle large documents). + * + * @deprecated since 2.4, to remove in 3.0. Use a string in the scanner instead. + */ +class FileInputStream extends StringInputStream implements InputStream +{ + /** + * Load a file input stream. + * + * @param string $data The file or url path to load. + * @param string $encoding The encoding to use for the data. + * @param string $debug A fprintf format to use to echo the data on stdout. + */ + public function __construct($data, $encoding = 'UTF-8', $debug = '') + { + // Get the contents of the file. + $content = file_get_contents($data); + + parent::__construct($content, $encoding, $debug); + } +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/InputStream.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/InputStream.php new file mode 100644 index 000000000..ff4ef2266 --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/InputStream.php @@ -0,0 +1,87 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +/** + * Interface for stream readers. + * + * The parser only reads from streams. Various input sources can write + * an adapater to this InputStream. + * + * Currently provided InputStream implementations include + * FileInputStream and StringInputStream. + * + * @deprecated since 2.4, to remove in 3.0. Use a string in the scanner instead. + */ +interface InputStream extends \Iterator +{ + /** + * Returns the current line that is being consumed. + * + * TODO: Move this to the scanner. + */ + public function currentLine(); + + /** + * Returns the current column of the current line that the tokenizer is at. + * + * Newlines are column 0. The first char after a newline is column 1. + * + * @TODO Move this to the scanner. + * + * @return int The column number. + */ + public function columnOffset(); + + /** + * Get all characters until EOF. + * + * This consumes characters until the EOF. + */ + public function remainingChars(); + + /** + * Read to a particular match (or until $max bytes are consumed). + * + * This operates on byte sequences, not characters. + * + * Matches as far as possible until we reach a certain set of bytes + * and returns the matched substring. + * + * @see strcspn + * + * @param string $bytes Bytes to match. + * @param int $max Maximum number of bytes to scan. + * + * @return mixed Index or false if no match is found. You should use strong + * equality when checking the result, since index could be 0. + */ + public function charsUntil($bytes, $max = null); + + /** + * Returns the string so long as $bytes matches. + * + * Matches as far as possible with a certain set of bytes + * and returns the matched substring. + * + * @see strspn + * + * @param string $bytes A mask of bytes to match. If ANY byte in this mask matches the + * current char, the pointer advances and the char is part of the + * substring. + * @param int $max The max number of chars to read. + */ + public function charsWhile($bytes, $max = null); + + /** + * Unconsume one character. + * + * @param int $howMany The number of characters to move the pointer back. + */ + public function unconsume($howMany = 1); + + /** + * Retrieve the next character without advancing the pointer. + */ + public function peek(); +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/ParseError.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/ParseError.php new file mode 100644 index 000000000..640e516c8 --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/ParseError.php @@ -0,0 +1,10 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +/** + * Emit when the parser has an error. + */ +class ParseError extends \Exception +{ +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/README.md b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/README.md new file mode 100644 index 000000000..9f929570c --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/README.md @@ -0,0 +1,53 @@ +# The Parser Model + +The parser model here follows the model in section +[8.2.1](http://www.w3.org/TR/2012/CR-html5-20121217/syntax.html#parsing) +of the HTML5 specification, though we do not assume a networking layer. + + [ InputStream ] // Generic support for reading input. + || + [ Scanner ] // Breaks down the stream into characters. + || + [ Tokenizer ] // Groups characters into syntactic + || + [ Tree Builder ] // Organizes units into a tree of objects + || + [ DOM Document ] // The final state of the parsed document. + + +## InputStream + +This is an interface with at least two concrete implementations: + +- StringInputStream: Reads an HTML5 string. +- FileInputStream: Reads an HTML5 file. + +## Scanner + +This is a mechanical piece of the parser. + +## Tokenizer + +This follows section 8.4 of the HTML5 spec. It is (roughly) a recursive +descent parser. (Though there are plenty of optimizations that are less +than purely functional. + +## EventHandler and DOMTree + +EventHandler is the interface for tree builders. Since not all +implementations will necessarily build trees, we've chosen a more +generic name. + +The event handler emits tokens during tokenization. + +The DOMTree is an event handler that builds a DOM tree. The output of +the DOMTree builder is a DOMDocument. + +## DOMDocument + +PHP has a DOMDocument class built-in (technically, it's part of libxml.) +We use that, thus rendering the output of this process compatible with +SimpleXML, QueryPath, and many other XML/HTML processing tools. + +For cases where the HTML5 is a fragment of a HTML5 document a +DOMDocumentFragment is returned instead. This is another built-in class. diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/Scanner.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/Scanner.php new file mode 100644 index 000000000..1b52983e7 --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/Scanner.php @@ -0,0 +1,416 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +use Masterminds\HTML5\Exception; + +/** + * The scanner scans over a given data input to react appropriately to characters. + */ +class Scanner +{ + const CHARS_HEX = 'abcdefABCDEF01234567890'; + const CHARS_ALNUM = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890'; + const CHARS_ALPHA = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'; + + /** + * The string data we're parsing. + */ + private $data; + + /** + * The current integer byte position we are in $data. + */ + private $char; + + /** + * Length of $data; when $char === $data, we are at the end-of-file. + */ + private $EOF; + + /** + * Parse errors. + */ + public $errors = array(); + + /** + * Create a new Scanner. + * + * @param string $data Data to parse. + * @param string $encoding The encoding to use for the data. + * + * @throws Exception If the given data cannot be encoded to UTF-8. + */ + public function __construct($data, $encoding = 'UTF-8') + { + if ($data instanceof InputStream) { + @trigger_error('InputStream objects are deprecated since version 2.4 and will be removed in 3.0. Use strings instead.', E_USER_DEPRECATED); + $data = (string) $data; + } + + $data = UTF8Utils::convertToUTF8($data, $encoding); + + // There is good reason to question whether it makes sense to + // do this here, since most of these checks are done during + // parsing, and since this check doesn't actually *do* anything. + $this->errors = UTF8Utils::checkForIllegalCodepoints($data); + + $data = $this->replaceLinefeeds($data); + + $this->data = $data; + $this->char = 0; + $this->EOF = strlen($data); + } + + /** + * Check if upcomming chars match the given sequence. + * + * This will read the stream for the $sequence. If it's + * found, this will return true. If not, return false. + * Since this unconsumes any chars it reads, the caller + * will still need to read the next sequence, even if + * this returns true. + * + * Example: $this->scanner->sequenceMatches('</script>') will + * see if the input stream is at the start of a + * '</script>' string. + * + * @param string $sequence + * @param bool $caseSensitive + * + * @return bool + */ + public function sequenceMatches($sequence, $caseSensitive = true) + { + $portion = substr($this->data, $this->char, strlen($sequence)); + + return $caseSensitive ? $portion === $sequence : 0 === strcasecmp($portion, $sequence); + } + + /** + * Get the current position. + * + * @return int The current intiger byte position. + */ + public function position() + { + return $this->char; + } + + /** + * Take a peek at the next character in the data. + * + * @return string The next character. + */ + public function peek() + { + if (($this->char + 1) <= $this->EOF) { + return $this->data[$this->char + 1]; + } + + return false; + } + + /** + * Get the next character. + * Note: This advances the pointer. + * + * @return string The next character. + */ + public function next() + { + ++$this->char; + + if ($this->char < $this->EOF) { + return $this->data[$this->char]; + } + + return false; + } + + /** + * Get the current character. + * Note, this does not advance the pointer. + * + * @return string The current character. + */ + public function current() + { + if ($this->char < $this->EOF) { + return $this->data[$this->char]; + } + + return false; + } + + /** + * Silently consume N chars. + * + * @param int $count + */ + public function consume($count = 1) + { + $this->char += $count; + } + + /** + * Unconsume some of the data. + * This moves the data pointer backwards. + * + * @param int $howMany The number of characters to move the pointer back. + */ + public function unconsume($howMany = 1) + { + if (($this->char - $howMany) >= 0) { + $this->char -= $howMany; + } + } + + /** + * Get the next group of that contains hex characters. + * Note, along with getting the characters the pointer in the data will be + * moved as well. + * + * @return string The next group that is hex characters. + */ + public function getHex() + { + return $this->doCharsWhile(static::CHARS_HEX); + } + + /** + * Get the next group of characters that are ASCII Alpha characters. + * Note, along with getting the characters the pointer in the data will be + * moved as well. + * + * @return string The next group of ASCII alpha characters. + */ + public function getAsciiAlpha() + { + return $this->doCharsWhile(static::CHARS_ALPHA); + } + + /** + * Get the next group of characters that are ASCII Alpha characters and numbers. + * Note, along with getting the characters the pointer in the data will be + * moved as well. + * + * @return string The next group of ASCII alpha characters and numbers. + */ + public function getAsciiAlphaNum() + { + return $this->doCharsWhile(static::CHARS_ALNUM); + } + + /** + * Get the next group of numbers. + * Note, along with getting the characters the pointer in the data will be + * moved as well. + * + * @return string The next group of numbers. + */ + public function getNumeric() + { + return $this->doCharsWhile('0123456789'); + } + + /** + * Consume whitespace. + * Whitespace in HTML5 is: formfeed, tab, newline, space. + * + * @return int The length of the matched whitespaces. + */ + public function whitespace() + { + if ($this->char >= $this->EOF) { + return false; + } + + $len = strspn($this->data, "\n\t\f ", $this->char); + + $this->char += $len; + + return $len; + } + + /** + * Returns the current line that is being consumed. + * + * @return int The current line number. + */ + public function currentLine() + { + if (empty($this->EOF) || 0 === $this->char) { + return 1; + } + + // Add one to $this->char because we want the number for the next + // byte to be processed. + return substr_count($this->data, "\n", 0, min($this->char, $this->EOF)) + 1; + } + + /** + * Read chars until something in the mask is encountered. + * + * @param string $mask + * + * @return mixed + */ + public function charsUntil($mask) + { + return $this->doCharsUntil($mask); + } + + /** + * Read chars as long as the mask matches. + * + * @param string $mask + * + * @return int + */ + public function charsWhile($mask) + { + return $this->doCharsWhile($mask); + } + + /** + * Returns the current column of the current line that the tokenizer is at. + * + * Newlines are column 0. The first char after a newline is column 1. + * + * @return int The column number. + */ + public function columnOffset() + { + // Short circuit for the first char. + if (0 === $this->char) { + return 0; + } + + // strrpos is weird, and the offset needs to be negative for what we + // want (i.e., the last \n before $this->char). This needs to not have + // one (to make it point to the next character, the one we want the + // position of) added to it because strrpos's behaviour includes the + // final offset byte. + $backwardFrom = $this->char - 1 - strlen($this->data); + $lastLine = strrpos($this->data, "\n", $backwardFrom); + + // However, for here we want the length up until the next byte to be + // processed, so add one to the current byte ($this->char). + if (false !== $lastLine) { + $findLengthOf = substr($this->data, $lastLine + 1, $this->char - 1 - $lastLine); + } else { + // After a newline. + $findLengthOf = substr($this->data, 0, $this->char); + } + + return UTF8Utils::countChars($findLengthOf); + } + + /** + * Get all characters until EOF. + * + * This consumes characters until the EOF. + * + * @return int The number of characters remaining. + */ + public function remainingChars() + { + if ($this->char < $this->EOF) { + $data = substr($this->data, $this->char); + $this->char = $this->EOF; + + return $data; + } + + return ''; // false; + } + + /** + * Replace linefeed characters according to the spec. + * + * @param $data + * + * @return string + */ + private function replaceLinefeeds($data) + { + /* + * U+000D CARRIAGE RETURN (CR) characters and U+000A LINE FEED (LF) characters are treated specially. + * Any CR characters that are followed by LF characters must be removed, and any CR characters not + * followed by LF characters must be converted to LF characters. Thus, newlines in HTML DOMs are + * represented by LF characters, and there are never any CR characters in the input to the tokenization + * stage. + */ + $crlfTable = array( + "\0" => "\xEF\xBF\xBD", + "\r\n" => "\n", + "\r" => "\n", + ); + + return strtr($data, $crlfTable); + } + + /** + * Read to a particular match (or until $max bytes are consumed). + * + * This operates on byte sequences, not characters. + * + * Matches as far as possible until we reach a certain set of bytes + * and returns the matched substring. + * + * @param string $bytes Bytes to match. + * @param int $max Maximum number of bytes to scan. + * + * @return mixed Index or false if no match is found. You should use strong + * equality when checking the result, since index could be 0. + */ + private function doCharsUntil($bytes, $max = null) + { + if ($this->char >= $this->EOF) { + return false; + } + + if (0 === $max || $max) { + $len = strcspn($this->data, $bytes, $this->char, $max); + } else { + $len = strcspn($this->data, $bytes, $this->char); + } + + $string = (string) substr($this->data, $this->char, $len); + $this->char += $len; + + return $string; + } + + /** + * Returns the string so long as $bytes matches. + * + * Matches as far as possible with a certain set of bytes + * and returns the matched substring. + * + * @param string $bytes A mask of bytes to match. If ANY byte in this mask matches the + * current char, the pointer advances and the char is part of the + * substring. + * @param int $max The max number of chars to read. + * + * @return string + */ + private function doCharsWhile($bytes, $max = null) + { + if ($this->char >= $this->EOF) { + return false; + } + + if (0 === $max || $max) { + $len = strspn($this->data, $bytes, $this->char, $max); + } else { + $len = strspn($this->data, $bytes, $this->char); + } + + $string = (string) substr($this->data, $this->char, $len); + $this->char += $len; + + return $string; + } +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/StringInputStream.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/StringInputStream.php new file mode 100644 index 000000000..0c213feb6 --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/StringInputStream.php @@ -0,0 +1,331 @@ +<?php +/** + * Loads a string to be parsed. + */ + +namespace Masterminds\HTML5\Parser; + +/* + * +* Based on code from html5lib: + +Copyright 2009 Geoffrey Sneddon <http://gsnedders.com/> + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS +OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +*/ + +// Some conventions: +// - /* */ indicates verbatim text from the HTML 5 specification +// MPB: Not sure which version of the spec. Moving from HTML5lib to +// HTML5-PHP, I have been using this version: +// http://www.w3.org/TR/2012/CR-html5-20121217/Overview.html#contents +// +// - // indicates regular comments + +/** + * @deprecated since 2.4, to remove in 3.0. Use a string in the scanner instead. + */ +class StringInputStream implements InputStream +{ + /** + * The string data we're parsing. + */ + private $data; + + /** + * The current integer byte position we are in $data. + */ + private $char; + + /** + * Length of $data; when $char === $data, we are at the end-of-file. + */ + private $EOF; + + /** + * Parse errors. + */ + public $errors = array(); + + /** + * Create a new InputStream wrapper. + * + * @param string $data Data to parse. + * @param string $encoding The encoding to use for the data. + * @param string $debug A fprintf format to use to echo the data on stdout. + */ + public function __construct($data, $encoding = 'UTF-8', $debug = '') + { + $data = UTF8Utils::convertToUTF8($data, $encoding); + if ($debug) { + fprintf(STDOUT, $debug, $data, strlen($data)); + } + + // There is good reason to question whether it makes sense to + // do this here, since most of these checks are done during + // parsing, and since this check doesn't actually *do* anything. + $this->errors = UTF8Utils::checkForIllegalCodepoints($data); + + $data = $this->replaceLinefeeds($data); + + $this->data = $data; + $this->char = 0; + $this->EOF = strlen($data); + } + + public function __toString() + { + return $this->data; + } + + /** + * Replace linefeed characters according to the spec. + */ + protected function replaceLinefeeds($data) + { + /* + * U+000D CARRIAGE RETURN (CR) characters and U+000A LINE FEED (LF) characters are treated specially. + * Any CR characters that are followed by LF characters must be removed, and any CR characters not + * followed by LF characters must be converted to LF characters. Thus, newlines in HTML DOMs are + * represented by LF characters, and there are never any CR characters in the input to the tokenization + * stage. + */ + $crlfTable = array( + "\0" => "\xEF\xBF\xBD", + "\r\n" => "\n", + "\r" => "\n", + ); + + return strtr($data, $crlfTable); + } + + /** + * Returns the current line that the tokenizer is at. + */ + public function currentLine() + { + if (empty($this->EOF) || 0 === $this->char) { + return 1; + } + // Add one to $this->char because we want the number for the next + // byte to be processed. + return substr_count($this->data, "\n", 0, min($this->char, $this->EOF)) + 1; + } + + /** + * @deprecated + */ + public function getCurrentLine() + { + return $this->currentLine(); + } + + /** + * Returns the current column of the current line that the tokenizer is at. + * Newlines are column 0. The first char after a newline is column 1. + * + * @return int The column number. + */ + public function columnOffset() + { + // Short circuit for the first char. + if (0 === $this->char) { + return 0; + } + // strrpos is weird, and the offset needs to be negative for what we + // want (i.e., the last \n before $this->char). This needs to not have + // one (to make it point to the next character, the one we want the + // position of) added to it because strrpos's behaviour includes the + // final offset byte. + $backwardFrom = $this->char - 1 - strlen($this->data); + $lastLine = strrpos($this->data, "\n", $backwardFrom); + + // However, for here we want the length up until the next byte to be + // processed, so add one to the current byte ($this->char). + if (false !== $lastLine) { + $findLengthOf = substr($this->data, $lastLine + 1, $this->char - 1 - $lastLine); + } else { + // After a newline. + $findLengthOf = substr($this->data, 0, $this->char); + } + + return UTF8Utils::countChars($findLengthOf); + } + + /** + * @deprecated + */ + public function getColumnOffset() + { + return $this->columnOffset(); + } + + /** + * Get the current character. + * + * @return string The current character. + */ + public function current() + { + return $this->data[$this->char]; + } + + /** + * Advance the pointer. + * This is part of the Iterator interface. + */ + public function next() + { + ++$this->char; + } + + /** + * Rewind to the start of the string. + */ + public function rewind() + { + $this->char = 0; + } + + /** + * Is the current pointer location valid. + * + * @return bool Whether the current pointer location is valid. + */ + public function valid() + { + return $this->char < $this->EOF; + } + + /** + * Get all characters until EOF. + * + * This reads to the end of the file, and sets the read marker at the + * end of the file. + * + * Note this performs bounds checking. + * + * @return string Returns the remaining text. If called when the InputStream is + * already exhausted, it returns an empty string. + */ + public function remainingChars() + { + if ($this->char < $this->EOF) { + $data = substr($this->data, $this->char); + $this->char = $this->EOF; + + return $data; + } + + return ''; // false; + } + + /** + * Read to a particular match (or until $max bytes are consumed). + * + * This operates on byte sequences, not characters. + * + * Matches as far as possible until we reach a certain set of bytes + * and returns the matched substring. + * + * @param string $bytes Bytes to match. + * @param int $max Maximum number of bytes to scan. + * + * @return mixed Index or false if no match is found. You should use strong + * equality when checking the result, since index could be 0. + */ + public function charsUntil($bytes, $max = null) + { + if ($this->char >= $this->EOF) { + return false; + } + + if (0 === $max || $max) { + $len = strcspn($this->data, $bytes, $this->char, $max); + } else { + $len = strcspn($this->data, $bytes, $this->char); + } + + $string = (string) substr($this->data, $this->char, $len); + $this->char += $len; + + return $string; + } + + /** + * Returns the string so long as $bytes matches. + * + * Matches as far as possible with a certain set of bytes + * and returns the matched substring. + * + * @param string $bytes A mask of bytes to match. If ANY byte in this mask matches the + * current char, the pointer advances and the char is part of the + * substring. + * @param int $max The max number of chars to read. + * + * @return string + */ + public function charsWhile($bytes, $max = null) + { + if ($this->char >= $this->EOF) { + return false; + } + + if (0 === $max || $max) { + $len = strspn($this->data, $bytes, $this->char, $max); + } else { + $len = strspn($this->data, $bytes, $this->char); + } + $string = (string) substr($this->data, $this->char, $len); + $this->char += $len; + + return $string; + } + + /** + * Unconsume characters. + * + * @param int $howMany The number of characters to unconsume. + */ + public function unconsume($howMany = 1) + { + if (($this->char - $howMany) >= 0) { + $this->char -= $howMany; + } + } + + /** + * Look ahead without moving cursor. + */ + public function peek() + { + if (($this->char + 1) <= $this->EOF) { + return $this->data[$this->char + 1]; + } + + return false; + } + + public function key() + { + return $this->char; + } +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/Tokenizer.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/Tokenizer.php new file mode 100644 index 000000000..300a44626 --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/Tokenizer.php @@ -0,0 +1,1191 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +use Masterminds\HTML5\Elements; + +/** + * The HTML5 tokenizer. + * + * The tokenizer's role is reading data from the scanner and gathering it into + * semantic units. From the tokenizer, data is emitted to an event handler, + * which may (for example) create a DOM tree. + * + * The HTML5 specification has a detailed explanation of tokenizing HTML5. We + * follow that specification to the maximum extent that we can. If you find + * a discrepancy that is not documented, please file a bug and/or submit a + * patch. + * + * This tokenizer is implemented as a recursive descent parser. + * + * Within the API documentation, you may see references to the specific section + * of the HTML5 spec that the code attempts to reproduce. Example: 8.2.4.1. + * This refers to section 8.2.4.1 of the HTML5 CR specification. + * + * @see http://www.w3.org/TR/2012/CR-html5-20121217/ + */ +class Tokenizer +{ + protected $scanner; + + protected $events; + + protected $tok; + + /** + * Buffer for text. + */ + protected $text = ''; + + // When this goes to false, the parser stops. + protected $carryOn = true; + + protected $textMode = 0; // TEXTMODE_NORMAL; + protected $untilTag = null; + + const CONFORMANT_XML = 'xml'; + const CONFORMANT_HTML = 'html'; + protected $mode = self::CONFORMANT_HTML; + + /** + * Create a new tokenizer. + * + * Typically, parsing a document involves creating a new tokenizer, giving + * it a scanner (input) and an event handler (output), and then calling + * the Tokenizer::parse() method.` + * + * @param Scanner $scanner A scanner initialized with an input stream. + * @param EventHandler $eventHandler An event handler, initialized and ready to receive events. + * @param string $mode + */ + public function __construct($scanner, $eventHandler, $mode = self::CONFORMANT_HTML) + { + $this->scanner = $scanner; + $this->events = $eventHandler; + $this->mode = $mode; + } + + /** + * Begin parsing. + * + * This will begin scanning the document, tokenizing as it goes. + * Tokens are emitted into the event handler. + * + * Tokenizing will continue until the document is completely + * read. Errors are emitted into the event handler, but + * the parser will attempt to continue parsing until the + * entire input stream is read. + */ + public function parse() + { + do { + $this->consumeData(); + // FIXME: Add infinite loop protection. + } while ($this->carryOn); + } + + /** + * Set the text mode for the character data reader. + * + * HTML5 defines three different modes for reading text: + * - Normal: Read until a tag is encountered. + * - RCDATA: Read until a tag is encountered, but skip a few otherwise- + * special characters. + * - Raw: Read until a special closing tag is encountered (viz. pre, script) + * + * This allows those modes to be set. + * + * Normally, setting is done by the event handler via a special return code on + * startTag(), but it can also be set manually using this function. + * + * @param int $textmode One of Elements::TEXT_*. + * @param string $untilTag The tag that should stop RAW or RCDATA mode. Normal mode does not + * use this indicator. + */ + public function setTextMode($textmode, $untilTag = null) + { + $this->textMode = $textmode & (Elements::TEXT_RAW | Elements::TEXT_RCDATA); + $this->untilTag = $untilTag; + } + + /** + * Consume a character and make a move. + * HTML5 8.2.4.1. + */ + protected function consumeData() + { + $tok = $this->scanner->current(); + + if ('&' === $tok) { + // Character reference + $ref = $this->decodeCharacterReference(); + $this->buffer($ref); + + $tok = $this->scanner->current(); + } + + // Parse tag + if ('<' === $tok) { + // Any buffered text data can go out now. + $this->flushBuffer(); + + $tok = $this->scanner->next(); + + if ('!' === $tok) { + $this->markupDeclaration(); + } elseif ('/' === $tok) { + $this->endTag(); + } elseif ('?' === $tok) { + $this->processingInstruction(); + } elseif (ctype_alpha($tok)) { + $this->tagName(); + } else { + $this->parseError('Illegal tag opening'); + // TODO is this necessary ? + $this->characterData(); + } + + $tok = $this->scanner->current(); + } + + if (false === $tok) { + // Handle end of document + $this->eof(); + } else { + // Parse character + switch ($this->textMode) { + case Elements::TEXT_RAW: + $this->rawText($tok); + break; + + case Elements::TEXT_RCDATA: + $this->rcdata($tok); + break; + + default: + if ('<' === $tok || '&' === $tok) { + break; + } + + // NULL character + if ("\00" === $tok) { + $this->parseError('Received null character.'); + + $this->text .= $tok; + $this->scanner->consume(); + + break; + } + + $this->text .= $this->scanner->charsUntil("<&\0"); + } + } + + return $this->carryOn; + } + + /** + * Parse anything that looks like character data. + * + * Different rules apply based on the current text mode. + * + * @see Elements::TEXT_RAW Elements::TEXT_RCDATA. + */ + protected function characterData() + { + $tok = $this->scanner->current(); + if (false === $tok) { + return false; + } + switch ($this->textMode) { + case Elements::TEXT_RAW: + return $this->rawText($tok); + case Elements::TEXT_RCDATA: + return $this->rcdata($tok); + default: + if ('<' === $tok || '&' === $tok) { + return false; + } + + return $this->text($tok); + } + } + + /** + * This buffers the current token as character data. + * + * @param string $tok The current token. + * + * @return bool + */ + protected function text($tok) + { + // This should never happen... + if (false === $tok) { + return false; + } + + // NULL character + if ("\00" === $tok) { + $this->parseError('Received null character.'); + } + + $this->buffer($tok); + $this->scanner->consume(); + + return true; + } + + /** + * Read text in RAW mode. + * + * @param string $tok The current token. + * + * @return bool + */ + protected function rawText($tok) + { + if (is_null($this->untilTag)) { + return $this->text($tok); + } + + $sequence = '</' . $this->untilTag . '>'; + $txt = $this->readUntilSequence($sequence); + $this->events->text($txt); + $this->setTextMode(0); + + return $this->endTag(); + } + + /** + * Read text in RCDATA mode. + * + * @param string $tok The current token. + * + * @return bool + */ + protected function rcdata($tok) + { + if (is_null($this->untilTag)) { + return $this->text($tok); + } + + $sequence = '</' . $this->untilTag; + $txt = ''; + + $caseSensitive = !Elements::isHtml5Element($this->untilTag); + while (false !== $tok && !('<' == $tok && ($this->scanner->sequenceMatches($sequence, $caseSensitive)))) { + if ('&' == $tok) { + $txt .= $this->decodeCharacterReference(); + $tok = $this->scanner->current(); + } else { + $txt .= $tok; + $tok = $this->scanner->next(); + } + } + $len = strlen($sequence); + $this->scanner->consume($len); + $len += $this->scanner->whitespace(); + if ('>' !== $this->scanner->current()) { + $this->parseError('Unclosed RCDATA end tag'); + } + + $this->scanner->unconsume($len); + $this->events->text($txt); + $this->setTextMode(0); + + return $this->endTag(); + } + + /** + * If the document is read, emit an EOF event. + */ + protected function eof() + { + // fprintf(STDOUT, "EOF"); + $this->flushBuffer(); + $this->events->eof(); + $this->carryOn = false; + } + + /** + * Look for markup. + */ + protected function markupDeclaration() + { + $tok = $this->scanner->next(); + + // Comment: + if ('-' == $tok && '-' == $this->scanner->peek()) { + $this->scanner->consume(2); + + return $this->comment(); + } elseif ('D' == $tok || 'd' == $tok) { // Doctype + return $this->doctype(); + } elseif ('[' == $tok) { // CDATA section + return $this->cdataSection(); + } + + // FINISH + $this->parseError('Expected <!--, <![CDATA[, or <!DOCTYPE. Got <!%s', $tok); + $this->bogusComment('<!'); + + return true; + } + + /** + * Consume an end tag. See section 8.2.4.9. + */ + protected function endTag() + { + if ('/' != $this->scanner->current()) { + return false; + } + $tok = $this->scanner->next(); + + // a-zA-Z -> tagname + // > -> parse error + // EOF -> parse error + // -> parse error + if (!ctype_alpha($tok)) { + $this->parseError("Expected tag name, got '%s'", $tok); + if ("\0" == $tok || false === $tok) { + return false; + } + + return $this->bogusComment('</'); + } + + $name = $this->scanner->charsUntil("\n\f \t>"); + $name = self::CONFORMANT_XML === $this->mode ? $name : strtolower($name); + // Trash whitespace. + $this->scanner->whitespace(); + + $tok = $this->scanner->current(); + if ('>' != $tok) { + $this->parseError("Expected >, got '%s'", $tok); + // We just trash stuff until we get to the next tag close. + $this->scanner->charsUntil('>'); + } + + $this->events->endTag($name); + $this->scanner->consume(); + + return true; + } + + /** + * Consume a tag name and body. See section 8.2.4.10. + */ + protected function tagName() + { + // We know this is at least one char. + $name = $this->scanner->charsWhile(':_-0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'); + $name = self::CONFORMANT_XML === $this->mode ? $name : strtolower($name); + $attributes = array(); + $selfClose = false; + + // Handle attribute parse exceptions here so that we can + // react by trying to build a sensible parse tree. + try { + do { + $this->scanner->whitespace(); + $this->attribute($attributes); + } while (!$this->isTagEnd($selfClose)); + } catch (ParseError $e) { + $selfClose = false; + } + + $mode = $this->events->startTag($name, $attributes, $selfClose); + + if (is_int($mode)) { + $this->setTextMode($mode, $name); + } + + $this->scanner->consume(); + + return true; + } + + /** + * Check if the scanner has reached the end of a tag. + */ + protected function isTagEnd(&$selfClose) + { + $tok = $this->scanner->current(); + if ('/' == $tok) { + $this->scanner->consume(); + $this->scanner->whitespace(); + $tok = $this->scanner->current(); + + if ('>' == $tok) { + $selfClose = true; + + return true; + } + if (false === $tok) { + $this->parseError('Unexpected EOF inside of tag.'); + + return true; + } + // Basically, we skip the / token and go on. + // See 8.2.4.43. + $this->parseError("Unexpected '%s' inside of a tag.", $tok); + + return false; + } + + if ('>' == $tok) { + return true; + } + if (false === $tok) { + $this->parseError('Unexpected EOF inside of tag.'); + + return true; + } + + return false; + } + + /** + * Parse attributes from inside of a tag. + * + * @param string[] $attributes + * + * @return bool + * + * @throws ParseError + */ + protected function attribute(&$attributes) + { + $tok = $this->scanner->current(); + if ('/' == $tok || '>' == $tok || false === $tok) { + return false; + } + + if ('<' == $tok) { + $this->parseError("Unexpected '<' inside of attributes list."); + // Push the < back onto the stack. + $this->scanner->unconsume(); + // Let the caller figure out how to handle this. + throw new ParseError('Start tag inside of attribute.'); + } + + $name = strtolower($this->scanner->charsUntil("/>=\n\f\t ")); + + if (0 == strlen($name)) { + $tok = $this->scanner->current(); + $this->parseError('Expected an attribute name, got %s.', $tok); + // Really, only '=' can be the char here. Everything else gets absorbed + // under one rule or another. + $name = $tok; + $this->scanner->consume(); + } + + $isValidAttribute = true; + // Attribute names can contain most Unicode characters for HTML5. + // But method "DOMElement::setAttribute" is throwing exception + // because of it's own internal restriction so these have to be filtered. + // see issue #23: https://github.com/Masterminds/html5-php/issues/23 + // and http://www.w3.org/TR/2011/WD-html5-20110525/syntax.html#syntax-attribute-name + if (preg_match("/[\x1-\x2C\\/\x3B-\x40\x5B-\x5E\x60\x7B-\x7F]/u", $name)) { + $this->parseError('Unexpected characters in attribute name: %s', $name); + $isValidAttribute = false; + } // There is no limitation for 1st character in HTML5. + // But method "DOMElement::setAttribute" is throwing exception for the + // characters below so they have to be filtered. + // see issue #23: https://github.com/Masterminds/html5-php/issues/23 + // and http://www.w3.org/TR/2011/WD-html5-20110525/syntax.html#syntax-attribute-name + elseif (preg_match('/^[0-9.-]/u', $name)) { + $this->parseError('Unexpected character at the begining of attribute name: %s', $name); + $isValidAttribute = false; + } + // 8.1.2.3 + $this->scanner->whitespace(); + + $val = $this->attributeValue(); + if ($isValidAttribute) { + $attributes[$name] = $val; + } + + return true; + } + + /** + * Consume an attribute value. See section 8.2.4.37 and after. + * + * @return string|null + */ + protected function attributeValue() + { + if ('=' != $this->scanner->current()) { + return null; + } + $this->scanner->consume(); + // 8.1.2.3 + $this->scanner->whitespace(); + + $tok = $this->scanner->current(); + switch ($tok) { + case "\n": + case "\f": + case ' ': + case "\t": + // Whitespace here indicates an empty value. + return null; + case '"': + case "'": + $this->scanner->consume(); + + return $this->quotedAttributeValue($tok); + case '>': + // case '/': // 8.2.4.37 seems to allow foo=/ as a valid attr. + $this->parseError('Expected attribute value, got tag end.'); + + return null; + case '=': + case '`': + $this->parseError('Expecting quotes, got %s.', $tok); + + return $this->unquotedAttributeValue(); + default: + return $this->unquotedAttributeValue(); + } + } + + /** + * Get an attribute value string. + * + * @param string $quote IMPORTANT: This is a series of chars! Any one of which will be considered + * termination of an attribute's value. E.g. "\"'" will stop at either + * ' or ". + * + * @return string The attribute value. + */ + protected function quotedAttributeValue($quote) + { + $stoplist = "\f" . $quote; + $val = ''; + + while (true) { + $tokens = $this->scanner->charsUntil($stoplist . '&'); + if (false !== $tokens) { + $val .= $tokens; + } else { + break; + } + + $tok = $this->scanner->current(); + if ('&' == $tok) { + $val .= $this->decodeCharacterReference(true); + continue; + } + break; + } + $this->scanner->consume(); + + return $val; + } + + protected function unquotedAttributeValue() + { + $val = ''; + $tok = $this->scanner->current(); + while (false !== $tok) { + switch ($tok) { + case "\n": + case "\f": + case ' ': + case "\t": + case '>': + break 2; + + case '&': + $val .= $this->decodeCharacterReference(true); + $tok = $this->scanner->current(); + + break; + + case "'": + case '"': + case '<': + case '=': + case '`': + $this->parseError('Unexpected chars in unquoted attribute value %s', $tok); + $val .= $tok; + $tok = $this->scanner->next(); + break; + + default: + $val .= $this->scanner->charsUntil("\t\n\f >&\"'<=`"); + + $tok = $this->scanner->current(); + } + } + + return $val; + } + + /** + * Consume malformed markup as if it were a comment. + * 8.2.4.44. + * + * The spec requires that the ENTIRE tag-like thing be enclosed inside of + * the comment. So this will generate comments like: + * + * <!--</+foo>--> + * + * @param string $leading Prepend any leading characters. This essentially + * negates the need to backtrack, but it's sort of a hack. + * + * @return bool + */ + protected function bogusComment($leading = '') + { + $comment = $leading; + $tokens = $this->scanner->charsUntil('>'); + if (false !== $tokens) { + $comment .= $tokens; + } + $tok = $this->scanner->current(); + if (false !== $tok) { + $comment .= $tok; + } + + $this->flushBuffer(); + $this->events->comment($comment); + $this->scanner->consume(); + + return true; + } + + /** + * Read a comment. + * Expects the first tok to be inside of the comment. + * + * @return bool + */ + protected function comment() + { + $tok = $this->scanner->current(); + $comment = ''; + + // <!-->. Emit an empty comment because 8.2.4.46 says to. + if ('>' == $tok) { + // Parse error. Emit the comment token. + $this->parseError("Expected comment data, got '>'"); + $this->events->comment(''); + $this->scanner->consume(); + + return true; + } + + // Replace NULL with the replacement char. + if ("\0" == $tok) { + $tok = UTF8Utils::FFFD; + } + while (!$this->isCommentEnd()) { + $comment .= $tok; + $tok = $this->scanner->next(); + } + + $this->events->comment($comment); + $this->scanner->consume(); + + return true; + } + + /** + * Check if the scanner has reached the end of a comment. + * + * @return bool + */ + protected function isCommentEnd() + { + $tok = $this->scanner->current(); + + // EOF + if (false === $tok) { + // Hit the end. + $this->parseError('Unexpected EOF in a comment.'); + + return true; + } + + // If it doesn't start with -, not the end. + if ('-' != $tok) { + return false; + } + + // Advance one, and test for '->' + if ('-' == $this->scanner->next() && '>' == $this->scanner->peek()) { + $this->scanner->consume(); // Consume the last '>' + return true; + } + // Unread '-'; + $this->scanner->unconsume(1); + + return false; + } + + /** + * Parse a DOCTYPE. + * + * Parse a DOCTYPE declaration. This method has strong bearing on whether or + * not Quirksmode is enabled on the event handler. + * + * @todo This method is a little long. Should probably refactor. + * + * @return bool + */ + protected function doctype() + { + // Check that string is DOCTYPE. + if ($this->scanner->sequenceMatches('DOCTYPE', false)) { + $this->scanner->consume(7); + } else { + $chars = $this->scanner->charsWhile('DOCTYPEdoctype'); + $this->parseError('Expected DOCTYPE, got %s', $chars); + + return $this->bogusComment('<!' . $chars); + } + + $this->scanner->whitespace(); + $tok = $this->scanner->current(); + + // EOF: die. + if (false === $tok) { + $this->events->doctype('html5', EventHandler::DOCTYPE_NONE, '', true); + $this->eof(); + + return true; + } + + // NULL char: convert. + if ("\0" === $tok) { + $this->parseError('Unexpected null character in DOCTYPE.'); + } + + $stop = " \n\f>"; + $doctypeName = $this->scanner->charsUntil($stop); + // Lowercase ASCII, replace \0 with FFFD + $doctypeName = strtolower(strtr($doctypeName, "\0", UTF8Utils::FFFD)); + + $tok = $this->scanner->current(); + + // If false, emit a parse error, DOCTYPE, and return. + if (false === $tok) { + $this->parseError('Unexpected EOF in DOCTYPE declaration.'); + $this->events->doctype($doctypeName, EventHandler::DOCTYPE_NONE, null, true); + + return true; + } + + // Short DOCTYPE, like <!DOCTYPE html> + if ('>' == $tok) { + // DOCTYPE without a name. + if (0 == strlen($doctypeName)) { + $this->parseError('Expected a DOCTYPE name. Got nothing.'); + $this->events->doctype($doctypeName, 0, null, true); + $this->scanner->consume(); + + return true; + } + $this->events->doctype($doctypeName); + $this->scanner->consume(); + + return true; + } + $this->scanner->whitespace(); + + $pub = strtoupper($this->scanner->getAsciiAlpha()); + $white = $this->scanner->whitespace(); + + // Get ID, and flag it as pub or system. + if (('PUBLIC' == $pub || 'SYSTEM' == $pub) && $white > 0) { + // Get the sys ID. + $type = 'PUBLIC' == $pub ? EventHandler::DOCTYPE_PUBLIC : EventHandler::DOCTYPE_SYSTEM; + $id = $this->quotedString("\0>"); + if (false === $id) { + $this->events->doctype($doctypeName, $type, $pub, false); + + return true; + } + + // Premature EOF. + if (false === $this->scanner->current()) { + $this->parseError('Unexpected EOF in DOCTYPE'); + $this->events->doctype($doctypeName, $type, $id, true); + + return true; + } + + // Well-formed complete DOCTYPE. + $this->scanner->whitespace(); + if ('>' == $this->scanner->current()) { + $this->events->doctype($doctypeName, $type, $id, false); + $this->scanner->consume(); + + return true; + } + + // If we get here, we have <!DOCTYPE foo PUBLIC "bar" SOME_JUNK + // Throw away the junk, parse error, quirks mode, return true. + $this->scanner->charsUntil('>'); + $this->parseError('Malformed DOCTYPE.'); + $this->events->doctype($doctypeName, $type, $id, true); + $this->scanner->consume(); + + return true; + } + + // Else it's a bogus DOCTYPE. + // Consume to > and trash. + $this->scanner->charsUntil('>'); + + $this->parseError('Expected PUBLIC or SYSTEM. Got %s.', $pub); + $this->events->doctype($doctypeName, 0, null, true); + $this->scanner->consume(); + + return true; + } + + /** + * Utility for reading a quoted string. + * + * @param string $stopchars Characters (in addition to a close-quote) that should stop the string. + * E.g. sometimes '>' is higher precedence than '"' or "'". + * + * @return mixed String if one is found (quotations omitted). + */ + protected function quotedString($stopchars) + { + $tok = $this->scanner->current(); + if ('"' == $tok || "'" == $tok) { + $this->scanner->consume(); + $ret = $this->scanner->charsUntil($tok . $stopchars); + if ($this->scanner->current() == $tok) { + $this->scanner->consume(); + } else { + // Parse error because no close quote. + $this->parseError('Expected %s, got %s', $tok, $this->scanner->current()); + } + + return $ret; + } + + return false; + } + + /** + * Handle a CDATA section. + * + * @return bool + */ + protected function cdataSection() + { + $cdata = ''; + $this->scanner->consume(); + + $chars = $this->scanner->charsWhile('CDAT'); + if ('CDATA' != $chars || '[' != $this->scanner->current()) { + $this->parseError('Expected [CDATA[, got %s', $chars); + + return $this->bogusComment('<![' . $chars); + } + + $tok = $this->scanner->next(); + do { + if (false === $tok) { + $this->parseError('Unexpected EOF inside CDATA.'); + $this->bogusComment('<![CDATA[' . $cdata); + + return true; + } + $cdata .= $tok; + $tok = $this->scanner->next(); + } while (!$this->scanner->sequenceMatches(']]>')); + + // Consume ]]> + $this->scanner->consume(3); + + $this->events->cdata($cdata); + + return true; + } + + // ================================================================ + // Non-HTML5 + // ================================================================ + + /** + * Handle a processing instruction. + * + * XML processing instructions are supposed to be ignored in HTML5, + * treated as "bogus comments". However, since we're not a user + * agent, we allow them. We consume until ?> and then issue a + * EventListener::processingInstruction() event. + * + * @return bool + */ + protected function processingInstruction() + { + if ('?' != $this->scanner->current()) { + return false; + } + + $tok = $this->scanner->next(); + $procName = $this->scanner->getAsciiAlpha(); + $white = $this->scanner->whitespace(); + + // If not a PI, send to bogusComment. + if (0 == strlen($procName) || 0 == $white || false == $this->scanner->current()) { + $this->parseError("Expected processing instruction name, got $tok"); + $this->bogusComment('<?' . $tok . $procName); + + return true; + } + + $data = ''; + // As long as it's not the case that the next two chars are ? and >. + while (!('?' == $this->scanner->current() && '>' == $this->scanner->peek())) { + $data .= $this->scanner->current(); + + $tok = $this->scanner->next(); + if (false === $tok) { + $this->parseError('Unexpected EOF in processing instruction.'); + $this->events->processingInstruction($procName, $data); + + return true; + } + } + + $this->scanner->consume(2); // Consume the closing tag + $this->events->processingInstruction($procName, $data); + + return true; + } + + // ================================================================ + // UTILITY FUNCTIONS + // ================================================================ + + /** + * Read from the input stream until we get to the desired sequene + * or hit the end of the input stream. + * + * @param string $sequence + * + * @return string + */ + protected function readUntilSequence($sequence) + { + $buffer = ''; + + // Optimization for reading larger blocks faster. + $first = substr($sequence, 0, 1); + while (false !== $this->scanner->current()) { + $buffer .= $this->scanner->charsUntil($first); + + // Stop as soon as we hit the stopping condition. + if ($this->scanner->sequenceMatches($sequence, false)) { + return $buffer; + } + $buffer .= $this->scanner->current(); + $this->scanner->consume(); + } + + // If we get here, we hit the EOF. + $this->parseError('Unexpected EOF during text read.'); + + return $buffer; + } + + /** + * Check if upcomming chars match the given sequence. + * + * This will read the stream for the $sequence. If it's + * found, this will return true. If not, return false. + * Since this unconsumes any chars it reads, the caller + * will still need to read the next sequence, even if + * this returns true. + * + * Example: $this->scanner->sequenceMatches('</script>') will + * see if the input stream is at the start of a + * '</script>' string. + * + * @param string $sequence + * @param bool $caseSensitive + * + * @return bool + */ + protected function sequenceMatches($sequence, $caseSensitive = true) + { + @trigger_error(__METHOD__ . ' method is deprecated since version 2.4 and will be removed in 3.0. Use Scanner::sequenceMatches() instead.', E_USER_DEPRECATED); + + return $this->scanner->sequenceMatches($sequence, $caseSensitive); + } + + /** + * Send a TEXT event with the contents of the text buffer. + * + * This emits an EventHandler::text() event with the current contents of the + * temporary text buffer. (The buffer is used to group as much PCDATA + * as we can instead of emitting lots and lots of TEXT events.) + */ + protected function flushBuffer() + { + if ('' === $this->text) { + return; + } + $this->events->text($this->text); + $this->text = ''; + } + + /** + * Add text to the temporary buffer. + * + * @see flushBuffer() + * + * @param string $str + */ + protected function buffer($str) + { + $this->text .= $str; + } + + /** + * Emit a parse error. + * + * A parse error always returns false because it never consumes any + * characters. + * + * @param string $msg + * + * @return string + */ + protected function parseError($msg) + { + $args = func_get_args(); + + if (count($args) > 1) { + array_shift($args); + $msg = vsprintf($msg, $args); + } + + $line = $this->scanner->currentLine(); + $col = $this->scanner->columnOffset(); + $this->events->parseError($msg, $line, $col); + + return false; + } + + /** + * Decode a character reference and return the string. + * + * If $inAttribute is set to true, a bare & will be returned as-is. + * + * @param bool $inAttribute Set to true if the text is inside of an attribute value. + * false otherwise. + * + * @return string + */ + protected function decodeCharacterReference($inAttribute = false) + { + // Next char after &. + $tok = $this->scanner->next(); + $start = $this->scanner->position(); + + if (false === $tok) { + return '&'; + } + + // These indicate not an entity. We return just + // the &. + if ("\t" === $tok || "\n" === $tok || "\f" === $tok || ' ' === $tok || '&' === $tok || '<' === $tok) { + // $this->scanner->next(); + return '&'; + } + + // Numeric entity + if ('#' === $tok) { + $tok = $this->scanner->next(); + + if (false === $tok) { + $this->parseError('Expected &#DEC; &#HEX;, got EOF'); + $this->scanner->unconsume(1); + + return '&'; + } + + // Hexidecimal encoding. + // X[0-9a-fA-F]+; + // x[0-9a-fA-F]+; + if ('x' === $tok || 'X' === $tok) { + $tok = $this->scanner->next(); // Consume x + + // Convert from hex code to char. + $hex = $this->scanner->getHex(); + if (empty($hex)) { + $this->parseError('Expected &#xHEX;, got &#x%s', $tok); + // We unconsume because we don't know what parser rules might + // be in effect for the remaining chars. For example. '&#>' + // might result in a specific parsing rule inside of tag + // contexts, while not inside of pcdata context. + $this->scanner->unconsume(2); + + return '&'; + } + $entity = CharacterReference::lookupHex($hex); + } // Decimal encoding. + // [0-9]+; + else { + // Convert from decimal to char. + $numeric = $this->scanner->getNumeric(); + if (false === $numeric) { + $this->parseError('Expected &#DIGITS;, got &#%s', $tok); + $this->scanner->unconsume(2); + + return '&'; + } + $entity = CharacterReference::lookupDecimal($numeric); + } + } elseif ('=' === $tok && $inAttribute) { + return '&'; + } else { // String entity. + // Attempt to consume a string up to a ';'. + // [a-zA-Z0-9]+; + $cname = $this->scanner->getAsciiAlphaNum(); + $entity = CharacterReference::lookupName($cname); + + // When no entity is found provide the name of the unmatched string + // and continue on as the & is not part of an entity. The & will + // be converted to & elsewhere. + if (null === $entity) { + if (!$inAttribute || '' === $cname) { + $this->parseError("No match in entity table for '%s'", $cname); + } + $this->scanner->unconsume($this->scanner->position() - $start); + + return '&'; + } + } + + // The scanner has advanced the cursor for us. + $tok = $this->scanner->current(); + + // We have an entity. We're done here. + if (';' === $tok) { + $this->scanner->consume(); + + return $entity; + } + + // Failing to match ; means unconsume the entire string. + $this->scanner->unconsume($this->scanner->position() - $start); + + $this->parseError('Expected &ENTITY;, got &ENTITY%s (no trailing ;) ', $tok); + + return '&'; + } +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/TreeBuildingRules.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/TreeBuildingRules.php new file mode 100644 index 000000000..00d3951fd --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/TreeBuildingRules.php @@ -0,0 +1,127 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +/** + * Handles special-case rules for the DOM tree builder. + * + * Many tags have special rules that need to be accomodated on an + * individual basis. This class handles those rules. + * + * See section 8.1.2.4 of the spec. + * + * @todo - colgroup and col special behaviors + * - body and head special behaviors + */ +class TreeBuildingRules +{ + protected static $tags = array( + 'li' => 1, + 'dd' => 1, + 'dt' => 1, + 'rt' => 1, + 'rp' => 1, + 'tr' => 1, + 'th' => 1, + 'td' => 1, + 'thead' => 1, + 'tfoot' => 1, + 'tbody' => 1, + 'table' => 1, + 'optgroup' => 1, + 'option' => 1, + ); + + /** + * Returns true if the given tagname has special processing rules. + */ + public function hasRules($tagname) + { + return isset(static::$tags[$tagname]); + } + + /** + * Evaluate the rule for the current tag name. + * + * This may modify the existing DOM. + * + * @return \DOMElement The new Current DOM element. + */ + public function evaluate($new, $current) + { + switch ($new->tagName) { + case 'li': + return $this->handleLI($new, $current); + case 'dt': + case 'dd': + return $this->handleDT($new, $current); + case 'rt': + case 'rp': + return $this->handleRT($new, $current); + case 'optgroup': + return $this->closeIfCurrentMatches($new, $current, array( + 'optgroup', + )); + case 'option': + return $this->closeIfCurrentMatches($new, $current, array( + 'option', + )); + case 'tr': + return $this->closeIfCurrentMatches($new, $current, array( + 'tr', + )); + case 'td': + case 'th': + return $this->closeIfCurrentMatches($new, $current, array( + 'th', + 'td', + )); + case 'tbody': + case 'thead': + case 'tfoot': + case 'table': // Spec isn't explicit about this, but it's necessary. + + return $this->closeIfCurrentMatches($new, $current, array( + 'thead', + 'tfoot', + 'tbody', + )); + } + + return $current; + } + + protected function handleLI($ele, $current) + { + return $this->closeIfCurrentMatches($ele, $current, array( + 'li', + )); + } + + protected function handleDT($ele, $current) + { + return $this->closeIfCurrentMatches($ele, $current, array( + 'dt', + 'dd', + )); + } + + protected function handleRT($ele, $current) + { + return $this->closeIfCurrentMatches($ele, $current, array( + 'rt', + 'rp', + )); + } + + protected function closeIfCurrentMatches($ele, $current, $match) + { + if (in_array($current->tagName, $match, true)) { + $current->parentNode->appendChild($ele); + } else { + $current->appendChild($ele); + } + + return $ele; + } +} diff --git a/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/UTF8Utils.php b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/UTF8Utils.php new file mode 100644 index 000000000..f6a70bfac --- /dev/null +++ b/plugins/af_readability/vendor/masterminds/html5/src/HTML5/Parser/UTF8Utils.php @@ -0,0 +1,183 @@ +<?php + +namespace Masterminds\HTML5\Parser; + +/* +Portions based on code from html5lib files with the following copyright: + +Copyright 2009 Geoffrey Sneddon <http://gsnedders.com/> + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS +OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +use Masterminds\HTML5\Exception; + +class UTF8Utils +{ + /** + * The Unicode replacement character. + */ + const FFFD = "\xEF\xBF\xBD"; + + /** + * Count the number of characters in a string. + * UTF-8 aware. This will try (in order) iconv, MB, libxml, and finally a custom counter. + * + * @param string $string + * + * @return int + */ + public static function countChars($string) + { + // Get the length for the string we need. + if (function_exists('mb_strlen')) { + return mb_strlen($string, 'utf-8'); + } + + if (function_exists('iconv_strlen')) { + return iconv_strlen($string, 'utf-8'); + } + + if (function_exists('utf8_decode')) { + // MPB: Will this work? Won't certain decodes lead to two chars + // extrapolated out of 2-byte chars? + return strlen(utf8_decode($string)); + } + + $count = count_chars($string); + + // 0x80 = 0x7F - 0 + 1 (one added to get inclusive range) + // 0x33 = 0xF4 - 0x2C + 1 (one added to get inclusive range) + return array_sum(array_slice($count, 0, 0x80)) + array_sum(array_slice($count, 0xC2, 0x33)); + } + + /** + * Convert data from the given encoding to UTF-8. + * + * This has not yet been tested with charactersets other than UTF-8. + * It should work with ISO-8859-1/-13 and standard Latin Win charsets. + * + * @param string $data The data to convert + * @param string $encoding A valid encoding. Examples: http://www.php.net/manual/en/mbstring.supported-encodings.php + * + * @return string + */ + public static function convertToUTF8($data, $encoding = 'UTF-8') + { + /* + * From the HTML5 spec: Given an encoding, the bytes in the input stream must be converted + * to Unicode characters for the tokeniser, as described by the rules for that encoding, + * except that the leading U+FEFF BYTE ORDER MARK character, if any, must not be stripped + * by the encoding layer (it is stripped by the rule below). Bytes or sequences of bytes + * in the original byte stream that could not be converted to Unicode characters must be + * converted to U+FFFD REPLACEMENT CHARACTER code points. + */ + + // mb_convert_encoding is chosen over iconv because of a bug. The best + // details for the bug are on http://us1.php.net/manual/en/function.iconv.php#108643 + // which contains links to the actual but reports as well as work around + // details. + if (function_exists('mb_convert_encoding')) { + // mb library has the following behaviors: + // - UTF-16 surrogates result in false. + // - Overlongs and outside Plane 16 result in empty strings. + + // Before we run mb_convert_encoding we need to tell it what to do with + // characters it does not know. This could be different than the parent + // application executing this library so we store the value, change it + // to our needs, and then change it back when we are done. This feels + // a little excessive and it would be great if there was a better way. + $save = mb_substitute_character(); + mb_substitute_character('none'); + $data = mb_convert_encoding($data, 'UTF-8', $encoding); + mb_substitute_character($save); + } + // @todo Get iconv running in at least some environments if that is possible. + elseif (function_exists('iconv') && 'auto' !== $encoding) { + // fprintf(STDOUT, "iconv found\n"); + // iconv has the following behaviors: + // - Overlong representations are ignored. + // - Beyond Plane 16 is replaced with a lower char. + // - Incomplete sequences generate a warning. + $data = @iconv($encoding, 'UTF-8//IGNORE', $data); + } else { + throw new Exception('Not implemented, please install mbstring or iconv'); + } + + /* + * One leading U+FEFF BYTE ORDER MARK character must be ignored if any are present. + */ + if ("\xEF\xBB\xBF" === substr($data, 0, 3)) { + $data = substr($data, 3); + } + + return $data; + } + + /** + * Checks for Unicode code points that are not valid in a document. + * + * @param string $data A string to analyze + * + * @return array An array of (string) error messages produced by the scanning + */ + public static function checkForIllegalCodepoints($data) + { + // Vestigal error handling. + $errors = array(); + + /* + * All U+0000 null characters in the input must be replaced by U+FFFD REPLACEMENT CHARACTERs. + * Any occurrences of such characters is a parse error. + */ + for ($i = 0, $count = substr_count($data, "\0"); $i < $count; ++$i) { + $errors[] = 'null-character'; + } + + /* + * Any occurrences of any characters in the ranges U+0001 to U+0008, U+000B, U+000E to U+001F, U+007F + * to U+009F, U+D800 to U+DFFF , U+FDD0 to U+FDEF, and characters U+FFFE, U+FFFF, U+1FFFE, U+1FFFF, + * U+2FFFE, U+2FFFF, U+3FFFE, U+3FFFF, U+4FFFE, U+4FFFF, U+5FFFE, U+5FFFF, U+6FFFE, U+6FFFF, U+7FFFE, + * U+7FFFF, U+8FFFE, U+8FFFF, U+9FFFE, U+9FFFF, U+AFFFE, U+AFFFF, U+BFFFE, U+BFFFF, U+CFFFE, U+CFFFF, + * U+DFFFE, U+DFFFF, U+EFFFE, U+EFFFF, U+FFFFE, U+FFFFF, U+10FFFE, and U+10FFFF are parse errors. + * (These are all control characters or permanently undefined Unicode characters.) + */ + // Check PCRE is loaded. + $count = preg_match_all( + '/(?: + [\x01-\x08\x0B\x0E-\x1F\x7F] # U+0001 to U+0008, U+000B, U+000E to U+001F and U+007F + | + \xC2[\x80-\x9F] # U+0080 to U+009F + | + \xED(?:\xA0[\x80-\xFF]|[\xA1-\xBE][\x00-\xFF]|\xBF[\x00-\xBF]) # U+D800 to U+DFFFF + | + \xEF\xB7[\x90-\xAF] # U+FDD0 to U+FDEF + | + \xEF\xBF[\xBE\xBF] # U+FFFE and U+FFFF + | + [\xF0-\xF4][\x8F-\xBF]\xBF[\xBE\xBF] # U+nFFFE and U+nFFFF (1 <= n <= 10_{16}) + )/x', $data, $matches); + for ($i = 0; $i < $count; ++$i) { + $errors[] = 'invalid-codepoint'; + } + + return $errors; + } +} |