diff options
author | Asmir Mustafic <[email protected]> | 2018-11-25 16:45:06 +0100 |
---|---|---|
committer | GitHub <[email protected]> | 2018-11-25 16:45:06 +0100 |
commit | 54d066b1664a5fb749511c764e8d208f6bc80c3b (patch) | |
tree | 5089aec726a28a1247e21f7febd96e746cf4c6f1 /src | |
parent | c76378a560eeefa900429989fb6e85859f3a6b5e (diff) | |
parent | 91e7977d14f1ea2e78b5d46f85851c30bf3c6695 (diff) |
Merge pull request #160 from tgalopin/coding-style
Improve Travis configuration and add PHP-CS-Fixer
Diffstat (limited to 'src')
-rw-r--r-- | src/HTML5.php | 127 | ||||
-rw-r--r-- | src/HTML5/Elements.php | 515 | ||||
-rw-r--r-- | src/HTML5/Entities.php | 4 | ||||
-rw-r--r-- | src/HTML5/Exception.php | 1 | ||||
-rw-r--r-- | src/HTML5/InstructionProcessor.php | 20 | ||||
-rw-r--r-- | src/HTML5/Parser/CharacterReference.php | 32 | ||||
-rw-r--r-- | src/HTML5/Parser/DOMTreeBuilder.php | 181 | ||||
-rw-r--r-- | src/HTML5/Parser/EventHandler.php | 36 | ||||
-rw-r--r-- | src/HTML5/Parser/FileInputStream.php | 5 | ||||
-rw-r--r-- | src/HTML5/Parser/InputStream.php | 24 | ||||
-rw-r--r-- | src/HTML5/Parser/ParseError.php | 1 | ||||
-rw-r--r-- | src/HTML5/Parser/Scanner.php | 57 | ||||
-rw-r--r-- | src/HTML5/Parser/StringInputStream.php | 62 | ||||
-rw-r--r-- | src/HTML5/Parser/Tokenizer.php | 331 | ||||
-rw-r--r-- | src/HTML5/Parser/TreeBuildingRules.php | 31 | ||||
-rw-r--r-- | src/HTML5/Parser/UTF8Utils.php | 23 | ||||
-rw-r--r-- | src/HTML5/Serializer/HTML5Entities.php | 6 | ||||
-rw-r--r-- | src/HTML5/Serializer/OutputRules.php | 114 | ||||
-rw-r--r-- | src/HTML5/Serializer/RulesInterface.php | 26 | ||||
-rw-r--r-- | src/HTML5/Serializer/Traverser.php | 35 |
20 files changed, 783 insertions, 848 deletions
diff --git a/src/HTML5.php b/src/HTML5.php index 0697bed..3d7eee9 100644 --- a/src/HTML5.php +++ b/src/HTML5.php @@ -1,9 +1,7 @@ <?php + namespace Masterminds; -use Masterminds\HTML5\Parser\FileInputStream; -use Masterminds\HTML5\Parser\InputStream; -use Masterminds\HTML5\Parser\StringInputStream; use Masterminds\HTML5\Parser\DOMTreeBuilder; use Masterminds\HTML5\Parser\Scanner; use Masterminds\HTML5\Parser\Tokenizer; @@ -12,37 +10,38 @@ use Masterminds\HTML5\Serializer\Traverser; /** * This class offers convenience methods for parsing and serializing HTML5. - * It is roughly designed to mirror the \DOMDocument class that is - * provided with most versions of PHP. + * It is roughly designed to mirror the \DOMDocument native class. */ class HTML5 { - /** * Global options for the parser and serializer. * * @var array */ - protected $options = array( - // If the serializer should encode all entities. - 'encode_entities' => false + private $defaultOptions = array( + // Whether the serializer should aggressively encode all characters as entities. + 'encode_entities' => false, + + // Prevents the parser from automatically assigning the HTML5 namespace to the DOM document. + 'disable_html_ns' => false, ); protected $errors = array(); - public function __construct(array $options = array()) + public function __construct(array $defaultOptions = array()) { - $this->options = array_merge($this->options, $options); + $this->defaultOptions = array_merge($this->defaultOptions, $defaultOptions); } /** - * Get the default options. + * Get the current default options. * - * @return array The default options. + * @return array */ public function getOptions() { - return $this->options; + return $this->defaultOptions; } /** @@ -55,14 +54,13 @@ class HTML5 * * The rules governing parsing are set out in the HTML 5 spec. * - * @param string|resource $file - * The path to the file to parse. If this is a resource, it is - * assumed to be an open stream whose pointer is set to the first - * byte of input. - * @param array $options - * Configuration options when parsing the HTML + * @param string|resource $file The path to the file to parse. If this is a resource, it is + * assumed to be an open stream whose pointer is set to the first + * byte of input. + * @param array $options Configuration options when parsing the HTML. + * * @return \DOMDocument A DOM document. These object type is defined by the libxml - * library, and should have been included with your version of PHP. + * library, and should have been included with your version of PHP. */ public function load($file, array $options = array()) { @@ -80,12 +78,11 @@ class HTML5 * Take a string of HTML 5 (or earlier) and parse it into a * DOMDocument. * - * @param string $string - * A html5 document as a string. - * @param array $options - * Configuration options when parsing the HTML + * @param string $string A html5 document as a string. + * @param array $options Configuration options when parsing the HTML. + * * @return \DOMDocument A DOM document. DOM is part of libxml, which is included with - * almost all distribtions of PHP. + * almost all distribtions of PHP. */ public function loadHTML($string, array $options = array()) { @@ -98,15 +95,13 @@ class HTML5 * This is here to provide backwards compatibility with the * PHP DOM implementation. It simply calls load(). * - * @param string $file - * The path to the file to parse. If this is a resource, it is - * assumed to be an open stream whose pointer is set to the first - * byte of input. - * @param array $options - * Configuration options when parsing the HTML + * @param string $file The path to the file to parse. If this is a resource, it is + * assumed to be an open stream whose pointer is set to the first + * byte of input. + * @param array $options Configuration options when parsing the HTML. * * @return \DOMDocument A DOM document. These object type is defined by the libxml - * library, and should have been included with your version of PHP. + * library, and should have been included with your version of PHP. */ public function loadHTMLFile($file, array $options = array()) { @@ -116,11 +111,11 @@ class HTML5 /** * Parse a HTML fragment from a string. * - * @param string $string The HTML5 fragment as a string. - * @param array $options Configuration options when parsing the HTML + * @param string $string the HTML5 fragment as a string + * @param array $options Configuration options when parsing the HTML * * @return \DOMDocumentFragment A DOM fragment. The DOM is part of libxml, which is included with - * almost all distributions of PHP. + * almost all distributions of PHP. */ public function loadHTMLFragment($string, array $options = array()) { @@ -128,7 +123,7 @@ class HTML5 } /** - * Return all errors encountered into parsing phase + * Return all errors encountered into parsing phase. * * @return array */ @@ -138,7 +133,7 @@ class HTML5 } /** - * Return true it some errors were encountered into parsing phase + * Return true it some errors were encountered into parsing phase. * * @return bool */ @@ -148,23 +143,20 @@ class HTML5 } /** - * Parse an input stream. - * - * Lower-level loading function. This requires an input stream instead - * of a string, file, or resource. + * Parse an input string. * * @param string $input - * @param array $options + * @param array $options * * @return \DOMDocument */ public function parse($input, array $options = array()) { $this->errors = array(); - $options = array_merge($this->getOptions(), $options); + $options = array_merge($this->defaultOptions, $options); $events = new DOMTreeBuilder(false, $options); $scanner = new Scanner($input); - $parser = new Tokenizer($scanner, $events, !empty($options['xmlNamespaces']) ? Tokenizer::CONFORMANT_XML: Tokenizer::CONFORMANT_HTML); + $parser = new Tokenizer($scanner, $events, !empty($options['xmlNamespaces']) ? Tokenizer::CONFORMANT_XML : Tokenizer::CONFORMANT_HTML); $parser->parse(); $this->errors = $events->getErrors(); @@ -178,17 +170,17 @@ class HTML5 * Lower-level loading function. This requires an input stream instead * of a string, file, or resource. * - * @param string $input The input data to parse in the form of a string. - * @param array $options An array of options + * @param string $input The input data to parse in the form of a string. + * @param array $options An array of options. * * @return \DOMDocumentFragment */ public function parseFragment($input, array $options = array()) { - $options = array_merge($this->getOptions(), $options); + $options = array_merge($this->defaultOptions, $options); $events = new DOMTreeBuilder(true, $options); $scanner = new Scanner($input); - $parser = new Tokenizer($scanner, $events, !empty($options['xmlNamespaces']) ? Tokenizer::CONFORMANT_XML: Tokenizer::CONFORMANT_HTML); + $parser = new Tokenizer($scanner, $events, !empty($options['xmlNamespaces']) ? Tokenizer::CONFORMANT_XML : Tokenizer::CONFORMANT_HTML); $parser->parse(); $this->errors = $events->getErrors(); @@ -199,15 +191,12 @@ class HTML5 /** * Save a DOM into a given file as HTML5. * - * @param mixed $dom - * The DOM to be serialized. - * @param string|resource $file - * The filename to be written or resource to write to. - * @param array $options - * Configuration options when serializing the DOM. These include: - * - encode_entities: Text written to the output is escaped by default and not all - * entities are encoded. If this is set to true all entities will be encoded. - * Defaults to false. + * @param mixed $dom The DOM to be serialized. + * @param string|resource $file The filename to be written or resource to write to. + * @param array $options Configuration options when serializing the DOM. These include: + * - encode_entities: Text written to the output is escaped by default and not all + * entities are encoded. If this is set to true all entities will be encoded. + * Defaults to false. */ public function save($dom, $file, $options = array()) { @@ -216,9 +205,9 @@ class HTML5 $stream = $file; $close = false; } else { - $stream = fopen($file, 'w'); + $stream = fopen($file, 'wb'); } - $options = array_merge($this->getOptions(), $options); + $options = array_merge($this->defaultOptions, $options); $rules = new OutputRules($stream, $options); $trav = new Traverser($dom, $stream, $rules, $options); @@ -232,21 +221,19 @@ class HTML5 /** * Convert a DOM into an HTML5 string. * - * @param mixed $dom - * The DOM to be serialized. - * @param array $options - * Configuration options when serializing the DOM. These include: - * - encode_entities: Text written to the output is escaped by default and not all - * entities are encoded. If this is set to true all entities will be encoded. - * Defaults to false. + * @param mixed $dom The DOM to be serialized. + * @param array $options Configuration options when serializing the DOM. These include: + * - encode_entities: Text written to the output is escaped by default and not all + * entities are encoded. If this is set to true all entities will be encoded. + * Defaults to false. * * @return string A HTML5 documented generated from the DOM. */ public function saveHTML($dom, $options = array()) { - $stream = fopen('php://temp', 'w'); - $this->save($dom, $stream, array_merge($this->getOptions(), $options)); + $stream = fopen('php://temp', 'wb'); + $this->save($dom, $stream, array_merge($this->defaultOptions, $options)); - return stream_get_contents($stream, - 1, 0); + return stream_get_contents($stream, -1, 0); } } diff --git a/src/HTML5/Elements.php b/src/HTML5/Elements.php index 3cb6093..8fe7987 100644 --- a/src/HTML5/Elements.php +++ b/src/HTML5/Elements.php @@ -2,6 +2,7 @@ /** * Provide general element functions. */ + namespace Masterminds\HTML5; /** @@ -17,7 +18,6 @@ namespace Masterminds\HTML5; */ class Elements { - /** * Indicates an element is described in the specification. */ @@ -77,116 +77,116 @@ class Elements * @var array */ public static $html5 = array( - "a" => 1, - "abbr" => 1, - "address" => 65, // NORMAL | BLOCK_TAG - "area" => 9, // NORMAL | VOID_TAG - "article" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "aside" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "audio" => 1, // NORMAL - "b" => 1, - "base" => 9, // NORMAL | VOID_TAG - "bdi" => 1, - "bdo" => 1, - "blockquote" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "body" => 1, - "br" => 9, // NORMAL | VOID_TAG - "button" => 1, - "canvas" => 65, // NORMAL | BLOCK_TAG - "caption" => 1, - "cite" => 1, - "code" => 1, - "col" => 9, // NORMAL | VOID_TAG - "colgroup" => 1, - "command" => 9, // NORMAL | VOID_TAG + 'a' => 1, + 'abbr' => 1, + 'address' => 65, // NORMAL | BLOCK_TAG + 'area' => 9, // NORMAL | VOID_TAG + 'article' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'aside' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'audio' => 1, // NORMAL + 'b' => 1, + 'base' => 9, // NORMAL | VOID_TAG + 'bdi' => 1, + 'bdo' => 1, + 'blockquote' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'body' => 1, + 'br' => 9, // NORMAL | VOID_TAG + 'button' => 1, + 'canvas' => 65, // NORMAL | BLOCK_TAG + 'caption' => 1, + 'cite' => 1, + 'code' => 1, + 'col' => 9, // NORMAL | VOID_TAG + 'colgroup' => 1, + 'command' => 9, // NORMAL | VOID_TAG // "data" => 1, // This is highly experimental and only part of the whatwg spec (not w3c). See https://developer.mozilla.org/en-US/docs/HTML/Element/data - "datalist" => 1, - "dd" => 65, // NORMAL | BLOCK_TAG - "del" => 1, - "details" => 17, // NORMAL | AUTOCLOSE_P, - "dfn" => 1, - "dialog" => 17, // NORMAL | AUTOCLOSE_P, - "div" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "dl" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "dt" => 1, - "em" => 1, - "embed" => 9, // NORMAL | VOID_TAG - "fieldset" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "figcaption" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "figure" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "footer" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "form" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "h1" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "h2" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "h3" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "h4" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "h5" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "h6" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "head" => 1, - "header" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "hgroup" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "hr" => 73, // NORMAL | VOID_TAG - "html" => 1, - "i" => 1, - "iframe" => 3, // NORMAL | TEXT_RAW - "img" => 9, // NORMAL | VOID_TAG - "input" => 9, // NORMAL | VOID_TAG - "kbd" => 1, - "ins" => 1, - "keygen" => 9, // NORMAL | VOID_TAG - "label" => 1, - "legend" => 1, - "li" => 1, - "link" => 9, // NORMAL | VOID_TAG - "map" => 1, - "mark" => 1, - "menu" => 17, // NORMAL | AUTOCLOSE_P, - "meta" => 9, // NORMAL | VOID_TAG - "meter" => 1, - "nav" => 17, // NORMAL | AUTOCLOSE_P, - "noscript" => 65, // NORMAL | BLOCK_TAG - "object" => 1, - "ol" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "optgroup" => 1, - "option" => 1, - "output" => 65, // NORMAL | BLOCK_TAG - "p" => 209, // NORMAL | AUTOCLOSE_P | BLOCK_TAG | BLOCK_ONLY_INLINE - "param" => 9, // NORMAL | VOID_TAG - "pre" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "progress" => 1, - "q" => 1, - "rp" => 1, - "rt" => 1, - "ruby" => 1, - "s" => 1, - "samp" => 1, - "script" => 3, // NORMAL | TEXT_RAW - "section" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "select" => 1, - "small" => 1, - "source" => 9, // NORMAL | VOID_TAG - "span" => 1, - "strong" => 1, - "style" => 3, // NORMAL | TEXT_RAW - "sub" => 1, - "summary" => 17, // NORMAL | AUTOCLOSE_P, - "sup" => 1, - "table" => 65, // NORMAL | BLOCK_TAG - "tbody" => 1, - "td" => 1, - "textarea" => 5, // NORMAL | TEXT_RCDATA - "tfoot" => 65, // NORMAL | BLOCK_TAG - "th" => 1, - "thead" => 1, - "time" => 1, - "title" => 5, // NORMAL | TEXT_RCDATA - "tr" => 1, - "track" => 9, // NORMAL | VOID_TAG - "u" => 1, - "ul" => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG - "var" => 1, - "video" => 65, // NORMAL | BLOCK_TAG - "wbr" => 9, // NORMAL | VOID_TAG + 'datalist' => 1, + 'dd' => 65, // NORMAL | BLOCK_TAG + 'del' => 1, + 'details' => 17, // NORMAL | AUTOCLOSE_P, + 'dfn' => 1, + 'dialog' => 17, // NORMAL | AUTOCLOSE_P, + 'div' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'dl' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'dt' => 1, + 'em' => 1, + 'embed' => 9, // NORMAL | VOID_TAG + 'fieldset' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'figcaption' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'figure' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'footer' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'form' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'h1' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'h2' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'h3' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'h4' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'h5' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'h6' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'head' => 1, + 'header' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'hgroup' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'hr' => 73, // NORMAL | VOID_TAG + 'html' => 1, + 'i' => 1, + 'iframe' => 3, // NORMAL | TEXT_RAW + 'img' => 9, // NORMAL | VOID_TAG + 'input' => 9, // NORMAL | VOID_TAG + 'kbd' => 1, + 'ins' => 1, + 'keygen' => 9, // NORMAL | VOID_TAG + 'label' => 1, + 'legend' => 1, + 'li' => 1, + 'link' => 9, // NORMAL | VOID_TAG + 'map' => 1, + 'mark' => 1, + 'menu' => 17, // NORMAL | AUTOCLOSE_P, + 'meta' => 9, // NORMAL | VOID_TAG + 'meter' => 1, + 'nav' => 17, // NORMAL | AUTOCLOSE_P, + 'noscript' => 65, // NORMAL | BLOCK_TAG + 'object' => 1, + 'ol' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'optgroup' => 1, + 'option' => 1, + 'output' => 65, // NORMAL | BLOCK_TAG + 'p' => 209, // NORMAL | AUTOCLOSE_P | BLOCK_TAG | BLOCK_ONLY_INLINE + 'param' => 9, // NORMAL | VOID_TAG + 'pre' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'progress' => 1, + 'q' => 1, + 'rp' => 1, + 'rt' => 1, + 'ruby' => 1, + 's' => 1, + 'samp' => 1, + 'script' => 3, // NORMAL | TEXT_RAW + 'section' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'select' => 1, + 'small' => 1, + 'source' => 9, // NORMAL | VOID_TAG + 'span' => 1, + 'strong' => 1, + 'style' => 3, // NORMAL | TEXT_RAW + 'sub' => 1, + 'summary' => 17, // NORMAL | AUTOCLOSE_P, + 'sup' => 1, + 'table' => 65, // NORMAL | BLOCK_TAG + 'tbody' => 1, + 'td' => 1, + 'textarea' => 5, // NORMAL | TEXT_RCDATA + 'tfoot' => 65, // NORMAL | BLOCK_TAG + 'th' => 1, + 'thead' => 1, + 'time' => 1, + 'title' => 5, // NORMAL | TEXT_RCDATA + 'tr' => 1, + 'track' => 9, // NORMAL | VOID_TAG + 'u' => 1, + 'ul' => 81, // NORMAL | AUTOCLOSE_P | BLOCK_TAG + 'var' => 1, + 'video' => 65, // NORMAL | BLOCK_TAG + 'wbr' => 9, // NORMAL | VOID_TAG // Legacy? 'basefont' => 8, // VOID_TAG @@ -202,7 +202,7 @@ class Elements 'marquee' => 0, 'isindex' => 8, // VOID_TAG 'xmp' => 20, // AUTOCLOSE_P | VOID_TAG | RAW_TEXT - 'noembed' => 2 // RAW_TEXT + 'noembed' => 2, // RAW_TEXT ); /** @@ -215,45 +215,45 @@ class Elements * @var array */ public static $mathml = array( - "maction" => 1, - "maligngroup" => 1, - "malignmark" => 1, - "math" => 1, - "menclose" => 1, - "merror" => 1, - "mfenced" => 1, - "mfrac" => 1, - "mglyph" => 1, - "mi" => 1, - "mlabeledtr" => 1, - "mlongdiv" => 1, - "mmultiscripts" => 1, - "mn" => 1, - "mo" => 1, - "mover" => 1, - "mpadded" => 1, - "mphantom" => 1, - "mroot" => 1, - "mrow" => 1, - "ms" => 1, - "mscarries" => 1, - "mscarry" => 1, - "msgroup" => 1, - "msline" => 1, - "mspace" => 1, - "msqrt" => 1, - "msrow" => 1, - "mstack" => 1, - "mstyle" => 1, - "msub" => 1, - "msup" => 1, - "msubsup" => 1, - "mtable" => 1, - "mtd" => 1, - "mtext" => 1, - "mtr" => 1, - "munder" => 1, - "munderover" => 1 + 'maction' => 1, + 'maligngroup' => 1, + 'malignmark' => 1, + 'math' => 1, + 'menclose' => 1, + 'merror' => 1, + 'mfenced' => 1, + 'mfrac' => 1, + 'mglyph' => 1, + 'mi' => 1, + 'mlabeledtr' => 1, + 'mlongdiv' => 1, + 'mmultiscripts' => 1, + 'mn' => 1, + 'mo' => 1, + 'mover' => 1, + 'mpadded' => 1, + 'mphantom' => 1, + 'mroot' => 1, + 'mrow' => 1, + 'ms' => 1, + 'mscarries' => 1, + 'mscarry' => 1, + 'msgroup' => 1, + 'msline' => 1, + 'mspace' => 1, + 'msqrt' => 1, + 'msrow' => 1, + 'mstack' => 1, + 'mstyle' => 1, + 'msub' => 1, + 'msup' => 1, + 'msubsup' => 1, + 'mtable' => 1, + 'mtd' => 1, + 'mtext' => 1, + 'mtr' => 1, + 'munder' => 1, + 'munderover' => 1, ); /** @@ -269,86 +269,86 @@ class Elements * @var array */ public static $svg = array( - "a" => 1, - "altGlyph" => 1, - "altGlyphDef" => 1, - "altGlyphItem" => 1, - "animate" => 1, - "animateColor" => 1, - "animateMotion" => 1, - "animateTransform" => 1, - "circle" => 1, - "clipPath" => 1, - "color-profile" => 1, - "cursor" => 1, - "defs" => 1, - "desc" => 1, - "ellipse" => 1, - "feBlend" => 1, - "feColorMatrix" => 1, - "feComponentTransfer" => 1, - "feComposite" => 1, - "feConvolveMatrix" => 1, - "feDiffuseLighting" => 1, - "feDisplacementMap" => 1, - "feDistantLight" => 1, - "feFlood" => 1, - "feFuncA" => 1, - "feFuncB" => 1, - "feFuncG" => 1, - "feFuncR" => 1, - "feGaussianBlur" => 1, - "feImage" => 1, - "feMerge" => 1, - "feMergeNode" => 1, - "feMorphology" => 1, - "feOffset" => 1, - "fePointLight" => 1, - "feSpecularLighting" => 1, - "feSpotLight" => 1, - "feTile" => 1, - "feTurbulence" => 1, - "filter" => 1, - "font" => 1, - "font-face" => 1, - "font-face-format" => 1, - "font-face-name" => 1, - "font-face-src" => 1, - "font-face-uri" => 1, - "foreignObject" => 1, - "g" => 1, - "glyph" => 1, - "glyphRef" => 1, - "hkern" => 1, - "image" => 1, - "line" => 1, - "linearGradient" => 1, - "marker" => 1, - "mask" => 1, - "metadata" => 1, - "missing-glyph" => 1, - "mpath" => 1, - "path" => 1, - "pattern" => 1, - "polygon" => 1, - "polyline" => 1, - "radialGradient" => 1, - "rect" => 1, - "script" => 3, // NORMAL | RAW_TEXT - "set" => 1, - "stop" => 1, - "style" => 3, // NORMAL | RAW_TEXT - "svg" => 1, - "switch" => 1, - "symbol" => 1, - "text" => 1, - "textPath" => 1, - "title" => 1, - "tref" => 1, - "tspan" => 1, - "use" => 1, - "view" => 1, - "vkern" => 1 + 'a' => 1, + 'altGlyph' => 1, + 'altGlyphDef' => 1, + 'altGlyphItem' => 1, + 'animate' => 1, + 'animateColor' => 1, + 'animateMotion' => 1, + 'animateTransform' => 1, + 'circle' => 1, + 'clipPath' => 1, + 'color-profile' => 1, + 'cursor' => 1, + 'defs' => 1, + 'desc' => 1, + 'ellipse' => 1, + 'feBlend' => 1, + 'feColorMatrix' => 1, + 'feComponentTransfer' => 1, + 'feComposite' => 1, + 'feConvolveMatrix' => 1, + 'feDiffuseLighting' => 1, + 'feDisplacementMap' => 1, + 'feDistantLight' => 1, + 'feFlood' => 1, + 'feFuncA' => 1, + 'feFuncB' => 1, + 'feFuncG' => 1, + 'feFuncR' => 1, + 'feGaussianBlur' => 1, + 'feImage' => 1, + 'feMerge' => 1, + 'feMergeNode' => 1, + 'feMorphology' => 1, + 'feOffset' => 1, + 'fePointLight' => 1, + 'feSpecularLighting' => 1, + 'feSpotLight' => 1, + 'feTile' => 1, + 'feTurbulence' => 1, + 'filter' => 1, + 'font' => 1, + 'font-face' => 1, + 'font-face-format' => 1, + 'font-face-name' => 1, + 'font-face-src' => 1, + 'font-face-uri' => 1, + 'foreignObject' => 1, + 'g' => 1, + 'glyph' => 1, + 'glyphRef' => 1, + 'hkern' => 1, + 'image' => 1, + 'line' => 1, + 'linearGradient' => 1, + 'marker' => 1, + 'mask' => 1, + 'metadata' => 1, + 'missing-glyph' => 1, + 'mpath' => 1, + 'path' => 1, + 'pattern' => 1, + 'polygon' => 1, + 'polyline' => 1, + 'radialGradient' => 1, + 'rect' => 1, + 'script' => 3, // NORMAL | RAW_TEXT + 'set' => 1, + 'stop' => 1, + 'style' => 3, // NORMAL | RAW_TEXT + 'svg' => 1, + 'switch' => 1, + 'symbol' => 1, + 'text' => 1, + 'textPath' => 1, + 'title' => 1, + 'tref' => 1, + 'tspan' => 1, + 'use' => 1, + 'view' => 1, + 'vkern' => 1, ); /** @@ -419,7 +419,7 @@ class Elements 'viewtarget' => 'viewTarget', 'xchannelselector' => 'xChannelSelector', 'ychannelselector' => 'yChannelSelector', - 'zoomandpan' => 'zoomAndPan' + 'zoomandpan' => 'zoomAndPan', ); /** @@ -465,7 +465,7 @@ class Elements 'glyphref' => 'glyphRef', 'lineargradient' => 'linearGradient', 'radialgradient' => 'radialGradient', - 'textpath' => 'textPath' + 'textpath' => 'textPath', ); /** @@ -477,24 +477,22 @@ class Elements * * Elements::isA('script', Elements::TEXT_RCDATA); // Returns false. * - * @param string $name - * The element name. - * @param int $mask - * One of the constants on this class. - * @return boolean true if the element matches the mask, false otherwise. + * @param string $name The element name. + * @param int $mask One of the constants on this class. + * + * @return bool true if the element matches the mask, false otherwise. */ public static function isA($name, $mask) { - return (static::element($name) & $mask) == $mask; + return (static::element($name) & $mask) === $mask; } /** * Test if an element is a valid html5 element. * - * @param string $name - * The name of the element. + * @param string $name The name of the element. * - * @return bool True if a html5 element and false otherwise. + * @return bool true if a html5 element and false otherwise. */ public static function isHtml5Element($name) { @@ -506,10 +504,9 @@ class Elements /** * Test if an element name is a valid MathML presentation element. * - * @param string $name - * The name of the element. + * @param string $name The name of the element. * - * @return bool True if a MathML name and false otherwise. + * @return bool true if a MathML name and false otherwise. */ public static function isMathMLElement($name) { @@ -520,10 +517,9 @@ class Elements /** * Test if an element is a valid SVG element. * - * @param string $name - * The name of the element. + * @param string $name The name of the element. * - * @return boolean True if a SVG element and false otherise. + * @return bool true if a SVG element and false otherise. */ public static function isSvgElement($name) { @@ -533,14 +529,12 @@ class Elements /** * Is an element name valid in an html5 document. - * * This includes html5 elements along with other allowed embedded content * such as svg and mathml. * - * @param string $name - * The name of the element. + * @param string $name The name of the element. * - * @return bool True if valid and false otherwise. + * @return bool true if valid and false otherwise. */ public static function isElement($name) { @@ -550,10 +544,9 @@ class Elements /** * Get the element mask for the given element name. * - * @param string $name - * The name of the element. + * @param string $name The name of the element. * - * @return int The element mask. + * @return int the element mask. */ public static function element($name) { @@ -573,10 +566,9 @@ class Elements /** * Normalize a SVG element name to its proper case and form. * - * @param string $name - * The name of the element. + * @param string $name The name of the element. * - * @return string The normalized form of the element name. + * @return string the normalized form of the element name. */ public static function normalizeSvgElement($name) { @@ -591,8 +583,7 @@ class Elements /** * Normalize a SVG attribute name to its proper case and form. * - * @param string $name - * The name of the attribute. + * @param string $name The name of the attribute. * * @return string The normalized form of the attribute name. */ @@ -608,11 +599,9 @@ class Elements /** * Normalize a MathML attribute name to its proper case and form. - * * Note, all MathML element names are lowercase. * - * @param string $name - * The name of the attribute. + * @param string $name The name of the attribute. * * @return string The normalized form of the attribute name. */ @@ -621,7 +610,7 @@ class Elements $name = strtolower($name); // Only one attribute has a mixed case form for MathML. - if ($name == 'definitionurl') { + if ('definitionurl' === $name) { $name = 'definitionURL'; } diff --git a/src/HTML5/Entities.php b/src/HTML5/Entities.php index 2e605d6..0e7227d 100644 --- a/src/HTML5/Entities.php +++ b/src/HTML5/Entities.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5; /** @@ -7,7 +8,6 @@ namespace Masterminds\HTML5; */ class Entities { - public static $byName = array( 'Aacute' => 'Á', 'Aacut' => 'Á', @@ -2231,6 +2231,6 @@ class Entities 'Zscr' => '𝒵', 'zscr' => '𝓏', 'zwj' => '', - 'zwnj' => '' + 'zwnj' => '', ); } diff --git a/src/HTML5/Exception.php b/src/HTML5/Exception.php index 8f33126..64e97e6 100644 --- a/src/HTML5/Exception.php +++ b/src/HTML5/Exception.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5; /** diff --git a/src/HTML5/InstructionProcessor.php b/src/HTML5/InstructionProcessor.php index ac6a23c..33a73fc 100644 --- a/src/HTML5/InstructionProcessor.php +++ b/src/HTML5/InstructionProcessor.php @@ -2,6 +2,7 @@ /** * A handler for processor instructions. */ + namespace Masterminds\HTML5; /** @@ -18,7 +19,6 @@ namespace Masterminds\HTML5; */ interface InstructionProcessor { - /** * Process an individual processing instruction. * @@ -28,16 +28,14 @@ interface InstructionProcessor * - Making any subsequent modifications to the DOM by modifying the * DOMElement or its attached DOM tree. * - * @param DOMElement $element - * The parent element for the current processing instruction. - * @param string $name - * The instruction's name. E.g. `<?php` has the name `php`. - * @param string $data - * All of the data between the opening and closing PI marks. - * @return DOMElement The element that should be considered "Current". This may just be - * the element passed in, but if the processor added more elements, - * it may choose to reset the current element to one of the elements - * it created. (When in doubt, return the element passed in.) + * @param \DOMElement $element The parent element for the current processing instruction. + * @param string $name The instruction's name. E.g. `<?php` has the name `php`. + * @param string $data All of the data between the opening and closing PI marks. + * + * @return \DOMElement The element that should be considered "Current". This may just be + * the element passed in, but if the processor added more elements, + * it may choose to reset the current element to one of the elements + * it created. (When in doubt, return the element passed in.) */ public function process(\DOMElement $element, $name, $data); } diff --git a/src/HTML5/Parser/CharacterReference.php b/src/HTML5/Parser/CharacterReference.php index c1617e7..490b548 100644 --- a/src/HTML5/Parser/CharacterReference.php +++ b/src/HTML5/Parser/CharacterReference.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Parser; use Masterminds\HTML5\Entities; @@ -6,25 +7,22 @@ use Masterminds\HTML5\Entities; /** * Manage entity references. * - * This is a simple resolver for HTML5 character reference entitites. - * See \Masterminds\HTML5\Entities for the list of supported entities. + * 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 + 0xFFFF, ); /** - * Given a name (e.g. - * 'amp'), lookup the UTF-8 character ('&') + * Given a name (e.g. 'amp'), lookup the UTF-8 character ('&'). + * + * @param string $name The name to look up. * - * @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) @@ -34,20 +32,16 @@ class CharacterReference } /** - * Given a Unicode codepoint, return the UTF-8 character. - * - * (NOT USED ANYWHERE) - */ - /* - * public static function lookupCode($codePoint) { return 'POINT'; } - */ - - /** * 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'); @@ -55,6 +49,10 @@ class CharacterReference /** * Given a hexidecimal number, return the UTF-8 character. + * + * @param $hexdec + * + * @return false|string|string[]|null */ public static function lookupHex($hexdec) { diff --git a/src/HTML5/Parser/DOMTreeBuilder.php b/src/HTML5/Parser/DOMTreeBuilder.php index 7f0e16a..f01cf4d 100644 --- a/src/HTML5/Parser/DOMTreeBuilder.php +++ b/src/HTML5/Parser/DOMTreeBuilder.php @@ -1,7 +1,9 @@ <?php + namespace Masterminds\HTML5\Parser; use Masterminds\HTML5\Elements; +use Masterminds\HTML5\InstructionProcessor; /** * Create an HTML5 DOM tree from events. @@ -24,7 +26,7 @@ use Masterminds\HTML5\Elements; class DOMTreeBuilder implements EventHandler { /** - * Defined in http://www.w3.org/TR/html51/infrastructure.html#html-namespace-0 + * Defined in http://www.w3.org/TR/html51/infrastructure.html#html-namespace-0. */ const NAMESPACE_HTML = 'http://www.w3.org/1999/xhtml'; @@ -45,14 +47,14 @@ class DOMTreeBuilder implements EventHandler const OPT_IMPLICIT_NS = 'implicit_namespaces'; /** - * Holds the HTML5 element names that causes a namespace switch + * 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 + 'math' => self::NAMESPACE_MATHML, ); /** @@ -63,7 +65,7 @@ class DOMTreeBuilder implements EventHandler protected $implicitNamespaces = array( 'xml' => self::NAMESPACE_XML, 'xmlns' => self::NAMESPACE_XMLNS, - 'xlink' => self::NAMESPACE_XLINK + 'xlink' => self::NAMESPACE_XLINK, ); /** @@ -146,15 +148,15 @@ class DOMTreeBuilder implements EventHandler protected $insertMode = 0; /** - * Track if we are in an element that allows only inline child nodes + * 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. + * Any document that is missing the DT will be considered to be in quirks mode. */ protected $quirks = true; @@ -175,24 +177,23 @@ class DOMTreeBuilder implements EventHandler // $this->doc = \DOMImplementation::createDocument(NULL, 'html', $dt); $this->doc = $impl->createDocument(null, null, $dt); } + $this->errors = array(); $this->current = $this->doc; // ->documentElement; // Create a rules engine for tags. - $this->rules = new TreeBuildingRules($this->doc); + $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 = $this->options["implicitNamespaces"]; + } elseif (isset($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 - ) + $this->implicitNamespaces); + array_unshift($this->nsStack, $implicitNS + array('' => self::NAMESPACE_HTML) + $this->implicitNamespaces); if ($isFragment) { $this->insertMode = static::IM_IN_BODY; @@ -229,8 +230,10 @@ class DOMTreeBuilder implements EventHandler * * 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(\Masterminds\HTML5\InstructionProcessor $proc) + public function setInstructionProcessor(InstructionProcessor $proc) { $this->processor = $proc; } @@ -242,7 +245,7 @@ class DOMTreeBuilder implements EventHandler $this->quirks = $quirks; if ($this->insertMode > static::IM_INITIAL) { - $this->parseError("Illegal placement of DOCTYPE tag. Ignoring: " . $name); + $this->parseError('Illegal placement of DOCTYPE tag. Ignoring: ' . $name); return; } @@ -256,27 +259,32 @@ class DOMTreeBuilder implements EventHandler * @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) { - // fprintf(STDOUT, $name); $lname = $this->normalizeTagName($name); // Make sure we have an html element. - if (! $this->doc->documentElement && $name !== 'html' && ! $this->frag) { + if (!$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) { + if ($this->insertMode === static::IM_INITIAL) { $this->quirks = true; - $this->parseError("No DOCTYPE specified."); + $this->parseError('No DOCTYPE specified.'); } // SPECIAL TAG HANDLING: // Spec says do this, and "don't ask." // find the spec where this is defined... looks problematic - if ($name == 'image' && !($this->insertMode === static::IM_IN_SVG || $this->insertMode === static::IM_IN_MATHML)) { + if ('image' === $name && !($this->insertMode === static::IM_IN_SVG || $this->insertMode === static::IM_IN_MATHML)) { $name = 'img'; } @@ -292,7 +300,7 @@ class DOMTreeBuilder implements EventHandler break; case 'head': if ($this->insertMode > static::IM_BEFORE_HEAD) { - $this->parseError("Unexpected head tag outside of head context."); + $this->parseError('Unexpected head tag outside of head context.'); } else { $this->insertMode = static::IM_IN_HEAD; } @@ -307,14 +315,14 @@ class DOMTreeBuilder implements EventHandler $this->insertMode = static::IM_IN_MATHML; break; case 'noscript': - if ($this->insertMode == static::IM_IN_HEAD) { + 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) { + if ($this->insertMode === static::IM_IN_SVG) { $lname = Elements::normalizeSvgElement($lname); } @@ -322,62 +330,58 @@ class DOMTreeBuilder implements EventHandler // 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] + '' => $this->nsRoots[$lname], ) + $this->nsStack[0]); - $pushes ++; + ++$pushes; } $needsWorkaround = false; - if (isset($this->options["xmlNamespaces"]) && $this->options["xmlNamespaces"]) { + if (isset($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 => $aVal) { - if ($aName === 'xmlns') { + if ('xmlns' === $aName) { $needsWorkaround = $aVal; array_unshift($this->nsStack, array( - '' => $aVal + '' => $aVal, ) + $this->nsStack[0]); - $pushes ++; - } elseif ((($pos = strpos($aName, ':')) ? substr($aName, 0, $pos) : '') === 'xmlns') { + ++$pushes; + } elseif ('xmlns' === (($pos = strpos($aName, ':')) ? substr($aName, 0, $pos) : '')) { array_unshift($this->nsStack, array( - substr($aName, $pos + 1) => $aVal + substr($aName, $pos + 1) => $aVal, ) + $this->nsStack[0]); - $pushes ++; + ++$pushes; } } } if ($this->onlyInline && Elements::isA($lname, Elements::BLOCK_TAG)) { - $this->autoclose($this->onlyInline); - $this->onlyInline = null; + $this->autoclose($this->onlyInline); + $this->onlyInline = null; } try { $prefix = ($pos = strpos($lname, ':')) ? substr($lname, 0, $pos) : ''; - - if ($needsWorkaround!==false) { - - $xml = "<$lname xmlns=\"$needsWorkaround\" ".(strlen($prefix) && isset($this->nsStack[0][$prefix])?("xmlns:$prefix=\"".$this->nsStack[0][$prefix]."\""):"")."/>"; + 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]) && $this->options[self::OPT_DISABLE_HTML_NS])) { + if (!isset($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; + $this->onlyInline = $lname; } // When we add some namespacess, we have to track them. Later, when "endElement" is invoked, we have to remove them. @@ -396,23 +400,23 @@ class DOMTreeBuilder implements EventHandler foreach ($attributes as $aName => $aVal) { // xmlns attributes can't be set - if ($aName === 'xmlns') { + if ('xmlns' === $aName) { continue; } - if ($this->insertMode == static::IM_IN_SVG) { + if ($this->insertMode === static::IM_IN_SVG) { $aName = Elements::normalizeSvgAttribute($aName); - } elseif ($this->insertMode == static::IM_IN_MATHML) { + } elseif ($this->insertMode === static::IM_IN_MATHML) { $aName = Elements::normalizeMathMlAttribute($aName); } try { $prefix = ($pos = strpos($aName, ':')) ? substr($aName, 0, $pos) : false; - if ($prefix==='xmlns') { - $ele->setAttributeNs(self::NAMESPACE_XMLNS, $aName, $aVal); - } elseif ($prefix!==false && isset($this->nsStack[0][$prefix])) { - $ele->setAttributeNs($this->nsStack[0][$prefix], $aName, $aVal); + 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, $aVal); } @@ -422,19 +426,19 @@ class DOMTreeBuilder implements EventHandler } // This is necessary on a non-DTD schema, like HTML5. - if ($aName == 'id') { + if ('id' === $aName) { $ele->setIdAttribute('id', true); } } - // Some elements have special processing rules. Handle those separately. - if ($this->rules->hasRules($name) && $this->frag !== $this->current) { + if ($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); - } // Otherwise, it's a standard element. - else { + } else { + // Otherwise, it's a standard element. $this->current->appendChild($ele); - if (! Elements::isA($name, Elements::VOID_TAG)) { + if (!Elements::isA($name, Elements::VOID_TAG)) { $this->current = $ele; } @@ -448,7 +452,7 @@ class DOMTreeBuilder implements EventHandler // This is sort of a last-ditch attempt to correct for cases where no head/body // elements are provided. - if ($this->insertMode <= static::IM_BEFORE_HEAD && $name != 'head' && $name != 'html') { + if ($this->insertMode <= static::IM_BEFORE_HEAD && 'head' !== $name && 'html' !== $name) { $this->insertMode = static::IM_IN_BODY; } @@ -456,7 +460,7 @@ class DOMTreeBuilder implements EventHandler // 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; $i ++) { + for ($i = 0; $i < $pushes; ++$i) { array_shift($this->nsStack); } } @@ -485,7 +489,7 @@ class DOMTreeBuilder implements EventHandler 'html', 'br', 'head', - 'title' + 'title', ))) { $this->startTag('html'); $this->endTag($name); @@ -495,13 +499,13 @@ class DOMTreeBuilder implements EventHandler } // Ignore the tag. - $this->parseError("Illegal closing tag at global scope."); + $this->parseError('Illegal closing tag at global scope.'); return; } // Special case handling for SVG. - if ($this->insertMode == static::IM_IN_SVG) { + if ($this->insertMode === static::IM_IN_SVG) { $lname = Elements::normalizeSvgElement($lname); } @@ -512,39 +516,33 @@ class DOMTreeBuilder implements EventHandler $cid = spl_object_hash($this->current); } - // XXX: Not sure whether we need this anymore. - // if ($name != $lname) { - // return $this->quirksTreeResolver($lname); - // } - // XXX: HTML has no parent. What do we do, though, // if this element appears in the wrong place? - if ($lname == 'html') { + if ('html' === $lname) { return; } // remove the namespaced definded by current node if (isset($this->pushes[$cid])) { - for ($i = 0; $i < $this->pushes[$cid][0]; $i ++) { + for ($i = 0; $i < $this->pushes[$cid][0]; ++$i) { array_shift($this->nsStack); } unset($this->pushes[$cid]); } - if (! $this->autoclose($lname)) { + if (!$this->autoclose($lname)) { $this->parseError('Could not find closing tag for ' . $lname); } - // switch ($this->insertMode) { switch ($lname) { - case "head": + case 'head': $this->insertMode = static::IM_AFTER_HEAD; break; - case "body": + case 'body': $this->insertMode = static::IM_AFTER_BODY; break; - case "svg": - case "mathml": + case 'svg': + case 'mathml': $this->insertMode = static::IM_IN_BODY; break; } @@ -566,9 +564,9 @@ class DOMTreeBuilder implements EventHandler // 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($dataTmp)) { + if (!empty($dataTmp)) { // fprintf(STDOUT, "Unexpected insert mode: %d", $this->insertMode); - $this->parseError("Unexpected text. Ignoring: " . $dataTmp); + $this->parseError('Unexpected text. Ignoring: ' . $dataTmp); } return; @@ -585,7 +583,7 @@ class DOMTreeBuilder implements EventHandler public function parseError($msg, $line = 0, $col = 0) { - $this->errors[] = sprintf("Line %d, Col %d: %s", $line, $col, $msg); + $this->errors[] = sprintf('Line %d, Col %d: %s', $line, $col, $msg); } public function getErrors() @@ -602,15 +600,14 @@ class DOMTreeBuilder implements EventHandler public function processingInstruction($name, $data = null) { // XXX: Ignore initial XML declaration, per the spec. - if ($this->insertMode == static::IM_INITIAL && 'xml' == strtolower($name)) { + if ($this->insertMode === static::IM_INITIAL && 'xml' === strtolower($name)) { return; } - // Important: The processor may modify the current DOM tree however - // it sees fit. - if (isset($this->processor)) { + // 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)) { + if (!empty($res)) { $this->current = $res; } @@ -629,24 +626,23 @@ class DOMTreeBuilder implements EventHandler /** * Apply normalization rules to a tag name. - * * See sections 2.9 and 8.1.2. * - * @param string $name - * The tag name. + * @param string $tagName + * * @return string The normalized tag name. */ - protected function normalizeTagName($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 $name; + return $tagName; } protected function quirksTreeResolver($name) { - throw new \Exception("Not implemented."); + throw new \Exception('Not implemented.'); } /** @@ -660,15 +656,16 @@ class DOMTreeBuilder implements EventHandler { $working = $this->current; do { - if ($working->nodeType != XML_ELEMENT_NODE) { + if (XML_ELEMENT_NODE !== $working->nodeType) { return false; } - if ($working->tagName == $tagName) { + if ($working->tagName === $tagName) { $this->current = $working->parentNode; return true; } } while ($working = $working->parentNode); + return false; } @@ -685,8 +682,8 @@ class DOMTreeBuilder implements EventHandler protected function isAncestor($tagName) { $candidate = $this->current; - while ($candidate->nodeType === XML_ELEMENT_NODE) { - if ($candidate->tagName == $tagName) { + while (XML_ELEMENT_NODE === $candidate->nodeType) { + if ($candidate->tagName === $tagName) { return true; } $candidate = $candidate->parentNode; @@ -704,6 +701,6 @@ class DOMTreeBuilder implements EventHandler */ protected function isParent($tagName) { - return $this->current->tagName == $tagName; + return $this->current->tagName === $tagName; } } diff --git a/src/HTML5/Parser/EventHandler.php b/src/HTML5/Parser/EventHandler.php index 3da71a3..9893a71 100644 --- a/src/HTML5/Parser/EventHandler.php +++ b/src/HTML5/Parser/EventHandler.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Parser; /** @@ -20,7 +21,6 @@ namespace Masterminds\HTML5\Parser; */ interface EventHandler { - const DOCTYPE_NONE = 0; const DOCTYPE_PUBLIC = 1; @@ -30,15 +30,11 @@ interface EventHandler /** * 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 boolean $quirks - * Indicates whether the builder should enter quirks mode. + * @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); @@ -63,13 +59,11 @@ interface EventHandler * 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 boolean $selfClosing - * An indicator of whether or not this tag is self-closing (<foo/>) - * @return int One of the Tokenizer::TEXTMODE_* constants. + * @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); @@ -104,7 +98,7 @@ interface EventHandler * A CDATA section. * * @param string $data - * The unparsed character data. + * The unparsed character data */ public function cdata($data); @@ -113,10 +107,8 @@ interface EventHandler * * 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. + * @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/src/HTML5/Parser/FileInputStream.php b/src/HTML5/Parser/FileInputStream.php index 76bd17b..b081ed9 100644 --- a/src/HTML5/Parser/FileInputStream.php +++ b/src/HTML5/Parser/FileInputStream.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Parser; /** @@ -18,9 +19,9 @@ class FileInputStream extends StringInputStream implements InputStream /** * Load a file input stream. * - * @param string $data The file or url path to load. + * @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. + * @param string $debug A fprintf format to use to echo the data on stdout. */ public function __construct($data, $encoding = 'UTF-8', $debug = '') { diff --git a/src/HTML5/Parser/InputStream.php b/src/HTML5/Parser/InputStream.php index e4a106a..ff4ef22 100644 --- a/src/HTML5/Parser/InputStream.php +++ b/src/HTML5/Parser/InputStream.php @@ -49,12 +49,12 @@ interface InputStream extends \Iterator * and returns the matched substring. * * @see strcspn - * @param string $bytes - * Bytes to match. - * @param int $max - * Maximum number of bytes to scan. + * + * @param string $bytes Bytes to match. + * @param int $max Maximum number of bytes to scan. + * * @return mixed Index or false if no match is found. You should use strong - * equality when checking the result, since index could be 0. + * equality when checking the result, since index could be 0. */ public function charsUntil($bytes, $max = null); @@ -65,20 +65,18 @@ interface InputStream extends \Iterator * 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. + * + * @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. + * @param int $howMany The number of characters to move the pointer back. */ public function unconsume($howMany = 1); diff --git a/src/HTML5/Parser/ParseError.php b/src/HTML5/Parser/ParseError.php index 86498a1..640e516 100644 --- a/src/HTML5/Parser/ParseError.php +++ b/src/HTML5/Parser/ParseError.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Parser; /** diff --git a/src/HTML5/Parser/Scanner.php b/src/HTML5/Parser/Scanner.php index cec9a13..1b52983 100644 --- a/src/HTML5/Parser/Scanner.php +++ b/src/HTML5/Parser/Scanner.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Parser; use Masterminds\HTML5\Exception; @@ -18,7 +19,7 @@ class Scanner private $data; /** - * The current integer byte position we are in $data + * The current integer byte position we are in $data. */ private $char; @@ -35,7 +36,7 @@ class Scanner /** * Create a new Scanner. * - * @param string $data Data to parse + * @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. @@ -75,14 +76,15 @@ class Scanner * '</script>' string. * * @param string $sequence - * @param bool $caseSensitive + * @param bool $caseSensitive * * @return bool */ public function sequenceMatches($sequence, $caseSensitive = true) { $portion = substr($this->data, $this->char, strlen($sequence)); - return $caseSensitive ? $portion === $sequence : strcasecmp($portion, $sequence) === 0; + + return $caseSensitive ? $portion === $sequence : 0 === strcasecmp($portion, $sequence); } /** @@ -111,14 +113,13 @@ class Scanner /** * Get the next character. - * * Note: This advances the pointer. * * @return string The next character. */ public function next() { - $this->char++; + ++$this->char; if ($this->char < $this->EOF) { return $this->data[$this->char]; @@ -129,7 +130,6 @@ class Scanner /** * Get the current character. - * * Note, this does not advance the pointer. * * @return string The current character. @@ -157,19 +157,17 @@ class Scanner * Unconsume some of the data. * This moves the data pointer backwards. * - * @param int $howMany - * The number of characters to move the pointer back. + * @param int $howMany The number of characters to move the pointer back. */ public function unconsume($howMany = 1) { if (($this->char - $howMany) >= 0) { - $this->char = $this->char - $howMany; + $this->char -= $howMany; } } /** * Get the next group of that contains hex characters. - * * Note, along with getting the characters the pointer in the data will be * moved as well. * @@ -182,7 +180,6 @@ class Scanner /** * Get the next group of characters that are ASCII Alpha characters. - * * Note, along with getting the characters the pointer in the data will be * moved as well. * @@ -195,7 +192,6 @@ class Scanner /** * Get the next group of characters that are ASCII Alpha characters and numbers. - * * Note, along with getting the characters the pointer in the data will be * moved as well. * @@ -208,7 +204,6 @@ class Scanner /** * Get the next group of numbers. - * * Note, along with getting the characters the pointer in the data will be * moved as well. * @@ -221,10 +216,9 @@ class Scanner /** * Consume whitespace. - * * Whitespace in HTML5 is: formfeed, tab, newline, space. * - * @return int The length of the matched whitespaces + * @return int The length of the matched whitespaces. */ public function whitespace() { @@ -246,7 +240,7 @@ class Scanner */ public function currentLine() { - if (empty($this->EOF) || $this->char == 0) { + if (empty($this->EOF) || 0 === $this->char) { return 1; } @@ -289,7 +283,7 @@ class Scanner public function columnOffset() { // Short circuit for the first char. - if ($this->char == 0) { + if (0 === $this->char) { return 0; } @@ -303,7 +297,7 @@ class Scanner // However, for here we want the length up until the next byte to be // processed, so add one to the current byte ($this->char). - if ($lastLine !== false) { + if (false !== $lastLine) { $findLengthOf = substr($this->data, $lastLine + 1, $this->char - 1 - $lastLine); } else { // After a newline. @@ -351,7 +345,7 @@ class Scanner $crlfTable = array( "\0" => "\xEF\xBF\xBD", "\r\n" => "\n", - "\r" => "\n" + "\r" => "\n", ); return strtr($data, $crlfTable); @@ -365,12 +359,11 @@ class Scanner * 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. + * @param string $bytes Bytes to match. + * @param int $max Maximum number of bytes to scan. + * * @return mixed Index or false if no match is found. You should use strong - * equality when checking the result, since index could be 0. + * equality when checking the result, since index could be 0. */ private function doCharsUntil($bytes, $max = null) { @@ -378,7 +371,7 @@ class Scanner return false; } - if ($max === 0 || $max) { + if (0 === $max || $max) { $len = strcspn($this->data, $bytes, $this->char, $max); } else { $len = strcspn($this->data, $bytes, $this->char); @@ -396,12 +389,10 @@ class Scanner * 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. + * @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 $max The max number of chars to read. * * @return string */ @@ -411,7 +402,7 @@ class Scanner return false; } - if ($max === 0 || $max) { + if (0 === $max || $max) { $len = strspn($this->data, $bytes, $this->char, $max); } else { $len = strspn($this->data, $bytes, $this->char); diff --git a/src/HTML5/Parser/StringInputStream.php b/src/HTML5/Parser/StringInputStream.php index 0118468..0c213fe 100644 --- a/src/HTML5/Parser/StringInputStream.php +++ b/src/HTML5/Parser/StringInputStream.php @@ -2,6 +2,7 @@ /** * Loads a string to be parsed. */ + namespace Masterminds\HTML5\Parser; /* @@ -50,7 +51,7 @@ class StringInputStream implements InputStream private $data; /** - * The current integer byte position we are in $data + * The current integer byte position we are in $data. */ private $char; @@ -67,9 +68,9 @@ class StringInputStream implements InputStream /** * Create a new InputStream wrapper. * - * @param string $data Data to parse + * @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. + * @param string $debug A fprintf format to use to echo the data on stdout. */ public function __construct($data, $encoding = 'UTF-8', $debug = '') { @@ -110,7 +111,7 @@ class StringInputStream implements InputStream $crlfTable = array( "\0" => "\xEF\xBF\xBD", "\r\n" => "\n", - "\r" => "\n" + "\r" => "\n", ); return strtr($data, $crlfTable); @@ -121,7 +122,7 @@ class StringInputStream implements InputStream */ public function currentLine() { - if (empty($this->EOF) || $this->char == 0) { + if (empty($this->EOF) || 0 === $this->char) { return 1; } // Add one to $this->char because we want the number for the next @@ -130,9 +131,7 @@ class StringInputStream implements InputStream } /** - * * @deprecated - * */ public function getCurrentLine() { @@ -141,7 +140,6 @@ class StringInputStream implements InputStream /** * Returns the current column of the current line that the tokenizer is at. - * * Newlines are column 0. The first char after a newline is column 1. * * @return int The column number. @@ -149,7 +147,7 @@ class StringInputStream implements InputStream public function columnOffset() { // Short circuit for the first char. - if ($this->char == 0) { + if (0 === $this->char) { return 0; } // strrpos is weird, and the offset needs to be negative for what we @@ -162,7 +160,7 @@ class StringInputStream implements InputStream // However, for here we want the length up until the next byte to be // processed, so add one to the current byte ($this->char). - if ($lastLine !== false) { + if (false !== $lastLine) { $findLengthOf = substr($this->data, $lastLine + 1, $this->char - 1 - $lastLine); } else { // After a newline. @@ -173,9 +171,7 @@ class StringInputStream implements InputStream } /** - * * @deprecated - * */ public function getColumnOffset() { @@ -198,7 +194,7 @@ class StringInputStream implements InputStream */ public function next() { - $this->char ++; + ++$this->char; } /** @@ -212,15 +208,11 @@ class StringInputStream implements InputStream /** * Is the current pointer location valid. * - * @return bool Is the current pointer location valid. + * @return bool Whether the current pointer location is valid. */ public function valid() { - if ($this->char < $this->EOF) { - return true; - } - - return false; + return $this->char < $this->EOF; } /** @@ -229,10 +221,10 @@ class StringInputStream implements InputStream * This reads to the end of the file, and sets the read marker at the * end of the file. * - * @note This performs bounds checking + * Note this performs bounds checking. * * @return string Returns the remaining text. If called when the InputStream is - * already exhausted, it returns an empty string. + * already exhausted, it returns an empty string. */ public function remainingChars() { @@ -254,12 +246,11 @@ class StringInputStream implements InputStream * 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. + * @param string $bytes Bytes to match. + * @param int $max Maximum number of bytes to scan. + * * @return mixed Index or false if no match is found. You should use strong - * equality when checking the result, since index could be 0. + * equality when checking the result, since index could be 0. */ public function charsUntil($bytes, $max = null) { @@ -267,7 +258,7 @@ class StringInputStream implements InputStream return false; } - if ($max === 0 || $max) { + if (0 === $max || $max) { $len = strcspn($this->data, $bytes, $this->char, $max); } else { $len = strcspn($this->data, $bytes, $this->char); @@ -285,12 +276,10 @@ class StringInputStream implements InputStream * 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. + * @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 $max The max number of chars to read. * * @return string */ @@ -300,7 +289,7 @@ class StringInputStream implements InputStream return false; } - if ($max === 0 || $max) { + if (0 === $max || $max) { $len = strspn($this->data, $bytes, $this->char, $max); } else { $len = strspn($this->data, $bytes, $this->char); @@ -314,13 +303,12 @@ class StringInputStream implements InputStream /** * Unconsume characters. * - * @param int $howMany - * The number of characters to unconsume. + * @param int $howMany The number of characters to unconsume. */ public function unconsume($howMany = 1) { if (($this->char - $howMany) >= 0) { - $this->char = $this->char - $howMany; + $this->char -= $howMany; } } diff --git a/src/HTML5/Parser/Tokenizer.php b/src/HTML5/Parser/Tokenizer.php index ba9de52..6284733 100644 --- a/src/HTML5/Parser/Tokenizer.php +++ b/src/HTML5/Parser/Tokenizer.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Parser; use Masterminds\HTML5\Elements; @@ -25,7 +26,6 @@ use Masterminds\HTML5\Elements; */ class Tokenizer { - protected $scanner; protected $events; @@ -56,12 +56,9 @@ class Tokenizer * it a scanner (input) and an event handler (output), and then calling * the Tokenizer::parse() method.` * - * @param \Masterminds\HTML5\Parser\Scanner $scanner - * A scanner initialized with an input stream. - * @param \Masterminds\HTML5\Parser\EventHandler $eventHandler - * An event handler, initialized and ready to receive - * events. - * @param string $mode + * @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) { @@ -103,11 +100,9 @@ class Tokenizer * 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 integer $textmode - * One of Elements::TEXT_* - * @param string $untilTag - * The tag that should stop RAW or RCDATA mode. Normal mode does not - * use this indicator. + * @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) { @@ -117,13 +112,13 @@ class Tokenizer /** * Consume a character and make a move. - * HTML5 8.2.4.1 + * HTML5 8.2.4.1. */ protected function consumeData() { $tok = $this->scanner->current(); - if ($tok === '&') { + if ('&' === $tok) { // Character reference $ref = $this->decodeCharacterReference(); $this->buffer($ref); @@ -132,7 +127,7 @@ class Tokenizer } // Parse tag - if ($tok === '<') { + if ('<' === $tok) { // Any buffered text data can go out now. $this->flushBuffer(); @@ -143,7 +138,7 @@ class Tokenizer || $this->processingInstruction() || $this->tagName() // This always returns false. - || $this->parseError("Illegal tag opening") + || $this->parseError('Illegal tag opening') || $this->characterData(); $tok = $this->scanner->current(); @@ -153,7 +148,7 @@ class Tokenizer $this->eof($tok); // Parse character - if ($tok !== false) { + if (false !== $tok) { switch ($this->textMode) { case Elements::TEXT_RAW: $this->rawText($tok); @@ -164,10 +159,10 @@ class Tokenizer break; default: - if (!strspn($tok, "<&")) { + if (!strspn($tok, '<&')) { // NULL character - if ($tok === "\00") { - $this->parseError("Received null character."); + if ("\00" === $tok) { + $this->parseError('Received null character.'); } $this->text .= $tok; @@ -189,7 +184,7 @@ class Tokenizer protected function characterData() { $tok = $this->scanner->current(); - if ($tok === false) { + if (false === $tok) { return false; } switch ($this->textMode) { @@ -198,9 +193,10 @@ class Tokenizer case Elements::TEXT_RCDATA: return $this->rcdata($tok); default: - if (strspn($tok, "<&")) { + if (strspn($tok, '<&')) { return false; } + return $this->text($tok); } } @@ -215,13 +211,13 @@ class Tokenizer protected function text($tok) { // This should never happen... - if ($tok === false) { + if (false === $tok) { return false; } // NULL character - if ($tok === "\00") { - $this->parseError("Received null character."); + if ("\00" === $tok) { + $this->parseError('Received null character.'); } $this->buffer($tok); @@ -268,8 +264,8 @@ class Tokenizer $txt = ''; $caseSensitive = !Elements::isHtml5Element($this->untilTag); - while ($tok !== false && ! ($tok == '<' && ($this->scanner->sequenceMatches($sequence, $caseSensitive)))) { - if ($tok == '&') { + while (false !== $tok && !('<' == $tok && ($this->scanner->sequenceMatches($sequence, $caseSensitive)))) { + if ('&' == $tok) { $txt .= $this->decodeCharacterReference(); $tok = $this->scanner->current(); } else { @@ -280,8 +276,8 @@ class Tokenizer $len = strlen($sequence); $this->scanner->consume($len); $len += $this->scanner->whitespace(); - if ($this->scanner->current() !== '>') { - $this->parseError("Unclosed RCDATA end tag"); + if ('>' !== $this->scanner->current()) { + $this->parseError('Unclosed RCDATA end tag'); } $this->scanner->unconsume($len); @@ -296,7 +292,7 @@ class Tokenizer */ protected function eof($tok) { - if ($tok === false) { + if (false === $tok) { // fprintf(STDOUT, "EOF"); $this->flushBuffer(); $this->events->eof(); @@ -313,40 +309,36 @@ class Tokenizer */ protected function markupDeclaration($tok) { - if ($tok != '!') { + if ('!' != $tok) { return false; } $tok = $this->scanner->next(); // Comment: - if ($tok == '-' && $this->scanner->peek() == '-') { + if ('-' == $tok && '-' == $this->scanner->peek()) { $this->scanner->next(); // Consume the other '-' $this->scanner->next(); // Next char. return $this->comment(); - } - - elseif ($tok == 'D' || $tok == 'd') { // Doctype + } elseif ('D' == $tok || 'd' == $tok) { // Doctype return $this->doctype(); - } - - elseif ($tok == '[') { // CDATA section + } elseif ('[' == $tok) { // CDATA section return $this->cdataSection(); } // FINISH - $this->parseError("Expected <!--, <![CDATA[, or <!DOCTYPE. Got <!%s", $tok); + $this->parseError('Expected <!--, <![CDATA[, or <!DOCTYPE. Got <!%s', $tok); $this->bogusComment('<!'); + return true; } /** - * Consume an end tag. - * 8.2.4.9 + * Consume an end tag. See section 8.2.4.9. */ protected function endTag() { - if ($this->scanner->current() != '/') { + if ('/' != $this->scanner->current()) { return false; } $tok = $this->scanner->next(); @@ -355,21 +347,22 @@ class Tokenizer // > -> parse error // EOF -> parse error // -> parse error - if (! ctype_alpha($tok)) { + if (!ctype_alpha($tok)) { $this->parseError("Expected tag name, got '%s'", $tok); - if ($tok == "\0" || $tok === false) { + if ("\0" == $tok || false === $tok) { return false; } + return $this->bogusComment('</'); } $name = $this->scanner->charsUntil("\n\f \t>"); - $name = $this->mode === self::CONFORMANT_XML ? $name: strtolower($name); + $name = self::CONFORMANT_XML === $this->mode ? $name : strtolower($name); // Trash whitespace. $this->scanner->whitespace(); $tok = $this->scanner->current(); - if ($tok != '>') { + if ('>' != $tok) { $this->parseError("Expected >, got '%s'", $tok); // We just trash stuff until we get to the next tag close. $this->scanner->charsUntil('>'); @@ -377,23 +370,23 @@ class Tokenizer $this->events->endTag($name); $this->scanner->next(); + return true; } /** - * Consume a tag name and body. - * 8.2.4.10 + * Consume a tag name and body. See section 8.2.4.10. */ protected function tagName() { $tok = $this->scanner->current(); - if (! ctype_alpha($tok)) { + if (!ctype_alpha($tok)) { return false; } // We know this is at least one char. - $name = $this->scanner->charsWhile(":_-0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"); - $name = $this->mode === self::CONFORMANT_XML ? $name : strtolower($name); + $name = $this->scanner->charsWhile(':_-0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'); + $name = self::CONFORMANT_XML === $this->mode ? $name : strtolower($name); $attributes = array(); $selfClose = false; @@ -403,7 +396,7 @@ class Tokenizer do { $this->scanner->whitespace(); $this->attribute($attributes); - } while (! $this->isTagEnd($selfClose)); + } while (!$this->isTagEnd($selfClose)); } catch (ParseError $e) { $selfClose = false; } @@ -425,30 +418,34 @@ class Tokenizer protected function isTagEnd(&$selfClose) { $tok = $this->scanner->current(); - if ($tok == '/') { + if ('/' == $tok) { $this->scanner->next(); $this->scanner->whitespace(); $tok = $this->scanner->current(); - if ($tok == '>') { + if ('>' == $tok) { $selfClose = true; + return true; } - if ($tok === false) { - $this->parseError("Unexpected EOF inside of tag."); + 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 == '>') { + if ('>' == $tok) { return true; } - if ($tok === false) { - $this->parseError("Unexpected EOF inside of tag."); + if (false === $tok) { + $this->parseError('Unexpected EOF inside of tag.'); + return true; } @@ -467,23 +464,23 @@ class Tokenizer protected function attribute(&$attributes) { $tok = $this->scanner->current(); - if ($tok == '/' || $tok == '>' || $tok === false) { + if ('/' == $tok || '>' == $tok || false === $tok) { return false; } - if ($tok == '<') { + 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."); + throw new ParseError('Start tag inside of attribute.'); } $name = strtolower($this->scanner->charsUntil("/>=\n\f\t ")); - if (strlen($name) == 0) { + if (0 == strlen($name)) { $tok = $this->scanner->current(); - $this->parseError("Expected an attribute name, got %s.", $tok); + $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; @@ -497,18 +494,17 @@ class Tokenizer // 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); + $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 - else - if (preg_match("/^[0-9.-]/u", $name)) { - $this->parseError("Unexpected character at the begining of attribute name: %s", $name); - $isValidAttribute = false; - } + 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 $this->scanner->whitespace(); @@ -516,18 +512,18 @@ class Tokenizer if ($isValidAttribute) { $attributes[$name] = $val; } + return true; } /** - * Consume an attribute value. - * 8.2.4.37 and after. + * Consume an attribute value. See section 8.2.4.37 and after. * * @return string|null */ protected function attributeValue() { - if ($this->scanner->current() != '=') { + if ('=' != $this->scanner->current()) { return null; } $this->scanner->next(); @@ -538,21 +534,24 @@ class Tokenizer switch ($tok) { case "\n": case "\f": - case " ": + case ' ': case "\t": // Whitespace here indicates an empty value. return null; case '"': case "'": $this->scanner->next(); + 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."); + $this->parseError('Expected attribute value, got tag end.'); + return null; case '=': case '`': - $this->parseError("Expecting quotes, got %s.", $tok); + $this->parseError('Expecting quotes, got %s.', $tok); + return $this->unquotedAttributeValue(); default: return $this->unquotedAttributeValue(); @@ -562,10 +561,10 @@ class Tokenizer /** * 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 ". + * @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) @@ -574,21 +573,22 @@ class Tokenizer $val = ''; while (true) { - $tokens = $this->scanner->charsUntil($stoplist.'&'); - if ($tokens !== false) { + $tokens = $this->scanner->charsUntil($stoplist . '&'); + if (false !== $tokens) { $val .= $tokens; } else { break; } $tok = $this->scanner->current(); - if ($tok == '&') { + if ('&' == $tok) { $val .= $this->decodeCharacterReference(true); continue; } break; } $this->scanner->next(); + return $val; } @@ -597,34 +597,33 @@ class Tokenizer $stoplist = "\t\n\f >"; $val = ''; $tok = $this->scanner->current(); - while (strspn($tok, $stoplist) == 0 && $tok !== false) { - if ($tok == '&') { + while (0 == strspn($tok, $stoplist) && false !== $tok) { + if ('&' == $tok) { $val .= $this->decodeCharacterReference(true); $tok = $this->scanner->current(); } else { if (strspn($tok, "\"'<=`") > 0) { - $this->parseError("Unexpected chars in unquoted attribute value %s", $tok); + $this->parseError('Unexpected chars in unquoted attribute value %s', $tok); } $val .= $tok; $tok = $this->scanner->next(); } } + return $val; } /** * Consume malformed markup as if it were a comment. - * 8.2.4.44 + * 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. + * @param string $leading Prepend any leading characters. This essentially + * negates the need to backtrack, but it's sort of a hack. * * @return bool */ @@ -632,11 +631,11 @@ class Tokenizer { $comment = $leading; $tokens = $this->scanner->charsUntil('>'); - if ($tokens !== false) { + if (false !== $tokens) { $comment .= $tokens; } $tok = $this->scanner->current(); - if ($tok !== false) { + if (false !== $tok) { $comment .= $tok; } @@ -649,7 +648,6 @@ class Tokenizer /** * Read a comment. - * * Expects the first tok to be inside of the comment. * * @return bool @@ -660,25 +658,27 @@ class Tokenizer $comment = ''; // <!-->. Emit an empty comment because 8.2.4.46 says to. - if ($tok == '>') { + if ('>' == $tok) { // Parse error. Emit the comment token. $this->parseError("Expected comment data, got '>'"); $this->events->comment(''); $this->scanner->next(); + return true; } // Replace NULL with the replacement char. - if ($tok == "\0") { + if ("\0" == $tok) { $tok = UTF8Utils::FFFD; } - while (! $this->isCommentEnd()) { + while (!$this->isCommentEnd()) { $comment .= $tok; $tok = $this->scanner->next(); } $this->events->comment($comment); $this->scanner->next(); + return true; } @@ -692,24 +692,26 @@ class Tokenizer $tok = $this->scanner->current(); // EOF - if ($tok === false) { + if (false === $tok) { // Hit the end. - $this->parseError("Unexpected EOF in a comment."); + $this->parseError('Unexpected EOF in a comment.'); + return true; } // If it doesn't start with -, not the end. - if ($tok != '-') { + if ('-' != $tok) { return false; } // Advance one, and test for '->' - if ($this->scanner->next() == '-' && $this->scanner->peek() == '>') { + if ('-' == $this->scanner->next() && '>' == $this->scanner->peek()) { $this->scanner->next(); // Consume the last '>' return true; } // Unread '-'; $this->scanner->unconsume(1); + return false; } @@ -729,9 +731,10 @@ class Tokenizer return false; } // Check that string is DOCTYPE. - $chars = $this->scanner->charsWhile("DOCTYPEdoctype"); + $chars = $this->scanner->charsWhile('DOCTYPEdoctype'); if (strcasecmp($chars, 'DOCTYPE')) { $this->parseError('Expected DOCTYPE, got %s', $chars); + return $this->bogusComment('<!' . $chars); } @@ -739,14 +742,15 @@ class Tokenizer $tok = $this->scanner->current(); // EOF: die. - if ($tok === false) { + if (false === $tok) { $this->events->doctype('html5', EventHandler::DOCTYPE_NONE, '', true); + return $this->eof($tok); } // NULL char: convert. - if ($tok === "\0") { - $this->parseError("Unexpected null character in DOCTYPE."); + if ("\0" === $tok) { + $this->parseError('Unexpected null character in DOCTYPE.'); } $stop = " \n\f>"; @@ -757,23 +761,26 @@ class Tokenizer $tok = $this->scanner->current(); // If false, emit a parse error, DOCTYPE, and return. - if ($tok === false) { + 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 == '>') { + if ('>' == $tok) { // DOCTYPE without a name. - if (strlen($doctypeName) == 0) { - $this->parseError("Expected a DOCTYPE name. Got nothing."); + if (0 == strlen($doctypeName)) { + $this->parseError('Expected a DOCTYPE name. Got nothing.'); $this->events->doctype($doctypeName, 0, null, true); $this->scanner->next(); + return true; } $this->events->doctype($doctypeName); $this->scanner->next(); + return true; } $this->scanner->whitespace(); @@ -782,36 +789,40 @@ class Tokenizer $white = $this->scanner->whitespace(); // Get ID, and flag it as pub or system. - if (($pub == 'PUBLIC' || $pub == 'SYSTEM') && $white > 0) { + if (('PUBLIC' == $pub || 'SYSTEM' == $pub) && $white > 0) { // Get the sys ID. - $type = $pub == 'PUBLIC' ? EventHandler::DOCTYPE_PUBLIC : EventHandler::DOCTYPE_SYSTEM; + $type = 'PUBLIC' == $pub ? EventHandler::DOCTYPE_PUBLIC : EventHandler::DOCTYPE_SYSTEM; $id = $this->quotedString("\0>"); - if ($id === false) { + if (false === $id) { $this->events->doctype($doctypeName, $type, $pub, false); + return false; } // Premature EOF. - if ($this->scanner->current() === false) { - $this->parseError("Unexpected EOF in DOCTYPE"); + 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() == '>') { + if ('>' == $this->scanner->current()) { $this->events->doctype($doctypeName, $type, $id, false); $this->scanner->next(); + 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->scanner->charsUntil('>'); + $this->parseError('Malformed DOCTYPE.'); $this->events->doctype($doctypeName, $type, $id, true); $this->scanner->next(); + return true; } @@ -819,35 +830,37 @@ class Tokenizer // Consume to > and trash. $this->scanner->charsUntil('>'); - $this->parseError("Expected PUBLIC or SYSTEM. Got %s.", $pub); + $this->parseError('Expected PUBLIC or SYSTEM. Got %s.', $pub); $this->events->doctype($doctypeName, 0, null, true); $this->scanner->next(); + 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 "'". + * @param string $stopchars Characters (in addition to a close-quote) that should stop the string. + * E.g. sometimes '>' is higher precedence than '"' or "'". * - * @return mixed String if one is found (quotations omitted) + * @return mixed String if one is found (quotations omitted). */ protected function quotedString($stopchars) { $tok = $this->scanner->current(); - if ($tok == '"' || $tok == "'") { + if ('"' == $tok || "'" == $tok) { $this->scanner->next(); $ret = $this->scanner->charsUntil($tok . $stopchars); if ($this->scanner->current() == $tok) { $this->scanner->next(); } else { // Parse error because no close quote. - $this->parseError("Expected %s, got %s", $tok, $this->scanner->current()); + $this->parseError('Expected %s, got %s', $tok, $this->scanner->current()); } + return $ret; } + return false; } @@ -858,39 +871,43 @@ class Tokenizer */ protected function cdataSection() { - if ($this->scanner->current() != '[') { + if ('[' != $this->scanner->current()) { return false; } $cdata = ''; $this->scanner->next(); $chars = $this->scanner->charsWhile('CDAT'); - if ($chars != 'CDATA' || $this->scanner->current() != '[') { + if ('CDATA' != $chars || '[' != $this->scanner->current()) { $this->parseError('Expected [CDATA[, got %s', $chars); + return $this->bogusComment('<![' . $chars); } $tok = $this->scanner->next(); do { - if ($tok === false) { + if (false === $tok) { $this->parseError('Unexpected EOF inside CDATA.'); $this->bogusComment('<![CDATA[' . $cdata); + return true; } $cdata .= $tok; $tok = $this->scanner->next(); - } while (! $this->scanner->sequenceMatches(']]>')); + } while (!$this->scanner->sequenceMatches(']]>')); // Consume ]]> $this->scanner->consume(3); $this->events->cdata($cdata); + return true; } // ================================================================ // Non-HTML5 // ================================================================ + /** * Handle a processing instruction. * @@ -903,7 +920,7 @@ class Tokenizer */ protected function processingInstruction() { - if ($this->scanner->current() != '?') { + if ('?' != $this->scanner->current()) { return false; } @@ -912,21 +929,23 @@ class Tokenizer $white = $this->scanner->whitespace(); // If not a PI, send to bogusComment. - if (strlen($procName) == 0 || $white == 0 || $this->scanner->current() == false) { + if (0 == strlen($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() == '>')) { + while (!('?' == $this->scanner->current() && '>' == $this->scanner->peek())) { $data .= $this->scanner->current(); $tok = $this->scanner->next(); - if ($tok === false) { - $this->parseError("Unexpected EOF in processing instruction."); + if (false === $tok) { + $this->parseError('Unexpected EOF in processing instruction.'); $this->events->processingInstruction($procName, $data); + return true; } } @@ -934,6 +953,7 @@ class Tokenizer $this->scanner->next(); // > $this->scanner->next(); // Next token. $this->events->processingInstruction($procName, $data); + return true; } @@ -955,7 +975,7 @@ class Tokenizer // Optimization for reading larger blocks faster. $first = substr($sequence, 0, 1); - while ($this->scanner->current() !== false) { + while (false !== $this->scanner->current()) { $buffer .= $this->scanner->charsUntil($first); // Stop as soon as we hit the stopping condition. @@ -967,7 +987,8 @@ class Tokenizer } // If we get here, we hit the EOF. - $this->parseError("Unexpected EOF during text read."); + $this->parseError('Unexpected EOF during text read.'); + return $buffer; } @@ -985,7 +1006,7 @@ class Tokenizer * '</script>' string. * * @param string $sequence - * @param bool $caseSensitive + * @param bool $caseSensitive * * @return bool */ @@ -1005,7 +1026,7 @@ class Tokenizer */ protected function flushBuffer() { - if ($this->text === '') { + if ('' === $this->text) { return; } $this->events->text($this->text); @@ -1055,9 +1076,8 @@ class Tokenizer * * 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. + * @param bool $inAttribute Set to true if the text is inside of an attribute value. + * false otherwise. * * @return string */ @@ -1067,36 +1087,37 @@ class Tokenizer $tok = $this->scanner->next(); $start = $this->scanner->position(); - if ($tok == false) { + if (false === $tok) { return '&'; } // These indicate not an entity. We return just // the &. - if (strspn($tok, static::WHITE . "&<") == 1) { + if (1 === strspn($tok, static::WHITE . '&<')) { // $this->scanner->next(); return '&'; } // Numeric entity - if ($tok == '#') { + if ('#' === $tok) { $tok = $this->scanner->next(); // Hexidecimal encoding. // X[0-9a-fA-F]+; // x[0-9a-fA-F]+; - if ($tok == 'x' || $tok == 'X') { + 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); + $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); @@ -1105,17 +1126,17 @@ class Tokenizer else { // Convert from decimal to char. $numeric = $this->scanner->getNumeric(); - if ($numeric === false) { - $this->parseError("Expected &#DIGITS;, got &#%s", $tok); + if (false === $numeric) { + $this->parseError('Expected &#DIGITS;, got &#%s', $tok); $this->scanner->unconsume(2); + return '&'; } $entity = CharacterReference::lookupDecimal($numeric); } - } elseif ($tok === '=' && $inAttribute) { + } elseif ('=' === $tok && $inAttribute) { return '&'; } else { // String entity. - // Attempt to consume a string up to a ';'. // [a-zA-Z0-9]+; $cname = $this->scanner->getAsciiAlphaNum(); @@ -1124,11 +1145,12 @@ class Tokenizer // When no entity is found provide the name of the unmatched string // and continue on as the & is not part of an entity. The & will // be converted to & elsewhere. - if ($entity == null) { - if (!$inAttribute || strlen($cname) === 0) { + if (null === $entity) { + if (!$inAttribute || '' === $cname) { $this->parseError("No match in entity table for '%s'", $cname); } $this->scanner->unconsume($this->scanner->position() - $start); + return '&'; } } @@ -1137,8 +1159,9 @@ class Tokenizer $tok = $this->scanner->current(); // We have an entity. We're done here. - if ($tok == ';') { + if (';' === $tok) { $this->scanner->next(); + return $entity; } @@ -1146,10 +1169,12 @@ class Tokenizer // entire string. Otherwise, failure to match is an error. if ($inAttribute) { $this->scanner->unconsume($this->scanner->position() - $start); + return '&'; } - $this->parseError("Expected &ENTITY;, got &ENTITY%s (no trailing ;) ", $tok); + $this->parseError('Expected &ENTITY;, got &ENTITY%s (no trailing ;) ', $tok); + return '&' . $entity; } } diff --git a/src/HTML5/Parser/TreeBuildingRules.php b/src/HTML5/Parser/TreeBuildingRules.php index d092872..00d3951 100644 --- a/src/HTML5/Parser/TreeBuildingRules.php +++ b/src/HTML5/Parser/TreeBuildingRules.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Parser; /** @@ -14,7 +15,6 @@ namespace Masterminds\HTML5\Parser; */ class TreeBuildingRules { - protected static $tags = array( 'li' => 1, 'dd' => 1, @@ -29,21 +29,10 @@ class TreeBuildingRules 'tbody' => 1, 'table' => 1, 'optgroup' => 1, - 'option' => 1 + 'option' => 1, ); /** - * Build a new rules engine. - * - * @param \DOMDocument $doc - * The DOM document to use for evaluation and modification. - */ - public function __construct($doc) - { - $this->doc = $doc; - } - - /** * Returns true if the given tagname has special processing rules. */ public function hasRules($tagname) @@ -71,7 +60,7 @@ class TreeBuildingRules return $this->handleRT($new, $current); case 'optgroup': return $this->closeIfCurrentMatches($new, $current, array( - 'optgroup' + 'optgroup', )); case 'option': return $this->closeIfCurrentMatches($new, $current, array( @@ -79,13 +68,13 @@ class TreeBuildingRules )); case 'tr': return $this->closeIfCurrentMatches($new, $current, array( - 'tr' + 'tr', )); case 'td': case 'th': return $this->closeIfCurrentMatches($new, $current, array( 'th', - 'td' + 'td', )); case 'tbody': case 'thead': @@ -95,7 +84,7 @@ class TreeBuildingRules return $this->closeIfCurrentMatches($new, $current, array( 'thead', 'tfoot', - 'tbody' + 'tbody', )); } @@ -105,7 +94,7 @@ class TreeBuildingRules protected function handleLI($ele, $current) { return $this->closeIfCurrentMatches($ele, $current, array( - 'li' + 'li', )); } @@ -113,7 +102,7 @@ class TreeBuildingRules { return $this->closeIfCurrentMatches($ele, $current, array( 'dt', - 'dd' + 'dd', )); } @@ -121,13 +110,13 @@ class TreeBuildingRules { return $this->closeIfCurrentMatches($ele, $current, array( 'rt', - 'rp' + 'rp', )); } protected function closeIfCurrentMatches($ele, $current, $match) { - if (in_array($current->tagName, $match)) { + if (in_array($current->tagName, $match, true)) { $current->parentNode->appendChild($ele); } else { $current->appendChild($ele); diff --git a/src/HTML5/Parser/UTF8Utils.php b/src/HTML5/Parser/UTF8Utils.php index 451c155..bbf6d5b 100644 --- a/src/HTML5/Parser/UTF8Utils.php +++ b/src/HTML5/Parser/UTF8Utils.php @@ -1,5 +1,7 @@ <?php + namespace Masterminds\HTML5\Parser; + /* * * Portions based on code from html5lib files with the following copyright: @@ -30,11 +32,10 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. use Masterminds\HTML5\Exception; /** - * UTF-8 Utilities + * UTF-8 Utilities. */ class UTF8Utils { - /** * The Unicode replacement character.. */ @@ -76,10 +77,8 @@ class UTF8Utils * 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 + * @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 */ @@ -108,7 +107,7 @@ class UTF8Utils $data = mb_convert_encoding($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') && $encoding != 'auto') { + elseif (function_exists('iconv') && 'auto' !== $encoding) { // fprintf(STDOUT, "iconv found\n"); // iconv has the following behaviors: // - Overlong representations are ignored. @@ -122,7 +121,7 @@ class UTF8Utils /* * One leading U+FEFF BYTE ORDER MARK character must be ignored if any are present. */ - if (substr($data, 0, 3) === "\xEF\xBB\xBF") { + if ("\xEF\xBB\xBF" === substr($data, 0, 3)) { $data = substr($data, 3); } @@ -132,9 +131,9 @@ class UTF8Utils /** * Checks for Unicode code points that are not valid in a document. * - * @param string $data A string to analyze. + * @param string $data A string to analyze * - * @return array An array of (string) error messages produced by the scanning. + * @return array An array of (string) error messages produced by the scanning */ public static function checkForIllegalCodepoints($data) { @@ -144,7 +143,7 @@ class UTF8Utils /* * 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; $i ++) { + for ($i = 0, $count = substr_count($data, "\0"); $i < $count; ++$i) { $errors[] = 'null-character'; } @@ -166,7 +165,7 @@ class UTF8Utils | [\xF0-\xF4][\x8F-\xBF]\xBF[\xBE\xBF] # U+nFFFE and U+nFFFF (1 <= n <= 10_{16}) )/x', $data, $matches); - for ($i = 0; $i < $count; $i ++) { + for ($i = 0; $i < $count; ++$i) { $errors[] = 'invalid-codepoint'; } diff --git a/src/HTML5/Serializer/HTML5Entities.php b/src/HTML5/Serializer/HTML5Entities.php index 4f90f84..e9421a1 100644 --- a/src/HTML5/Serializer/HTML5Entities.php +++ b/src/HTML5/Serializer/HTML5Entities.php @@ -3,11 +3,12 @@ * @file * This contains HTML5 entities to use with serializing. * - * The list here is mildly different from the list at \Masterminds\HTML5\Entities because + * The list here is mildly different from the list at Entities because * that list was generated from the w3c. It contains some entities that are * not entirely proper such as &am; which maps to &. This list is meant to be * a fallback for PHP versions prior to PHP 5.4 when dealing with encoding. */ + namespace Masterminds\HTML5\Serializer; /** @@ -17,7 +18,6 @@ namespace Masterminds\HTML5\Serializer; */ class HTML5Entities { - public static $map = array( ' ' => '	', "\n" => '
', @@ -1528,6 +1528,6 @@ class HTML5Entities '𝕨' => '𝕨', '𝕩' => '𝕩', '𝕪' => '𝕪', - '𝕫' => '𝕫' + '𝕫' => '𝕫', ); } diff --git a/src/HTML5/Serializer/OutputRules.php b/src/HTML5/Serializer/OutputRules.php index a22683c..41616d5 100644 --- a/src/HTML5/Serializer/OutputRules.php +++ b/src/HTML5/Serializer/OutputRules.php @@ -6,6 +6,7 @@ * These output rules are likely to generate output similar to the document that * was parsed. It is not intended to output exactly the document that was parsed. */ + namespace Masterminds\HTML5\Serializer; use Masterminds\HTML5\Elements; @@ -13,10 +14,10 @@ use Masterminds\HTML5\Elements; /** * Generate the output html5 based on element rules. */ -class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface +class OutputRules implements RulesInterface { /** - * Defined in http://www.w3.org/TR/html51/infrastructure.html#html-namespace-0 + * Defined in http://www.w3.org/TR/html51/infrastructure.html#html-namespace-0. */ const NAMESPACE_HTML = 'http://www.w3.org/1999/xhtml'; @@ -31,7 +32,7 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface const NAMESPACE_XMLNS = 'http://www.w3.org/2000/xmlns/'; /** - * Holds the HTML5 element names that causes a namespace switch + * Holds the HTML5 element names that causes a namespace switch. * * @var array */ @@ -50,8 +51,9 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface const IM_IN_MATHML = 3; /** - * Used as cache to detect if is available ENT_HTML5 - * @var boolean + * Used as cache to detect if is available ENT_HTML5. + * + * @var bool */ private $hasHTML5 = false; @@ -169,12 +171,13 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface // If HHVM, see https://github.com/facebook/hhvm/issues/2727 $this->hasHTML5 = defined('ENT_HTML5') && !defined('HHVM_VERSION'); } + public function addRule(array $rule) { $this->nonBooleanAttributes[] = $rule; } - public function setTraverser(\Masterminds\HTML5\Serializer\Traverser $traverser) + public function setTraverser(Traverser $traverser) { $this->traverser = $traverser; @@ -211,10 +214,10 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface // If we are in SVG or MathML there is special handling. // Using if/elseif instead of switch because it's faster in PHP. - if ($name == 'svg') { + if ('svg' == $name) { $this->outputMode = static::IM_IN_SVG; $name = Elements::normalizeSvgElement($name); - } elseif ($name == 'math') { + } elseif ('math' == $name) { $this->outputMode = static::IM_IN_MATHML; } @@ -234,13 +237,13 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface } // Close out the SVG or MathML special handling. - if ($name == 'svg' || $name == 'math') { + if ('svg' == $name || 'math' == $name) { $this->outputMode = static::IM_IN_HTML; } } // If not unary, add a closing tag. - if (! Elements::isA($name, Elements::VOID_TAG)) { + if (!Elements::isA($name, Elements::VOID_TAG)) { $this->closeTag($ele); } } @@ -248,13 +251,13 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface /** * Write a text node. * - * @param \DOMText $ele - * The text node to write. + * @param \DOMText $ele The text node to write. */ public function text($ele) { if (isset($ele->parentNode) && isset($ele->parentNode->tagName) && Elements::isA($ele->parentNode->localName, Elements::TEXT_RAW)) { $this->wr($ele->data); + return; } @@ -283,20 +286,19 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface ->wr($ele->data) ->wr('?>'); } + /** - * Write the namespace attributes + * Write the namespace attributes. * - * - * @param \DOMNode $ele - * The element being written. + * @param \DOMNode $ele The element being written. */ protected function namespaceAttrs($ele) { - if (!$this->xpath || $this->xpath->document !== $ele->ownerDocument){ + if (!$this->xpath || $this->xpath->document !== $ele->ownerDocument) { $this->xpath = new \DOMXPath($ele->ownerDocument); } - foreach( $this->xpath->query('namespace::*[not(.=../../namespace::*)]', $ele ) as $nsNode ) { + foreach ($this->xpath->query('namespace::*[not(.=../../namespace::*)]', $ele) as $nsNode) { if (!in_array($nsNode->nodeValue, $this->implicitNamespaces)) { $this->wr(' ')->wr($nsNode->nodeName)->wr('="')->wr($nsNode->nodeValue)->wr('"'); } @@ -309,18 +311,15 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface * Tags for HTML, MathML, and SVG are in the local name. Otherwise, use the * qualified name (8.3). * - * @param \DOMNode $ele - * The element being written. + * @param \DOMNode $ele The element being written. */ protected function openTag($ele) { $this->wr('<')->wr($this->traverser->isLocalElement($ele) ? $ele->localName : $ele->tagName); - $this->attrs($ele); $this->namespaceAttrs($ele); - if ($this->outputMode == static::IM_IN_HTML) { $this->wr('>'); } // If we are not in html mode we are in SVG, MathML, or XML embedded content. @@ -337,7 +336,7 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface protected function attrs($ele) { // FIXME: Needs support for xml, xmlns, xlink, and namespaced elements. - if (! $ele->hasAttributes()) { + if (!$ele->hasAttributes()) { return $this; } @@ -345,7 +344,7 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface // value-less attributes. $map = $ele->attributes; $len = $map->length; - for ($i = 0; $i < $len; ++ $i) { + for ($i = 0; $i < $len; ++$i) { $node = $map->item($i); $val = $this->enc($node->value, true); @@ -365,45 +364,42 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface $this->wr(' ')->wr($name); - if ((isset($val) && $val !== '') || $this->nonBooleanAttribute($node)) { + if ((isset($val) && '' !== $val) || $this->nonBooleanAttribute($node)) { $this->wr('="')->wr($val)->wr('"'); } } } - protected function nonBooleanAttribute(\DOMAttr $attr) { $ele = $attr->ownerElement; - foreach($this->nonBooleanAttributes as $rule){ - - if(isset($rule['nodeNamespace']) && $rule['nodeNamespace']!==$ele->namespaceURI){ + foreach ($this->nonBooleanAttributes as $rule) { + if (isset($rule['nodeNamespace']) && $rule['nodeNamespace'] !== $ele->namespaceURI) { continue; } - if(isset($rule['attNamespace']) && $rule['attNamespace']!==$attr->namespaceURI){ + if (isset($rule['attNamespace']) && $rule['attNamespace'] !== $attr->namespaceURI) { continue; } - if(isset($rule['nodeName']) && !is_array($rule['nodeName']) && $rule['nodeName']!==$ele->localName){ + if (isset($rule['nodeName']) && !is_array($rule['nodeName']) && $rule['nodeName'] !== $ele->localName) { continue; } - if(isset($rule['nodeName']) && is_array($rule['nodeName']) && !in_array($ele->localName, $rule['nodeName'], true)){ + if (isset($rule['nodeName']) && is_array($rule['nodeName']) && !in_array($ele->localName, $rule['nodeName'], true)) { continue; } - if(isset($rule['attrName']) && !is_array($rule['attrName']) && $rule['attrName']!==$attr->localName){ + if (isset($rule['attrName']) && !is_array($rule['attrName']) && $rule['attrName'] !== $attr->localName) { continue; } - if(isset($rule['attrName']) && is_array($rule['attrName']) && !in_array($attr->localName, $rule['attrName'], true)){ + if (isset($rule['attrName']) && is_array($rule['attrName']) && !in_array($attr->localName, $rule['attrName'], true)) { continue; } - if(isset($rule['xpath'])){ - + if (isset($rule['xpath'])) { $xp = $this->getXPath($attr); - if(isset($rule['prefixes'])){ - foreach($rule['prefixes'] as $nsPrefix => $ns){ + if (isset($rule['prefixes'])) { + foreach ($rule['prefixes'] as $nsPrefix => $ns) { $xp->registerNamespace($nsPrefix, $ns); } } - if(!$xp->evaluate($rule['xpath'], $attr)){ + if (!$xp->evaluate($rule['xpath'], $attr)) { continue; } } @@ -414,10 +410,12 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface return false; } - private function getXPath(\DOMNode $node){ - if(!$this->xpath){ + private function getXPath(\DOMNode $node) + { + if (!$this->xpath) { $this->xpath = new \DOMXPath($node->ownerDocument); } + return $this->xpath; } @@ -427,8 +425,7 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface * Tags for HTML, MathML, and SVG are in the local name. Otherwise, use the * qualified name (8.3). * - * @param \DOMNode $ele - * The element being written. + * @param \DOMNode $ele The element being written. */ protected function closeTag($ele) { @@ -440,25 +437,26 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface /** * Write to the output. * - * @param string $text - * The string to put into the output. + * @param string $text The string to put into the output * - * @return \Masterminds\HTML5\Serializer\Traverser $this so it can be used in chaining. + * @return $this */ protected function wr($text) { fwrite($this->out, $text); + return $this; } /** * Write a new line character. * - * @return \Masterminds\HTML5\Serializer\Traverser $this so it can be used in chaining. + * @return $this */ protected function nl() { fwrite($this->out, PHP_EOL); + return $this; } @@ -484,18 +482,15 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface * * @todo Use the Entities class in php 5.3 to have html5 entities. * - * @param string $text - * text to encode. - * @param boolean $attribute - * True if we are encoding an attrubute, false otherwise + * @param string $text Text to encode. + * @param bool $attribute True if we are encoding an attrubute, false otherwise. * * @return string The encoded text. */ protected function enc($text, $attribute = false) { - // Escape the text rather than convert to named character references. - if (! $this->encode) { + if (!$this->encode) { return $this->escape($text, $attribute); } @@ -507,7 +502,7 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface } // If a version earlier than 5.4 html5 entities are not entirely handled. // This manually handles them. else { - return strtr($text, \Masterminds\HTML5\Serializer\HTML5Entities::$map); + return strtr($text, HTML5Entities::$map); } } @@ -525,14 +520,11 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface * * @see http://www.w3.org/TR/2013/CR-html5-20130806/syntax.html#escapingString * - * @param string $text - * text to escape. - * @param boolean $attribute - * True if we are escaping an attrubute, false otherwise + * @param string $text Text to escape. + * @param bool $attribute True if we are escaping an attrubute, false otherwise. */ protected function escape($text, $attribute = false) { - // Not using htmlspecialchars because, while it does escaping, it doesn't // match the requirements of section 8.5. For example, it doesn't handle // non-breaking spaces. @@ -540,14 +532,14 @@ class OutputRules implements \Masterminds\HTML5\Serializer\RulesInterface $replace = array( '"' => '"', '&' => '&', - "\xc2\xa0" => ' ' + "\xc2\xa0" => ' ', ); } else { $replace = array( '<' => '<', '>' => '>', '&' => '&', - "\xc2\xa0" => ' ' + "\xc2\xa0" => ' ', ); } diff --git a/src/HTML5/Serializer/RulesInterface.php b/src/HTML5/Serializer/RulesInterface.php index 6ef5e5e..69a6ecd 100644 --- a/src/HTML5/Serializer/RulesInterface.php +++ b/src/HTML5/Serializer/RulesInterface.php @@ -3,28 +3,24 @@ * @file * The interface definition for Rules to generate output. */ + namespace Masterminds\HTML5\Serializer; /** - * To create a new rule set for writing output the RulesInterface needs to be - * implemented. - * The resulting class can be specified in the options with the - * key of rules. + * To create a new rule set for writing output the RulesInterface needs to be implemented. + * The resulting class can be specified in the options with the key of rules. * - * For an example implementation see \Masterminds\HTML5\Serializer\OutputRules. + * For an example implementation see Serializer\OutputRules. */ interface RulesInterface { - /** * The class constructor. * * Note, before the rules can be used a traverser must be registered. * - * @param mixed $output - * The output stream to write output to. - * @param array $options - * An array of options. + * @param mixed $output The output stream to write output to. + * @param array $options An array of options. */ public function __construct($output, $options = array()); @@ -33,11 +29,11 @@ interface RulesInterface * * Note, only one traverser can be used by the rules. * - * @param \Masterminds\HTML5\Serializer\Traverser $traverser - * The traverser used in the rules. - * @return \Masterminds\HTML5\Serializer\RulesInterface $this for the current object. + * @param Traverser $traverser The traverser used in the rules. + * + * @return RulesInterface $this for the current object. */ - public function setTraverser(\Masterminds\HTML5\Serializer\Traverser $traverser); + public function setTraverser(Traverser $traverser); /** * Write a document element (\DOMDocument). @@ -92,7 +88,7 @@ interface RulesInterface /** * Write a processor instruction. * - * To learn about processor instructions see \Masterminds\HTML5\InstructionProcessor + * To learn about processor instructions see InstructionProcessor * * Instead of returning the result write it to the output stream ($output) * that was passed into the constructor. diff --git a/src/HTML5/Serializer/Traverser.php b/src/HTML5/Serializer/Traverser.php index 399570d..1e8d792 100644 --- a/src/HTML5/Serializer/Traverser.php +++ b/src/HTML5/Serializer/Traverser.php @@ -1,4 +1,5 @@ <?php + namespace Masterminds\HTML5\Serializer; /** @@ -12,14 +13,13 @@ namespace Masterminds\HTML5\Serializer; */ class Traverser { - /** * Namespaces that should be treated as "local" to HTML5. */ protected static $local_ns = array( 'http://www.w3.org/1999/xhtml' => 'html', 'http://www.w3.org/1998/Math/MathML' => 'math', - 'http://www.w3.org/2000/svg' => 'svg' + 'http://www.w3.org/2000/svg' => 'svg', ); protected $dom; @@ -35,16 +35,13 @@ class Traverser /** * Create a traverser. * - * @param DOMNode|DOMNodeList $dom - * The document or node to traverse. - * @param resource $out - * A stream that allows writing. The traverser will output into this - * stream. - * @param array $options - * An array or options for the traverser as key/value pairs. These include: - * - encode_entities: A bool to specify if full encding should happen for all named - * charachter references. Defaults to false which escapes &'<>". - * - output_rules: The path to the class handling the output rules. + * @param \DOMNode|\DOMNodeList $dom The document or node to traverse. + * @param resource $out A stream that allows writing. The traverser will output into this + * stream. + * @param array $options An array of options for the traverser as key/value pairs. These include: + * - encode_entities: A bool to specify if full encding should happen for all named + * charachter references. Defaults to false which escapes &'<>". + * - output_rules: The path to the class handling the output rules. */ public function __construct($dom, $out, RulesInterface $rules, $options = array()) { @@ -59,8 +56,7 @@ class Traverser /** * Tell the traverser to walk the DOM. * - * @return resource $out - * Returns the output stream. + * @return resource $out Returns the output stream. */ public function walk() { @@ -87,8 +83,7 @@ class Traverser /** * Process a node in the DOM. * - * @param mixed $node - * A node implementing \DOMNode. + * @param mixed $node A node implementing \DOMNode. */ public function node($node) { @@ -119,8 +114,7 @@ class Traverser /** * Walk through all the nodes on a node list. * - * @param \DOMNodeList $nl - * A list of child elements to walk through. + * @param \DOMNodeList $nl A list of child elements to walk through. */ public function children($nl) { @@ -132,10 +126,9 @@ class Traverser /** * Is an element local? * - * @param mixed $ele - * An element that implement \DOMNode. + * @param mixed $ele An element that implement \DOMNode. * - * @return bool True if local and false otherwise. + * @return bool true if local and false otherwise. */ public function isLocalElement($ele) { |