aboutsummaryrefslogtreecommitdiffstats
path: root/library/HTMLPurifier/Lexer
diff options
context:
space:
mode:
authorfriendica <info@friendica.com>2015-01-01 22:18:27 -0800
committerfriendica <info@friendica.com>2015-01-01 22:18:27 -0800
commita0052f0176bd079e6a94baec59fea2ec5a8d651e (patch)
treec323edd823681bc2e8ca757e7eaf8354d42c7b51 /library/HTMLPurifier/Lexer
parent545e47933a0816699c68d98a7742a03260d6a54f (diff)
downloadvolse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.tar.gz
volse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.tar.bz2
volse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.zip
htmlpurifier update - compatibility issue with language library autoloader
Diffstat (limited to 'library/HTMLPurifier/Lexer')
-rw-r--r--library/HTMLPurifier/Lexer/DOMLex.php161
-rw-r--r--library/HTMLPurifier/Lexer/DirectLex.php217
-rw-r--r--library/HTMLPurifier/Lexer/PEARSax3.php139
-rw-r--r--library/HTMLPurifier/Lexer/PH5P.php4324
4 files changed, 2850 insertions, 1991 deletions
diff --git a/library/HTMLPurifier/Lexer/DOMLex.php b/library/HTMLPurifier/Lexer/DOMLex.php
index 20dc2ed48..720754454 100644
--- a/library/HTMLPurifier/Lexer/DOMLex.php
+++ b/library/HTMLPurifier/Lexer/DOMLex.php
@@ -27,16 +27,26 @@
class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
{
+ /**
+ * @type HTMLPurifier_TokenFactory
+ */
private $factory;
- public function __construct() {
+ public function __construct()
+ {
// setup the factory
parent::__construct();
$this->factory = new HTMLPurifier_TokenFactory();
}
- public function tokenizeHTML($html, $config, $context) {
-
+ /**
+ * @param string $html
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return HTMLPurifier_Token[]
+ */
+ public function tokenizeHTML($html, $config, $context)
+ {
$html = $this->normalize($html, $config, $context);
// attempt to armor stray angled brackets that cannot possibly
@@ -65,30 +75,67 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
$tokens = array();
$this->tokenizeDOM(
$doc->getElementsByTagName('html')->item(0)-> // <html>
- getElementsByTagName('body')->item(0)-> // <body>
- getElementsByTagName('div')->item(0) // <div>
- , $tokens);
+ getElementsByTagName('body')->item(0)-> // <body>
+ getElementsByTagName('div')->item(0), // <div>
+ $tokens
+ );
return $tokens;
}
/**
- * Recursive function that tokenizes a node, putting it into an accumulator.
- *
- * @param $node DOMNode to be tokenized.
- * @param $tokens Array-list of already tokenized tokens.
- * @param $collect Says whether or start and close are collected, set to
- * false at first recursion because it's the implicit DIV
- * tag you're dealing with.
- * @returns Tokens of node appended to previously passed tokens.
+ * Iterative function that tokenizes a node, putting it into an accumulator.
+ * To iterate is human, to recurse divine - L. Peter Deutsch
+ * @param DOMNode $node DOMNode to be tokenized.
+ * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens.
+ * @return HTMLPurifier_Token of node appended to previously passed tokens.
*/
- protected function tokenizeDOM($node, &$tokens, $collect = false) {
+ protected function tokenizeDOM($node, &$tokens)
+ {
+ $level = 0;
+ $nodes = array($level => new HTMLPurifier_Queue(array($node)));
+ $closingNodes = array();
+ do {
+ while (!$nodes[$level]->isEmpty()) {
+ $node = $nodes[$level]->shift(); // FIFO
+ $collect = $level > 0 ? true : false;
+ $needEndingTag = $this->createStartNode($node, $tokens, $collect);
+ if ($needEndingTag) {
+ $closingNodes[$level][] = $node;
+ }
+ if ($node->childNodes && $node->childNodes->length) {
+ $level++;
+ $nodes[$level] = new HTMLPurifier_Queue();
+ foreach ($node->childNodes as $childNode) {
+ $nodes[$level]->push($childNode);
+ }
+ }
+ }
+ $level--;
+ if ($level && isset($closingNodes[$level])) {
+ while ($node = array_pop($closingNodes[$level])) {
+ $this->createEndNode($node, $tokens);
+ }
+ }
+ } while ($level > 0);
+ }
+ /**
+ * @param DOMNode $node DOMNode to be tokenized.
+ * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens.
+ * @param bool $collect Says whether or start and close are collected, set to
+ * false at first recursion because it's the implicit DIV
+ * tag you're dealing with.
+ * @return bool if the token needs an endtoken
+ * @todo data and tagName properties don't seem to exist in DOMNode?
+ */
+ protected function createStartNode($node, &$tokens, $collect)
+ {
// intercept non element nodes. WE MUST catch all of them,
// but we're not getting the character reference nodes because
// those should have been preprocessed
if ($node->nodeType === XML_TEXT_NODE) {
$tokens[] = $this->factory->createText($node->data);
- return;
+ return false;
} elseif ($node->nodeType === XML_CDATA_SECTION_NODE) {
// undo libxml's special treatment of <script> and <style> tags
$last = end($tokens);
@@ -106,59 +153,61 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
}
}
$tokens[] = $this->factory->createText($this->parseData($data));
- return;
+ return false;
} elseif ($node->nodeType === XML_COMMENT_NODE) {
// this is code is only invoked for comments in script/style in versions
// of libxml pre-2.6.28 (regular comments, of course, are still
// handled regularly)
$tokens[] = $this->factory->createComment($node->data);
- return;
- } elseif (
+ return false;
+ } elseif ($node->nodeType !== XML_ELEMENT_NODE) {
// not-well tested: there may be other nodes we have to grab
- $node->nodeType !== XML_ELEMENT_NODE
- ) {
- return;
+ return false;
}
- $attr = $node->hasAttributes() ?
- $this->transformAttrToAssoc($node->attributes) :
- array();
+ $attr = $node->hasAttributes() ? $this->transformAttrToAssoc($node->attributes) : array();
// We still have to make sure that the element actually IS empty
if (!$node->childNodes->length) {
if ($collect) {
$tokens[] = $this->factory->createEmpty($node->tagName, $attr);
}
+ return false;
} else {
- if ($collect) { // don't wrap on first iteration
+ if ($collect) {
$tokens[] = $this->factory->createStart(
$tag_name = $node->tagName, // somehow, it get's dropped
$attr
);
}
- foreach ($node->childNodes as $node) {
- // remember, it's an accumulator. Otherwise, we'd have
- // to use array_merge
- $this->tokenizeDOM($node, $tokens, true);
- }
- if ($collect) {
- $tokens[] = $this->factory->createEnd($tag_name);
- }
+ return true;
}
+ }
+ /**
+ * @param DOMNode $node
+ * @param HTMLPurifier_Token[] $tokens
+ */
+ protected function createEndNode($node, &$tokens)
+ {
+ $tokens[] = $this->factory->createEnd($node->tagName);
}
+
/**
* Converts a DOMNamedNodeMap of DOMAttr objects into an assoc array.
*
- * @param $attribute_list DOMNamedNodeMap of DOMAttr objects.
- * @returns Associative array of attributes.
+ * @param DOMNamedNodeMap $node_map DOMNamedNodeMap of DOMAttr objects.
+ * @return array Associative array of attributes.
*/
- protected function transformAttrToAssoc($node_map) {
+ protected function transformAttrToAssoc($node_map)
+ {
// NamedNodeMap is documented very well, so we're using undocumented
// features, namely, the fact that it implements Iterator and
// has a ->length attribute
- if ($node_map->length === 0) return array();
+ if ($node_map->length === 0) {
+ return array();
+ }
$array = array();
foreach ($node_map as $attr) {
$array[$attr->name] = $attr->value;
@@ -168,46 +217,64 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
/**
* An error handler that mutes all errors
+ * @param int $errno
+ * @param string $errstr
*/
- public function muteErrorHandler($errno, $errstr) {}
+ public function muteErrorHandler($errno, $errstr)
+ {
+ }
/**
* Callback function for undoing escaping of stray angled brackets
* in comments
+ * @param array $matches
+ * @return string
*/
- public function callbackUndoCommentSubst($matches) {
- return '<!--' . strtr($matches[1], array('&amp;'=>'&','&lt;'=>'<')) . $matches[2];
+ public function callbackUndoCommentSubst($matches)
+ {
+ return '<!--' . strtr($matches[1], array('&amp;' => '&', '&lt;' => '<')) . $matches[2];
}
/**
* Callback function that entity-izes ampersands in comments so that
* callbackUndoCommentSubst doesn't clobber them
+ * @param array $matches
+ * @return string
*/
- public function callbackArmorCommentEntities($matches) {
+ public function callbackArmorCommentEntities($matches)
+ {
return '<!--' . str_replace('&', '&amp;', $matches[1]) . $matches[2];
}
/**
* Wraps an HTML fragment in the necessary HTML
+ * @param string $html
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return string
*/
- protected function wrapHTML($html, $config, $context) {
+ protected function wrapHTML($html, $config, $context)
+ {
$def = $config->getDefinition('HTML');
$ret = '';
if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
$ret .= '<!DOCTYPE html ';
- if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
- if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" ';
+ if (!empty($def->doctype->dtdPublic)) {
+ $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
+ }
+ if (!empty($def->doctype->dtdSystem)) {
+ $ret .= '"' . $def->doctype->dtdSystem . '" ';
+ }
$ret .= '>';
}
$ret .= '<html><head>';
$ret .= '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />';
// No protection if $html contains a stray </div>!
- $ret .= '</head><body><div>'.$html.'</div></body></html>';
+ $ret .= '</head><body><div>' . $html . '</div></body></html>';
return $ret;
}
-
}
// vim: et sw=4 sts=4
diff --git a/library/HTMLPurifier/Lexer/DirectLex.php b/library/HTMLPurifier/Lexer/DirectLex.php
index 456e6e190..746b6e315 100644
--- a/library/HTMLPurifier/Lexer/DirectLex.php
+++ b/library/HTMLPurifier/Lexer/DirectLex.php
@@ -12,30 +12,44 @@
*/
class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
{
-
+ /**
+ * @type bool
+ */
public $tracksLineNumbers = true;
/**
* Whitespace characters for str(c)spn.
+ * @type string
*/
protected $_whitespace = "\x20\x09\x0D\x0A";
/**
* Callback function for script CDATA fudge
- * @param $matches, in form of array(opening tag, contents, closing tag)
+ * @param array $matches, in form of array(opening tag, contents, closing tag)
+ * @return string
*/
- protected function scriptCallback($matches) {
+ protected function scriptCallback($matches)
+ {
return $matches[1] . htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8') . $matches[3];
}
- public function tokenizeHTML($html, $config, $context) {
-
+ /**
+ * @param String $html
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return array|HTMLPurifier_Token[]
+ */
+ public function tokenizeHTML($html, $config, $context)
+ {
// special normalization for script tags without any armor
// our "armor" heurstic is a < sign any number of whitespaces after
// the first script tag
if ($config->get('HTML.Trusted')) {
- $html = preg_replace_callback('#(<script[^>]*>)(\s*[^<].+?)(</script>)#si',
- array($this, 'scriptCallback'), $html);
+ $html = preg_replace_callback(
+ '#(<script[^>]*>)(\s*[^<].+?)(</script>)#si',
+ array($this, 'scriptCallback'),
+ $html
+ );
}
$html = $this->normalize($html, $config, $context);
@@ -55,15 +69,15 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
if ($maintain_line_numbers) {
$current_line = 1;
- $current_col = 0;
+ $current_col = 0;
$length = strlen($html);
} else {
$current_line = false;
- $current_col = false;
+ $current_col = false;
$length = false;
}
$context->register('CurrentLine', $current_line);
- $context->register('CurrentCol', $current_col);
+ $context->register('CurrentCol', $current_col);
$nl = "\n";
// how often to manually recalculate. This will ALWAYS be right,
// but it's pretty wasteful. Set to 0 to turn off
@@ -77,16 +91,14 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
// for testing synchronization
$loops = 0;
- while(++$loops) {
-
+ while (++$loops) {
// $cursor is either at the start of a token, or inside of
// a tag (i.e. there was a < immediately before it), as indicated
// by $inside_tag
if ($maintain_line_numbers) {
-
// $rcursor, however, is always at the start of a token.
- $rcursor = $cursor - (int) $inside_tag;
+ $rcursor = $cursor - (int)$inside_tag;
// Column number is cheap, so we calculate it every round.
// We're interested at the *end* of the newline string, so
@@ -96,14 +108,11 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
$current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1);
// recalculate lines
- if (
- $synchronize_interval && // synchronization is on
- $cursor > 0 && // cursor is further than zero
- $loops % $synchronize_interval === 0 // time to synchronize!
- ) {
+ if ($synchronize_interval && // synchronization is on
+ $cursor > 0 && // cursor is further than zero
+ $loops % $synchronize_interval === 0) { // time to synchronize!
$current_line = 1 + $this->substrCount($html, $nl, 0, $cursor);
}
-
}
$position_next_lt = strpos($html, '<', $cursor);
@@ -119,35 +128,42 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
if (!$inside_tag && $position_next_lt !== false) {
// We are not inside tag and there still is another tag to parse
$token = new
- HTMLPurifier_Token_Text(
- $this->parseData(
- substr(
- $html, $cursor, $position_next_lt - $cursor
- )
+ HTMLPurifier_Token_Text(
+ $this->parseData(
+ substr(
+ $html,
+ $cursor,
+ $position_next_lt - $cursor
)
- );
+ )
+ );
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor);
}
$array[] = $token;
- $cursor = $position_next_lt + 1;
+ $cursor = $position_next_lt + 1;
$inside_tag = true;
continue;
} elseif (!$inside_tag) {
// We are not inside tag but there are no more tags
// If we're already at the end, break
- if ($cursor === strlen($html)) break;
+ if ($cursor === strlen($html)) {
+ break;
+ }
// Create Text of rest of string
$token = new
- HTMLPurifier_Token_Text(
- $this->parseData(
- substr(
- $html, $cursor
- )
+ HTMLPurifier_Token_Text(
+ $this->parseData(
+ substr(
+ $html,
+ $cursor
)
- );
- if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+ )
+ );
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ }
$array[] = $token;
break;
} elseif ($inside_tag && $position_next_gt !== false) {
@@ -171,16 +187,16 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
}
// Check if it's a comment
- if (
- substr($segment, 0, 3) === '!--'
- ) {
+ if (substr($segment, 0, 3) === '!--') {
// re-determine segment length, looking for -->
$position_comment_end = strpos($html, '-->', $cursor);
if ($position_comment_end === false) {
// uh oh, we have a comment that extends to
// infinity. Can't be helped: set comment
// end position to end of string
- if ($e) $e->send(E_WARNING, 'Lexer: Unclosed comment');
+ if ($e) {
+ $e->send(E_WARNING, 'Lexer: Unclosed comment');
+ }
$position_comment_end = strlen($html);
$end = true;
} else {
@@ -189,11 +205,13 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
$strlen_segment = $position_comment_end - $cursor;
$segment = substr($html, $cursor, $strlen_segment);
$token = new
- HTMLPurifier_Token_Comment(
- substr(
- $segment, 3, $strlen_segment - 3
- )
- );
+ HTMLPurifier_Token_Comment(
+ substr(
+ $segment,
+ 3,
+ $strlen_segment - 3
+ )
+ );
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
$current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment);
@@ -205,7 +223,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
}
// Check if it's an end tag
- $is_end_tag = (strpos($segment,'/') === 0);
+ $is_end_tag = (strpos($segment, '/') === 0);
if ($is_end_tag) {
$type = substr($segment, 1);
$token = new HTMLPurifier_Token_End($type);
@@ -224,7 +242,9 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
// text and go our merry way
if (!ctype_alpha($segment[0])) {
// XML: $segment[0] !== '_' && $segment[0] !== ':'
- if ($e) $e->send(E_NOTICE, 'Lexer: Unescaped lt');
+ if ($e) {
+ $e->send(E_NOTICE, 'Lexer: Unescaped lt');
+ }
$token = new HTMLPurifier_Token_Text('<');
if ($maintain_line_numbers) {
$token->rawPosition($current_line, $current_col);
@@ -239,7 +259,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
// trailing slash. Remember, we could have a tag like <br>, so
// any later token processing scripts must convert improperly
// classified EmptyTags from StartTags.
- $is_self_closing = (strrpos($segment,'/') === $strlen_segment-1);
+ $is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1);
if ($is_self_closing) {
$strlen_segment--;
$segment = substr($segment, 0, $strlen_segment);
@@ -269,14 +289,16 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
$attribute_string =
trim(
substr(
- $segment, $position_first_space
+ $segment,
+ $position_first_space
)
);
if ($attribute_string) {
$attr = $this->parseAttributeString(
- $attribute_string
- , $config, $context
- );
+ $attribute_string,
+ $config,
+ $context
+ );
} else {
$attr = array();
}
@@ -296,15 +318,19 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
continue;
} else {
// inside tag, but there's no ending > sign
- if ($e) $e->send(E_WARNING, 'Lexer: Missing gt');
+ if ($e) {
+ $e->send(E_WARNING, 'Lexer: Missing gt');
+ }
$token = new
- HTMLPurifier_Token_Text(
- '<' .
- $this->parseData(
- substr($html, $cursor)
- )
- );
- if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+ HTMLPurifier_Token_Text(
+ '<' .
+ $this->parseData(
+ substr($html, $cursor)
+ )
+ );
+ if ($maintain_line_numbers) {
+ $token->rawPosition($current_line, $current_col);
+ }
// no cursor scroll? Hmm...
$array[] = $token;
break;
@@ -319,8 +345,14 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
/**
* PHP 5.0.x compatible substr_count that implements offset and length
+ * @param string $haystack
+ * @param string $needle
+ * @param int $offset
+ * @param int $length
+ * @return int
*/
- protected function substrCount($haystack, $needle, $offset, $length) {
+ protected function substrCount($haystack, $needle, $offset, $length)
+ {
static $oldVersion;
if ($oldVersion === null) {
$oldVersion = version_compare(PHP_VERSION, '5.1', '<');
@@ -336,13 +368,18 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
/**
* Takes the inside of an HTML tag and makes an assoc array of attributes.
*
- * @param $string Inside of tag excluding name.
- * @returns Assoc array of attributes.
+ * @param string $string Inside of tag excluding name.
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return array Assoc array of attributes.
*/
- public function parseAttributeString($string, $config, $context) {
- $string = (string) $string; // quick typecast
+ public function parseAttributeString($string, $config, $context)
+ {
+ $string = (string)$string; // quick typecast
- if ($string == '') return array(); // no attributes
+ if ($string == '') {
+ return array();
+ } // no attributes
$e = false;
if ($config->get('Core.CollectErrors')) {
@@ -361,46 +398,55 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
list($key, $quoted_value) = explode('=', $string);
$quoted_value = trim($quoted_value);
if (!$key) {
- if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ if ($e) {
+ $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ }
return array();
}
- if (!$quoted_value) return array($key => '');
+ if (!$quoted_value) {
+ return array($key => '');
+ }
$first_char = @$quoted_value[0];
- $last_char = @$quoted_value[strlen($quoted_value)-1];
+ $last_char = @$quoted_value[strlen($quoted_value) - 1];
$same_quote = ($first_char == $last_char);
$open_quote = ($first_char == '"' || $first_char == "'");
- if ( $same_quote && $open_quote) {
+ if ($same_quote && $open_quote) {
// well behaved
$value = substr($quoted_value, 1, strlen($quoted_value) - 2);
} else {
// not well behaved
if ($open_quote) {
- if ($e) $e->send(E_ERROR, 'Lexer: Missing end quote');
+ if ($e) {
+ $e->send(E_ERROR, 'Lexer: Missing end quote');
+ }
$value = substr($quoted_value, 1);
} else {
$value = $quoted_value;
}
}
- if ($value === false) $value = '';
+ if ($value === false) {
+ $value = '';
+ }
return array($key => $this->parseData($value));
}
// setup loop environment
- $array = array(); // return assoc array of attributes
+ $array = array(); // return assoc array of attributes
$cursor = 0; // current position in string (moves forward)
- $size = strlen($string); // size of the string (stays the same)
+ $size = strlen($string); // size of the string (stays the same)
// if we have unquoted attributes, the parser expects a terminating
// space, so let's guarantee that there's always a terminating space.
$string .= ' ';
- while(true) {
-
- if ($cursor >= $size) {
- break;
+ $old_cursor = -1;
+ while ($cursor < $size) {
+ if ($old_cursor >= $cursor) {
+ throw new Exception("Infinite loop detected");
}
+ $old_cursor = $cursor;
$cursor += ($value = strspn($string, $this->_whitespace, $cursor));
// grab the key
@@ -415,8 +461,10 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
$key = substr($string, $key_begin, $key_end - $key_begin);
if (!$key) {
- if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
- $cursor += strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop
+ if ($e) {
+ $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ }
+ $cursor += 1 + strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop
continue; // empty key
}
@@ -467,24 +515,25 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
}
$value = substr($string, $value_begin, $value_end - $value_begin);
- if ($value === false) $value = '';
+ if ($value === false) {
+ $value = '';
+ }
$array[$key] = $this->parseData($value);
$cursor++;
-
} else {
// boolattr
if ($key !== '') {
$array[$key] = $key;
} else {
// purely theoretical
- if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ if ($e) {
+ $e->send(E_ERROR, 'Lexer: Missing attribute key');
+ }
}
-
}
}
return $array;
}
-
}
// vim: et sw=4 sts=4
diff --git a/library/HTMLPurifier/Lexer/PEARSax3.php b/library/HTMLPurifier/Lexer/PEARSax3.php
deleted file mode 100644
index 1d358c7b6..000000000
--- a/library/HTMLPurifier/Lexer/PEARSax3.php
+++ /dev/null
@@ -1,139 +0,0 @@
-<?php
-
-/**
- * Proof-of-concept lexer that uses the PEAR package XML_HTMLSax3 to parse HTML.
- *
- * PEAR, not suprisingly, also has a SAX parser for HTML. I don't know
- * very much about implementation, but it's fairly well written. However, that
- * abstraction comes at a price: performance. You need to have it installed,
- * and if the API changes, it might break our adapter. Not sure whether or not
- * it's UTF-8 aware, but it has some entity parsing trouble (in all areas,
- * text and attributes).
- *
- * Quite personally, I don't recommend using the PEAR class, and the defaults
- * don't use it. The unit tests do perform the tests on the SAX parser too, but
- * whatever it does for poorly formed HTML is up to it.
- *
- * @todo Generalize so that XML_HTMLSax is also supported.
- *
- * @warning Entity-resolution inside attributes is broken.
- */
-
-class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
-{
-
- /**
- * Internal accumulator array for SAX parsers.
- */
- protected $tokens = array();
- protected $last_token_was_empty;
-
- private $parent_handler;
- private $stack = array();
-
- public function tokenizeHTML($string, $config, $context) {
-
- $this->tokens = array();
- $this->last_token_was_empty = false;
-
- $string = $this->normalize($string, $config, $context);
-
- $this->parent_handler = set_error_handler(array($this, 'muteStrictErrorHandler'));
-
- $parser = new XML_HTMLSax3();
- $parser->set_object($this);
- $parser->set_element_handler('openHandler','closeHandler');
- $parser->set_data_handler('dataHandler');
- $parser->set_escape_handler('escapeHandler');
-
- // doesn't seem to work correctly for attributes
- $parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
-
- $parser->parse($string);
-
- restore_error_handler();
-
- return $this->tokens;
-
- }
-
- /**
- * Open tag event handler, interface is defined by PEAR package.
- */
- public function openHandler(&$parser, $name, $attrs, $closed) {
- // entities are not resolved in attrs
- foreach ($attrs as $key => $attr) {
- $attrs[$key] = $this->parseData($attr);
- }
- if ($closed) {
- $this->tokens[] = new HTMLPurifier_Token_Empty($name, $attrs);
- $this->last_token_was_empty = true;
- } else {
- $this->tokens[] = new HTMLPurifier_Token_Start($name, $attrs);
- }
- $this->stack[] = $name;
- return true;
- }
-
- /**
- * Close tag event handler, interface is defined by PEAR package.
- */
- public function closeHandler(&$parser, $name) {
- // HTMLSax3 seems to always send empty tags an extra close tag
- // check and ignore if you see it:
- // [TESTME] to make sure it doesn't overreach
- if ($this->last_token_was_empty) {
- $this->last_token_was_empty = false;
- return true;
- }
- $this->tokens[] = new HTMLPurifier_Token_End($name);
- if (!empty($this->stack)) array_pop($this->stack);
- return true;
- }
-
- /**
- * Data event handler, interface is defined by PEAR package.
- */
- public function dataHandler(&$parser, $data) {
- $this->last_token_was_empty = false;
- $this->tokens[] = new HTMLPurifier_Token_Text($data);
- return true;
- }
-
- /**
- * Escaped text handler, interface is defined by PEAR package.
- */
- public function escapeHandler(&$parser, $data) {
- if (strpos($data, '--') === 0) {
- // remove trailing and leading double-dashes
- $data = substr($data, 2);
- if (strlen($data) >= 2 && substr($data, -2) == "--") {
- $data = substr($data, 0, -2);
- }
- if (isset($this->stack[sizeof($this->stack) - 1]) &&
- $this->stack[sizeof($this->stack) - 1] == "style") {
- $this->tokens[] = new HTMLPurifier_Token_Text($data);
- } else {
- $this->tokens[] = new HTMLPurifier_Token_Comment($data);
- }
- $this->last_token_was_empty = false;
- }
- // CDATA is handled elsewhere, but if it was handled here:
- //if (strpos($data, '[CDATA[') === 0) {
- // $this->tokens[] = new HTMLPurifier_Token_Text(
- // substr($data, 7, strlen($data) - 9) );
- //}
- return true;
- }
-
- /**
- * An error handler that mutes strict errors
- */
- public function muteStrictErrorHandler($errno, $errstr, $errfile=null, $errline=null, $errcontext=null) {
- if ($errno == E_STRICT) return;
- return call_user_func($this->parent_handler, $errno, $errstr, $errfile, $errline, $errcontext);
- }
-
-}
-
-// vim: et sw=4 sts=4
diff --git a/library/HTMLPurifier/Lexer/PH5P.php b/library/HTMLPurifier/Lexer/PH5P.php
index fa1bf973e..a4587e4cd 100644
--- a/library/HTMLPurifier/Lexer/PH5P.php
+++ b/library/HTMLPurifier/Lexer/PH5P.php
@@ -3,16 +3,23 @@
/**
* Experimental HTML5-based parser using Jeroen van der Meer's PH5P library.
* Occupies space in the HTML5 pseudo-namespace, which may cause conflicts.
- *
+ *
* @note
* Recent changes to PHP's DOM extension have resulted in some fatal
* error conditions with the original version of PH5P. Pending changes,
- * this lexer will punt to DirectLex if DOM throughs an exception.
+ * this lexer will punt to DirectLex if DOM throws an exception.
*/
-class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex {
-
- public function tokenizeHTML($html, $config, $context) {
+class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex
+{
+ /**
+ * @param string $html
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return HTMLPurifier_Token[]
+ */
+ public function tokenizeHTML($html, $config, $context)
+ {
$new_html = $this->normalize($html, $config, $context);
$new_html = $this->wrapHTML($new_html, $config, $context);
try {
@@ -27,40 +34,42 @@ class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex {
$tokens = array();
$this->tokenizeDOM(
$doc->getElementsByTagName('html')->item(0)-> // <html>
- getElementsByTagName('body')->item(0)-> // <body>
- getElementsByTagName('div')->item(0) // <div>
- , $tokens);
+ getElementsByTagName('body')->item(0)-> // <body>
+ getElementsByTagName('div')->item(0) // <div>
+ ,
+ $tokens
+ );
return $tokens;
}
-
}
/*
-Copyright 2007 Jeroen van der Meer <http://jero.net/>
+Copyright 2007 Jeroen van der Meer <http://jero.net/>
-Permission is hereby granted, free of charge, to any person obtaining a
-copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
-OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
-class HTML5 {
+class HTML5
+{
private $data;
private $char;
private $EOF;
@@ -69,91 +78,418 @@ class HTML5 {
private $token;
private $content_model;
private $escape = false;
- private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute',
- 'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;',
- 'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;',
- 'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;',
- 'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;',
- 'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;',
- 'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;',
- 'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;',
- 'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;',
- 'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN',
- 'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;',
- 'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;',
- 'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig',
- 'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;',
- 'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;',
- 'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil',
- 'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;',
- 'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;',
- 'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;',
- 'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth',
- 'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12',
- 'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt',
- 'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc',
- 'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;',
- 'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;',
- 'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;',
- 'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro',
- 'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;',
- 'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;',
- 'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;',
- 'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash',
- 'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;',
- 'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;',
- 'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;',
- 'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;',
- 'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;',
- 'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;',
- 'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;',
- 'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;',
- 'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc',
- 'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;',
- 'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;');
-
- const PCDATA = 0;
- const RCDATA = 1;
- const CDATA = 2;
+ private $entities = array(
+ 'AElig;',
+ 'AElig',
+ 'AMP;',
+ 'AMP',
+ 'Aacute;',
+ 'Aacute',
+ 'Acirc;',
+ 'Acirc',
+ 'Agrave;',
+ 'Agrave',
+ 'Alpha;',
+ 'Aring;',
+ 'Aring',
+ 'Atilde;',
+ 'Atilde',
+ 'Auml;',
+ 'Auml',
+ 'Beta;',
+ 'COPY;',
+ 'COPY',
+ 'Ccedil;',
+ 'Ccedil',
+ 'Chi;',
+ 'Dagger;',
+ 'Delta;',
+ 'ETH;',
+ 'ETH',
+ 'Eacute;',
+ 'Eacute',
+ 'Ecirc;',
+ 'Ecirc',
+ 'Egrave;',
+ 'Egrave',
+ 'Epsilon;',
+ 'Eta;',
+ 'Euml;',
+ 'Euml',
+ 'GT;',
+ 'GT',
+ 'Gamma;',
+ 'Iacute;',
+ 'Iacute',
+ 'Icirc;',
+ 'Icirc',
+ 'Igrave;',
+ 'Igrave',
+ 'Iota;',
+ 'Iuml;',
+ 'Iuml',
+ 'Kappa;',
+ 'LT;',
+ 'LT',
+ 'Lambda;',
+ 'Mu;',
+ 'Ntilde;',
+ 'Ntilde',
+ 'Nu;',
+ 'OElig;',
+ 'Oacute;',
+ 'Oacute',
+ 'Ocirc;',
+ 'Ocirc',
+ 'Ograve;',
+ 'Ograve',
+ 'Omega;',
+ 'Omicron;',
+ 'Oslash;',
+ 'Oslash',
+ 'Otilde;',
+ 'Otilde',
+ 'Ouml;',
+ 'Ouml',
+ 'Phi;',
+ 'Pi;',
+ 'Prime;',
+ 'Psi;',
+ 'QUOT;',
+ 'QUOT',
+ 'REG;',
+ 'REG',
+ 'Rho;',
+ 'Scaron;',
+ 'Sigma;',
+ 'THORN;',
+ 'THORN',
+ 'TRADE;',
+ 'Tau;',
+ 'Theta;',
+ 'Uacute;',
+ 'Uacute',
+ 'Ucirc;',
+ 'Ucirc',
+ 'Ugrave;',
+ 'Ugrave',
+ 'Upsilon;',
+ 'Uuml;',
+ 'Uuml',
+ 'Xi;',
+ 'Yacute;',
+ 'Yacute',
+ 'Yuml;',
+ 'Zeta;',
+ 'aacute;',
+ 'aacute',
+ 'acirc;',
+ 'acirc',
+ 'acute;',
+ 'acute',
+ 'aelig;',
+ 'aelig',
+ 'agrave;',
+ 'agrave',
+ 'alefsym;',
+ 'alpha;',
+ 'amp;',
+ 'amp',
+ 'and;',
+ 'ang;',
+ 'apos;',
+ 'aring;',
+ 'aring',
+ 'asymp;',
+ 'atilde;',
+ 'atilde',
+ 'auml;',
+ 'auml',
+ 'bdquo;',
+ 'beta;',
+ 'brvbar;',
+ 'brvbar',
+ 'bull;',
+ 'cap;',
+ 'ccedil;',
+ 'ccedil',
+ 'cedil;',
+ 'cedil',
+ 'cent;',
+ 'cent',
+ 'chi;',
+ 'circ;',
+ 'clubs;',
+ 'cong;',
+ 'copy;',
+ 'copy',
+ 'crarr;',
+ 'cup;',
+ 'curren;',
+ 'curren',
+ 'dArr;',
+ 'dagger;',
+ 'darr;',
+ 'deg;',
+ 'deg',
+ 'delta;',
+ 'diams;',
+ 'divide;',
+ 'divide',
+ 'eacute;',
+ 'eacute',
+ 'ecirc;',
+ 'ecirc',
+ 'egrave;',
+ 'egrave',
+ 'empty;',
+ 'emsp;',
+ 'ensp;',
+ 'epsilon;',
+ 'equiv;',
+ 'eta;',
+ 'eth;',
+ 'eth',
+ 'euml;',
+ 'euml',
+ 'euro;',
+ 'exist;',
+ 'fnof;',
+ 'forall;',
+ 'frac12;',
+ 'frac12',
+ 'frac14;',
+ 'frac14',
+ 'frac34;',
+ 'frac34',
+ 'frasl;',
+ 'gamma;',
+ 'ge;',
+ 'gt;',
+ 'gt',
+ 'hArr;',
+ 'harr;',
+ 'hearts;',
+ 'hellip;',
+ 'iacute;',
+ 'iacute',
+ 'icirc;',
+ 'icirc',
+ 'iexcl;',
+ 'iexcl',
+ 'igrave;',
+ 'igrave',
+ 'image;',
+ 'infin;',
+ 'int;',
+ 'iota;',
+ 'iquest;',
+ 'iquest',
+ 'isin;',
+ 'iuml;',
+ 'iuml',
+ 'kappa;',
+ 'lArr;',
+ 'lambda;',
+ 'lang;',
+ 'laquo;',
+ 'laquo',
+ 'larr;',
+ 'lceil;',
+ 'ldquo;',
+ 'le;',
+ 'lfloor;',
+ 'lowast;',
+ 'loz;',
+ 'lrm;',
+ 'lsaquo;',
+ 'lsquo;',
+ 'lt;',
+ 'lt',
+ 'macr;',
+ 'macr',
+ 'mdash;',
+ 'micro;',
+ 'micro',
+ 'middot;',
+ 'middot',
+ 'minus;',
+ 'mu;',
+ 'nabla;',
+ 'nbsp;',
+ 'nbsp',
+ 'ndash;',
+ 'ne;',
+ 'ni;',
+ 'not;',
+ 'not',
+ 'notin;',
+ 'nsub;',
+ 'ntilde;',
+ 'ntilde',
+ 'nu;',
+ 'oacute;',
+ 'oacute',
+ 'ocirc;',
+ 'ocirc',
+ 'oelig;',
+ 'ograve;',
+ 'ograve',
+ 'oline;',
+ 'omega;',
+ 'omicron;',
+ 'oplus;',
+ 'or;',
+ 'ordf;',
+ 'ordf',
+ 'ordm;',
+ 'ordm',
+ 'oslash;',
+ 'oslash',
+ 'otilde;',
+ 'otilde',
+ 'otimes;',
+ 'ouml;',
+ 'ouml',
+ 'para;',
+ 'para',
+ 'part;',
+ 'permil;',
+ 'perp;',
+ 'phi;',
+ 'pi;',
+ 'piv;',
+ 'plusmn;',
+ 'plusmn',
+ 'pound;',
+ 'pound',
+ 'prime;',
+ 'prod;',
+ 'prop;',
+ 'psi;',
+ 'quot;',
+ 'quot',
+ 'rArr;',
+ 'radic;',
+ 'rang;',
+ 'raquo;',
+ 'raquo',
+ 'rarr;',
+ 'rceil;',
+ 'rdquo;',
+ 'real;',
+ 'reg;',
+ 'reg',
+ 'rfloor;',
+ 'rho;',
+ 'rlm;',
+ 'rsaquo;',
+ 'rsquo;',
+ 'sbquo;',
+ 'scaron;',
+ 'sdot;',
+ 'sect;',
+ 'sect',
+ 'shy;',
+ 'shy',
+ 'sigma;',
+ 'sigmaf;',
+ 'sim;',
+ 'spades;',
+ 'sub;',
+ 'sube;',
+ 'sum;',
+ 'sup1;',
+ 'sup1',
+ 'sup2;',
+ 'sup2',
+ 'sup3;',
+ 'sup3',
+ 'sup;',
+ 'supe;',
+ 'szlig;',
+ 'szlig',
+ 'tau;',
+ 'there4;',
+ 'theta;',
+ 'thetasym;',
+ 'thinsp;',
+ 'thorn;',
+ 'thorn',
+ 'tilde;',
+ 'times;',
+ 'times',
+ 'trade;',
+ 'uArr;',
+ 'uacute;',
+ 'uacute',
+ 'uarr;',
+ 'ucirc;',
+ 'ucirc',
+ 'ugrave;',
+ 'ugrave',
+ 'uml;',
+ 'uml',
+ 'upsih;',
+ 'upsilon;',
+ 'uuml;',
+ 'uuml',
+ 'weierp;',
+ 'xi;',
+ 'yacute;',
+ 'yacute',
+ 'yen;',
+ 'yen',
+ 'yuml;',
+ 'yuml',
+ 'zeta;',
+ 'zwj;',
+ 'zwnj;'
+ );
+
+ const PCDATA = 0;
+ const RCDATA = 1;
+ const CDATA = 2;
const PLAINTEXT = 3;
- const DOCTYPE = 0;
+ const DOCTYPE = 0;
const STARTTAG = 1;
- const ENDTAG = 2;
- const COMMENT = 3;
+ const ENDTAG = 2;
+ const COMMENT = 3;
const CHARACTR = 4;
- const EOF = 5;
-
- public function __construct($data) {
- $data = str_replace("\r\n", "\n", $data);
- $data = str_replace("\r", null, $data);
+ const EOF = 5;
+ public function __construct($data)
+ {
$this->data = $data;
$this->char = -1;
- $this->EOF = strlen($data);
+ $this->EOF = strlen($data);
$this->tree = new HTML5TreeConstructer;
$this->content_model = self::PCDATA;
$this->state = 'data';
- while($this->state !== null) {
- $this->{$this->state.'State'}();
+ while ($this->state !== null) {
+ $this->{$this->state . 'State'}();
}
}
- public function save() {
+ public function save()
+ {
return $this->tree->save();
}
- private function char() {
+ private function char()
+ {
return ($this->char < $this->EOF)
? $this->data[$this->char]
: false;
}
- private function character($s, $l = 0) {
- if($s + $l < $this->EOF) {
- if($l === 0) {
+ private function character($s, $l = 0)
+ {
+ if ($s + $l < $this->EOF) {
+ if ($l === 0) {
return $this->data[$s];
} else {
return substr($this->data, $s, $l);
@@ -161,46 +497,52 @@ class HTML5 {
}
}
- private function characters($char_class, $start) {
- return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start));
+ private function characters($char_class, $start)
+ {
+ return preg_replace('#^([' . $char_class . ']+).*#s', '\\1', substr($this->data, $start));
}
- private function dataState() {
+ private function dataState()
+ {
// Consume the next input character
$this->char++;
$char = $this->char();
- if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
+ if ($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
/* U+0026 AMPERSAND (&)
When the content model flag is set to one of the PCDATA or RCDATA
states: switch to the entity data state. Otherwise: treat it as per
the "anything else" entry below. */
$this->state = 'entityData';
- } elseif($char === '-') {
+ } elseif ($char === '-') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is false, and there are at
least three characters before this one in the input stream, and the
last four characters in the input stream, including this one, are
U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS,
and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */
- if(($this->content_model === self::RCDATA || $this->content_model ===
- self::CDATA) && $this->escape === false &&
- $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') {
+ if (($this->content_model === self::RCDATA || $this->content_model ===
+ self::CDATA) && $this->escape === false &&
+ $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--'
+ ) {
$this->escape = true;
}
/* In any case, emit the input character as a character token. Stay
in the data state. */
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => $char
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ )
+ );
- /* U+003C LESS-THAN SIGN (<) */
- } elseif($char === '<' && ($this->content_model === self::PCDATA ||
- (($this->content_model === self::RCDATA ||
- $this->content_model === self::CDATA) && $this->escape === false))) {
+ /* U+003C LESS-THAN SIGN (<) */
+ } elseif ($char === '<' && ($this->content_model === self::PCDATA ||
+ (($this->content_model === self::RCDATA ||
+ $this->content_model === self::CDATA) && $this->escape === false))
+ ) {
/* When the content model flag is set to the PCDATA state: switch
to the tag open state.
@@ -211,39 +553,44 @@ class HTML5 {
Otherwise: treat it as per the "anything else" entry below. */
$this->state = 'tagOpen';
- /* U+003E GREATER-THAN SIGN (>) */
- } elseif($char === '>') {
+ /* U+003E GREATER-THAN SIGN (>) */
+ } elseif ($char === '>') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is true, and the last three
characters in the input stream including this one are U+002D
HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"),
set the escape flag to false. */
- if(($this->content_model === self::RCDATA ||
- $this->content_model === self::CDATA) && $this->escape === true &&
- $this->character($this->char, 3) === '-->') {
+ if (($this->content_model === self::RCDATA ||
+ $this->content_model === self::CDATA) && $this->escape === true &&
+ $this->character($this->char, 3) === '-->'
+ ) {
$this->escape = false;
}
/* In any case, emit the input character as a character token.
Stay in the data state. */
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => $char
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ )
+ );
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Emit an end-of-file token. */
$this->EOF();
- } elseif($this->content_model === self::PLAINTEXT) {
+ } elseif ($this->content_model === self::PLAINTEXT) {
/* When the content model flag is set to the PLAINTEXT state
THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of
the text and emit it as a character token. */
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => substr($this->data, $this->char)
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => substr($this->data, $this->char)
+ )
+ );
$this->EOF();
@@ -252,37 +599,43 @@ class HTML5 {
THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that
otherwise would also be treated as a character token and emit it
as a single character token. Stay in the data state. */
- $len = strcspn($this->data, '<&', $this->char);
+ $len = strcspn($this->data, '<&', $this->char);
$char = substr($this->data, $this->char, $len);
$this->char += $len - 1;
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => $char
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ )
+ );
$this->state = 'data';
}
}
- private function entityDataState() {
+ private function entityDataState()
+ {
// Attempt to consume an entity.
$entity = $this->entity();
// If nothing is returned, emit a U+0026 AMPERSAND character token.
// Otherwise, emit the character token that was returned.
$char = (!$entity) ? '&' : $entity;
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => $char
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => $char
+ )
+ );
// Finally, switch to the data state.
$this->state = 'data';
}
- private function tagOpenState() {
- switch($this->content_model) {
+ private function tagOpenState()
+ {
+ switch ($this->content_model) {
case self::RCDATA:
case self::CDATA:
/* If the next input character is a U+002F SOLIDUS (/) character,
@@ -290,19 +643,21 @@ class HTML5 {
input character is not a U+002F SOLIDUS (/) character, emit a
U+003C LESS-THAN SIGN character token and switch to the data
state to process the next input character. */
- if($this->character($this->char + 1) === '/') {
+ if ($this->character($this->char + 1) === '/') {
$this->char++;
$this->state = 'closeTagOpen';
} else {
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => '<'
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => '<'
+ )
+ );
$this->state = 'data';
}
- break;
+ break;
case self::PCDATA:
// If the content model flag is set to the PCDATA state
@@ -310,42 +665,44 @@ class HTML5 {
$this->char++;
$char = $this->char();
- if($char === '!') {
+ if ($char === '!') {
/* U+0021 EXCLAMATION MARK (!)
Switch to the markup declaration open state. */
$this->state = 'markupDeclarationOpen';
- } elseif($char === '/') {
+ } elseif ($char === '/') {
/* U+002F SOLIDUS (/)
Switch to the close tag open state. */
$this->state = 'closeTagOpen';
- } elseif(preg_match('/^[A-Za-z]$/', $char)) {
+ } elseif (preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new start tag token, set its tag name to the lowercase
version of the input character (add 0x0020 to the character's code
point), then switch to the tag name state. (Don't emit the token
yet; further details will be filled in before it is emitted.) */
$this->token = array(
- 'name' => strtolower($char),
- 'type' => self::STARTTAG,
- 'attr' => array()
+ 'name' => strtolower($char),
+ 'type' => self::STARTTAG,
+ 'attr' => array()
);
$this->state = 'tagName';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Emit a U+003C LESS-THAN SIGN character token and a
U+003E GREATER-THAN SIGN character token. Switch to the data state. */
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => '<>'
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => '<>'
+ )
+ );
$this->state = 'data';
- } elseif($char === '?') {
+ } elseif ($char === '?') {
/* U+003F QUESTION MARK (?)
Parse error. Switch to the bogus comment state. */
$this->state = 'bogusComment';
@@ -354,25 +711,31 @@ class HTML5 {
/* Anything else
Parse error. Emit a U+003C LESS-THAN SIGN character token and
reconsume the current input character in the data state. */
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => '<'
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => '<'
+ )
+ );
$this->char--;
$this->state = 'data';
}
- break;
+ break;
}
}
- private function closeTagOpenState() {
+ private function closeTagOpenState()
+ {
$next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
$the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
- if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
- (!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/',
- $this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) {
+ if (($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
+ (!$the_same || ($the_same && (!preg_match(
+ '/[\t\n\x0b\x0c >\/]/',
+ $this->character($this->char + 1 + strlen($next_node))
+ ) || $this->EOF === $this->char)))
+ ) {
/* If the content model flag is set to the RCDATA or CDATA states then
examine the next few characters. If they do not match the tag name of
the last start tag token emitted (case insensitively), or if they do but
@@ -388,10 +751,12 @@ class HTML5 {
...then there is a parse error. Emit a U+003C LESS-THAN SIGN character
token, a U+002F SOLIDUS character token, and switch to the data state
to process the next input character. */
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => '</'
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => '</'
+ )
+ );
$this->state = 'data';
@@ -402,32 +767,34 @@ class HTML5 {
$this->char++;
$char = $this->char();
- if(preg_match('/^[A-Za-z]$/', $char)) {
+ if (preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new end tag token, set its tag name to the lowercase version
of the input character (add 0x0020 to the character's code point), then
switch to the tag name state. (Don't emit the token yet; further details
will be filled in before it is emitted.) */
$this->token = array(
- 'name' => strtolower($char),
- 'type' => self::ENDTAG
+ 'name' => strtolower($char),
+ 'type' => self::ENDTAG
);
$this->state = 'tagName';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Switch to the data state. */
$this->state = 'data';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F
SOLIDUS character token. Reconsume the EOF character in the data state. */
- $this->emitToken(array(
- 'type' => self::CHARACTR,
- 'data' => '</'
- ));
+ $this->emitToken(
+ array(
+ 'type' => self::CHARACTR,
+ 'data' => '</'
+ )
+ );
$this->char--;
$this->state = 'data';
@@ -439,12 +806,13 @@ class HTML5 {
}
}
- private function tagNameState() {
+ private function tagNameState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
@@ -453,13 +821,13 @@ class HTML5 {
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
@@ -468,7 +836,7 @@ class HTML5 {
$this->char--;
$this->state = 'data';
- } elseif($char === '/') {
+ } elseif ($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
@@ -483,12 +851,13 @@ class HTML5 {
}
}
- private function beforeAttributeNameState() {
+ private function beforeAttributeNameState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
@@ -497,19 +866,19 @@ class HTML5 {
Stay in the before attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
- } elseif($char === '/') {
+ } elseif ($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Stay in the before
attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
@@ -524,7 +893,7 @@ class HTML5 {
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
- 'name' => strtolower($char),
+ 'name' => strtolower($char),
'value' => null
);
@@ -532,12 +901,13 @@ class HTML5 {
}
}
- private function attributeNameState() {
+ private function attributeNameState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
@@ -546,24 +916,24 @@ class HTML5 {
Stay in the before attribute name state. */
$this->state = 'afterAttributeName';
- } elseif($char === '=') {
+ } elseif ($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
- } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+ } elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
@@ -583,12 +953,13 @@ class HTML5 {
}
}
- private function afterAttributeNameState() {
+ private function afterAttributeNameState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
@@ -597,24 +968,24 @@ class HTML5 {
Stay in the after attribute name state. */
$this->state = 'afterAttributeName';
- } elseif($char === '=') {
+ } elseif ($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
- } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+ } elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the
before attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
@@ -629,7 +1000,7 @@ class HTML5 {
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
- 'name' => strtolower($char),
+ 'name' => strtolower($char),
'value' => null
);
@@ -637,12 +1008,13 @@ class HTML5 {
}
}
- private function beforeAttributeValueState() {
+ private function beforeAttributeValueState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
@@ -651,24 +1023,24 @@ class HTML5 {
Stay in the before attribute value state. */
$this->state = 'beforeAttributeValue';
- } elseif($char === '"') {
+ } elseif ($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the attribute value (double-quoted) state. */
$this->state = 'attributeValueDoubleQuoted';
- } elseif($char === '&') {
+ } elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the attribute value (unquoted) state and reconsume
this input character. */
$this->char--;
$this->state = 'attributeValueUnquoted';
- } elseif($char === '\'') {
+ } elseif ($char === '\'') {
/* U+0027 APOSTROPHE (')
Switch to the attribute value (single-quoted) state. */
$this->state = 'attributeValueSingleQuoted';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
@@ -685,22 +1057,23 @@ class HTML5 {
}
}
- private function attributeValueDoubleQuotedState() {
+ private function attributeValueDoubleQuotedState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if($char === '"') {
+ if ($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($char === '&') {
+ } elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('double');
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
@@ -720,22 +1093,23 @@ class HTML5 {
}
}
- private function attributeValueSingleQuotedState() {
+ private function attributeValueSingleQuotedState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if($char === '\'') {
+ if ($char === '\'') {
/* U+0022 QUOTATION MARK (')
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($char === '&') {
+ } elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('single');
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
@@ -755,12 +1129,13 @@ class HTML5 {
}
}
- private function attributeValueUnquotedState() {
+ private function attributeValueUnquotedState()
+ {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
@@ -769,12 +1144,12 @@ class HTML5 {
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
- } elseif($char === '&') {
+ } elseif ($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState();
- } elseif($char === '>') {
+ } elseif ($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
@@ -791,7 +1166,8 @@ class HTML5 {
}
}
- private function entityInAttributeValueState() {
+ private function entityInAttributeValueState()
+ {
// Attempt to consume an entity.
$entity = $this->entity();
@@ -806,7 +1182,8 @@ class HTML5 {
$this->token['attr'][$last]['value'] .= $char;
}
- private function bogusCommentState() {
+ private function bogusCommentState()
+ {
/* Consume every character up to the first U+003E GREATER-THAN SIGN
character (>) or the end of the file (EOF), whichever comes first. Emit
a comment token whose data is the concatenation of all the characters
@@ -816,10 +1193,12 @@ class HTML5 {
end of the file otherwise. (If the comment was started by the end of
the file (EOF), the token is empty.) */
$data = $this->characters('^>', $this->char);
- $this->emitToken(array(
- 'data' => $data,
- 'type' => self::COMMENT
- ));
+ $this->emitToken(
+ array(
+ 'data' => $data,
+ 'type' => self::COMMENT
+ )
+ );
$this->char += strlen($data);
@@ -827,16 +1206,17 @@ class HTML5 {
$this->state = 'data';
/* If the end of the file was reached, reconsume the EOF character. */
- if($this->char === $this->EOF) {
+ if ($this->char === $this->EOF) {
$this->char = $this->EOF - 1;
}
}
- private function markupDeclarationOpenState() {
+ private function markupDeclarationOpenState()
+ {
/* If the next two characters are both U+002D HYPHEN-MINUS (-)
characters, consume those two characters, create a comment token whose
data is the empty string, and switch to the comment state. */
- if($this->character($this->char + 1, 2) === '--') {
+ if ($this->character($this->char + 1, 2) === '--') {
$this->char += 2;
$this->state = 'comment';
$this->token = array(
@@ -844,41 +1224,42 @@ class HTML5 {
'type' => self::COMMENT
);
- /* Otherwise if the next seven chacacters are a case-insensitive match
- for the word "DOCTYPE", then consume those characters and switch to the
- DOCTYPE state. */
- } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') {
+ /* Otherwise if the next seven chacacters are a case-insensitive match
+ for the word "DOCTYPE", then consume those characters and switch to the
+ DOCTYPE state. */
+ } elseif (strtolower($this->character($this->char + 1, 7)) === 'doctype') {
$this->char += 7;
$this->state = 'doctype';
- /* Otherwise, is is a parse error. Switch to the bogus comment state.
- The next character that is consumed, if any, is the first character
- that will be in the comment. */
+ /* Otherwise, is is a parse error. Switch to the bogus comment state.
+ The next character that is consumed, if any, is the first character
+ that will be in the comment. */
} else {
$this->char++;
$this->state = 'bogusComment';
}
}
- private function commentState() {
+ private function commentState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
- if($char === '-') {
+ if ($char === '-') {
/* Switch to the comment dash state */
$this->state = 'commentDash';
- /* EOF */
- } elseif($this->char === $this->EOF) {
+ /* EOF */
+ } elseif ($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
- /* Anything else */
+ /* Anything else */
} else {
/* Append the input character to the comment token's data. Stay in
the comment state. */
@@ -886,62 +1267,65 @@ class HTML5 {
}
}
- private function commentDashState() {
+ private function commentDashState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
- if($char === '-') {
+ if ($char === '-') {
/* Switch to the comment end state */
$this->state = 'commentEnd';
- /* EOF */
- } elseif($this->char === $this->EOF) {
+ /* EOF */
+ } elseif ($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
- /* Anything else */
+ /* Anything else */
} else {
/* Append a U+002D HYPHEN-MINUS (-) character and the input
character to the comment token's data. Switch to the comment state. */
- $this->token['data'] .= '-'.$char;
+ $this->token['data'] .= '-' . $char;
$this->state = 'comment';
}
}
- private function commentEndState() {
+ private function commentEndState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
- if($char === '>') {
+ if ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
- } elseif($char === '-') {
+ } elseif ($char === '-') {
$this->token['data'] .= '-';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
- $this->token['data'] .= '--'.$char;
+ $this->token['data'] .= '--' . $char;
$this->state = 'comment';
}
}
- private function doctypeState() {
+ private function doctypeState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'beforeDoctypeName';
} else {
@@ -950,15 +1334,16 @@ class HTML5 {
}
}
- private function beforeDoctypeNameState() {
+ private function beforeDoctypeNameState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the before DOCTYPE name state.
- } elseif(preg_match('/^[a-z]$/', $char)) {
+ } elseif (preg_match('/^[a-z]$/', $char)) {
$this->token = array(
'name' => strtoupper($char),
'type' => self::DOCTYPE,
@@ -967,21 +1352,25 @@ class HTML5 {
$this->state = 'doctypeName';
- } elseif($char === '>') {
- $this->emitToken(array(
- 'name' => null,
- 'type' => self::DOCTYPE,
- 'error' => true
- ));
+ } elseif ($char === '>') {
+ $this->emitToken(
+ array(
+ 'name' => null,
+ 'type' => self::DOCTYPE,
+ 'error' => true
+ )
+ );
$this->state = 'data';
- } elseif($this->char === $this->EOF) {
- $this->emitToken(array(
- 'name' => null,
- 'type' => self::DOCTYPE,
- 'error' => true
- ));
+ } elseif ($this->char === $this->EOF) {
+ $this->emitToken(
+ array(
+ 'name' => null,
+ 'type' => self::DOCTYPE,
+ 'error' => true
+ )
+ );
$this->char--;
$this->state = 'data';
@@ -997,22 +1386,23 @@ class HTML5 {
}
}
- private function doctypeNameState() {
+ private function doctypeNameState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'AfterDoctypeName';
- } elseif($char === '>') {
+ } elseif ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
- } elseif(preg_match('/^[a-z]$/', $char)) {
+ } elseif (preg_match('/^[a-z]$/', $char)) {
$this->token['name'] .= strtoupper($char);
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
@@ -1026,19 +1416,20 @@ class HTML5 {
: true;
}
- private function afterDoctypeNameState() {
+ private function afterDoctypeNameState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
- if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+ if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the DOCTYPE name state.
- } elseif($char === '>') {
+ } elseif ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
@@ -1049,16 +1440,17 @@ class HTML5 {
}
}
- private function bogusDoctypeState() {
+ private function bogusDoctypeState()
+ {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
- if($char === '>') {
+ if ($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
- } elseif($this->char === $this->EOF) {
+ } elseif ($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
@@ -1068,22 +1460,23 @@ class HTML5 {
}
}
- private function entity() {
+ private function entity()
+ {
$start = $this->char;
// This section defines how to consume an entity. This definition is
// used when parsing entities in text and in attributes.
// The behaviour depends on the identity of the next character (the
- // one immediately after the U+0026 AMPERSAND character):
+ // one immediately after the U+0026 AMPERSAND character):
- switch($this->character($this->char + 1)) {
+ switch ($this->character($this->char + 1)) {
// U+0023 NUMBER SIGN (#)
case '#':
// The behaviour further depends on the character after the
// U+0023 NUMBER SIGN:
- switch($this->character($this->char + 1)) {
+ switch ($this->character($this->char + 1)) {
// U+0078 LATIN SMALL LETTER X
// U+0058 LATIN CAPITAL LETTER X
case 'x':
@@ -1096,7 +1489,7 @@ class HTML5 {
// words, 0-9, A-F, a-f).
$char = 1;
$char_class = '0-9A-Fa-f';
- break;
+ break;
// Anything else
default:
@@ -1105,7 +1498,7 @@ class HTML5 {
// NINE (i.e. just 0-9).
$char = 0;
$char_class = '0-9';
- break;
+ break;
}
// Consume as many characters as match the range of characters
@@ -1116,7 +1509,7 @@ class HTML5 {
$cond = strlen($e_name) > 0;
// The rest of the parsing happens bellow.
- break;
+ break;
// Anything else
default:
@@ -1126,12 +1519,12 @@ class HTML5 {
$e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
$len = strlen($e_name);
- for($c = 1; $c <= $len; $c++) {
+ for ($c = 1; $c <= $len; $c++) {
$id = substr($e_name, 0, $c);
$this->char++;
- if(in_array($id, $this->entities)) {
- if ($e_name[$c-1] !== ';') {
+ if (in_array($id, $this->entities)) {
+ if ($e_name[$c - 1] !== ';') {
if ($c < $len && $e_name[$c] == ';') {
$this->char++; // consume extra semicolon
}
@@ -1143,10 +1536,10 @@ class HTML5 {
$cond = isset($entity);
// The rest of the parsing happens bellow.
- break;
+ break;
}
- if(!$cond) {
+ if (!$cond) {
// If no match can be made, then this is a parse error. No
// characters are consumed, and nothing is returned.
$this->char = $start;
@@ -1155,81 +1548,157 @@ class HTML5 {
// Return a character token for the character corresponding to the
// entity name (as given by the second column of the entities table).
- return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8');
+ return html_entity_decode('&' . $entity . ';', ENT_QUOTES, 'UTF-8');
}
- private function emitToken($token) {
+ private function emitToken($token)
+ {
$emit = $this->tree->emitToken($token);
- if(is_int($emit)) {
+ if (is_int($emit)) {
$this->content_model = $emit;
- } elseif($token['type'] === self::ENDTAG) {
+ } elseif ($token['type'] === self::ENDTAG) {
$this->content_model = self::PCDATA;
}
}
- private function EOF() {
+ private function EOF()
+ {
$this->state = null;
- $this->tree->emitToken(array(
- 'type' => self::EOF
- ));
+ $this->tree->emitToken(
+ array(
+ 'type' => self::EOF
+ )
+ );
}
}
-class HTML5TreeConstructer {
+class HTML5TreeConstructer
+{
public $stack = array();
private $phase;
private $mode;
private $dom;
private $foster_parent = null;
- private $a_formatting = array();
+ private $a_formatting = array();
private $head_pointer = null;
private $form_pointer = null;
- private $scoping = array('button','caption','html','marquee','object','table','td','th');
- private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u');
- private $special = array('address','area','base','basefont','bgsound',
- 'blockquote','body','br','center','col','colgroup','dd','dir','div','dl',
- 'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5',
- 'h6','head','hr','iframe','image','img','input','isindex','li','link',
- 'listing','menu','meta','noembed','noframes','noscript','ol','optgroup',
- 'option','p','param','plaintext','pre','script','select','spacer','style',
- 'tbody','textarea','tfoot','thead','title','tr','ul','wbr');
+ private $scoping = array('button', 'caption', 'html', 'marquee', 'object', 'table', 'td', 'th');
+ private $formatting = array(
+ 'a',
+ 'b',
+ 'big',
+ 'em',
+ 'font',
+ 'i',
+ 'nobr',
+ 's',
+ 'small',
+ 'strike',
+ 'strong',
+ 'tt',
+ 'u'
+ );
+ private $special = array(
+ 'address',
+ 'area',
+ 'base',
+ 'basefont',
+ 'bgsound',
+ 'blockquote',
+ 'body',
+ 'br',
+ 'center',
+ 'col',
+ 'colgroup',
+ 'dd',
+ 'dir',
+ 'div',
+ 'dl',
+ 'dt',
+ 'embed',
+ 'fieldset',
+ 'form',
+ 'frame',
+ 'frameset',
+ 'h1',
+ 'h2',
+ 'h3',
+ 'h4',
+ 'h5',
+ 'h6',
+ 'head',
+ 'hr',
+ 'iframe',
+ 'image',
+ 'img',
+ 'input',
+ 'isindex',
+ 'li',
+ 'link',
+ 'listing',
+ 'menu',
+ 'meta',
+ 'noembed',
+ 'noframes',
+ 'noscript',
+ 'ol',
+ 'optgroup',
+ 'option',
+ 'p',
+ 'param',
+ 'plaintext',
+ 'pre',
+ 'script',
+ 'select',
+ 'spacer',
+ 'style',
+ 'tbody',
+ 'textarea',
+ 'tfoot',
+ 'thead',
+ 'title',
+ 'tr',
+ 'ul',
+ 'wbr'
+ );
// The different phases.
const INIT_PHASE = 0;
const ROOT_PHASE = 1;
const MAIN_PHASE = 2;
- const END_PHASE = 3;
+ const END_PHASE = 3;
// The different insertion modes for the main phase.
const BEFOR_HEAD = 0;
- const IN_HEAD = 1;
+ const IN_HEAD = 1;
const AFTER_HEAD = 2;
- const IN_BODY = 3;
- const IN_TABLE = 4;
+ const IN_BODY = 3;
+ const IN_TABLE = 4;
const IN_CAPTION = 5;
- const IN_CGROUP = 6;
- const IN_TBODY = 7;
- const IN_ROW = 8;
- const IN_CELL = 9;
- const IN_SELECT = 10;
+ const IN_CGROUP = 6;
+ const IN_TBODY = 7;
+ const IN_ROW = 8;
+ const IN_CELL = 9;
+ const IN_SELECT = 10;
const AFTER_BODY = 11;
- const IN_FRAME = 12;
+ const IN_FRAME = 12;
const AFTR_FRAME = 13;
// The different types of elements.
- const SPECIAL = 0;
- const SCOPING = 1;
+ const SPECIAL = 0;
+ const SCOPING = 1;
const FORMATTING = 2;
- const PHRASING = 3;
+ const PHRASING = 3;
- const MARKER = 0;
+ const MARKER = 0;
- public function __construct() {
+ public function __construct()
+ {
$this->phase = self::INIT_PHASE;
$this->mode = self::BEFOR_HEAD;
$this->dom = new DOMDocument;
@@ -1241,16 +1710,26 @@ class HTML5TreeConstructer {
}
// Process tag tokens
- public function emitToken($token) {
- switch($this->phase) {
- case self::INIT_PHASE: return $this->initPhase($token); break;
- case self::ROOT_PHASE: return $this->rootElementPhase($token); break;
- case self::MAIN_PHASE: return $this->mainPhase($token); break;
- case self::END_PHASE : return $this->trailingEndPhase($token); break;
+ public function emitToken($token)
+ {
+ switch ($this->phase) {
+ case self::INIT_PHASE:
+ return $this->initPhase($token);
+ break;
+ case self::ROOT_PHASE:
+ return $this->rootElementPhase($token);
+ break;
+ case self::MAIN_PHASE:
+ return $this->mainPhase($token);
+ break;
+ case self::END_PHASE :
+ return $this->trailingEndPhase($token);
+ break;
}
}
- private function initPhase($token) {
+ private function initPhase($token)
+ {
/* Initially, the tree construction stage must handle each token
emitted from the tokenisation stage as follows: */
@@ -1262,13 +1741,14 @@ class HTML5TreeConstructer {
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE
An end-of-file token */
- if((isset($token['error']) && $token['error']) ||
- $token['type'] === HTML5::COMMENT ||
- $token['type'] === HTML5::STARTTAG ||
- $token['type'] === HTML5::ENDTAG ||
- $token['type'] === HTML5::EOF ||
- ($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
- !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) {
+ if ((isset($token['error']) && $token['error']) ||
+ $token['type'] === HTML5::COMMENT ||
+ $token['type'] === HTML5::STARTTAG ||
+ $token['type'] === HTML5::ENDTAG ||
+ $token['type'] === HTML5::EOF ||
+ ($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
+ !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))
+ ) {
/* This specification does not define how to handle this case. In
particular, user agents may ignore the entirety of this specification
altogether for such documents, and instead invoke special parse modes
@@ -1277,8 +1757,8 @@ class HTML5TreeConstructer {
$this->phase = self::ROOT_PHASE;
return $this->rootElementPhase($token);
- /* A DOCTYPE token marked as being correct */
- } elseif(isset($token['error']) && !$token['error']) {
+ /* A DOCTYPE token marked as being correct */
+ } elseif (isset($token['error']) && !$token['error']) {
/* Append a DocumentType node to the Document node, with the name
attribute set to the name given in the DOCTYPE token (which will be
"HTML"), and the other attributes specific to DocumentType objects
@@ -1289,52 +1769,58 @@ class HTML5TreeConstructer {
stage. */
$this->phase = self::ROOT_PHASE;
- /* A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
- or U+0020 SPACE */
- } elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
- $token['data'])) {
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ } elseif (isset($token['data']) && preg_match(
+ '/^[\t\n\x0b\x0c ]+$/',
+ $token['data']
+ )
+ ) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
}
}
- private function rootElementPhase($token) {
+ private function rootElementPhase($token)
+ {
/* After the initial phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
- if($token['type'] === HTML5::DOCTYPE) {
+ if ($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
- /* A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
- or U+0020 SPACE */
- } elseif($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ } elseif ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
- /* A character token that is not one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED
- (FF), or U+0020 SPACE
- A start tag token
- An end tag token
- An end-of-file token */
- } elseif(($token['type'] === HTML5::CHARACTR &&
- !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
- $token['type'] === HTML5::STARTTAG ||
- $token['type'] === HTML5::ENDTAG ||
- $token['type'] === HTML5::EOF) {
+ /* A character token that is not one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED
+ (FF), or U+0020 SPACE
+ A start tag token
+ An end tag token
+ An end-of-file token */
+ } elseif (($token['type'] === HTML5::CHARACTR &&
+ !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
+ $token['type'] === HTML5::STARTTAG ||
+ $token['type'] === HTML5::ENDTAG ||
+ $token['type'] === HTML5::EOF
+ ) {
/* Create an HTMLElement node with the tag name html, in the HTML
namespace. Append it to the Document object. Switch to the main
phase and reprocess the current token. */
@@ -1347,15 +1833,16 @@ class HTML5TreeConstructer {
}
}
- private function mainPhase($token) {
+ private function mainPhase($token)
+ {
/* Tokens in the main phase must be handled as follows: */
/* A DOCTYPE token */
- if($token['type'] === HTML5::DOCTYPE) {
+ if ($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
- /* A start tag token with the tag name "html" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
+ /* A start tag token with the tag name "html" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
/* If this start tag token was not the first start tag token, then
it is a parse error. */
@@ -1363,59 +1850,91 @@ class HTML5TreeConstructer {
is already present on the top element of the stack of open elements.
If it is not, add the attribute and its corresponding value to that
element. */
- foreach($token['attr'] as $attr) {
- if(!$this->stack[0]->hasAttribute($attr['name'])) {
+ foreach ($token['attr'] as $attr) {
+ if (!$this->stack[0]->hasAttribute($attr['name'])) {
$this->stack[0]->setAttribute($attr['name'], $attr['value']);
}
}
- /* An end-of-file token */
- } elseif($token['type'] === HTML5::EOF) {
+ /* An end-of-file token */
+ } elseif ($token['type'] === HTML5::EOF) {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
- /* Anything else. */
+ /* Anything else. */
} else {
/* Depends on the insertion mode: */
- switch($this->mode) {
- case self::BEFOR_HEAD: return $this->beforeHead($token); break;
- case self::IN_HEAD: return $this->inHead($token); break;
- case self::AFTER_HEAD: return $this->afterHead($token); break;
- case self::IN_BODY: return $this->inBody($token); break;
- case self::IN_TABLE: return $this->inTable($token); break;
- case self::IN_CAPTION: return $this->inCaption($token); break;
- case self::IN_CGROUP: return $this->inColumnGroup($token); break;
- case self::IN_TBODY: return $this->inTableBody($token); break;
- case self::IN_ROW: return $this->inRow($token); break;
- case self::IN_CELL: return $this->inCell($token); break;
- case self::IN_SELECT: return $this->inSelect($token); break;
- case self::AFTER_BODY: return $this->afterBody($token); break;
- case self::IN_FRAME: return $this->inFrameset($token); break;
- case self::AFTR_FRAME: return $this->afterFrameset($token); break;
- case self::END_PHASE: return $this->trailingEndPhase($token); break;
+ switch ($this->mode) {
+ case self::BEFOR_HEAD:
+ return $this->beforeHead($token);
+ break;
+ case self::IN_HEAD:
+ return $this->inHead($token);
+ break;
+ case self::AFTER_HEAD:
+ return $this->afterHead($token);
+ break;
+ case self::IN_BODY:
+ return $this->inBody($token);
+ break;
+ case self::IN_TABLE:
+ return $this->inTable($token);
+ break;
+ case self::IN_CAPTION:
+ return $this->inCaption($token);
+ break;
+ case self::IN_CGROUP:
+ return $this->inColumnGroup($token);
+ break;
+ case self::IN_TBODY:
+ return $this->inTableBody($token);
+ break;
+ case self::IN_ROW:
+ return $this->inRow($token);
+ break;
+ case self::IN_CELL:
+ return $this->inCell($token);
+ break;
+ case self::IN_SELECT:
+ return $this->inSelect($token);
+ break;
+ case self::AFTER_BODY:
+ return $this->afterBody($token);
+ break;
+ case self::IN_FRAME:
+ return $this->inFrameset($token);
+ break;
+ case self::AFTR_FRAME:
+ return $this->afterFrameset($token);
+ break;
+ case self::END_PHASE:
+ return $this->trailingEndPhase($token);
+ break;
}
}
}
- private function beforeHead($token) {
+ private function beforeHead($token)
+ {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
- if($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ if ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Append the character to the current node. */
$this->insertText($token['data']);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
- /* A start tag token with the tag name "head" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
+ /* A start tag token with the tag name "head" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
/* Create an element for the token, append the new element to the
current node and push it onto the stack of open elements. */
$element = $this->insertElement($token);
@@ -1426,32 +1945,38 @@ class HTML5TreeConstructer {
/* Change the insertion mode to "in head". */
$this->mode = self::IN_HEAD;
- /* A start tag token whose tag name is one of: "base", "link", "meta",
- "script", "style", "title". Or an end tag with the tag name "html".
- Or a character token that is not one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
- or U+0020 SPACE. Or any other start tag token */
- } elseif($token['type'] === HTML5::STARTTAG ||
- ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
- ($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/',
- $token['data']))) {
+ /* A start tag token whose tag name is one of: "base", "link", "meta",
+ "script", "style", "title". Or an end tag with the tag name "html".
+ Or a character token that is not one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE. Or any other start tag token */
+ } elseif ($token['type'] === HTML5::STARTTAG ||
+ ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
+ ($token['type'] === HTML5::CHARACTR && !preg_match(
+ '/^[\t\n\x0b\x0c ]$/',
+ $token['data']
+ ))
+ ) {
/* Act as if a start tag token with the tag name "head" and no
attributes had been seen, then reprocess the current token. */
- $this->beforeHead(array(
- 'name' => 'head',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
+ $this->beforeHead(
+ array(
+ 'name' => 'head',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
return $this->inHead($token);
- /* Any other end tag */
- } elseif($token['type'] === HTML5::ENDTAG) {
+ /* Any other end tag */
+ } elseif ($token['type'] === HTML5::ENDTAG) {
/* Parse error. Ignore the token. */
}
}
- private function inHead($token) {
+ private function inHead($token)
+ {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
@@ -1461,30 +1986,34 @@ class HTML5TreeConstructer {
THIS DIFFERS FROM THE SPEC: If the current node is either a title, style
or script element, append the character to the current node regardless
of its content. */
- if(($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
- $token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName,
- array('title', 'style', 'script')))) {
+ if (($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
+ $token['type'] === HTML5::CHARACTR && in_array(
+ end($this->stack)->nodeName,
+ array('title', 'style', 'script')
+ ))
+ ) {
/* Append the character to the current node. */
$this->insertText($token['data']);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
- } elseif($token['type'] === HTML5::ENDTAG &&
- in_array($token['name'], array('title', 'style', 'script'))) {
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ in_array($token['name'], array('title', 'style', 'script'))
+ ) {
array_pop($this->stack);
return HTML5::PCDATA;
- /* A start tag with the tag name "title" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
+ /* A start tag with the tag name "title" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
- if($this->head_pointer !== null) {
+ if ($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
@@ -1495,12 +2024,12 @@ class HTML5TreeConstructer {
/* Switch the tokeniser's content model flag to the RCDATA state. */
return HTML5::RCDATA;
- /* A start tag with the tag name "style" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
+ /* A start tag with the tag name "style" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
- if($this->head_pointer !== null) {
+ if ($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
@@ -1511,8 +2040,8 @@ class HTML5TreeConstructer {
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
- /* A start tag with the tag name "script" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
+ /* A start tag with the tag name "script" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
/* Create an element for the token. */
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
@@ -1520,13 +2049,16 @@ class HTML5TreeConstructer {
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
- /* A start tag with the tag name "base", "link", or "meta" */
- } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('base', 'link', 'meta'))) {
+ /* A start tag with the tag name "base", "link", or "meta" */
+ } elseif ($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array('base', 'link', 'meta')
+ )
+ ) {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
- if($this->head_pointer !== null) {
+ if ($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
array_pop($this->stack);
@@ -1535,14 +2067,14 @@ class HTML5TreeConstructer {
$this->insertElement($token);
}
- /* An end tag with the tag name "head" */
- } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
+ /* An end tag with the tag name "head" */
+ } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
/* If the current node is a head element, pop the current node off
the stack of open elements. */
- if($this->head_pointer->isSameNode(end($this->stack))) {
+ if ($this->head_pointer->isSameNode(end($this->stack))) {
array_pop($this->stack);
- /* Otherwise, this is a parse error. */
+ /* Otherwise, this is a parse error. */
} else {
// k
}
@@ -1550,22 +2082,25 @@ class HTML5TreeConstructer {
/* Change the insertion mode to "after head". */
$this->mode = self::AFTER_HEAD;
- /* A start tag with the tag name "head" or an end tag except "html". */
- } elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
- ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) {
+ /* A start tag with the tag name "head" or an end tag except "html". */
+ } elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
+ ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')
+ ) {
// Parse error. Ignore the token.
- /* Anything else */
+ /* Anything else */
} else {
/* If the current node is a head element, act as if an end tag
token with the tag name "head" had been seen. */
- if($this->head_pointer->isSameNode(end($this->stack))) {
- $this->inHead(array(
- 'name' => 'head',
- 'type' => HTML5::ENDTAG
- ));
+ if ($this->head_pointer->isSameNode(end($this->stack))) {
+ $this->inHead(
+ array(
+ 'name' => 'head',
+ 'type' => HTML5::ENDTAG
+ )
+ );
- /* Otherwise, change the insertion mode to "after head". */
+ /* Otherwise, change the insertion mode to "after head". */
} else {
$this->mode = self::AFTER_HEAD;
}
@@ -1575,66 +2110,74 @@ class HTML5TreeConstructer {
}
}
- private function afterHead($token) {
+ private function afterHead($token)
+ {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
- if($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ if ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Append the character to the current node. */
$this->insertText($token['data']);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
- /* A start tag token with the tag name "body" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
+ /* A start tag token with the tag name "body" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
/* Insert a body element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in body". */
$this->mode = self::IN_BODY;
- /* A start tag token with the tag name "frameset" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
+ /* A start tag token with the tag name "frameset" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
/* Insert a frameset element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in frameset". */
$this->mode = self::IN_FRAME;
- /* A start tag token whose tag name is one of: "base", "link", "meta",
- "script", "style", "title" */
- } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('base', 'link', 'meta', 'script', 'style', 'title'))) {
+ /* A start tag token whose tag name is one of: "base", "link", "meta",
+ "script", "style", "title" */
+ } elseif ($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array('base', 'link', 'meta', 'script', 'style', 'title')
+ )
+ ) {
/* Parse error. Switch the insertion mode back to "in head" and
reprocess the token. */
$this->mode = self::IN_HEAD;
return $this->inHead($token);
- /* Anything else */
+ /* Anything else */
} else {
/* Act as if a start tag token with the tag name "body" and no
attributes had been seen, and then reprocess the current token. */
- $this->afterHead(array(
- 'name' => 'body',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
+ $this->afterHead(
+ array(
+ 'name' => 'body',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
return $this->inBody($token);
}
}
- private function inBody($token) {
+ private function inBody($token)
+ {
/* Handle the token as follows: */
- switch($token['type']) {
+ switch ($token['type']) {
/* A character token */
case HTML5::CHARACTR:
/* Reconstruct the active formatting elements, if any. */
@@ -1642,1015 +2185,1159 @@ class HTML5TreeConstructer {
/* Append the token's character to the current node. */
$this->insertText($token['data']);
- break;
+ break;
/* A comment token */
case HTML5::COMMENT:
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
- break;
+ break;
case HTML5::STARTTAG:
- switch($token['name']) {
- /* A start tag token whose tag name is one of: "script",
- "style" */
- case 'script': case 'style':
- /* Process the token as if the insertion mode had been "in
- head". */
- return $this->inHead($token);
- break;
+ switch ($token['name']) {
+ /* A start tag token whose tag name is one of: "script",
+ "style" */
+ case 'script':
+ case 'style':
+ /* Process the token as if the insertion mode had been "in
+ head". */
+ return $this->inHead($token);
+ break;
- /* A start tag token whose tag name is one of: "base", "link",
- "meta", "title" */
- case 'base': case 'link': case 'meta': case 'title':
- /* Parse error. Process the token as if the insertion mode
- had been "in head". */
- return $this->inHead($token);
- break;
+ /* A start tag token whose tag name is one of: "base", "link",
+ "meta", "title" */
+ case 'base':
+ case 'link':
+ case 'meta':
+ case 'title':
+ /* Parse error. Process the token as if the insertion mode
+ had been "in head". */
+ return $this->inHead($token);
+ break;
- /* A start tag token with the tag name "body" */
- case 'body':
- /* Parse error. If the second element on the stack of open
- elements is not a body element, or, if the stack of open
- elements has only one node on it, then ignore the token.
- (innerHTML case) */
- if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
- // Ignore
-
- /* Otherwise, for each attribute on the token, check to see
- if the attribute is already present on the body element (the
- second element) on the stack of open elements. If it is not,
- add the attribute and its corresponding value to that
- element. */
- } else {
- foreach($token['attr'] as $attr) {
- if(!$this->stack[1]->hasAttribute($attr['name'])) {
- $this->stack[1]->setAttribute($attr['name'], $attr['value']);
+ /* A start tag token with the tag name "body" */
+ case 'body':
+ /* Parse error. If the second element on the stack of open
+ elements is not a body element, or, if the stack of open
+ elements has only one node on it, then ignore the token.
+ (innerHTML case) */
+ if (count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
+ // Ignore
+
+ /* Otherwise, for each attribute on the token, check to see
+ if the attribute is already present on the body element (the
+ second element) on the stack of open elements. If it is not,
+ add the attribute and its corresponding value to that
+ element. */
+ } else {
+ foreach ($token['attr'] as $attr) {
+ if (!$this->stack[1]->hasAttribute($attr['name'])) {
+ $this->stack[1]->setAttribute($attr['name'], $attr['value']);
+ }
}
}
- }
- break;
-
- /* A start tag whose tag name is one of: "address",
- "blockquote", "center", "dir", "div", "dl", "fieldset",
- "listing", "menu", "ol", "p", "ul" */
- case 'address': case 'blockquote': case 'center': case 'dir':
- case 'div': case 'dl': case 'fieldset': case 'listing':
- case 'menu': case 'ol': case 'p': case 'ul':
- /* If the stack of open elements has a p element in scope,
- then act as if an end tag with the tag name p had been
- seen. */
- if($this->elementInScope('p')) {
- $this->emitToken(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
- }
-
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
- break;
+ break;
- /* A start tag whose tag name is "form" */
- case 'form':
- /* If the form element pointer is not null, ignore the
- token with a parse error. */
- if($this->form_pointer !== null) {
- // Ignore.
-
- /* Otherwise: */
- } else {
- /* If the stack of open elements has a p element in
- scope, then act as if an end tag with the tag name p
- had been seen. */
- if($this->elementInScope('p')) {
- $this->emitToken(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
+ /* A start tag whose tag name is one of: "address",
+ "blockquote", "center", "dir", "div", "dl", "fieldset",
+ "listing", "menu", "ol", "p", "ul" */
+ case 'address':
+ case 'blockquote':
+ case 'center':
+ case 'dir':
+ case 'div':
+ case 'dl':
+ case 'fieldset':
+ case 'listing':
+ case 'menu':
+ case 'ol':
+ case 'p':
+ case 'ul':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been
+ seen. */
+ if ($this->elementInScope('p')) {
+ $this->emitToken(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
- /* Insert an HTML element for the token, and set the
- form element pointer to point to the element created. */
- $element = $this->insertElement($token);
- $this->form_pointer = $element;
- }
- break;
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+ break;
- /* A start tag whose tag name is "li", "dd" or "dt" */
- case 'li': case 'dd': case 'dt':
- /* If the stack of open elements has a p element in scope,
- then act as if an end tag with the tag name p had been
- seen. */
- if($this->elementInScope('p')) {
- $this->emitToken(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
- }
+ /* A start tag whose tag name is "form" */
+ case 'form':
+ /* If the form element pointer is not null, ignore the
+ token with a parse error. */
+ if ($this->form_pointer !== null) {
+ // Ignore.
- $stack_length = count($this->stack) - 1;
-
- for($n = $stack_length; 0 <= $n; $n--) {
- /* 1. Initialise node to be the current node (the
- bottommost node of the stack). */
- $stop = false;
- $node = $this->stack[$n];
- $cat = $this->getElementCategory($node->tagName);
-
- /* 2. If node is an li, dd or dt element, then pop all
- the nodes from the current node up to node, including
- node, then stop this algorithm. */
- if($token['name'] === $node->tagName || ($token['name'] !== 'li'
- && ($node->tagName === 'dd' || $node->tagName === 'dt'))) {
- for($x = $stack_length; $x >= $n ; $x--) {
- array_pop($this->stack);
+ /* Otherwise: */
+ } else {
+ /* If the stack of open elements has a p element in
+ scope, then act as if an end tag with the tag name p
+ had been seen. */
+ if ($this->elementInScope('p')) {
+ $this->emitToken(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
- break;
+ /* Insert an HTML element for the token, and set the
+ form element pointer to point to the element created. */
+ $element = $this->insertElement($token);
+ $this->form_pointer = $element;
}
+ break;
- /* 3. If node is not in the formatting category, and is
- not in the phrasing category, and is not an address or
- div element, then stop this algorithm. */
- if($cat !== self::FORMATTING && $cat !== self::PHRASING &&
- $node->tagName !== 'address' && $node->tagName !== 'div') {
- break;
+ /* A start tag whose tag name is "li", "dd" or "dt" */
+ case 'li':
+ case 'dd':
+ case 'dt':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been
+ seen. */
+ if ($this->elementInScope('p')) {
+ $this->emitToken(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
- }
- /* Finally, insert an HTML element with the same tag
- name as the token's. */
- $this->insertElement($token);
- break;
+ $stack_length = count($this->stack) - 1;
+
+ for ($n = $stack_length; 0 <= $n; $n--) {
+ /* 1. Initialise node to be the current node (the
+ bottommost node of the stack). */
+ $stop = false;
+ $node = $this->stack[$n];
+ $cat = $this->getElementCategory($node->tagName);
+
+ /* 2. If node is an li, dd or dt element, then pop all
+ the nodes from the current node up to node, including
+ node, then stop this algorithm. */
+ if ($token['name'] === $node->tagName || ($token['name'] !== 'li'
+ && ($node->tagName === 'dd' || $node->tagName === 'dt'))
+ ) {
+ for ($x = $stack_length; $x >= $n; $x--) {
+ array_pop($this->stack);
+ }
- /* A start tag token whose tag name is "plaintext" */
- case 'plaintext':
- /* If the stack of open elements has a p element in scope,
- then act as if an end tag with the tag name p had been
- seen. */
- if($this->elementInScope('p')) {
- $this->emitToken(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
- }
+ break;
+ }
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* 3. If node is not in the formatting category, and is
+ not in the phrasing category, and is not an address or
+ div element, then stop this algorithm. */
+ if ($cat !== self::FORMATTING && $cat !== self::PHRASING &&
+ $node->tagName !== 'address' && $node->tagName !== 'div'
+ ) {
+ break;
+ }
+ }
- return HTML5::PLAINTEXT;
- break;
+ /* Finally, insert an HTML element with the same tag
+ name as the token's. */
+ $this->insertElement($token);
+ break;
- /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
- "h5", "h6" */
- case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
- /* If the stack of open elements has a p element in scope,
- then act as if an end tag with the tag name p had been seen. */
- if($this->elementInScope('p')) {
- $this->emitToken(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
- }
+ /* A start tag token whose tag name is "plaintext" */
+ case 'plaintext':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been
+ seen. */
+ if ($this->elementInScope('p')) {
+ $this->emitToken(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+ }
- /* If the stack of open elements has in scope an element whose
- tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
- this is a parse error; pop elements from the stack until an
- element with one of those tag names has been popped from the
- stack. */
- while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
- array_pop($this->stack);
- }
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
- break;
+ return HTML5::PLAINTEXT;
+ break;
- /* A start tag whose tag name is "a" */
- case 'a':
- /* If the list of active formatting elements contains
- an element whose tag name is "a" between the end of the
- list and the last marker on the list (or the start of
- the list if there is no marker on the list), then this
- is a parse error; act as if an end tag with the tag name
- "a" had been seen, then remove that element from the list
- of active formatting elements and the stack of open
- elements if the end tag didn't already remove it (it
- might not have if the element is not in table scope). */
- $leng = count($this->a_formatting);
-
- for($n = $leng - 1; $n >= 0; $n--) {
- if($this->a_formatting[$n] === self::MARKER) {
- break;
-
- } elseif($this->a_formatting[$n]->nodeName === 'a') {
- $this->emitToken(array(
- 'name' => 'a',
- 'type' => HTML5::ENDTAG
- ));
- break;
+ /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
+ "h5", "h6" */
+ case 'h1':
+ case 'h2':
+ case 'h3':
+ case 'h4':
+ case 'h5':
+ case 'h6':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been seen. */
+ if ($this->elementInScope('p')) {
+ $this->emitToken(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
- }
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* If the stack of open elements has in scope an element whose
+ tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
+ this is a parse error; pop elements from the stack until an
+ element with one of those tag names has been popped from the
+ stack. */
+ while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
+ array_pop($this->stack);
+ }
- /* Insert an HTML element for the token. */
- $el = $this->insertElement($token);
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+ break;
- /* Add that element to the list of active formatting
- elements. */
- $this->a_formatting[] = $el;
- break;
+ /* A start tag whose tag name is "a" */
+ case 'a':
+ /* If the list of active formatting elements contains
+ an element whose tag name is "a" between the end of the
+ list and the last marker on the list (or the start of
+ the list if there is no marker on the list), then this
+ is a parse error; act as if an end tag with the tag name
+ "a" had been seen, then remove that element from the list
+ of active formatting elements and the stack of open
+ elements if the end tag didn't already remove it (it
+ might not have if the element is not in table scope). */
+ $leng = count($this->a_formatting);
+
+ for ($n = $leng - 1; $n >= 0; $n--) {
+ if ($this->a_formatting[$n] === self::MARKER) {
+ break;
- /* A start tag whose tag name is one of: "b", "big", "em", "font",
- "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
- case 'b': case 'big': case 'em': case 'font': case 'i':
- case 'nobr': case 's': case 'small': case 'strike':
- case 'strong': case 'tt': case 'u':
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ } elseif ($this->a_formatting[$n]->nodeName === 'a') {
+ $this->emitToken(
+ array(
+ 'name' => 'a',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+ break;
+ }
+ }
- /* Insert an HTML element for the token. */
- $el = $this->insertElement($token);
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
- /* Add that element to the list of active formatting
- elements. */
- $this->a_formatting[] = $el;
- break;
+ /* Insert an HTML element for the token. */
+ $el = $this->insertElement($token);
- /* A start tag token whose tag name is "button" */
- case 'button':
- /* If the stack of open elements has a button element in scope,
- then this is a parse error; act as if an end tag with the tag
- name "button" had been seen, then reprocess the token. (We don't
- do that. Unnecessary.) */
- if($this->elementInScope('button')) {
- $this->inBody(array(
- 'name' => 'button',
- 'type' => HTML5::ENDTAG
- ));
- }
+ /* Add that element to the list of active formatting
+ elements. */
+ $this->a_formatting[] = $el;
+ break;
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* A start tag whose tag name is one of: "b", "big", "em", "font",
+ "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
+ case 'b':
+ case 'big':
+ case 'em':
+ case 'font':
+ case 'i':
+ case 'nobr':
+ case 's':
+ case 'small':
+ case 'strike':
+ case 'strong':
+ case 'tt':
+ case 'u':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $el = $this->insertElement($token);
+
+ /* Add that element to the list of active formatting
+ elements. */
+ $this->a_formatting[] = $el;
+ break;
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* A start tag token whose tag name is "button" */
+ case 'button':
+ /* If the stack of open elements has a button element in scope,
+ then this is a parse error; act as if an end tag with the tag
+ name "button" had been seen, then reprocess the token. (We don't
+ do that. Unnecessary.) */
+ if ($this->elementInScope('button')) {
+ $this->inBody(
+ array(
+ 'name' => 'button',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+ }
- /* Insert a marker at the end of the list of active
- formatting elements. */
- $this->a_formatting[] = self::MARKER;
- break;
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
- /* A start tag token whose tag name is one of: "marquee", "object" */
- case 'marquee': case 'object':
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* Insert a marker at the end of the list of active
+ formatting elements. */
+ $this->a_formatting[] = self::MARKER;
+ break;
- /* Insert a marker at the end of the list of active
- formatting elements. */
- $this->a_formatting[] = self::MARKER;
- break;
+ /* A start tag token whose tag name is one of: "marquee", "object" */
+ case 'marquee':
+ case 'object':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
- /* A start tag token whose tag name is "xmp" */
- case 'xmp':
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* Insert a marker at the end of the list of active
+ formatting elements. */
+ $this->a_formatting[] = self::MARKER;
+ break;
- /* Switch the content model flag to the CDATA state. */
- return HTML5::CDATA;
- break;
+ /* A start tag token whose tag name is "xmp" */
+ case 'xmp':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
- /* A start tag whose tag name is "table" */
- case 'table':
- /* If the stack of open elements has a p element in scope,
- then act as if an end tag with the tag name p had been seen. */
- if($this->elementInScope('p')) {
- $this->emitToken(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
- }
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* Switch the content model flag to the CDATA state. */
+ return HTML5::CDATA;
+ break;
- /* Change the insertion mode to "in table". */
- $this->mode = self::IN_TABLE;
- break;
+ /* A start tag whose tag name is "table" */
+ case 'table':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been seen. */
+ if ($this->elementInScope('p')) {
+ $this->emitToken(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+ }
- /* A start tag whose tag name is one of: "area", "basefont",
- "bgsound", "br", "embed", "img", "param", "spacer", "wbr" */
- case 'area': case 'basefont': case 'bgsound': case 'br':
- case 'embed': case 'img': case 'param': case 'spacer':
- case 'wbr':
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* Change the insertion mode to "in table". */
+ $this->mode = self::IN_TABLE;
+ break;
- /* Immediately pop the current node off the stack of open elements. */
- array_pop($this->stack);
- break;
+ /* A start tag whose tag name is one of: "area", "basefont",
+ "bgsound", "br", "embed", "img", "param", "spacer", "wbr" */
+ case 'area':
+ case 'basefont':
+ case 'bgsound':
+ case 'br':
+ case 'embed':
+ case 'img':
+ case 'param':
+ case 'spacer':
+ case 'wbr':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
+
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
+
+ /* Immediately pop the current node off the stack of open elements. */
+ array_pop($this->stack);
+ break;
- /* A start tag whose tag name is "hr" */
- case 'hr':
- /* If the stack of open elements has a p element in scope,
- then act as if an end tag with the tag name p had been seen. */
- if($this->elementInScope('p')) {
- $this->emitToken(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
- }
+ /* A start tag whose tag name is "hr" */
+ case 'hr':
+ /* If the stack of open elements has a p element in scope,
+ then act as if an end tag with the tag name p had been seen. */
+ if ($this->elementInScope('p')) {
+ $this->emitToken(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+ }
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
- /* Immediately pop the current node off the stack of open elements. */
- array_pop($this->stack);
- break;
+ /* Immediately pop the current node off the stack of open elements. */
+ array_pop($this->stack);
+ break;
- /* A start tag whose tag name is "image" */
- case 'image':
- /* Parse error. Change the token's tag name to "img" and
- reprocess it. (Don't ask.) */
- $token['name'] = 'img';
- return $this->inBody($token);
- break;
+ /* A start tag whose tag name is "image" */
+ case 'image':
+ /* Parse error. Change the token's tag name to "img" and
+ reprocess it. (Don't ask.) */
+ $token['name'] = 'img';
+ return $this->inBody($token);
+ break;
- /* A start tag whose tag name is "input" */
- case 'input':
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* A start tag whose tag name is "input" */
+ case 'input':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
- /* Insert an input element for the token. */
- $element = $this->insertElement($token, false);
+ /* Insert an input element for the token. */
+ $element = $this->insertElement($token, false);
- /* If the form element pointer is not null, then associate the
- input element with the form element pointed to by the form
- element pointer. */
- $this->form_pointer !== null
- ? $this->form_pointer->appendChild($element)
- : end($this->stack)->appendChild($element);
+ /* If the form element pointer is not null, then associate the
+ input element with the form element pointed to by the form
+ element pointer. */
+ $this->form_pointer !== null
+ ? $this->form_pointer->appendChild($element)
+ : end($this->stack)->appendChild($element);
- /* Pop that input element off the stack of open elements. */
- array_pop($this->stack);
- break;
+ /* Pop that input element off the stack of open elements. */
+ array_pop($this->stack);
+ break;
- /* A start tag whose tag name is "isindex" */
- case 'isindex':
- /* Parse error. */
- // w/e
-
- /* If the form element pointer is not null,
- then ignore the token. */
- if($this->form_pointer === null) {
- /* Act as if a start tag token with the tag name "form" had
- been seen. */
- $this->inBody(array(
- 'name' => 'body',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
-
- /* Act as if a start tag token with the tag name "hr" had
- been seen. */
- $this->inBody(array(
- 'name' => 'hr',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
-
- /* Act as if a start tag token with the tag name "p" had
- been seen. */
- $this->inBody(array(
- 'name' => 'p',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
-
- /* Act as if a start tag token with the tag name "label"
- had been seen. */
- $this->inBody(array(
- 'name' => 'label',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
-
- /* Act as if a stream of character tokens had been seen. */
- $this->insertText('This is a searchable index. '.
- 'Insert your search keywords here: ');
-
- /* Act as if a start tag token with the tag name "input"
- had been seen, with all the attributes from the "isindex"
- token, except with the "name" attribute set to the value
- "isindex" (ignoring any explicit "name" attribute). */
- $attr = $token['attr'];
- $attr[] = array('name' => 'name', 'value' => 'isindex');
-
- $this->inBody(array(
- 'name' => 'input',
- 'type' => HTML5::STARTTAG,
- 'attr' => $attr
- ));
-
- /* Act as if a stream of character tokens had been seen
- (see below for what they should say). */
- $this->insertText('This is a searchable index. '.
- 'Insert your search keywords here: ');
-
- /* Act as if an end tag token with the tag name "label"
- had been seen. */
- $this->inBody(array(
- 'name' => 'label',
- 'type' => HTML5::ENDTAG
- ));
-
- /* Act as if an end tag token with the tag name "p" had
- been seen. */
- $this->inBody(array(
- 'name' => 'p',
- 'type' => HTML5::ENDTAG
- ));
-
- /* Act as if a start tag token with the tag name "hr" had
- been seen. */
- $this->inBody(array(
- 'name' => 'hr',
- 'type' => HTML5::ENDTAG
- ));
-
- /* Act as if an end tag token with the tag name "form" had
- been seen. */
- $this->inBody(array(
- 'name' => 'form',
- 'type' => HTML5::ENDTAG
- ));
- }
- break;
+ /* A start tag whose tag name is "isindex" */
+ case 'isindex':
+ /* Parse error. */
+ // w/e
- /* A start tag whose tag name is "textarea" */
- case 'textarea':
- $this->insertElement($token);
+ /* If the form element pointer is not null,
+ then ignore the token. */
+ if ($this->form_pointer === null) {
+ /* Act as if a start tag token with the tag name "form" had
+ been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'body',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
+
+ /* Act as if a start tag token with the tag name "hr" had
+ been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'hr',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
+
+ /* Act as if a start tag token with the tag name "p" had
+ been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
+
+ /* Act as if a start tag token with the tag name "label"
+ had been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'label',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
+
+ /* Act as if a stream of character tokens had been seen. */
+ $this->insertText(
+ 'This is a searchable index. ' .
+ 'Insert your search keywords here: '
+ );
+
+ /* Act as if a start tag token with the tag name "input"
+ had been seen, with all the attributes from the "isindex"
+ token, except with the "name" attribute set to the value
+ "isindex" (ignoring any explicit "name" attribute). */
+ $attr = $token['attr'];
+ $attr[] = array('name' => 'name', 'value' => 'isindex');
+
+ $this->inBody(
+ array(
+ 'name' => 'input',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => $attr
+ )
+ );
+
+ /* Act as if a stream of character tokens had been seen
+ (see below for what they should say). */
+ $this->insertText(
+ 'This is a searchable index. ' .
+ 'Insert your search keywords here: '
+ );
+
+ /* Act as if an end tag token with the tag name "label"
+ had been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'label',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+
+ /* Act as if an end tag token with the tag name "p" had
+ been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'p',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+
+ /* Act as if a start tag token with the tag name "hr" had
+ been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'hr',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+
+ /* Act as if an end tag token with the tag name "form" had
+ been seen. */
+ $this->inBody(
+ array(
+ 'name' => 'form',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+ }
+ break;
- /* Switch the tokeniser's content model flag to the
- RCDATA state. */
- return HTML5::RCDATA;
- break;
+ /* A start tag whose tag name is "textarea" */
+ case 'textarea':
+ $this->insertElement($token);
- /* A start tag whose tag name is one of: "iframe", "noembed",
- "noframes" */
- case 'iframe': case 'noembed': case 'noframes':
- $this->insertElement($token);
+ /* Switch the tokeniser's content model flag to the
+ RCDATA state. */
+ return HTML5::RCDATA;
+ break;
- /* Switch the tokeniser's content model flag to the CDATA state. */
- return HTML5::CDATA;
- break;
+ /* A start tag whose tag name is one of: "iframe", "noembed",
+ "noframes" */
+ case 'iframe':
+ case 'noembed':
+ case 'noframes':
+ $this->insertElement($token);
- /* A start tag whose tag name is "select" */
- case 'select':
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* Switch the tokeniser's content model flag to the CDATA state. */
+ return HTML5::CDATA;
+ break;
- /* Insert an HTML element for the token. */
- $this->insertElement($token);
+ /* A start tag whose tag name is "select" */
+ case 'select':
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
- /* Change the insertion mode to "in select". */
- $this->mode = self::IN_SELECT;
- break;
+ /* Insert an HTML element for the token. */
+ $this->insertElement($token);
- /* A start or end tag whose tag name is one of: "caption", "col",
- "colgroup", "frame", "frameset", "head", "option", "optgroup",
- "tbody", "td", "tfoot", "th", "thead", "tr". */
- case 'caption': case 'col': case 'colgroup': case 'frame':
- case 'frameset': case 'head': case 'option': case 'optgroup':
- case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead':
- case 'tr':
- // Parse error. Ignore the token.
- break;
+ /* Change the insertion mode to "in select". */
+ $this->mode = self::IN_SELECT;
+ break;
- /* A start or end tag whose tag name is one of: "event-source",
- "section", "nav", "article", "aside", "header", "footer",
- "datagrid", "command" */
- case 'event-source': case 'section': case 'nav': case 'article':
- case 'aside': case 'header': case 'footer': case 'datagrid':
- case 'command':
- // Work in progress!
- break;
+ /* A start or end tag whose tag name is one of: "caption", "col",
+ "colgroup", "frame", "frameset", "head", "option", "optgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr". */
+ case 'caption':
+ case 'col':
+ case 'colgroup':
+ case 'frame':
+ case 'frameset':
+ case 'head':
+ case 'option':
+ case 'optgroup':
+ case 'tbody':
+ case 'td':
+ case 'tfoot':
+ case 'th':
+ case 'thead':
+ case 'tr':
+ // Parse error. Ignore the token.
+ break;
- /* A start tag token not covered by the previous entries */
- default:
- /* Reconstruct the active formatting elements, if any. */
- $this->reconstructActiveFormattingElements();
+ /* A start or end tag whose tag name is one of: "event-source",
+ "section", "nav", "article", "aside", "header", "footer",
+ "datagrid", "command" */
+ case 'event-source':
+ case 'section':
+ case 'nav':
+ case 'article':
+ case 'aside':
+ case 'header':
+ case 'footer':
+ case 'datagrid':
+ case 'command':
+ // Work in progress!
+ break;
+
+ /* A start tag token not covered by the previous entries */
+ default:
+ /* Reconstruct the active formatting elements, if any. */
+ $this->reconstructActiveFormattingElements();
- $this->insertElement($token, true, true);
+ $this->insertElement($token, true, true);
+ break;
+ }
break;
- }
- break;
case HTML5::ENDTAG:
- switch($token['name']) {
- /* An end tag with the tag name "body" */
- case 'body':
- /* If the second element in the stack of open elements is
- not a body element, this is a parse error. Ignore the token.
- (innerHTML case) */
- if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
- // Ignore.
-
- /* If the current node is not the body element, then this
- is a parse error. */
- } elseif(end($this->stack)->nodeName !== 'body') {
- // Parse error.
- }
+ switch ($token['name']) {
+ /* An end tag with the tag name "body" */
+ case 'body':
+ /* If the second element in the stack of open elements is
+ not a body element, this is a parse error. Ignore the token.
+ (innerHTML case) */
+ if (count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
+ // Ignore.
+
+ /* If the current node is not the body element, then this
+ is a parse error. */
+ } elseif (end($this->stack)->nodeName !== 'body') {
+ // Parse error.
+ }
- /* Change the insertion mode to "after body". */
- $this->mode = self::AFTER_BODY;
- break;
+ /* Change the insertion mode to "after body". */
+ $this->mode = self::AFTER_BODY;
+ break;
- /* An end tag with the tag name "html" */
- case 'html':
- /* Act as if an end tag with tag name "body" had been seen,
- then, if that token wasn't ignored, reprocess the current
- token. */
- $this->inBody(array(
- 'name' => 'body',
- 'type' => HTML5::ENDTAG
- ));
+ /* An end tag with the tag name "html" */
+ case 'html':
+ /* Act as if an end tag with tag name "body" had been seen,
+ then, if that token wasn't ignored, reprocess the current
+ token. */
+ $this->inBody(
+ array(
+ 'name' => 'body',
+ 'type' => HTML5::ENDTAG
+ )
+ );
- return $this->afterBody($token);
- break;
+ return $this->afterBody($token);
+ break;
- /* An end tag whose tag name is one of: "address", "blockquote",
- "center", "dir", "div", "dl", "fieldset", "listing", "menu",
- "ol", "pre", "ul" */
- case 'address': case 'blockquote': case 'center': case 'dir':
- case 'div': case 'dl': case 'fieldset': case 'listing':
- case 'menu': case 'ol': case 'pre': case 'ul':
- /* If the stack of open elements has an element in scope
- with the same tag name as that of the token, then generate
- implied end tags. */
- if($this->elementInScope($token['name'])) {
- $this->generateImpliedEndTags();
-
- /* Now, if the current node is not an element with
- the same tag name as that of the token, then this
- is a parse error. */
- // w/e
+ /* An end tag whose tag name is one of: "address", "blockquote",
+ "center", "dir", "div", "dl", "fieldset", "listing", "menu",
+ "ol", "pre", "ul" */
+ case 'address':
+ case 'blockquote':
+ case 'center':
+ case 'dir':
+ case 'div':
+ case 'dl':
+ case 'fieldset':
+ case 'listing':
+ case 'menu':
+ case 'ol':
+ case 'pre':
+ case 'ul':
+ /* If the stack of open elements has an element in scope
+ with the same tag name as that of the token, then generate
+ implied end tags. */
+ if ($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags();
- /* If the stack of open elements has an element in
- scope with the same tag name as that of the token,
- then pop elements from this stack until an element
- with that tag name has been popped from the stack. */
- for($n = count($this->stack) - 1; $n >= 0; $n--) {
- if($this->stack[$n]->nodeName === $token['name']) {
- $n = -1;
+ /* Now, if the current node is not an element with
+ the same tag name as that of the token, then this
+ is a parse error. */
+ // w/e
+
+ /* If the stack of open elements has an element in
+ scope with the same tag name as that of the token,
+ then pop elements from this stack until an element
+ with that tag name has been popped from the stack. */
+ for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if ($this->stack[$n]->nodeName === $token['name']) {
+ $n = -1;
+ }
+
+ array_pop($this->stack);
}
+ }
+ break;
+
+ /* An end tag whose tag name is "form" */
+ case 'form':
+ /* If the stack of open elements has an element in scope
+ with the same tag name as that of the token, then generate
+ implied end tags. */
+ if ($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags();
- array_pop($this->stack);
}
- }
- break;
- /* An end tag whose tag name is "form" */
- case 'form':
- /* If the stack of open elements has an element in scope
- with the same tag name as that of the token, then generate
- implied end tags. */
- if($this->elementInScope($token['name'])) {
- $this->generateImpliedEndTags();
+ if (end($this->stack)->nodeName !== $token['name']) {
+ /* Now, if the current node is not an element with the
+ same tag name as that of the token, then this is a parse
+ error. */
+ // w/e
- }
+ } else {
+ /* Otherwise, if the current node is an element with
+ the same tag name as that of the token pop that element
+ from the stack. */
+ array_pop($this->stack);
+ }
- if(end($this->stack)->nodeName !== $token['name']) {
- /* Now, if the current node is not an element with the
- same tag name as that of the token, then this is a parse
- error. */
- // w/e
+ /* In any case, set the form element pointer to null. */
+ $this->form_pointer = null;
+ break;
- } else {
- /* Otherwise, if the current node is an element with
- the same tag name as that of the token pop that element
- from the stack. */
- array_pop($this->stack);
- }
+ /* An end tag whose tag name is "p" */
+ case 'p':
+ /* If the stack of open elements has a p element in scope,
+ then generate implied end tags, except for p elements. */
+ if ($this->elementInScope('p')) {
+ $this->generateImpliedEndTags(array('p'));
- /* In any case, set the form element pointer to null. */
- $this->form_pointer = null;
- break;
+ /* If the current node is not a p element, then this is
+ a parse error. */
+ // k
- /* An end tag whose tag name is "p" */
- case 'p':
- /* If the stack of open elements has a p element in scope,
- then generate implied end tags, except for p elements. */
- if($this->elementInScope('p')) {
- $this->generateImpliedEndTags(array('p'));
-
- /* If the current node is not a p element, then this is
- a parse error. */
- // k
-
- /* If the stack of open elements has a p element in
- scope, then pop elements from this stack until the stack
- no longer has a p element in scope. */
- for($n = count($this->stack) - 1; $n >= 0; $n--) {
- if($this->elementInScope('p')) {
- array_pop($this->stack);
+ /* If the stack of open elements has a p element in
+ scope, then pop elements from this stack until the stack
+ no longer has a p element in scope. */
+ for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if ($this->elementInScope('p')) {
+ array_pop($this->stack);
- } else {
- break;
+ } else {
+ break;
+ }
}
}
- }
- break;
-
- /* An end tag whose tag name is "dd", "dt", or "li" */
- case 'dd': case 'dt': case 'li':
- /* If the stack of open elements has an element in scope
- whose tag name matches the tag name of the token, then
- generate implied end tags, except for elements with the
- same tag name as the token. */
- if($this->elementInScope($token['name'])) {
- $this->generateImpliedEndTags(array($token['name']));
-
- /* If the current node is not an element with the same
- tag name as the token, then this is a parse error. */
- // w/e
+ break;
+ /* An end tag whose tag name is "dd", "dt", or "li" */
+ case 'dd':
+ case 'dt':
+ case 'li':
/* If the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then
- pop elements from this stack until an element with that
- tag name has been popped from the stack. */
- for($n = count($this->stack) - 1; $n >= 0; $n--) {
- if($this->stack[$n]->nodeName === $token['name']) {
- $n = -1;
- }
+ generate implied end tags, except for elements with the
+ same tag name as the token. */
+ if ($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags(array($token['name']));
+
+ /* If the current node is not an element with the same
+ tag name as the token, then this is a parse error. */
+ // w/e
+
+ /* If the stack of open elements has an element in scope
+ whose tag name matches the tag name of the token, then
+ pop elements from this stack until an element with that
+ tag name has been popped from the stack. */
+ for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if ($this->stack[$n]->nodeName === $token['name']) {
+ $n = -1;
+ }
- array_pop($this->stack);
+ array_pop($this->stack);
+ }
}
- }
- break;
-
- /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
- "h5", "h6" */
- case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
- $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
+ break;
- /* If the stack of open elements has in scope an element whose
- tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
- generate implied end tags. */
- if($this->elementInScope($elements)) {
- $this->generateImpliedEndTags();
+ /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
+ "h5", "h6" */
+ case 'h1':
+ case 'h2':
+ case 'h3':
+ case 'h4':
+ case 'h5':
+ case 'h6':
+ $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
+
+ /* If the stack of open elements has in scope an element whose
+ tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
+ generate implied end tags. */
+ if ($this->elementInScope($elements)) {
+ $this->generateImpliedEndTags();
- /* Now, if the current node is not an element with the same
- tag name as that of the token, then this is a parse error. */
- // w/e
+ /* Now, if the current node is not an element with the same
+ tag name as that of the token, then this is a parse error. */
+ // w/e
- /* If the stack of open elements has in scope an element
- whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
- "h6", then pop elements from the stack until an element
- with one of those tag names has been popped from the stack. */
- while($this->elementInScope($elements)) {
- array_pop($this->stack);
+ /* If the stack of open elements has in scope an element
+ whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
+ "h6", then pop elements from the stack until an element
+ with one of those tag names has been popped from the stack. */
+ while ($this->elementInScope($elements)) {
+ array_pop($this->stack);
+ }
}
- }
- break;
+ break;
- /* An end tag whose tag name is one of: "a", "b", "big", "em",
- "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
- case 'a': case 'b': case 'big': case 'em': case 'font':
- case 'i': case 'nobr': case 's': case 'small': case 'strike':
- case 'strong': case 'tt': case 'u':
- /* 1. Let the formatting element be the last element in
- the list of active formatting elements that:
- * is between the end of the list and the last scope
- marker in the list, if any, or the start of the list
- otherwise, and
- * has the same tag name as the token.
- */
- while(true) {
- for($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
- if($this->a_formatting[$a] === self::MARKER) {
+ /* An end tag whose tag name is one of: "a", "b", "big", "em",
+ "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
+ case 'a':
+ case 'b':
+ case 'big':
+ case 'em':
+ case 'font':
+ case 'i':
+ case 'nobr':
+ case 's':
+ case 'small':
+ case 'strike':
+ case 'strong':
+ case 'tt':
+ case 'u':
+ /* 1. Let the formatting element be the last element in
+ the list of active formatting elements that:
+ * is between the end of the list and the last scope
+ marker in the list, if any, or the start of the list
+ otherwise, and
+ * has the same tag name as the token.
+ */
+ while (true) {
+ for ($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
+ if ($this->a_formatting[$a] === self::MARKER) {
+ break;
+
+ } elseif ($this->a_formatting[$a]->tagName === $token['name']) {
+ $formatting_element = $this->a_formatting[$a];
+ $in_stack = in_array($formatting_element, $this->stack, true);
+ $fe_af_pos = $a;
+ break;
+ }
+ }
+
+ /* If there is no such node, or, if that node is
+ also in the stack of open elements but the element
+ is not in scope, then this is a parse error. Abort
+ these steps. The token is ignored. */
+ if (!isset($formatting_element) || ($in_stack &&
+ !$this->elementInScope($token['name']))
+ ) {
break;
- } elseif($this->a_formatting[$a]->tagName === $token['name']) {
- $formatting_element = $this->a_formatting[$a];
- $in_stack = in_array($formatting_element, $this->stack, true);
- $fe_af_pos = $a;
+ /* Otherwise, if there is such a node, but that node
+ is not in the stack of open elements, then this is a
+ parse error; remove the element from the list, and
+ abort these steps. */
+ } elseif (isset($formatting_element) && !$in_stack) {
+ unset($this->a_formatting[$fe_af_pos]);
+ $this->a_formatting = array_merge($this->a_formatting);
break;
}
- }
-
- /* If there is no such node, or, if that node is
- also in the stack of open elements but the element
- is not in scope, then this is a parse error. Abort
- these steps. The token is ignored. */
- if(!isset($formatting_element) || ($in_stack &&
- !$this->elementInScope($token['name']))) {
- break;
-
- /* Otherwise, if there is such a node, but that node
- is not in the stack of open elements, then this is a
- parse error; remove the element from the list, and
- abort these steps. */
- } elseif(isset($formatting_element) && !$in_stack) {
- unset($this->a_formatting[$fe_af_pos]);
- $this->a_formatting = array_merge($this->a_formatting);
- break;
- }
- /* 2. Let the furthest block be the topmost node in the
- stack of open elements that is lower in the stack
- than the formatting element, and is not an element in
- the phrasing or formatting categories. There might
- not be one. */
- $fe_s_pos = array_search($formatting_element, $this->stack, true);
- $length = count($this->stack);
+ /* 2. Let the furthest block be the topmost node in the
+ stack of open elements that is lower in the stack
+ than the formatting element, and is not an element in
+ the phrasing or formatting categories. There might
+ not be one. */
+ $fe_s_pos = array_search($formatting_element, $this->stack, true);
+ $length = count($this->stack);
- for($s = $fe_s_pos + 1; $s < $length; $s++) {
- $category = $this->getElementCategory($this->stack[$s]->nodeName);
+ for ($s = $fe_s_pos + 1; $s < $length; $s++) {
+ $category = $this->getElementCategory($this->stack[$s]->nodeName);
- if($category !== self::PHRASING && $category !== self::FORMATTING) {
- $furthest_block = $this->stack[$s];
+ if ($category !== self::PHRASING && $category !== self::FORMATTING) {
+ $furthest_block = $this->stack[$s];
+ }
}
- }
- /* 3. If there is no furthest block, then the UA must
- skip the subsequent steps and instead just pop all
- the nodes from the bottom of the stack of open
- elements, from the current node up to the formatting
- element, and remove the formatting element from the
- list of active formatting elements. */
- if(!isset($furthest_block)) {
- for($n = $length - 1; $n >= $fe_s_pos; $n--) {
- array_pop($this->stack);
- }
+ /* 3. If there is no furthest block, then the UA must
+ skip the subsequent steps and instead just pop all
+ the nodes from the bottom of the stack of open
+ elements, from the current node up to the formatting
+ element, and remove the formatting element from the
+ list of active formatting elements. */
+ if (!isset($furthest_block)) {
+ for ($n = $length - 1; $n >= $fe_s_pos; $n--) {
+ array_pop($this->stack);
+ }
- unset($this->a_formatting[$fe_af_pos]);
- $this->a_formatting = array_merge($this->a_formatting);
- break;
- }
+ unset($this->a_formatting[$fe_af_pos]);
+ $this->a_formatting = array_merge($this->a_formatting);
+ break;
+ }
- /* 4. Let the common ancestor be the element
- immediately above the formatting element in the stack
- of open elements. */
- $common_ancestor = $this->stack[$fe_s_pos - 1];
+ /* 4. Let the common ancestor be the element
+ immediately above the formatting element in the stack
+ of open elements. */
+ $common_ancestor = $this->stack[$fe_s_pos - 1];
- /* 5. If the furthest block has a parent node, then
- remove the furthest block from its parent node. */
- if($furthest_block->parentNode !== null) {
- $furthest_block->parentNode->removeChild($furthest_block);
- }
+ /* 5. If the furthest block has a parent node, then
+ remove the furthest block from its parent node. */
+ if ($furthest_block->parentNode !== null) {
+ $furthest_block->parentNode->removeChild($furthest_block);
+ }
- /* 6. Let a bookmark note the position of the
- formatting element in the list of active formatting
- elements relative to the elements on either side
- of it in the list. */
- $bookmark = $fe_af_pos;
-
- /* 7. Let node and last node be the furthest block.
- Follow these steps: */
- $node = $furthest_block;
- $last_node = $furthest_block;
-
- while(true) {
- for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
- /* 7.1 Let node be the element immediately
- prior to node in the stack of open elements. */
- $node = $this->stack[$n];
-
- /* 7.2 If node is not in the list of active
- formatting elements, then remove node from
- the stack of open elements and then go back
- to step 1. */
- if(!in_array($node, $this->a_formatting, true)) {
- unset($this->stack[$n]);
- $this->stack = array_merge($this->stack);
+ /* 6. Let a bookmark note the position of the
+ formatting element in the list of active formatting
+ elements relative to the elements on either side
+ of it in the list. */
+ $bookmark = $fe_af_pos;
+
+ /* 7. Let node and last node be the furthest block.
+ Follow these steps: */
+ $node = $furthest_block;
+ $last_node = $furthest_block;
+
+ while (true) {
+ for ($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
+ /* 7.1 Let node be the element immediately
+ prior to node in the stack of open elements. */
+ $node = $this->stack[$n];
+
+ /* 7.2 If node is not in the list of active
+ formatting elements, then remove node from
+ the stack of open elements and then go back
+ to step 1. */
+ if (!in_array($node, $this->a_formatting, true)) {
+ unset($this->stack[$n]);
+ $this->stack = array_merge($this->stack);
+
+ } else {
+ break;
+ }
+ }
- } else {
+ /* 7.3 Otherwise, if node is the formatting
+ element, then go to the next step in the overall
+ algorithm. */
+ if ($node === $formatting_element) {
break;
+
+ /* 7.4 Otherwise, if last node is the furthest
+ block, then move the aforementioned bookmark to
+ be immediately after the node in the list of
+ active formatting elements. */
+ } elseif ($last_node === $furthest_block) {
+ $bookmark = array_search($node, $this->a_formatting, true) + 1;
}
- }
- /* 7.3 Otherwise, if node is the formatting
- element, then go to the next step in the overall
- algorithm. */
- if($node === $formatting_element) {
- break;
+ /* 7.5 If node has any children, perform a
+ shallow clone of node, replace the entry for
+ node in the list of active formatting elements
+ with an entry for the clone, replace the entry
+ for node in the stack of open elements with an
+ entry for the clone, and let node be the clone. */
+ if ($node->hasChildNodes()) {
+ $clone = $node->cloneNode();
+ $s_pos = array_search($node, $this->stack, true);
+ $a_pos = array_search($node, $this->a_formatting, true);
+
+ $this->stack[$s_pos] = $clone;
+ $this->a_formatting[$a_pos] = $clone;
+ $node = $clone;
+ }
- /* 7.4 Otherwise, if last node is the furthest
- block, then move the aforementioned bookmark to
- be immediately after the node in the list of
- active formatting elements. */
- } elseif($last_node === $furthest_block) {
- $bookmark = array_search($node, $this->a_formatting, true) + 1;
- }
+ /* 7.6 Insert last node into node, first removing
+ it from its previous parent node if any. */
+ if ($last_node->parentNode !== null) {
+ $last_node->parentNode->removeChild($last_node);
+ }
+
+ $node->appendChild($last_node);
- /* 7.5 If node has any children, perform a
- shallow clone of node, replace the entry for
- node in the list of active formatting elements
- with an entry for the clone, replace the entry
- for node in the stack of open elements with an
- entry for the clone, and let node be the clone. */
- if($node->hasChildNodes()) {
- $clone = $node->cloneNode();
- $s_pos = array_search($node, $this->stack, true);
- $a_pos = array_search($node, $this->a_formatting, true);
-
- $this->stack[$s_pos] = $clone;
- $this->a_formatting[$a_pos] = $clone;
- $node = $clone;
+ /* 7.7 Let last node be node. */
+ $last_node = $node;
}
- /* 7.6 Insert last node into node, first removing
- it from its previous parent node if any. */
- if($last_node->parentNode !== null) {
+ /* 8. Insert whatever last node ended up being in
+ the previous step into the common ancestor node,
+ first removing it from its previous parent node if
+ any. */
+ if ($last_node->parentNode !== null) {
$last_node->parentNode->removeChild($last_node);
}
- $node->appendChild($last_node);
+ $common_ancestor->appendChild($last_node);
- /* 7.7 Let last node be node. */
- $last_node = $node;
- }
+ /* 9. Perform a shallow clone of the formatting
+ element. */
+ $clone = $formatting_element->cloneNode();
- /* 8. Insert whatever last node ended up being in
- the previous step into the common ancestor node,
- first removing it from its previous parent node if
- any. */
- if($last_node->parentNode !== null) {
- $last_node->parentNode->removeChild($last_node);
- }
+ /* 10. Take all of the child nodes of the furthest
+ block and append them to the clone created in the
+ last step. */
+ while ($furthest_block->hasChildNodes()) {
+ $child = $furthest_block->firstChild;
+ $furthest_block->removeChild($child);
+ $clone->appendChild($child);
+ }
- $common_ancestor->appendChild($last_node);
+ /* 11. Append that clone to the furthest block. */
+ $furthest_block->appendChild($clone);
- /* 9. Perform a shallow clone of the formatting
- element. */
- $clone = $formatting_element->cloneNode();
+ /* 12. Remove the formatting element from the list
+ of active formatting elements, and insert the clone
+ into the list of active formatting elements at the
+ position of the aforementioned bookmark. */
+ $fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
+ unset($this->a_formatting[$fe_af_pos]);
+ $this->a_formatting = array_merge($this->a_formatting);
- /* 10. Take all of the child nodes of the furthest
- block and append them to the clone created in the
- last step. */
- while($furthest_block->hasChildNodes()) {
- $child = $furthest_block->firstChild;
- $furthest_block->removeChild($child);
- $clone->appendChild($child);
+ $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
+ $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
+ $this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
+
+ /* 13. Remove the formatting element from the stack
+ of open elements, and insert the clone into the stack
+ of open elements immediately after (i.e. in a more
+ deeply nested position than) the position of the
+ furthest block in that stack. */
+ $fe_s_pos = array_search($formatting_element, $this->stack, true);
+ $fb_s_pos = array_search($furthest_block, $this->stack, true);
+ unset($this->stack[$fe_s_pos]);
+
+ $s_part1 = array_slice($this->stack, 0, $fb_s_pos);
+ $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
+ $this->stack = array_merge($s_part1, array($clone), $s_part2);
+
+ /* 14. Jump back to step 1 in this series of steps. */
+ unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
}
+ break;
- /* 11. Append that clone to the furthest block. */
- $furthest_block->appendChild($clone);
-
- /* 12. Remove the formatting element from the list
- of active formatting elements, and insert the clone
- into the list of active formatting elements at the
- position of the aforementioned bookmark. */
- $fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
- unset($this->a_formatting[$fe_af_pos]);
- $this->a_formatting = array_merge($this->a_formatting);
-
- $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
- $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
- $this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
-
- /* 13. Remove the formatting element from the stack
- of open elements, and insert the clone into the stack
- of open elements immediately after (i.e. in a more
- deeply nested position than) the position of the
- furthest block in that stack. */
- $fe_s_pos = array_search($formatting_element, $this->stack, true);
- $fb_s_pos = array_search($furthest_block, $this->stack, true);
- unset($this->stack[$fe_s_pos]);
-
- $s_part1 = array_slice($this->stack, 0, $fb_s_pos);
- $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
- $this->stack = array_merge($s_part1, array($clone), $s_part2);
-
- /* 14. Jump back to step 1 in this series of steps. */
- unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
- }
- break;
+ /* An end tag token whose tag name is one of: "button",
+ "marquee", "object" */
+ case 'button':
+ case 'marquee':
+ case 'object':
+ /* If the stack of open elements has an element in scope whose
+ tag name matches the tag name of the token, then generate implied
+ tags. */
+ if ($this->elementInScope($token['name'])) {
+ $this->generateImpliedEndTags();
- /* An end tag token whose tag name is one of: "button",
- "marquee", "object" */
- case 'button': case 'marquee': case 'object':
- /* If the stack of open elements has an element in scope whose
- tag name matches the tag name of the token, then generate implied
- tags. */
- if($this->elementInScope($token['name'])) {
- $this->generateImpliedEndTags();
-
- /* Now, if the current node is not an element with the same
- tag name as the token, then this is a parse error. */
- // k
-
- /* Now, if the stack of open elements has an element in scope
- whose tag name matches the tag name of the token, then pop
- elements from the stack until that element has been popped from
- the stack, and clear the list of active formatting elements up
- to the last marker. */
- for($n = count($this->stack) - 1; $n >= 0; $n--) {
- if($this->stack[$n]->nodeName === $token['name']) {
- $n = -1;
- }
+ /* Now, if the current node is not an element with the same
+ tag name as the token, then this is a parse error. */
+ // k
- array_pop($this->stack);
- }
+ /* Now, if the stack of open elements has an element in scope
+ whose tag name matches the tag name of the token, then pop
+ elements from the stack until that element has been popped from
+ the stack, and clear the list of active formatting elements up
+ to the last marker. */
+ for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if ($this->stack[$n]->nodeName === $token['name']) {
+ $n = -1;
+ }
- $marker = end(array_keys($this->a_formatting, self::MARKER, true));
+ array_pop($this->stack);
+ }
- for($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
- array_pop($this->a_formatting);
- }
- }
- break;
+ $marker = end(array_keys($this->a_formatting, self::MARKER, true));
- /* Or an end tag whose tag name is one of: "area", "basefont",
- "bgsound", "br", "embed", "hr", "iframe", "image", "img",
- "input", "isindex", "noembed", "noframes", "param", "select",
- "spacer", "table", "textarea", "wbr" */
- case 'area': case 'basefont': case 'bgsound': case 'br':
- case 'embed': case 'hr': case 'iframe': case 'image':
- case 'img': case 'input': case 'isindex': case 'noembed':
- case 'noframes': case 'param': case 'select': case 'spacer':
- case 'table': case 'textarea': case 'wbr':
- // Parse error. Ignore the token.
- break;
+ for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
+ array_pop($this->a_formatting);
+ }
+ }
+ break;
- /* An end tag token not covered by the previous entries */
- default:
- for($n = count($this->stack) - 1; $n >= 0; $n--) {
- /* Initialise node to be the current node (the bottommost
- node of the stack). */
- $node = end($this->stack);
-
- /* If node has the same tag name as the end tag token,
- then: */
- if($token['name'] === $node->nodeName) {
- /* Generate implied end tags. */
- $this->generateImpliedEndTags();
+ /* Or an end tag whose tag name is one of: "area", "basefont",
+ "bgsound", "br", "embed", "hr", "iframe", "image", "img",
+ "input", "isindex", "noembed", "noframes", "param", "select",
+ "spacer", "table", "textarea", "wbr" */
+ case 'area':
+ case 'basefont':
+ case 'bgsound':
+ case 'br':
+ case 'embed':
+ case 'hr':
+ case 'iframe':
+ case 'image':
+ case 'img':
+ case 'input':
+ case 'isindex':
+ case 'noembed':
+ case 'noframes':
+ case 'param':
+ case 'select':
+ case 'spacer':
+ case 'table':
+ case 'textarea':
+ case 'wbr':
+ // Parse error. Ignore the token.
+ break;
- /* If the tag name of the end tag token does not
- match the tag name of the current node, this is a
- parse error. */
- // k
+ /* An end tag token not covered by the previous entries */
+ default:
+ for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+ /* Initialise node to be the current node (the bottommost
+ node of the stack). */
+ $node = end($this->stack);
+
+ /* If node has the same tag name as the end tag token,
+ then: */
+ if ($token['name'] === $node->nodeName) {
+ /* Generate implied end tags. */
+ $this->generateImpliedEndTags();
+
+ /* If the tag name of the end tag token does not
+ match the tag name of the current node, this is a
+ parse error. */
+ // k
+
+ /* Pop all the nodes from the current node up to
+ node, including node, then stop this algorithm. */
+ for ($x = count($this->stack) - $n; $x >= $n; $x--) {
+ array_pop($this->stack);
+ }
- /* Pop all the nodes from the current node up to
- node, including node, then stop this algorithm. */
- for($x = count($this->stack) - $n; $x >= $n; $x--) {
- array_pop($this->stack);
- }
-
- } else {
- $category = $this->getElementCategory($node);
-
- if($category !== self::SPECIAL && $category !== self::SCOPING) {
- /* Otherwise, if node is in neither the formatting
- category nor the phrasing category, then this is a
- parse error. Stop this algorithm. The end tag token
- is ignored. */
- return false;
+ } else {
+ $category = $this->getElementCategory($node);
+
+ if ($category !== self::SPECIAL && $category !== self::SCOPING) {
+ /* Otherwise, if node is in neither the formatting
+ category nor the phrasing category, then this is a
+ parse error. Stop this algorithm. The end tag token
+ is ignored. */
+ return false;
+ }
}
}
- }
+ break;
+ }
break;
- }
- break;
}
}
- private function inTable($token) {
+ private function inTable($token)
+ {
$clear = array('html', 'table');
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
- if($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ if ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
- /* A start tag whose tag name is "caption" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- $token['name'] === 'caption') {
+ /* A start tag whose tag name is "caption" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'caption'
+ ) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
@@ -2663,9 +3350,10 @@ class HTML5TreeConstructer {
$this->insertElement($token);
$this->mode = self::IN_CAPTION;
- /* A start tag whose tag name is "colgroup" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- $token['name'] === 'colgroup') {
+ /* A start tag whose tag name is "colgroup" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'colgroup'
+ ) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
@@ -2674,20 +3362,26 @@ class HTML5TreeConstructer {
$this->insertElement($token);
$this->mode = self::IN_CGROUP;
- /* A start tag whose tag name is "col" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- $token['name'] === 'col') {
- $this->inTable(array(
- 'name' => 'colgroup',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
+ /* A start tag whose tag name is "col" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'col'
+ ) {
+ $this->inTable(
+ array(
+ 'name' => 'colgroup',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
$this->inColumnGroup($token);
- /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
- } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('tbody', 'tfoot', 'thead'))) {
+ /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
+ } elseif ($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array('tbody', 'tfoot', 'thead')
+ )
+ ) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
@@ -2696,42 +3390,49 @@ class HTML5TreeConstructer {
$this->insertElement($token);
$this->mode = self::IN_TBODY;
- /* A start tag whose tag name is one of: "td", "th", "tr" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- in_array($token['name'], array('td', 'th', 'tr'))) {
+ /* A start tag whose tag name is one of: "td", "th", "tr" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ in_array($token['name'], array('td', 'th', 'tr'))
+ ) {
/* Act as if a start tag token with the tag name "tbody" had been
seen, then reprocess the current token. */
- $this->inTable(array(
- 'name' => 'tbody',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
+ $this->inTable(
+ array(
+ 'name' => 'tbody',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
return $this->inTableBody($token);
- /* A start tag whose tag name is "table" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- $token['name'] === 'table') {
+ /* A start tag whose tag name is "table" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'table'
+ ) {
/* Parse error. Act as if an end tag token with the tag name "table"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
- $this->inTable(array(
- 'name' => 'table',
- 'type' => HTML5::ENDTAG
- ));
+ $this->inTable(
+ array(
+ 'name' => 'table',
+ 'type' => HTML5::ENDTAG
+ )
+ );
return $this->mainPhase($token);
- /* An end tag whose tag name is "table" */
- } elseif($token['type'] === HTML5::ENDTAG &&
- $token['name'] === 'table') {
+ /* An end tag whose tag name is "table" */
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'table'
+ ) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
return false;
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
@@ -2742,11 +3443,11 @@ class HTML5TreeConstructer {
/* Pop elements from this stack until a table element has been
popped from the stack. */
- while(true) {
+ while (true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
- if($current === 'table') {
+ if ($current === 'table') {
break;
}
}
@@ -2755,14 +3456,28 @@ class HTML5TreeConstructer {
$this->resetInsertionMode();
}
- /* An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
- } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
- array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td',
- 'tfoot', 'th', 'thead', 'tr'))) {
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif ($token['type'] === HTML5::ENDTAG && in_array(
+ $token['name'],
+ array(
+ 'body',
+ 'caption',
+ 'col',
+ 'colgroup',
+ 'html',
+ 'tbody',
+ 'td',
+ 'tfoot',
+ 'th',
+ 'thead',
+ 'tr'
+ )
+ )
+ ) {
// Parse error. Ignore the token.
- /* Anything else */
+ /* Anything else */
} else {
/* Parse error. Process the token as if the insertion mode was "in
body", with the following exception: */
@@ -2770,8 +3485,11 @@ class HTML5TreeConstructer {
/* If the current node is a table, tbody, tfoot, thead, or tr
element, then, whenever a node would be inserted into the current
node, it must instead be inserted into the foster parent element. */
- if(in_array(end($this->stack)->nodeName,
- array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
+ if (in_array(
+ end($this->stack)->nodeName,
+ array('table', 'tbody', 'tfoot', 'thead', 'tr')
+ )
+ ) {
/* The foster parent element is the parent element of the last
table element in the stack of open elements, if there is a
table element and it has such a parent element. If there is no
@@ -2783,21 +3501,22 @@ class HTML5TreeConstructer {
its parent node is not an element, then the foster parent
element is the element before the last table element in the
stack of open elements. */
- for($n = count($this->stack) - 1; $n >= 0; $n--) {
- if($this->stack[$n]->nodeName === 'table') {
+ for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if ($this->stack[$n]->nodeName === 'table') {
$table = $this->stack[$n];
break;
}
}
- if(isset($table) && $table->parentNode !== null) {
+ if (isset($table) && $table->parentNode !== null) {
$this->foster_parent = $table->parentNode;
- } elseif(!isset($table)) {
+ } elseif (!isset($table)) {
$this->foster_parent = $this->stack[0];
- } elseif(isset($table) && ($table->parentNode === null ||
- $table->parentNode->nodeType !== XML_ELEMENT_NODE)) {
+ } elseif (isset($table) && ($table->parentNode === null ||
+ $table->parentNode->nodeType !== XML_ELEMENT_NODE)
+ ) {
$this->foster_parent = $this->stack[$n - 1];
}
}
@@ -2806,16 +3525,17 @@ class HTML5TreeConstructer {
}
}
- private function inCaption($token) {
+ private function inCaption($token)
+ {
/* An end tag whose tag name is "caption" */
- if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
+ if ($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
// Ignore
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
@@ -2826,11 +3546,11 @@ class HTML5TreeConstructer {
/* Pop elements from this stack until a caption element has
been popped from the stack. */
- while(true) {
+ while (true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
- if($node === 'caption') {
+ if ($node === 'caption') {
break;
}
}
@@ -2843,99 +3563,131 @@ class HTML5TreeConstructer {
$this->mode = self::IN_TABLE;
}
- /* A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
- name is "table" */
- } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
- 'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG &&
- $token['name'] === 'table')) {
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
+ name is "table" */
+ } elseif (($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array(
+ 'caption',
+ 'col',
+ 'colgroup',
+ 'tbody',
+ 'td',
+ 'tfoot',
+ 'th',
+ 'thead',
+ 'tr'
+ )
+ )) || ($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'table')
+ ) {
/* Parse error. Act as if an end tag with the tag name "caption"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
- $this->inCaption(array(
- 'name' => 'caption',
- 'type' => HTML5::ENDTAG
- ));
+ $this->inCaption(
+ array(
+ 'name' => 'caption',
+ 'type' => HTML5::ENDTAG
+ )
+ );
return $this->inTable($token);
- /* An end tag whose tag name is one of: "body", "col", "colgroup",
- "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
- } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
- array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th',
- 'thead', 'tr'))) {
+ /* An end tag whose tag name is one of: "body", "col", "colgroup",
+ "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif ($token['type'] === HTML5::ENDTAG && in_array(
+ $token['name'],
+ array(
+ 'body',
+ 'col',
+ 'colgroup',
+ 'html',
+ 'tbody',
+ 'tfoot',
+ 'th',
+ 'thead',
+ 'tr'
+ )
+ )
+ ) {
// Parse error. Ignore the token.
- /* Anything else */
+ /* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
- private function inColumnGroup($token) {
+ private function inColumnGroup($token)
+ {
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
- if($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ if ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
- /* A start tag whose tag name is "col" */
- } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
+ /* A start tag whose tag name is "col" */
+ } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
/* Insert a col element for the token. Immediately pop the current
node off the stack of open elements. */
$this->insertElement($token);
array_pop($this->stack);
- /* An end tag whose tag name is "colgroup" */
- } elseif($token['type'] === HTML5::ENDTAG &&
- $token['name'] === 'colgroup') {
+ /* An end tag whose tag name is "colgroup" */
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'colgroup'
+ ) {
/* If the current node is the root html element, then this is a
parse error, ignore the token. (innerHTML case) */
- if(end($this->stack)->nodeName === 'html') {
+ if (end($this->stack)->nodeName === 'html') {
// Ignore
- /* Otherwise, pop the current node (which will be a colgroup
- element) from the stack of open elements. Switch the insertion
- mode to "in table". */
+ /* Otherwise, pop the current node (which will be a colgroup
+ element) from the stack of open elements. Switch the insertion
+ mode to "in table". */
} else {
array_pop($this->stack);
$this->mode = self::IN_TABLE;
}
- /* An end tag whose tag name is "col" */
- } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
+ /* An end tag whose tag name is "col" */
+ } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
/* Parse error. Ignore the token. */
- /* Anything else */
+ /* Anything else */
} else {
/* Act as if an end tag with the tag name "colgroup" had been seen,
and then, if that token wasn't ignored, reprocess the current token. */
- $this->inColumnGroup(array(
- 'name' => 'colgroup',
- 'type' => HTML5::ENDTAG
- ));
+ $this->inColumnGroup(
+ array(
+ 'name' => 'colgroup',
+ 'type' => HTML5::ENDTAG
+ )
+ );
return $this->inTable($token);
}
}
- private function inTableBody($token) {
+ private function inTableBody($token)
+ {
$clear = array('tbody', 'tfoot', 'thead', 'html');
/* A start tag whose tag name is "tr" */
- if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
+ if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
@@ -2944,29 +3696,33 @@ class HTML5TreeConstructer {
$this->insertElement($token);
$this->mode = self::IN_ROW;
- /* A start tag whose tag name is one of: "th", "td" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- ($token['name'] === 'th' || $token['name'] === 'td')) {
+ /* A start tag whose tag name is one of: "th", "td" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ ($token['name'] === 'th' || $token['name'] === 'td')
+ ) {
/* Parse error. Act as if a start tag with the tag name "tr" had
been seen, then reprocess the current token. */
- $this->inTableBody(array(
- 'name' => 'tr',
- 'type' => HTML5::STARTTAG,
- 'attr' => array()
- ));
+ $this->inTableBody(
+ array(
+ 'name' => 'tr',
+ 'type' => HTML5::STARTTAG,
+ 'attr' => array()
+ )
+ );
return $this->inRow($token);
- /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
- } elseif($token['type'] === HTML5::ENDTAG &&
- in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
+ /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ in_array($token['name'], array('tbody', 'tfoot', 'thead'))
+ ) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
// Ignore
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
@@ -2977,18 +3733,21 @@ class HTML5TreeConstructer {
$this->mode = self::IN_TABLE;
}
- /* A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
- } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) ||
- ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) {
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
+ } elseif (($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead')
+ )) ||
+ ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')
+ ) {
/* If the stack of open elements does not have a tbody, thead, or
tfoot element in table scope, this is a parse error. Ignore the
token. (innerHTML case) */
- if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
+ if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
// Ignore.
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
@@ -2996,33 +3755,40 @@ class HTML5TreeConstructer {
/* Act as if an end tag with the same tag name as the current
node ("tbody", "tfoot", or "thead") had been seen, then
reprocess the current token. */
- $this->inTableBody(array(
- 'name' => end($this->stack)->nodeName,
- 'type' => HTML5::ENDTAG
- ));
+ $this->inTableBody(
+ array(
+ 'name' => end($this->stack)->nodeName,
+ 'type' => HTML5::ENDTAG
+ )
+ );
return $this->mainPhase($token);
}
- /* An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html", "td", "th", "tr" */
- } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
- array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html", "td", "th", "tr" */
+ } elseif ($token['type'] === HTML5::ENDTAG && in_array(
+ $token['name'],
+ array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr')
+ )
+ ) {
/* Parse error. Ignore the token. */
- /* Anything else */
+ /* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
- private function inRow($token) {
+ private function inRow($token)
+ {
$clear = array('tr', 'html');
/* A start tag whose tag name is one of: "th", "td" */
- if($token['type'] === HTML5::STARTTAG &&
- ($token['name'] === 'th' || $token['name'] === 'td')) {
+ if ($token['type'] === HTML5::STARTTAG &&
+ ($token['name'] === 'th' || $token['name'] === 'td')
+ ) {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
@@ -3035,15 +3801,15 @@ class HTML5TreeConstructer {
elements. */
$this->a_formatting[] = self::MARKER;
- /* An end tag whose tag name is "tr" */
- } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
+ /* An end tag whose tag name is "tr" */
+ } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
// Ignore.
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
@@ -3055,64 +3821,77 @@ class HTML5TreeConstructer {
$this->mode = self::IN_TBODY;
}
- /* A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
- } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) {
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
+ } elseif ($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr')
+ )
+ ) {
/* Act as if an end tag with the tag name "tr" had been seen, then,
if that token wasn't ignored, reprocess the current token. */
- $this->inRow(array(
- 'name' => 'tr',
- 'type' => HTML5::ENDTAG
- ));
+ $this->inRow(
+ array(
+ 'name' => 'tr',
+ 'type' => HTML5::ENDTAG
+ )
+ );
return $this->inCell($token);
- /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
- } elseif($token['type'] === HTML5::ENDTAG &&
- in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
+ /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ in_array($token['name'], array('tbody', 'tfoot', 'thead'))
+ ) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
// Ignore.
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Otherwise, act as if an end tag with the tag name "tr" had
been seen, then reprocess the current token. */
- $this->inRow(array(
- 'name' => 'tr',
- 'type' => HTML5::ENDTAG
- ));
+ $this->inRow(
+ array(
+ 'name' => 'tr',
+ 'type' => HTML5::ENDTAG
+ )
+ );
return $this->inCell($token);
}
- /* An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html", "td", "th" */
- } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
- array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html", "td", "th" */
+ } elseif ($token['type'] === HTML5::ENDTAG && in_array(
+ $token['name'],
+ array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr')
+ )
+ ) {
/* Parse error. Ignore the token. */
- /* Anything else */
+ /* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
- private function inCell($token) {
+ private function inCell($token)
+ {
/* An end tag whose tag name is one of: "td", "th" */
- if($token['type'] === HTML5::ENDTAG &&
- ($token['name'] === 'td' || $token['name'] === 'th')) {
+ if ($token['type'] === HTML5::ENDTAG &&
+ ($token['name'] === 'td' || $token['name'] === 'th')
+ ) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token, then this is a
parse error and the token must be ignored. */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
// Ignore.
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Generate implied end tags, except for elements with the same
tag name as the token. */
@@ -3124,11 +3903,11 @@ class HTML5TreeConstructer {
/* Pop elements from this stack until an element with the same
tag name as the token has been popped from the stack. */
- while(true) {
+ while (true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
- if($node === $token['name']) {
+ if ($node === $token['name']) {
break;
}
}
@@ -3142,178 +3921,223 @@ class HTML5TreeConstructer {
$this->mode = self::IN_ROW;
}
- /* A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "td", "tfoot", "th", "thead", "tr" */
- } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
- 'thead', 'tr'))) {
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif ($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array(
+ 'caption',
+ 'col',
+ 'colgroup',
+ 'tbody',
+ 'td',
+ 'tfoot',
+ 'th',
+ 'thead',
+ 'tr'
+ )
+ )
+ ) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
- if(!$this->elementInScope(array('td', 'th'), true)) {
+ if (!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
- /* Otherwise, close the cell (see below) and reprocess the current
- token. */
+ /* Otherwise, close the cell (see below) and reprocess the current
+ token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
- /* A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "td", "tfoot", "th", "thead", "tr" */
- } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
- array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
- 'thead', 'tr'))) {
+ /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+ "tbody", "td", "tfoot", "th", "thead", "tr" */
+ } elseif ($token['type'] === HTML5::STARTTAG && in_array(
+ $token['name'],
+ array(
+ 'caption',
+ 'col',
+ 'colgroup',
+ 'tbody',
+ 'td',
+ 'tfoot',
+ 'th',
+ 'thead',
+ 'tr'
+ )
+ )
+ ) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
- if(!$this->elementInScope(array('td', 'th'), true)) {
+ if (!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
- /* Otherwise, close the cell (see below) and reprocess the current
- token. */
+ /* Otherwise, close the cell (see below) and reprocess the current
+ token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
- /* An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html" */
- } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
- array('body', 'caption', 'col', 'colgroup', 'html'))) {
+ /* An end tag whose tag name is one of: "body", "caption", "col",
+ "colgroup", "html" */
+ } elseif ($token['type'] === HTML5::ENDTAG && in_array(
+ $token['name'],
+ array('body', 'caption', 'col', 'colgroup', 'html')
+ )
+ ) {
/* Parse error. Ignore the token. */
- /* An end tag whose tag name is one of: "table", "tbody", "tfoot",
- "thead", "tr" */
- } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
- array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
+ /* An end tag whose tag name is one of: "table", "tbody", "tfoot",
+ "thead", "tr" */
+ } elseif ($token['type'] === HTML5::ENDTAG && in_array(
+ $token['name'],
+ array('table', 'tbody', 'tfoot', 'thead', 'tr')
+ )
+ ) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token (which can only
happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
then this is a parse error and the token must be ignored. */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
// Ignore.
- /* Otherwise, close the cell (see below) and reprocess the current
- token. */
+ /* Otherwise, close the cell (see below) and reprocess the current
+ token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
- /* Anything else */
+ /* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
- private function inSelect($token) {
+ private function inSelect($token)
+ {
/* Handle the token as follows: */
/* A character token */
- if($token['type'] === HTML5::CHARACTR) {
+ if ($token['type'] === HTML5::CHARACTR) {
/* Append the token's character to the current node. */
$this->insertText($token['data']);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
- /* A start tag token whose tag name is "option" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- $token['name'] === 'option') {
+ /* A start tag token whose tag name is "option" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'option'
+ ) {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
- if(end($this->stack)->nodeName === 'option') {
- $this->inSelect(array(
- 'name' => 'option',
- 'type' => HTML5::ENDTAG
- ));
+ if (end($this->stack)->nodeName === 'option') {
+ $this->inSelect(
+ array(
+ 'name' => 'option',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
- /* A start tag token whose tag name is "optgroup" */
- } elseif($token['type'] === HTML5::STARTTAG &&
- $token['name'] === 'optgroup') {
+ /* A start tag token whose tag name is "optgroup" */
+ } elseif ($token['type'] === HTML5::STARTTAG &&
+ $token['name'] === 'optgroup'
+ ) {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
- if(end($this->stack)->nodeName === 'option') {
- $this->inSelect(array(
- 'name' => 'option',
- 'type' => HTML5::ENDTAG
- ));
+ if (end($this->stack)->nodeName === 'option') {
+ $this->inSelect(
+ array(
+ 'name' => 'option',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
/* If the current node is an optgroup element, act as if an end tag
with the tag name "optgroup" had been seen. */
- if(end($this->stack)->nodeName === 'optgroup') {
- $this->inSelect(array(
- 'name' => 'optgroup',
- 'type' => HTML5::ENDTAG
- ));
+ if (end($this->stack)->nodeName === 'optgroup') {
+ $this->inSelect(
+ array(
+ 'name' => 'optgroup',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
- /* An end tag token whose tag name is "optgroup" */
- } elseif($token['type'] === HTML5::ENDTAG &&
- $token['name'] === 'optgroup') {
+ /* An end tag token whose tag name is "optgroup" */
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'optgroup'
+ ) {
/* First, if the current node is an option element, and the node
immediately before it in the stack of open elements is an optgroup
element, then act as if an end tag with the tag name "option" had
been seen. */
$elements_in_stack = count($this->stack);
- if($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
- $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') {
- $this->inSelect(array(
- 'name' => 'option',
- 'type' => HTML5::ENDTAG
- ));
+ if ($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
+ $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup'
+ ) {
+ $this->inSelect(
+ array(
+ 'name' => 'option',
+ 'type' => HTML5::ENDTAG
+ )
+ );
}
/* If the current node is an optgroup element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
- if($this->stack[$elements_in_stack - 1] === 'optgroup') {
+ if ($this->stack[$elements_in_stack - 1] === 'optgroup') {
array_pop($this->stack);
}
- /* An end tag token whose tag name is "option" */
- } elseif($token['type'] === HTML5::ENDTAG &&
- $token['name'] === 'option') {
+ /* An end tag token whose tag name is "option" */
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'option'
+ ) {
/* If the current node is an option element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
- if(end($this->stack)->nodeName === 'option') {
+ if (end($this->stack)->nodeName === 'option') {
array_pop($this->stack);
}
- /* An end tag whose tag name is "select" */
- } elseif($token['type'] === HTML5::ENDTAG &&
- $token['name'] === 'select') {
+ /* An end tag whose tag name is "select" */
+ } elseif ($token['type'] === HTML5::ENDTAG &&
+ $token['name'] === 'select'
+ ) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
- if(!$this->elementInScope($token['name'], true)) {
+ if (!$this->elementInScope($token['name'], true)) {
// w/e
- /* Otherwise: */
+ /* Otherwise: */
} else {
/* Pop elements from the stack of open elements until a select
element has been popped from the stack. */
- while(true) {
+ while (true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
- if($current === 'select') {
+ if ($current === 'select') {
break;
}
}
@@ -3322,20 +4146,35 @@ class HTML5TreeConstructer {
$this->resetInsertionMode();
}
- /* A start tag whose tag name is "select" */
- } elseif($token['name'] === 'select' &&
- $token['type'] === HTML5::STARTTAG) {
+ /* A start tag whose tag name is "select" */
+ } elseif ($token['name'] === 'select' &&
+ $token['type'] === HTML5::STARTTAG
+ ) {
/* Parse error. Act as if the token had been an end tag with the
tag name "select" instead. */
- $this->inSelect(array(
- 'name' => 'select',
- 'type' => HTML5::ENDTAG
- ));
-
- /* An end tag whose tag name is one of: "caption", "table", "tbody",
- "tfoot", "thead", "tr", "td", "th" */
- } elseif(in_array($token['name'], array('caption', 'table', 'tbody',
- 'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) {
+ $this->inSelect(
+ array(
+ 'name' => 'select',
+ 'type' => HTML5::ENDTAG
+ )
+ );
+
+ /* An end tag whose tag name is one of: "caption", "table", "tbody",
+ "tfoot", "thead", "tr", "td", "th" */
+ } elseif (in_array(
+ $token['name'],
+ array(
+ 'caption',
+ 'table',
+ 'tbody',
+ 'tfoot',
+ 'thead',
+ 'tr',
+ 'td',
+ 'th'
+ )
+ ) && $token['type'] === HTML5::ENDTAG
+ ) {
/* Parse error. */
// w/e
@@ -3343,43 +4182,47 @@ class HTML5TreeConstructer {
the same tag name as that of the token, then act as if an end tag
with the tag name "select" had been seen, and reprocess the token.
Otherwise, ignore the token. */
- if($this->elementInScope($token['name'], true)) {
- $this->inSelect(array(
- 'name' => 'select',
- 'type' => HTML5::ENDTAG
- ));
+ if ($this->elementInScope($token['name'], true)) {
+ $this->inSelect(
+ array(
+ 'name' => 'select',
+ 'type' => HTML5::ENDTAG
+ )
+ );
$this->mainPhase($token);
}
- /* Anything else */
+ /* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
- private function afterBody($token) {
+ private function afterBody($token)
+ {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
- if($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ if ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Process the token as it would be processed if the insertion mode
was "in body". */
$this->inBody($token);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the first element in the stack of open
elements (the html element), with the data attribute set to the
data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->stack[0]->appendChild($comment);
- /* An end tag with the tag name "html" */
- } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
+ /* An end tag with the tag name "html" */
+ } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
/* If the parser was originally created in order to handle the
setting of an element's innerHTML attribute, this is a parse error;
ignore the token. (The element will be an html element in this
@@ -3388,7 +4231,7 @@ class HTML5TreeConstructer {
/* Otherwise, switch to the trailing end phase. */
$this->phase = self::END_PHASE;
- /* Anything else */
+ /* Anything else */
} else {
/* Parse error. Set the insertion mode to "in body" and reprocess
the token. */
@@ -3397,34 +4240,38 @@ class HTML5TreeConstructer {
}
}
- private function inFrameset($token) {
+ private function inFrameset($token)
+ {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
- if($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ if ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Append the character to the current node. */
$this->insertText($token['data']);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
- /* A start tag with the tag name "frameset" */
- } elseif($token['name'] === 'frameset' &&
- $token['type'] === HTML5::STARTTAG) {
+ /* A start tag with the tag name "frameset" */
+ } elseif ($token['name'] === 'frameset' &&
+ $token['type'] === HTML5::STARTTAG
+ ) {
$this->insertElement($token);
- /* An end tag with the tag name "frameset" */
- } elseif($token['name'] === 'frameset' &&
- $token['type'] === HTML5::ENDTAG) {
+ /* An end tag with the tag name "frameset" */
+ } elseif ($token['name'] === 'frameset' &&
+ $token['type'] === HTML5::ENDTAG
+ ) {
/* If the current node is the root html element, then this is a
parse error; ignore the token. (innerHTML case) */
- if(end($this->stack)->nodeName === 'html') {
+ if (end($this->stack)->nodeName === 'html') {
// Ignore
} else {
@@ -3439,103 +4286,113 @@ class HTML5TreeConstructer {
$this->mode = self::AFTR_FRAME;
}
- /* A start tag with the tag name "frame" */
- } elseif($token['name'] === 'frame' &&
- $token['type'] === HTML5::STARTTAG) {
+ /* A start tag with the tag name "frame" */
+ } elseif ($token['name'] === 'frame' &&
+ $token['type'] === HTML5::STARTTAG
+ ) {
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
- /* A start tag with the tag name "noframes" */
- } elseif($token['name'] === 'noframes' &&
- $token['type'] === HTML5::STARTTAG) {
+ /* A start tag with the tag name "noframes" */
+ } elseif ($token['name'] === 'noframes' &&
+ $token['type'] === HTML5::STARTTAG
+ ) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
- /* Anything else */
+ /* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
- private function afterFrameset($token) {
+ private function afterFrameset($token)
+ {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
- if($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ if ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Append the character to the current node. */
$this->insertText($token['data']);
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
- /* An end tag with the tag name "html" */
- } elseif($token['name'] === 'html' &&
- $token['type'] === HTML5::ENDTAG) {
+ /* An end tag with the tag name "html" */
+ } elseif ($token['name'] === 'html' &&
+ $token['type'] === HTML5::ENDTAG
+ ) {
/* Switch to the trailing end phase. */
$this->phase = self::END_PHASE;
- /* A start tag with the tag name "noframes" */
- } elseif($token['name'] === 'noframes' &&
- $token['type'] === HTML5::STARTTAG) {
+ /* A start tag with the tag name "noframes" */
+ } elseif ($token['name'] === 'noframes' &&
+ $token['type'] === HTML5::STARTTAG
+ ) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
- /* Anything else */
+ /* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
- private function trailingEndPhase($token) {
+ private function trailingEndPhase($token)
+ {
/* After the main phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
- if($token['type'] === HTML5::DOCTYPE) {
+ if ($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
- /* A comment token */
- } elseif($token['type'] === HTML5::COMMENT) {
+ /* A comment token */
+ } elseif ($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
- /* A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
- or U+0020 SPACE */
- } elseif($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+ /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE */
+ } elseif ($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
+ ) {
/* Process the token as it would be processed in the main phase. */
$this->mainPhase($token);
- /* A character token that is not one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
- or U+0020 SPACE. Or a start tag token. Or an end tag token. */
- } elseif(($token['type'] === HTML5::CHARACTR &&
- preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
- $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) {
+ /* A character token that is not one of U+0009 CHARACTER TABULATION,
+ U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
+ or U+0020 SPACE. Or a start tag token. Or an end tag token. */
+ } elseif (($token['type'] === HTML5::CHARACTR &&
+ preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
+ $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG
+ ) {
/* Parse error. Switch back to the main phase and reprocess the
token. */
$this->phase = self::MAIN_PHASE;
return $this->mainPhase($token);
- /* An end-of-file token */
- } elseif($token['type'] === HTML5::EOF) {
+ /* An end-of-file token */
+ } elseif ($token['type'] === HTML5::EOF) {
/* OMG DONE!! */
}
}
- private function insertElement($token, $append = true, $check = false) {
+ private function insertElement($token, $append = true, $check = false)
+ {
// Proprietary workaround for libxml2's limitations with tag names
if ($check) {
// Slightly modified HTML5 tag-name modification,
@@ -3544,13 +4401,15 @@ class HTML5TreeConstructer {
// Remove leading hyphens and numbers
$token['name'] = ltrim($token['name'], '-0..9');
// In theory, this should ever be needed, but just in case
- if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice
+ if ($token['name'] === '') {
+ $token['name'] = 'span';
+ } // arbitrary generic choice
}
-
+
$el = $this->dom->createElement($token['name']);
- foreach($token['attr'] as $attr) {
- if(!$el->hasAttribute($attr['name'])) {
+ foreach ($token['attr'] as $attr) {
+ if (!$el->hasAttribute($attr['name'])) {
$el->setAttribute($attr['name'], $attr['value']);
}
}
@@ -3561,48 +4420,54 @@ class HTML5TreeConstructer {
return $el;
}
- private function insertText($data) {
+ private function insertText($data)
+ {
$text = $this->dom->createTextNode($data);
$this->appendToRealParent($text);
}
- private function insertComment($data) {
+ private function insertComment($data)
+ {
$comment = $this->dom->createComment($data);
$this->appendToRealParent($comment);
}
- private function appendToRealParent($node) {
- if($this->foster_parent === null) {
+ private function appendToRealParent($node)
+ {
+ if ($this->foster_parent === null) {
end($this->stack)->appendChild($node);
- } elseif($this->foster_parent !== null) {
+ } elseif ($this->foster_parent !== null) {
/* If the foster parent element is the parent element of the
last table element in the stack of open elements, then the new
node must be inserted immediately before the last table element
in the stack of open elements in the foster parent element;
otherwise, the new node must be appended to the foster parent
element. */
- for($n = count($this->stack) - 1; $n >= 0; $n--) {
- if($this->stack[$n]->nodeName === 'table' &&
- $this->stack[$n]->parentNode !== null) {
+ for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+ if ($this->stack[$n]->nodeName === 'table' &&
+ $this->stack[$n]->parentNode !== null
+ ) {
$table = $this->stack[$n];
break;
}
}
- if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
+ if (isset($table) && $this->foster_parent->isSameNode($table->parentNode)) {
$this->foster_parent->insertBefore($node, $table);
- else
+ } else {
$this->foster_parent->appendChild($node);
+ }
$this->foster_parent = null;
}
}
- private function elementInScope($el, $table = false) {
- if(is_array($el)) {
- foreach($el as $element) {
- if($this->elementInScope($element, $table)) {
+ private function elementInScope($el, $table = false)
+ {
+ if (is_array($el)) {
+ foreach ($el as $element) {
+ if ($this->elementInScope($element, $table)) {
return true;
}
}
@@ -3612,28 +4477,38 @@ class HTML5TreeConstructer {
$leng = count($this->stack);
- for($n = 0; $n < $leng; $n++) {
+ for ($n = 0; $n < $leng; $n++) {
/* 1. Initialise node to be the current node (the bottommost node of
the stack). */
$node = $this->stack[$leng - 1 - $n];
- if($node->tagName === $el) {
+ if ($node->tagName === $el) {
/* 2. If node is the target node, terminate in a match state. */
return true;
- } elseif($node->tagName === 'table') {
+ } elseif ($node->tagName === 'table') {
/* 3. Otherwise, if node is a table element, terminate in a failure
state. */
return false;
- } elseif($table === true && in_array($node->tagName, array('caption', 'td',
- 'th', 'button', 'marquee', 'object'))) {
+ } elseif ($table === true && in_array(
+ $node->tagName,
+ array(
+ 'caption',
+ 'td',
+ 'th',
+ 'button',
+ 'marquee',
+ 'object'
+ )
+ )
+ ) {
/* 4. Otherwise, if the algorithm is the "has an element in scope"
variant (rather than the "has an element in table scope" variant),
and node is one of the following, terminate in a failure state. */
return false;
- } elseif($node === $node->ownerDocument->documentElement) {
+ } elseif ($node === $node->ownerDocument->documentElement) {
/* 5. Otherwise, if node is an html element (root element), terminate
in a failure state. (This can only happen if the node is the topmost
node of the stack of open elements, and prevents the next step from
@@ -3648,12 +4523,13 @@ class HTML5TreeConstructer {
}
}
- private function reconstructActiveFormattingElements() {
+ private function reconstructActiveFormattingElements()
+ {
/* 1. If there are no entries in the list of active formatting elements,
then there is nothing to reconstruct; stop this algorithm. */
$formatting_elements = count($this->a_formatting);
- if($formatting_elements === 0) {
+ if ($formatting_elements === 0) {
return false;
}
@@ -3665,14 +4541,14 @@ class HTML5TreeConstructer {
formatting elements is a marker, or if it is an element that is in the
stack of open elements, then there is nothing to reconstruct; stop this
algorithm. */
- if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+ if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
return false;
}
- for($a = $formatting_elements - 1; $a >= 0; true) {
+ for ($a = $formatting_elements - 1; $a >= 0; true) {
/* 4. If there are no entries before entry in the list of active
formatting elements, then jump to step 8. */
- if($a === 0) {
+ if ($a === 0) {
$step_seven = false;
break;
}
@@ -3684,15 +4560,15 @@ class HTML5TreeConstructer {
/* 6. If entry is neither a marker nor an element that is also in
thetack of open elements, go to step 4. */
- if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+ if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
break;
}
}
- while(true) {
+ while (true) {
/* 7. Let entry be the element one later than entry in the list of
active formatting elements. */
- if(isset($step_seven) && $step_seven === true) {
+ if (isset($step_seven) && $step_seven === true) {
$a++;
$entry = $this->a_formatting[$a];
}
@@ -3711,7 +4587,7 @@ class HTML5TreeConstructer {
/* 11. If the entry for clone in the list of active formatting
elements is not the last entry in the list, return to step 7. */
- if(end($this->a_formatting) !== $clone) {
+ if (end($this->a_formatting) !== $clone) {
$step_seven = true;
} else {
break;
@@ -3719,12 +4595,13 @@ class HTML5TreeConstructer {
}
}
- private function clearTheActiveFormattingElementsUpToTheLastMarker() {
+ private function clearTheActiveFormattingElementsUpToTheLastMarker()
+ {
/* When the steps below require the UA to clear the list of active
formatting elements up to the last marker, the UA must perform the
following steps: */
- while(true) {
+ while (true) {
/* 1. Let entry be the last (most recently added) entry in the list
of active formatting elements. */
$entry = end($this->a_formatting);
@@ -3734,13 +4611,14 @@ class HTML5TreeConstructer {
/* 3. If entry was a marker, then stop the algorithm at this point.
The list has been cleared up to the last marker. */
- if($entry === self::MARKER) {
+ if ($entry === self::MARKER) {
break;
}
}
}
- private function generateImpliedEndTags($exclude = array()) {
+ private function generateImpliedEndTags($exclude = array())
+ {
/* When the steps below require the UA to generate implied end tags,
then, if the current node is a dd element, a dt element, an li element,
a p element, a td element, a th element, or a tr element, the UA must
@@ -3749,36 +4627,36 @@ class HTML5TreeConstructer {
$node = end($this->stack);
$elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
- while(in_array(end($this->stack)->nodeName, $elements)) {
+ while (in_array(end($this->stack)->nodeName, $elements)) {
array_pop($this->stack);
}
}
- private function getElementCategory($node) {
+ private function getElementCategory($node)
+ {
$name = $node->tagName;
- if(in_array($name, $this->special))
+ if (in_array($name, $this->special)) {
return self::SPECIAL;
-
- elseif(in_array($name, $this->scoping))
+ } elseif (in_array($name, $this->scoping)) {
return self::SCOPING;
-
- elseif(in_array($name, $this->formatting))
+ } elseif (in_array($name, $this->formatting)) {
return self::FORMATTING;
-
- else
+ } else {
return self::PHRASING;
+ }
}
- private function clearStackToTableContext($elements) {
+ private function clearStackToTableContext($elements)
+ {
/* When the steps above require the UA to clear the stack back to a
table context, it means that the UA must, while the current node is not
a table element or an html element, pop elements from the stack of open
elements. If this causes any elements to be popped from the stack, then
this is a parse error. */
- while(true) {
+ while (true) {
$node = end($this->stack)->nodeName;
- if(in_array($node, $elements)) {
+ if (in_array($node, $elements)) {
break;
} else {
array_pop($this->stack);
@@ -3786,12 +4664,13 @@ class HTML5TreeConstructer {
}
}
- private function resetInsertionMode() {
+ private function resetInsertionMode()
+ {
/* 1. Let last be false. */
$last = false;
$leng = count($this->stack);
- for($n = $leng - 1; $n >= 0; $n--) {
+ for ($n = $leng - 1; $n >= 0; $n--) {
/* 2. Let node be the last node in the stack of open elements. */
$node = $this->stack[$n];
@@ -3799,108 +4678,111 @@ class HTML5TreeConstructer {
set last to true. If the element whose innerHTML attribute is being
set is neither a td element nor a th element, then set node to the
element whose innerHTML attribute is being set. (innerHTML case) */
- if($this->stack[0]->isSameNode($node)) {
+ if ($this->stack[0]->isSameNode($node)) {
$last = true;
}
/* 4. If node is a select element, then switch the insertion mode to
"in select" and abort these steps. (innerHTML case) */
- if($node->nodeName === 'select') {
+ if ($node->nodeName === 'select') {
$this->mode = self::IN_SELECT;
break;
- /* 5. If node is a td or th element, then switch the insertion mode
- to "in cell" and abort these steps. */
- } elseif($node->nodeName === 'td' || $node->nodeName === 'th') {
+ /* 5. If node is a td or th element, then switch the insertion mode
+ to "in cell" and abort these steps. */
+ } elseif ($node->nodeName === 'td' || $node->nodeName === 'th') {
$this->mode = self::IN_CELL;
break;
- /* 6. If node is a tr element, then switch the insertion mode to
- "in row" and abort these steps. */
- } elseif($node->nodeName === 'tr') {
+ /* 6. If node is a tr element, then switch the insertion mode to
+ "in row" and abort these steps. */
+ } elseif ($node->nodeName === 'tr') {
$this->mode = self::IN_ROW;
break;
- /* 7. If node is a tbody, thead, or tfoot element, then switch the
- insertion mode to "in table body" and abort these steps. */
- } elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
+ /* 7. If node is a tbody, thead, or tfoot element, then switch the
+ insertion mode to "in table body" and abort these steps. */
+ } elseif (in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
$this->mode = self::IN_TBODY;
break;
- /* 8. If node is a caption element, then switch the insertion mode
- to "in caption" and abort these steps. */
- } elseif($node->nodeName === 'caption') {
+ /* 8. If node is a caption element, then switch the insertion mode
+ to "in caption" and abort these steps. */
+ } elseif ($node->nodeName === 'caption') {
$this->mode = self::IN_CAPTION;
break;
- /* 9. If node is a colgroup element, then switch the insertion mode
- to "in column group" and abort these steps. (innerHTML case) */
- } elseif($node->nodeName === 'colgroup') {
+ /* 9. If node is a colgroup element, then switch the insertion mode
+ to "in column group" and abort these steps. (innerHTML case) */
+ } elseif ($node->nodeName === 'colgroup') {
$this->mode = self::IN_CGROUP;
break;
- /* 10. If node is a table element, then switch the insertion mode
- to "in table" and abort these steps. */
- } elseif($node->nodeName === 'table') {
+ /* 10. If node is a table element, then switch the insertion mode
+ to "in table" and abort these steps. */
+ } elseif ($node->nodeName === 'table') {
$this->mode = self::IN_TABLE;
break;
- /* 11. If node is a head element, then switch the insertion mode
- to "in body" ("in body"! not "in head"!) and abort these steps.
- (innerHTML case) */
- } elseif($node->nodeName === 'head') {
+ /* 11. If node is a head element, then switch the insertion mode
+ to "in body" ("in body"! not "in head"!) and abort these steps.
+ (innerHTML case) */
+ } elseif ($node->nodeName === 'head') {
$this->mode = self::IN_BODY;
break;
- /* 12. If node is a body element, then switch the insertion mode to
- "in body" and abort these steps. */
- } elseif($node->nodeName === 'body') {
+ /* 12. If node is a body element, then switch the insertion mode to
+ "in body" and abort these steps. */
+ } elseif ($node->nodeName === 'body') {
$this->mode = self::IN_BODY;
break;
- /* 13. If node is a frameset element, then switch the insertion
- mode to "in frameset" and abort these steps. (innerHTML case) */
- } elseif($node->nodeName === 'frameset') {
+ /* 13. If node is a frameset element, then switch the insertion
+ mode to "in frameset" and abort these steps. (innerHTML case) */
+ } elseif ($node->nodeName === 'frameset') {
$this->mode = self::IN_FRAME;
break;
- /* 14. If node is an html element, then: if the head element
- pointer is null, switch the insertion mode to "before head",
- otherwise, switch the insertion mode to "after head". In either
- case, abort these steps. (innerHTML case) */
- } elseif($node->nodeName === 'html') {
+ /* 14. If node is an html element, then: if the head element
+ pointer is null, switch the insertion mode to "before head",
+ otherwise, switch the insertion mode to "after head". In either
+ case, abort these steps. (innerHTML case) */
+ } elseif ($node->nodeName === 'html') {
$this->mode = ($this->head_pointer === null)
? self::BEFOR_HEAD
: self::AFTER_HEAD;
break;
- /* 15. If last is true, then set the insertion mode to "in body"
- and abort these steps. (innerHTML case) */
- } elseif($last) {
+ /* 15. If last is true, then set the insertion mode to "in body"
+ and abort these steps. (innerHTML case) */
+ } elseif ($last) {
$this->mode = self::IN_BODY;
break;
}
}
}
- private function closeCell() {
+ private function closeCell()
+ {
/* If the stack of open elements has a td or th element in table scope,
then act as if an end tag token with that tag name had been seen. */
- foreach(array('td', 'th') as $cell) {
- if($this->elementInScope($cell, true)) {
- $this->inCell(array(
- 'name' => $cell,
- 'type' => HTML5::ENDTAG
- ));
+ foreach (array('td', 'th') as $cell) {
+ if ($this->elementInScope($cell, true)) {
+ $this->inCell(
+ array(
+ 'name' => $cell,
+ 'type' => HTML5::ENDTAG
+ )
+ );
break;
}
}
}
- public function save() {
+ public function save()
+ {
return $this->dom;
}
}
-?>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-09 17:12:39 +0000