wp-parsely / vendor / masterminds / html5 / src / HTML5 / Parser / EventHandler.php

EventHandler.php in Parse.ly 3.20.0, at vendor/masterminds/html5/src/HTML5/Parser/EventHandler.php

115 lines 3.6 KB

Raw Download Zip

1	<?php
2
3	namespace Masterminds\HTML5\Parser;
4
5	/**
6	* Standard events for HTML5.
7	*
8	* This is roughly analogous to a SAX2 or expat-style interface.
9	* However, it is tuned specifically for HTML5, according to section 8
10	* of the HTML5 specification.
11	*
12	* An event handler receives parser events. For a concrete
13	* implementation, see DOMTreeBuilder.
14	*
15	* Quirks support in the parser is limited to close-in syntax (malformed
16	* tags or attributes). Higher order syntax and semantic issues with a
17	* document (e.g. mismatched tags, illegal nesting, etc.) are the
18	* responsibility of the event handler implementation.
19	*
20	* See HTML5 spec section 8.2.4
21	*/
22	interface EventHandler
23	{
24	const DOCTYPE_NONE = 0;
25
26	const DOCTYPE_PUBLIC = 1;
27
28	const DOCTYPE_SYSTEM = 2;
29
30	/**
31	* A doctype declaration.
32	*
33	* @param string $name The name of the root element.
34	* @param int $idType One of DOCTYPE_NONE, DOCTYPE_PUBLIC, or DOCTYPE_SYSTEM
35	* @param string $id The identifier. For DOCTYPE_PUBLIC, this is the public ID. If DOCTYPE_SYSTEM,
36	* then this is a system ID.
37	* @param bool $quirks Indicates whether the builder should enter quirks mode.
38	*/
39	public function doctype($name, $idType = 0, $id = null, $quirks = false);
40
41	/**
42	* A start tag.
43	*
44	* IMPORTANT: The parser watches the return value of this event. If this returns
45	* an integer, the parser will switch TEXTMODE patters according to the int.
46	*
47	* This is how the Tree Builder can tell the Tokenizer when a certain tag should
48	* cause the parser to go into RAW text mode.
49	*
50	* The HTML5 standard requires that the builder is the one that initiates this
51	* step, and this is the only way short of a circular reference that we can
52	* do that.
53	*
54	* Example: if a startTag even for a `script` name is fired, and the startTag()
55	* implementation returns Tokenizer::TEXTMODE_RAW, then the tokenizer will
56	* switch into RAW text mode and consume data until it reaches a closing
57	* `script` tag.
58	*
59	* The textmode is automatically reset to Tokenizer::TEXTMODE_NORMAL when the
60	* closing tag is encounter. This behavior may change.
61	*
62	* @param string $name The tag name.
63	* @param array $attributes An array with all of the tag's attributes.
64	* @param bool $selfClosing An indicator of whether or not this tag is self-closing (<foo/>).
65	*
66	* @return int one of the Tokenizer::TEXTMODE_* constants
67	*/
68	public function startTag($name, $attributes = array(), $selfClosing = false);
69
70	/**
71	* An end-tag.
72	*/
73	public function endTag($name);
74
75	/**
76	* A comment section (unparsed character data).
77	*/
78	public function comment($cdata);
79
80	/**
81	* A unit of parsed character data.
82	*
83	* Entities in this text are already decoded.
84	*/
85	public function text($cdata);
86
87	/**
88	* Indicates that the document has been entirely processed.
89	*/
90	public function eof();
91
92	/**
93	* Emitted when the parser encounters an error condition.
94	*/
95	public function parseError($msg, $line, $col);
96
97	/**
98	* A CDATA section.
99	*
100	* @param string $data
101	* The unparsed character data
102	*/
103	public function cdata($data);
104
105	/**
106	* This is a holdover from the XML spec.
107	*
108	* While user agents don't get PIs, server-side does.
109	*
110	* @param string $name The name of the processor (e.g. 'php').
111	* @param string $data The unparsed data.
112	*/
113	public function processingInstruction($name, $data = null);
114	}
115