Scanner.php — Independent Analytics – WordPress Analytics Plugin 1.17

independent-analytics / vendor / masterminds / html5 / src / HTML5 / Parser / Scanner.php

independent-analytics / vendor / masterminds / html5 / src / HTML5 / Parser Last commit date

CharacterReference.php 3 years ago DOMTreeBuilder.php 3 years ago EventHandler.php 3 years ago FileInputStream.php 3 years ago InputStream.php 3 years ago ParseError.php 3 years ago Scanner.php 3 years ago StringInputStream.php 3 years ago Tokenizer.php 3 years ago TreeBuildingRules.php 3 years ago UTF8Utils.php 3 years ago

Scanner.php

363 lines

1	<?php
2
3	namespace IAWP\Masterminds\HTML5\Parser;
4
5	use IAWP\Masterminds\HTML5\Exception;
6	/**
7	* The scanner scans over a given data input to react appropriately to characters.
8	*/
9	class Scanner
10	{
11	const CHARS_HEX = 'abcdefABCDEF01234567890';
12	const CHARS_ALNUM = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890';
13	const CHARS_ALPHA = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ';
14	/**
15	* The string data we're parsing.
16	*/
17	private $data;
18	/**
19	* The current integer byte position we are in $data.
20	*/
21	private $char;
22	/**
23	* Length of $data; when $char === $data, we are at the end-of-file.
24	*/
25	private $EOF;
26	/**
27	* Parse errors.
28	*/
29	public $errors = array();
30	/**
31	* Create a new Scanner.
32	*
33	* @param string $data Data to parse.
34	* @param string $encoding The encoding to use for the data.
35	*
36	* @throws Exception If the given data cannot be encoded to UTF-8.
37	*/
38	public function __construct($data, $encoding = 'UTF-8')
39	{
40	if ($data instanceof InputStream) {
41	@\trigger_error('InputStream objects are deprecated since version 2.4 and will be removed in 3.0. Use strings instead.', \E_USER_DEPRECATED);
42	$data = (string) $data;
43	}
44	$data = UTF8Utils::convertToUTF8($data, $encoding);
45	// There is good reason to question whether it makes sense to
46	// do this here, since most of these checks are done during
47	// parsing, and since this check doesn't actually do anything.
48	$this->errors = UTF8Utils::checkForIllegalCodepoints($data);
49	$data = $this->replaceLinefeeds($data);
50	$this->data = $data;
51	$this->char = 0;
52	$this->EOF = \strlen($data);
53	}
54	/**
55	* Check if upcomming chars match the given sequence.
56	*
57	* This will read the stream for the $sequence. If it's
58	* found, this will return true. If not, return false.
59	* Since this unconsumes any chars it reads, the caller
60	* will still need to read the next sequence, even if
61	* this returns true.
62	*
63	* Example: $this->scanner->sequenceMatches('</script>') will
64	* see if the input stream is at the start of a
65	* '</script>' string.
66	*
67	* @param string $sequence
68	* @param bool $caseSensitive
69	*
70	* @return bool
71	*/
72	public function sequenceMatches($sequence, $caseSensitive = \true)
73	{
74	$portion = \substr($this->data, $this->char, \strlen($sequence));
75	return $caseSensitive ? $portion === $sequence : 0 === \strcasecmp($portion, $sequence);
76	}
77	/**
78	* Get the current position.
79	*
80	* @return int The current intiger byte position.
81	*/
82	public function position()
83	{
84	return $this->char;
85	}
86	/**
87	* Take a peek at the next character in the data.
88	*
89	* @return string The next character.
90	*/
91	public function peek()
92	{
93	if ($this->char + 1 < $this->EOF) {
94	return $this->data[$this->char + 1];
95	}
96	return \false;
97	}
98	/**
99	* Get the next character.
100	* Note: This advances the pointer.
101	*
102	* @return string The next character.
103	*/
104	public function next()
105	{
106	++$this->char;
107	if ($this->char < $this->EOF) {
108	return $this->data[$this->char];
109	}
110	return \false;
111	}
112	/**
113	* Get the current character.
114	* Note, this does not advance the pointer.
115	*
116	* @return string The current character.
117	*/
118	public function current()
119	{
120	if ($this->char < $this->EOF) {
121	return $this->data[$this->char];
122	}
123	return \false;
124	}
125	/**
126	* Silently consume N chars.
127	*
128	* @param int $count
129	*/
130	public function consume($count = 1)
131	{
132	$this->char += $count;
133	}
134	/**
135	* Unconsume some of the data.
136	* This moves the data pointer backwards.
137	*
138	* @param int $howMany The number of characters to move the pointer back.
139	*/
140	public function unconsume($howMany = 1)
141	{
142	if ($this->char - $howMany >= 0) {
143	$this->char -= $howMany;
144	}
145	}
146	/**
147	* Get the next group of that contains hex characters.
148	* Note, along with getting the characters the pointer in the data will be
149	* moved as well.
150	*
151	* @return string The next group that is hex characters.
152	*/
153	public function getHex()
154	{
155	return $this->doCharsWhile(static::CHARS_HEX);
156	}
157	/**
158	* Get the next group of characters that are ASCII Alpha characters.
159	* Note, along with getting the characters the pointer in the data will be
160	* moved as well.
161	*
162	* @return string The next group of ASCII alpha characters.
163	*/
164	public function getAsciiAlpha()
165	{
166	return $this->doCharsWhile(static::CHARS_ALPHA);
167	}
168	/**
169	* Get the next group of characters that are ASCII Alpha characters and numbers.
170	* Note, along with getting the characters the pointer in the data will be
171	* moved as well.
172	*
173	* @return string The next group of ASCII alpha characters and numbers.
174	*/
175	public function getAsciiAlphaNum()
176	{
177	return $this->doCharsWhile(static::CHARS_ALNUM);
178	}
179	/**
180	* Get the next group of numbers.
181	* Note, along with getting the characters the pointer in the data will be
182	* moved as well.
183	*
184	* @return string The next group of numbers.
185	*/
186	public function getNumeric()
187	{
188	return $this->doCharsWhile('0123456789');
189	}
190	/**
191	* Consume whitespace.
192	* Whitespace in HTML5 is: formfeed, tab, newline, space.
193	*
194	* @return int The length of the matched whitespaces.
195	*/
196	public function whitespace()
197	{
198	if ($this->char >= $this->EOF) {
199	return \false;
200	}
201	$len = \strspn($this->data, "\n\t\f ", $this->char);
202	$this->char += $len;
203	return $len;
204	}
205	/**
206	* Returns the current line that is being consumed.
207	*
208	* @return int The current line number.
209	*/
210	public function currentLine()
211	{
212	if (empty($this->EOF) \|\| 0 === $this->char) {
213	return 1;
214	}
215	// Add one to $this->char because we want the number for the next
216	// byte to be processed.
217	return \substr_count($this->data, "\n", 0, \min($this->char, $this->EOF)) + 1;
218	}
219	/**
220	* Read chars until something in the mask is encountered.
221	*
222	* @param string $mask
223	*
224	* @return mixed
225	*/
226	public function charsUntil($mask)
227	{
228	return $this->doCharsUntil($mask);
229	}
230	/**
231	* Read chars as long as the mask matches.
232	*
233	* @param string $mask
234	*
235	* @return int
236	*/
237	public function charsWhile($mask)
238	{
239	return $this->doCharsWhile($mask);
240	}
241	/**
242	* Returns the current column of the current line that the tokenizer is at.
243	*
244	* Newlines are column 0. The first char after a newline is column 1.
245	*
246	* @return int The column number.
247	*/
248	public function columnOffset()
249	{
250	// Short circuit for the first char.
251	if (0 === $this->char) {
252	return 0;
253	}
254	// strrpos is weird, and the offset needs to be negative for what we
255	// want (i.e., the last \n before $this->char). This needs to not have
256	// one (to make it point to the next character, the one we want the
257	// position of) added to it because strrpos's behaviour includes the
258	// final offset byte.
259	$backwardFrom = $this->char - 1 - \strlen($this->data);
260	$lastLine = \strrpos($this->data, "\n", $backwardFrom);
261	// However, for here we want the length up until the next byte to be
262	// processed, so add one to the current byte ($this->char).
263	if (\false !== $lastLine) {
264	$findLengthOf = \substr($this->data, $lastLine + 1, $this->char - 1 - $lastLine);
265	} else {
266	// After a newline.
267	$findLengthOf = \substr($this->data, 0, $this->char);
268	}
269	return UTF8Utils::countChars($findLengthOf);
270	}
271	/**
272	* Get all characters until EOF.
273	*
274	* This consumes characters until the EOF.
275	*
276	* @return int The number of characters remaining.
277	*/
278	public function remainingChars()
279	{
280	if ($this->char < $this->EOF) {
281	$data = \substr($this->data, $this->char);
282	$this->char = $this->EOF;
283	return $data;
284	}
285	return '';
286	// false;
287	}
288	/**
289	* Replace linefeed characters according to the spec.
290	*
291	* @param $data
292	*
293	* @return string
294	*/
295	private function replaceLinefeeds($data)
296	{
297	/*
298	* U+000D CARRIAGE RETURN (CR) characters and U+000A LINE FEED (LF) characters are treated specially.
299	* Any CR characters that are followed by LF characters must be removed, and any CR characters not
300	* followed by LF characters must be converted to LF characters. Thus, newlines in HTML DOMs are
301	* represented by LF characters, and there are never any CR characters in the input to the tokenization
302	* stage.
303	*/
304	$crlfTable = array("\x00" => "�", "\r\n" => "\n", "\r" => "\n");
305	return \strtr($data, $crlfTable);
306	}
307	/**
308	* Read to a particular match (or until $max bytes are consumed).
309	*
310	* This operates on byte sequences, not characters.
311	*
312	* Matches as far as possible until we reach a certain set of bytes
313	* and returns the matched substring.
314	*
315	* @param string $bytes Bytes to match.
316	* @param int $max Maximum number of bytes to scan.
317	*
318	* @return mixed Index or false if no match is found. You should use strong
319	* equality when checking the result, since index could be 0.
320	*/
321	private function doCharsUntil($bytes, $max = null)
322	{
323	if ($this->char >= $this->EOF) {
324	return \false;
325	}
326	if (0 === $max \|\| $max) {
327	$len = \strcspn($this->data, $bytes, $this->char, $max);
328	} else {
329	$len = \strcspn($this->data, $bytes, $this->char);
330	}
331	$string = (string) \substr($this->data, $this->char, $len);
332	$this->char += $len;
333	return $string;
334	}
335	/**
336	* Returns the string so long as $bytes matches.
337	*
338	* Matches as far as possible with a certain set of bytes
339	* and returns the matched substring.
340	*
341	* @param string $bytes A mask of bytes to match. If ANY byte in this mask matches the
342	* current char, the pointer advances and the char is part of the
343	* substring.
344	* @param int $max The max number of chars to read.
345	*
346	* @return string
347	*/
348	private function doCharsWhile($bytes, $max = null)
349	{
350	if ($this->char >= $this->EOF) {
351	return \false;
352	}
353	if (0 === $max \|\| $max) {
354	$len = \strspn($this->data, $bytes, $this->char, $max);
355	} else {
356	$len = \strspn($this->data, $bytes, $this->char);
357	}
358	$string = (string) \substr($this->data, $this->char, $len);
359	$this->char += $len;
360	return $string;
361	}
362	}
363