|
1
|
|
|
<?php |
|
2
|
|
|
namespace Masterminds\Html5\Parser; |
|
3
|
|
|
use Psr\Log\LoggerInterface; |
|
4
|
|
|
use Psr\Log\NullLogger; |
|
5
|
|
|
|
|
6
|
|
|
/** |
|
7
|
|
|
* The scanner. |
|
8
|
|
|
* |
|
9
|
|
|
* This scans over an input stream. |
|
10
|
|
|
*/ |
|
11
|
|
|
class Scanner |
|
12
|
|
|
{ |
|
13
|
|
|
|
|
14
|
|
|
const CHARS_HEX = 'abcdefABCDEF01234567890'; |
|
15
|
|
|
|
|
16
|
|
|
const CHARS_ALNUM = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890'; |
|
17
|
|
|
|
|
18
|
|
|
const CHARS_ALPHA = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'; |
|
19
|
|
|
|
|
20
|
|
|
protected $is; |
|
21
|
|
|
|
|
22
|
|
|
/** |
|
23
|
|
|
* @var LoggerInterface |
|
24
|
|
|
*/ |
|
25
|
|
|
protected $logger; |
|
26
|
|
|
|
|
27
|
|
|
/** |
|
28
|
|
|
* Create a new Scanner. |
|
29
|
|
|
* |
|
30
|
|
|
* @param InputStream $input An InputStream to be scanned. |
|
31
|
|
|
* @param LoggerInterface $logger |
|
32
|
|
|
*/ |
|
33
|
126 |
|
public function __construct(InputStream $input, LoggerInterface $logger = null) |
|
34
|
|
|
{ |
|
35
|
126 |
|
$this->is = $input; |
|
36
|
126 |
|
$this->logger = $logger ?: new NullLogger(); |
|
37
|
126 |
|
} |
|
38
|
|
|
|
|
39
|
|
|
/** |
|
40
|
|
|
* Get the current position. |
|
41
|
|
|
* |
|
42
|
|
|
* @return int The current intiger byte position. |
|
43
|
|
|
*/ |
|
44
|
115 |
|
public function position() |
|
45
|
|
|
{ |
|
46
|
115 |
|
return $this->is->key(); |
|
47
|
|
|
} |
|
48
|
|
|
|
|
49
|
|
|
/** |
|
50
|
|
|
* Take a peek at the next character in the data. |
|
51
|
|
|
* |
|
52
|
|
|
* @return string The next character. |
|
53
|
|
|
*/ |
|
54
|
12 |
|
public function peek() |
|
55
|
|
|
{ |
|
56
|
12 |
|
return $this->is->peek(); |
|
57
|
|
|
} |
|
58
|
|
|
|
|
59
|
|
|
/** |
|
60
|
|
|
* Get the next character. |
|
61
|
|
|
* |
|
62
|
|
|
* Note: This advances the pointer. |
|
63
|
|
|
*/ |
|
64
|
122 |
|
public function next() |
|
65
|
|
|
{ |
|
66
|
122 |
|
$this->is->next(); |
|
67
|
122 |
|
} |
|
68
|
|
|
|
|
69
|
|
|
/** |
|
70
|
|
|
* Get the current character. |
|
71
|
|
|
* |
|
72
|
|
|
* Note, this does not advance the pointer. |
|
73
|
|
|
* |
|
74
|
|
|
* @return mixed Any value can be returned. Typically the current character. |
|
75
|
|
|
*/ |
|
76
|
115 |
|
public function current() |
|
77
|
|
|
{ |
|
78
|
115 |
|
if ($this->is->valid()) { |
|
79
|
113 |
|
$this->logger->debug(sprintf("> %s\n", $this->is->current())); |
|
80
|
113 |
|
return $this->is->current(); |
|
81
|
|
|
} |
|
82
|
|
|
|
|
83
|
113 |
|
return false; |
|
84
|
|
|
} |
|
85
|
|
|
|
|
86
|
|
|
/** |
|
87
|
|
|
* Silently consume N chars. |
|
88
|
|
|
*/ |
|
89
|
36 |
|
public function consume($count = 1) |
|
90
|
|
|
{ |
|
91
|
36 |
|
for ($i = 0; $i < $count; ++ $i) { |
|
92
|
36 |
|
$this->next(); |
|
93
|
36 |
|
} |
|
94
|
36 |
|
} |
|
95
|
|
|
|
|
96
|
|
|
/** |
|
97
|
|
|
* Unconsume some of the data. |
|
98
|
|
|
* This moves the data pointer backwards. |
|
99
|
|
|
* |
|
100
|
|
|
* @param int $howMany |
|
101
|
|
|
* The number of characters to move the pointer back. |
|
102
|
|
|
*/ |
|
103
|
52 |
|
public function unconsume($howMany = 1) |
|
104
|
|
|
{ |
|
105
|
52 |
|
$this->is->unconsume($howMany); |
|
106
|
52 |
|
} |
|
107
|
|
|
|
|
108
|
|
|
/** |
|
109
|
|
|
* Get the next group of that contains hex characters. |
|
110
|
|
|
* |
|
111
|
|
|
* Note, along with getting the characters the pointer in the data will be |
|
112
|
|
|
* moved as well. |
|
113
|
|
|
* |
|
114
|
|
|
* @return string The next group that is hex characters. |
|
115
|
|
|
*/ |
|
116
|
4 |
|
public function getHex() |
|
117
|
|
|
{ |
|
118
|
4 |
|
return $this->is->charsWhile(static::CHARS_HEX); |
|
119
|
|
|
} |
|
120
|
|
|
|
|
121
|
|
|
/** |
|
122
|
|
|
* Get the next group of characters that are ASCII Alpha characters. |
|
123
|
|
|
* |
|
124
|
|
|
* Note, along with getting the characters the pointer in the data will be |
|
125
|
|
|
* moved as well. |
|
126
|
|
|
* |
|
127
|
|
|
* @return string The next group of ASCII alpha characters. |
|
128
|
|
|
*/ |
|
129
|
16 |
|
public function getAsciiAlpha() |
|
130
|
|
|
{ |
|
131
|
16 |
|
return $this->is->charsWhile(static::CHARS_ALPHA); |
|
132
|
|
|
} |
|
133
|
|
|
|
|
134
|
|
|
/** |
|
135
|
|
|
* Get the next group of characters that are ASCII Alpha characters and numbers. |
|
136
|
|
|
* |
|
137
|
|
|
* Note, along with getting the characters the pointer in the data will be |
|
138
|
|
|
* moved as well. |
|
139
|
|
|
* |
|
140
|
|
|
* @return string The next group of ASCII alpha characters and numbers. |
|
141
|
|
|
*/ |
|
142
|
4 |
|
public function getAsciiAlphaNum() |
|
143
|
|
|
{ |
|
144
|
4 |
|
return $this->is->charsWhile(static::CHARS_ALNUM); |
|
145
|
|
|
} |
|
146
|
|
|
|
|
147
|
|
|
/** |
|
148
|
|
|
* Get the next group of numbers. |
|
149
|
|
|
* |
|
150
|
|
|
* Note, along with getting the characters the pointer in the data will be |
|
151
|
|
|
* moved as well. |
|
152
|
|
|
* |
|
153
|
|
|
* @return string The next group of numbers. |
|
154
|
|
|
*/ |
|
155
|
2 |
|
public function getNumeric() |
|
156
|
|
|
{ |
|
157
|
2 |
|
return $this->is->charsWhile('0123456789'); |
|
158
|
|
|
} |
|
159
|
|
|
|
|
160
|
|
|
/** |
|
161
|
|
|
* Consume whitespace. |
|
162
|
|
|
* |
|
163
|
|
|
* Whitespace in HTML5 is: formfeed, tab, newline, space. |
|
164
|
|
|
*/ |
|
165
|
107 |
|
public function whitespace() |
|
166
|
|
|
{ |
|
167
|
107 |
|
return $this->is->charsWhile("\n\t\f "); |
|
168
|
|
|
} |
|
169
|
|
|
|
|
170
|
|
|
/** |
|
171
|
|
|
* Returns the current line that is being consumed. |
|
172
|
|
|
* |
|
173
|
|
|
* @return int The current line number. |
|
174
|
|
|
*/ |
|
175
|
14 |
|
public function currentLine() |
|
176
|
|
|
{ |
|
177
|
14 |
|
return $this->is->currentLine(); |
|
178
|
|
|
} |
|
179
|
|
|
|
|
180
|
|
|
/** |
|
181
|
|
|
* Read chars until something in the mask is encountered. |
|
182
|
|
|
*/ |
|
183
|
102 |
|
public function charsUntil($mask) |
|
184
|
|
|
{ |
|
185
|
102 |
|
return $this->is->charsUntil($mask); |
|
186
|
|
|
} |
|
187
|
|
|
|
|
188
|
|
|
/** |
|
189
|
|
|
* Read chars as long as the mask matches. |
|
190
|
|
|
*/ |
|
191
|
104 |
|
public function charsWhile($mask) |
|
192
|
|
|
{ |
|
193
|
104 |
|
return $this->is->charsWhile($mask); |
|
194
|
|
|
} |
|
195
|
|
|
|
|
196
|
|
|
/** |
|
197
|
|
|
* Returns the current column of the current line that the tokenizer is at. |
|
198
|
|
|
* |
|
199
|
|
|
* Newlines are column 0. The first char after a newline is column 1. |
|
200
|
|
|
* |
|
201
|
|
|
* @return int The column number. |
|
202
|
|
|
*/ |
|
203
|
14 |
|
public function columnOffset() |
|
204
|
|
|
{ |
|
205
|
14 |
|
return $this->is->columnOffset(); |
|
206
|
|
|
} |
|
207
|
|
|
|
|
208
|
|
|
/** |
|
209
|
|
|
* Get all characters until EOF. |
|
210
|
|
|
* |
|
211
|
|
|
* This consumes characters until the EOF. |
|
212
|
|
|
* |
|
213
|
|
|
* @return int The number of characters remaining. |
|
214
|
|
|
*/ |
|
215
|
1 |
|
public function remainingChars() |
|
216
|
|
|
{ |
|
217
|
1 |
|
return $this->is->remainingChars(); |
|
218
|
|
|
} |
|
219
|
|
|
} |
|
220
|
|
|
|