1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* This file is part of the league/commonmark package. |
5
|
|
|
* |
6
|
|
|
* (c) Colin O'Dell <[email protected]> |
7
|
|
|
* |
8
|
|
|
* Original code based on the CommonMark JS reference parser (https://bitly.com/commonmark-js) |
9
|
|
|
* - (c) John MacFarlane |
10
|
|
|
* |
11
|
|
|
* For the full copyright and license information, please view the LICENSE |
12
|
|
|
* file that was distributed with this source code. |
13
|
|
|
*/ |
14
|
|
|
|
15
|
|
|
namespace League\CommonMark\Parser; |
16
|
|
|
|
17
|
|
|
use League\CommonMark\Environment\EnvironmentInterface; |
18
|
|
|
use League\CommonMark\Event\DocumentParsedEvent; |
19
|
|
|
use League\CommonMark\Event\DocumentPreParsedEvent; |
20
|
|
|
use League\CommonMark\Input\MarkdownInput; |
21
|
|
|
use League\CommonMark\Node\Block\Document; |
22
|
|
|
use League\CommonMark\Node\Block\Paragraph; |
23
|
|
|
use League\CommonMark\Parser\Block\BlockContinueParserInterface; |
24
|
|
|
use League\CommonMark\Parser\Block\BlockStart; |
25
|
|
|
use League\CommonMark\Parser\Block\BlockStartParserInterface; |
26
|
|
|
use League\CommonMark\Parser\Block\DocumentBlockParser; |
27
|
|
|
use League\CommonMark\Parser\Block\ParagraphParser; |
28
|
|
|
use League\CommonMark\Reference\ReferenceInterface; |
29
|
|
|
use League\CommonMark\Reference\ReferenceMap; |
30
|
|
|
use League\CommonMark\Util\RegexHelper; |
31
|
|
|
|
32
|
|
|
final class MarkdownParser implements MarkdownParserInterface |
33
|
|
|
{ |
34
|
|
|
/** @var EnvironmentInterface */ |
35
|
|
|
private $environment; |
36
|
|
|
|
37
|
|
|
/** @var int|float */ |
38
|
|
|
private $maxNestingLevel; |
39
|
|
|
|
40
|
|
|
/** @var ReferenceMap */ |
41
|
|
|
private $referenceMap; |
42
|
|
|
|
43
|
|
|
/** @var int */ |
44
|
|
|
private $lineNumber = 0; |
45
|
|
|
|
46
|
|
|
/** @var Cursor */ |
47
|
|
|
private $cursor; |
48
|
|
|
|
49
|
|
|
/** @var array<int, BlockContinueParserInterface> */ |
50
|
|
|
private $allBlockParsers = []; |
51
|
|
|
|
52
|
|
|
/** @var array<int, BlockContinueParserInterface> */ |
53
|
|
|
private $activeBlockParsers = []; |
54
|
|
|
|
55
|
|
|
/** |
56
|
|
|
* @param EnvironmentInterface $environment |
57
|
|
|
*/ |
58
|
2508 |
|
public function __construct(EnvironmentInterface $environment) |
59
|
|
|
{ |
60
|
2508 |
|
$this->environment = $environment; |
61
|
2508 |
|
$this->maxNestingLevel = $environment->getConfig('max_nesting_level', \INF); |
62
|
2508 |
|
} |
63
|
|
|
|
64
|
2499 |
|
private function initialize(): void |
65
|
|
|
{ |
66
|
2499 |
|
$this->referenceMap = new ReferenceMap(); |
67
|
2499 |
|
$this->lineNumber = 0; |
68
|
2499 |
|
$this->allBlockParsers = []; |
69
|
2499 |
|
$this->activeBlockParsers = []; |
70
|
2499 |
|
} |
71
|
|
|
|
72
|
|
|
/** |
73
|
|
|
* @param string $input |
74
|
|
|
* |
75
|
|
|
* @throws \RuntimeException |
76
|
|
|
* |
77
|
|
|
* @return Document |
78
|
|
|
*/ |
79
|
2499 |
|
public function parse(string $input): Document |
80
|
|
|
{ |
81
|
2499 |
|
$this->initialize(); |
82
|
|
|
|
83
|
2499 |
|
$documentParser = new DocumentBlockParser($this->referenceMap); |
84
|
2499 |
|
$this->activateBlockParser($documentParser); |
85
|
|
|
|
86
|
2499 |
|
$preParsedEvent = new DocumentPreParsedEvent($documentParser->getBlock(), new MarkdownInput($input)); |
87
|
2493 |
|
$this->environment->dispatch($preParsedEvent); |
88
|
2493 |
|
$markdown = $preParsedEvent->getMarkdown(); |
89
|
|
|
|
90
|
2493 |
|
foreach ($markdown->getLines() as $line) { |
91
|
2493 |
|
++$this->lineNumber; |
92
|
2493 |
|
$this->incorporateLine($line); |
93
|
|
|
} |
94
|
|
|
|
95
|
2493 |
|
$this->finalizeBlocks($this->getActiveBlockParsers(), $this->lineNumber); |
96
|
2493 |
|
$this->processInlines(); |
97
|
|
|
|
98
|
2493 |
|
$this->environment->dispatch(new DocumentParsedEvent($documentParser->getBlock())); |
99
|
|
|
|
100
|
2490 |
|
return $documentParser->getBlock(); |
101
|
|
|
} |
102
|
|
|
|
103
|
|
|
/** |
104
|
|
|
* Analyze a line of text and update the document appropriately. We parse markdown text by calling this on each |
105
|
|
|
* line of input, then finalizing the document. |
106
|
|
|
* |
107
|
|
|
* @param string $line |
108
|
|
|
*/ |
109
|
2493 |
|
private function incorporateLine(string $line): void |
110
|
|
|
{ |
111
|
2493 |
|
$this->cursor = new Cursor($line); |
112
|
|
|
|
113
|
2493 |
|
$matches = 1; |
114
|
|
|
/** @var BlockContinueParserInterface $blockParser */ |
115
|
2493 |
|
foreach ($this->getActiveBlockParsers(1) as $blockParser) { |
116
|
1299 |
|
$blockContinue = $blockParser->tryContinue(clone $this->cursor, $this->getActiveBlockParser()); |
117
|
1299 |
|
if ($blockContinue === null) { |
118
|
825 |
|
break; |
119
|
|
|
} |
120
|
|
|
|
121
|
900 |
|
if ($blockContinue->isFinalize()) { |
122
|
87 |
|
$this->finalizeAndClose($blockParser, $this->lineNumber); |
123
|
|
|
|
124
|
87 |
|
return; |
125
|
|
|
} |
126
|
|
|
|
127
|
894 |
|
if (($state = $blockContinue->getCursorState()) !== null) { |
128
|
894 |
|
$this->cursor->restoreState($state); |
|
|
|
|
129
|
|
|
} |
130
|
|
|
|
131
|
894 |
|
$matches++; |
132
|
|
|
} |
133
|
|
|
|
134
|
2493 |
|
$unmatchedBlockParsers = $this->getActiveBlockParsers($matches); |
135
|
2493 |
|
$lastMatchedBlockParser = $this->getActiveBlockParsers()[$matches - 1]; |
136
|
2493 |
|
$blockParser = $lastMatchedBlockParser; |
137
|
2493 |
|
$allClosed = empty($unmatchedBlockParsers); |
138
|
|
|
|
139
|
|
|
// Unless last matched container is a code block, try new container starts |
140
|
2493 |
|
$tryBlockStarts = $blockParser->getBlock() instanceof Paragraph || $blockParser->isContainer(); |
141
|
2493 |
|
while ($tryBlockStarts) { |
142
|
|
|
// this is a little performance optimization |
143
|
2493 |
|
if ($this->cursor->isBlank()) { |
144
|
627 |
|
$this->cursor->advanceToEnd(); |
145
|
627 |
|
break; |
146
|
2493 |
|
} elseif (!$this->cursor->isIndented() && RegexHelper::isLetter($this->cursor->getNextNonSpaceCharacter())) { |
147
|
1020 |
|
$this->cursor->advanceToNextNonSpaceOrTab(); |
148
|
1020 |
|
break; |
149
|
|
|
} |
150
|
|
|
|
151
|
2109 |
|
if ($blockParser->getBlock()->getDepth() >= $this->maxNestingLevel) { |
152
|
3 |
|
break; |
153
|
|
|
} |
154
|
|
|
|
155
|
2109 |
|
$blockStart = $this->findBlockStart($blockParser); |
156
|
2109 |
|
if ($blockStart === null) { |
157
|
1296 |
|
$this->cursor->advanceToNextNonSpaceOrTab(); |
158
|
1296 |
|
break; |
159
|
|
|
} |
160
|
|
|
|
161
|
951 |
|
if (($state = $blockStart->getCursorState()) !== null) { |
162
|
951 |
|
$this->cursor->restoreState($state); |
|
|
|
|
163
|
|
|
} |
164
|
|
|
|
165
|
951 |
|
if (!$allClosed) { |
166
|
210 |
|
$this->finalizeBlocks($unmatchedBlockParsers, $this->lineNumber - 1); |
167
|
210 |
|
$allClosed = true; |
168
|
|
|
} |
169
|
|
|
|
170
|
951 |
|
if ($blockStart->isReplaceActiveBlockParser()) { |
171
|
132 |
|
$this->prepareActiveBlockParserForReplacement(); |
172
|
|
|
} |
173
|
|
|
|
174
|
951 |
|
foreach ($blockStart->getBlockParsers() as $newBlockParser) { |
175
|
951 |
|
$blockParser = $this->addChild($newBlockParser); |
176
|
951 |
|
$tryBlockStarts = $newBlockParser->isContainer(); |
177
|
|
|
} |
178
|
|
|
} |
179
|
|
|
|
180
|
|
|
// What remains ath the offset is a text line. Add the text to the appropriate block. |
181
|
|
|
|
182
|
|
|
// First check for a lazy paragraph continuation: |
183
|
2493 |
|
if (!$allClosed && !$this->cursor->isBlank() && $this->getActiveBlockParser()->canHaveLazyContinuationLines()) { |
184
|
48 |
|
$this->getActiveBlockParser()->addLine($this->cursor->getRemainder()); |
185
|
|
|
} else { |
186
|
|
|
// finalize any blocks not matched |
187
|
2493 |
|
if (!$allClosed) { |
188
|
666 |
|
$this->finalizeBlocks($unmatchedBlockParsers, $this->lineNumber); |
189
|
|
|
} |
190
|
|
|
|
191
|
2493 |
|
if (!$blockParser->isContainer()) { |
192
|
978 |
|
$this->getActiveBlockParser()->addLine($this->cursor->getRemainder()); |
193
|
2178 |
|
} elseif (!$this->cursor->isBlank()) { |
194
|
2130 |
|
$this->addChild(new ParagraphParser()); |
195
|
2130 |
|
$this->getActiveBlockParser()->addLine($this->cursor->getRemainder()); |
196
|
|
|
} |
197
|
|
|
} |
198
|
2493 |
|
} |
199
|
|
|
|
200
|
2109 |
|
private function findBlockStart(BlockContinueParserInterface $lastMatchedBlockParser): ?BlockStart |
201
|
|
|
{ |
202
|
2109 |
|
$matchedBlockParser = new MarkdownParserState($this->getActiveBlockParser(), $lastMatchedBlockParser); |
203
|
|
|
|
204
|
|
|
/** @var BlockStartParserInterface $blockStartParser */ |
205
|
2109 |
|
foreach ($this->environment->getBlockStartParsers() as $blockStartParser) { |
206
|
2106 |
|
if (($result = $blockStartParser->tryStart(clone $this->cursor, $matchedBlockParser)) !== null) { |
207
|
951 |
|
return $result; |
208
|
|
|
} |
209
|
|
|
} |
210
|
|
|
|
211
|
1296 |
|
return null; |
212
|
|
|
} |
213
|
|
|
|
214
|
|
|
/** |
215
|
|
|
* @param array<int, BlockContinueParserInterface> $blockParsers |
216
|
|
|
* @param int $endLineNumber |
217
|
|
|
*/ |
218
|
2493 |
|
private function finalizeBlocks(array $blockParsers, int $endLineNumber): void |
219
|
|
|
{ |
220
|
2493 |
|
foreach (\array_reverse($blockParsers) as $blockParser) { |
221
|
2493 |
|
$this->finalizeAndClose($blockParser, $endLineNumber); |
222
|
|
|
} |
223
|
2493 |
|
} |
224
|
|
|
|
225
|
|
|
/** |
226
|
|
|
* Finalize a block. Close it and do any necessary postprocessing, e.g. creating string_content from strings, |
227
|
|
|
* setting the 'tight' or 'loose' status of a list, and parsing the beginnings of paragraphs for reference |
228
|
|
|
* definitions. |
229
|
|
|
*/ |
230
|
2493 |
|
private function finalizeAndClose(BlockContinueParserInterface $blockParser, int $endLineNumber): void |
231
|
|
|
{ |
232
|
2493 |
|
if ($this->getActiveBlockParser() === $blockParser) { |
233
|
2493 |
|
$this->deactivateBlockParser(); |
234
|
|
|
} |
235
|
|
|
|
236
|
2493 |
|
if ($blockParser instanceof ParagraphParser) { |
237
|
2028 |
|
$this->updateReferenceMap($blockParser->getReferences()); |
238
|
|
|
} |
239
|
|
|
|
240
|
2493 |
|
$blockParser->getBlock()->setEndLine($endLineNumber); |
241
|
2493 |
|
$blockParser->closeBlock(); |
242
|
2493 |
|
} |
243
|
|
|
|
244
|
|
|
/** |
245
|
|
|
* Walk through a block & children recursively, parsing string content into inline content where appropriate. |
246
|
|
|
*/ |
247
|
2493 |
|
private function processInlines(): void |
248
|
|
|
{ |
249
|
2493 |
|
$p = new InlineParserEngine($this->environment, $this->referenceMap); |
250
|
|
|
|
251
|
|
|
/** @var BlockContinueParserInterface $blockParser */ |
252
|
2493 |
|
foreach ($this->allBlockParsers as $blockParser) { |
253
|
2493 |
|
$blockParser->parseInlines($p); |
254
|
|
|
} |
255
|
2493 |
|
} |
256
|
|
|
|
257
|
|
|
/** |
258
|
|
|
* Add block of type tag as a child of the tip. If the tip can't accept children, close and finalize it and try |
259
|
|
|
* its parent, and so on til we find a block that can accept children. |
260
|
|
|
*/ |
261
|
2493 |
|
private function addChild(BlockContinueParserInterface $blockParser): BlockContinueParserInterface |
262
|
|
|
{ |
263
|
2493 |
|
$blockParser->getBlock()->setStartLine($this->lineNumber); |
264
|
|
|
|
265
|
2493 |
|
while (!$this->getActiveBlockParser()->canContain($blockParser->getBlock())) { |
266
|
123 |
|
$this->finalizeAndClose($this->getActiveBlockParser(), $this->lineNumber - 1); |
267
|
|
|
} |
268
|
|
|
|
269
|
2493 |
|
$this->getActiveBlockParser()->getBlock()->appendChild($blockParser->getBlock()); |
270
|
2493 |
|
$this->activateBlockParser($blockParser); |
271
|
|
|
|
272
|
2493 |
|
return $blockParser; |
273
|
|
|
} |
274
|
|
|
|
275
|
2499 |
|
private function activateBlockParser(BlockContinueParserInterface $blockParser): void |
276
|
|
|
{ |
277
|
2499 |
|
$this->activeBlockParsers[] = $blockParser; |
278
|
2499 |
|
$this->allBlockParsers[] = $blockParser; |
279
|
2499 |
|
} |
280
|
|
|
|
281
|
2493 |
|
private function deactivateBlockParser(): BlockContinueParserInterface |
282
|
|
|
{ |
283
|
2493 |
|
return \array_pop($this->activeBlockParsers); |
284
|
|
|
} |
285
|
|
|
|
286
|
132 |
|
private function prepareActiveBlockParserForReplacement(): void |
287
|
|
|
{ |
288
|
132 |
|
$old = $this->deactivateBlockParser(); |
289
|
132 |
|
$key = \array_search($old, $this->allBlockParsers, true); |
290
|
132 |
|
unset($this->allBlockParsers[$key]); |
291
|
|
|
|
292
|
132 |
|
if ($old instanceof ParagraphParser) { |
293
|
132 |
|
$this->updateReferenceMap($old->getReferences()); |
294
|
|
|
} |
295
|
|
|
|
296
|
132 |
|
$old->getBlock()->detach(); |
297
|
132 |
|
} |
298
|
|
|
|
299
|
|
|
/** |
300
|
|
|
* @param ReferenceInterface[] $references |
301
|
|
|
*/ |
302
|
2130 |
|
private function updateReferenceMap(iterable $references): void |
303
|
|
|
{ |
304
|
2130 |
|
foreach ($references as $reference) { |
305
|
234 |
|
if (!$this->referenceMap->contains($reference->getLabel())) { |
306
|
234 |
|
$this->referenceMap->add($reference); |
307
|
|
|
} |
308
|
|
|
} |
309
|
2130 |
|
} |
310
|
|
|
|
311
|
|
|
/** |
312
|
|
|
* @param int|null $offset |
313
|
|
|
* |
314
|
|
|
* @return array<int, BlockContinueParserInterface> |
|
|
|
|
315
|
|
|
*/ |
316
|
2493 |
|
private function getActiveBlockParsers(?int $offset = 0): array |
317
|
|
|
{ |
318
|
2493 |
|
if (\is_int($offset)) { |
319
|
2493 |
|
return \array_slice($this->activeBlockParsers, $offset); |
320
|
|
|
} |
321
|
|
|
|
322
|
|
|
return $this->activeBlockParsers; |
323
|
|
|
} |
324
|
|
|
|
325
|
2493 |
|
public function getActiveBlockParser(): BlockContinueParserInterface |
326
|
|
|
{ |
327
|
2493 |
|
$active = \end($this->activeBlockParsers); |
328
|
2493 |
|
if ($active === false) { |
329
|
|
|
throw new \RuntimeException('No active block parsers are available'); |
330
|
|
|
} |
331
|
|
|
|
332
|
2493 |
|
return $active; |
333
|
|
|
} |
334
|
|
|
} |
335
|
|
|
|
PHP Analyzer performs a side-effects analysis of your code. A side-effect is basically anything that might be visible after the scope of the method is left.
Let’s take a look at an example:
If we look at the
getEmail()
method, we can see that it has no side-effect. Whether you call this method or not, no future calls to other methods are affected by this. As such code as the following is useless:On the hand, if we look at the
setEmail()
, this method _has_ side-effects. In the following case, we could not remove the method call: