Complex classes like DocParser often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use DocParser, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
22 | class DocParser |
||
23 | { |
||
24 | /** |
||
25 | * @var Environment |
||
26 | */ |
||
27 | protected $environment; |
||
28 | |||
29 | /** |
||
30 | * @var InlineParserEngine |
||
31 | */ |
||
32 | private $inlineParserEngine; |
||
33 | |||
34 | /** |
||
35 | * @var int|float |
||
36 | */ |
||
37 | private $maxNestingLevel; |
||
38 | |||
39 | /** |
||
40 | * @param Environment $environment |
||
41 | */ |
||
42 | 1950 | public function __construct(Environment $environment) |
|
43 | 2 | { |
|
44 | 1950 | $this->environment = $environment; |
|
45 | 1950 | $this->inlineParserEngine = new InlineParserEngine($environment); |
|
46 | 1950 | $this->maxNestingLevel = $environment->getConfig('max_nesting_level', INF); |
|
47 | 1950 | } |
|
48 | |||
49 | /** |
||
50 | * @return Environment |
||
51 | */ |
||
52 | 1950 | public function getEnvironment() |
|
56 | |||
57 | /** |
||
58 | * @param string $input |
||
59 | * |
||
60 | * @return string[] |
||
61 | */ |
||
62 | 1941 | private function preProcessInput($input) |
|
63 | { |
||
64 | 1941 | $lines = preg_split('/\r\n|\n|\r/', $input); |
|
65 | |||
66 | // Remove any newline which appears at the very end of the string. |
||
67 | // We've already split the document by newlines, so we can simply drop |
||
68 | // any empty element which appears on the end. |
||
69 | 1941 | if (end($lines) === '') { |
|
70 | 1926 | array_pop($lines); |
|
71 | 642 | } |
|
72 | |||
73 | 1941 | return $lines; |
|
74 | } |
||
75 | |||
76 | /** |
||
77 | * @param string $input |
||
78 | * |
||
79 | * @return Document |
||
80 | */ |
||
81 | 1941 | public function parse($input) |
|
82 | { |
||
83 | 1941 | $context = new Context(new Document(), $this->getEnvironment()); |
|
84 | 1941 | $context->setEncoding(mb_detect_encoding($input, 'ASCII,UTF-8', true) ?: 'ISO-8859-1'); |
|
85 | |||
86 | 1941 | $lines = $this->preProcessInput($input); |
|
87 | 1941 | foreach ($lines as $line) { |
|
88 | 1938 | $context->setNextLine($line); |
|
89 | 1938 | $this->incorporateLine($context); |
|
90 | 647 | } |
|
91 | |||
92 | 1941 | $lineCount = count($lines); |
|
93 | 1941 | while ($tip = $context->getTip()) { |
|
94 | 1941 | $tip->finalize($context, $lineCount); |
|
95 | 647 | } |
|
96 | |||
97 | 1941 | $this->processInlines($context); |
|
98 | |||
99 | 1941 | $this->processDocument($context); |
|
100 | |||
101 | 1941 | return $context->getDocument(); |
|
102 | } |
||
103 | |||
104 | 1938 | private function incorporateLine(ContextInterface $context) |
|
105 | { |
||
106 | 1938 | $context->getBlockCloser()->resetTip(); |
|
107 | 1938 | $context->setBlocksParsed(false); |
|
108 | |||
109 | 1938 | $cursor = new Cursor($context->getLine(), $context->getEncoding()); |
|
110 | |||
111 | 1938 | $this->resetContainer($context, $cursor); |
|
112 | 1938 | $context->getBlockCloser()->setLastMatchedContainer($context->getContainer()); |
|
113 | |||
114 | 1938 | $this->parseBlocks($context, $cursor); |
|
115 | |||
116 | // What remains at the offset is a text line. Add the text to the appropriate container. |
||
117 | // First check for a lazy paragraph continuation: |
||
118 | 1938 | if ($this->isLazyParagraphContinuation($context, $cursor)) { |
|
119 | // lazy paragraph continuation |
||
120 | 33 | $context->getTip()->addLine($cursor->getRemainder()); |
|
121 | |||
122 | 33 | return; |
|
123 | } |
||
124 | |||
125 | // not a lazy continuation |
||
126 | // finalize any blocks not matched |
||
127 | 1938 | $context->getBlockCloser()->closeUnmatchedBlocks(); |
|
128 | |||
129 | // Determine whether the last line is blank, updating parents as needed |
||
130 | 1938 | $this->setAndPropagateLastLineBlank($context, $cursor); |
|
131 | |||
132 | // Handle any remaining cursor contents |
||
133 | 1938 | if ($context->getContainer()->acceptsLines()) { |
|
134 | 726 | $context->getContainer()->handleRemainingContents($context, $cursor); |
|
135 | 1774 | } elseif (!$cursor->isBlank()) { |
|
136 | // Create paragraph container for line |
||
137 | 1614 | $context->addBlock(new Paragraph()); |
|
138 | 1614 | $cursor->advanceToNextNonSpaceOrTab(); |
|
139 | 1614 | $context->getTip()->addLine($cursor->getRemainder()); |
|
140 | 538 | } |
|
141 | 1938 | } |
|
142 | |||
143 | 1941 | private function processDocument(ContextInterface $context) |
|
144 | { |
||
145 | 1941 | foreach ($this->getEnvironment()->getDocumentProcessors() as $documentProcessor) { |
|
146 | $documentProcessor->processDocument($context->getDocument()); |
||
147 | 647 | } |
|
148 | 1941 | } |
|
149 | |||
150 | 1941 | private function processInlines(ContextInterface $context) |
|
151 | { |
||
152 | 1941 | $walker = $context->getDocument()->walker(); |
|
153 | |||
154 | 1941 | while ($event = $walker->next()) { |
|
155 | 1941 | if (!$event->isEntering()) { |
|
156 | 1941 | continue; |
|
157 | } |
||
158 | |||
159 | 1941 | $node = $event->getNode(); |
|
160 | 1941 | if ($node instanceof InlineContainerInterface) { |
|
161 | 1662 | $this->inlineParserEngine->parse($node, $context->getDocument()->getReferenceMap()); |
|
162 | 554 | } |
|
163 | 647 | } |
|
164 | 1941 | } |
|
165 | |||
166 | /** |
||
167 | * Sets the container to the last open child (or its parent) |
||
168 | * |
||
169 | * @param ContextInterface $context |
||
170 | * @param Cursor $cursor |
||
171 | */ |
||
172 | 1938 | private function resetContainer(ContextInterface $context, Cursor $cursor) |
|
173 | { |
||
174 | 1938 | $container = $context->getDocument(); |
|
175 | |||
176 | 1938 | while ($lastChild = $container->lastChild()) { |
|
177 | 1080 | if (!($lastChild instanceof AbstractBlock)) { |
|
178 | break; |
||
179 | } |
||
180 | |||
181 | 1080 | if (!$lastChild->isOpen()) { |
|
182 | 450 | break; |
|
183 | } |
||
184 | |||
185 | 1071 | $container = $lastChild; |
|
186 | 1071 | if (!$container->matchesNextLine($cursor)) { |
|
187 | 693 | $container = $container->parent(); // back up to the last matching block |
|
188 | 693 | break; |
|
189 | } |
||
190 | 250 | } |
|
191 | |||
192 | 1938 | $context->setContainer($container); |
|
193 | 1938 | } |
|
194 | |||
195 | /** |
||
196 | * Parse blocks |
||
197 | * |
||
198 | * @param ContextInterface $context |
||
199 | * @param Cursor $cursor |
||
200 | */ |
||
201 | 1938 | private function parseBlocks(ContextInterface $context, Cursor $cursor) |
|
202 | { |
||
203 | 1938 | while (!$context->getContainer()->isCode() && !$context->getBlocksParsed()) { |
|
204 | 1938 | $parsed = false; |
|
205 | 1938 | foreach ($this->environment->getBlockParsers() as $parser) { |
|
206 | 1938 | if ($parser->parse($context, $cursor)) { |
|
207 | 804 | $parsed = true; |
|
208 | 1560 | break; |
|
209 | } |
||
210 | 646 | } |
|
211 | |||
212 | 1938 | if (!$parsed || $context->getContainer()->acceptsLines() || $context->getTip()->getDepth() >= $this->maxNestingLevel) { |
|
213 | 1911 | $context->setBlocksParsed(true); |
|
214 | 1911 | break; |
|
215 | } |
||
216 | 132 | } |
|
217 | 1938 | } |
|
218 | |||
219 | /** |
||
220 | * @param ContextInterface $context |
||
221 | * @param Cursor $cursor |
||
222 | * |
||
223 | * @return bool |
||
224 | */ |
||
225 | 1938 | private function isLazyParagraphContinuation(ContextInterface $context, Cursor $cursor) |
|
232 | |||
233 | /** |
||
234 | * @param ContextInterface $context |
||
235 | * @param Cursor $cursor |
||
236 | */ |
||
237 | 1938 | private function setAndPropagateLastLineBlank(ContextInterface $context, Cursor $cursor) |
|
238 | { |
||
239 | 1938 | $container = $context->getContainer(); |
|
240 | |||
255 | } |
||
256 |