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 |
||
25 | final class DocParser implements DocParserInterface |
||
26 | { |
||
27 | /** |
||
28 | * @var EnvironmentInterface |
||
29 | */ |
||
30 | private $environment; |
||
31 | |||
32 | /** |
||
33 | * @var InlineParserEngine |
||
34 | */ |
||
35 | private $inlineParserEngine; |
||
36 | |||
37 | /** |
||
38 | * @var int|float |
||
39 | */ |
||
40 | private $maxNestingLevel; |
||
41 | |||
42 | /** |
||
43 | * @param EnvironmentInterface $environment |
||
44 | */ |
||
45 | 2442 | public function __construct(EnvironmentInterface $environment) |
|
46 | { |
||
47 | 2442 | $this->environment = $environment; |
|
48 | 2442 | $this->inlineParserEngine = new InlineParserEngine($environment); |
|
49 | 2442 | $this->maxNestingLevel = $environment->getConfig('max_nesting_level', \INF); |
|
50 | 2442 | } |
|
51 | |||
52 | /** |
||
53 | * @param string $input |
||
54 | * |
||
55 | * @return string[] |
||
56 | */ |
||
57 | 2427 | private function preProcessInput(string $input): array |
|
58 | { |
||
59 | /** @var string[] $lines */ |
||
60 | 2427 | $lines = \preg_split('/\r\n|\n|\r/', $input); |
|
61 | |||
62 | // Remove any newline which appears at the very end of the string. |
||
63 | // We've already split the document by newlines, so we can simply drop |
||
64 | // any empty element which appears on the end. |
||
65 | 2427 | if (\end($lines) === '') { |
|
66 | 2187 | \array_pop($lines); |
|
67 | } |
||
68 | |||
69 | 2427 | return $lines; |
|
70 | } |
||
71 | |||
72 | /** |
||
73 | * @param string $input |
||
74 | * |
||
75 | * @throws \RuntimeException |
||
76 | * |
||
77 | * @return Document |
||
78 | */ |
||
79 | 2433 | public function parse(string $input): Document |
|
80 | { |
||
81 | 2433 | $document = new Document(); |
|
82 | 2433 | $context = new Context($document, $this->environment); |
|
83 | |||
84 | 2433 | $this->assertValidUTF8($input); |
|
85 | 2427 | $lines = $this->preProcessInput($input); |
|
86 | 2427 | foreach ($lines as $line) { |
|
87 | 2427 | $context->setNextLine($line); |
|
88 | 2427 | $this->incorporateLine($context); |
|
89 | } |
||
90 | |||
91 | 2427 | $lineCount = \count($lines); |
|
92 | 2427 | while ($tip = $context->getTip()) { |
|
93 | 2427 | $tip->finalize($context, $lineCount); |
|
94 | } |
||
95 | |||
96 | 2427 | $this->processInlines($context); |
|
97 | |||
98 | 2427 | $this->environment->dispatch(new DocumentParsedEvent($document)); |
|
99 | |||
100 | 2427 | return $document; |
|
101 | } |
||
102 | |||
103 | 2427 | private function incorporateLine(ContextInterface $context) |
|
104 | { |
||
105 | 2427 | $context->getBlockCloser()->resetTip(); |
|
106 | 2427 | $context->setBlocksParsed(false); |
|
107 | |||
108 | 2427 | $cursor = new Cursor($context->getLine()); |
|
109 | |||
110 | 2427 | $this->resetContainer($context, $cursor); |
|
111 | 2427 | $context->getBlockCloser()->setLastMatchedContainer($context->getContainer()); |
|
112 | |||
113 | 2427 | $this->parseBlocks($context, $cursor); |
|
114 | |||
115 | // What remains at the offset is a text line. Add the text to the appropriate container. |
||
116 | // First check for a lazy paragraph continuation: |
||
117 | 2427 | if ($this->handleLazyParagraphContinuation($context, $cursor)) { |
|
118 | 36 | return; |
|
119 | } |
||
120 | |||
121 | // not a lazy continuation |
||
122 | // finalize any blocks not matched |
||
123 | 2427 | $context->getBlockCloser()->closeUnmatchedBlocks(); |
|
124 | |||
125 | // Determine whether the last line is blank, updating parents as needed |
||
126 | 2427 | $this->setAndPropagateLastLineBlank($context, $cursor); |
|
127 | |||
128 | // Handle any remaining cursor contents |
||
129 | 2427 | if ($context->getContainer() instanceof StringContainerInterface) { |
|
130 | 864 | $context->getContainer()->handleRemainingContents($context, $cursor); |
|
131 | 2175 | } elseif (!$cursor->isBlank()) { |
|
132 | // Create paragraph container for line |
||
133 | 2094 | $p = new Paragraph(); |
|
134 | 2094 | $context->addBlock($p); |
|
135 | 2094 | $cursor->advanceToNextNonSpaceOrTab(); |
|
136 | 2094 | $p->addLine($cursor->getRemainder()); |
|
137 | } |
||
138 | 2427 | } |
|
139 | |||
140 | 2427 | private function processInlines(ContextInterface $context) |
|
155 | |||
156 | /** |
||
157 | * Sets the container to the last open child (or its parent) |
||
158 | * |
||
159 | * @param ContextInterface $context |
||
160 | * @param Cursor $cursor |
||
161 | */ |
||
162 | 2427 | private function resetContainer(ContextInterface $context, Cursor $cursor) |
|
184 | |||
185 | /** |
||
186 | * Parse blocks |
||
187 | * |
||
188 | * @param ContextInterface $context |
||
189 | * @param Cursor $cursor |
||
190 | */ |
||
191 | 2427 | private function parseBlocks(ContextInterface $context, Cursor $cursor) |
|
208 | |||
209 | /** |
||
210 | * @param ContextInterface $context |
||
211 | * @param Cursor $cursor |
||
212 | * |
||
213 | * @return bool |
||
214 | */ |
||
215 | 2427 | private function handleLazyParagraphContinuation(ContextInterface $context, Cursor $cursor): bool |
|
232 | |||
233 | /** |
||
234 | * @param ContextInterface $context |
||
235 | * @param Cursor $cursor |
||
236 | */ |
||
237 | 2427 | private function setAndPropagateLastLineBlank(ContextInterface $context, Cursor $cursor) |
|
255 | |||
256 | 2433 | private function assertValidUTF8(string $input) |
|
262 | } |
||
263 |