Complex classes like Tokenizer 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 Tokenizer, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
10 | class Tokenizer |
||
11 | { |
||
12 | protected $source; |
||
13 | protected $pos = 0; |
||
14 | protected $line = 1; |
||
15 | protected $lineStart = 0; |
||
16 | |||
17 | /** @var Token */ |
||
18 | protected $lookAhead; |
||
19 | |||
20 | 37 | public function setSource($source) |
|
25 | |||
26 | 37 | protected function next() |
|
41 | |||
42 | 37 | protected function skipWhitespace() |
|
43 | { |
||
44 | 37 | while ($this->pos < strlen($this->source)) { |
|
45 | 37 | $ch = $this->source[$this->pos]; |
|
46 | 37 | if ($ch === ' ' || $ch === "\t") { |
|
47 | 35 | $this->pos++; |
|
48 | 37 | } elseif ($ch === "\r") { |
|
49 | $this->pos++; |
||
50 | if ($this->source[$this->pos] === "\n") { |
||
51 | $this->pos++; |
||
52 | } |
||
53 | $this->line++; |
||
54 | $this->lineStart = $this->pos; |
||
55 | 37 | } elseif ($ch === "\n") { |
|
56 | 10 | $this->pos++; |
|
57 | 10 | $this->line++; |
|
58 | 10 | $this->lineStart = $this->pos; |
|
59 | } else { |
||
60 | 37 | break; |
|
61 | } |
||
62 | } |
||
63 | 37 | } |
|
64 | |||
65 | /** |
||
66 | * @return Token |
||
67 | */ |
||
68 | 37 | protected function scan() |
|
148 | |||
149 | 3 | protected function checkFragment() |
|
167 | |||
168 | 36 | protected function scanWord() |
|
169 | { |
||
170 | 36 | $start = $this->pos; |
|
171 | 36 | $this->pos++; |
|
172 | |||
173 | 36 | while ($this->pos < strlen($this->source)) { |
|
174 | 36 | $ch = $this->source[$this->pos]; |
|
175 | |||
176 | 36 | if ($ch === '_' || $ch === '$' || 'a' <= $ch && $ch <= ('z') || 'A' <= $ch && $ch <= 'Z' || '0' <= $ch && $ch <= '9') { |
|
177 | 36 | $this->pos++; |
|
178 | } else { |
||
179 | 35 | break; |
|
180 | } |
||
181 | } |
||
182 | |||
183 | 36 | $value = substr($this->source, $start, $this->pos - $start); |
|
184 | |||
185 | 36 | return new Token($this->getKeyword($value), $value); |
|
186 | } |
||
187 | |||
188 | 36 | protected function getKeyword($name) |
|
189 | { |
||
190 | switch ($name) { |
||
191 | 36 | case 'null': |
|
192 | 2 | return Token::TYPE_NULL; |
|
193 | |||
194 | case 'true': |
||
195 | 2 | return Token::TYPE_TRUE; |
|
196 | |||
197 | case 'false': |
||
198 | 1 | return Token::TYPE_FALSE; |
|
199 | |||
200 | case 'query': |
||
201 | 8 | return Token::TYPE_QUERY; |
|
202 | |||
203 | case 'fragment': |
||
204 | 1 | return Token::TYPE_FRAGMENT; |
|
205 | |||
206 | case 'mutation': |
||
207 | 5 | return Token::TYPE_MUTATION; |
|
208 | |||
209 | 35 | case 'on': |
|
210 | 1 | return Token::TYPE_ON; |
|
211 | } |
||
212 | |||
213 | 35 | return Token::TYPE_IDENTIFIER; |
|
214 | } |
||
215 | |||
216 | 8 | protected function scanNumber() |
|
217 | { |
||
218 | 8 | $start = $this->pos; |
|
219 | |||
220 | |||
221 | 8 | $this->skipInteger(); |
|
222 | |||
223 | 8 | if ($this->source[$this->pos] === '.') { |
|
224 | 1 | $this->pos++; |
|
225 | 1 | $this->skipInteger(); |
|
226 | } |
||
227 | |||
228 | 8 | $value = substr($this->source, $start, $this->pos - $start); |
|
229 | |||
230 | 8 | if(strpos($value, '.') === false){ |
|
231 | 8 | $value = (int) $value; |
|
232 | } else { |
||
233 | 1 | $value = (float) $value; |
|
234 | } |
||
235 | |||
236 | 8 | return new Token(Token::TYPE_NUMBER, $value); |
|
237 | } |
||
238 | |||
239 | 8 | protected function skipInteger() |
|
240 | { |
||
241 | 8 | $start = $this->pos; |
|
242 | |||
243 | 8 | while ($this->pos < strlen($this->source)) { |
|
244 | 8 | $ch = $this->source[$this->pos]; |
|
245 | 8 | if ('0' <= $ch && $ch <= '9') { |
|
246 | 8 | $this->pos++; |
|
247 | } else { |
||
248 | 8 | break; |
|
249 | } |
||
250 | } |
||
251 | |||
252 | 8 | if ($this->pos - $start === 0) { |
|
253 | throw $this->createIllegal(); |
||
254 | } |
||
255 | 8 | } |
|
256 | |||
257 | protected function createIllegal() |
||
263 | |||
264 | 3 | protected function createError($message) |
|
268 | |||
269 | 3 | protected function getColumn() |
|
273 | |||
274 | 8 | protected function scanString() |
|
275 | { |
||
276 | 8 | $this->pos++; |
|
277 | |||
278 | 8 | $value = ''; |
|
279 | 8 | while ($this->pos < strlen($this->source)) { |
|
280 | 8 | $ch = $this->source[$this->pos]; |
|
281 | 8 | if ($ch === '"') { |
|
282 | 8 | $this->pos++; |
|
283 | |||
284 | 8 | return new Token(Token::TYPE_STRING, $value); |
|
285 | } |
||
286 | |||
287 | 8 | if ($ch === "\r" || $ch === "\n") { |
|
288 | break; |
||
289 | } |
||
290 | |||
291 | 8 | $value .= $ch; |
|
292 | 8 | $this->pos++; |
|
293 | } |
||
294 | |||
295 | throw $this->createIllegal(); |
||
296 | } |
||
297 | |||
298 | 37 | protected function end() |
|
302 | |||
303 | 37 | protected function peek() |
|
307 | |||
308 | 36 | protected function lex() |
|
315 | |||
316 | 7 | protected function createUnexpected(Token $token) |
|
317 | { |
||
318 | 7 | switch ($token->getType()) { |
|
319 | 7 | case Token::TYPE_END: |
|
320 | 1 | return $this->createError('Unexpected end of input'); |
|
321 | 6 | case Token::TYPE_NUMBER: |
|
331 | } |