Total Complexity | 47 |
Total Lines | 394 |
Duplicated Lines | 0 % |
Changes | 3 | ||
Bugs | 0 | Features | 0 |
Complex classes like Mailcode_Parser_Statement_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.
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 Mailcode_Parser_Statement_Tokenizer, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
22 | class Mailcode_Parser_Statement_Tokenizer |
||
23 | { |
||
24 | const ERROR_TOKENIZE_METHOD_MISSING = 49801; |
||
25 | const ERROR_INVALID_TOKEN_CREATED = 49802; |
||
26 | |||
27 | /** |
||
28 | * @var string[] |
||
29 | */ |
||
30 | protected $operands = array( |
||
31 | '==', |
||
32 | '<=', |
||
33 | '>=', |
||
34 | '!=', |
||
35 | '=', |
||
36 | '+', |
||
37 | '-', |
||
38 | '/', |
||
39 | '*', |
||
40 | '>', |
||
41 | '<' |
||
42 | ); |
||
43 | |||
44 | /** |
||
45 | * @var string[] |
||
46 | */ |
||
47 | protected $keywords = array( |
||
48 | 'in:', |
||
49 | 'insensitive:', |
||
50 | 'urlencode:' |
||
51 | ); |
||
52 | |||
53 | /** |
||
54 | * @var string |
||
55 | */ |
||
56 | protected $delimiter = '§§'; |
||
57 | |||
58 | /** |
||
59 | * @var string[] |
||
60 | */ |
||
61 | protected $tokenCategories = array( |
||
62 | 'variables', |
||
63 | 'normalize_quotes', |
||
64 | 'escaped_quotes', |
||
65 | 'string_literals', |
||
66 | 'keywords', |
||
67 | 'numbers', |
||
68 | 'operands', |
||
69 | 'extract_tokens' |
||
70 | ); |
||
71 | |||
72 | /** |
||
73 | * @var Mailcode_Parser_Statement |
||
74 | */ |
||
75 | protected $statement; |
||
76 | |||
77 | /** |
||
78 | * @var string |
||
79 | */ |
||
80 | protected $tokenized; |
||
81 | |||
82 | /** |
||
83 | * @var Mailcode_Parser_Statement_Tokenizer_Token[] |
||
84 | */ |
||
85 | protected $tokensTemporary = array(); |
||
86 | |||
87 | /** |
||
88 | * @var Mailcode_Parser_Statement_Tokenizer_Token[] |
||
89 | */ |
||
90 | protected $tokensOrdered = array(); |
||
91 | |||
92 | /** |
||
93 | * @var string[] |
||
94 | */ |
||
95 | protected static $ids = array(); |
||
96 | |||
97 | public function __construct(Mailcode_Parser_Statement $statement) |
||
98 | { |
||
99 | $this->statement = $statement; |
||
100 | |||
101 | $this->tokenize($statement->getStatementString()); |
||
102 | } |
||
103 | |||
104 | /** |
||
105 | * Retrieves all tokens detected in the statement string, in |
||
106 | * the order they were found. |
||
107 | * |
||
108 | * @return Mailcode_Parser_Statement_Tokenizer_Token[] |
||
109 | */ |
||
110 | public function getTokens() |
||
111 | { |
||
112 | return $this->tokensOrdered; |
||
113 | } |
||
114 | |||
115 | public function hasTokens() : bool |
||
116 | { |
||
117 | return !empty($this->tokensOrdered); |
||
118 | } |
||
119 | |||
120 | /** |
||
121 | * Whether there were any unknown tokens in the statement. |
||
122 | * |
||
123 | * @return bool |
||
124 | */ |
||
125 | public function hasUnknown() : bool |
||
126 | { |
||
127 | $unknown = $this->getUnknown(); |
||
128 | |||
129 | return !empty($unknown); |
||
130 | } |
||
131 | |||
132 | /** |
||
133 | * Retrieves all unknown content tokens, if any. |
||
134 | * |
||
135 | * @return \Mailcode\Mailcode_Parser_Statement_Tokenizer_Token_Unknown[] |
||
136 | */ |
||
137 | public function getUnknown() |
||
138 | { |
||
139 | $result = array(); |
||
140 | |||
141 | foreach($this->tokensOrdered as $token) |
||
142 | { |
||
143 | if($token instanceof Mailcode_Parser_Statement_Tokenizer_Token_Unknown) |
||
144 | { |
||
145 | $result[] = $token; |
||
146 | } |
||
147 | } |
||
148 | |||
149 | return $result; |
||
150 | } |
||
151 | |||
152 | public function getFirstUnknown() : ?Mailcode_Parser_Statement_Tokenizer_Token_Unknown |
||
153 | { |
||
154 | $unknown = $this->getUnknown(); |
||
155 | |||
156 | if(!empty($unknown)) |
||
157 | { |
||
158 | return array_shift($unknown); |
||
159 | } |
||
160 | |||
161 | return null; |
||
162 | } |
||
163 | |||
164 | public function getNormalized() : string |
||
165 | { |
||
166 | $parts = array(); |
||
167 | |||
168 | foreach($this->tokensOrdered as $token) |
||
169 | { |
||
170 | $string = $token->getNormalized(); |
||
171 | |||
172 | if($string != '') |
||
173 | { |
||
174 | $parts[] = $string; |
||
175 | } |
||
176 | } |
||
177 | |||
178 | return implode(' ', $parts); |
||
179 | } |
||
180 | |||
181 | protected function tokenize(string $statement) : void |
||
203 | } |
||
204 | } |
||
205 | |||
206 | /** |
||
207 | * Registers a token to add in the statement string. |
||
208 | * |
||
209 | * @param string $type |
||
210 | * @param string $matchedText |
||
211 | * @param mixed $subject |
||
212 | */ |
||
213 | protected function registerToken(string $type, string $matchedText, $subject=null) : void |
||
216 | } |
||
217 | |||
218 | protected function createToken(string $type, string $matchedText, $subject=null) : Mailcode_Parser_Statement_Tokenizer_Token |
||
219 | { |
||
220 | $tokenID = $this->generateID(); |
||
221 | |||
222 | $this->tokenized = str_replace( |
||
223 | $matchedText, |
||
224 | $this->delimiter.$tokenID.$this->delimiter, |
||
225 | $this->tokenized |
||
226 | ); |
||
227 | |||
228 | $class = '\Mailcode\Mailcode_Parser_Statement_Tokenizer_Token_'.$type; |
||
229 | |||
230 | return new $class($tokenID, $matchedText, $subject); |
||
231 | } |
||
232 | |||
233 | public function appendKeyword(string $name) : Mailcode_Parser_Statement_Tokenizer_Token_Keyword |
||
234 | { |
||
235 | $name = rtrim($name, ':').':'; |
||
236 | |||
237 | $token = $this->appendToken('Keyword', $name); |
||
238 | |||
239 | if($token instanceof Mailcode_Parser_Statement_Tokenizer_Token_Keyword) |
||
240 | { |
||
241 | return $token; |
||
242 | } |
||
243 | |||
244 | throw new Mailcode_Exception( |
||
245 | 'Invalid token created', |
||
246 | '', |
||
247 | self::ERROR_INVALID_TOKEN_CREATED |
||
248 | ); |
||
249 | } |
||
250 | |||
251 | public function removeToken(Mailcode_Parser_Statement_Tokenizer_Token $token) : Mailcode_Parser_Statement_Tokenizer |
||
252 | { |
||
253 | $keep = array(); |
||
254 | $tokenID = $token->getID(); |
||
255 | |||
256 | foreach ($this->tokensOrdered as $checkToken) |
||
257 | { |
||
258 | if($checkToken->getID() !== $tokenID) |
||
259 | { |
||
260 | $keep[] = $checkToken; |
||
261 | } |
||
262 | } |
||
263 | |||
264 | $this->tokensOrdered = $keep; |
||
265 | |||
266 | return $this; |
||
267 | } |
||
268 | |||
269 | protected function appendToken(string $type, string $matchedText, $subject=null) : Mailcode_Parser_Statement_Tokenizer_Token |
||
276 | } |
||
277 | |||
278 | protected function getTokenByID(string $tokenID) : ?Mailcode_Parser_Statement_Tokenizer_Token |
||
279 | { |
||
280 | foreach($this->tokensTemporary as $token) |
||
281 | { |
||
282 | if($token->getID() === $tokenID) |
||
283 | { |
||
284 | return $token; |
||
285 | } |
||
286 | } |
||
287 | |||
288 | return null; |
||
289 | } |
||
290 | |||
291 | /** |
||
292 | * Some WYSIWYG editors like using pretty quotes instead |
||
293 | * of the usual double quotes. This simply replaces all |
||
294 | * occurrences with the regular variant. |
||
295 | */ |
||
296 | protected function tokenize_normalize_quotes() : void |
||
299 | } |
||
300 | |||
301 | protected function tokenize_escaped_quotes() : void |
||
304 | } |
||
305 | |||
306 | protected function tokenize_keywords() : void |
||
307 | { |
||
308 | foreach($this->keywords as $keyword) |
||
309 | { |
||
310 | if(strstr($this->tokenized, $keyword)) |
||
311 | { |
||
312 | $this->registerToken('Keyword', $keyword); |
||
313 | } |
||
314 | } |
||
315 | } |
||
316 | |||
317 | protected function tokenize_extract_tokens() : void |
||
318 | { |
||
319 | // split the string by the delimiters: this gives an |
||
320 | // array with tokenIDs, and any content that may be left |
||
321 | // over that could not be tokenized. |
||
322 | $parts = \AppUtils\ConvertHelper::explodeTrim($this->delimiter, $this->tokenized); |
||
323 | |||
324 | foreach($parts as $part) |
||
325 | { |
||
326 | $token = $this->getTokenByID($part); |
||
327 | |||
328 | // if the entry is a token, simply add it. |
||
329 | if($token) |
||
330 | { |
||
331 | $this->tokensOrdered[] = $token; |
||
332 | } |
||
333 | // anything else is added as an unknown token. |
||
334 | else |
||
335 | { |
||
336 | $this->tokensOrdered[] = new Mailcode_Parser_Statement_Tokenizer_Token_Unknown($this->generateID(), $part); |
||
337 | } |
||
338 | } |
||
339 | } |
||
340 | |||
341 | protected function tokenize_variables() : void |
||
342 | { |
||
343 | $vars = Mailcode::create()->findVariables($this->tokenized)->getGroupedByHash(); |
||
344 | |||
345 | foreach($vars as $var) |
||
346 | { |
||
347 | $this->registerToken('Variable', $var->getMatchedText(), $var); |
||
348 | } |
||
349 | } |
||
350 | |||
351 | protected function tokenize_operands() : void |
||
352 | { |
||
353 | foreach($this->operands as $operand) |
||
354 | { |
||
355 | if(strstr($this->tokenized, $operand)) |
||
356 | { |
||
357 | $this->registerToken('Operand', $operand); |
||
358 | } |
||
359 | } |
||
360 | } |
||
361 | |||
362 | protected function tokenize_string_literals() : void |
||
370 | } |
||
371 | } |
||
372 | |||
373 | protected function tokenize_numbers() : void |
||
374 | { |
||
375 | $matches = array(); |
||
376 | preg_match_all('/-*[0-9]+\s*[.,]\s*[0-9]+|-*[0-9]+/sx', $this->tokenized, $matches, PREG_PATTERN_ORDER); |
||
377 | |||
378 | foreach($matches[0] as $match) |
||
379 | { |
||
380 | $this->registerToken('Number', $match); |
||
381 | } |
||
382 | } |
||
383 | |||
384 | /** |
||
385 | * Generates a unique alphabet-based ID without numbers |
||
386 | * to use as token name, to avoid conflicts with the |
||
387 | * numbers detection. |
||
388 | * |
||
389 | * @return string |
||
390 | */ |
||
391 | protected function generateID() : string |
||
416 | } |
||
417 | } |
||
418 |