1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
declare(strict_types=1); |
4
|
|
|
|
5
|
|
|
namespace Yiisoft\Db\Sqlite; |
6
|
|
|
|
7
|
|
|
use function mb_strtoupper; |
8
|
|
|
use function strtr; |
9
|
|
|
|
10
|
|
|
/** |
11
|
|
|
* Splits SQLite queries into individual SQL tokens. |
12
|
|
|
* |
13
|
|
|
* It's used to obtain `CHECK` constraint information from a `CREATE TABLE` SQL code. |
14
|
|
|
* |
15
|
|
|
* @link https://www.sqlite.org/draft/tokenreq.html |
16
|
|
|
* @link https://sqlite.org/lang.html |
17
|
|
|
*/ |
18
|
|
|
final class SqlTokenizer extends AbstractTokenizer |
19
|
|
|
{ |
20
|
|
|
/** |
21
|
|
|
* Returns whether there's a space at the current offset. |
22
|
|
|
* |
23
|
|
|
* If this method returns `true`, it has to set the `$length` parameter to the length of the matched string. |
24
|
|
|
* |
25
|
|
|
* @param int $length The length of the matched string. |
26
|
|
|
* |
27
|
|
|
* @return bool Whether there's a space at the current offset. |
28
|
|
|
*/ |
29
|
171 |
|
protected function isWhitespace(int &$length): bool |
30
|
|
|
{ |
31
|
171 |
|
$whitespaces = ["\f" => true, "\n" => true, "\r" => true, "\t" => true, ' ' => true]; |
32
|
171 |
|
$length = 1; |
33
|
171 |
|
return isset($whitespaces[$this->substring($length)]); |
34
|
|
|
} |
35
|
|
|
|
36
|
|
|
/** |
37
|
|
|
* Returns whether there's a commentary at the current offset. |
38
|
|
|
* |
39
|
|
|
* If these methods return `true`, it has to set the `$length` parameter to the length of the matched string. |
40
|
|
|
* |
41
|
|
|
* @param int $length The length of the matched string. |
42
|
|
|
* |
43
|
|
|
* @return bool Whether there's a commentary at the current offset. |
44
|
|
|
*/ |
45
|
171 |
|
protected function isComment(int &$length): bool |
46
|
|
|
{ |
47
|
171 |
|
$comments = ['--' => true, '/*' => true]; |
48
|
171 |
|
$length = 2; |
49
|
|
|
|
50
|
171 |
|
if (!isset($comments[$this->substring($length)])) { |
51
|
171 |
|
return false; |
52
|
|
|
} |
53
|
|
|
|
54
|
31 |
|
$char = $this->substring($length) === '--' ? "\n" : '*/'; |
55
|
31 |
|
$length = $this->indexAfter($char) - $this->offset; |
56
|
|
|
|
57
|
31 |
|
return true; |
58
|
|
|
} |
59
|
|
|
|
60
|
|
|
/** |
61
|
|
|
* Returns whether there's an operator at the current offset. |
62
|
|
|
* |
63
|
|
|
* If these methods return `true`, it has to set the `$length` parameter to the length of the matched string. |
64
|
|
|
* |
65
|
|
|
* It may also set `$content` to a string that will be used as a token content. |
66
|
|
|
* |
67
|
|
|
* @param int $length The length of the matched string. |
68
|
|
|
* @param string|null $content Optional content instead of the matched string. |
69
|
|
|
* |
70
|
|
|
* @return bool Whether there's an operator at the current offset. |
71
|
|
|
*/ |
72
|
171 |
|
protected function isOperator(int &$length, string|null &$content): bool |
73
|
|
|
{ |
74
|
171 |
|
$operators = [ |
75
|
171 |
|
'!=', |
76
|
171 |
|
'%', |
77
|
171 |
|
'&', |
78
|
171 |
|
'(', |
79
|
171 |
|
')', |
80
|
171 |
|
'*', |
81
|
171 |
|
'+', |
82
|
171 |
|
',', |
83
|
171 |
|
'-', |
84
|
171 |
|
'.', |
85
|
171 |
|
'/', |
86
|
171 |
|
';', |
87
|
171 |
|
'<', |
88
|
171 |
|
'<<', |
89
|
171 |
|
'<=', |
90
|
171 |
|
'<>', |
91
|
171 |
|
'=', |
92
|
171 |
|
'==', |
93
|
171 |
|
'>', |
94
|
171 |
|
'>=', |
95
|
171 |
|
'>>', |
96
|
171 |
|
'|', |
97
|
171 |
|
'||', |
98
|
171 |
|
'~', |
99
|
171 |
|
]; |
100
|
|
|
|
101
|
171 |
|
return $this->startsWithAnyLongest($operators, true, $length); |
102
|
|
|
} |
103
|
|
|
|
104
|
|
|
/** |
105
|
|
|
* Returns whether there's an identifier at the current offset. |
106
|
|
|
* |
107
|
|
|
* If this method returns `true`, it has to set the `$length` parameter to the length of the matched string. |
108
|
|
|
* |
109
|
|
|
* It may also set `$content` to a string that will be used as a token content. |
110
|
|
|
* |
111
|
|
|
* @param int $length The length of the matched string. |
112
|
|
|
* @param string|null $content Optional content instead of the matched string. |
113
|
|
|
* |
114
|
|
|
* @return bool Whether there's an identifier at the current offset. |
115
|
|
|
*/ |
116
|
171 |
|
protected function isIdentifier(int &$length, string|null &$content): bool |
117
|
|
|
{ |
118
|
171 |
|
$identifierDelimiters = ['"' => '"', '[' => ']', '`' => '`']; |
119
|
|
|
|
120
|
171 |
|
if (!isset($identifierDelimiters[$this->substring(1)])) { |
121
|
171 |
|
return false; |
122
|
|
|
} |
123
|
|
|
|
124
|
131 |
|
$delimiter = $identifierDelimiters[$this->substring(1)]; |
125
|
131 |
|
$offset = $this->offset; |
126
|
|
|
|
127
|
131 |
|
while (true) { |
128
|
131 |
|
$offset = $this->indexAfter($delimiter, $offset + 1); |
129
|
131 |
|
if ($delimiter === ']' || $this->substring(1, true, $offset) !== $delimiter) { |
130
|
131 |
|
break; |
131
|
|
|
} |
132
|
|
|
} |
133
|
|
|
|
134
|
131 |
|
$length = $offset - $this->offset; |
135
|
131 |
|
$content = $this->substring($length - 2, true, $this->offset + 1); |
136
|
|
|
|
137
|
131 |
|
if ($delimiter !== ']') { |
138
|
131 |
|
$content = strtr($content, ["$delimiter$delimiter" => $delimiter]); |
139
|
|
|
} |
140
|
|
|
|
141
|
131 |
|
return true; |
142
|
|
|
} |
143
|
|
|
|
144
|
|
|
/** |
145
|
|
|
* Returns whether there's a string literal at the current offset. |
146
|
|
|
* |
147
|
|
|
* If this method returns `true`, it has to set the `$length` parameter to the length of the matched string. |
148
|
|
|
* |
149
|
|
|
* It may also set `$content` to a string that will be used as a token content. |
150
|
|
|
* |
151
|
|
|
* @param int $length The length of the matched string. |
152
|
|
|
* @param string|null $content Optional content instead of the matched string. |
153
|
|
|
* |
154
|
|
|
* @return bool Whether there's a string literal at the current offset. |
155
|
|
|
*/ |
156
|
171 |
|
protected function isStringLiteral(int &$length, string|null &$content): bool |
157
|
|
|
{ |
158
|
171 |
|
if ($this->substring(1) !== "'") { |
159
|
171 |
|
return false; |
160
|
|
|
} |
161
|
|
|
|
162
|
43 |
|
$offset = $this->offset; |
163
|
|
|
|
164
|
43 |
|
while (true) { |
165
|
43 |
|
$offset = $this->indexAfter("'", $offset + 1); |
166
|
43 |
|
if ($this->substring(1, true, $offset) !== "'") { |
167
|
43 |
|
break; |
168
|
|
|
} |
169
|
|
|
} |
170
|
|
|
|
171
|
43 |
|
$length = $offset - $this->offset; |
172
|
43 |
|
$content = strtr($this->substring($length - 2, true, $this->offset + 1), ["''" => "'"]); |
173
|
|
|
|
174
|
43 |
|
return true; |
175
|
|
|
} |
176
|
|
|
|
177
|
|
|
/** |
178
|
|
|
* Returns whether the given string is a keyword. |
179
|
|
|
* |
180
|
|
|
* The method may set `$content` to a string that will be used as a token content. |
181
|
|
|
* |
182
|
|
|
* @param string $string The string to match. |
183
|
|
|
* @param string|null $content Optional content instead of the matched string. |
184
|
|
|
* |
185
|
|
|
* @return bool Whether the given string is a keyword. |
186
|
|
|
*/ |
187
|
171 |
|
protected function isKeyword(string $string, string|null &$content): bool |
188
|
|
|
{ |
189
|
171 |
|
$keywords = [ |
190
|
171 |
|
'ABORT' => true, |
191
|
171 |
|
'ACTION' => true, |
192
|
171 |
|
'ADD' => true, |
193
|
171 |
|
'AFTER' => true, |
194
|
171 |
|
'ALL' => true, |
195
|
171 |
|
'ALTER' => true, |
196
|
171 |
|
'ANALYZE' => true, |
197
|
171 |
|
'AND' => true, |
198
|
171 |
|
'AS' => true, |
199
|
171 |
|
'ASC' => true, |
200
|
171 |
|
'ATTACH' => true, |
201
|
171 |
|
'AUTOINCREMENT' => true, |
202
|
171 |
|
'BEFORE' => true, |
203
|
171 |
|
'BEGIN' => true, |
204
|
171 |
|
'BETWEEN' => true, |
205
|
171 |
|
'BY' => true, |
206
|
171 |
|
'CASCADE' => true, |
207
|
171 |
|
'CASE' => true, |
208
|
171 |
|
'CAST' => true, |
209
|
171 |
|
'CHECK' => true, |
210
|
171 |
|
'COLLATE' => true, |
211
|
171 |
|
'COLUMN' => true, |
212
|
171 |
|
'COMMIT' => true, |
213
|
171 |
|
'CONFLICT' => true, |
214
|
171 |
|
'CONSTRAINT' => true, |
215
|
171 |
|
'CREATE' => true, |
216
|
171 |
|
'CROSS' => true, |
217
|
171 |
|
'CURRENT_DATE' => true, |
218
|
171 |
|
'CURRENT_TIME' => true, |
219
|
171 |
|
'CURRENT_TIMESTAMP' => true, |
220
|
171 |
|
'DATABASE' => true, |
221
|
171 |
|
'DEFAULT' => true, |
222
|
171 |
|
'DEFERRABLE' => true, |
223
|
171 |
|
'DEFERRED' => true, |
224
|
171 |
|
'DELETE' => true, |
225
|
171 |
|
'DESC' => true, |
226
|
171 |
|
'DETACH' => true, |
227
|
171 |
|
'DISTINCT' => true, |
228
|
171 |
|
'DROP' => true, |
229
|
171 |
|
'EACH' => true, |
230
|
171 |
|
'ELSE' => true, |
231
|
171 |
|
'END' => true, |
232
|
171 |
|
'ESCAPE' => true, |
233
|
171 |
|
'EXCEPT' => true, |
234
|
171 |
|
'EXCLUSIVE' => true, |
235
|
171 |
|
'EXISTS' => true, |
236
|
171 |
|
'EXPLAIN' => true, |
237
|
171 |
|
'FAIL' => true, |
238
|
171 |
|
'FOR' => true, |
239
|
171 |
|
'FOREIGN' => true, |
240
|
171 |
|
'FROM' => true, |
241
|
171 |
|
'FULL' => true, |
242
|
171 |
|
'GLOB' => true, |
243
|
171 |
|
'GROUP' => true, |
244
|
171 |
|
'HAVING' => true, |
245
|
171 |
|
'IF' => true, |
246
|
171 |
|
'IGNORE' => true, |
247
|
171 |
|
'IMMEDIATE' => true, |
248
|
171 |
|
'IN' => true, |
249
|
171 |
|
'INDEX' => true, |
250
|
171 |
|
'INDEXED' => true, |
251
|
171 |
|
'INITIALLY' => true, |
252
|
171 |
|
'INNER' => true, |
253
|
171 |
|
'INSERT' => true, |
254
|
171 |
|
'INSTEAD' => true, |
255
|
171 |
|
'INTERSECT' => true, |
256
|
171 |
|
'INTO' => true, |
257
|
171 |
|
'IS' => true, |
258
|
171 |
|
'ISNULL' => true, |
259
|
171 |
|
'JOIN' => true, |
260
|
171 |
|
'KEY' => true, |
261
|
171 |
|
'LEFT' => true, |
262
|
171 |
|
'LIKE' => true, |
263
|
171 |
|
'LIMIT' => true, |
264
|
171 |
|
'MATCH' => true, |
265
|
171 |
|
'NATURAL' => true, |
266
|
171 |
|
'NO' => true, |
267
|
171 |
|
'NOT' => true, |
268
|
171 |
|
'NOTNULL' => true, |
269
|
171 |
|
'NULL' => true, |
270
|
171 |
|
'OF' => true, |
271
|
171 |
|
'OFFSET' => true, |
272
|
171 |
|
'ON' => true, |
273
|
171 |
|
'OR' => true, |
274
|
171 |
|
'ORDER' => true, |
275
|
171 |
|
'OUTER' => true, |
276
|
171 |
|
'PLAN' => true, |
277
|
171 |
|
'PRAGMA' => true, |
278
|
171 |
|
'PRIMARY' => true, |
279
|
171 |
|
'QUERY' => true, |
280
|
171 |
|
'RAISE' => true, |
281
|
171 |
|
'RECURSIVE' => true, |
282
|
171 |
|
'REFERENCES' => true, |
283
|
171 |
|
'REGEXP' => true, |
284
|
171 |
|
'REINDEX' => true, |
285
|
171 |
|
'RELEASE' => true, |
286
|
171 |
|
'RENAME' => true, |
287
|
171 |
|
'REPLACE' => true, |
288
|
171 |
|
'RESTRICT' => true, |
289
|
171 |
|
'RIGHT' => true, |
290
|
171 |
|
'ROLLBACK' => true, |
291
|
171 |
|
'ROW' => true, |
292
|
171 |
|
'SAVEPOINT' => true, |
293
|
171 |
|
'SELECT' => true, |
294
|
171 |
|
'SET' => true, |
295
|
171 |
|
'TABLE' => true, |
296
|
171 |
|
'TEMP' => true, |
297
|
171 |
|
'TEMPORARY' => true, |
298
|
171 |
|
'THEN' => true, |
299
|
171 |
|
'TO' => true, |
300
|
171 |
|
'TRANSACTION' => true, |
301
|
171 |
|
'TRIGGER' => true, |
302
|
171 |
|
'UNION' => true, |
303
|
171 |
|
'UNIQUE' => true, |
304
|
171 |
|
'UPDATE' => true, |
305
|
171 |
|
'USING' => true, |
306
|
171 |
|
'VACUUM' => true, |
307
|
171 |
|
'VALUES' => true, |
308
|
171 |
|
'VIEW' => true, |
309
|
171 |
|
'VIRTUAL' => true, |
310
|
171 |
|
'WHEN' => true, |
311
|
171 |
|
'WHERE' => true, |
312
|
171 |
|
'WITH' => true, |
313
|
171 |
|
'WITHOUT' => true, |
314
|
171 |
|
]; |
315
|
|
|
|
316
|
171 |
|
$string = mb_strtoupper($string, 'UTF-8'); |
317
|
|
|
|
318
|
171 |
|
if (!isset($keywords[$string])) { |
319
|
170 |
|
return false; |
320
|
|
|
} |
321
|
|
|
|
322
|
171 |
|
$content = $string; |
323
|
|
|
|
324
|
171 |
|
return true; |
325
|
|
|
} |
326
|
|
|
} |
327
|
|
|
|