-
Notifications
You must be signed in to change notification settings - Fork 3
/
SqlFormatter.class.php
1085 lines (944 loc) · 43.7 KB
/
SqlFormatter.class.php
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<?php
/**
* SQL Formatter is a collection of utilities for debugging SQL queries.
* It includes methods for formatting, syntax highlighting, removing comments, etc.
*
* @package SqlFormatter
* @author Jeremy Dorn <[email protected]>
* @author Florin Patan <[email protected]>
* @copyright 2013 Jeremy Dorn
* @license http://opensource.org/licenses/MIT
* @link http://github.com/jdorn/sql-formatter
* @version 1.2.14
*/
class SqlFormatter
{
// Constants for token types
const TOKEN_TYPE_WHITESPACE = 0;
const TOKEN_TYPE_WORD = 1;
const TOKEN_TYPE_QUOTE = 2;
const TOKEN_TYPE_BACKTICK_QUOTE = 3;
const TOKEN_TYPE_RESERVED = 4;
const TOKEN_TYPE_RESERVED_TOPLEVEL = 5;
const TOKEN_TYPE_RESERVED_NEWLINE = 6;
const TOKEN_TYPE_BOUNDARY = 7;
const TOKEN_TYPE_COMMENT = 8;
const TOKEN_TYPE_BLOCK_COMMENT = 9;
const TOKEN_TYPE_NUMBER = 10;
const TOKEN_TYPE_ERROR = 11;
const TOKEN_TYPE_VARIABLE = 12;
// Constants for different components of a token
const TOKEN_TYPE = 0;
const TOKEN_VALUE = 1;
// Reserved words (for syntax highlighting)
protected static $reserved = array(
'ACCESSIBLE', 'ACTION', 'AGAINST', 'AGGREGATE', 'ALGORITHM', 'ALL', 'ALTER', 'ANALYSE', 'ANALYZE', 'AS', 'ASC',
'AUTOCOMMIT', 'AUTO_INCREMENT', 'BACKUP', 'BEGIN', 'BETWEEN', 'BINLOG', 'BOTH', 'CASCADE', 'CASE', 'CHANGE', 'CHANGED', 'CHARACTER SET',
'CHARSET', 'CHECK', 'CHECKSUM', 'COLLATE', 'COLLATION', 'COLUMN', 'COLUMNS', 'COMMENT', 'COMMIT', 'COMMITTED', 'COMPRESSED', 'CONCURRENT',
'CONSTRAINT', 'CONTAINS', 'CONVERT', 'CREATE', 'CROSS', 'CURRENT_TIMESTAMP', 'DATABASE', 'DATABASES', 'DAY', 'DAY_HOUR', 'DAY_MINUTE',
'DAY_SECOND', 'DEFAULT', 'DEFINER', 'DELAYED', 'DELETE', 'DESC', 'DESCRIBE', 'DETERMINISTIC', 'DISTINCT', 'DISTINCTROW', 'DIV',
'DO', 'DUMPFILE', 'DUPLICATE', 'DYNAMIC', 'ELSE', 'ENCLOSED', 'END', 'ENGINE', 'ENGINE_TYPE', 'ENGINES', 'ESCAPE', 'ESCAPED', 'EVENTS', 'EXECUTE',
'EXISTS', 'EXPLAIN', 'EXTENDED', 'FAST', 'FIELDS', 'FILE', 'FIRST', 'FIXED', 'FLUSH', 'FOR', 'FORCE', 'FOREIGN', 'FULL', 'FULLTEXT',
'FUNCTION', 'GLOBAL', 'GRANT', 'GRANTS', 'GROUP_CONCAT', 'HEAP', 'HIGH_PRIORITY', 'HOSTS', 'HOUR', 'HOUR_MINUTE',
'HOUR_SECOND', 'IDENTIFIED', 'IF', 'IFNULL', 'IGNORE', 'IN', 'INDEX', 'INDEXES', 'INFILE', 'INSERT', 'INSERT_ID', 'INSERT_METHOD', 'INTERVAL',
'INTO', 'INVOKER', 'IS', 'ISOLATION', 'KEY', 'KEYS', 'KILL', 'LAST_INSERT_ID', 'LEADING', 'LEVEL', 'LIKE', 'LINEAR',
'LINES', 'LOAD', 'LOCAL', 'LOCK', 'LOCKS', 'LOGS', 'LOW_PRIORITY', 'MARIA', 'MASTER', 'MASTER_CONNECT_RETRY', 'MASTER_HOST', 'MASTER_LOG_FILE',
'MATCH','MAX_CONNECTIONS_PER_HOUR', 'MAX_QUERIES_PER_HOUR', 'MAX_ROWS', 'MAX_UPDATES_PER_HOUR', 'MAX_USER_CONNECTIONS',
'MEDIUM', 'MERGE', 'MINUTE', 'MINUTE_SECOND', 'MIN_ROWS', 'MODE', 'MODIFY',
'MONTH', 'MRG_MYISAM', 'MYISAM', 'NAMES', 'NATURAL', 'NOT', 'NOW()','NULL', 'OFFSET', 'ON', 'OPEN', 'OPTIMIZE', 'OPTION', 'OPTIONALLY',
'ON UPDATE', 'ON DELETE', 'OUTFILE', 'PACK_KEYS', 'PAGE', 'PARTIAL', 'PARTITION', 'PARTITIONS', 'PASSWORD', 'PRIMARY', 'PRIVILEGES', 'PROCEDURE',
'PROCESS', 'PROCESSLIST', 'PURGE', 'QUICK', 'RANGE', 'RAID0', 'RAID_CHUNKS', 'RAID_CHUNKSIZE','RAID_TYPE', 'READ', 'READ_ONLY',
'READ_WRITE', 'REFERENCES', 'REGEXP', 'RELOAD', 'RENAME', 'REPAIR', 'REPEATABLE', 'REPLACE', 'REPLICATION', 'RESET', 'RESTORE', 'RESTRICT',
'RETURN', 'RETURNS', 'REVOKE', 'RLIKE', 'ROLLBACK', 'ROW', 'ROWS', 'ROW_FORMAT', 'SECOND', 'SECURITY', 'SEPARATOR',
'SERIALIZABLE', 'SESSION', 'SHARE', 'SHOW', 'SHUTDOWN', 'SLAVE', 'SONAME', 'SOUNDS', 'SQL', 'SQL_AUTO_IS_NULL', 'SQL_BIG_RESULT',
'SQL_BIG_SELECTS', 'SQL_BIG_TABLES', 'SQL_BUFFER_RESULT', 'SQL_CALC_FOUND_ROWS', 'SQL_LOG_BIN', 'SQL_LOG_OFF', 'SQL_LOG_UPDATE',
'SQL_LOW_PRIORITY_UPDATES', 'SQL_MAX_JOIN_SIZE', 'SQL_QUOTE_SHOW_CREATE', 'SQL_SAFE_UPDATES', 'SQL_SELECT_LIMIT', 'SQL_SLAVE_SKIP_COUNTER',
'SQL_SMALL_RESULT', 'SQL_WARNINGS', 'SQL_CACHE', 'SQL_NO_CACHE', 'START', 'STARTING', 'STATUS', 'STOP', 'STORAGE',
'STRAIGHT_JOIN', 'STRING', 'STRIPED', 'SUPER', 'TABLE', 'TABLES', 'TEMPORARY', 'TERMINATED', 'THEN', 'TO', 'TRAILING', 'TRANSACTIONAL', 'TRUE',
'TRUNCATE', 'TYPE', 'TYPES', 'UNCOMMITTED', 'UNIQUE', 'UNLOCK', 'UNSIGNED', 'USAGE', 'USE', 'USING', 'VARIABLES',
'VIEW', 'WHEN', 'WITH', 'WORK', 'WRITE', 'YEAR_MONTH'
);
// For SQL formatting
// These keywords will all be on their own line
protected static $reserved_toplevel = array(
'SELECT', 'FROM', 'WHERE', 'SET', 'ORDER BY', 'GROUP BY', 'LIMIT', 'DROP',
'VALUES', 'UPDATE', 'HAVING', 'ADD', 'AFTER', 'ALTER TABLE', 'DELETE FROM', 'UNION ALL', 'UNION', 'EXCEPT', 'INTERSECT'
);
protected static $reserved_newline = array(
'LEFT OUTER JOIN', 'RIGHT OUTER JOIN', 'LEFT JOIN', 'RIGHT JOIN', 'OUTER JOIN', 'INNER JOIN', 'JOIN', 'XOR', 'OR', 'AND'
);
protected static $functions = array (
'ABS', 'ACOS', 'ADDDATE', 'ADDTIME', 'AES_DECRYPT', 'AES_ENCRYPT', 'AREA', 'ASBINARY', 'ASCII', 'ASIN', 'ASTEXT', 'ATAN', 'ATAN2',
'AVG', 'BDMPOLYFROMTEXT', 'BDMPOLYFROMWKB', 'BDPOLYFROMTEXT', 'BDPOLYFROMWKB', 'BENCHMARK', 'BIN', 'BIT_AND', 'BIT_COUNT', 'BIT_LENGTH',
'BIT_OR', 'BIT_XOR', 'BOUNDARY', 'BUFFER', 'CAST', 'CEIL', 'CEILING', 'CENTROID', 'CHAR', 'CHARACTER_LENGTH', 'CHARSET', 'CHAR_LENGTH',
'COALESCE', 'COERCIBILITY', 'COLLATION', 'COMPRESS', 'CONCAT', 'CONCAT_WS', 'CONNECTION_ID', 'CONTAINS', 'CONV', 'CONVERT', 'CONVERT_TZ',
'CONVEXHULL', 'COS', 'COT', 'COUNT', 'CRC32', 'CROSSES', 'CURDATE', 'CURRENT_DATE', 'CURRENT_TIME', 'CURRENT_TIMESTAMP', 'CURRENT_USER',
'CURTIME', 'DATABASE', 'DATE', 'DATEDIFF', 'DATE_ADD', 'DATE_DIFF', 'DATE_FORMAT', 'DATE_SUB', 'DAY', 'DAYNAME', 'DAYOFMONTH', 'DAYOFWEEK',
'DAYOFYEAR', 'DECODE', 'DEFAULT', 'DEGREES', 'DES_DECRYPT', 'DES_ENCRYPT', 'DIFFERENCE', 'DIMENSION', 'DISJOINT', 'DISTANCE', 'ELT', 'ENCODE',
'ENCRYPT', 'ENDPOINT', 'ENVELOPE', 'EQUALS', 'EXP', 'EXPORT_SET', 'EXTERIORRING', 'EXTRACT', 'EXTRACTVALUE', 'FIELD', 'FIND_IN_SET', 'FLOOR',
'FORMAT', 'FOUND_ROWS', 'FROM_DAYS', 'FROM_UNIXTIME', 'GEOMCOLLFROMTEXT', 'GEOMCOLLFROMWKB', 'GEOMETRYCOLLECTION', 'GEOMETRYCOLLECTIONFROMTEXT',
'GEOMETRYCOLLECTIONFROMWKB', 'GEOMETRYFROMTEXT', 'GEOMETRYFROMWKB', 'GEOMETRYN', 'GEOMETRYTYPE', 'GEOMFROMTEXT', 'GEOMFROMWKB', 'GET_FORMAT',
'GET_LOCK', 'GLENGTH', 'GREATEST', 'GROUP_CONCAT', 'GROUP_UNIQUE_USERS', 'HEX', 'HOUR', 'IF', 'IFNULL', 'INET_ATON', 'INET_NTOA', 'INSERT', 'INSTR',
'INTERIORRINGN', 'INTERSECTION', 'INTERSECTS', 'INTERVAL', 'ISCLOSED', 'ISEMPTY', 'ISNULL', 'ISRING', 'ISSIMPLE', 'IS_FREE_LOCK', 'IS_USED_LOCK',
'LAST_DAY', 'LAST_INSERT_ID', 'LCASE', 'LEAST', 'LEFT', 'LENGTH', 'LINEFROMTEXT', 'LINEFROMWKB', 'LINESTRING', 'LINESTRINGFROMTEXT', 'LINESTRINGFROMWKB',
'LN', 'LOAD_FILE', 'LOCALTIME', 'LOCALTIMESTAMP', 'LOCATE', 'LOG', 'LOG10', 'LOG2', 'LOWER', 'LPAD', 'LTRIM', 'MAKEDATE', 'MAKETIME', 'MAKE_SET',
'MASTER_POS_WAIT', 'MAX', 'MBRCONTAINS', 'MBRDISJOINT', 'MBREQUAL', 'MBRINTERSECTS', 'MBROVERLAPS', 'MBRTOUCHES', 'MBRWITHIN', 'MD5', 'MICROSECOND',
'MID', 'MIN', 'MINUTE', 'MLINEFROMTEXT', 'MLINEFROMWKB', 'MOD', 'MONTH', 'MONTHNAME', 'MPOINTFROMTEXT', 'MPOINTFROMWKB', 'MPOLYFROMTEXT', 'MPOLYFROMWKB',
'MULTILINESTRING', 'MULTILINESTRINGFROMTEXT', 'MULTILINESTRINGFROMWKB', 'MULTIPOINT', 'MULTIPOINTFROMTEXT', 'MULTIPOINTFROMWKB', 'MULTIPOLYGON',
'MULTIPOLYGONFROMTEXT', 'MULTIPOLYGONFROMWKB', 'NAME_CONST', 'NULLIF', 'NUMGEOMETRIES', 'NUMINTERIORRINGS', 'NUMPOINTS', 'OCT', 'OCTET_LENGTH',
'OLD_PASSWORD', 'ORD', 'OVERLAPS', 'PASSWORD', 'PERIOD_ADD', 'PERIOD_DIFF', 'PI', 'POINT', 'POINTFROMTEXT', 'POINTFROMWKB', 'POINTN', 'POINTONSURFACE',
'POLYFROMTEXT', 'POLYFROMWKB', 'POLYGON', 'POLYGONFROMTEXT', 'POLYGONFROMWKB', 'POSITION', 'POW', 'POWER', 'QUARTER', 'QUOTE', 'RADIANS', 'RAND',
'RELATED', 'RELEASE_LOCK', 'REPEAT', 'REPLACE', 'REVERSE', 'RIGHT', 'ROUND', 'ROW_COUNT', 'RPAD', 'RTRIM', 'SCHEMA', 'SECOND', 'SEC_TO_TIME',
'SESSION_USER', 'SHA', 'SHA1', 'SIGN', 'SIN', 'SLEEP', 'SOUNDEX', 'SPACE', 'SQRT', 'SRID', 'STARTPOINT', 'STD', 'STDDEV', 'STDDEV_POP', 'STDDEV_SAMP',
'STRCMP', 'STR_TO_DATE', 'SUBDATE', 'SUBSTR', 'SUBSTRING', 'SUBSTRING_INDEX', 'SUBTIME', 'SUM', 'SYMDIFFERENCE', 'SYSDATE', 'SYSTEM_USER', 'TAN',
'TIME', 'TIMEDIFF', 'TIMESTAMP', 'TIMESTAMPADD', 'TIMESTAMPDIFF', 'TIME_FORMAT', 'TIME_TO_SEC', 'TOUCHES', 'TO_DAYS', 'TRIM', 'TRUNCATE', 'UCASE',
'UNCOMPRESS', 'UNCOMPRESSED_LENGTH', 'UNHEX', 'UNIQUE_USERS', 'UNIX_TIMESTAMP', 'UPDATEXML', 'UPPER', 'USER', 'UTC_DATE', 'UTC_TIME', 'UTC_TIMESTAMP',
'UUID', 'VARIANCE', 'VAR_POP', 'VAR_SAMP', 'VERSION', 'WEEK', 'WEEKDAY', 'WEEKOFYEAR', 'WITHIN', 'X', 'Y', 'YEAR', 'YEARWEEK'
);
// Punctuation that can be used as a boundary between other tokens
protected static $boundaries = array(',', ';',':', ')', '(', '.', '=', '<', '>', '+', '-', '*', '/', '!', '^', '%', '|', '&', '#');
// For HTML syntax highlighting
// Styles applied to different token types
public static $quote_attributes = 'style="color: blue;"';
public static $backtick_quote_attributes = 'style="color: purple;"';
public static $reserved_attributes = 'style="font-weight:bold;"';
public static $boundary_attributes = '';
public static $number_attributes = 'style="color: green;"';
public static $word_attributes = 'style="color: #333;"';
public static $error_attributes = 'style="background-color: red;"';
public static $comment_attributes = 'style="color: #aaa;"';
public static $variable_attributes = 'style="color: orange;"';
public static $pre_attributes = 'style="color: black; background-color: white;"';
// Boolean - whether or not the current environment is the CLI
// This affects the type of syntax highlighting
// If not defined, it will be determined automatically
public static $cli;
// For CLI syntax highlighting
public static $cli_quote = "\x1b[34;1m";
public static $cli_backtick_quote = "\x1b[35;1m";
public static $cli_reserved = "\x1b[37m";
public static $cli_boundary = "";
public static $cli_number = "\x1b[32;1m";
public static $cli_word = "";
public static $cli_error = "\x1b[31;1;7m";
public static $cli_comment = "\x1b[30;1m";
public static $cli_functions = "\x1b[37m";
public static $cli_variable = "\x1b[36;1m";
// The tab character to use when formatting SQL
public static $tab = ' ';
// This flag tells us if queries need to be enclosed in <pre> tags
public static $use_pre = true;
// This flag tells us if SqlFormatted has been initialized
protected static $init;
// Regular expressions for tokenizing
protected static $regex_boundaries;
protected static $regex_reserved;
protected static $regex_reserved_newline;
protected static $regex_reserved_toplevel;
protected static $regex_function;
// Cache variables
// Only tokens shorter than this size will be cached. Somewhere between 10 and 20 seems to work well for most cases.
public static $max_cachekey_size = 15;
protected static $token_cache = array();
protected static $cache_hits = 0;
protected static $cache_misses = 0;
/**
* Get stats about the token cache
* @return Array An array containing the keys 'hits', 'misses', 'entries', and 'size' in bytes
*/
public static function getCacheStats()
{
return array(
'hits'=>self::$cache_hits,
'misses'=>self::$cache_misses,
'entries'=>count(self::$token_cache),
'size'=>strlen(serialize(self::$token_cache))
);
}
/**
* Stuff that only needs to be done once. Builds regular expressions and sorts the reserved words.
*/
protected static function init()
{
if (self::$init) return;
// Sort reserved word list from longest word to shortest
usort(self::$reserved, array('SqlFormatter', 'sortLength'));
// Set up regular expressions
self::$regex_boundaries = '('.implode('|',array_map(array('SqlFormatter', 'quote_regex'),self::$boundaries)).')';
self::$regex_reserved = '('.implode('|',array_map(array('SqlFormatter', 'quote_regex'),self::$reserved)).')';
self::$regex_reserved_toplevel = str_replace(' ','\\s+','('.implode('|',array_map(array('SqlFormatter', 'quote_regex'),self::$reserved_toplevel)).')');
self::$regex_reserved_newline = str_replace(' ','\\s+','('.implode('|',array_map(array('SqlFormatter', 'quote_regex'),self::$reserved_newline)).')');
self::$regex_function = '('.implode('|',array_map(array('SqlFormatter', 'quote_regex'),self::$functions)).')';
self::$init = true;
}
/**
* Return the next token and token type in a SQL string.
* Quoted strings, comments, reserved words, whitespace, and punctuation are all their own tokens.
*
* @param String $string The SQL string
* @param array $previous The result of the previous getNextToken() call
*
* @return Array An associative array containing the type and value of the token.
*/
protected static function getNextToken($string, $previous = null)
{
// Whitespace
if (preg_match('/^\s+/',$string,$matches)) {
return array(
self::TOKEN_VALUE => $matches[0],
self::TOKEN_TYPE=>self::TOKEN_TYPE_WHITESPACE
);
}
// Comment
if ($string[0] === '#' || (isset($string[1])&&($string[0]==='-'&&$string[1]==='-') || ($string[0]==='/'&&$string[1]==='*'))) {
// Comment until end of line
if ($string[0] === '-' || $string[0] === '#') {
$last = strpos($string, "\n");
$type = self::TOKEN_TYPE_COMMENT;
} else { // Comment until closing comment tag
$last = strpos($string, "*/", 2) + 2;
$type = self::TOKEN_TYPE_BLOCK_COMMENT;
}
if ($last === false) {
$last = strlen($string);
}
return array(
self::TOKEN_VALUE => substr($string, 0, $last),
self::TOKEN_TYPE => $type
);
}
// Quoted String
if ($string[0]==='"' || $string[0]==='\'' || $string[0]==='`') {
$return = array(
self::TOKEN_TYPE => ($string[0]==='`'? self::TOKEN_TYPE_BACKTICK_QUOTE : self::TOKEN_TYPE_QUOTE),
self::TOKEN_VALUE => self::getQuotedString($string)
);
// If a quote was opened, but doesn't have a closing quote, return the remaining string
if ($return[self::TOKEN_VALUE] === null) {
$return[self::TOKEN_VALUE] = $string;
}
return $return;
}
// User-defined Variable
if ($string[0] === '@' && isset($string[1])) {
// If the variable name is quoted
if ($string[1]==='"' || $string[1]==='\'' || $string[1]==='`') {
return array(
self::TOKEN_VALUE => '@'.self::getQuotedString(substr($string,1)),
self::TOKEN_TYPE => self::TOKEN_TYPE_VARIABLE
);
}
// Non-quoted variable name
else {
preg_match('/^(@[a-zA-Z0-9\._\$]+)/',$string,$matches);
if ($matches) {
return array(
self::TOKEN_VALUE => $matches[1],
self::TOKEN_TYPE => self::TOKEN_TYPE_VARIABLE
);
}
}
}
// Number (decimal, binary, or hex)
if (preg_match('/^([0-9]+(\.[0-9]+)?|0x[0-9a-fA-F]+|0b[01]+)($|\s|"\'`|'.self::$regex_boundaries.')/',$string,$matches)) {
return array(
self::TOKEN_VALUE => $matches[1],
self::TOKEN_TYPE=>self::TOKEN_TYPE_NUMBER
);
}
// Boundary Character (punctuation and symbols)
if (preg_match('/^('.self::$regex_boundaries.')/',$string,$matches)) {
return array(
self::TOKEN_VALUE => $matches[1],
self::TOKEN_TYPE => self::TOKEN_TYPE_BOUNDARY
);
}
// A reserved word cannot be preceded by a '.'
// this makes it so in "mytable.from", "from" is not considered a reserved word
if (!$previous || !isset($previous[self::TOKEN_VALUE]) || $previous[self::TOKEN_VALUE] !== '.') {
$upper = strtoupper($string);
// Top Level Reserved Word
if (preg_match('/^('.self::$regex_reserved_toplevel.')($|\s|'.self::$regex_boundaries.')/', $upper,$matches)) {
return array(
self::TOKEN_TYPE=>self::TOKEN_TYPE_RESERVED_TOPLEVEL,
self::TOKEN_VALUE=>substr($string,0,strlen($matches[1]))
);
}
// Newline Reserved Word
if (preg_match('/^('.self::$regex_reserved_newline.')($|\s|'.self::$regex_boundaries.')/', $upper,$matches)) {
return array(
self::TOKEN_TYPE=>self::TOKEN_TYPE_RESERVED_NEWLINE,
self::TOKEN_VALUE=>substr($string,0,strlen($matches[1]))
);
}
// Other Reserved Word
if (preg_match('/^('.self::$regex_reserved.')($|\s|'.self::$regex_boundaries.')/', $upper,$matches)) {
return array(
self::TOKEN_TYPE=>self::TOKEN_TYPE_RESERVED,
self::TOKEN_VALUE=>substr($string,0,strlen($matches[1]))
);
}
}
// A function must be suceeded by '('
// this makes it so "count(" is considered a function, but "count" alone is not
$upper = strtoupper($string);
// function
if (preg_match('/^('.self::$regex_function.'[(]|\s|[)])/', $upper,$matches)) {
return array(
self::TOKEN_TYPE=>self::TOKEN_TYPE_RESERVED,
self::TOKEN_VALUE=>substr($string,0,strlen($matches[1])-1)
);
}
// Non reserved word
preg_match('/^(.*?)($|\s|["\'`]|'.self::$regex_boundaries.')/',$string,$matches);
return array(
self::TOKEN_VALUE => $matches[1],
self::TOKEN_TYPE => self::TOKEN_TYPE_WORD
);
}
protected static function getQuotedString($string)
{
// This checks for the following patterns:
// 1. backtick quoted string using `` to escape
// 2. double quoted string using "" or \" to escape
// 3. single quoted string using '' or \' to escape
if ( preg_match('/^(((`[^`]*($|`))+)|(("[^"\\\\]*(?:\\\\.[^"\\\\]*)*("|$))+)|((\'[^\'\\\\]*(?:\\\\.[^\'\\\\]*)*(\'|$))+))/s', $string, $matches)) {
return $matches[1];
}
return null;
}
/**
* Takes a SQL string and breaks it into tokens.
* Each token is an associative array with type and value.
*
* @param String $string The SQL string
*
* @return Array An array of tokens.
*/
protected static function tokenize($string)
{
self::init();
$tokens = array();
// Used for debugging if there is an error while tokenizing the string
$original_length = strlen($string);
// Used to make sure the string keeps shrinking on each iteration
$old_string_len = strlen($string) + 1;
$token = null;
$current_length = strlen($string);
// Keep processing the string until it is empty
while ($current_length) {
// If the string stopped shrinking, there was a problem
if ($old_string_len <= $current_length) {
$tokens[] = array(
self::TOKEN_VALUE=>$string,
self::TOKEN_TYPE=>self::TOKEN_TYPE_ERROR
);
return $tokens;
}
$old_string_len = $current_length;
// Determine if we can use caching
if ($current_length >= self::$max_cachekey_size) {
$cacheKey = substr($string,0,self::$max_cachekey_size);
} else {
$cacheKey = false;
}
// See if the token is already cached
if ($cacheKey && isset(self::$token_cache[$cacheKey])) {
// Retrieve from cache
$token = self::$token_cache[$cacheKey];
$token_length = strlen($token[self::TOKEN_VALUE]);
self::$cache_hits++;
} else {
// Get the next token and the token type
$token = self::getNextToken($string, $token);
$token_length = strlen($token[self::TOKEN_VALUE]);
self::$cache_misses++;
// If the token is shorter than the max length, store it in cache
if ($cacheKey && $token_length < self::$max_cachekey_size) {
self::$token_cache[$cacheKey] = $token;
}
}
$tokens[] = $token;
// Advance the string
$string = substr($string, $token_length);
$current_length -= $token_length;
}
return $tokens;
}
/**
* Format the whitespace in a SQL string to make it easier to read.
*
* @param String $string The SQL string
* @param boolean $highlight If true, syntax highlighting will also be performed
*
* @return String The SQL string with HTML styles and formatting wrapped in a <pre> tag
*/
public static function format($string, $highlight=true)
{
// This variable will be populated with formatted html
$return = '';
// Use an actual tab while formatting and then switch out with self::$tab at the end
$tab = "\t";
$indent_level = 0;
$newline = false;
$inline_parentheses = false;
$increase_special_indent = false;
$increase_block_indent = false;
$indent_types = array();
$added_newline = false;
$inline_count = 0;
$inline_indented = false;
$clause_limit = false;
// Tokenize String
$original_tokens = self::tokenize($string);
// Remove existing whitespace
$tokens = array();
foreach ($original_tokens as $i=>$token) {
if ($token[self::TOKEN_TYPE] !== self::TOKEN_TYPE_WHITESPACE) {
$token['i'] = $i;
$tokens[] = $token;
}
}
// Format token by token
foreach ($tokens as $i=>$token) {
// Get highlighted token if doing syntax highlighting
if ($highlight) {
$highlighted = self::highlightToken($token);
} else { // If returning raw text
$highlighted = $token[self::TOKEN_VALUE];
}
// If we are increasing the special indent level now
if ($increase_special_indent) {
$indent_level++;
$increase_special_indent = false;
array_unshift($indent_types,'special');
}
// If we are increasing the block indent level now
if ($increase_block_indent) {
$indent_level++;
$increase_block_indent = false;
array_unshift($indent_types,'block');
}
// If we need a new line before the token
if ($newline) {
$return .= "\n" . str_repeat($tab, $indent_level);
$newline = false;
$added_newline = true;
} else {
$added_newline = false;
}
// Display comments directly where they appear in the source
if ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_COMMENT || $token[self::TOKEN_TYPE] === self::TOKEN_TYPE_BLOCK_COMMENT) {
if ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_BLOCK_COMMENT) {
$indent = str_repeat($tab,$indent_level);
$return .= "\n" . $indent;
$highlighted = str_replace("\n","\n".$indent,$highlighted);
}
$return .= $highlighted;
$newline = true;
continue;
}
if ($inline_parentheses) {
// End of inline parentheses
if ($token[self::TOKEN_VALUE] === ')') {
$return = rtrim($return,' ');
if ($inline_indented) {
array_shift($indent_types);
$indent_level --;
$return .= "\n" . str_repeat($tab, $indent_level);
}
$inline_parentheses = false;
$return .= $highlighted . ' ';
continue;
}
if ($token[self::TOKEN_VALUE] === ',') {
if ($inline_count >= 30) {
$inline_count = 0;
$newline = true;
}
}
$inline_count += strlen($token[self::TOKEN_VALUE]);
}
// Opening parentheses increase the block indent level and start a new line
if ($token[self::TOKEN_VALUE] === '(') {
// First check if this should be an inline parentheses block
// Examples are "NOW()", "COUNT(*)", "int(10)", key(`somecolumn`), DECIMAL(7,2)
// Allow up to 3 non-whitespace tokens inside inline parentheses
$length = 0;
for ($j=1;$j<=250;$j++) {
// Reached end of string
if (!isset($tokens[$i+$j])) break;
$next = $tokens[$i+$j];
// Reached closing parentheses, able to inline it
if ($next[self::TOKEN_VALUE] === ')') {
$inline_parentheses = true;
$inline_count = 0;
$inline_indented = false;
break;
}
// Reached an invalid token for inline parentheses
if ($next[self::TOKEN_VALUE]===';' || $next[self::TOKEN_VALUE]==='(') {
break;
}
// Reached an invalid token type for inline parentheses
if ($next[self::TOKEN_TYPE]===self::TOKEN_TYPE_RESERVED_TOPLEVEL || $next[self::TOKEN_TYPE]===self::TOKEN_TYPE_RESERVED_NEWLINE || $next[self::TOKEN_TYPE]===self::TOKEN_TYPE_COMMENT || $next[self::TOKEN_TYPE]===self::TOKEN_TYPE_BLOCK_COMMENT) {
break;
}
$length += strlen($next[self::TOKEN_VALUE]);
}
if ($inline_parentheses && $length > 30) {
$increase_block_indent = true;
$inline_indented = true;
$newline = true;
}
// Take out the preceding space unless there was whitespace there in the original query
if (isset($original_tokens[$token['i']-1]) && $original_tokens[$token['i']-1][self::TOKEN_TYPE] !== self::TOKEN_TYPE_WHITESPACE) {
$return = rtrim($return,' ');
}
if (!$inline_parentheses) {
$increase_block_indent = true;
// Add a newline after the parentheses
$newline = true;
}
}
// Closing parentheses decrease the block indent level
elseif ($token[self::TOKEN_VALUE] === ')') {
// Remove whitespace before the closing parentheses
$return = rtrim($return,' ');
$indent_level--;
// Reset indent level
while ($j=array_shift($indent_types)) {
if ($j==='special') {
$indent_level--;
} else {
break;
}
}
if ($indent_level < 0) {
// This is an error
$indent_level = 0;
if ($highlight) {
$return .= "\n".self::highlightError($token[self::TOKEN_VALUE]);
continue;
}
}
// Add a newline before the closing parentheses (if not already added)
if (!$added_newline) {
$return .= "\n" . str_repeat($tab, $indent_level);
}
}
// Top level reserved words start a new line and increase the special indent level
elseif ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_RESERVED_TOPLEVEL) {
$increase_special_indent = true;
// If the last indent type was 'special', decrease the special indent for this round
reset($indent_types);
if (current($indent_types)==='special') {
$indent_level--;
array_shift($indent_types);
}
// Add a newline after the top level reserved word
$newline = true;
// Add a newline before the top level reserved word (if not already added)
if (!$added_newline) {
$return .= "\n" . str_repeat($tab, $indent_level);
}
// If we already added a newline, redo the indentation since it may be different now
else {
$return = rtrim($return,$tab).str_repeat($tab, $indent_level);
}
// If the token may have extra whitespace
if (strpos($token[self::TOKEN_VALUE],' ')!==false || strpos($token[self::TOKEN_VALUE],"\n")!==false || strpos($token[self::TOKEN_VALUE],"\t")!==false) {
$highlighted = preg_replace('/\s+/',' ',$highlighted);
}
//if SQL 'LIMIT' clause, start variable to reset newline
if ($token[self::TOKEN_VALUE] === 'LIMIT' && !$inline_parentheses) {
$clause_limit = true;
}
}
// Checks if we are out of the limit clause
elseif ($clause_limit && $token[self::TOKEN_VALUE] !== "," && $token[self::TOKEN_TYPE] !== self::TOKEN_TYPE_NUMBER && $token[self::TOKEN_TYPE] !== self::TOKEN_TYPE_WHITESPACE) {
$clause_limit = false;
}
// Commas start a new line (unless within inline parentheses or SQL 'LIMIT' clause)
elseif ($token[self::TOKEN_VALUE] === ',' && !$inline_parentheses) {
//If the previous TOKEN_VALUE is 'LIMIT', resets new line
if ($clause_limit === true) {
$newline = false;
$clause_limit = false;
}
// All other cases of commas
else {
$newline = true;
}
}
// Newline reserved words start a new line
elseif ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_RESERVED_NEWLINE) {
// Add a newline before the reserved word (if not already added)
if (!$added_newline) {
$return .= "\n" . str_repeat($tab, $indent_level);
}
// If the token may have extra whitespace
if (strpos($token[self::TOKEN_VALUE],' ')!==false || strpos($token[self::TOKEN_VALUE],"\n")!==false || strpos($token[self::TOKEN_VALUE],"\t")!==false) {
$highlighted = preg_replace('/\s+/',' ',$highlighted);
}
}
// Multiple boundary characters in a row should not have spaces between them (not including parentheses)
elseif ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_BOUNDARY) {
if ($tokens[$i-1][self::TOKEN_TYPE] === self::TOKEN_TYPE_BOUNDARY) {
if (isset($original_tokens[$token['i']-1]) && $original_tokens[$token['i']-1][self::TOKEN_TYPE] !== self::TOKEN_TYPE_WHITESPACE) {
$return = rtrim($return,' ');
}
}
}
// If the token shouldn't have a space before it
if ($token[self::TOKEN_VALUE] === '.' || $token[self::TOKEN_VALUE] === ',' || $token[self::TOKEN_VALUE] === ';') {
$return = rtrim($return, ' ');
}
$return .= $highlighted.' ';
// If the token shouldn't have a space after it
if ($token[self::TOKEN_VALUE] === '(' || $token[self::TOKEN_VALUE] === '.') {
$return = rtrim($return,' ');
}
}
// If there are unmatched parentheses
if ($highlight && array_search('block',$indent_types) !== false) {
$return .= "\n".self::highlightError("WARNING: unclosed parentheses or section");
}
// Replace tab characters with the configuration tab character
$return = trim(str_replace("\t",self::$tab,$return));
if ($highlight) {
$return = self::output($return);
}
return $return;
}
/**
* Add syntax highlighting to a SQL string
*
* @param String $string The SQL string
*
* @return String The SQL string with HTML styles applied
*/
public static function highlight($string)
{
$tokens = self::tokenize($string);
$return = '';
foreach ($tokens as $token) {
$return .= self::highlightToken($token);
}
return self::output($return);
}
/**
* Split a SQL string into multiple queries.
* Uses ";" as a query delimiter.
*
* @param String $string The SQL string
*
* @return Array An array of individual query strings without trailing semicolons
*/
public static function splitQuery($string)
{
$queries = array();
$current_query = '';
$empty = true;
$tokens = self::tokenize($string);
foreach ($tokens as $token) {
// If this is a query separator
if ($token[self::TOKEN_VALUE] === ';') {
if (!$empty) {
$queries[] = $current_query.';';
}
$current_query = '';
$empty = true;
continue;
}
// If this is a non-empty character
if ($token[self::TOKEN_TYPE] !== self::TOKEN_TYPE_WHITESPACE && $token[self::TOKEN_TYPE] !== self::TOKEN_TYPE_COMMENT && $token[self::TOKEN_TYPE] !== self::TOKEN_TYPE_BLOCK_COMMENT) {
$empty = false;
}
$current_query .= $token[self::TOKEN_VALUE];
}
if (!$empty) {
$queries[] = trim($current_query);
}
return $queries;
}
/**
* Remove all comments from a SQL string
*
* @param String $string The SQL string
*
* @return String The SQL string without comments
*/
public static function removeComments($string)
{
$result = '';
$tokens = self::tokenize($string);
foreach ($tokens as $token) {
// Skip comment tokens
if ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_COMMENT || $token[self::TOKEN_TYPE] === self::TOKEN_TYPE_BLOCK_COMMENT) {
continue;
}
$result .= $token[self::TOKEN_VALUE];
}
$result = self::format( $result,false);
return $result;
}
/**
* Compress a query by collapsing white space and removing comments
*
* @param String $string The SQL string
*
* @return String The SQL string without comments
*/
public static function compress($string)
{
$result = '';
$tokens = self::tokenize($string);
$whitespace = true;
foreach ($tokens as $token) {
// Skip comment tokens
if ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_COMMENT || $token[self::TOKEN_TYPE] === self::TOKEN_TYPE_BLOCK_COMMENT) {
continue;
}
// Remove extra whitespace in reserved words (e.g "OUTER JOIN" becomes "OUTER JOIN")
elseif ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_RESERVED || $token[self::TOKEN_TYPE] === self::TOKEN_TYPE_RESERVED_NEWLINE || $token[self::TOKEN_TYPE] === self::TOKEN_TYPE_RESERVED_TOPLEVEL) {
$token[self::TOKEN_VALUE] = preg_replace('/\s+/',' ',$token[self::TOKEN_VALUE]);
}
if ($token[self::TOKEN_TYPE] === self::TOKEN_TYPE_WHITESPACE) {
// If the last token was whitespace, don't add another one
if ($whitespace) {
continue;
} else {
$whitespace = true;
// Convert all whitespace to a single space
$token[self::TOKEN_VALUE] = ' ';
}
} else {
$whitespace = false;
}
$result .= $token[self::TOKEN_VALUE];
}
return rtrim($result);
}
/**
* Highlights a token depending on its type.
*
* @param Array $token An associative array containing type and value.
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightToken($token)
{
$type = $token[self::TOKEN_TYPE];
if (self::is_cli()) {
$token = $token[self::TOKEN_VALUE];
} else {
$token = htmlentities($token[self::TOKEN_VALUE],ENT_COMPAT,'UTF-8');
}
if ($type===self::TOKEN_TYPE_BOUNDARY) {
return self::highlightBoundary($token);
} elseif ($type===self::TOKEN_TYPE_WORD) {
return self::highlightWord($token);
} elseif ($type===self::TOKEN_TYPE_BACKTICK_QUOTE) {
return self::highlightBacktickQuote($token);
} elseif ($type===self::TOKEN_TYPE_QUOTE) {
return self::highlightQuote($token);
} elseif ($type===self::TOKEN_TYPE_RESERVED) {
return self::highlightReservedWord($token);
} elseif ($type===self::TOKEN_TYPE_RESERVED_TOPLEVEL) {
return self::highlightReservedWord($token);
} elseif ($type===self::TOKEN_TYPE_RESERVED_NEWLINE) {
return self::highlightReservedWord($token);
} elseif ($type===self::TOKEN_TYPE_NUMBER) {
return self::highlightNumber($token);
} elseif ($type===self::TOKEN_TYPE_VARIABLE) {
return self::highlightVariable($token);
} elseif ($type===self::TOKEN_TYPE_COMMENT || $type===self::TOKEN_TYPE_BLOCK_COMMENT) {
return self::highlightComment($token);
}
return $token;
}
/**
* Highlights a quoted string
*
* @param String $value The token's value
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightQuote($value)
{
if (self::is_cli()) {
return self::$cli_quote . $value . "\x1b[0m";
} else {
return '<span ' . self::$quote_attributes . '>' . $value . '</span>';
}
}
/**
* Highlights a backtick quoted string
*
* @param String $value The token's value
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightBacktickQuote($value)
{
if (self::is_cli()) {
return self::$cli_backtick_quote . $value . "\x1b[0m";
} else {
return '<span ' . self::$backtick_quote_attributes . '>' . $value . '</span>';
}
}
/**
* Highlights a reserved word
*
* @param String $value The token's value
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightReservedWord($value)
{
if (self::is_cli()) {
return self::$cli_reserved . $value . "\x1b[0m";
} else {
return '<span ' . self::$reserved_attributes . '>' . $value . '</span>';
}
}
/**
* Highlights a boundary token
*
* @param String $value The token's value
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightBoundary($value)
{
if ($value==='(' || $value===')') return $value;
if (self::is_cli()) {
return self::$cli_boundary . $value . "\x1b[0m";
} else {
return '<span ' . self::$boundary_attributes . '>' . $value . '</span>';
}
}
/**
* Highlights a number
*
* @param String $value The token's value
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightNumber($value)
{
if (self::is_cli()) {
return self::$cli_number . $value . "\x1b[0m";
} else {
return '<span ' . self::$number_attributes . '>' . $value . '</span>';
}
}
/**
* Highlights an error
*
* @param String $value The token's value
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightError($value)
{
if (self::is_cli()) {
return self::$cli_error . $value . "\x1b[0m";
} else {
return '<span ' . self::$error_attributes . '>' . $value . '</span>';
}
}
/**
* Highlights a comment
*
* @param String $value The token's value
*
* @return String HTML code of the highlighted token.
*/
protected static function highlightComment($value)
{
if (self::is_cli()) {
return self::$cli_comment . $value . "\x1b[0m";
} else {
return '<span ' . self::$comment_attributes . '>' . $value . '</span>';
}
}