/ Check-in [62b87751]
Login
SQLite training in Houston TX on 2019-11-05 (details)
Part of the 2019 Tcl Conference

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Split the sqlite3_complete() API out into a separate source file so that in static links where it is not used it will not take up space in the resulting binary. (CVS 2594)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 62b87751dea56c565bcc2aca88a2edda7dfc2a57
User & Date: drh 2005-08-14 17:53:21
Context
2005-08-14
20:47
General code cleanup resulting in smaller footprint. (CVS 2595) check-in: 98338abf user: drh tags: trunk
17:53
Split the sqlite3_complete() API out into a separate source file so that in static links where it is not used it will not take up space in the resulting binary. (CVS 2594) check-in: 62b87751 user: drh tags: trunk
01:34
Declare local-use functions as static. Ticket #1363. (CVS 2593) check-in: 94efd790 user: drh tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to Makefile.in.

109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
...
129
130
131
132
133
134
135

136
137
138
139
140
141
142
...
187
188
189
190
191
192
193
194

195
196
197
198
199
200
201
...
286
287
288
289
290
291
292



293
294
295
296
297
298
299

OPTS += -DSQLITE_OMIT_CURSOR          # Cursors do not work at this time
TCC += -DSQLITE_OMIT_CURSOR

# Object files for the SQLite library.
#
LIBOBJ = alter.lo analyze.lo attach.lo auth.lo btree.lo build.lo \
         callback.lo date.lo \
         delete.lo expr.lo func.lo hash.lo insert.lo \
         main.lo opcodes.lo os_unix.lo os_win.lo \
         pager.lo parse.lo pragma.lo prepare.lo printf.lo random.lo \
         select.lo table.lo tokenize.lo trigger.lo update.lo \
         util.lo vacuum.lo \
         vdbe.lo vdbeapi.lo vdbeaux.lo vdbefifo.lo vdbemem.lo \
         where.lo utf.lo legacy.lo
................................................................................
  $(TOP)/src/analyze.c \
  $(TOP)/src/attach.c \
  $(TOP)/src/auth.c \
  $(TOP)/src/btree.c \
  $(TOP)/src/btree.h \
  $(TOP)/src/build.c \
  $(TOP)/src/callback.c \

  $(TOP)/src/date.c \
  $(TOP)/src/delete.c \
  $(TOP)/src/expr.c \
  $(TOP)/src/func.c \
  $(TOP)/src/hash.c \
  $(TOP)/src/hash.h \
  $(TOP)/src/insert.c \
................................................................................
  $(TOP)/src/test2.c \
  $(TOP)/src/test3.c \
  $(TOP)/src/test4.c \
  $(TOP)/src/test5.c \
  $(TOP)/src/utf.c \
  $(TOP)/src/util.c \
  $(TOP)/src/vdbe.c \
  $(TOP)/src/md5.c


# In LIBOBJ but not TESTSRC
COMMONOBJ = $(foreach obj,$(LIBOBJ),\
	$(if $(findstring $(patsubst %.lo,%.c,$(obj)),$(TESTSRC)),,$(obj)))

# Header files used by all library source files.
#
................................................................................
	$(LTCOMPILE) -c $(TOP)/src/btree.c

build.lo:	$(TOP)/src/build.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/build.c

callback.lo:	$(TOP)/src/callback.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/callback.c




date.lo:	$(TOP)/src/date.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/date.c

delete.lo:	$(TOP)/src/delete.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/delete.c








|







 







>







 







|
>







 







>
>
>







109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
...
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
...
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
...
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304

OPTS += -DSQLITE_OMIT_CURSOR          # Cursors do not work at this time
TCC += -DSQLITE_OMIT_CURSOR

# Object files for the SQLite library.
#
LIBOBJ = alter.lo analyze.lo attach.lo auth.lo btree.lo build.lo \
         callback.lo complete.lo date.lo \
         delete.lo expr.lo func.lo hash.lo insert.lo \
         main.lo opcodes.lo os_unix.lo os_win.lo \
         pager.lo parse.lo pragma.lo prepare.lo printf.lo random.lo \
         select.lo table.lo tokenize.lo trigger.lo update.lo \
         util.lo vacuum.lo \
         vdbe.lo vdbeapi.lo vdbeaux.lo vdbefifo.lo vdbemem.lo \
         where.lo utf.lo legacy.lo
................................................................................
  $(TOP)/src/analyze.c \
  $(TOP)/src/attach.c \
  $(TOP)/src/auth.c \
  $(TOP)/src/btree.c \
  $(TOP)/src/btree.h \
  $(TOP)/src/build.c \
  $(TOP)/src/callback.c \
  $(TOP)/src/complete.c \
  $(TOP)/src/date.c \
  $(TOP)/src/delete.c \
  $(TOP)/src/expr.c \
  $(TOP)/src/func.c \
  $(TOP)/src/hash.c \
  $(TOP)/src/hash.h \
  $(TOP)/src/insert.c \
................................................................................
  $(TOP)/src/test2.c \
  $(TOP)/src/test3.c \
  $(TOP)/src/test4.c \
  $(TOP)/src/test5.c \
  $(TOP)/src/utf.c \
  $(TOP)/src/util.c \
  $(TOP)/src/vdbe.c \
  $(TOP)/src/md5.c \
  $(TOP)/src/where.c

# In LIBOBJ but not TESTSRC
COMMONOBJ = $(foreach obj,$(LIBOBJ),\
	$(if $(findstring $(patsubst %.lo,%.c,$(obj)),$(TESTSRC)),,$(obj)))

# Header files used by all library source files.
#
................................................................................
	$(LTCOMPILE) -c $(TOP)/src/btree.c

build.lo:	$(TOP)/src/build.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/build.c

callback.lo:	$(TOP)/src/callback.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/callback.c

complete.lo:	$(TOP)/src/complete.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/complete.c

date.lo:	$(TOP)/src/date.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/date.c

delete.lo:	$(TOP)/src/delete.c $(HDR)
	$(LTCOMPILE) -c $(TOP)/src/delete.c

Changes to main.mk.

51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
..
71
72
73
74
75
76
77

78
79
80
81
82
83
84
...
217
218
219
220
221
222
223



224
225
226
227
228
229
230
# This is how we compile
#
TCCX = $(TCC) $(OPTS) $(THREADSAFE) $(USLEEP) -I. -I$(TOP)/src

# Object files for the SQLite library.
#
LIBOBJ+= alter.o analyze.o attach.o auth.o btree.o build.o \
         callback.o date.o delete.o \
         expr.o func.o hash.o insert.o \
         main.o opcodes.o os_unix.o os_win.o \
         pager.o parse.o pragma.o prepare.o printf.o random.o \
         select.o table.o tclsqlite.o tokenize.o trigger.o \
         update.o util.o vacuum.o \
         vdbe.o vdbeapi.o vdbeaux.o vdbefifo.o vdbemem.o \
         where.o utf.o legacy.o
................................................................................
  $(TOP)/src/analyze.c \
  $(TOP)/src/attach.c \
  $(TOP)/src/auth.c \
  $(TOP)/src/btree.c \
  $(TOP)/src/btree.h \
  $(TOP)/src/build.c \
  $(TOP)/src/callback.c \

  $(TOP)/src/date.c \
  $(TOP)/src/delete.c \
  $(TOP)/src/expr.c \
  $(TOP)/src/func.c \
  $(TOP)/src/hash.c \
  $(TOP)/src/hash.h \
  $(TOP)/src/insert.c \
................................................................................
	$(TCCX) -c $(TOP)/src/btree.c

build.o:	$(TOP)/src/build.c $(HDR)
	$(TCCX) -c $(TOP)/src/build.c

callback.o:	$(TOP)/src/callback.c $(HDR)
	$(TCCX) -c $(TOP)/src/callback.c




date.o:	$(TOP)/src/date.c $(HDR)
	$(TCCX) -c $(TOP)/src/date.c

delete.o:	$(TOP)/src/delete.c $(HDR)
	$(TCCX) -c $(TOP)/src/delete.c








|







 







>







 







>
>
>







51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
..
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
...
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
# This is how we compile
#
TCCX = $(TCC) $(OPTS) $(THREADSAFE) $(USLEEP) -I. -I$(TOP)/src

# Object files for the SQLite library.
#
LIBOBJ+= alter.o analyze.o attach.o auth.o btree.o build.o \
         callback.o complete.o date.o delete.o \
         expr.o func.o hash.o insert.o \
         main.o opcodes.o os_unix.o os_win.o \
         pager.o parse.o pragma.o prepare.o printf.o random.o \
         select.o table.o tclsqlite.o tokenize.o trigger.o \
         update.o util.o vacuum.o \
         vdbe.o vdbeapi.o vdbeaux.o vdbefifo.o vdbemem.o \
         where.o utf.o legacy.o
................................................................................
  $(TOP)/src/analyze.c \
  $(TOP)/src/attach.c \
  $(TOP)/src/auth.c \
  $(TOP)/src/btree.c \
  $(TOP)/src/btree.h \
  $(TOP)/src/build.c \
  $(TOP)/src/callback.c \
  $(TOP)/src/complete.c \
  $(TOP)/src/date.c \
  $(TOP)/src/delete.c \
  $(TOP)/src/expr.c \
  $(TOP)/src/func.c \
  $(TOP)/src/hash.c \
  $(TOP)/src/hash.h \
  $(TOP)/src/insert.c \
................................................................................
	$(TCCX) -c $(TOP)/src/btree.c

build.o:	$(TOP)/src/build.c $(HDR)
	$(TCCX) -c $(TOP)/src/build.c

callback.o:	$(TOP)/src/callback.c $(HDR)
	$(TCCX) -c $(TOP)/src/callback.c

complete.o:	$(TOP)/src/complete.c $(HDR)
	$(TCCX) -c $(TOP)/src/complete.c

date.o:	$(TOP)/src/date.c $(HDR)
	$(TCCX) -c $(TOP)/src/date.c

delete.o:	$(TOP)/src/delete.c $(HDR)
	$(TCCX) -c $(TOP)/src/delete.c

Added src/complete.c.















































































































































































































































































































































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
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
/*
** 2001 September 15
**
** The author disclaims copyright to this source code.  In place of
** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** An tokenizer for SQL
**
** This file contains C code that implements the sqlite3_complete() API.
** This code used to be part of the tokenizer.c source file.  But by
** separating it out, the code will be automatically omitted from
** static links that do not use it.
**
** $Id: complete.c,v 1.1 2005/08/14 17:53:21 drh Exp $
*/
#include "sqliteInt.h"
#ifndef SQLITE_OMIT_COMPLETE

/*
** This is defined in tokenize.c.  We just have to import the definition.
*/
extern const char sqlite3IsIdChar[];
#define IdChar(C)  (((c=C)&0x80)!=0 || (c>0x1f && sqlite3IsIdChar[c-0x20]))


/*
** Token types used by the sqlite3_complete() routine.  See the header
** comments on that procedure for additional information.
*/
#define tkSEMI    0
#define tkWS      1
#define tkOTHER   2
#define tkEXPLAIN 3
#define tkCREATE  4
#define tkTEMP    5
#define tkTRIGGER 6
#define tkEND     7

/*
** Return TRUE if the given SQL string ends in a semicolon.
**
** Special handling is require for CREATE TRIGGER statements.
** Whenever the CREATE TRIGGER keywords are seen, the statement
** must end with ";END;".
**
** This implementation uses a state machine with 7 states:
**
**   (0) START     At the beginning or end of an SQL statement.  This routine
**                 returns 1 if it ends in the START state and 0 if it ends
**                 in any other state.
**
**   (1) NORMAL    We are in the middle of statement which ends with a single
**                 semicolon.
**
**   (2) EXPLAIN   The keyword EXPLAIN has been seen at the beginning of 
**                 a statement.
**
**   (3) CREATE    The keyword CREATE has been seen at the beginning of a
**                 statement, possibly preceeded by EXPLAIN and/or followed by
**                 TEMP or TEMPORARY
**
**   (4) TRIGGER   We are in the middle of a trigger definition that must be
**                 ended by a semicolon, the keyword END, and another semicolon.
**
**   (5) SEMI      We've seen the first semicolon in the ";END;" that occurs at
**                 the end of a trigger definition.
**
**   (6) END       We've seen the ";END" of the ";END;" that occurs at the end
**                 of a trigger difinition.
**
** Transitions between states above are determined by tokens extracted
** from the input.  The following tokens are significant:
**
**   (0) tkSEMI      A semicolon.
**   (1) tkWS        Whitespace
**   (2) tkOTHER     Any other SQL token.
**   (3) tkEXPLAIN   The "explain" keyword.
**   (4) tkCREATE    The "create" keyword.
**   (5) tkTEMP      The "temp" or "temporary" keyword.
**   (6) tkTRIGGER   The "trigger" keyword.
**   (7) tkEND       The "end" keyword.
**
** Whitespace never causes a state transition and is always ignored.
**
** If we compile with SQLITE_OMIT_TRIGGER, all of the computation needed
** to recognize the end of a trigger can be omitted.  All we have to do
** is look for a semicolon that is not part of an string or comment.
*/
int sqlite3_complete(const char *zSql){
  u8 state = 0;   /* Current state, using numbers defined in header comment */
  u8 token;       /* Value of the next token */

#ifndef SQLITE_OMIT_TRIGGER
  /* A complex statement machine used to detect the end of a CREATE TRIGGER
  ** statement.  This is the normal case.
  */
  static const u8 trans[7][8] = {
                     /* Token:                                                */
     /* State:       **  SEMI  WS  OTHER EXPLAIN  CREATE  TEMP  TRIGGER  END  */
     /* 0   START: */ {    0,  0,     1,      2,      3,    1,       1,   1,  },
     /* 1  NORMAL: */ {    0,  1,     1,      1,      1,    1,       1,   1,  },
     /* 2 EXPLAIN: */ {    0,  2,     1,      1,      3,    1,       1,   1,  },
     /* 3  CREATE: */ {    0,  3,     1,      1,      1,    3,       4,   1,  },
     /* 4 TRIGGER: */ {    5,  4,     4,      4,      4,    4,       4,   4,  },
     /* 5    SEMI: */ {    5,  5,     4,      4,      4,    4,       4,   6,  },
     /* 6     END: */ {    0,  6,     4,      4,      4,    4,       4,   4,  },
  };
#else
  /* If triggers are not suppored by this compile then the statement machine
  ** used to detect the end of a statement is much simplier
  */
  static const u8 trans[2][3] = {
                     /* Token:           */
     /* State:       **  SEMI  WS  OTHER */
     /* 0   START: */ {    0,  0,     1, },
     /* 1  NORMAL: */ {    0,  1,     1, },
  };
#endif /* SQLITE_OMIT_TRIGGER */

  while( *zSql ){
    switch( *zSql ){
      case ';': {  /* A semicolon */
        token = tkSEMI;
        break;
      }
      case ' ':
      case '\r':
      case '\t':
      case '\n':
      case '\f': {  /* White space is ignored */
        token = tkWS;
        break;
      }
      case '/': {   /* C-style comments */
        if( zSql[1]!='*' ){
          token = tkOTHER;
          break;
        }
        zSql += 2;
        while( zSql[0] && (zSql[0]!='*' || zSql[1]!='/') ){ zSql++; }
        if( zSql[0]==0 ) return 0;
        zSql++;
        token = tkWS;
        break;
      }
      case '-': {   /* SQL-style comments from "--" to end of line */
        if( zSql[1]!='-' ){
          token = tkOTHER;
          break;
        }
        while( *zSql && *zSql!='\n' ){ zSql++; }
        if( *zSql==0 ) return state==0;
        token = tkWS;
        break;
      }
      case '[': {   /* Microsoft-style identifiers in [...] */
        zSql++;
        while( *zSql && *zSql!=']' ){ zSql++; }
        if( *zSql==0 ) return 0;
        token = tkOTHER;
        break;
      }
      case '`':     /* Grave-accent quoted symbols used by MySQL */
      case '"':     /* single- and double-quoted strings */
      case '\'': {
        int c = *zSql;
        zSql++;
        while( *zSql && *zSql!=c ){ zSql++; }
        if( *zSql==0 ) return 0;
        token = tkOTHER;
        break;
      }
      default: {
        int c;
        if( IdChar((u8)*zSql) ){
          /* Keywords and unquoted identifiers */
          int nId;
          for(nId=1; IdChar(zSql[nId]); nId++){}
#ifdef SQLITE_OMIT_TRIGGER
          token = tkOTHER;
#else
          switch( *zSql ){
            case 'c': case 'C': {
              if( nId==6 && sqlite3StrNICmp(zSql, "create", 6)==0 ){
                token = tkCREATE;
              }else{
                token = tkOTHER;
              }
              break;
            }
            case 't': case 'T': {
              if( nId==7 && sqlite3StrNICmp(zSql, "trigger", 7)==0 ){
                token = tkTRIGGER;
              }else if( nId==4 && sqlite3StrNICmp(zSql, "temp", 4)==0 ){
                token = tkTEMP;
              }else if( nId==9 && sqlite3StrNICmp(zSql, "temporary", 9)==0 ){
                token = tkTEMP;
              }else{
                token = tkOTHER;
              }
              break;
            }
            case 'e':  case 'E': {
              if( nId==3 && sqlite3StrNICmp(zSql, "end", 3)==0 ){
                token = tkEND;
              }else
#ifndef SQLITE_OMIT_EXPLAIN
              if( nId==7 && sqlite3StrNICmp(zSql, "explain", 7)==0 ){
                token = tkEXPLAIN;
              }else
#endif
              {
                token = tkOTHER;
              }
              break;
            }
            default: {
              token = tkOTHER;
              break;
            }
          }
#endif /* SQLITE_OMIT_TRIGGER */
          zSql += nId-1;
        }else{
          /* Operators and special symbols */
          token = tkOTHER;
        }
        break;
      }
    }
    state = trans[state][token];
    zSql++;
  }
  return state==0;
}

#ifndef SQLITE_OMIT_UTF16
/*
** This routine is the same as the sqlite3_complete() routine described
** above, except that the parameter is required to be UTF-16 encoded, not
** UTF-8.
*/
int sqlite3_complete16(const void *zSql){
  sqlite3_value *pVal;
  char const *zSql8;
  int rc = 0;

  pVal = sqlite3ValueNew();
  sqlite3ValueSetStr(pVal, -1, zSql, SQLITE_UTF16NATIVE, SQLITE_STATIC);
  zSql8 = sqlite3ValueText(pVal, SQLITE_UTF8);
  if( zSql8 ){
    rc = sqlite3_complete(zSql8);
  }
  sqlite3ValueFree(pVal);
  return rc;
}
#endif /* SQLITE_OMIT_UTF16 */
#endif /* SQLITE_OMIT_COMPLETE */

Changes to src/tokenize.c.

11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
..
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
...
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
*************************************************************************
** An tokenizer for SQL
**
** This file contains C code that splits an SQL input string up into
** individual tokens and sends those tokens one-by-one over to the
** parser for analysis.
**
** $Id: tokenize.c,v 1.105 2005/08/13 18:15:43 drh Exp $
*/
#include "sqliteInt.h"
#include "os.h"
#include <ctype.h>
#include <stdlib.h>

/*
................................................................................
** the #include below.
*/
#include "keywordhash.h"


/*
** If X is a character that can be used in an identifier and
** X&0x80==0 then isIdChar[X] will be 1.  If X&0x80==0x80 then
** X is always an identifier character.  (Hence all UTF-8
** characters can be part of an identifier).  isIdChar[X] will
** be 0 for every character in the lower 128 ASCII characters
** that cannot be used as part of an identifier.
**
** In this implementation, an identifier can be a string of
** alphabetic characters, digits, and "_" plus any character
** with the high-order bit set.  The latter rule means that
** any sequence of UTF-8 characters or characters taken from
................................................................................
** an extended ISO8859 character set can form an identifier.
**
** Ticket #1066.  the SQL standard does not allow '$' in the
** middle of identfiers.  But many SQL implementations do. 
** SQLite will allow '$' in identifiers for compatibility.
** But the feature is undocumented.
*/
static const char isIdChar[] = {
/* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xA xB xC xD xE xF */
    0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  /* 2x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,  /* 3x */
    0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 4x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1,  /* 5x */
    0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 6x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,  /* 7x */
};

#define IdChar(C)  (((c=C)&0x80)!=0 || (c>0x1f && isIdChar[c-0x20]))

/*
** Return the length of the token that begins at z[0]. 
** Store the token type in *tokenType before returning.
*/
static int getToken(const unsigned char *z, int *tokenType){
  int i, c;
................................................................................
  sqlite3DeleteTrigger(pParse->pNewTrigger);
  sqliteFree(pParse->apVarExpr);
  if( nErr>0 && (pParse->rc==SQLITE_OK || pParse->rc==SQLITE_DONE) ){
    pParse->rc = SQLITE_ERROR;
  }
  return nErr;
}

/* The sqlite3_complete() API may be omitted (to save code space) by
** defining the following symbol.
*/
#ifndef SQLITE_OMIT_COMPLETE

/*
** Token types used by the sqlite3_complete() routine.  See the header
** comments on that procedure for additional information.
*/
#define tkSEMI    0
#define tkWS      1
#define tkOTHER   2
#define tkEXPLAIN 3
#define tkCREATE  4
#define tkTEMP    5
#define tkTRIGGER 6
#define tkEND     7

/*
** Return TRUE if the given SQL string ends in a semicolon.
**
** Special handling is require for CREATE TRIGGER statements.
** Whenever the CREATE TRIGGER keywords are seen, the statement
** must end with ";END;".
**
** This implementation uses a state machine with 7 states:
**
**   (0) START     At the beginning or end of an SQL statement.  This routine
**                 returns 1 if it ends in the START state and 0 if it ends
**                 in any other state.
**
**   (1) NORMAL    We are in the middle of statement which ends with a single
**                 semicolon.
**
**   (2) EXPLAIN   The keyword EXPLAIN has been seen at the beginning of 
**                 a statement.
**
**   (3) CREATE    The keyword CREATE has been seen at the beginning of a
**                 statement, possibly preceeded by EXPLAIN and/or followed by
**                 TEMP or TEMPORARY
**
**   (4) TRIGGER   We are in the middle of a trigger definition that must be
**                 ended by a semicolon, the keyword END, and another semicolon.
**
**   (5) SEMI      We've seen the first semicolon in the ";END;" that occurs at
**                 the end of a trigger definition.
**
**   (6) END       We've seen the ";END" of the ";END;" that occurs at the end
**                 of a trigger difinition.
**
** Transitions between states above are determined by tokens extracted
** from the input.  The following tokens are significant:
**
**   (0) tkSEMI      A semicolon.
**   (1) tkWS        Whitespace
**   (2) tkOTHER     Any other SQL token.
**   (3) tkEXPLAIN   The "explain" keyword.
**   (4) tkCREATE    The "create" keyword.
**   (5) tkTEMP      The "temp" or "temporary" keyword.
**   (6) tkTRIGGER   The "trigger" keyword.
**   (7) tkEND       The "end" keyword.
**
** Whitespace never causes a state transition and is always ignored.
**
** If we compile with SQLITE_OMIT_TRIGGER, all of the computation needed
** to recognize the end of a trigger can be omitted.  All we have to do
** is look for a semicolon that is not part of an string or comment.
*/
int sqlite3_complete(const char *zSql){
  u8 state = 0;   /* Current state, using numbers defined in header comment */
  u8 token;       /* Value of the next token */

#ifndef SQLITE_OMIT_TRIGGER
  /* A complex statement machine used to detect the end of a CREATE TRIGGER
  ** statement.  This is the normal case.
  */
  static const u8 trans[7][8] = {
                     /* Token:                                                */
     /* State:       **  SEMI  WS  OTHER EXPLAIN  CREATE  TEMP  TRIGGER  END  */
     /* 0   START: */ {    0,  0,     1,      2,      3,    1,       1,   1,  },
     /* 1  NORMAL: */ {    0,  1,     1,      1,      1,    1,       1,   1,  },
     /* 2 EXPLAIN: */ {    0,  2,     1,      1,      3,    1,       1,   1,  },
     /* 3  CREATE: */ {    0,  3,     1,      1,      1,    3,       4,   1,  },
     /* 4 TRIGGER: */ {    5,  4,     4,      4,      4,    4,       4,   4,  },
     /* 5    SEMI: */ {    5,  5,     4,      4,      4,    4,       4,   6,  },
     /* 6     END: */ {    0,  6,     4,      4,      4,    4,       4,   4,  },
  };
#else
  /* If triggers are not suppored by this compile then the statement machine
  ** used to detect the end of a statement is much simplier
  */
  static const u8 trans[2][3] = {
                     /* Token:           */
     /* State:       **  SEMI  WS  OTHER */
     /* 0   START: */ {    0,  0,     1, },
     /* 1  NORMAL: */ {    0,  1,     1, },
  };
#endif /* SQLITE_OMIT_TRIGGER */

  while( *zSql ){
    switch( *zSql ){
      case ';': {  /* A semicolon */
        token = tkSEMI;
        break;
      }
      case ' ':
      case '\r':
      case '\t':
      case '\n':
      case '\f': {  /* White space is ignored */
        token = tkWS;
        break;
      }
      case '/': {   /* C-style comments */
        if( zSql[1]!='*' ){
          token = tkOTHER;
          break;
        }
        zSql += 2;
        while( zSql[0] && (zSql[0]!='*' || zSql[1]!='/') ){ zSql++; }
        if( zSql[0]==0 ) return 0;
        zSql++;
        token = tkWS;
        break;
      }
      case '-': {   /* SQL-style comments from "--" to end of line */
        if( zSql[1]!='-' ){
          token = tkOTHER;
          break;
        }
        while( *zSql && *zSql!='\n' ){ zSql++; }
        if( *zSql==0 ) return state==0;
        token = tkWS;
        break;
      }
      case '[': {   /* Microsoft-style identifiers in [...] */
        zSql++;
        while( *zSql && *zSql!=']' ){ zSql++; }
        if( *zSql==0 ) return 0;
        token = tkOTHER;
        break;
      }
      case '`':     /* Grave-accent quoted symbols used by MySQL */
      case '"':     /* single- and double-quoted strings */
      case '\'': {
        int c = *zSql;
        zSql++;
        while( *zSql && *zSql!=c ){ zSql++; }
        if( *zSql==0 ) return 0;
        token = tkOTHER;
        break;
      }
      default: {
        int c;
        if( IdChar((u8)*zSql) ){
          /* Keywords and unquoted identifiers */
          int nId;
          for(nId=1; IdChar(zSql[nId]); nId++){}
#ifdef SQLITE_OMIT_TRIGGER
          token = tkOTHER;
#else
          switch( *zSql ){
            case 'c': case 'C': {
              if( nId==6 && sqlite3StrNICmp(zSql, "create", 6)==0 ){
                token = tkCREATE;
              }else{
                token = tkOTHER;
              }
              break;
            }
            case 't': case 'T': {
              if( nId==7 && sqlite3StrNICmp(zSql, "trigger", 7)==0 ){
                token = tkTRIGGER;
              }else if( nId==4 && sqlite3StrNICmp(zSql, "temp", 4)==0 ){
                token = tkTEMP;
              }else if( nId==9 && sqlite3StrNICmp(zSql, "temporary", 9)==0 ){
                token = tkTEMP;
              }else{
                token = tkOTHER;
              }
              break;
            }
            case 'e':  case 'E': {
              if( nId==3 && sqlite3StrNICmp(zSql, "end", 3)==0 ){
                token = tkEND;
              }else
#ifndef SQLITE_OMIT_EXPLAIN
              if( nId==7 && sqlite3StrNICmp(zSql, "explain", 7)==0 ){
                token = tkEXPLAIN;
              }else
#endif
              {
                token = tkOTHER;
              }
              break;
            }
            default: {
              token = tkOTHER;
              break;
            }
          }
#endif /* SQLITE_OMIT_TRIGGER */
          zSql += nId-1;
        }else{
          /* Operators and special symbols */
          token = tkOTHER;
        }
        break;
      }
    }
    state = trans[state][token];
    zSql++;
  }
  return state==0;
}

#ifndef SQLITE_OMIT_UTF16
/*
** This routine is the same as the sqlite3_complete() routine described
** above, except that the parameter is required to be UTF-16 encoded, not
** UTF-8.
*/
int sqlite3_complete16(const void *zSql){
  sqlite3_value *pVal;
  char const *zSql8;
  int rc = 0;

  pVal = sqlite3ValueNew();
  sqlite3ValueSetStr(pVal, -1, zSql, SQLITE_UTF16NATIVE, SQLITE_STATIC);
  zSql8 = sqlite3ValueText(pVal, SQLITE_UTF8);
  if( zSql8 ){
    rc = sqlite3_complete(zSql8);
  }
  sqlite3ValueFree(pVal);
  return rc;
}
#endif /* SQLITE_OMIT_UTF16 */
#endif /* SQLITE_OMIT_COMPLETE */







|







 







|

|







 







|









|







 







<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
..
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
...
420
421
422
423
424
425
426















































































































































































































































*************************************************************************
** An tokenizer for SQL
**
** This file contains C code that splits an SQL input string up into
** individual tokens and sends those tokens one-by-one over to the
** parser for analysis.
**
** $Id: tokenize.c,v 1.106 2005/08/14 17:53:21 drh Exp $
*/
#include "sqliteInt.h"
#include "os.h"
#include <ctype.h>
#include <stdlib.h>

/*
................................................................................
** the #include below.
*/
#include "keywordhash.h"


/*
** If X is a character that can be used in an identifier and
** X&0x80==0 then sqlite3IsIdChar[X] will be 1.  If X&0x80==0x80 then
** X is always an identifier character.  (Hence all UTF-8
** characters can be part of an identifier).  sqlite3IsIdChar[X] will
** be 0 for every character in the lower 128 ASCII characters
** that cannot be used as part of an identifier.
**
** In this implementation, an identifier can be a string of
** alphabetic characters, digits, and "_" plus any character
** with the high-order bit set.  The latter rule means that
** any sequence of UTF-8 characters or characters taken from
................................................................................
** an extended ISO8859 character set can form an identifier.
**
** Ticket #1066.  the SQL standard does not allow '$' in the
** middle of identfiers.  But many SQL implementations do. 
** SQLite will allow '$' in identifiers for compatibility.
** But the feature is undocumented.
*/
const char sqlite3IsIdChar[] = {
/* x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xA xB xC xD xE xF */
    0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  /* 2x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,  /* 3x */
    0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 4x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1,  /* 5x */
    0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* 6x */
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,  /* 7x */
};

#define IdChar(C)  (((c=C)&0x80)!=0 || (c>0x1f && sqlite3IsIdChar[c-0x20]))

/*
** Return the length of the token that begins at z[0]. 
** Store the token type in *tokenType before returning.
*/
static int getToken(const unsigned char *z, int *tokenType){
  int i, c;
................................................................................
  sqlite3DeleteTrigger(pParse->pNewTrigger);
  sqliteFree(pParse->apVarExpr);
  if( nErr>0 && (pParse->rc==SQLITE_OK || pParse->rc==SQLITE_DONE) ){
    pParse->rc = SQLITE_ERROR;
  }
  return nErr;
}