-
Notifications
You must be signed in to change notification settings - Fork 12
Expand file tree
/
Copy pathfts3.c
More file actions
5352 lines (4908 loc) · 178 KB
/
fts3.c
File metadata and controls
5352 lines (4908 loc) · 178 KB
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
/*
** 2006 Oct 10
**
** 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.
**
******************************************************************************
**
** This is an SQLite module implementing full-text search.
*/
/*
** The code in this file is only compiled if:
**
** * The FTS3 module is being built as an extension
** (in which case SQLITE_CORE is not defined), or
**
** * The FTS3 module is being built into the core of
** SQLite (in which case SQLITE_ENABLE_FTS3 is defined).
*/
/* The full-text index is stored in a series of b+tree (-like)
** structures called segments which map terms to doclists. The
** structures are like b+trees in layout, but are constructed from the
** bottom up in optimal fashion and are not updatable. Since trees
** are built from the bottom up, things will be described from the
** bottom up.
**
**
**** Varints ****
** The basic unit of encoding is a variable-length integer called a
** varint. We encode variable-length integers in little-endian order
** using seven bits * per byte as follows:
**
** KEY:
** A = 0xxxxxxx 7 bits of data and one flag bit
** B = 1xxxxxxx 7 bits of data and one flag bit
**
** 7 bits - A
** 14 bits - BA
** 21 bits - BBA
** and so on.
**
** This is similar in concept to how sqlite encodes "varints" but
** the encoding is not the same. SQLite varints are big-endian
** are are limited to 9 bytes in length whereas FTS3 varints are
** little-endian and can be up to 10 bytes in length (in theory).
**
** Example encodings:
**
** 1: 0x01
** 127: 0x7f
** 128: 0x81 0x00
**
**
**** Document lists ****
** A doclist (document list) holds a docid-sorted list of hits for a
** given term. Doclists hold docids and associated token positions.
** A docid is the unique integer identifier for a single document.
** A position is the index of a word within the document. The first
** word of the document has a position of 0.
**
** FTS3 used to optionally store character offsets using a compile-time
** option. But that functionality is no longer supported.
**
** A doclist is stored like this:
**
** array {
** varint docid; (delta from previous doclist)
** array { (position list for column 0)
** varint position; (2 more than the delta from previous position)
** }
** array {
** varint POS_COLUMN; (marks start of position list for new column)
** varint column; (index of new column)
** array {
** varint position; (2 more than the delta from previous position)
** }
** }
** varint POS_END; (marks end of positions for this document.
** }
**
** Here, array { X } means zero or more occurrences of X, adjacent in
** memory. A "position" is an index of a token in the token stream
** generated by the tokenizer. Note that POS_END and POS_COLUMN occur
** in the same logical place as the position element, and act as sentinals
** ending a position list array. POS_END is 0. POS_COLUMN is 1.
** The positions numbers are not stored literally but rather as two more
** than the difference from the prior position, or the just the position plus
** 2 for the first position. Example:
**
** label: A B C D E F G H I J K
** value: 123 5 9 1 1 14 35 0 234 72 0
**
** The 123 value is the first docid. For column zero in this document
** there are two matches at positions 3 and 10 (5-2 and 9-2+3). The 1
** at D signals the start of a new column; the 1 at E indicates that the
** new column is column number 1. There are two positions at 12 and 45
** (14-2 and 35-2+12). The 0 at H indicate the end-of-document. The
** 234 at I is the delta to next docid (357). It has one position 70
** (72-2) and then terminates with the 0 at K.
**
** A "position-list" is the list of positions for multiple columns for
** a single docid. A "column-list" is the set of positions for a single
** column. Hence, a position-list consists of one or more column-lists,
** a document record consists of a docid followed by a position-list and
** a doclist consists of one or more document records.
**
** A bare doclist omits the position information, becoming an
** array of varint-encoded docids.
**
**** Segment leaf nodes ****
** Segment leaf nodes store terms and doclists, ordered by term. Leaf
** nodes are written using LeafWriter, and read using LeafReader (to
** iterate through a single leaf node's data) and LeavesReader (to
** iterate through a segment's entire leaf layer). Leaf nodes have
** the format:
**
** varint iHeight; (height from leaf level, always 0)
** varint nTerm; (length of first term)
** char pTerm[nTerm]; (content of first term)
** varint nDoclist; (length of term's associated doclist)
** char pDoclist[nDoclist]; (content of doclist)
** array {
** (further terms are delta-encoded)
** varint nPrefix; (length of prefix shared with previous term)
** varint nSuffix; (length of unshared suffix)
** char pTermSuffix[nSuffix];(unshared suffix of next term)
** varint nDoclist; (length of term's associated doclist)
** char pDoclist[nDoclist]; (content of doclist)
** }
**
** Here, array { X } means zero or more occurrences of X, adjacent in
** memory.
**
** Leaf nodes are broken into blocks which are stored contiguously in
** the %_segments table in sorted order. This means that when the end
** of a node is reached, the next term is in the node with the next
** greater node id.
**
** New data is spilled to a new leaf node when the current node
** exceeds LEAF_MAX bytes (default 2048). New data which itself is
** larger than STANDALONE_MIN (default 1024) is placed in a standalone
** node (a leaf node with a single term and doclist). The goal of
** these settings is to pack together groups of small doclists while
** making it efficient to directly access large doclists. The
** assumption is that large doclists represent terms which are more
** likely to be query targets.
**
** TODO(shess) It may be useful for blocking decisions to be more
** dynamic. For instance, it may make more sense to have a 2.5k leaf
** node rather than splitting into 2k and .5k nodes. My intuition is
** that this might extend through 2x or 4x the pagesize.
**
**
**** Segment interior nodes ****
** Segment interior nodes store blockids for subtree nodes and terms
** to describe what data is stored by the each subtree. Interior
** nodes are written using InteriorWriter, and read using
** InteriorReader. InteriorWriters are created as needed when
** SegmentWriter creates new leaf nodes, or when an interior node
** itself grows too big and must be split. The format of interior
** nodes:
**
** varint iHeight; (height from leaf level, always >0)
** varint iBlockid; (block id of node's leftmost subtree)
** optional {
** varint nTerm; (length of first term)
** char pTerm[nTerm]; (content of first term)
** array {
** (further terms are delta-encoded)
** varint nPrefix; (length of shared prefix with previous term)
** varint nSuffix; (length of unshared suffix)
** char pTermSuffix[nSuffix]; (unshared suffix of next term)
** }
** }
**
** Here, optional { X } means an optional element, while array { X }
** means zero or more occurrences of X, adjacent in memory.
**
** An interior node encodes n terms separating n+1 subtrees. The
** subtree blocks are contiguous, so only the first subtree's blockid
** is encoded. The subtree at iBlockid will contain all terms less
** than the first term encoded (or all terms if no term is encoded).
** Otherwise, for terms greater than or equal to pTerm[i] but less
** than pTerm[i+1], the subtree for that term will be rooted at
** iBlockid+i. Interior nodes only store enough term data to
** distinguish adjacent children (if the rightmost term of the left
** child is "something", and the leftmost term of the right child is
** "wicked", only "w" is stored).
**
** New data is spilled to a new interior node at the same height when
** the current node exceeds INTERIOR_MAX bytes (default 2048).
** INTERIOR_MIN_TERMS (default 7) keeps large terms from monopolizing
** interior nodes and making the tree too skinny. The interior nodes
** at a given height are naturally tracked by interior nodes at
** height+1, and so on.
**
**
**** Segment directory ****
** The segment directory in table %_segdir stores meta-information for
** merging and deleting segments, and also the root node of the
** segment's tree.
**
** The root node is the top node of the segment's tree after encoding
** the entire segment, restricted to ROOT_MAX bytes (default 1024).
** This could be either a leaf node or an interior node. If the top
** node requires more than ROOT_MAX bytes, it is flushed to %_segments
** and a new root interior node is generated (which should always fit
** within ROOT_MAX because it only needs space for 2 varints, the
** height and the blockid of the previous root).
**
** The meta-information in the segment directory is:
** level - segment level (see below)
** idx - index within level
** - (level,idx uniquely identify a segment)
** start_block - first leaf node
** leaves_end_block - last leaf node
** end_block - last block (including interior nodes)
** root - contents of root node
**
** If the root node is a leaf node, then start_block,
** leaves_end_block, and end_block are all 0.
**
**
**** Segment merging ****
** To amortize update costs, segments are grouped into levels and
** merged in batches. Each increase in level represents exponentially
** more documents.
**
** New documents (actually, document updates) are tokenized and
** written individually (using LeafWriter) to a level 0 segment, with
** incrementing idx. When idx reaches MERGE_COUNT (default 16), all
** level 0 segments are merged into a single level 1 segment. Level 1
** is populated like level 0, and eventually MERGE_COUNT level 1
** segments are merged to a single level 2 segment (representing
** MERGE_COUNT^2 updates), and so on.
**
** A segment merge traverses all segments at a given level in
** parallel, performing a straightforward sorted merge. Since segment
** leaf nodes are written in to the %_segments table in order, this
** merge traverses the underlying sqlite disk structures efficiently.
** After the merge, all segment blocks from the merged level are
** deleted.
**
** MERGE_COUNT controls how often we merge segments. 16 seems to be
** somewhat of a sweet spot for insertion performance. 32 and 64 show
** very similar performance numbers to 16 on insertion, though they're
** a tiny bit slower (perhaps due to more overhead in merge-time
** sorting). 8 is about 20% slower than 16, 4 about 50% slower than
** 16, 2 about 66% slower than 16.
**
** At query time, high MERGE_COUNT increases the number of segments
** which need to be scanned and merged. For instance, with 100k docs
** inserted:
**
** MERGE_COUNT segments
** 16 25
** 8 12
** 4 10
** 2 6
**
** This appears to have only a moderate impact on queries for very
** frequent terms (which are somewhat dominated by segment merge
** costs), and infrequent and non-existent terms still seem to be fast
** even with many segments.
**
** TODO(shess) That said, it would be nice to have a better query-side
** argument for MERGE_COUNT of 16. Also, it is possible/likely that
** optimizations to things like doclist merging will swing the sweet
** spot around.
**
**
**
**** Handling of deletions and updates ****
** Since we're using a segmented structure, with no docid-oriented
** index into the term index, we clearly cannot simply update the term
** index when a document is deleted or updated. For deletions, we
** write an empty doclist (varint(docid) varint(POS_END)), for updates
** we simply write the new doclist. Segment merges overwrite older
** data for a particular docid with newer data, so deletes or updates
** will eventually overtake the earlier data and knock it out. The
** query logic likewise merges doclists so that newer data knocks out
** older data.
*/
#include "fts3Int.h"
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
#if defined(SQLITE_ENABLE_FTS3) && !defined(SQLITE_CORE)
# define SQLITE_CORE 1
#endif
#include <assert.h>
#include <stdlib.h>
#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include <stdarg.h>
#include "fts3.h"
#ifndef SQLITE_CORE
# include "sqlite3ext.h"
SQLITE_EXTENSION_INIT1
#endif
static int fts3EvalNext(Fts3Cursor *pCsr);
static int fts3EvalStart(Fts3Cursor *pCsr);
static int fts3TermSegReaderCursor(
Fts3Cursor *, const char *, int, int, Fts3MultiSegReader **);
/*
** Write a 64-bit variable-length integer to memory starting at p[0].
** The length of data written will be between 1 and FTS3_VARINT_MAX bytes.
** The number of bytes written is returned.
*/
int sqlite3Fts3PutVarint(char *p, sqlite_int64 v){
unsigned char *q = (unsigned char *) p;
sqlite_uint64 vu = v;
do{
*q++ = (unsigned char) ((vu & 0x7f) | 0x80);
vu >>= 7;
}while( vu!=0 );
q[-1] &= 0x7f; /* turn off high bit in final byte */
assert( q - (unsigned char *)p <= FTS3_VARINT_MAX );
return (int) (q - (unsigned char *)p);
}
/*
** Read a 64-bit variable-length integer from memory starting at p[0].
** Return the number of bytes read, or 0 on error.
** The value is stored in *v.
*/
int sqlite3Fts3GetVarint(const char *p, sqlite_int64 *v){
const unsigned char *q = (const unsigned char *) p;
sqlite_uint64 x = 0, y = 1;
while( (*q&0x80)==0x80 && q-(unsigned char *)p<FTS3_VARINT_MAX ){
x += y * (*q++ & 0x7f);
y <<= 7;
}
x += y * (*q++);
*v = (sqlite_int64) x;
return (int) (q - (unsigned char *)p);
}
/*
** Similar to sqlite3Fts3GetVarint(), except that the output is truncated to a
** 32-bit integer before it is returned.
*/
int sqlite3Fts3GetVarint32(const char *p, int *pi){
sqlite_int64 i;
int ret = sqlite3Fts3GetVarint(p, &i);
*pi = (int) i;
return ret;
}
/*
** Return the number of bytes required to encode v as a varint
*/
int sqlite3Fts3VarintLen(sqlite3_uint64 v){
int i = 0;
do{
i++;
v >>= 7;
}while( v!=0 );
return i;
}
/*
** Convert an SQL-style quoted string into a normal string by removing
** the quote characters. The conversion is done in-place. If the
** input does not begin with a quote character, then this routine
** is a no-op.
**
** Examples:
**
** "abc" becomes abc
** 'xyz' becomes xyz
** [pqr] becomes pqr
** `mno` becomes mno
**
*/
void sqlite3Fts3Dequote(char *z){
char quote; /* Quote character (if any ) */
quote = z[0];
if( quote=='[' || quote=='\'' || quote=='"' || quote=='`' ){
int iIn = 1; /* Index of next byte to read from input */
int iOut = 0; /* Index of next byte to write to output */
/* If the first byte was a '[', then the close-quote character is a ']' */
if( quote=='[' ) quote = ']';
while( ALWAYS(z[iIn]) ){
if( z[iIn]==quote ){
if( z[iIn+1]!=quote ) break;
z[iOut++] = quote;
iIn += 2;
}else{
z[iOut++] = z[iIn++];
}
}
z[iOut] = '\0';
}
}
/*
** Read a single varint from the doclist at *pp and advance *pp to point
** to the first byte past the end of the varint. Add the value of the varint
** to *pVal.
*/
static void fts3GetDeltaVarint(char **pp, sqlite3_int64 *pVal){
sqlite3_int64 iVal;
*pp += sqlite3Fts3GetVarint(*pp, &iVal);
*pVal += iVal;
}
/*
** When this function is called, *pp points to the first byte following a
** varint that is part of a doclist (or position-list, or any other list
** of varints). This function moves *pp to point to the start of that varint,
** and sets *pVal by the varint value.
**
** Argument pStart points to the first byte of the doclist that the
** varint is part of.
*/
static void fts3GetReverseVarint(
char **pp,
char *pStart,
sqlite3_int64 *pVal
){
sqlite3_int64 iVal;
char *p;
/* Pointer p now points at the first byte past the varint we are
** interested in. So, unless the doclist is corrupt, the 0x80 bit is
** clear on character p[-1]. */
for(p = (*pp)-2; p>=pStart && *p&0x80; p--);
p++;
*pp = p;
sqlite3Fts3GetVarint(p, &iVal);
*pVal = iVal;
}
/*
** The xDisconnect() virtual table method.
*/
static int fts3DisconnectMethod(sqlite3_vtab *pVtab){
Fts3Table *p = (Fts3Table *)pVtab;
int i;
assert( p->nPendingData==0 );
assert( p->pSegments==0 );
/* Free any prepared statements held */
for(i=0; i<SizeofArray(p->aStmt); i++){
sqlite3_finalize(p->aStmt[i]);
}
sqlite3_free(p->zSegmentsTbl);
sqlite3_free(p->zReadExprlist);
sqlite3_free(p->zWriteExprlist);
sqlite3_free(p->zContentTbl);
sqlite3_free(p->zLanguageid);
/* Invoke the tokenizer destructor to free the tokenizer. */
p->pTokenizer->pModule->xDestroy(p->pTokenizer);
sqlite3_free(p);
return SQLITE_OK;
}
/*
** Construct one or more SQL statements from the format string given
** and then evaluate those statements. The success code is written
** into *pRc.
**
** If *pRc is initially non-zero then this routine is a no-op.
*/
static void fts3DbExec(
int *pRc, /* Success code */
sqlite3 *db, /* Database in which to run SQL */
const char *zFormat, /* Format string for SQL */
... /* Arguments to the format string */
){
va_list ap;
char *zSql;
if( *pRc ) return;
va_start(ap, zFormat);
zSql = sqlite3_vmprintf(zFormat, ap);
va_end(ap);
if( zSql==0 ){
*pRc = SQLITE_NOMEM;
}else{
*pRc = sqlite3_exec(db, zSql, 0, 0, 0);
sqlite3_free(zSql);
}
}
/*
** The xDestroy() virtual table method.
*/
static int fts3DestroyMethod(sqlite3_vtab *pVtab){
Fts3Table *p = (Fts3Table *)pVtab;
int rc = SQLITE_OK; /* Return code */
const char *zDb = p->zDb; /* Name of database (e.g. "main", "temp") */
sqlite3 *db = p->db; /* Database handle */
/* Drop the shadow tables */
if( p->zContentTbl==0 ){
fts3DbExec(&rc, db, "DROP TABLE IF EXISTS %Q.'%q_content'", zDb, p->zName);
}
fts3DbExec(&rc, db, "DROP TABLE IF EXISTS %Q.'%q_segments'", zDb,p->zName);
fts3DbExec(&rc, db, "DROP TABLE IF EXISTS %Q.'%q_segdir'", zDb, p->zName);
fts3DbExec(&rc, db, "DROP TABLE IF EXISTS %Q.'%q_docsize'", zDb, p->zName);
fts3DbExec(&rc, db, "DROP TABLE IF EXISTS %Q.'%q_stat'", zDb, p->zName);
/* If everything has worked, invoke fts3DisconnectMethod() to free the
** memory associated with the Fts3Table structure and return SQLITE_OK.
** Otherwise, return an SQLite error code.
*/
return (rc==SQLITE_OK ? fts3DisconnectMethod(pVtab) : rc);
}
/*
** Invoke sqlite3_declare_vtab() to declare the schema for the FTS3 table
** passed as the first argument. This is done as part of the xConnect()
** and xCreate() methods.
**
** If *pRc is non-zero when this function is called, it is a no-op.
** Otherwise, if an error occurs, an SQLite error code is stored in *pRc
** before returning.
*/
static void fts3DeclareVtab(int *pRc, Fts3Table *p){
if( *pRc==SQLITE_OK ){
int i; /* Iterator variable */
int rc; /* Return code */
char *zSql; /* SQL statement passed to declare_vtab() */
char *zCols; /* List of user defined columns */
const char *zLanguageid;
zLanguageid = (p->zLanguageid ? p->zLanguageid : "__langid");
sqlite3_vtab_config(p->db, SQLITE_VTAB_CONSTRAINT_SUPPORT, 1);
/* Create a list of user columns for the virtual table */
zCols = sqlite3_mprintf("%Q, ", p->azColumn[0]);
for(i=1; zCols && i<p->nColumn; i++){
zCols = sqlite3_mprintf("%z%Q, ", zCols, p->azColumn[i]);
}
/* Create the whole "CREATE TABLE" statement to pass to SQLite */
zSql = sqlite3_mprintf(
"CREATE TABLE x(%s %Q HIDDEN, docid HIDDEN, %Q HIDDEN)",
zCols, p->zName, zLanguageid
);
if( !zCols || !zSql ){
rc = SQLITE_NOMEM;
}else{
rc = sqlite3_declare_vtab(p->db, zSql);
}
sqlite3_free(zSql);
sqlite3_free(zCols);
*pRc = rc;
}
}
/*
** Create the %_stat table if it does not already exist.
*/
void sqlite3Fts3CreateStatTable(int *pRc, Fts3Table *p){
fts3DbExec(pRc, p->db,
"CREATE TABLE IF NOT EXISTS %Q.'%q_stat'"
"(id INTEGER PRIMARY KEY, value BLOB);",
p->zDb, p->zName
);
if( (*pRc)==SQLITE_OK ) p->bHasStat = 1;
}
/*
** Create the backing store tables (%_content, %_segments and %_segdir)
** required by the FTS3 table passed as the only argument. This is done
** as part of the vtab xCreate() method.
**
** If the p->bHasDocsize boolean is true (indicating that this is an
** FTS4 table, not an FTS3 table) then also create the %_docsize and
** %_stat tables required by FTS4.
*/
static int fts3CreateTables(Fts3Table *p){
int rc = SQLITE_OK; /* Return code */
int i; /* Iterator variable */
sqlite3 *db = p->db; /* The database connection */
if( p->zContentTbl==0 ){
const char *zLanguageid = p->zLanguageid;
char *zContentCols; /* Columns of %_content table */
/* Create a list of user columns for the content table */
zContentCols = sqlite3_mprintf("docid INTEGER PRIMARY KEY");
for(i=0; zContentCols && i<p->nColumn; i++){
char *z = p->azColumn[i];
zContentCols = sqlite3_mprintf("%z, 'c%d%q'", zContentCols, i, z);
}
if( zLanguageid && zContentCols ){
zContentCols = sqlite3_mprintf("%z, langid", zContentCols, zLanguageid);
}
if( zContentCols==0 ) rc = SQLITE_NOMEM;
/* Create the content table */
fts3DbExec(&rc, db,
"CREATE TABLE %Q.'%q_content'(%s)",
p->zDb, p->zName, zContentCols
);
sqlite3_free(zContentCols);
}
/* Create other tables */
fts3DbExec(&rc, db,
"CREATE TABLE %Q.'%q_segments'(blockid INTEGER PRIMARY KEY, block BLOB);",
p->zDb, p->zName
);
fts3DbExec(&rc, db,
"CREATE TABLE %Q.'%q_segdir'("
"level INTEGER,"
"idx INTEGER,"
"start_block INTEGER,"
"leaves_end_block INTEGER,"
"end_block INTEGER,"
"root BLOB,"
"PRIMARY KEY(level, idx)"
");",
p->zDb, p->zName
);
if( p->bHasDocsize ){
fts3DbExec(&rc, db,
"CREATE TABLE %Q.'%q_docsize'(docid INTEGER PRIMARY KEY, size BLOB);",
p->zDb, p->zName
);
}
assert( p->bHasStat==p->bFts4 );
if( p->bHasStat ){
sqlite3Fts3CreateStatTable(&rc, p);
}
return rc;
}
/*
** Store the current database page-size in bytes in p->nPgsz.
**
** If *pRc is non-zero when this function is called, it is a no-op.
** Otherwise, if an error occurs, an SQLite error code is stored in *pRc
** before returning.
*/
static void fts3DatabasePageSize(int *pRc, Fts3Table *p){
if( *pRc==SQLITE_OK ){
int rc; /* Return code */
char *zSql; /* SQL text "PRAGMA %Q.page_size" */
sqlite3_stmt *pStmt; /* Compiled "PRAGMA %Q.page_size" statement */
zSql = sqlite3_mprintf("PRAGMA %Q.page_size", p->zDb);
if( !zSql ){
rc = SQLITE_NOMEM;
}else{
rc = sqlite3_prepare(p->db, zSql, -1, &pStmt, 0);
if( rc==SQLITE_OK ){
sqlite3_step(pStmt);
p->nPgsz = sqlite3_column_int(pStmt, 0);
rc = sqlite3_finalize(pStmt);
}else if( rc==SQLITE_AUTH ){
p->nPgsz = 1024;
rc = SQLITE_OK;
}
}
assert( p->nPgsz>0 || rc!=SQLITE_OK );
sqlite3_free(zSql);
*pRc = rc;
}
}
/*
** "Special" FTS4 arguments are column specifications of the following form:
**
** <key> = <value>
**
** There may not be whitespace surrounding the "=" character. The <value>
** term may be quoted, but the <key> may not.
*/
static int fts3IsSpecialColumn(
const char *z,
int *pnKey,
char **pzValue
){
char *zValue;
const char *zCsr = z;
while( *zCsr!='=' ){
if( *zCsr=='\0' ) return 0;
zCsr++;
}
*pnKey = (int)(zCsr-z);
zValue = sqlite3_mprintf("%s", &zCsr[1]);
if( zValue ){
sqlite3Fts3Dequote(zValue);
}
*pzValue = zValue;
return 1;
}
/*
** Append the output of a printf() style formatting to an existing string.
*/
static void fts3Appendf(
int *pRc, /* IN/OUT: Error code */
char **pz, /* IN/OUT: Pointer to string buffer */
const char *zFormat, /* Printf format string to append */
... /* Arguments for printf format string */
){
if( *pRc==SQLITE_OK ){
va_list ap;
char *z;
va_start(ap, zFormat);
z = sqlite3_vmprintf(zFormat, ap);
va_end(ap);
if( z && *pz ){
char *z2 = sqlite3_mprintf("%s%s", *pz, z);
sqlite3_free(z);
z = z2;
}
if( z==0 ) *pRc = SQLITE_NOMEM;
sqlite3_free(*pz);
*pz = z;
}
}
/*
** Return a copy of input string zInput enclosed in double-quotes (") and
** with all double quote characters escaped. For example:
**
** fts3QuoteId("un \"zip\"") -> "un \"\"zip\"\""
**
** The pointer returned points to memory obtained from sqlite3_malloc(). It
** is the callers responsibility to call sqlite3_free() to release this
** memory.
*/
static char *fts3QuoteId(char const *zInput){
int nRet;
char *zRet;
nRet = 2 + (int)strlen(zInput)*2 + 1;
zRet = sqlite3_malloc(nRet);
if( zRet ){
int i;
char *z = zRet;
*(z++) = '"';
for(i=0; zInput[i]; i++){
if( zInput[i]=='"' ) *(z++) = '"';
*(z++) = zInput[i];
}
*(z++) = '"';
*(z++) = '\0';
}
return zRet;
}
/*
** Return a list of comma separated SQL expressions and a FROM clause that
** could be used in a SELECT statement such as the following:
**
** SELECT <list of expressions> FROM %_content AS x ...
**
** to return the docid, followed by each column of text data in order
** from left to write. If parameter zFunc is not NULL, then instead of
** being returned directly each column of text data is passed to an SQL
** function named zFunc first. For example, if zFunc is "unzip" and the
** table has the three user-defined columns "a", "b", and "c", the following
** string is returned:
**
** "docid, unzip(x.'a'), unzip(x.'b'), unzip(x.'c') FROM %_content AS x"
**
** The pointer returned points to a buffer allocated by sqlite3_malloc(). It
** is the responsibility of the caller to eventually free it.
**
** If *pRc is not SQLITE_OK when this function is called, it is a no-op (and
** a NULL pointer is returned). Otherwise, if an OOM error is encountered
** by this function, NULL is returned and *pRc is set to SQLITE_NOMEM. If
** no error occurs, *pRc is left unmodified.
*/
static char *fts3ReadExprList(Fts3Table *p, const char *zFunc, int *pRc){
char *zRet = 0;
char *zFree = 0;
char *zFunction;
int i;
if( p->zContentTbl==0 ){
if( !zFunc ){
zFunction = "";
}else{
zFree = zFunction = fts3QuoteId(zFunc);
}
fts3Appendf(pRc, &zRet, "docid");
for(i=0; i<p->nColumn; i++){
fts3Appendf(pRc, &zRet, ",%s(x.'c%d%q')", zFunction, i, p->azColumn[i]);
}
if( p->zLanguageid ){
fts3Appendf(pRc, &zRet, ", x.%Q", "langid");
}
sqlite3_free(zFree);
}else{
fts3Appendf(pRc, &zRet, "rowid");
for(i=0; i<p->nColumn; i++){
fts3Appendf(pRc, &zRet, ", x.'%q'", p->azColumn[i]);
}
if( p->zLanguageid ){
fts3Appendf(pRc, &zRet, ", x.%Q", p->zLanguageid);
}
}
fts3Appendf(pRc, &zRet, " FROM '%q'.'%q%s' AS x",
p->zDb,
(p->zContentTbl ? p->zContentTbl : p->zName),
(p->zContentTbl ? "" : "_content")
);
return zRet;
}
/*
** Return a list of N comma separated question marks, where N is the number
** of columns in the %_content table (one for the docid plus one for each
** user-defined text column).
**
** If argument zFunc is not NULL, then all but the first question mark
** is preceded by zFunc and an open bracket, and followed by a closed
** bracket. For example, if zFunc is "zip" and the FTS3 table has three
** user-defined text columns, the following string is returned:
**
** "?, zip(?), zip(?), zip(?)"
**
** The pointer returned points to a buffer allocated by sqlite3_malloc(). It
** is the responsibility of the caller to eventually free it.
**
** If *pRc is not SQLITE_OK when this function is called, it is a no-op (and
** a NULL pointer is returned). Otherwise, if an OOM error is encountered
** by this function, NULL is returned and *pRc is set to SQLITE_NOMEM. If
** no error occurs, *pRc is left unmodified.
*/
static char *fts3WriteExprList(Fts3Table *p, const char *zFunc, int *pRc){
char *zRet = 0;
char *zFree = 0;
char *zFunction;
int i;
if( !zFunc ){
zFunction = "";
}else{
zFree = zFunction = fts3QuoteId(zFunc);
}
fts3Appendf(pRc, &zRet, "?");
for(i=0; i<p->nColumn; i++){
fts3Appendf(pRc, &zRet, ",%s(?)", zFunction);
}
if( p->zLanguageid ){
fts3Appendf(pRc, &zRet, ", ?");
}
sqlite3_free(zFree);
return zRet;
}
/*
** This function interprets the string at (*pp) as a non-negative integer
** value. It reads the integer and sets *pnOut to the value read, then
** sets *pp to point to the byte immediately following the last byte of
** the integer value.
**
** Only decimal digits ('0'..'9') may be part of an integer value.
**
** If *pp does not being with a decimal digit SQLITE_ERROR is returned and
** the output value undefined. Otherwise SQLITE_OK is returned.
**
** This function is used when parsing the "prefix=" FTS4 parameter.
*/
static int fts3GobbleInt(const char **pp, int *pnOut){
const char *p; /* Iterator pointer */
int nInt = 0; /* Output value */
for(p=*pp; p[0]>='0' && p[0]<='9'; p++){
nInt = nInt * 10 + (p[0] - '0');
}
if( p==*pp ) return SQLITE_ERROR;
*pnOut = nInt;
*pp = p;
return SQLITE_OK;
}
/*
** This function is called to allocate an array of Fts3Index structures
** representing the indexes maintained by the current FTS table. FTS tables
** always maintain the main "terms" index, but may also maintain one or
** more "prefix" indexes, depending on the value of the "prefix=" parameter
** (if any) specified as part of the CREATE VIRTUAL TABLE statement.
**
** Argument zParam is passed the value of the "prefix=" option if one was
** specified, or NULL otherwise.
**
** If no error occurs, SQLITE_OK is returned and *apIndex set to point to
** the allocated array. *pnIndex is set to the number of elements in the
** array. If an error does occur, an SQLite error code is returned.
**
** Regardless of whether or not an error is returned, it is the responsibility
** of the caller to call sqlite3_free() on the output array to free it.
*/
static int fts3PrefixParameter(
const char *zParam, /* ABC in prefix=ABC parameter to parse */
int *pnIndex, /* OUT: size of *apIndex[] array */
struct Fts3Index **apIndex /* OUT: Array of indexes for this table */
){
struct Fts3Index *aIndex; /* Allocated array */
int nIndex = 1; /* Number of entries in array */
if( zParam && zParam[0] ){
const char *p;
nIndex++;
for(p=zParam; *p; p++){
if( *p==',' ) nIndex++;
}
}
aIndex = sqlite3_malloc(sizeof(struct Fts3Index) * nIndex);
*apIndex = aIndex;
*pnIndex = nIndex;
if( !aIndex ){
return SQLITE_NOMEM;
}
memset(aIndex, 0, sizeof(struct Fts3Index) * nIndex);
if( zParam ){
const char *p = zParam;
int i;
for(i=1; i<nIndex; i++){
int nPrefix;
if( fts3GobbleInt(&p, &nPrefix) ) return SQLITE_ERROR;
aIndex[i].nPrefix = nPrefix;
p++;
}
}
return SQLITE_OK;
}
/*
** This function is called when initializing an FTS4 table that uses the
** content=xxx option. It determines the number of and names of the columns
** of the new FTS4 table.
**
** The third argument passed to this function is the value passed to the
** config=xxx option (i.e. "xxx"). This function queries the database for
** a table of that name. If found, the output variables are populated
** as follows:
**
** *pnCol: Set to the number of columns table xxx has,
**
** *pnStr: Set to the total amount of space required to store a copy
** of each columns name, including the nul-terminator.
**
** *pazCol: Set to point to an array of *pnCol strings. Each string is
** the name of the corresponding column in table xxx. The array
** and its contents are allocated using a single allocation. It
** is the responsibility of the caller to free this allocation
** by eventually passing the *pazCol value to sqlite3_free().
**
** If the table cannot be found, an error code is returned and the output
** variables are undefined. Or, if an OOM is encountered, SQLITE_NOMEM is
** returned (and the output variables are undefined).
*/
static int fts3ContentColumns(
sqlite3 *db, /* Database handle */
const char *zDb, /* Name of db (i.e. "main", "temp" etc.) */
const char *zTbl, /* Name of content table */
const char ***pazCol, /* OUT: Malloc'd array of column names */
int *pnCol, /* OUT: Size of array *pazCol */
int *pnStr /* OUT: Bytes of string content */
){
int rc = SQLITE_OK; /* Return code */
char *zSql; /* "SELECT *" statement on zTbl */
sqlite3_stmt *pStmt = 0; /* Compiled version of zSql */
zSql = sqlite3_mprintf("SELECT * FROM %Q.%Q", zDb, zTbl);
if( !zSql ){
rc = SQLITE_NOMEM;
}else{
rc = sqlite3_prepare(db, zSql, -1, &pStmt, 0);
}
sqlite3_free(zSql);
if( rc==SQLITE_OK ){
const char **azCol; /* Output array */
int nStr = 0; /* Size of all column names (incl. 0x00) */