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
|
/*
** The author disclaims copyright to this source code.
**
*************************************************************************
** Implementation of the "simple" full-text-search tokenizer.
*/
#include <assert.h>
#if !defined(__APPLE__)
#include <malloc.h>
#else
#include <stdlib.h>
#endif
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include "tokenizer.h"
/* Duplicate a string; the caller must free() the returned string.
* (We don't use strdup() since it's not part of the standard C library and
* may not be available everywhere.) */
/* TODO(shess) Copied from fulltext.c, consider util.c for such
** things. */
static char *string_dup(const char *s){
char *str = malloc(strlen(s) + 1);
strcpy(str, s);
return str;
}
typedef struct simple_tokenizer {
sqlite3_tokenizer base;
const char *zDelim; /* token delimiters */
} simple_tokenizer;
typedef struct simple_tokenizer_cursor {
sqlite3_tokenizer_cursor base;
const char *pInput; /* input we are tokenizing */
int nBytes; /* size of the input */
const char *pCurrent; /* current position in pInput */
int iToken; /* index of next token to be returned */
char *zToken; /* storage for current token */
int nTokenBytes; /* actual size of current token */
int nTokenAllocated; /* space allocated to zToken buffer */
} simple_tokenizer_cursor;
static sqlite3_tokenizer_module simpleTokenizerModule;/* forward declaration */
static int simpleCreate(
int argc, const char **argv,
sqlite3_tokenizer **ppTokenizer
){
simple_tokenizer *t;
t = (simple_tokenizer *) malloc(sizeof(simple_tokenizer));
/* TODO(shess) Delimiters need to remain the same from run to run,
** else we need to reindex. One solution would be a meta-table to
** track such information in the database, then we'd only want this
** information on the initial create.
*/
if( argc>1 ){
t->zDelim = string_dup(argv[1]);
} else {
/* Build a string excluding alphanumeric ASCII characters */
char zDelim[0x80]; /* nul-terminated, so nul not a member */
int i, j;
for(i=1, j=0; i<0x80; i++){
if( !isalnum(i) ){
zDelim[j++] = i;
}
}
zDelim[j++] = '\0';
assert( j<=sizeof(zDelim) );
t->zDelim = string_dup(zDelim);
}
*ppTokenizer = &t->base;
return SQLITE_OK;
}
static int simpleDestroy(sqlite3_tokenizer *pTokenizer){
simple_tokenizer *t = (simple_tokenizer *) pTokenizer;
free((void *) t->zDelim);
free(t);
return SQLITE_OK;
}
static int simpleOpen(
sqlite3_tokenizer *pTokenizer,
const char *pInput, int nBytes,
sqlite3_tokenizer_cursor **ppCursor
){
simple_tokenizer_cursor *c;
c = (simple_tokenizer_cursor *) malloc(sizeof(simple_tokenizer_cursor));
c->pInput = pInput;
c->nBytes = nBytes<0 ? (int) strlen(pInput) : nBytes;
c->pCurrent = c->pInput; /* start tokenizing at the beginning */
c->iToken = 0;
c->zToken = NULL; /* no space allocated, yet. */
c->nTokenBytes = 0;
c->nTokenAllocated = 0;
*ppCursor = &c->base;
return SQLITE_OK;
}
static int simpleClose(sqlite3_tokenizer_cursor *pCursor){
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
if( NULL!=c->zToken ){
free(c->zToken);
}
free(c);
return SQLITE_OK;
}
static int simpleNext(
sqlite3_tokenizer_cursor *pCursor,
const char **ppToken, int *pnBytes,
int *piStartOffset, int *piEndOffset, int *piPosition
){
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
simple_tokenizer *t = (simple_tokenizer *) pCursor->pTokenizer;
int ii;
while( c->pCurrent-c->pInput<c->nBytes ){
int n = (int) strcspn(c->pCurrent, t->zDelim);
if( n>0 ){
if( n+1>c->nTokenAllocated ){
c->zToken = realloc(c->zToken, n+1);
}
for(ii=0; ii<n; ii++){
/* TODO(shess) This needs expansion to handle UTF-8
** case-insensitivity.
*/
char ch = c->pCurrent[ii];
c->zToken[ii] = (unsigned char)ch<0x80 ? tolower((unsigned char)ch):ch;
}
c->zToken[n] = '\0';
*ppToken = c->zToken;
*pnBytes = n;
*piStartOffset = (int) (c->pCurrent-c->pInput);
*piEndOffset = *piStartOffset+n;
*piPosition = c->iToken++;
c->pCurrent += n + 1;
return SQLITE_OK;
}
c->pCurrent += n + 1;
/* TODO(shess) could strspn() to skip delimiters en masse. Needs
** to happen in two places, though, which is annoying.
*/
}
return SQLITE_DONE;
}
static sqlite3_tokenizer_module simpleTokenizerModule = {
0,
simpleCreate,
simpleDestroy,
simpleOpen,
simpleClose,
simpleNext,
};
void get_simple_tokenizer_module(
sqlite3_tokenizer_module **ppModule
){
*ppModule = &simpleTokenizerModule;
}
|