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
| /*
** 2007 June 22
**
** 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 file implements a tokenizer for fts3 based on the ICU library.
*/
#include "fts3Int.h"
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3)
#ifdef SQLITE_ENABLE_ICU
#include <assert.h>
#include <string.h>
#include "fts3_tokenizer.h"
#include <unicode/ubrk.h>
#include <unicode/ucol.h>
#include <unicode/ustring.h>
#include <unicode/utf16.h>
typedef struct IcuTokenizer IcuTokenizer;
typedef struct IcuCursor IcuCursor;
struct IcuTokenizer {
sqlite3_tokenizer base;
char *zLocale;
};
struct IcuCursor {
sqlite3_tokenizer_cursor base;
UBreakIterator *pIter; /* ICU break-iterator object */
int nChar; /* Number of UChar elements in pInput */
UChar *aChar; /* Copy of input using utf-16 encoding */
int *aOffset; /* Offsets of each character in utf-8 input */
int nBuffer;
char *zBuffer;
int iToken;
};
/*
** Create a new tokenizer instance.
*/
static int icuCreate(
int argc, /* Number of entries in argv[] */
const char * const *argv, /* Tokenizer creation arguments */
sqlite3_tokenizer **ppTokenizer /* OUT: Created tokenizer */
){
IcuTokenizer *p;
int n = 0;
if( argc>0 ){
n = strlen(argv[0])+1;
}
p = (IcuTokenizer *)sqlite3_malloc(sizeof(IcuTokenizer)+n);
if( !p ){
return SQLITE_NOMEM;
}
memset(p, 0, sizeof(IcuTokenizer));
if( n ){
p->zLocale = (char *)&p[1];
memcpy(p->zLocale, argv[0], n);
}
*ppTokenizer = (sqlite3_tokenizer *)p;
return SQLITE_OK;
}
/*
** Destroy a tokenizer
*/
static int icuDestroy(sqlite3_tokenizer *pTokenizer){
IcuTokenizer *p = (IcuTokenizer *)pTokenizer;
sqlite3_free(p);
return SQLITE_OK;
}
/*
** Prepare to begin tokenizing a particular string. The input
** string to be tokenized is pInput[0..nBytes-1]. A cursor
** used to incrementally tokenize this string is returned in
** *ppCursor.
*/
static int icuOpen(
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
const char *zInput, /* Input string */
int nInput, /* Length of zInput in bytes */
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
){
IcuTokenizer *p = (IcuTokenizer *)pTokenizer;
IcuCursor *pCsr;
const int32_t opt = U_FOLD_CASE_DEFAULT;
UErrorCode status = U_ZERO_ERROR;
int nChar;
UChar32 c;
int iInput = 0;
int iOut = 0;
*ppCursor = 0;
if( zInput==0 ){
nInput = 0;
zInput = "";
}else if( nInput<0 ){
nInput = strlen(zInput);
}
nChar = nInput+1;
pCsr = (IcuCursor *)sqlite3_malloc(
sizeof(IcuCursor) + /* IcuCursor */
((nChar+3)&~3) * sizeof(UChar) + /* IcuCursor.aChar[] */
(nChar+1) * sizeof(int) /* IcuCursor.aOffset[] */
);
if( !pCsr ){
return SQLITE_NOMEM;
}
memset(pCsr, 0, sizeof(IcuCursor));
pCsr->aChar = (UChar *)&pCsr[1];
pCsr->aOffset = (int *)&pCsr->aChar[(nChar+3)&~3];
pCsr->aOffset[iOut] = iInput;
U8_NEXT(zInput, iInput, nInput, c);
while( c>0 ){
int isError = 0;
c = u_foldCase(c, opt);
U16_APPEND(pCsr->aChar, iOut, nChar, c, isError);
if( isError ){
sqlite3_free(pCsr);
return SQLITE_ERROR;
}
pCsr->aOffset[iOut] = iInput;
if( iInput<nInput ){
U8_NEXT(zInput, iInput, nInput, c);
}else{
c = 0;
}
}
pCsr->pIter = ubrk_open(UBRK_WORD, p->zLocale, pCsr->aChar, iOut, &status);
if( !U_SUCCESS(status) ){
sqlite3_free(pCsr);
return SQLITE_ERROR;
}
pCsr->nChar = iOut;
ubrk_first(pCsr->pIter);
*ppCursor = (sqlite3_tokenizer_cursor *)pCsr;
return SQLITE_OK;
}
/*
** Close a tokenization cursor previously opened by a call to icuOpen().
*/
static int icuClose(sqlite3_tokenizer_cursor *pCursor){
IcuCursor *pCsr = (IcuCursor *)pCursor;
ubrk_close(pCsr->pIter);
sqlite3_free(pCsr->zBuffer);
sqlite3_free(pCsr);
return SQLITE_OK;
}
/*
** Extract the next token from a tokenization cursor.
*/
static int icuNext(
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by simpleOpen */
const char **ppToken, /* OUT: *ppToken is the token text */
int *pnBytes, /* OUT: Number of bytes in token */
int *piStartOffset, /* OUT: Starting offset of token */
int *piEndOffset, /* OUT: Ending offset of token */
int *piPosition /* OUT: Position integer of token */
){
IcuCursor *pCsr = (IcuCursor *)pCursor;
int iStart = 0;
int iEnd = 0;
int nByte = 0;
while( iStart==iEnd ){
UChar32 c;
iStart = ubrk_current(pCsr->pIter);
iEnd = ubrk_next(pCsr->pIter);
if( iEnd==UBRK_DONE ){
return SQLITE_DONE;
}
while( iStart<iEnd ){
int iWhite = iStart;
U16_NEXT(pCsr->aChar, iWhite, pCsr->nChar, c);
if( u_isspace(c) ){
iStart = iWhite;
}else{
break;
}
}
assert(iStart<=iEnd);
}
do {
UErrorCode status = U_ZERO_ERROR;
if( nByte ){
char *zNew = sqlite3_realloc(pCsr->zBuffer, nByte);
if( !zNew ){
return SQLITE_NOMEM;
}
pCsr->zBuffer = zNew;
pCsr->nBuffer = nByte;
}
u_strToUTF8(
pCsr->zBuffer, pCsr->nBuffer, &nByte, /* Output vars */
&pCsr->aChar[iStart], iEnd-iStart, /* Input vars */
&status /* Output success/failure */
);
} while( nByte>pCsr->nBuffer );
*ppToken = pCsr->zBuffer;
*pnBytes = nByte;
*piStartOffset = pCsr->aOffset[iStart];
*piEndOffset = pCsr->aOffset[iEnd];
*piPosition = pCsr->iToken++;
return SQLITE_OK;
}
/*
** The set of routines that implement the simple tokenizer
*/
static const sqlite3_tokenizer_module icuTokenizerModule = {
0, /* iVersion */
icuCreate, /* xCreate */
icuDestroy, /* xCreate */
icuOpen, /* xOpen */
icuClose, /* xClose */
icuNext, /* xNext */
};
/*
** Set *ppModule to point at the implementation of the ICU tokenizer.
*/
void sqlite3Fts3IcuTokenizerModule(
sqlite3_tokenizer_module const**ppModule
){
*ppModule = &icuTokenizerModule;
}
#endif /* defined(SQLITE_ENABLE_ICU) */
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */
|