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
|
/*
** The author disclaims copyright to this source code.
**
*************************************************************************
** Implementation of the "simple" full-text-search tokenizer.
*/
/*
** The code in this file is only compiled if:
**
** * The FTS1 module is being built as an extension
** (in which case SQLITE_CORE is not defined), or
**
** * The FTS1 module is being built into the core of
** SQLite (in which case SQLITE_ENABLE_FTS1 is defined).
*/
#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1)
#include <assert.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include "fts1_tokenizer.h"
typedef struct simple_tokenizer {
sqlite3_tokenizer base;
char delim[128]; /* flag ASCII 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 */
int iOffset; /* current position in pInput */
int iToken; /* index of next token to be returned */
char *pToken; /* storage for current token */
int nTokenAllocated; /* space allocated to zToken buffer */
} simple_tokenizer_cursor;
/* Forward declaration */
static const sqlite3_tokenizer_module simpleTokenizerModule;
static int isDelim(simple_tokenizer *t, unsigned char c){
return c<0x80 && t->delim[c];
}
/*
** Create a new tokenizer instance.
*/
static int simpleCreate(
int argc, const char * const *argv,
sqlite3_tokenizer **ppTokenizer
){
simple_tokenizer *t;
t = (simple_tokenizer *) calloc(sizeof(*t), 1);
if( t==NULL ) return SQLITE_NOMEM;
/* 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 ){
int i, n = strlen(argv[1]);
for(i=0; i<n; i++){
unsigned char ch = argv[1][i];
/* We explicitly don't support UTF-8 delimiters for now. */
if( ch>=0x80 ){
free(t);
return SQLITE_ERROR;
}
t->delim[ch] = 1;
}
} else {
/* Mark non-alphanumeric ASCII characters as delimiters */
int i;
for(i=1; i<0x80; i++){
t->delim[i] = !isalnum(i);
}
}
*ppTokenizer = &t->base;
return SQLITE_OK;
}
/*
** Destroy a tokenizer
*/
static int simpleDestroy(sqlite3_tokenizer *pTokenizer){
free(pTokenizer);
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 simpleOpen(
sqlite3_tokenizer *pTokenizer, /* The tokenizer */
const char *pInput, int nBytes, /* String to be tokenized */
sqlite3_tokenizer_cursor **ppCursor /* OUT: Tokenization cursor */
){
simple_tokenizer_cursor *c;
c = (simple_tokenizer_cursor *) malloc(sizeof(*c));
if( c==NULL ) return SQLITE_NOMEM;
c->pInput = pInput;
if( pInput==0 ){
c->nBytes = 0;
}else if( nBytes<0 ){
c->nBytes = (int)strlen(pInput);
}else{
c->nBytes = nBytes;
}
c->iOffset = 0; /* start tokenizing at the beginning */
c->iToken = 0;
c->pToken = NULL; /* no space allocated, yet. */
c->nTokenAllocated = 0;
*ppCursor = &c->base;
return SQLITE_OK;
}
/*
** Close a tokenization cursor previously opened by a call to
** simpleOpen() above.
*/
static int simpleClose(sqlite3_tokenizer_cursor *pCursor){
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
free(c->pToken);
free(c);
return SQLITE_OK;
}
/*
** Extract the next token from a tokenization cursor. The cursor must
** have been opened by a prior call to simpleOpen().
*/
static int simpleNext(
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 */
){
simple_tokenizer_cursor *c = (simple_tokenizer_cursor *) pCursor;
simple_tokenizer *t = (simple_tokenizer *) pCursor->pTokenizer;
unsigned char *p = (unsigned char *)c->pInput;
while( c->iOffset<c->nBytes ){
int iStartOffset;
/* Scan past delimiter characters */
while( c->iOffset<c->nBytes && isDelim(t, p[c->iOffset]) ){
c->iOffset++;
}
/* Count non-delimiter characters. */
iStartOffset = c->iOffset;
while( c->iOffset<c->nBytes && !isDelim(t, p[c->iOffset]) ){
c->iOffset++;
}
if( c->iOffset>iStartOffset ){
int i, n = c->iOffset-iStartOffset;
if( n>c->nTokenAllocated ){
c->nTokenAllocated = n+20;
c->pToken = realloc(c->pToken, c->nTokenAllocated);
if( c->pToken==NULL ) return SQLITE_NOMEM;
}
for(i=0; i<n; i++){
/* TODO(shess) This needs expansion to handle UTF-8
** case-insensitivity.
*/
unsigned char ch = p[iStartOffset+i];
c->pToken[i] = ch<0x80 ? tolower(ch) : ch;
}
*ppToken = c->pToken;
*pnBytes = n;
*piStartOffset = iStartOffset;
*piEndOffset = c->iOffset;
*piPosition = c->iToken++;
return SQLITE_OK;
}
}
return SQLITE_DONE;
}
/*
** The set of routines that implement the simple tokenizer
*/
static const sqlite3_tokenizer_module simpleTokenizerModule = {
0,
simpleCreate,
simpleDestroy,
simpleOpen,
simpleClose,
simpleNext,
};
/*
** Allocate a new simple tokenizer. Return a pointer to the new
** tokenizer in *ppModule
*/
void sqlite3Fts1SimpleTokenizerModule(
sqlite3_tokenizer_module const**ppModule
){
*ppModule = &simpleTokenizerModule;
}
#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS1) */
|