sqllogictest
Check-in [f0b45ac9a5]
Not logged in

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

Overview
Comment:Update the built-in SQLite to the first 3.9.0 beta.
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: f0b45ac9a5f96f9c8f3b5c97f1ce6d3d5ac8b862
User & Date: drh 2015-10-10 13:45:35
Context
2015-10-10
18:53
Another SQLite 3.9.0 beta. check-in: 7f101da5c9 user: drh tags: trunk
13:45
Update the built-in SQLite to the first 3.9.0 beta. check-in: f0b45ac9a5 user: drh tags: trunk
2015-10-07
20:51
Update the built-in SQLite to the first 3.8.12 beta. check-in: be219301cd user: drh tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to src/sqlite3.c.

more than 10,000 changes

Changes to src/sqlite3.h.

107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
....
7916
7917
7918
7919
7920
7921
7922
7923

































































































































































































































































































































































































































































































































** string contains the date and time of the check-in (UTC) and an SHA1
** hash of the entire source tree.
**
** See also: [sqlite3_libversion()],
** [sqlite3_libversion_number()], [sqlite3_sourceid()],
** [sqlite_version()] and [sqlite_source_id()].
*/
#define SQLITE_VERSION        "3.8.12"
#define SQLITE_VERSION_NUMBER 3008012
#define SQLITE_SOURCE_ID      "2015-10-07 17:06:17 13adcd038fc20dd1b6f344f79b449b4034f8f8f2"

/*
** CAPI3REF: Run-Time Library Version Numbers
** KEYWORDS: sqlite3_version, sqlite3_sourceid
**
** These interfaces provide the same information as the [SQLITE_VERSION],
** [SQLITE_VERSION_NUMBER], and [SQLITE_SOURCE_ID] C preprocessor macros
................................................................................


#ifdef __cplusplus
}  /* end of the 'extern "C"' block */
#endif

#endif  /* ifndef _SQLITE3RTREE_H_ */









































































































































































































































































































































































































































































































































|
|
|







 








>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
....
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
** string contains the date and time of the check-in (UTC) and an SHA1
** hash of the entire source tree.
**
** See also: [sqlite3_libversion()],
** [sqlite3_libversion_number()], [sqlite3_sourceid()],
** [sqlite_version()] and [sqlite_source_id()].
*/
#define SQLITE_VERSION        "3.9.0"
#define SQLITE_VERSION_NUMBER 3009000
#define SQLITE_SOURCE_ID      "2015-10-09 20:40:44 4a47f0177851721cdf6c981df962b6e8862372e7"

/*
** CAPI3REF: Run-Time Library Version Numbers
** KEYWORDS: sqlite3_version, sqlite3_sourceid
**
** These interfaces provide the same information as the [SQLITE_VERSION],
** [SQLITE_VERSION_NUMBER], and [SQLITE_SOURCE_ID] C preprocessor macros
................................................................................


#ifdef __cplusplus
}  /* end of the 'extern "C"' block */
#endif

#endif  /* ifndef _SQLITE3RTREE_H_ */

/*
** 2014 May 31
**
** 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.
**
******************************************************************************
**
** Interfaces to extend FTS5. Using the interfaces defined in this file, 
** FTS5 may be extended with:
**
**     * custom tokenizers, and
**     * custom auxiliary functions.
*/


#ifndef _FTS5_H
#define _FTS5_H

#include "sqlite3.h"

/*************************************************************************
** CUSTOM AUXILIARY FUNCTIONS
**
** Virtual table implementations may overload SQL functions by implementing
** the sqlite3_module.xFindFunction() method.
*/

typedef struct Fts5ExtensionApi Fts5ExtensionApi;
typedef struct Fts5Context Fts5Context;
typedef struct Fts5PhraseIter Fts5PhraseIter;

typedef void (*fts5_extension_function)(
  const Fts5ExtensionApi *pApi,   /* API offered by current FTS version */
  Fts5Context *pFts,              /* First arg to pass to pApi functions */
  sqlite3_context *pCtx,          /* Context for returning result/error */
  int nVal,                       /* Number of values in apVal[] array */
  sqlite3_value **apVal           /* Array of trailing arguments */
);

struct Fts5PhraseIter {
  const unsigned char *a;
  const unsigned char *b;
};

/*
** EXTENSION API FUNCTIONS
**
** xUserData(pFts):
**   Return a copy of the context pointer the extension function was 
**   registered with.
**
** xColumnTotalSize(pFts, iCol, pnToken):
**   If parameter iCol is less than zero, set output variable *pnToken
**   to the total number of tokens in the FTS5 table. Or, if iCol is
**   non-negative but less than the number of columns in the table, return
**   the total number of tokens in column iCol, considering all rows in 
**   the FTS5 table.
**
**   If parameter iCol is greater than or equal to the number of columns
**   in the table, SQLITE_RANGE is returned. Or, if an error occurs (e.g.
**   an OOM condition or IO error), an appropriate SQLite error code is 
**   returned.
**
** xColumnCount(pFts):
**   Return the number of columns in the table.
**
** xColumnSize(pFts, iCol, pnToken):
**   If parameter iCol is less than zero, set output variable *pnToken
**   to the total number of tokens in the current row. Or, if iCol is
**   non-negative but less than the number of columns in the table, set
**   *pnToken to the number of tokens in column iCol of the current row.
**
**   If parameter iCol is greater than or equal to the number of columns
**   in the table, SQLITE_RANGE is returned. Or, if an error occurs (e.g.
**   an OOM condition or IO error), an appropriate SQLite error code is 
**   returned.
**
** xColumnText:
**   This function attempts to retrieve the text of column iCol of the
**   current document. If successful, (*pz) is set to point to a buffer
**   containing the text in utf-8 encoding, (*pn) is set to the size in bytes
**   (not characters) of the buffer and SQLITE_OK is returned. Otherwise,
**   if an error occurs, an SQLite error code is returned and the final values
**   of (*pz) and (*pn) are undefined.
**
** xPhraseCount:
**   Returns the number of phrases in the current query expression.
**
** xPhraseSize:
**   Returns the number of tokens in phrase iPhrase of the query. Phrases
**   are numbered starting from zero.
**
** xInstCount:
**   Set *pnInst to the total number of occurrences of all phrases within
**   the query within the current row. Return SQLITE_OK if successful, or
**   an error code (i.e. SQLITE_NOMEM) if an error occurs.
**
** xInst:
**   Query for the details of phrase match iIdx within the current row.
**   Phrase matches are numbered starting from zero, so the iIdx argument
**   should be greater than or equal to zero and smaller than the value
**   output by xInstCount().
**
**   Returns SQLITE_OK if successful, or an error code (i.e. SQLITE_NOMEM) 
**   if an error occurs.
**
** xRowid:
**   Returns the rowid of the current row.
**
** xTokenize:
**   Tokenize text using the tokenizer belonging to the FTS5 table.
**
** xQueryPhrase(pFts5, iPhrase, pUserData, xCallback):
**   This API function is used to query the FTS table for phrase iPhrase
**   of the current query. Specifically, a query equivalent to:
**
**       ... FROM ftstable WHERE ftstable MATCH $p ORDER BY rowid
**
**   with $p set to a phrase equivalent to the phrase iPhrase of the
**   current query is executed. For each row visited, the callback function
**   passed as the fourth argument is invoked. The context and API objects 
**   passed to the callback function may be used to access the properties of
**   each matched row. Invoking Api.xUserData() returns a copy of the pointer
**   passed as the third argument to pUserData.
**
**   If the callback function returns any value other than SQLITE_OK, the
**   query is abandoned and the xQueryPhrase function returns immediately.
**   If the returned value is SQLITE_DONE, xQueryPhrase returns SQLITE_OK.
**   Otherwise, the error code is propagated upwards.
**
**   If the query runs to completion without incident, SQLITE_OK is returned.
**   Or, if some error occurs before the query completes or is aborted by
**   the callback, an SQLite error code is returned.
**
**
** xSetAuxdata(pFts5, pAux, xDelete)
**
**   Save the pointer passed as the second argument as the extension functions 
**   "auxiliary data". The pointer may then be retrieved by the current or any
**   future invocation of the same fts5 extension function made as part of
**   of the same MATCH query using the xGetAuxdata() API.
**
**   Each extension function is allocated a single auxiliary data slot for
**   each FTS query (MATCH expression). If the extension function is invoked 
**   more than once for a single FTS query, then all invocations share a 
**   single auxiliary data context.
**
**   If there is already an auxiliary data pointer when this function is
**   invoked, then it is replaced by the new pointer. If an xDelete callback
**   was specified along with the original pointer, it is invoked at this
**   point.
**
**   The xDelete callback, if one is specified, is also invoked on the
**   auxiliary data pointer after the FTS5 query has finished.
**
**   If an error (e.g. an OOM condition) occurs within this function, an
**   the auxiliary data is set to NULL and an error code returned. If the
**   xDelete parameter was not NULL, it is invoked on the auxiliary data
**   pointer before returning.
**
**
** xGetAuxdata(pFts5, bClear)
**
**   Returns the current auxiliary data pointer for the fts5 extension 
**   function. See the xSetAuxdata() method for details.
**
**   If the bClear argument is non-zero, then the auxiliary data is cleared
**   (set to NULL) before this function returns. In this case the xDelete,
**   if any, is not invoked.
**
**
** xRowCount(pFts5, pnRow)
**
**   This function is used to retrieve the total number of rows in the table.
**   In other words, the same value that would be returned by:
**
**        SELECT count(*) FROM ftstable;
**
** xPhraseFirst()
**   This function is used, along with type Fts5PhraseIter and the xPhraseNext
**   method, to iterate through all instances of a single query phrase within
**   the current row. This is the same information as is accessible via the
**   xInstCount/xInst APIs. While the xInstCount/xInst APIs are more convenient
**   to use, this API may be faster under some circumstances. To iterate 
**   through instances of phrase iPhrase, use the following code:
**
**       Fts5PhraseIter iter;
**       int iCol, iOff;
**       for(pApi->xPhraseFirst(pFts, iPhrase, &iter, &iCol, &iOff);
**           iOff>=0;
**           pApi->xPhraseNext(pFts, &iter, &iCol, &iOff)
**       ){
**         // An instance of phrase iPhrase at offset iOff of column iCol
**       }
**
**   The Fts5PhraseIter structure is defined above. Applications should not
**   modify this structure directly - it should only be used as shown above
**   with the xPhraseFirst() and xPhraseNext() API methods.
**
** xPhraseNext()
**   See xPhraseFirst above.
*/
struct Fts5ExtensionApi {
  int iVersion;                   /* Currently always set to 1 */

  void *(*xUserData)(Fts5Context*);

  int (*xColumnCount)(Fts5Context*);
  int (*xRowCount)(Fts5Context*, sqlite3_int64 *pnRow);
  int (*xColumnTotalSize)(Fts5Context*, int iCol, sqlite3_int64 *pnToken);

  int (*xTokenize)(Fts5Context*, 
    const char *pText, int nText, /* Text to tokenize */
    void *pCtx,                   /* Context passed to xToken() */
    int (*xToken)(void*, int, const char*, int, int, int)       /* Callback */
  );

  int (*xPhraseCount)(Fts5Context*);
  int (*xPhraseSize)(Fts5Context*, int iPhrase);

  int (*xInstCount)(Fts5Context*, int *pnInst);
  int (*xInst)(Fts5Context*, int iIdx, int *piPhrase, int *piCol, int *piOff);

  sqlite3_int64 (*xRowid)(Fts5Context*);
  int (*xColumnText)(Fts5Context*, int iCol, const char **pz, int *pn);
  int (*xColumnSize)(Fts5Context*, int iCol, int *pnToken);

  int (*xQueryPhrase)(Fts5Context*, int iPhrase, void *pUserData,
    int(*)(const Fts5ExtensionApi*,Fts5Context*,void*)
  );
  int (*xSetAuxdata)(Fts5Context*, void *pAux, void(*xDelete)(void*));
  void *(*xGetAuxdata)(Fts5Context*, int bClear);

  void (*xPhraseFirst)(Fts5Context*, int iPhrase, Fts5PhraseIter*, int*, int*);
  void (*xPhraseNext)(Fts5Context*, Fts5PhraseIter*, int *piCol, int *piOff);
};

/* 
** CUSTOM AUXILIARY FUNCTIONS
*************************************************************************/

/*************************************************************************
** CUSTOM TOKENIZERS
**
** Applications may also register custom tokenizer types. A tokenizer 
** is registered by providing fts5 with a populated instance of the 
** following structure. All structure methods must be defined, setting
** any member of the fts5_tokenizer struct to NULL leads to undefined
** behaviour. The structure methods are expected to function as follows:
**
** xCreate:
**   This function is used to allocate and inititalize a tokenizer instance.
**   A tokenizer instance is required to actually tokenize text.
**
**   The first argument passed to this function is a copy of the (void*)
**   pointer provided by the application when the fts5_tokenizer object
**   was registered with FTS5 (the third argument to xCreateTokenizer()). 
**   The second and third arguments are an array of nul-terminated strings
**   containing the tokenizer arguments, if any, specified following the
**   tokenizer name as part of the CREATE VIRTUAL TABLE statement used
**   to create the FTS5 table.
**
**   The final argument is an output variable. If successful, (*ppOut) 
**   should be set to point to the new tokenizer handle and SQLITE_OK
**   returned. If an error occurs, some value other than SQLITE_OK should
**   be returned. In this case, fts5 assumes that the final value of *ppOut 
**   is undefined.
**
** xDelete:
**   This function is invoked to delete a tokenizer handle previously
**   allocated using xCreate(). Fts5 guarantees that this function will
**   be invoked exactly once for each successful call to xCreate().
**
** xTokenize:
**   This function is expected to tokenize the nText byte string indicated 
**   by argument pText. pText may or may not be nul-terminated. The first
**   argument passed to this function is a pointer to an Fts5Tokenizer object
**   returned by an earlier call to xCreate().
**
**   The second argument indicates the reason that FTS5 is requesting
**   tokenization of the supplied text. This is always one of the following
**   four values:
**
**   <ul><li> <b>FTS5_TOKENIZE_DOCUMENT</b> - A document is being inserted into
**            or removed from the FTS table. The tokenizer is being invoked to
**            determine the set of tokens to add to (or delete from) the
**            FTS index.
**
**       <li> <b>FTS5_TOKENIZE_QUERY</b> - A MATCH query is being executed 
**            against the FTS index. The tokenizer is being called to tokenize 
**            a bareword or quoted string specified as part of the query.
**
**       <li> <b>(FTS5_TOKENIZE_QUERY | FTS5_TOKENIZE_PREFIX)</b> - Same as
**            FTS5_TOKENIZE_QUERY, except that the bareword or quoted string is
**            followed by a "*" character, indicating that the last token
**            returned by the tokenizer will be treated as a token prefix.
**
**       <li> <b>FTS5_TOKENIZE_AUX</b> - The tokenizer is being invoked to 
**            satisfy an fts5_api.xTokenize() request made by an auxiliary
**            function. Or an fts5_api.xColumnSize() request made by the same
**            on a columnsize=0 database.  
**   </ul>
**
**   For each token in the input string, the supplied callback xToken() must
**   be invoked. The first argument to it should be a copy of the pointer
**   passed as the second argument to xTokenize(). The third and fourth
**   arguments are a pointer to a buffer containing the token text, and the
**   size of the token in bytes. The 4th and 5th arguments are the byte offsets
**   of the first byte of and first byte immediately following the text from
**   which the token is derived within the input.
**
**   The second argument passed to the xToken() callback ("tflags") should
**   normally be set to 0. The exception is if the tokenizer supports 
**   synonyms. In this case see the discussion below for details.
**
**   FTS5 assumes the xToken() callback is invoked for each token in the 
**   order that they occur within the input text.
**
**   If an xToken() callback returns any value other than SQLITE_OK, then
**   the tokenization should be abandoned and the xTokenize() method should
**   immediately return a copy of the xToken() return value. Or, if the
**   input buffer is exhausted, xTokenize() should return SQLITE_OK. Finally,
**   if an error occurs with the xTokenize() implementation itself, it
**   may abandon the tokenization and return any error code other than
**   SQLITE_OK or SQLITE_DONE.
**
** SYNONYM SUPPORT
**
**   Custom tokenizers may also support synonyms. Consider a case in which a
**   user wishes to query for a phrase such as "first place". Using the 
**   built-in tokenizers, the FTS5 query 'first + place' will match instances
**   of "first place" within the document set, but not alternative forms
**   such as "1st place". In some applications, it would be better to match
**   all instances of "first place" or "1st place" regardless of which form
**   the user specified in the MATCH query text.
**
**   There are several ways to approach this in FTS5:
**
**   <ol><li> By mapping all synonyms to a single token. In this case, the 
**            In the above example, this means that the tokenizer returns the
**            same token for inputs "first" and "1st". Say that token is in
**            fact "first", so that when the user inserts the document "I won
**            1st place" entries are added to the index for tokens "i", "won",
**            "first" and "place". If the user then queries for '1st + place',
**            the tokenizer substitutes "first" for "1st" and the query works
**            as expected.
**
**       <li> By adding multiple synonyms for a single term to the FTS index.
**            In this case, when tokenizing query text, the tokenizer may 
**            provide multiple synonyms for a single term within the document.
**            FTS5 then queries the index for each synonym individually. For
**            example, faced with the query:
**
**   <codeblock>
**     ... MATCH 'first place'</codeblock>
**
**            the tokenizer offers both "1st" and "first" as synonyms for the
**            first token in the MATCH query and FTS5 effectively runs a query 
**            similar to:
**
**   <codeblock>
**     ... MATCH '(first OR 1st) place'</codeblock>
**
**            except that, for the purposes of auxiliary functions, the query
**            still appears to contain just two phrases - "(first OR 1st)" 
**            being treated as a single phrase.
**
**       <li> By adding multiple synonyms for a single term to the FTS index.
**            Using this method, when tokenizing document text, the tokenizer
**            provides multiple synonyms for each token. So that when a 
**            document such as "I won first place" is tokenized, entries are
**            added to the FTS index for "i", "won", "first", "1st" and
**            "place".
**
**            This way, even if the tokenizer does not provide synonyms
**            when tokenizing query text (it should not - to do would be
**            inefficient), it doesn't matter if the user queries for 
**            'first + place' or '1st + place', as there are entires in the
**            FTS index corresponding to both forms of the first token.
**   </ol>
**
**   Whether it is parsing document or query text, any call to xToken that
**   specifies a <i>tflags</i> argument with the FTS5_TOKEN_COLOCATED bit
**   is considered to supply a synonym for the previous token. For example,
**   when parsing the document "I won first place", a tokenizer that supports
**   synonyms would call xToken() 5 times, as follows:
**
**   <codeblock>
**       xToken(pCtx, 0, "i",                      1,  0,  1);
**       xToken(pCtx, 0, "won",                    3,  2,  5);
**       xToken(pCtx, 0, "first",                  5,  6, 11);
**       xToken(pCtx, FTS5_TOKEN_COLOCATED, "1st", 3,  6, 11);
**       xToken(pCtx, 0, "place",                  5, 12, 17);
**</codeblock>
**
**   It is an error to specify the FTS5_TOKEN_COLOCATED flag the first time
**   xToken() is called. Multiple synonyms may be specified for a single token
**   by making multiple calls to xToken(FTS5_TOKEN_COLOCATED) in sequence. 
**   There is no limit to the number of synonyms that may be provided for a
**   single token.
**
**   In many cases, method (1) above is the best approach. It does not add 
**   extra data to the FTS index or require FTS5 to query for multiple terms,
**   so it is efficient in terms of disk space and query speed. However, it
**   does not support prefix queries very well. If, as suggested above, the
**   token "first" is subsituted for "1st" by the tokenizer, then the query:
**
**   <codeblock>
**     ... MATCH '1s*'</codeblock>
**
**   will not match documents that contain the token "1st" (as the tokenizer
**   will probably not map "1s" to any prefix of "first").
**
**   For full prefix support, method (3) may be preferred. In this case, 
**   because the index contains entries for both "first" and "1st", prefix
**   queries such as 'fi*' or '1s*' will match correctly. However, because
**   extra entries are added to the FTS index, this method uses more space
**   within the database.
**
**   Method (2) offers a midpoint between (1) and (3). Using this method,
**   a query such as '1s*' will match documents that contain the literal 
**   token "1st", but not "first" (assuming the tokenizer is not able to
**   provide synonyms for prefixes). However, a non-prefix query like '1st'
**   will match against "1st" and "first". This method does not require
**   extra disk space, as no extra entries are added to the FTS index. 
**   On the other hand, it may require more CPU cycles to run MATCH queries,
**   as separate queries of the FTS index are required for each synonym.
**
**   When using methods (2) or (3), it is important that the tokenizer only
**   provide synonyms when tokenizing document text (method (2)) or query
**   text (method (3)), not both. Doing so will not cause any errors, but is
**   inefficient.
*/
typedef struct Fts5Tokenizer Fts5Tokenizer;
typedef struct fts5_tokenizer fts5_tokenizer;
struct fts5_tokenizer {
  int (*xCreate)(void*, const char **azArg, int nArg, Fts5Tokenizer **ppOut);
  void (*xDelete)(Fts5Tokenizer*);
  int (*xTokenize)(Fts5Tokenizer*, 
      void *pCtx,
      int flags,            /* Mask of FTS5_TOKENIZE_* flags */
      const char *pText, int nText, 
      int (*xToken)(
        void *pCtx,         /* Copy of 2nd argument to xTokenize() */
        int tflags,         /* Mask of FTS5_TOKEN_* flags */
        const char *pToken, /* Pointer to buffer containing token */
        int nToken,         /* Size of token in bytes */
        int iStart,         /* Byte offset of token within input text */
        int iEnd            /* Byte offset of end of token within input text */
      )
  );
};

/* Flags that may be passed as the third argument to xTokenize() */
#define FTS5_TOKENIZE_QUERY     0x0001
#define FTS5_TOKENIZE_PREFIX    0x0002
#define FTS5_TOKENIZE_DOCUMENT  0x0004
#define FTS5_TOKENIZE_AUX       0x0008

/* Flags that may be passed by the tokenizer implementation back to FTS5
** as the third argument to the supplied xToken callback. */
#define FTS5_TOKEN_COLOCATED    0x0001      /* Same position as prev. token */

/*
** END OF CUSTOM TOKENIZERS
*************************************************************************/

/*************************************************************************
** FTS5 EXTENSION REGISTRATION API
*/
typedef struct fts5_api fts5_api;
struct fts5_api {
  int iVersion;                   /* Currently always set to 2 */

  /* Create a new tokenizer */
  int (*xCreateTokenizer)(
    fts5_api *pApi,
    const char *zName,
    void *pContext,
    fts5_tokenizer *pTokenizer,
    void (*xDestroy)(void*)
  );

  /* Find an existing tokenizer */
  int (*xFindTokenizer)(
    fts5_api *pApi,
    const char *zName,
    void **ppContext,
    fts5_tokenizer *pTokenizer
  );

  /* Create a new auxiliary function */
  int (*xCreateFunction)(
    fts5_api *pApi,
    const char *zName,
    void *pContext,
    fts5_extension_function xFunction,
    void (*xDestroy)(void*)
  );
};

/*
** END OF REGISTRATION API
*************************************************************************/

#endif /* _FTS5_H */