diff options
author | mpcomplete@google.com <mpcomplete@google.com@0039d316-1c4b-4281-b951-d872f2087c98> | 2009-01-06 22:39:41 +0000 |
---|---|---|
committer | mpcomplete@google.com <mpcomplete@google.com@0039d316-1c4b-4281-b951-d872f2087c98> | 2009-01-06 22:39:41 +0000 |
commit | 586381f8db3497c24c11f96234f1879b34e74bc7 (patch) | |
tree | 99f7d18350289b135ef6dd5c161baba8bce668a3 /third_party/sqlite/ext/fts3/fts3_tokenizer.c | |
parent | 6e3b12ff2cbbe8c481f986c8f0dd230bb50add2a (diff) | |
download | chromium_src-586381f8db3497c24c11f96234f1879b34e74bc7.zip chromium_src-586381f8db3497c24c11f96234f1879b34e74bc7.tar.gz chromium_src-586381f8db3497c24c11f96234f1879b34e74bc7.tar.bz2 |
Upgrade our sqlite to 3.6.1, with the local changes made by Gears. I'm
checking in the full sqlite tree to make upstream merges easier. This means
we'll have generated sources split out from the originals.
One important change this makes is that "BEGIN" now defaults to "BEGIN
IMMEDIATE" rather than "BEGIN DEFERRED". This doesn't affect us because we
don't use unqualified BEGIN statements.
The full CL is too big for Rietveld. I'm splitting it into 2. This one is
reviewable. The other CL is just a fresh drop of:
//depot/googleclient/gears/opensource/third_party/sqlite_google
Review URL: http://codereview.chromium.org/15067
git-svn-id: svn://svn.chromium.org/chrome/trunk/src@7623 0039d316-1c4b-4281-b951-d872f2087c98
Diffstat (limited to 'third_party/sqlite/ext/fts3/fts3_tokenizer.c')
-rwxr-xr-x | third_party/sqlite/ext/fts3/fts3_tokenizer.c | 371 |
1 files changed, 371 insertions, 0 deletions
diff --git a/third_party/sqlite/ext/fts3/fts3_tokenizer.c b/third_party/sqlite/ext/fts3/fts3_tokenizer.c new file mode 100755 index 0000000..ef19995 --- /dev/null +++ b/third_party/sqlite/ext/fts3/fts3_tokenizer.c @@ -0,0 +1,371 @@ +/* +** 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 is part of an SQLite module implementing full-text search. +** This particular file implements the generic tokenizer interface. +*/ + +/* +** 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). +*/ +#if !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) + +#include "sqlite3ext.h" +#ifndef SQLITE_CORE + SQLITE_EXTENSION_INIT1 +#endif + +#include "fts3_hash.h" +#include "fts3_tokenizer.h" +#include <assert.h> + +/* +** Implementation of the SQL scalar function for accessing the underlying +** hash table. This function may be called as follows: +** +** SELECT <function-name>(<key-name>); +** SELECT <function-name>(<key-name>, <pointer>); +** +** where <function-name> is the name passed as the second argument +** to the sqlite3Fts3InitHashTable() function (e.g. 'fts3_tokenizer'). +** +** If the <pointer> argument is specified, it must be a blob value +** containing a pointer to be stored as the hash data corresponding +** to the string <key-name>. If <pointer> is not specified, then +** the string <key-name> must already exist in the has table. Otherwise, +** an error is returned. +** +** Whether or not the <pointer> argument is specified, the value returned +** is a blob containing the pointer stored as the hash data corresponding +** to string <key-name> (after the hash-table is updated, if applicable). +*/ +static void scalarFunc( + sqlite3_context *context, + int argc, + sqlite3_value **argv +){ + fts3Hash *pHash; + void *pPtr = 0; + const unsigned char *zName; + int nName; + + assert( argc==1 || argc==2 ); + + pHash = (fts3Hash *)sqlite3_user_data(context); + + zName = sqlite3_value_text(argv[0]); + nName = sqlite3_value_bytes(argv[0])+1; + + if( argc==2 ){ + void *pOld; + int n = sqlite3_value_bytes(argv[1]); + if( n!=sizeof(pPtr) ){ + sqlite3_result_error(context, "argument type mismatch", -1); + return; + } + pPtr = *(void **)sqlite3_value_blob(argv[1]); + pOld = sqlite3Fts3HashInsert(pHash, (void *)zName, nName, pPtr); + if( pOld==pPtr ){ + sqlite3_result_error(context, "out of memory", -1); + return; + } + }else{ + pPtr = sqlite3Fts3HashFind(pHash, zName, nName); + if( !pPtr ){ + char *zErr = sqlite3_mprintf("unknown tokenizer: %s", zName); + sqlite3_result_error(context, zErr, -1); + sqlite3_free(zErr); + return; + } + } + + sqlite3_result_blob(context, (void *)&pPtr, sizeof(pPtr), SQLITE_TRANSIENT); +} + +#ifdef SQLITE_TEST + +#include <tcl.h> +#include <string.h> + +/* +** Implementation of a special SQL scalar function for testing tokenizers +** designed to be used in concert with the Tcl testing framework. This +** function must be called with two arguments: +** +** SELECT <function-name>(<key-name>, <input-string>); +** SELECT <function-name>(<key-name>, <pointer>); +** +** where <function-name> is the name passed as the second argument +** to the sqlite3Fts3InitHashTable() function (e.g. 'fts3_tokenizer') +** concatenated with the string '_test' (e.g. 'fts3_tokenizer_test'). +** +** The return value is a string that may be interpreted as a Tcl +** list. For each token in the <input-string>, three elements are +** added to the returned list. The first is the token position, the +** second is the token text (folded, stemmed, etc.) and the third is the +** substring of <input-string> associated with the token. For example, +** using the built-in "simple" tokenizer: +** +** SELECT fts_tokenizer_test('simple', 'I don't see how'); +** +** will return the string: +** +** "{0 i I 1 dont don't 2 see see 3 how how}" +** +*/ +static void testFunc( + sqlite3_context *context, + int argc, + sqlite3_value **argv +){ + fts3Hash *pHash; + sqlite3_tokenizer_module *p; + sqlite3_tokenizer *pTokenizer = 0; + sqlite3_tokenizer_cursor *pCsr = 0; + + const char *zErr = 0; + + const char *zName; + int nName; + const char *zInput; + int nInput; + + const char *zArg = 0; + + const char *zToken; + int nToken; + int iStart; + int iEnd; + int iPos; + + Tcl_Obj *pRet; + + assert( argc==2 || argc==3 ); + + nName = sqlite3_value_bytes(argv[0]); + zName = (const char *)sqlite3_value_text(argv[0]); + nInput = sqlite3_value_bytes(argv[argc-1]); + zInput = (const char *)sqlite3_value_text(argv[argc-1]); + + if( argc==3 ){ + zArg = (const char *)sqlite3_value_text(argv[1]); + } + + pHash = (fts3Hash *)sqlite3_user_data(context); + p = (sqlite3_tokenizer_module *)sqlite3Fts3HashFind(pHash, zName, nName+1); + + if( !p ){ + char *zErr = sqlite3_mprintf("unknown tokenizer: %s", zName); + sqlite3_result_error(context, zErr, -1); + sqlite3_free(zErr); + return; + } + + pRet = Tcl_NewObj(); + Tcl_IncrRefCount(pRet); + + if( SQLITE_OK!=p->xCreate(zArg ? 1 : 0, &zArg, &pTokenizer) ){ + zErr = "error in xCreate()"; + goto finish; + } + pTokenizer->pModule = p; + if( SQLITE_OK!=p->xOpen(pTokenizer, zInput, nInput, &pCsr) ){ + zErr = "error in xOpen()"; + goto finish; + } + pCsr->pTokenizer = pTokenizer; + + while( SQLITE_OK==p->xNext(pCsr, &zToken, &nToken, &iStart, &iEnd, &iPos) ){ + Tcl_ListObjAppendElement(0, pRet, Tcl_NewIntObj(iPos)); + Tcl_ListObjAppendElement(0, pRet, Tcl_NewStringObj(zToken, nToken)); + zToken = &zInput[iStart]; + nToken = iEnd-iStart; + Tcl_ListObjAppendElement(0, pRet, Tcl_NewStringObj(zToken, nToken)); + } + + if( SQLITE_OK!=p->xClose(pCsr) ){ + zErr = "error in xClose()"; + goto finish; + } + if( SQLITE_OK!=p->xDestroy(pTokenizer) ){ + zErr = "error in xDestroy()"; + goto finish; + } + +finish: + if( zErr ){ + sqlite3_result_error(context, zErr, -1); + }else{ + sqlite3_result_text(context, Tcl_GetString(pRet), -1, SQLITE_TRANSIENT); + } + Tcl_DecrRefCount(pRet); +} + +static +int registerTokenizer( + sqlite3 *db, + char *zName, + const sqlite3_tokenizer_module *p +){ + int rc; + sqlite3_stmt *pStmt; + const char zSql[] = "SELECT fts3_tokenizer(?, ?)"; + + rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0); + if( rc!=SQLITE_OK ){ + return rc; + } + + sqlite3_bind_text(pStmt, 1, zName, -1, SQLITE_STATIC); + sqlite3_bind_blob(pStmt, 2, &p, sizeof(p), SQLITE_STATIC); + sqlite3_step(pStmt); + + return sqlite3_finalize(pStmt); +} + +static +int queryTokenizer( + sqlite3 *db, + char *zName, + const sqlite3_tokenizer_module **pp +){ + int rc; + sqlite3_stmt *pStmt; + const char zSql[] = "SELECT fts3_tokenizer(?)"; + + *pp = 0; + rc = sqlite3_prepare_v2(db, zSql, -1, &pStmt, 0); + if( rc!=SQLITE_OK ){ + return rc; + } + + sqlite3_bind_text(pStmt, 1, zName, -1, SQLITE_STATIC); + if( SQLITE_ROW==sqlite3_step(pStmt) ){ + if( sqlite3_column_type(pStmt, 0)==SQLITE_BLOB ){ + memcpy(pp, sqlite3_column_blob(pStmt, 0), sizeof(*pp)); + } + } + + return sqlite3_finalize(pStmt); +} + +void sqlite3Fts3SimpleTokenizerModule(sqlite3_tokenizer_module const**ppModule); + +/* +** Implementation of the scalar function fts3_tokenizer_internal_test(). +** This function is used for testing only, it is not included in the +** build unless SQLITE_TEST is defined. +** +** The purpose of this is to test that the fts3_tokenizer() function +** can be used as designed by the C-code in the queryTokenizer and +** registerTokenizer() functions above. These two functions are repeated +** in the README.tokenizer file as an example, so it is important to +** test them. +** +** To run the tests, evaluate the fts3_tokenizer_internal_test() scalar +** function with no arguments. An assert() will fail if a problem is +** detected. i.e.: +** +** SELECT fts3_tokenizer_internal_test(); +** +*/ +static void intTestFunc( + sqlite3_context *context, + int argc, + sqlite3_value **argv +){ + int rc; + const sqlite3_tokenizer_module *p1; + const sqlite3_tokenizer_module *p2; + sqlite3 *db = (sqlite3 *)sqlite3_user_data(context); + + /* Test the query function */ + sqlite3Fts3SimpleTokenizerModule(&p1); + rc = queryTokenizer(db, "simple", &p2); + assert( rc==SQLITE_OK ); + assert( p1==p2 ); + rc = queryTokenizer(db, "nosuchtokenizer", &p2); + assert( rc==SQLITE_ERROR ); + assert( p2==0 ); + assert( 0==strcmp(sqlite3_errmsg(db), "unknown tokenizer: nosuchtokenizer") ); + + /* Test the storage function */ + rc = registerTokenizer(db, "nosuchtokenizer", p1); + assert( rc==SQLITE_OK ); + rc = queryTokenizer(db, "nosuchtokenizer", &p2); + assert( rc==SQLITE_OK ); + assert( p2==p1 ); + + sqlite3_result_text(context, "ok", -1, SQLITE_STATIC); +} + +#endif + +/* +** Set up SQL objects in database db used to access the contents of +** the hash table pointed to by argument pHash. The hash table must +** been initialised to use string keys, and to take a private copy +** of the key when a value is inserted. i.e. by a call similar to: +** +** sqlite3Fts3HashInit(pHash, FTS3_HASH_STRING, 1); +** +** This function adds a scalar function (see header comment above +** scalarFunc() in this file for details) and, if ENABLE_TABLE is +** defined at compilation time, a temporary virtual table (see header +** comment above struct HashTableVtab) to the database schema. Both +** provide read/write access to the contents of *pHash. +** +** The third argument to this function, zName, is used as the name +** of both the scalar and, if created, the virtual table. +*/ +int sqlite3Fts3InitHashTable( + sqlite3 *db, + fts3Hash *pHash, + const char *zName +){ + int rc = SQLITE_OK; + void *p = (void *)pHash; + const int any = SQLITE_ANY; + char *zTest = 0; + char *zTest2 = 0; + +#ifdef SQLITE_TEST + void *pdb = (void *)db; + zTest = sqlite3_mprintf("%s_test", zName); + zTest2 = sqlite3_mprintf("%s_internal_test", zName); + if( !zTest || !zTest2 ){ + rc = SQLITE_NOMEM; + } +#endif + + if( rc!=SQLITE_OK + || (rc = sqlite3_create_function(db, zName, 1, any, p, scalarFunc, 0, 0)) + || (rc = sqlite3_create_function(db, zName, 2, any, p, scalarFunc, 0, 0)) +#ifdef SQLITE_TEST + || (rc = sqlite3_create_function(db, zTest, 2, any, p, testFunc, 0, 0)) + || (rc = sqlite3_create_function(db, zTest, 3, any, p, testFunc, 0, 0)) + || (rc = sqlite3_create_function(db, zTest2, 0, any, pdb, intTestFunc, 0, 0)) +#endif + ); + + sqlite3_free(zTest); + sqlite3_free(zTest2); + return rc; +} + +#endif /* !defined(SQLITE_CORE) || defined(SQLITE_ENABLE_FTS3) */ |