mirror of
https://github.com/DBD-SQLite/DBD-SQLite
synced 2025-06-07 14:19:10 -04:00
Fix all type errors
This commit is contained in:
parent
8c0209e4f4
commit
1ad93cacc0
2 changed files with 89 additions and 87 deletions
|
@ -16,23 +16,14 @@ typedef struct perl_fts3_tokenizer_cursor {
|
|||
int currentChar; /* char position corresponding to currentByte */
|
||||
} perl_fts3_tokenizer_cursor;
|
||||
|
||||
typedef struct perl_fts5_tokenizer {
|
||||
fts5_tokenizer base;
|
||||
typedef struct perl_Fts5Tokenizer {
|
||||
Fts5Tokenizer base;
|
||||
SV *coderef; /* the perl tokenizer is a coderef that takes
|
||||
a string and returns a cursor coderef */
|
||||
} perl_fts5_tokenizer;
|
||||
|
||||
typedef struct perl_fts5_tokenizer_cursor {
|
||||
// fts5_tokenizer_cursor base;
|
||||
SV *coderef; /* ref to the closure that returns terms */
|
||||
char *pToken; /* storage for a copy of the last token */
|
||||
int nTokenAllocated; /* space allocated to pToken buffer */
|
||||
|
||||
/* members below are only used if the input string is in utf8 */
|
||||
const char *pInput; /* input we are tokenizing */
|
||||
const char *lastByteOffset; /* offset into pInput */
|
||||
int lastCharOffset; /* char offset corresponding to lastByteOffset */
|
||||
} perl_fts5_tokenizer_cursor;
|
||||
** a string and and some parameters and
|
||||
** in turn calls the xToken() function
|
||||
** passed to it
|
||||
*/
|
||||
} perl_Fts5Tokenizer;
|
||||
|
||||
/*
|
||||
** Create a new tokenizer instance.
|
||||
|
@ -340,20 +331,19 @@ int sqlite_db_register_fts3_perl_tokenizer(pTHX_ SV *dbh)
|
|||
** where qualified::function::name is a fully qualified perl function
|
||||
*/
|
||||
static int perl_fts5_tokenizer_Create(
|
||||
int argc, const char * const *argv,
|
||||
sqlite3_tokenizer **ppTokenizer
|
||||
void* pCtx, const char **azArg, int nArg, Fts5Tokenizer **ppOut
|
||||
){
|
||||
dTHX;
|
||||
dSP;
|
||||
int n_retval;
|
||||
SV *retval;
|
||||
perl_fts3_tokenizer *t;
|
||||
perl_Fts5Tokenizer *t;
|
||||
|
||||
if (!argc) {
|
||||
if (!nArg) {
|
||||
return SQLITE_ERROR;
|
||||
}
|
||||
|
||||
t = (perl_fts3_tokenizer *) sqlite3_malloc(sizeof(*t));
|
||||
t = (perl_Fts5Tokenizer *) sqlite3_malloc(sizeof(*t));
|
||||
if( t==NULL ) return SQLITE_NOMEM;
|
||||
memset(t, 0, sizeof(*t));
|
||||
|
||||
|
@ -363,7 +353,7 @@ static int perl_fts5_tokenizer_Create(
|
|||
/* call the qualified::function::name */
|
||||
PUSHMARK(SP);
|
||||
PUTBACK;
|
||||
n_retval = call_pv(argv[0], G_SCALAR);
|
||||
n_retval = call_pv(azArg[0], G_SCALAR);
|
||||
SPAGAIN;
|
||||
|
||||
/* store a copy of the returned coderef into the tokenizer structure */
|
||||
|
@ -372,7 +362,7 @@ static int perl_fts5_tokenizer_Create(
|
|||
}
|
||||
retval = POPs;
|
||||
t->coderef = newSVsv(retval);
|
||||
*ppTokenizer = &t->base;
|
||||
*ppOut = &t->base;
|
||||
|
||||
PUTBACK;
|
||||
FREETMPS;
|
||||
|
@ -384,27 +374,33 @@ static int perl_fts5_tokenizer_Create(
|
|||
/*
|
||||
** Destroy a tokenizer
|
||||
*/
|
||||
static int perl_fts5_tokenizer_Delete(Fts5Tokenizer *pTokenizer){
|
||||
static void perl_fts5_tokenizer_Delete(Fts5Tokenizer *pTokenizer){
|
||||
dTHX;
|
||||
perl_fts5_tokenizer *t = (perl_fts5_tokenizer *) pTokenizer;
|
||||
perl_Fts5Tokenizer *t = (perl_Fts5Tokenizer *) pTokenizer;
|
||||
sv_free(t->coderef);
|
||||
sqlite3_free(t);
|
||||
return SQLITE_OK;
|
||||
return;
|
||||
}
|
||||
|
||||
/*
|
||||
** Extract the next token from a tokenization cursor. The cursor must
|
||||
** have been opened by a prior call to perl_fts3_tokenizer_Open().
|
||||
** This does a tokenizing run over the string. Found tokens (and synonyms)
|
||||
** are stored by calling xToken()
|
||||
*/
|
||||
static int perl_fts5_tokenizer_Tokenize(
|
||||
sqlite3_tokenizer_cursor *pCursor, /* Cursor returned by perl_fts3_tokenizer_Open */
|
||||
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 */
|
||||
Fts5Tokenizer* tokenizer,
|
||||
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 */
|
||||
)
|
||||
){
|
||||
perl_fts3_tokenizer_cursor *c = (perl_fts3_tokenizer_cursor *) pCursor;
|
||||
perl_Fts5Tokenizer *c = (perl_Fts5Tokenizer *) tokenizer;
|
||||
int result;
|
||||
int n_retval;
|
||||
char *token;
|
||||
|
@ -418,61 +414,67 @@ static int perl_fts5_tokenizer_Tokenize(
|
|||
ENTER;
|
||||
SAVETMPS;
|
||||
|
||||
/* call the cursor */
|
||||
/* call the Perl tokenizer, and pass it our token callback */
|
||||
PUSHMARK(SP);
|
||||
PUTBACK;
|
||||
|
||||
// XXX Wrap the "found token" callback, and pass it to the user
|
||||
// Then, restructure the data if it is UTF-8
|
||||
// First, do all of this in Perl so it is easier to debug
|
||||
|
||||
///* if we get back an empty list, there is no more token */
|
||||
//if (n_retval == 0) {
|
||||
// result = SQLITE_DONE;
|
||||
//}
|
||||
///* otherwise, get token details from the return list */
|
||||
//else {
|
||||
// if (n_retval != 5) {
|
||||
// warn("tokenizer cursor returned %d arguments", n_retval);
|
||||
// }
|
||||
// *piPosition = POPi;
|
||||
// *piEndOffset = POPi;
|
||||
// *piStartOffset = POPi;
|
||||
// *pnBytes = POPi;
|
||||
// token = POPpx;
|
||||
//
|
||||
// if (c->pInput) { /* if working with utf8 data */
|
||||
//
|
||||
// /* recompute *pnBytes in bytes, not in chars */
|
||||
// *pnBytes = strlen(token);
|
||||
//
|
||||
// /* recompute start/end offsets in bytes, not in chars */
|
||||
// hop = *piStartOffset - c->lastCharOffset;
|
||||
// byteOffset = (char*)utf8_hop((U8*)c->lastByteOffset, hop);
|
||||
// hop = *piEndOffset - *piStartOffset;
|
||||
// *piStartOffset = byteOffset - c->pInput;
|
||||
// byteOffset = (char*)utf8_hop((U8*)byteOffset, hop);
|
||||
// *piEndOffset = byteOffset - c->pInput;
|
||||
//
|
||||
// /* remember where we are for next round */
|
||||
// c->lastCharOffset = *piEndOffset,
|
||||
// c->lastByteOffset = byteOffset;
|
||||
// }
|
||||
//
|
||||
// /* make sure we have enough storage for copying the token */
|
||||
// if (*pnBytes > c->nTokenAllocated ){
|
||||
// char *pNew;
|
||||
// c->nTokenAllocated = *pnBytes + 20;
|
||||
// pNew = sqlite3_realloc(c->pToken, c->nTokenAllocated);
|
||||
// if( !pNew ) return SQLITE_NOMEM;
|
||||
// c->pToken = pNew;
|
||||
// }
|
||||
//
|
||||
// /* need to copy the token into the C cursor before perl frees that
|
||||
// memory */
|
||||
// memcpy(c->pToken, token, *pnBytes);
|
||||
// *ppToken = c->pToken;
|
||||
//
|
||||
// result = SQLITE_OK;
|
||||
//
|
||||
|
||||
n_retval = call_sv(c->coderef, G_ARRAY);
|
||||
SPAGAIN;
|
||||
|
||||
/* if we get back an empty list, there is no more token */
|
||||
if (n_retval == 0) {
|
||||
result = SQLITE_DONE;
|
||||
}
|
||||
/* otherwise, get token details from the return list */
|
||||
else {
|
||||
if (n_retval != 5) {
|
||||
warn("tokenizer cursor returned %d arguments", n_retval);
|
||||
}
|
||||
*piPosition = POPi;
|
||||
*piEndOffset = POPi;
|
||||
*piStartOffset = POPi;
|
||||
*pnBytes = POPi;
|
||||
token = POPpx;
|
||||
|
||||
if (c->pInput) { /* if working with utf8 data */
|
||||
|
||||
/* recompute *pnBytes in bytes, not in chars */
|
||||
*pnBytes = strlen(token);
|
||||
|
||||
/* recompute start/end offsets in bytes, not in chars */
|
||||
hop = *piStartOffset - c->lastCharOffset;
|
||||
byteOffset = (char*)utf8_hop((U8*)c->lastByteOffset, hop);
|
||||
hop = *piEndOffset - *piStartOffset;
|
||||
*piStartOffset = byteOffset - c->pInput;
|
||||
byteOffset = (char*)utf8_hop((U8*)byteOffset, hop);
|
||||
*piEndOffset = byteOffset - c->pInput;
|
||||
|
||||
/* remember where we are for next round */
|
||||
c->lastCharOffset = *piEndOffset,
|
||||
c->lastByteOffset = byteOffset;
|
||||
}
|
||||
|
||||
/* make sure we have enough storage for copying the token */
|
||||
if (*pnBytes > c->nTokenAllocated ){
|
||||
char *pNew;
|
||||
c->nTokenAllocated = *pnBytes + 20;
|
||||
pNew = sqlite3_realloc(c->pToken, c->nTokenAllocated);
|
||||
if( !pNew ) return SQLITE_NOMEM;
|
||||
c->pToken = pNew;
|
||||
}
|
||||
|
||||
/* need to copy the token into the C cursor before perl frees that
|
||||
memory */
|
||||
memcpy(c->pToken, token, *pnBytes);
|
||||
*ppToken = c->pToken;
|
||||
|
||||
result = SQLITE_OK;
|
||||
}
|
||||
|
||||
PUTBACK;
|
||||
FREETMPS;
|
||||
|
@ -485,7 +487,6 @@ static int perl_fts5_tokenizer_Tokenize(
|
|||
** The set of routines that implement the perl FTS5 tokenizer
|
||||
*/
|
||||
fts5_tokenizer perl_fts5_tokenizer_Module = {
|
||||
0,
|
||||
perl_fts5_tokenizer_Create,
|
||||
perl_fts5_tokenizer_Delete,
|
||||
perl_fts5_tokenizer_Tokenize
|
||||
|
@ -530,7 +531,7 @@ int sqlite_db_register_fts5_perl_tokenizer(pTHX_ SV *dbh)
|
|||
|
||||
int rc;
|
||||
fts5_api *pFts5Api = sqlite_fetch_fts5_api(aTHX_ dbh);
|
||||
sqlite3_tokenizer_module *p = &perl_fts5_tokenizer_Module;
|
||||
fts5_tokenizer *p = &perl_fts5_tokenizer_Module;
|
||||
|
||||
// pFts5Api->xCreateTokenizer(pFts5Api,...);
|
||||
|
||||
|
|
|
@ -51,6 +51,7 @@ sub driver {
|
|||
DBD::SQLite::db->install_method('sqlite_enable_load_extension');
|
||||
DBD::SQLite::db->install_method('sqlite_load_extension');
|
||||
DBD::SQLite::db->install_method('sqlite_register_fts3_perl_tokenizer');
|
||||
DBD::SQLite::db->install_method('sqlite_register_fts5_perl_tokenizer');
|
||||
DBD::SQLite::db->install_method('sqlite_trace', { O => 0x0004 });
|
||||
DBD::SQLite::db->install_method('sqlite_profile', { O => 0x0004 });
|
||||
DBD::SQLite::db->install_method('sqlite_table_column_metadata', { O => 0x0004 });
|
||||
|
|
Loading…
Add table
Reference in a new issue