void
hlparsetext(TSCfgInfo * cfg, HLPRSTEXT * prs, QUERYTYPE * query, char *buf, int4 buflen)
{
int type,
lenlemm;
char *lemm = NULL;
WParserInfo *prsobj = findprs(cfg->prs_id);
LexizeData ldata;
TSLexeme *norms;
ParsedLex *lexs;
prsobj->prs = (void *) DatumGetPointer(
FunctionCall2(
&(prsobj->start_info),
PointerGetDatum(buf),
Int32GetDatum(buflen)
)
);
LexizeInit(&ldata, cfg);
do
{
type = DatumGetInt32(FunctionCall3(
&(prsobj->getlexeme_info),
PointerGetDatum(prsobj->prs),
PointerGetDatum(&lemm),
PointerGetDatum(&lenlemm)));
if (type > 0 && lenlemm >= MAXSTRLEN)
{
#ifdef IGNORE_LONGLEXEME
ereport(NOTICE,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("A word you are indexing is too long. It will be ignored.")));
continue;
#else
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("A word you are indexing is too long")));
#endif
}
LexizeAddLemm(&ldata, type, lemm, lenlemm);
do
{
if ((norms = LexizeExec(&ldata, &lexs)) != NULL)
addHLParsedLex(prs, query, lexs, norms);
else
addHLParsedLex(prs, query, lexs, NULL);
} while (norms);
} while (type > 0);
FunctionCall1(
&(prsobj->end_info),
PointerGetDatum(prsobj->prs)
);
}
void
hlparsetext(Oid cfgId, HeadlineParsedText *prs, TSQuery query, char *buf, int buflen)
{
int type,
lenlemm;
char *lemm = NULL;
LexizeData ldata;
TSLexeme *norms;
ParsedLex *lexs;
TSConfigCacheEntry *cfg;
TSParserCacheEntry *prsobj;
void *prsdata;
cfg = lookup_ts_config_cache(cfgId);
prsobj = lookup_ts_parser_cache(cfg->prsId);
prsdata = (void *) DatumGetPointer(FunctionCall2(&(prsobj->prsstart),
PointerGetDatum(buf),
Int32GetDatum(buflen)));
LexizeInit(&ldata, cfg);
do
{
type = DatumGetInt32(FunctionCall3(&(prsobj->prstoken),
PointerGetDatum(prsdata),
PointerGetDatum(&lemm),
PointerGetDatum(&lenlemm)));
if (type > 0 && lenlemm >= MAXSTRLEN)
{
#ifdef IGNORE_LONGLEXEME
ereport(NOTICE,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long to be indexed"),
errdetail("Words longer than %d characters are ignored.",
MAXSTRLEN)));
continue;
#else
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long to be indexed"),
errdetail("Words longer than %d characters are ignored.",
MAXSTRLEN)));
#endif
}
LexizeAddLemm(&ldata, type, lemm, lenlemm);
do
{
if ((norms = LexizeExec(&ldata, &lexs)) != NULL)
addHLParsedLex(prs, query, lexs, norms);
else
addHLParsedLex(prs, query, lexs, NULL);
} while (norms);
} while (type > 0);
FunctionCall1(&(prsobj->prsend), PointerGetDatum(prsdata));
}
/*
* Parse string and lexize words.
*
* prs will be filled in.
*/
void
parsetext(Oid cfgId, ParsedText *prs, char *buf, int buflen)
{
int type,
lenlemm;
char *lemm = NULL;
LexizeData ldata;
TSLexeme *norms;
TSConfigCacheEntry *cfg;
TSParserCacheEntry *prsobj;
void *prsdata;
cfg = lookup_ts_config_cache(cfgId);
prsobj = lookup_ts_parser_cache(cfg->prsId);
prsdata = (void *) DatumGetPointer(FunctionCall2(&prsobj->prsstart,
PointerGetDatum(buf),
Int32GetDatum(buflen)));
LexizeInit(&ldata, cfg);
do
{
type = DatumGetInt32(FunctionCall3(&(prsobj->prstoken),
PointerGetDatum(prsdata),
PointerGetDatum(&lemm),
PointerGetDatum(&lenlemm)));
if (type > 0 && lenlemm >= MAXSTRLEN)
{
#ifdef IGNORE_LONGLEXEME
ereport(NOTICE,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long to be indexed"),
errdetail("Words longer than %d characters are ignored.",
MAXSTRLEN)));
continue;
#else
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long to be indexed"),
errdetail("Words longer than %d characters are ignored.",
MAXSTRLEN)));
#endif
}
LexizeAddLemm(&ldata, type, lemm, lenlemm);
while ((norms = LexizeExec(&ldata, NULL)) != NULL)
{
TSLexeme *ptr = norms;
prs->pos++; /* set pos */
while (ptr->lexeme)
{
if (prs->curwords == prs->lenwords)
{
prs->lenwords *= 2;
prs->words = (ParsedWord *) repalloc((void *) prs->words, prs->lenwords * sizeof(ParsedWord));
}
if (ptr->flags & TSL_ADDPOS)
prs->pos++;
prs->words[prs->curwords].len = strlen(ptr->lexeme);
prs->words[prs->curwords].word = ptr->lexeme;
prs->words[prs->curwords].nvariant = ptr->nvariant;
prs->words[prs->curwords].flags = ptr->flags & TSL_PREFIX;
prs->words[prs->curwords].alen = 0;
prs->words[prs->curwords].pos.pos = LIMITPOS(prs->pos);
ptr++;
prs->curwords++;
}
pfree(norms);
}
} while (type > 0);
FunctionCall1(&(prsobj->prsend), PointerGetDatum(prsdata));
}
void
parsetext_v2(TSCfgInfo * cfg, PRSTEXT * prs, char *buf, int4 buflen)
{
int type,
lenlemm;
char *lemm = NULL;
WParserInfo *prsobj = findprs(cfg->prs_id);
LexizeData ldata;
TSLexeme *norms;
prsobj->prs = (void *) DatumGetPointer(
FunctionCall2(
&(prsobj->start_info),
PointerGetDatum(buf),
Int32GetDatum(buflen)
)
);
LexizeInit(&ldata, cfg);
do
{
type = DatumGetInt32(FunctionCall3(
&(prsobj->getlexeme_info),
PointerGetDatum(prsobj->prs),
PointerGetDatum(&lemm),
PointerGetDatum(&lenlemm)));
if (type > 0 && lenlemm >= MAXSTRLEN)
{
#ifdef IGNORE_LONGLEXEME
ereport(NOTICE,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("A word you are indexing is too long. It will be ignored.")));
continue;
#else
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("A word you are indexing is too long")));
#endif
}
LexizeAddLemm(&ldata, type, lemm, lenlemm);
while ((norms = LexizeExec(&ldata, NULL)) != NULL)
{
TSLexeme *ptr = norms;
prs->pos++; /* set pos */
while (ptr->lexeme)
{
if (prs->curwords == prs->lenwords)
{
prs->lenwords *= 2;
prs->words = (TSWORD *) repalloc((void *) prs->words, prs->lenwords * sizeof(TSWORD));
}
if (ptr->flags & TSL_ADDPOS)
prs->pos++;
prs->words[prs->curwords].len = strlen(ptr->lexeme);
prs->words[prs->curwords].word = ptr->lexeme;
prs->words[prs->curwords].nvariant = ptr->nvariant;
prs->words[prs->curwords].alen = 0;
prs->words[prs->curwords].pos.pos = LIMITPOS(prs->pos);
ptr++;
prs->curwords++;
}
pfree(norms);
}
} while (type > 0);
FunctionCall1(
&(prsobj->end_info),
PointerGetDatum(prsobj->prs)
);
}
