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)
);
}
Datum
set_curprs(PG_FUNCTION_ARGS)
{
SET_FUNCOID();
findprs(PG_GETARG_OID(0));
current_parser_id = PG_GETARG_OID(0);
PG_RETURN_VOID();
}
Datum
headline(PG_FUNCTION_ARGS)
{
text *in = PG_GETARG_TEXT_P(1);
QUERYTYPE *query = (QUERYTYPE *) DatumGetPointer(PG_DETOAST_DATUM(PG_GETARG_DATUM(2)));
text *opt = (PG_NARGS() > 3 && PG_GETARG_POINTER(3)) ? PG_GETARG_TEXT_P(3) : NULL;
HLPRSTEXT prs;
text *out;
TSCfgInfo *cfg;
WParserInfo *prsobj;
SET_FUNCOID();
cfg = findcfg(PG_GETARG_OID(0));
prsobj = findprs(cfg->prs_id);
memset(&prs, 0, sizeof(HLPRSTEXT));
prs.lenwords = 32;
prs.words = (HLWORD *) palloc(sizeof(HLWORD) * prs.lenwords);
hlparsetext(cfg, &prs, query, VARDATA(in), VARSIZE(in) - VARHDRSZ);
FunctionCall3(
&(prsobj->headline_info),
PointerGetDatum(&prs),
PointerGetDatum(opt),
PointerGetDatum(query)
);
out = genhl(&prs);
PG_FREE_IF_COPY(in, 1);
PG_FREE_IF_COPY(query, 2);
if (opt)
PG_FREE_IF_COPY(opt, 3);
pfree(prs.words);
pfree(prs.startsel);
pfree(prs.stopsel);
PG_RETURN_POINTER(out);
}
static void
setup_firstcall(FunctionCallInfo fcinfo, FuncCallContext *funcctx, Oid prsid)
{
TupleDesc tupdesc;
MemoryContext oldcontext;
TypeStorage *st;
WParserInfo *prs = findprs(prsid);
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
st = (TypeStorage *) palloc(sizeof(TypeStorage));
st->cur = 0;
st->list = (LexDescr *) DatumGetPointer(
OidFunctionCall1(prs->lextype, PointerGetDatum(prs->prs))
);
funcctx->user_fctx = (void *) st;
if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
tupdesc = CreateTupleDescCopy(tupdesc);
funcctx->attinmeta = TupleDescGetAttInMetadata(tupdesc);
MemoryContextSwitchTo(oldcontext);
}
WParserInfo *
findprs(Oid id)
{
/* last used prs */
if (PList.last_prs && PList.last_prs->prs_id == id)
return PList.last_prs;
/* already used prs */
if (PList.len != 0)
{
WParserInfo key;
key.prs_id = id;
PList.last_prs = bsearch(&key, PList.list, PList.len, sizeof(WParserInfo), compareprs);
if (PList.last_prs != NULL)
return PList.last_prs;
}
/* last chance */
if (PList.len == PList.reallen)
{
WParserInfo *tmp;
int reallen = (PList.reallen) ? 2 * PList.reallen : 16;
tmp = (WParserInfo *) realloc(PList.list, sizeof(WParserInfo) * reallen);
if (!tmp)
ts_error(ERROR, "No memory");
PList.reallen = reallen;
PList.list = tmp;
}
PList.last_prs = &(PList.list[PList.len]);
init_prs(id, PList.last_prs);
PList.len++;
qsort(PList.list, PList.len, sizeof(WParserInfo), compareprs);
return findprs(id); /* qsort changed order!! */ ;
}
static void
prs_setup_firstcall(FunctionCallInfo fcinfo, FuncCallContext *funcctx,
int prsid, text *txt)
{
TupleDesc tupdesc;
MemoryContext oldcontext;
PrsStorage *st;
WParserInfo *prs = findprs(prsid);
char *lex = NULL;
int llen = 0,
type = 0;
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
st = (PrsStorage *) palloc(sizeof(PrsStorage));
st->cur = 0;
st->len = 16;
st->list = (LexemeEntry *) palloc(sizeof(LexemeEntry) * st->len);
prs->prs = (void *) DatumGetPointer(
FunctionCall2(
&(prs->start_info),
PointerGetDatum(VARDATA(txt)),
Int32GetDatum(VARSIZE(txt) - VARHDRSZ)
)
);
while ((type = DatumGetInt32(FunctionCall3(
&(prs->getlexeme_info),
PointerGetDatum(prs->prs),
PointerGetDatum(&lex),
PointerGetDatum(&llen)))) != 0)
{
if (st->cur >= st->len)
{
st->len = 2 * st->len;
st->list = (LexemeEntry *) repalloc(st->list, sizeof(LexemeEntry) * st->len);
}
st->list[st->cur].lexeme = palloc(llen + 1);
memcpy(st->list[st->cur].lexeme, lex, llen);
st->list[st->cur].lexeme[llen] = '\0';
st->list[st->cur].type = type;
st->cur++;
}
FunctionCall1(
&(prs->end_info),
PointerGetDatum(prs->prs)
);
st->len = st->cur;
st->cur = 0;
funcctx->user_fctx = (void *) st;
if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
tupdesc = CreateTupleDescCopy(tupdesc);
funcctx->attinmeta = TupleDescGetAttInMetadata(tupdesc);
MemoryContextSwitchTo(oldcontext);
}
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)
);
}
