/*
* @@ selectivity for tsvector var vs tsquery constant
*/
static Selectivity
tsquerysel(VariableStatData *vardata, Datum constval)
{
Selectivity selec;
TSQuery query;
/* The caller made sure the const is a TSQuery, so get it now */
query = DatumGetTSQuery(constval);
/* Empty query matches nothing */
if (query->size == 0)
return (Selectivity) 0.0;
if (HeapTupleIsValid(vardata->statsTuple))
{
Form_pg_statistic stats;
Datum *values;
int nvalues;
float4 *numbers;
int nnumbers;
stats = (Form_pg_statistic) GETSTRUCT(vardata->statsTuple);
/* MCELEM will be an array of TEXT elements for a tsvector column */
if (get_attstatsslot(vardata->statsTuple,
TEXTOID, -1,
STATISTIC_KIND_MCELEM, InvalidOid,
NULL,
&values, &nvalues,
&numbers, &nnumbers))
{
/*
* There is a most-common-elements slot for the tsvector Var, so
* use that.
*/
selec = mcelem_tsquery_selec(query, values, nvalues,
numbers, nnumbers);
free_attstatsslot(TEXTOID, values, nvalues, numbers, nnumbers);
}
else
{
/* No most-common-elements info, so do without */
selec = tsquery_opr_selec_no_stats(query);
}
/*
* MCE stats count only non-null rows, so adjust for null rows.
*/
selec *= (1.0 - stats->stanullfrac);
}
else
{
/* No stats at all, so do without */
selec = tsquery_opr_selec_no_stats(query);
/* we assume no nulls here, so no stanullfrac correction */
}
return selec;
}
/*
* Extract data from the pg_statistic arrays into useful format.
*/
static Selectivity
mcelem_tsquery_selec(TSQuery query, Datum *mcelem, int nmcelem,
float4 *numbers, int nnumbers)
{
float4 minfreq;
TextFreq *lookup;
Selectivity selec;
int i;
/*
* There should be two more Numbers than Values, because the last two
* cells are taken for minimal and maximal frequency. Punt if not.
*
* (Note: the MCELEM statistics slot definition allows for a third extra
* number containing the frequency of nulls, but we're not expecting that
* to appear for a tsvector column.)
*/
if (nnumbers != nmcelem + 2)
return tsquery_opr_selec_no_stats(query);
/*
* Transpose the data into a single array so we can use bsearch().
*/
lookup = (TextFreq *) palloc(sizeof(TextFreq) * nmcelem);
for (i = 0; i < nmcelem; i++)
{
/*
* The text Datums came from an array, so it cannot be compressed or
* stored out-of-line -- it's safe to use VARSIZE_ANY*.
*/
Assert(!VARATT_IS_COMPRESSED(mcelem[i]) && !VARATT_IS_EXTERNAL(mcelem[i]));
lookup[i].element = (text *) DatumGetPointer(mcelem[i]);
lookup[i].frequency = numbers[i];
}
/*
* Grab the lowest frequency. compute_tsvector_stats() stored it for us in
* the one before the last cell of the Numbers array. See ts_typanalyze.c
*/
minfreq = numbers[nnumbers - 2];
selec = tsquery_opr_selec(GETQUERY(query), GETOPERAND(query), lookup,
nmcelem, minfreq);
pfree(lookup);
return selec;
}
