selfuncs.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

		 */
		Oid			eqopr = get_opclass_member(opclass, InvalidOid,
											   BTEqualStrategyNumber);
		List	   *eqargs;

		if (eqopr == InvalidOid)
			elog(ERROR, "no = operator for opclass %u", opclass);
		eqargs = list_make2(variable, prefix);
		result = DatumGetFloat8(DirectFunctionCall4(eqsel,
													PointerGetDatum(root),
													ObjectIdGetDatum(eqopr),
													PointerGetDatum(eqargs),
													Int32GetDatum(varRelid)));
	}
	else
	{
		/*
		 * Not exact-match pattern.  We estimate selectivity of the fixed
		 * prefix and remainder of pattern separately, then combine the two.
		 */
		Selectivity prefixsel;
		Selectivity restsel;
		Selectivity selec;

		if (pstatus == Pattern_Prefix_Partial)
			prefixsel = prefix_selectivity(root, variable, opclass, prefix);
		else
			prefixsel = 1.0;
		restsel = pattern_selectivity(rest, ptype);
		selec = prefixsel * restsel;
		/* result should be in range, but make sure... */
		CLAMP_PROBABILITY(selec);
		result = selec;
	}

	if (prefix)
	{
		pfree(DatumGetPointer(prefix->constvalue));
		pfree(prefix);
	}

	ReleaseVariableStats(vardata);

	return result;
}

/*
 *		regexeqsel		- Selectivity of regular-expression pattern match.
 */
Datum
regexeqsel(PG_FUNCTION_ARGS)
{
	PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex));
}

/*
 *		icregexeqsel	- Selectivity of case-insensitive regex match.
 */
Datum
icregexeqsel(PG_FUNCTION_ARGS)
{
	PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Regex_IC));
}

/*
 *		likesel			- Selectivity of LIKE pattern match.
 */
Datum
likesel(PG_FUNCTION_ARGS)
{
	PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like));
}

/*
 *		iclikesel			- Selectivity of ILIKE pattern match.
 */
Datum
iclikesel(PG_FUNCTION_ARGS)
{
	PG_RETURN_FLOAT8(patternsel(fcinfo, Pattern_Type_Like_IC));
}

/*
 *		regexnesel		- Selectivity of regular-expression pattern non-match.
 */
Datum
regexnesel(PG_FUNCTION_ARGS)
{
	double		result;

	result = patternsel(fcinfo, Pattern_Type_Regex);
	result = 1.0 - result;
	PG_RETURN_FLOAT8(result);
}

/*
 *		icregexnesel	- Selectivity of case-insensitive regex non-match.
 */
Datum
icregexnesel(PG_FUNCTION_ARGS)
{
	double		result;

	result = patternsel(fcinfo, Pattern_Type_Regex_IC);
	result = 1.0 - result;
	PG_RETURN_FLOAT8(result);
}

/*
 *		nlikesel		- Selectivity of LIKE pattern non-match.
 */
Datum
nlikesel(PG_FUNCTION_ARGS)
{
	double		result;

	result = patternsel(fcinfo, Pattern_Type_Like);
	result = 1.0 - result;
	PG_RETURN_FLOAT8(result);
}

/*
 *		icnlikesel		- Selectivity of ILIKE pattern non-match.
 */
Datum
icnlikesel(PG_FUNCTION_ARGS)
{
	double		result;

	result = patternsel(fcinfo, Pattern_Type_Like_IC);
	result = 1.0 - result;
	PG_RETURN_FLOAT8(result);
}

/*
 *		booltestsel		- Selectivity of BooleanTest Node.
 */
Selectivity
booltestsel(PlannerInfo *root, BoolTestType booltesttype, Node *arg,
			int varRelid, JoinType jointype)
{
	VariableStatData vardata;
	double		selec;

	examine_variable(root, arg, varRelid, &vardata);

	if (HeapTupleIsValid(vardata.statsTuple))
	{
		Form_pg_statistic stats;
		double		freq_null;
		Datum	   *values;
		int			nvalues;
		float4	   *numbers;
		int			nnumbers;

		stats = (Form_pg_statistic) GETSTRUCT(vardata.statsTuple);
		freq_null = stats->stanullfrac;

		if (get_attstatsslot(vardata.statsTuple,
							 vardata.atttype, vardata.atttypmod,
							 STATISTIC_KIND_MCV, InvalidOid,
							 &values, &nvalues,
							 &numbers, &nnumbers)
			&& nnumbers > 0)
		{
			double		freq_true;
			double		freq_false;

			/*
			 * Get first MCV frequency and derive frequency for true.
			 */
			if (DatumGetBool(values[0]))
				freq_true = numbers[0];
			else
				freq_true = 1.0 - numbers[0] - freq_null;

			/*
			 * Next derive frequency for false. Then use these as appropriate
			 * to derive frequency for each case.
			 */
			freq_false = 1.0 - freq_true - freq_null;

			switch (booltesttype)
			{
				case IS_UNKNOWN:
					/* select only NULL values */
					selec = freq_null;
					break;
				case IS_NOT_UNKNOWN:
					/* select non-NULL values */
					selec = 1.0 - freq_null;
					break;
				case IS_TRUE:
					/* select only TRUE values */
					selec = freq_true;
					break;
				case IS_NOT_TRUE:
					/* select non-TRUE values */
					selec = 1.0 - freq_true;
					break;
				case IS_FALSE:
					/* select only FALSE values */
					selec = freq_false;
					break;
				case IS_NOT_FALSE:
					/* select non-FALSE values */
					selec = 1.0 - freq_false;
					break;
				default:
					elog(ERROR, "unrecognized booltesttype: %d",
						 (int) booltesttype);
					selec = 0.0;	/* Keep compiler quiet */
					break;
			}

			free_attstatsslot(vardata.atttype, values, nvalues,
							  numbers, nnumbers);
		}
		else
		{
			/*
			 * No most-common-value info available. Still have null fraction
			 * information, so use it for IS [NOT] UNKNOWN. Otherwise adjust
			 * for null fraction and assume an even split for boolean tests.
			 */
			switch (booltesttype)
			{
				case IS_UNKNOWN:

					/*
					 * Use freq_null directly.
					 */
					selec = freq_null;
					break;
				case IS_NOT_UNKNOWN:

					/*
					 * Select not unknown (not null) values. Calculate from
					 * freq_null.
					 */
					selec = 1.0 - freq_null;
					break;
				case IS_TRUE:
				case IS_NOT_TRUE:
				case IS_FALSE:
				case IS_NOT_FALSE:
					selec = (1.0 - freq_null) / 2.0;
					break;
				default:
					elog(ERROR, "unrecognized booltesttype: %d",
						 (int) booltesttype);
					selec = 0.0;	/* Keep compiler quiet */
					break;
			}
		}
	}
	else
	{
		/*
		 * If we can't get variable statistics for the argument, perhaps
		 * clause_selectivity can do something with it.  We ignore the
		 * possibility of a NULL value when using clause_selectivity, and just
		 * assume the value is either TRUE or FALSE.
		 */
		switch (booltesttype)
		{
			case IS_UNKNOWN:
				selec = DEFAULT_UNK_SEL;
				break;
			case IS_NOT_UNKNOWN:
				selec = DEFAULT_NOT_UNK_SEL;
				break;
			case IS_TRUE:
			case IS_NOT_FALSE:
				selec = (double) clause_selectivity(root, arg,
													varRelid, jointype);
				break;
			case IS_FALSE:
			case IS_NOT_TRUE:
				selec = 1.0 - (double) clause_selectivity(root, arg,
														  varRelid, jointype);
				break;
			default:
				elog(ERROR, "unrecognized booltesttype: %d",
					 (int) booltesttype);
				selec = 0.0;	/* Keep compiler quiet */
				break;
		}
	}

	ReleaseVariableStats(vardata);

	/* result should be in range, but make sure... */
	CLAMP_PROBABILITY(selec);

	return (Selectivity) selec;
}

/*
 *		nulltestsel		- Selectivity of NullTest Node.
 */
Selectivity
nulltestsel(PlannerInfo *root, NullTestType nulltesttype,
			Node *arg, int varRelid)
{
	VariableStatData vardata;
	double		selec;

	examine_variable(root, arg, varRelid, &vardata);

	if (HeapTupleIsValid(vardata.statsTuple))
	{
		Form_pg_statistic stats;
		double		freq_null;

		stats = (Form_pg_statistic) GETSTRUCT(vardata.statsTuple);
		freq_null = stats->stanullfrac;

		switch (nulltesttype)
		{
			case IS_NULL:

				/*
				 * Use freq_null directly.
				 */
				selec = freq_null;
				break;
			case IS_NOT_NULL:

				/*
				 * Select not unknown (not null) values. Calculate from
				 * freq_null.
				 */
				selec = 1.0 - freq_null;
				break;
			default:
				elog(ERROR, "unrecognized nulltesttype: %d",
					 (int) nulltesttype);
				return (Selectivity) 0; /* keep compiler quiet */
		}
	}
	else
	{
		/*
		 * No VACUUM ANALYZE stats available, so make a guess
		 */
		switch (nulltesttype)
		{
			case IS_NULL:
				selec = DEFAULT_UNK_SEL;
				break;
			case IS_NOT_NULL:
				selec = DEFAULT_NOT_UNK_SEL;
				break;
			default:
				elog(ERROR, "unrecognized nulltesttype: %d",
					 (int) nulltesttype);
				return (Selectivity) 0; /* keep compiler quiet */
		}
	}

	ReleaseVariableStats(vardata);

	/* result should be in range, but make sure... */
	CLAMP_PROBABILITY(selec);

	return (Selectivity) selec;
}

/*
 *		eqjoinsel		- Join selectivity of "="
 */
Datum
eqjoinsel(PG_FUNCTION_ARGS)
{
	PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0);
	Oid			operator = PG_GETARG_OID(1);
	List	   *args = (List *) PG_GETARG_POINTER(2);
	JoinType	jointype = (JoinType) PG_GETARG_INT16(3);
	double		selec;
	VariableStatData vardata1;
	VariableStatData vardata2;
	double		nd1;
	double		nd2;
	Form_pg_statistic stats1 = NULL;
	Form_pg_statistic stats2 = NULL;
	bool		have_mcvs1 = false;
	Datum	   *values1 = NULL;
	int			nvalues1 = 0;
	float4	   *numbers1 = NULL;
	int			nnumbers1 = 0;
	bool		have_mcvs2 = false;
	Datum	   *values2 = NULL;
	int			nvalues2 = 0;
	float4	   *numbers2 = NULL;
	int			nnumbers2 = 0;

	get_join_variables(root, args, &vardata1, &vardata2);

	nd1 = get_variable_numdistinct(&vardata1);
	nd2 = get_variable_numdistinct(&vardata2);

	if (HeapTupleIsValid(vardata1.statsTuple))
	{
		stats1 = (Form_pg_statistic) GETSTRUCT(vardata1.statsTuple);
		have_mcvs1 = get_attstatsslot(vardata1.statsTuple,
									  vardata1.atttype,
									  vardata1.atttypmod,
									  STATISTIC_KIND_MCV,
									  InvalidOid,
									  &values1, &nvalues1,
									  &numbers1, &nnumbers1);
	}

	if (HeapTupleIsValid(vardata2.statsTuple))
	{
		stats2 = (Form_pg_statistic) GETSTRUCT(vardata2.statsTuple);
		have_mcvs2 = get_attstatsslot(vardata2.statsTuple,
									  vardata2.atttype,
									  vardata2.atttypmod,
									  STATISTIC_KIND_MCV,
									  InvalidOid,
									  &values2, &nvalues2,
									  &numbers2, &nnumbers2);
	}

	if (have_mcvs1 && have_mcvs2)
	{
		/*
		 * We have most-common-value lists for both relations.	Run through
		 * the lists to see which MCVs actually join to each other with the
		 * given operator.	This allows us to determine the exact join
		 * selectivity for the portion of the relations represented by the MCV
		 * lists.  We still have to estimate for the remaining population, but
		 * in a skewed distribution this gives us a big leg up in accuracy.
		 * For motivation see the analysis in Y. Ioannidis and S.
		 * Christodoulakis, "On the propagation of errors in the size of join
		 * results", Technical Report 1018, Computer Science Dept., University
		 * of Wisconsin, Madison, March 1991 (available from ftp.cs.wisc.edu).
		 */
		FmgrInfo	eqproc;
		bool	   *hasmatch1;
		bool	   *hasmatch2;
		double		nullfrac1 = stats1->stanullfrac;
		double		nullfrac2 = stats2->stanullfrac;
		double		matchprodfreq,
					matchfreq1,
					matchfreq2,
					unmatchfreq1,
					unmatchfreq2,
					otherfreq1,
					otherfreq2,
					totalsel1,
					totalsel2;
		int			i,
					nmatches;

		fmgr_info(get_opcode(operator), &eqproc);
		hasmatch1 = (bool *) palloc0(nvalues1 * sizeof(bool));
		hasmatch2 = (bool *) palloc0(nvalues2 * sizeof(bool));

		/*
		 * If we are doing any variant of JOIN_IN, pretend all the values of
		 * the righthand relation are unique (ie, act as if it's been
		 * DISTINCT'd).
		 *