clauses.c

来自「postgresql8.3.4源码,开源数据库」· C语言 代码 · 共 2,294 行 · 第 1/5 页

 *
 * Returns true if any nonstrict construct is found --- ie, anything that
 * could produce non-NULL output with a NULL input.
 *
 * The idea here is that the caller has verified that the expression contains
 * one or more Var or Param nodes (as appropriate for the caller's need), and
 * now wishes to prove that the expression result will be NULL if any of these
 * inputs is NULL.	If we return false, then the proof succeeded.
 */
bool
contain_nonstrict_functions(Node *clause)
{
	return contain_nonstrict_functions_walker(clause, NULL);
}

static bool
contain_nonstrict_functions_walker(Node *node, void *context)
{
	if (node == NULL)
		return false;
	if (IsA(node, Aggref))
	{
		/* an aggregate could return non-null with null input */
		return true;
	}
	if (IsA(node, ArrayRef))
	{
		/* array assignment is nonstrict, but subscripting is strict */
		if (((ArrayRef *) node)->refassgnexpr != NULL)
			return true;
		/* else fall through to check args */
	}
	if (IsA(node, FuncExpr))
	{
		FuncExpr   *expr = (FuncExpr *) node;

		if (!func_strict(expr->funcid))
			return true;
		/* else fall through to check args */
	}
	if (IsA(node, OpExpr))
	{
		OpExpr	   *expr = (OpExpr *) node;

		set_opfuncid(expr);
		if (!func_strict(expr->opfuncid))
			return true;
		/* else fall through to check args */
	}
	if (IsA(node, DistinctExpr))
	{
		/* IS DISTINCT FROM is inherently non-strict */
		return true;
	}
	if (IsA(node, ScalarArrayOpExpr))
	{
		ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node;

		if (!is_strict_saop(expr, false))
			return true;
		/* else fall through to check args */
	}
	if (IsA(node, BoolExpr))
	{
		BoolExpr   *expr = (BoolExpr *) node;

		switch (expr->boolop)
		{
			case AND_EXPR:
			case OR_EXPR:
				/* AND, OR are inherently non-strict */
				return true;
			default:
				break;
		}
	}
	if (IsA(node, SubLink))
	{
		/* In some cases a sublink might be strict, but in general not */
		return true;
	}
	if (IsA(node, SubPlan))
		return true;
	/* ArrayCoerceExpr is strict at the array level, regardless of elemfunc */
	if (IsA(node, FieldStore))
		return true;
	if (IsA(node, CaseExpr))
		return true;
	if (IsA(node, ArrayExpr))
		return true;
	if (IsA(node, RowExpr))
		return true;
	if (IsA(node, RowCompareExpr))
		return true;
	if (IsA(node, CoalesceExpr))
		return true;
	if (IsA(node, MinMaxExpr))
		return true;
	if (IsA(node, XmlExpr))
		return true;
	if (IsA(node, NullIfExpr))
		return true;
	if (IsA(node, NullTest))
		return true;
	if (IsA(node, BooleanTest))
		return true;
	return expression_tree_walker(node, contain_nonstrict_functions_walker,
								  context);
}


/*
 * find_nonnullable_rels
 *		Determine which base rels are forced nonnullable by given clause.
 *
 * Returns the set of all Relids that are referenced in the clause in such
 * a way that the clause cannot possibly return TRUE if any of these Relids
 * is an all-NULL row.	(It is OK to err on the side of conservatism; hence
 * the analysis here is simplistic.)
 *
 * The semantics here are subtly different from contain_nonstrict_functions:
 * that function is concerned with NULL results from arbitrary expressions,
 * but here we assume that the input is a Boolean expression, and wish to
 * see if NULL inputs will provably cause a FALSE-or-NULL result.  We expect
 * the expression to have been AND/OR flattened and converted to implicit-AND
 * format.
 *
 * top_level is TRUE while scanning top-level AND/OR structure; here, showing
 * the result is either FALSE or NULL is good enough.  top_level is FALSE when
 * we have descended below a NOT or a strict function: now we must be able to
 * prove that the subexpression goes to NULL.
 *
 * We don't use expression_tree_walker here because we don't want to descend
 * through very many kinds of nodes; only the ones we can be sure are strict.
 */
Relids
find_nonnullable_rels(Node *clause)
{
	return find_nonnullable_rels_walker(clause, true);
}

static Relids
find_nonnullable_rels_walker(Node *node, bool top_level)
{
	Relids		result = NULL;
	ListCell   *l;

	if (node == NULL)
		return NULL;
	if (IsA(node, Var))
	{
		Var		   *var = (Var *) node;

		if (var->varlevelsup == 0)
			result = bms_make_singleton(var->varno);
	}
	else if (IsA(node, List))
	{
		/*
		 * At top level, we are examining an implicit-AND list: if any of the
		 * arms produces FALSE-or-NULL then the result is FALSE-or-NULL. If
		 * not at top level, we are examining the arguments of a strict
		 * function: if any of them produce NULL then the result of the
		 * function must be NULL.  So in both cases, the set of nonnullable
		 * rels is the union of those found in the arms, and we pass down the
		 * top_level flag unmodified.
		 */
		foreach(l, (List *) node)
		{
			result = bms_join(result,
							  find_nonnullable_rels_walker(lfirst(l),
														   top_level));
		}
	}
	else if (IsA(node, FuncExpr))
	{
		FuncExpr   *expr = (FuncExpr *) node;

		if (func_strict(expr->funcid))
			result = find_nonnullable_rels_walker((Node *) expr->args, false);
	}
	else if (IsA(node, OpExpr))
	{
		OpExpr	   *expr = (OpExpr *) node;

		set_opfuncid(expr);
		if (func_strict(expr->opfuncid))
			result = find_nonnullable_rels_walker((Node *) expr->args, false);
	}
	else if (IsA(node, ScalarArrayOpExpr))
	{
		ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node;

		if (is_strict_saop(expr, true))
			result = find_nonnullable_rels_walker((Node *) expr->args, false);
	}
	else if (IsA(node, BoolExpr))
	{
		BoolExpr   *expr = (BoolExpr *) node;

		switch (expr->boolop)
		{
			case AND_EXPR:
				/* At top level we can just recurse (to the List case) */
				if (top_level)
				{
					result = find_nonnullable_rels_walker((Node *) expr->args,
														  top_level);
					break;
				}

				/*
				 * Below top level, even if one arm produces NULL, the result
				 * could be FALSE (hence not NULL).  However, if *all* the
				 * arms produce NULL then the result is NULL, so we can take
				 * the intersection of the sets of nonnullable rels, just as
				 * for OR.	Fall through to share code.
				 */
				/* FALL THRU */
			case OR_EXPR:

				/*
				 * OR is strict if all of its arms are, so we can take the
				 * intersection of the sets of nonnullable rels for each arm.
				 * This works for both values of top_level.
				 */
				foreach(l, expr->args)
				{
					Relids		subresult;

					subresult = find_nonnullable_rels_walker(lfirst(l),
															 top_level);
					if (result == NULL) /* first subresult? */
						result = subresult;
					else
						result = bms_int_members(result, subresult);

					/*
					 * If the intersection is empty, we can stop looking. This
					 * also justifies the test for first-subresult above.
					 */
					if (bms_is_empty(result))
						break;
				}
				break;
			case NOT_EXPR:
				/* NOT will return null if its arg is null */
				result = find_nonnullable_rels_walker((Node *) expr->args,
													  false);
				break;
			default:
				elog(ERROR, "unrecognized boolop: %d", (int) expr->boolop);
				break;
		}
	}
	else if (IsA(node, RelabelType))
	{
		RelabelType *expr = (RelabelType *) node;

		result = find_nonnullable_rels_walker((Node *) expr->arg, top_level);
	}
	else if (IsA(node, CoerceViaIO))
	{
		/* not clear this is useful, but it can't hurt */
		CoerceViaIO *expr = (CoerceViaIO *) node;

		result = find_nonnullable_rels_walker((Node *) expr->arg, top_level);
	}
	else if (IsA(node, ArrayCoerceExpr))
	{
		/* ArrayCoerceExpr is strict at the array level */
		ArrayCoerceExpr *expr = (ArrayCoerceExpr *) node;

		result = find_nonnullable_rels_walker((Node *) expr->arg, top_level);
	}
	else if (IsA(node, ConvertRowtypeExpr))
	{
		/* not clear this is useful, but it can't hurt */
		ConvertRowtypeExpr *expr = (ConvertRowtypeExpr *) node;

		result = find_nonnullable_rels_walker((Node *) expr->arg, top_level);
	}
	else if (IsA(node, NullTest))
	{
		/* IS NOT NULL can be considered strict, but only at top level */
		NullTest   *expr = (NullTest *) node;

		if (top_level && expr->nulltesttype == IS_NOT_NULL)
			result = find_nonnullable_rels_walker((Node *) expr->arg, false);
	}
	else if (IsA(node, BooleanTest))
	{
		/* Boolean tests that reject NULL are strict at top level */
		BooleanTest *expr = (BooleanTest *) node;

		if (top_level &&
			(expr->booltesttype == IS_TRUE ||
			 expr->booltesttype == IS_FALSE ||
			 expr->booltesttype == IS_NOT_UNKNOWN))
			result = find_nonnullable_rels_walker((Node *) expr->arg, false);
	}
	return result;
}

/*
 * Can we treat a ScalarArrayOpExpr as strict?
 *
 * If "falseOK" is true, then a "false" result can be considered strict,
 * else we need to guarantee an actual NULL result for NULL input.
 *
 * "foo op ALL array" is strict if the op is strict *and* we can prove
 * that the array input isn't an empty array.  We can check that
 * for the cases of an array constant and an ARRAY[] construct.
 *
 * "foo op ANY array" is strict in the falseOK sense if the op is strict.
 * If not falseOK, the test is the same as for "foo op ALL array".
 */
static bool
is_strict_saop(ScalarArrayOpExpr *expr, bool falseOK)
{
	Node	   *rightop;

	/* The contained operator must be strict. */
	set_sa_opfuncid(expr);
	if (!func_strict(expr->opfuncid))
		return false;
	/* If ANY and falseOK, that's all we need to check. */
	if (expr->useOr && falseOK)
		return true;
	/* Else, we have to see if the array is provably non-empty. */
	Assert(list_length(expr->args) == 2);
	rightop = (Node *) lsecond(expr->args);
	if (rightop && IsA(rightop, Const))
	{
		Datum		arraydatum = ((Const *) rightop)->constvalue;
		bool		arrayisnull = ((Const *) rightop)->constisnull;
		ArrayType  *arrayval;
		int			nitems;

		if (arrayisnull)
			return false;
		arrayval = DatumGetArrayTypeP(arraydatum);
		nitems = ArrayGetNItems(ARR_NDIM(arrayval), ARR_DIMS(arrayval));
		if (nitems > 0)
			return true;
	}
	else if (rightop && IsA(rightop, ArrayExpr))
	{
		ArrayExpr  *arrayexpr = (ArrayExpr *) rightop;

		if (arrayexpr->elements != NIL && !arrayexpr->multidims)
			return true;
	}
	return false;
}


/*****************************************************************************
 *		Check for "pseudo-constant" clauses
 *****************************************************************************/

/*
 * is_pseudo_constant_clause
 *	  Detect whether an expression is "pseudo constant", ie, it contains no
 *	  variables of the current query level and no uses of volatile functions.
 *	  Such an expr is not necessarily a true constant: it can still contain
 *	  Params and outer-level Vars, not to mention functions whose results
 *	  may vary from one statement to the next.	However, the expr's value
 *	  will be constant over any one scan of the current query, so it can be
 *	  used as, eg, an indexscan key.
 *
 * CAUTION: this function omits to test for one very important class of
 * not-constant expressions, namely aggregates (Aggrefs).  In current usage
 * this is only applied to WHERE clauses and so a check for Aggrefs would be
 * a waste of cycles; but be sure to also check contain_agg_clause() if you
 * want to know about pseudo-constness in other contexts.
 */
bool
is_pseudo_constant_clause(Node *clause)
{
	/*
	 * We could implement this check in one recursive scan.  But since the
	 * check for volatile functions is both moderately expensive and unlikely
	 * to fail, it seems better to look for Vars first and only check for
	 * volatile functions if we find no Vars.
	 */
	if (!contain_var_clause(clause) &&
		!contain_volatile_functions(clause))
		return true;
	return false;
}

/*
 * is_pseudo_constant_clause_relids
 *	  Same as above, except caller already has available the var membership
 *	  of the expression; this lets us avoid the contain_var_clause() scan.
 */
bool
is_pseudo_constant_clause_relids(Node *clause, Relids relids)
{
	if (bms_is_empty(relids) &&
		!contain_volatile_functions(clause))
		return true;
	return false;
}


/*****************************************************************************
 *		Tests on clauses of queries
 *
 * Possibly this code should go someplace else, since this isn't quite the
 * same meaning of "clause" as is used elsewhere in this module.  But I can't
 * think of a better place for it...
 *****************************************************************************/

/*
 * Test whether a query uses DISTINCT ON, ie, has a distinct-list that is
 * not the same as the set of output columns.
 */
bool
has_distinct_on_clause(Query *query)
{
	ListCell   *l;

	/* Is there a DISTINCT clause at all? */
	if (query->distinctClause == NIL)
		return false;

	/*
	 * If the DISTINCT list contains all the nonjunk targetlist items, and
	 * nothing else (ie, no junk tlist items), then it's a simple DISTINCT,
	 * else it's DISTINCT ON.  We do not require the lists to be in the same
	 * order (since the parser may have adjusted the DISTINCT clause ordering
	 * to agree with ORDER BY).  Furthermore, a non-DISTINCT junk tlist item
	 * that is in the sortClause is also evidence of DISTINCT ON, since we
	 * don't allow ORDER BY on junk tlist items when plain DISTINCT is used.
	 *
	 * This code assumes that the DISTINCT list is valid, ie, all its entries
	 * match some entry of the tlist.
	 */
	foreach(l, query->targetList)
	{
		TargetEntry *tle = (TargetEntry *) lfirst(l);

		if (tle->ressortgroupref == 0)
		{
			if (tle->resjunk)
				continue;		/* we can ignore unsorted junk cols */
			return true;		/* definitely not in DISTINCT list */
		}
		if (targetIsInSortList(tle, InvalidOid, query->distinctClause))
		{
			if (tle->resjunk)
				return true;	/* junk TLE in DISTINCT means DISTINCT ON */
			/* else this TLE is okay, keep looking */
		}
		else
		{
			/* This TLE is not in DISTINCT list */