xuzifu666 commented on code in PR #5052:
URL: https://github.com/apache/calcite/pull/5052#discussion_r3540918159
##########
core/src/main/java/org/apache/calcite/sql/validate/SqlValidatorImpl.java:
##########
@@ -5658,6 +5669,333 @@ protected RelDataType validateSelectList(final
SqlNodeList selectItems,
return typeFactory.createStructType(fieldList);
}
+ /**
+ * Rewrites scalar sub-queries in the SELECT list whose single select item is
+ * an aggregate function whose arguments reference only outer columns. Per
the
+ * SQL standard, such aggregates belong to the outer query.
+ *
+ * <p>The algorithm is:
+ * <ol>
+ * <li>For each item in the SELECT list, check whether it is a scalar
+ * sub-query, optionally wrapped in {@code AS} or {@code WITH}.
+ * <li>Inside the sub-query, require the SELECT list to contain exactly one
+ * item, and that item to be an aggregate function call.
+ * <li>Require every argument of the aggregate to reference only columns from
+ * the outer query (no inner columns), and to contain no nested sub-queries.
+ * <li>If all conditions hold, lift the aggregate out of the sub-query: keep
+ * the aggregate in the outer SELECT list, and guard it with
+ * {@code (SELECT 1 FROM ... LIMIT 1) IS NOT NULL}. The result is equivalent
+ * because the aggregate is evaluated over the outer rows, but yields NULL
+ * whenever the inner query has no rows (as the original scalar sub-query
+ * would).
+ * <li>If the outer query becomes an aggregate query as a result, upgrade its
+ * SELECT clause scope from {@link SelectScope} to
+ * {@link AggregatingSelectScope}.
+ * </ol>
+ *
+ * <p>For example,
+ * <blockquote><pre>
+ * WITH aa(a) AS (VALUES 1, 2, 3),
+ * t(x) AS (VALUES 10, 20, 30)
+ * SELECT (SELECT sum(a) FROM t) FROM aa
+ * </pre></blockquote>
+ * is rewritten to
+ * <blockquote><pre>
+ * WITH aa(a) AS (VALUES 1, 2, 3),
+ * t(x) AS (VALUES 10, 20, 30)
+ * SELECT CASE WHEN (SELECT 1 FROM t LIMIT 1) IS NOT NULL
+ * THEN sum(a) END FROM aa
+ * </pre></blockquote>
+ */
+ private void rewriteOuterAggregatesInSelectList(SqlSelect select) {
+ final SqlNodeList selectItems = select.getSelectList();
+ if (selectItems == null) {
+ return;
+ }
+ final SqlValidatorScope selectScope = getSelectScope(select);
+ final boolean wasAggregate = isAggregate(select);
+ for (int i = 0; i < selectItems.size(); i++) {
+ final SqlNode selectItem = selectItems.get(i);
+ final SqlNode rewrittenItem =
+ rewriteOuterAggregateItem(selectScope, selectItem);
+ if (rewrittenItem != selectItem) {
+ selectItems.set(i, rewrittenItem);
+ }
+ }
+ // The rewrite may have introduced an aggregate into a query that was not
+ // previously aggregate. Update the SELECT clause scope accordingly so that
+ // subsequent validation and conversion see an AggregatingSelectScope.
+ if (!wasAggregate && isAggregate(select)) {
+ SqlValidatorScope scope =
+ clauseScopes.get(IdPair.of(select, Clause.SELECT));
+ if (scope instanceof AggregatingSelectScope) {
+ scope = ((AggregatingSelectScope) scope).getParent();
+ }
+ clauseScopes.put(IdPair.of(select, Clause.SELECT),
+ new AggregatingSelectScope(
+ requireNonNull(scope, "scope"), select, false));
+ }
+ }
+
+ /**
+ * Validates that the SELECT list does not contain a correlated aggregate
+ * when the current conformance does not allow it.
+ */
+ private void checkNoCorrelatedAggregatesInSelectList(SqlSelect select) {
+ final SqlNodeList selectItems = select.getSelectList();
+ if (selectItems == null) {
+ return;
+ }
+ final SqlValidatorScope selectScope = getSelectScope(select);
+ for (SqlNode selectItem : selectItems) {
+ final SqlSelect subQuery = findScalarSubQuerySelect(selectItem);
+ if (subQuery == null) {
+ continue;
+ }
+ final SqlCall aggCall = findCorrelatedAggregate(subQuery, selectScope);
+ if (aggCall != null) {
+ throw newValidationError(aggCall,
+ RESOURCE.correlatedAggregateNotAllowed());
+ }
+ }
+ }
+
+ /**
+ * Rewrites a single SELECT list item if it is a scalar sub-query containing
+ * an aggregate over outer columns.
+ *
+ * @return the rewritten expression, or {@code selectItem} if no rewrite
applies
+ */
+ private SqlNode rewriteOuterAggregateItem(SqlValidatorScope parentScope,
+ SqlNode selectItem) {
+ final SqlSelect subQuery = findScalarSubQuerySelect(selectItem);
+ if (subQuery == null) {
+ return selectItem;
+ }
+ // Unwrap AS.
+ SqlNode expr = selectItem;
+ @Nullable SqlIdentifier alias = null;
+ if (SqlUtil.isCallTo(selectItem, SqlStdOperatorTable.AS)) {
+ SqlCall asCall = (SqlCall) selectItem;
+ expr = asCall.operand(0);
+ alias = asCall.operand(1);
+ }
+ final SqlBasicCall scalarSubQuery = (SqlBasicCall) expr;
+ final SqlNode query = scalarSubQuery.operand(0);
+ final SqlNode rewrittenSubQuery =
+ rewriteOuterAggregate(query, subQuery, parentScope);
+ if (rewrittenSubQuery == query) {
+ return selectItem;
+ }
+ SqlNode result = rewrittenSubQuery;
+ if (alias != null) {
+ result =
+ SqlStdOperatorTable.AS.createCall(selectItem.getParserPosition(),
+ rewrittenSubQuery, alias);
+ }
+ return result;
+ }
+
+ /**
+ * Extracts the {@link SqlSelect} from a SELECT list item that is a scalar
+ * sub-query, optionally wrapped in {@code AS}.
+ *
+ * @return the sub-query's SELECT, or {@code null} if the item is not a
+ * scalar sub-query
+ */
+ private @Nullable SqlSelect findScalarSubQuerySelect(SqlNode selectItem) {
+ SqlNode expr = selectItem;
+ if (SqlUtil.isCallTo(selectItem, SqlStdOperatorTable.AS)) {
+ expr = ((SqlCall) selectItem).operand(0);
+ }
+ if (!SqlUtil.isCallTo(expr, SqlStdOperatorTable.SCALAR_QUERY)) {
+ return null;
+ }
+ final SqlNode query = ((SqlBasicCall) expr).operand(0);
+ return query instanceof SqlWith
+ ? (SqlSelect) ((SqlWith) query).body
+ : query instanceof SqlSelect
+ ? (SqlSelect) query
+ : null;
+ }
+
+ /**
+ * Finds the aggregate function in a scalar sub-query's SELECT list whose
+ * arguments reference only columns from the outer query. Such an aggregate
+ * belongs to the outer query per the SQL standard.
+ *
+ * <p>Returns {@code null} unless the sub-query has exactly one select item,
Review Comment:
Thank you for pointing this issue, the previous implementation could not
correctly handle this scenario.
So I've extended the rewrite to handle this(For the sake of clarity, I have
also modified this comment): Instead of requiring the select item to be a
single aggregate call, findCorrelatedAggregate now lifts any select item that
contains an aggregate and references only outer columns (checked by applying
referencesOnlyOuterColumns to the whole item). So sum(a) + sum(b) over outer
columns is now lifted as a whole to the outer query.
The mixed case is handled safely: if the expression references any inner
column (e.g. sum(a) + sum(x) where x is inner), referencesOnlyOuterColumns
returns false and we don't rewrite, keeping the pre-existing behaviour rather
than silently producing a wrong result.
I've added test cases for all three: sum(a) + sum(b) (lifted, single row),
sum(a) + sum(x) (mixed, not lifted), and an empty-inner-table guard case, plus
validator-level conformance tests.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
