Skip to content

[YQL-17625] Fix ORDER BY by column missing in projections #1617

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 6, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 47 additions & 1 deletion ydb/library/yql/sql/v1/select.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1736,7 +1736,16 @@ class TSelectCore: public IRealSource {
return nullptr;
}

return Y("let", label, BuildSortSpec(OrderBy, label, false, AssumeSorted));
auto sorted = BuildSortSpec(OrderBy, label, false, AssumeSorted);
if (ExtraSortColumns.empty()) {
return Y("let", label, sorted);
}
auto body = Y();
for (const auto& [column, _] : ExtraSortColumns) {
body = L(body, Y("let", "row", Y("RemoveMember", "row", Q(column))));
}
body = L(body, Y("let", "res", "row"));
return Y("let", label, Y("OrderedMap", sorted, BuildLambda(Pos, Y("row"), body, "res")));
}

TNodePtr BuildCleanupColumns(TContext& ctx, const TString& label) override {
Expand Down Expand Up @@ -1801,6 +1810,31 @@ class TSelectCore: public IRealSource {
}
return Source->AddColumn(ctx, column);
}

if (OrderByInit && !Distinct && !GroupBy) {
bool reliable = column.IsReliable();
column.SetAsNotReliable();
auto maybeExist = IRealSource::AddColumn(ctx, column);
if (reliable) {
column.ResetAsReliable();
}
if (maybeExist && maybeExist.GetRef()) {
return true;
}

auto maybeSourceExist = Source->AddColumn(ctx, column);
if (!maybeSourceExist.Defined()) {
return maybeSourceExist;
}

// order by references column which is missing in projection, but may exists in source
const auto columnName = column.GetColumnName();
if (columnName) {
ExtraSortColumns.emplace(*columnName, TNodePtr(&column));
}
return true;
}

return IRealSource::AddColumn(ctx, column);
}

Expand Down Expand Up @@ -2139,6 +2173,17 @@ class TSelectCore: public IRealSource {
++column;
++isNamedColumn;
}

for (const auto& [columnName, column]: ExtraSortColumns) {
auto body = Y();
if (haveCompositeTerms) {
body = L(body, Y("let", "row", Y("Apply", "addCompositTerms", "row")));
}
body = L(body, Y("let", "res", column));
TPosition pos = column->GetPos();
auto projectItem = Y("SqlProjectItem", "projectCoreType", BuildQuotedAtom(pos, columnName), BuildLambda(pos, Y("row"), body, "res"));
sqlProjectArgs = L(sqlProjectArgs, projectItem);
}
}

auto block(Y(Y("let", "projectCoreType", Y("TypeOf", "core"))));
Expand Down Expand Up @@ -2199,6 +2244,7 @@ class TSelectCore: public IRealSource {
const bool SelectStream;
const TWriteSettings Settings;
const TColumnsSets UniqueSets, DistinctSets;
TMap<TString, TNodePtr> ExtraSortColumns;
};

class TProcessSource: public IRealSource {
Expand Down
11 changes: 5 additions & 6 deletions ydb/library/yql/sql/v1/sql_ut.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -2950,6 +2950,11 @@ Y_UNIT_TEST_SUITE(SqlToYQLErrors) {
UNIT_ASSERT_NO_DIFF(Err2Str(res), "<main>:1:45: Error: You should use in ORDER BY column name, qualified field, callable function or expression\n");
}

Y_UNIT_TEST(ErrorsInOrderByWhenColumnIsMissingInProjection) {
ExpectFailWithError("select subkey from (select 1 as subkey) order by key", "<main>:1:50: Error: Column key is not in source column set\n");
ExpectFailWithError("select subkey from plato.Input as a order by x.key", "<main>:1:46: Error: Unknown correlation name: x\n");
}

Y_UNIT_TEST(SelectAggregatedWhere) {
NYql::TAstParseResult res = SqlToYql("select * from plato.Input where count(key)");
UNIT_ASSERT(!res.Root);
Expand Down Expand Up @@ -3202,12 +3207,6 @@ Y_UNIT_TEST_SUITE(SqlToYQLErrors) {
UNIT_ASSERT_NO_DIFF(Err2Str(res), "<main>:1:1: Error: Duplicate column: key\n");
}

Y_UNIT_TEST(SelectOrderByUnknownLabel) {
NYql::TAstParseResult res = SqlToYql("select a from plato.Input order by b");
UNIT_ASSERT(!res.Root);
UNIT_ASSERT_NO_DIFF(Err2Str(res), "<main>:1:36: Error: Column b is not in source column set. Did you mean a?\n");
}

Y_UNIT_TEST(SelectFlattenBySameColumns) {
NYql::TAstParseResult res = SqlToYql("select key from plato.Input flatten by (key, key as kk)");
UNIT_ASSERT(!res.Root);
Expand Down
22 changes: 22 additions & 0 deletions ydb/library/yql/tests/sql/dq_file/part6/canondata/result.json
Original file line number Diff line number Diff line change
Expand Up @@ -1821,6 +1821,28 @@
}
],
"test.test[order_by-literal_single_item_sort--Results]": [],
"test.test[order_by-order_by_missing_project_column-default.txt-Analyze]": [
{
"checksum": "b5c2e8e2b9513028037ab15707571f52",
"size": 14060,
"uri": "https://{canondata_backend}/1871002/2fcd813e80c98be1c3c62b9a854d09ccca8851f8/resource.tar.gz#test.test_order_by-order_by_missing_project_column-default.txt-Analyze_/plan.txt"
}
],
"test.test[order_by-order_by_missing_project_column-default.txt-Debug]": [
{
"checksum": "749e10f58df2a7d1b43d444d02d08b4c",
"size": 4022,
"uri": "https://{canondata_backend}/1871002/2fcd813e80c98be1c3c62b9a854d09ccca8851f8/resource.tar.gz#test.test_order_by-order_by_missing_project_column-default.txt-Debug_/opt.yql_patched"
}
],
"test.test[order_by-order_by_missing_project_column-default.txt-Plan]": [
{
"checksum": "b5c2e8e2b9513028037ab15707571f52",
"size": 14060,
"uri": "https://{canondata_backend}/1871002/2fcd813e80c98be1c3c62b9a854d09ccca8851f8/resource.tar.gz#test.test_order_by-order_by_missing_project_column-default.txt-Plan_/plan.txt"
}
],
"test.test[order_by-order_by_missing_project_column-default.txt-Results]": [],
"test.test[order_by-sort_with_take--Analyze]": [
{
"checksum": "c78b6f43c8394d398e0c63aa70d6458c",
Expand Down
14 changes: 14 additions & 0 deletions ydb/library/yql/tests/sql/sql2yql/canondata/result.json
Original file line number Diff line number Diff line change
Expand Up @@ -10457,6 +10457,13 @@
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_order_by-order_by_list_of_strings_/sql.yql"
}
],
"test_sql2yql.test[order_by-order_by_missing_project_column]": [
{
"checksum": "5279857b1fc3341d168708325cb3f123",
"size": 10491,
"uri": "https://{canondata_backend}/1937429/114961b26476797b95763679349a6ea2e9f8cea8/resource.tar.gz#test_sql2yql.test_order_by-order_by_missing_project_column_/sql.yql"
}
],
"test_sql2yql.test[order_by-order_by_mul_columns]": [
{
"checksum": "3e69e4405b6dff02d1127352fe46de57",
Expand Down Expand Up @@ -27936,6 +27943,13 @@
"uri": "https://{canondata_backend}/1880306/64654158d6bfb1289c66c626a8162239289559d0/resource.tar.gz#test_sql_format.test_order_by-order_by_list_of_strings_/formatted.sql"
}
],
"test_sql_format.test[order_by-order_by_missing_project_column]": [
{
"checksum": "4cc3522c6b6eb8309231e398a855394f",
"size": 506,
"uri": "https://{canondata_backend}/1937429/114961b26476797b95763679349a6ea2e9f8cea8/resource.tar.gz#test_sql_format.test_order_by-order_by_missing_project_column_/formatted.sql"
}
],
"test_sql_format.test[order_by-order_by_mul_columns]": [
{
"checksum": "ecd62b80c49799026e8275d8c3daeaef",
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
use plato;

select subkey from Input order by key, value;
select subkey from Input order by "x" || key, value;
select subkey from Input order by key || "x" limit 3;

select subkey from Input as a order by "x" || key, a.value limit 3;
select subkey from Input as a order by a.key, value limit 1;
select subkey from Input as a order by key, value limit 2;

select subkey, key from Input order by key, value;
Original file line number Diff line number Diff line change
Expand Up @@ -1565,6 +1565,27 @@
"uri": "https://{canondata_backend}/1936997/a879c594903fb53f2cbc586abd0c0e9fac5dd32a/resource.tar.gz#test.test_order_by-literal_single_item_sort--Results_/Output.txt"
}
],
"test.test[order_by-order_by_missing_project_column-default.txt-Debug]": [
{
"checksum": "ad11528b26030156b137c66b82500102",
"size": 6459,
"uri": "https://{canondata_backend}/1871002/3978b39df1ca2a819856a9709f7dca5f5a74e2ac/resource.tar.gz#test.test_order_by-order_by_missing_project_column-default.txt-Debug_/opt.yql"
}
],
"test.test[order_by-order_by_missing_project_column-default.txt-Plan]": [
{
"checksum": "1926e1707b041bf34e0b061ad7ae3ec0",
"size": 19658,
"uri": "https://{canondata_backend}/1871002/3978b39df1ca2a819856a9709f7dca5f5a74e2ac/resource.tar.gz#test.test_order_by-order_by_missing_project_column-default.txt-Plan_/plan.txt"
}
],
"test.test[order_by-order_by_missing_project_column-default.txt-Results]": [
{
"checksum": "0bd033a7c39d748d49027400811d2547",
"size": 6050,
"uri": "https://{canondata_backend}/1871002/3978b39df1ca2a819856a9709f7dca5f5a74e2ac/resource.tar.gz#test.test_order_by-order_by_missing_project_column-default.txt-Results_/results.txt"
}
],
"test.test[order_by-sort_with_take--Debug]": [
{
"checksum": "ea8b90a7be2c019a9ee9ace75d9abd90",
Expand Down