Skip to content

YQL-17526 finilize fixing sample rate #2146

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
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
2 changes: 1 addition & 1 deletion ydb/library/yql/sql/v1/select.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -735,7 +735,7 @@ class TTableSource: public IRealSource {
return false;
}

samplingRate = PrepareSamplingRate(pos, sampleClause, samplingRate, true);
samplingRate = PrepareSamplingRate(pos, sampleClause, samplingRate);

auto sampleSettings = Q(Y(Q(modeName), Y("EvaluateAtom", Y("ToString", samplingRate)), Y("EvaluateAtom", Y("ToString", samplingSeed))));
auto sampleOption = Q(Y(Q("sample"), sampleSettings));
Expand Down
25 changes: 8 additions & 17 deletions ydb/library/yql/sql/v1/source.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -394,26 +394,17 @@ TWriteSettings ISource::GetWriteSettings() const {
return {};
}

TNodePtr ISource::PrepareSamplingRate(TPosition pos, ESampleClause clause, TNodePtr samplingRate, bool tempUseBlockExpr) {
TNodePtr ISource::PrepareSamplingRate(TPosition pos, ESampleClause clause, TNodePtr samplingRate) {
if (ESampleClause::Sample == clause) {
samplingRate = Y("*", samplingRate, Y("Double", Q("100")));
}
//TODO YQL-17526 temp for minimizing diff in canonized tests
if (tempUseBlockExpr) {
auto ensureLow = Y("Ensure", "samplingRate", Y(">=", "samplingRate", Y("Double", Q("0"))), Y("String", BuildQuotedAtom(pos, "Expected sampling rate to be nonnegative")));
auto ensureHigh = Y("Ensure", "samplingRate", Y("<=", "samplingRate", Y("Double", Q("100"))), Y("String", BuildQuotedAtom(pos, "Sampling rate is over 100%")));
auto ensureLow = Y("Ensure", "samplingRate", Y(">=", "samplingRate", Y("Double", Q("0"))), Y("String", BuildQuotedAtom(pos, "Expected sampling rate to be nonnegative")));
auto ensureHigh = Y("Ensure", "samplingRate", Y("<=", "samplingRate", Y("Double", Q("100"))), Y("String", BuildQuotedAtom(pos, "Sampling rate is over 100%")));

auto block(Y(Y("let", "samplingRate", samplingRate)));
block = L(block, Y("let", "samplingRate", ensureLow));
block = L(block, Y("let", "samplingRate", ensureHigh));

samplingRate = Y("block", Q(L(block, Y("return", "samplingRate"))));
} else {
samplingRate = Y("Ensure", samplingRate, Y(">=", samplingRate, Y("Double", Q("0"))),
Y("String", Q("\"Expected sampling rate to be nonnegative\"")));
samplingRate = Y("Ensure", samplingRate, Y("<=", samplingRate, Y("Double", Q("100"))),
Y("String", Q("\"Sampling rate is over 100%\"")));
}
auto block(Y(Y("let", "samplingRate", samplingRate)));
block = L(block, Y("let", "samplingRate", ensureLow));
block = L(block, Y("let", "samplingRate", ensureHigh));
samplingRate = Y("block", Q(L(block, Y("return", "samplingRate"))));
return samplingRate;
}

Expand Down Expand Up @@ -560,7 +551,7 @@ bool ISource::SetSamplingRate(TContext& ctx, ESampleClause clause, TNodePtr samp
if (!samplingRate->Init(ctx, this)) {
return false;
}
SamplingRate = PrepareSamplingRate(Pos, clause, samplingRate, false);
SamplingRate = PrepareSamplingRate(Pos, clause, samplingRate);
}
return true;
}
Expand Down
2 changes: 1 addition & 1 deletion ydb/library/yql/sql/v1/source.h
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ namespace NSQLTranslationV1 {
virtual bool IsStream() const;
virtual EOrderKind GetOrderKind() const;
virtual TWriteSettings GetWriteSettings() const;
TNodePtr PrepareSamplingRate(TPosition pos, ESampleClause clause, TNodePtr samplingRate, bool tempUseBlockExpr); //TODO fixme YQL-17526
TNodePtr PrepareSamplingRate(TPosition pos, ESampleClause clause, TNodePtr samplingRate);
virtual bool SetSamplingOptions(TContext& ctx, TPosition pos, ESampleClause clause, ESampleMode mode, TNodePtr samplingRate, TNodePtr samplingSeed);
virtual bool SetTableHints(TContext& ctx, TPosition pos, const TTableHints& hints, const TTableHints& contextHints);
virtual bool CalculateGroupingHint(TContext& ctx, const TVector<TString>& columns, ui64& hint) const;
Expand Down
90 changes: 45 additions & 45 deletions ydb/library/yql/tests/sql/sql2yql/canondata/result.json
Original file line number Diff line number Diff line change
Expand Up @@ -14155,16 +14155,16 @@
],
"test_sql2yql.test[sampling-bind_default]": [
{
"checksum": "a51d273308865245f068c36d91e21450",
"size": 2260,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-bind_default_/sql.yql"
"checksum": "a04f94b9380fc43e2131beaab18eebcf",
"size": 2341,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-bind_default_/sql.yql"
}
],
"test_sql2yql.test[sampling-bind_expr]": [
{
"checksum": "4a1b485ce7c346a70cd45b817ea54927",
"size": 3476,
"uri": "https://{canondata_backend}/1937027/973c239492ba32946806ddc66cf0af4b38c06ae8/resource.tar.gz#test_sql2yql.test_sampling-bind_expr_/sql.yql"
"checksum": "a62b5950b0d947044f56880f605c9bee",
"size": 3299,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-bind_expr_/sql.yql"
}
],
"test_sql2yql.test[sampling-bind_expr_subquery]": [
Expand All @@ -14183,37 +14183,37 @@
],
"test_sql2yql.test[sampling-bind_join_left]": [
{
"checksum": "d2aa12ea2827b5c7dbc20fa6ac349c13",
"size": 3320,
"uri": "https://{canondata_backend}/1937027/b5576dd03b65095c35e7cb4954821e4f66817b94/resource.tar.gz#test_sql2yql.test_sampling-bind_join_left_/sql.yql"
"checksum": "0039f41c005064ec96b69b0571c72e21",
"size": 3401,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-bind_join_left_/sql.yql"
}
],
"test_sql2yql.test[sampling-bind_join_right]": [
{
"checksum": "5bf8b5f8ea1ff4d683685f72ad33f469",
"size": 3154,
"uri": "https://{canondata_backend}/1937027/b5576dd03b65095c35e7cb4954821e4f66817b94/resource.tar.gz#test_sql2yql.test_sampling-bind_join_right_/sql.yql"
"checksum": "2bd5fe996098a26a36b70e16a0652d9d",
"size": 3235,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-bind_join_right_/sql.yql"
}
],
"test_sql2yql.test[sampling-bind_multiple_sample]": [
{
"checksum": "ed803b092d6cc4f201c1f0fbe1dab67f",
"size": 4449,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-bind_multiple_sample_/sql.yql"
"checksum": "bbbd8d4bfcf72298599a17c3c4ea55cd",
"size": 4608,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-bind_multiple_sample_/sql.yql"
}
],
"test_sql2yql.test[sampling-bind_small_rate]": [
{
"checksum": "1cf9ce5fc74f1e212026fa82b83a82f6",
"size": 2268,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-bind_small_rate_/sql.yql"
"checksum": "9a0107fb5a9f02eb137e9149d672f061",
"size": 2343,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-bind_small_rate_/sql.yql"
}
],
"test_sql2yql.test[sampling-bind_topsort]": [
{
"checksum": "456ade289ed489ae7b3b7f25b89e226d",
"size": 2579,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-bind_topsort_/sql.yql"
"checksum": "96340f0ef07cb33b17b30036617d9573",
"size": 2660,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-bind_topsort_/sql.yql"
}
],
"test_sql2yql.test[sampling-direct_read]": [
Expand Down Expand Up @@ -14309,9 +14309,9 @@
],
"test_sql2yql.test[sampling-sample]": [
{
"checksum": "61f9507fd003d17c8b5b6a6d4eb609b2",
"size": 3654,
"uri": "https://{canondata_backend}/1936947/d0bdc5228243912c5ef95425f5566fe38b25c878/resource.tar.gz#test_sql2yql.test_sampling-sample_/sql.yql"
"checksum": "00ca2fcfdc68ab21c3b3f94b9a0f08ef",
"size": 3675,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-sample_/sql.yql"
}
],
"test_sql2yql.test[sampling-sort]": [
Expand All @@ -14323,51 +14323,51 @@
],
"test_sql2yql.test[sampling-subquery_default]": [
{
"checksum": "c294567d38a41bb05a8053b96ee52d37",
"size": 2141,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-subquery_default_/sql.yql"
"checksum": "56121f51492c446ce76bfbe4b38eed05",
"size": 2222,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-subquery_default_/sql.yql"
}
],
"test_sql2yql.test[sampling-subquery_expr]": [
{
"checksum": "deebffa96df77a15760e21e2342da917",
"size": 3357,
"uri": "https://{canondata_backend}/1937027/973c239492ba32946806ddc66cf0af4b38c06ae8/resource.tar.gz#test_sql2yql.test_sampling-subquery_expr_/sql.yql"
"checksum": "68e68901b98cf16855eaf249fa34243b",
"size": 3180,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-subquery_expr_/sql.yql"
}
],
"test_sql2yql.test[sampling-subquery_filter]": [
{
"checksum": "292572b98078b91ccf76ea5cf5c23f8b",
"size": 2349,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-subquery_filter_/sql.yql"
"checksum": "471c149c29a379cdfaaad06b9150ed9b",
"size": 2430,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-subquery_filter_/sql.yql"
}
],
"test_sql2yql.test[sampling-subquery_limit]": [
{
"checksum": "8c082be739e34631b7d5d34eb5938573",
"size": 2227,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-subquery_limit_/sql.yql"
"checksum": "d928c82f2532fa514c7b7457c786f8b9",
"size": 2308,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-subquery_limit_/sql.yql"
}
],
"test_sql2yql.test[sampling-subquery_mapjoin]": [
{
"checksum": "e4f2b424647b60de2b7e24f75b4fa5e0",
"size": 2504,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-subquery_mapjoin_/sql.yql"
"checksum": "64087a51751fda4c8696344e4854a3a6",
"size": 2585,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-subquery_mapjoin_/sql.yql"
}
],
"test_sql2yql.test[sampling-subquery_multiple_sample]": [
{
"checksum": "08b3485d68c33580463fe1314b3564a9",
"size": 2550,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-subquery_multiple_sample_/sql.yql"
"checksum": "360c672aa2c8d7d680aa4428e73b350d",
"size": 2631,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-subquery_multiple_sample_/sql.yql"
}
],
"test_sql2yql.test[sampling-subquery_sort]": [
{
"checksum": "59c99805742112fcecadef38f3387049",
"size": 2309,
"uri": "https://{canondata_backend}/1936947/659b615f15086142a8960946dabd06b519d43335/resource.tar.gz#test_sql2yql.test_sampling-subquery_sort_/sql.yql"
"checksum": "a1760545b34529cd9ded6e9e1af16029",
"size": 2390,
"uri": "https://{canondata_backend}/1871182/d8e2ef96aa8f2c68e5369ead40ba50ab33dadf24/resource.tar.gz#test_sql2yql.test_sampling-subquery_sort_/sql.yql"
}
],
"test_sql2yql.test[sampling-system_sampling]": [
Expand Down