Skip to content

YDB FQ: Support Greenplum as an external data source #4907

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.

Sign up for GitHub

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 9 commits into from
May 29, 2024
Merged

YDB FQ: Support Greenplum as an external data source #4907

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
ec5e256
[add] Greenplum
May 26, 2024
37d4089
[add] greenplum
May 27, 2024
612a11f
[fix] lint
May 28, 2024
404cc3b
[refactor]
May 28, 2024
eaa382c
[refactor]
May 29, 2024
d02a32a
[refactor]
May 29, 2024
19c0e3a
[refactor]
May 29, 2024
cc27098
[refactor]
May 29, 2024
8909099
[refactor] lint
May 29, 2024
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
7 changes: 5 additions & 2 deletions ydb/core/external_sources/external_source_factory.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,11 @@ IExternalSourceFactory::TPtr CreateExternalSourceFactory(const std::vector<TStri
{
ToString(NYql::EDatabaseType::YT),
CreateExternalDataSource(TString{NYql::YtProviderName}, {"NONE", "TOKEN"}, {}, hostnamePatternsRegEx)
}
});
},
{
ToString(NYql::EDatabaseType::Greenplum),
CreateExternalDataSource(TString{NYql::GenericProviderName}, {"MDB_BASIC", "BASIC"}, {"database_name", "mdb_cluster_id", "use_tls", "schema"}, hostnamePatternsRegEx)
}});
}

}
7 changes: 6 additions & 1 deletion ydb/library/yql/providers/common/db_id_async_resolver/db_async_resolver.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,8 @@ enum class EDatabaseType {
ObjectStorage,
PostgreSQL,
YT,
MySQL
MySQL,
Greenplum
};

inline EDatabaseType DatabaseTypeFromDataSourceKind(NConnector::NApi::EDataSourceKind dataSourceKind) {
Expand All @@ -28,6 +29,8 @@ inline EDatabaseType DatabaseTypeFromDataSourceKind(NConnector::NApi::EDataSourc
return EDatabaseType::Ydb;
case NConnector::NApi::EDataSourceKind::MYSQL:
return EDatabaseType::MySQL;
case NConnector::NApi::EDataSourceKind::GREENPLUM:
return EDatabaseType::Greenplum;
default:
ythrow yexception() << "Unknown data source kind: " << NConnector::NApi::EDataSourceKind_Name(dataSourceKind);
}
Expand All @@ -43,6 +46,8 @@ inline NConnector::NApi::EDataSourceKind DatabaseTypeToDataSourceKind(EDatabaseT
return NConnector::NApi::EDataSourceKind::YDB;
case EDatabaseType::MySQL:
return NConnector::NApi::EDataSourceKind::MYSQL;
case EDatabaseType::Greenplum:
return NConnector::NApi::EDataSourceKind::GREENPLUM;
default:
ythrow yexception() << "Unknown database type: " << ToString(databaseType);
}
Expand Down
2 changes: 1 addition & 1 deletion ydb/library/yql/providers/generic/actors/yql_generic_provider_factories.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ namespace NYql::NDq {
args.MaxKeysInRequest);
};

for (auto& name : {"ClickHouseGeneric", "PostgreSqlGeneric", "YdbGeneric", "MySqlGeneric"}) {
for (auto& name : {"ClickHouseGeneric", "PostgreSqlGeneric", "YdbGeneric", "MySqlGeneric", "GreenplumGeneric"}) {
factory.RegisterSource<Generic::TSource>(name, readActorFactory);
factory.RegisterLookupSource<Generic::TLookupSource>(name, lookupActorFactory);
}
Expand Down
7 changes: 7 additions & 0 deletions ydb/library/yql/providers/generic/connector/api/common/data_source.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,12 @@ message TS3DataSourceOptions {
string bucket = 2;
}

// TGreenplumDataSourceOptions represents settings specific to Greenplum
message TGreenplumDataSourceOptions {
// Greenplum schema
string schema = 1;
}

// TDataSourceInstance helps to identify the instance of a data source to redirect request to.
message TDataSourceInstance {
// Data source kind
Expand All @@ -83,5 +89,6 @@ message TDataSourceInstance {
TPostgreSQLDataSourceOptions pg_options = 7;
TClickhouseDataSourceOptions ch_options = 8;
TS3DataSourceOptions s3_options = 9;
TGreenplumDataSourceOptions gp_options = 10;
}
}
7 changes: 1 addition & 6 deletions ydb/library/yql/providers/generic/provider/yql_generic_cluster_config.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,12 +192,7 @@ namespace NYql {
NYql::TGenericClusterConfig& clusterConfig) {
using namespace NConnector::NApi;

if (clusterConfig.GetKind() == EDataSourceKind::YDB) {
clusterConfig.SetProtocol(EProtocol::NATIVE);
return;
}

if (clusterConfig.GetKind() == EDataSourceKind::MYSQL) {
if (IsIn({EDataSourceKind::GREENPLUM, EDataSourceKind::YDB, EDataSourceKind::MYSQL}, clusterConfig.GetKind())) {
clusterConfig.SetProtocol(EProtocol::NATIVE);
return;
}
Expand Down
6 changes: 6 additions & 0 deletions ydb/library/yql/providers/generic/provider/yql_generic_dq_integration.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,9 @@ namespace NYql {
case NYql::NConnector::NApi::YDB:
sourceType = "YdbGeneric";
break;
case NYql::NConnector::NApi::GREENPLUM:
sourceType = "GreenplumGeneric";
break;
default:
ythrow yexception() << "Data source kind is unknown or not specified";
break;
Expand Down Expand Up @@ -213,6 +216,9 @@ namespace NYql {
case NConnector::NApi::YDB:
properties["SourceType"] = "Ydb";
break;
case NConnector::NApi::GREENPLUM:
properties["SourceType"] = "Greenplum";
break;
case NConnector::NApi::DATA_SOURCE_KIND_UNSPECIFIED:
break;
default:
Expand Down
32 changes: 20 additions & 12 deletions ydb/library/yql/providers/generic/provider/yql_generic_load_meta.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -313,6 +313,20 @@ namespace NYql {
*dsi->mutable_credentials()->mutable_token()->mutable_type() = "IAM";
}

template <typename T>
void SetSchema(T& request, const TGenericClusterConfig& clusterConfig) {
TString schema;
const auto it = clusterConfig.GetDataSourceOptions().find("schema");
if (it != clusterConfig.GetDataSourceOptions().end()) {
schema = it->second;
}
if (!schema) {
schema = "public";
}

request.set_schema(schema);
}

void FillDataSourceOptions(NConnector::NApi::TDescribeTableRequest& request, const TGenericClusterConfig& clusterConfig) {
const auto dataSourceKind = clusterConfig.GetKind();
switch (dataSourceKind) {
Expand All @@ -322,19 +336,13 @@ namespace NYql {
break;
case NYql::NConnector::NApi::MYSQL:
break;
case NYql::NConnector::NApi::GREENPLUM: {
auto* options = request.mutable_data_source_instance()->mutable_gp_options();
SetSchema(*options, clusterConfig);
} break;
case NYql::NConnector::NApi::POSTGRESQL: {
// for backward compability set schema "public" by default
// TODO: simplify during https://st.yandex-team.ru/YQ-2494
TString schema;
const auto it = clusterConfig.GetDataSourceOptions().find("schema");
if (it != clusterConfig.GetDataSourceOptions().end()) {
schema = it->second;
}
if (!schema) {
schema = "public";
}

request.mutable_data_source_instance()->mutable_pg_options()->set_schema(schema);
auto* options = request.mutable_data_source_instance()->mutable_pg_options();
SetSchema(*options, clusterConfig);
} break;

default:
Expand Down