From 4d765114d6e5dd1a78a7ad798750e7bc400a72a6 Mon Sep 17 00:00:00 2001 From: bogao007 Date: Sat, 22 Apr 2023 09:21:16 +0900 Subject: [PATCH] [SPARK-43046][SS][CONNECT] Implemented Python API dropDuplicatesWithinWatermark for Spark Connect ### What changes were proposed in this pull request? Implemented `dropDuplicatesWithinWatermark` Python API for Spark Connect. This change is based on a previous [commit](https://github.com/apache/spark/commit/0e9e34c1bd9bd16ad5efca77ce2763eb950f3103) that introduced `dropDuplicatesWithinWatermark` API in Spark. ### Why are the changes needed? We recently introduced dropDuplicatesWithinWatermark API in Spark ([commit link](https://github.com/apache/spark/commit/0e9e34c1bd9bd16ad5efca77ce2763eb950f3103)). We want to bring parity to the Spark Connect. ### Does this PR introduce _any_ user-facing change? Yes, this introduces a new public API, dropDuplicatesWithinWatermark in Spark Connect. ### How was this patch tested? Added new test cases in test suites. Closes #40834 from bogao007/drop-dup-watermark. Authored-by: bogao007 Signed-off-by: Hyukjin Kwon --- .../protobuf/spark/connect/relations.proto | 3 + .../spark/sql/connect/dsl/package.scala | 11 ++ .../connect/planner/SparkConnectPlanner.scala | 8 +- .../planner/SparkConnectPlannerSuite.scala | 30 ++++ .../planner/SparkConnectProtoSuite.scala | 10 ++ python/pyspark/sql/connect/dataframe.py | 22 ++- python/pyspark/sql/connect/plan.py | 3 + .../sql/connect/proto/relations_pb2.py | 152 +++++++++--------- .../sql/connect/proto/relations_pb2.pyi | 17 ++ .../sql/tests/connect/test_connect_basic.py | 10 +- 10 files changed, 183 insertions(+), 83 deletions(-) diff --git a/connector/connect/common/src/main/protobuf/spark/connect/relations.proto b/connector/connect/common/src/main/protobuf/spark/connect/relations.proto index 57bdf57c9cb81..29e701a42cf7f 100644 --- a/connector/connect/common/src/main/protobuf/spark/connect/relations.proto +++ b/connector/connect/common/src/main/protobuf/spark/connect/relations.proto @@ -362,6 +362,9 @@ message Deduplicate { // // This field does not co-use with `column_names`. optional bool all_columns_as_keys = 3; + + // (Optional) Deduplicate within the time range of watermark. + optional bool within_watermark = 4; } // A relation that does not need to be qualified by name. diff --git a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala index 21b9180ccfbc0..25d722cf58df4 100644 --- a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala +++ b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala @@ -596,6 +596,17 @@ package object dsl { .addAllColumnNames(colNames.asJava)) .build() + def deduplicateWithinWatermark(colNames: Seq[String]): Relation = + Relation + .newBuilder() + .setDeduplicate( + Deduplicate + .newBuilder() + .setInput(logicalPlan) + .addAllColumnNames(colNames.asJava) + .setWithinWatermark(true)) + .build() + def distinct(): Relation = Relation .newBuilder() diff --git a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala index ef502e282ee72..ba3943960777e 100644 --- a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala +++ b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala @@ -46,7 +46,7 @@ import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.parser.{CatalystSqlParser, ParseException, ParserUtils} import org.apache.spark.sql.catalyst.plans.{Cross, FullOuter, Inner, JoinType, LeftAnti, LeftOuter, LeftSemi, RightOuter, UsingJoin} import org.apache.spark.sql.catalyst.plans.logical -import org.apache.spark.sql.catalyst.plans.logical.{CollectMetrics, CommandResult, Deduplicate, DeserializeToObject, Except, Intersect, LocalRelation, LogicalPlan, MapPartitions, Project, Sample, SerializeFromObject, Sort, SubqueryAlias, TypedFilter, Union, Unpivot, UnresolvedHint} +import org.apache.spark.sql.catalyst.plans.logical.{CollectMetrics, CommandResult, Deduplicate, DeduplicateWithinWatermark, DeserializeToObject, Except, Intersect, LocalRelation, LogicalPlan, MapPartitions, Project, Sample, SerializeFromObject, Sort, SubqueryAlias, TypedFilter, Union, Unpivot, UnresolvedHint} import org.apache.spark.sql.catalyst.util.{CaseInsensitiveMap, CharVarcharUtils} import org.apache.spark.sql.connect.artifact.SparkConnectArtifactManager import org.apache.spark.sql.connect.common.{DataTypeProtoConverter, InvalidPlanInput, LiteralValueProtoConverter, StorageLevelProtoConverter, UdfPacket} @@ -738,7 +738,8 @@ class SparkConnectPlanner(val session: SparkSession) { val resolver = session.sessionState.analyzer.resolver val allColumns = queryExecution.analyzed.output if (rel.getAllColumnsAsKeys) { - Deduplicate(allColumns, queryExecution.analyzed) + if (rel.getWithinWatermark) DeduplicateWithinWatermark(allColumns, queryExecution.analyzed) + else Deduplicate(allColumns, queryExecution.analyzed) } else { val toGroupColumnNames = rel.getColumnNamesList.asScala.toSeq val groupCols = toGroupColumnNames.flatMap { (colName: String) => @@ -750,7 +751,8 @@ class SparkConnectPlanner(val session: SparkSession) { } cols } - Deduplicate(groupCols, queryExecution.analyzed) + if (rel.getWithinWatermark) DeduplicateWithinWatermark(groupCols, queryExecution.analyzed) + else Deduplicate(groupCols, queryExecution.analyzed) } } diff --git a/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectPlannerSuite.scala b/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectPlannerSuite.scala index ec2362d5a56b3..8dac0b166b6ad 100644 --- a/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectPlannerSuite.scala +++ b/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectPlannerSuite.scala @@ -381,6 +381,36 @@ class SparkConnectPlannerSuite extends SparkFunSuite with SparkConnectPlanTest { assert(e2.getMessage.contains("either deduplicate on all columns or a subset of columns")) } + test("Test invalid deduplicateWithinWatermark") { + val deduplicateWithinWatermark = proto.Deduplicate + .newBuilder() + .setInput(readRel) + .setAllColumnsAsKeys(true) + .addColumnNames("test") + .setWithinWatermark(true) + + val e = intercept[InvalidPlanInput] { + transform( + proto.Relation.newBuilder + .setDeduplicate(deduplicateWithinWatermark) + .build()) + } + assert( + e.getMessage.contains("Cannot deduplicate on both all columns and a subset of columns")) + + val deduplicateWithinWatermark2 = proto.Deduplicate + .newBuilder() + .setInput(readRel) + .setWithinWatermark(true) + val e2 = intercept[InvalidPlanInput] { + transform( + proto.Relation.newBuilder + .setDeduplicate(deduplicateWithinWatermark2) + .build()) + } + assert(e2.getMessage.contains("either deduplicate on all columns or a subset of columns")) + } + test("Test invalid intersect, except") { // Except with union_by_name=true val except = proto.SetOperation diff --git a/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala b/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala index 824ee7aceb4bd..96dae647db688 100644 --- a/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala +++ b/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala @@ -348,6 +348,16 @@ class SparkConnectProtoSuite extends PlanTest with SparkConnectPlanTest { comparePlans(connectPlan2, sparkPlan2) } + test("Test basic deduplicateWithinWatermark") { + val connectPlan = connectTestRelation.distinct() + val sparkPlan = sparkTestRelation.distinct() + comparePlans(connectPlan, sparkPlan) + + val connectPlan2 = connectTestRelation.deduplicateWithinWatermark(Seq("id", "name")) + val sparkPlan2 = sparkTestRelation.dropDuplicatesWithinWatermark(Seq("id", "name")) + comparePlans(connectPlan2, sparkPlan2) + } + test("Test union, except, intersect") { val connectPlan1 = connectTestRelation.except(connectTestRelation, isAll = false) val sparkPlan1 = sparkTestRelation.except(sparkTestRelation) diff --git a/python/pyspark/sql/connect/dataframe.py b/python/pyspark/sql/connect/dataframe.py index 87eb6df5cba98..3b39b82196e4f 100644 --- a/python/pyspark/sql/connect/dataframe.py +++ b/python/pyspark/sql/connect/dataframe.py @@ -379,7 +379,26 @@ def dropDuplicates(self, subset: Optional[List[str]] = None) -> "DataFrame": drop_duplicates = dropDuplicates def dropDuplicatesWithinWatermark(self, subset: Optional[List[str]] = None) -> "DataFrame": - raise NotImplementedError("dropDuplicatesWithinWatermark() is not implemented.") + if subset is not None and not isinstance(subset, (list, tuple)): + raise PySparkTypeError( + error_class="NOT_LIST_OR_TUPLE", + message_parameters={"arg_name": "subset", "arg_type": type(subset).__name__}, + ) + + if subset is None: + return DataFrame.withPlan( + plan.Deduplicate(child=self._plan, all_columns_as_keys=True, within_watermark=True), + session=self._session, + ) + else: + return DataFrame.withPlan( + plan.Deduplicate(child=self._plan, column_names=subset, within_watermark=True), + session=self._session, + ) + + dropDuplicatesWithinWatermark.__doc__ = PySparkDataFrame.dropDuplicatesWithinWatermark.__doc__ + + drop_duplicates_within_watermark = dropDuplicatesWithinWatermark def distinct(self) -> "DataFrame": return DataFrame.withPlan( @@ -595,7 +614,6 @@ def sample( fraction: Optional[Union[int, float]] = None, seed: Optional[int] = None, ) -> "DataFrame": - # For the cases below: # sample(True, 0.5 [, seed]) # sample(True, fraction=0.5 [, seed]) diff --git a/python/pyspark/sql/connect/plan.py b/python/pyspark/sql/connect/plan.py index 9e221814f12f6..8b6dda0b1ca7c 100644 --- a/python/pyspark/sql/connect/plan.py +++ b/python/pyspark/sql/connect/plan.py @@ -609,16 +609,19 @@ def __init__( child: Optional["LogicalPlan"], all_columns_as_keys: bool = False, column_names: Optional[List[str]] = None, + within_watermark: bool = False, ) -> None: super().__init__(child) self.all_columns_as_keys = all_columns_as_keys self.column_names = column_names + self.within_watermark = within_watermark def plan(self, session: "SparkConnectClient") -> proto.Relation: assert self._child is not None plan = self._create_proto_relation() plan.deduplicate.input.CopyFrom(self._child.plan(session)) plan.deduplicate.all_columns_as_keys = self.all_columns_as_keys + plan.deduplicate.within_watermark = self.within_watermark if self.column_names is not None: plan.deduplicate.column_names.extend(self.column_names) return plan diff --git a/python/pyspark/sql/connect/proto/relations_pb2.py b/python/pyspark/sql/connect/proto/relations_pb2.py index 6a4226185e794..b8b84f2774385 100644 --- a/python/pyspark/sql/connect/proto/relations_pb2.py +++ b/python/pyspark/sql/connect/proto/relations_pb2.py @@ -36,7 +36,7 @@ DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile( - b'\n\x1dspark/connect/relations.proto\x12\rspark.connect\x1a\x19google/protobuf/any.proto\x1a\x1fspark/connect/expressions.proto\x1a\x19spark/connect/types.proto\x1a\x1bspark/connect/catalog.proto"\x99\x16\n\x08Relation\x12\x35\n\x06\x63ommon\x18\x01 \x01(\x0b\x32\x1d.spark.connect.RelationCommonR\x06\x63ommon\x12)\n\x04read\x18\x02 \x01(\x0b\x32\x13.spark.connect.ReadH\x00R\x04read\x12\x32\n\x07project\x18\x03 \x01(\x0b\x32\x16.spark.connect.ProjectH\x00R\x07project\x12/\n\x06\x66ilter\x18\x04 \x01(\x0b\x32\x15.spark.connect.FilterH\x00R\x06\x66ilter\x12)\n\x04join\x18\x05 \x01(\x0b\x32\x13.spark.connect.JoinH\x00R\x04join\x12\x34\n\x06set_op\x18\x06 \x01(\x0b\x32\x1b.spark.connect.SetOperationH\x00R\x05setOp\x12)\n\x04sort\x18\x07 \x01(\x0b\x32\x13.spark.connect.SortH\x00R\x04sort\x12,\n\x05limit\x18\x08 \x01(\x0b\x32\x14.spark.connect.LimitH\x00R\x05limit\x12\x38\n\taggregate\x18\t \x01(\x0b\x32\x18.spark.connect.AggregateH\x00R\taggregate\x12&\n\x03sql\x18\n \x01(\x0b\x32\x12.spark.connect.SQLH\x00R\x03sql\x12\x45\n\x0elocal_relation\x18\x0b \x01(\x0b\x32\x1c.spark.connect.LocalRelationH\x00R\rlocalRelation\x12/\n\x06sample\x18\x0c \x01(\x0b\x32\x15.spark.connect.SampleH\x00R\x06sample\x12/\n\x06offset\x18\r \x01(\x0b\x32\x15.spark.connect.OffsetH\x00R\x06offset\x12>\n\x0b\x64\x65\x64uplicate\x18\x0e \x01(\x0b\x32\x1a.spark.connect.DeduplicateH\x00R\x0b\x64\x65\x64uplicate\x12,\n\x05range\x18\x0f \x01(\x0b\x32\x14.spark.connect.RangeH\x00R\x05range\x12\x45\n\x0esubquery_alias\x18\x10 \x01(\x0b\x32\x1c.spark.connect.SubqueryAliasH\x00R\rsubqueryAlias\x12>\n\x0brepartition\x18\x11 \x01(\x0b\x32\x1a.spark.connect.RepartitionH\x00R\x0brepartition\x12*\n\x05to_df\x18\x12 \x01(\x0b\x32\x13.spark.connect.ToDFH\x00R\x04toDf\x12U\n\x14with_columns_renamed\x18\x13 \x01(\x0b\x32!.spark.connect.WithColumnsRenamedH\x00R\x12withColumnsRenamed\x12<\n\x0bshow_string\x18\x14 \x01(\x0b\x32\x19.spark.connect.ShowStringH\x00R\nshowString\x12)\n\x04\x64rop\x18\x15 \x01(\x0b\x32\x13.spark.connect.DropH\x00R\x04\x64rop\x12)\n\x04tail\x18\x16 \x01(\x0b\x32\x13.spark.connect.TailH\x00R\x04tail\x12?\n\x0cwith_columns\x18\x17 \x01(\x0b\x32\x1a.spark.connect.WithColumnsH\x00R\x0bwithColumns\x12)\n\x04hint\x18\x18 \x01(\x0b\x32\x13.spark.connect.HintH\x00R\x04hint\x12\x32\n\x07unpivot\x18\x19 \x01(\x0b\x32\x16.spark.connect.UnpivotH\x00R\x07unpivot\x12\x36\n\tto_schema\x18\x1a \x01(\x0b\x32\x17.spark.connect.ToSchemaH\x00R\x08toSchema\x12\x64\n\x19repartition_by_expression\x18\x1b \x01(\x0b\x32&.spark.connect.RepartitionByExpressionH\x00R\x17repartitionByExpression\x12\x45\n\x0emap_partitions\x18\x1c \x01(\x0b\x32\x1c.spark.connect.MapPartitionsH\x00R\rmapPartitions\x12H\n\x0f\x63ollect_metrics\x18\x1d \x01(\x0b\x32\x1d.spark.connect.CollectMetricsH\x00R\x0e\x63ollectMetrics\x12,\n\x05parse\x18\x1e \x01(\x0b\x32\x14.spark.connect.ParseH\x00R\x05parse\x12\x36\n\tgroup_map\x18\x1f \x01(\x0b\x32\x17.spark.connect.GroupMapH\x00R\x08groupMap\x12=\n\x0c\x63o_group_map\x18 \x01(\x0b\x32\x19.spark.connect.CoGroupMapH\x00R\ncoGroupMap\x12\x45\n\x0ewith_watermark\x18! \x01(\x0b\x32\x1c.spark.connect.WithWatermarkH\x00R\rwithWatermark\x12\x63\n\x1a\x61pply_in_pandas_with_state\x18" \x01(\x0b\x32%.spark.connect.ApplyInPandasWithStateH\x00R\x16\x61pplyInPandasWithState\x12<\n\x0bhtml_string\x18# \x01(\x0b\x32\x19.spark.connect.HtmlStringH\x00R\nhtmlString\x12\x30\n\x07\x66ill_na\x18Z \x01(\x0b\x32\x15.spark.connect.NAFillH\x00R\x06\x66illNa\x12\x30\n\x07\x64rop_na\x18[ \x01(\x0b\x32\x15.spark.connect.NADropH\x00R\x06\x64ropNa\x12\x34\n\x07replace\x18\\ \x01(\x0b\x32\x18.spark.connect.NAReplaceH\x00R\x07replace\x12\x36\n\x07summary\x18\x64 \x01(\x0b\x32\x1a.spark.connect.StatSummaryH\x00R\x07summary\x12\x39\n\x08\x63rosstab\x18\x65 \x01(\x0b\x32\x1b.spark.connect.StatCrosstabH\x00R\x08\x63rosstab\x12\x39\n\x08\x64\x65scribe\x18\x66 \x01(\x0b\x32\x1b.spark.connect.StatDescribeH\x00R\x08\x64\x65scribe\x12*\n\x03\x63ov\x18g \x01(\x0b\x32\x16.spark.connect.StatCovH\x00R\x03\x63ov\x12-\n\x04\x63orr\x18h \x01(\x0b\x32\x17.spark.connect.StatCorrH\x00R\x04\x63orr\x12L\n\x0f\x61pprox_quantile\x18i \x01(\x0b\x32!.spark.connect.StatApproxQuantileH\x00R\x0e\x61pproxQuantile\x12=\n\nfreq_items\x18j \x01(\x0b\x32\x1c.spark.connect.StatFreqItemsH\x00R\tfreqItems\x12:\n\tsample_by\x18k \x01(\x0b\x32\x1b.spark.connect.StatSampleByH\x00R\x08sampleBy\x12\x33\n\x07\x63\x61talog\x18\xc8\x01 \x01(\x0b\x32\x16.spark.connect.CatalogH\x00R\x07\x63\x61talog\x12\x35\n\textension\x18\xe6\x07 \x01(\x0b\x32\x14.google.protobuf.AnyH\x00R\textension\x12\x33\n\x07unknown\x18\xe7\x07 \x01(\x0b\x32\x16.spark.connect.UnknownH\x00R\x07unknownB\n\n\x08rel_type"\t\n\x07Unknown"[\n\x0eRelationCommon\x12\x1f\n\x0bsource_info\x18\x01 \x01(\tR\nsourceInfo\x12\x1c\n\x07plan_id\x18\x02 \x01(\x03H\x00R\x06planId\x88\x01\x01\x42\n\n\x08_plan_id"\xa9\x01\n\x03SQL\x12\x14\n\x05query\x18\x01 \x01(\tR\x05query\x12\x30\n\x04\x61rgs\x18\x02 \x03(\x0b\x32\x1c.spark.connect.SQL.ArgsEntryR\x04\x61rgs\x1aZ\n\tArgsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x37\n\x05value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x05value:\x02\x38\x01"\x97\x05\n\x04Read\x12\x41\n\x0bnamed_table\x18\x01 \x01(\x0b\x32\x1e.spark.connect.Read.NamedTableH\x00R\nnamedTable\x12\x41\n\x0b\x64\x61ta_source\x18\x02 \x01(\x0b\x32\x1e.spark.connect.Read.DataSourceH\x00R\ndataSource\x12!\n\x0cis_streaming\x18\x03 \x01(\x08R\x0bisStreaming\x1a\xc0\x01\n\nNamedTable\x12/\n\x13unparsed_identifier\x18\x01 \x01(\tR\x12unparsedIdentifier\x12\x45\n\x07options\x18\x02 \x03(\x0b\x32+.spark.connect.Read.NamedTable.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x1a\x95\x02\n\nDataSource\x12\x1b\n\x06\x66ormat\x18\x01 \x01(\tH\x00R\x06\x66ormat\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x12\x45\n\x07options\x18\x03 \x03(\x0b\x32+.spark.connect.Read.DataSource.OptionsEntryR\x07options\x12\x14\n\x05paths\x18\x04 \x03(\tR\x05paths\x12\x1e\n\npredicates\x18\x05 \x03(\tR\npredicates\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x42\t\n\x07_formatB\t\n\x07_schemaB\x0b\n\tread_type"u\n\x07Project\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12;\n\x0b\x65xpressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0b\x65xpressions"p\n\x06\x46ilter\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x37\n\tcondition\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\tcondition"\xd7\x03\n\x04Join\x12+\n\x04left\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x04left\x12-\n\x05right\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\x05right\x12@\n\x0ejoin_condition\x18\x03 \x01(\x0b\x32\x19.spark.connect.ExpressionR\rjoinCondition\x12\x39\n\tjoin_type\x18\x04 \x01(\x0e\x32\x1c.spark.connect.Join.JoinTypeR\x08joinType\x12#\n\rusing_columns\x18\x05 \x03(\tR\x0cusingColumns"\xd0\x01\n\x08JoinType\x12\x19\n\x15JOIN_TYPE_UNSPECIFIED\x10\x00\x12\x13\n\x0fJOIN_TYPE_INNER\x10\x01\x12\x18\n\x14JOIN_TYPE_FULL_OUTER\x10\x02\x12\x18\n\x14JOIN_TYPE_LEFT_OUTER\x10\x03\x12\x19\n\x15JOIN_TYPE_RIGHT_OUTER\x10\x04\x12\x17\n\x13JOIN_TYPE_LEFT_ANTI\x10\x05\x12\x17\n\x13JOIN_TYPE_LEFT_SEMI\x10\x06\x12\x13\n\x0fJOIN_TYPE_CROSS\x10\x07"\xdf\x03\n\x0cSetOperation\x12\x36\n\nleft_input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\tleftInput\x12\x38\n\x0bright_input\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\nrightInput\x12\x45\n\x0bset_op_type\x18\x03 \x01(\x0e\x32%.spark.connect.SetOperation.SetOpTypeR\tsetOpType\x12\x1a\n\x06is_all\x18\x04 \x01(\x08H\x00R\x05isAll\x88\x01\x01\x12\x1c\n\x07\x62y_name\x18\x05 \x01(\x08H\x01R\x06\x62yName\x88\x01\x01\x12\x37\n\x15\x61llow_missing_columns\x18\x06 \x01(\x08H\x02R\x13\x61llowMissingColumns\x88\x01\x01"r\n\tSetOpType\x12\x1b\n\x17SET_OP_TYPE_UNSPECIFIED\x10\x00\x12\x19\n\x15SET_OP_TYPE_INTERSECT\x10\x01\x12\x15\n\x11SET_OP_TYPE_UNION\x10\x02\x12\x16\n\x12SET_OP_TYPE_EXCEPT\x10\x03\x42\t\n\x07_is_allB\n\n\x08_by_nameB\x18\n\x16_allow_missing_columns"L\n\x05Limit\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"O\n\x06Offset\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x16\n\x06offset\x18\x02 \x01(\x05R\x06offset"K\n\x04Tail\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"\xc6\x04\n\tAggregate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x41\n\ngroup_type\x18\x02 \x01(\x0e\x32".spark.connect.Aggregate.GroupTypeR\tgroupType\x12L\n\x14grouping_expressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12N\n\x15\x61ggregate_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x14\x61ggregateExpressions\x12\x34\n\x05pivot\x18\x05 \x01(\x0b\x32\x1e.spark.connect.Aggregate.PivotR\x05pivot\x1ao\n\x05Pivot\x12+\n\x03\x63ol\x18\x01 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x39\n\x06values\x18\x02 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values"\x81\x01\n\tGroupType\x12\x1a\n\x16GROUP_TYPE_UNSPECIFIED\x10\x00\x12\x16\n\x12GROUP_TYPE_GROUPBY\x10\x01\x12\x15\n\x11GROUP_TYPE_ROLLUP\x10\x02\x12\x13\n\x0fGROUP_TYPE_CUBE\x10\x03\x12\x14\n\x10GROUP_TYPE_PIVOT\x10\x04"\xa0\x01\n\x04Sort\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x05order\x18\x02 \x03(\x0b\x32#.spark.connect.Expression.SortOrderR\x05order\x12 \n\tis_global\x18\x03 \x01(\x08H\x00R\x08isGlobal\x88\x01\x01\x42\x0c\n\n_is_global"\x8d\x01\n\x04\x44rop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x33\n\x07\x63olumns\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07\x63olumns\x12!\n\x0c\x63olumn_names\x18\x03 \x03(\tR\x0b\x63olumnNames"\xab\x01\n\x0b\x44\x65\x64uplicate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames\x12\x32\n\x13\x61ll_columns_as_keys\x18\x03 \x01(\x08H\x00R\x10\x61llColumnsAsKeys\x88\x01\x01\x42\x16\n\x14_all_columns_as_keys"Y\n\rLocalRelation\x12\x17\n\x04\x64\x61ta\x18\x01 \x01(\x0cH\x00R\x04\x64\x61ta\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x42\x07\n\x05_dataB\t\n\x07_schema"\x91\x02\n\x06Sample\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1f\n\x0blower_bound\x18\x02 \x01(\x01R\nlowerBound\x12\x1f\n\x0bupper_bound\x18\x03 \x01(\x01R\nupperBound\x12.\n\x10with_replacement\x18\x04 \x01(\x08H\x00R\x0fwithReplacement\x88\x01\x01\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x01R\x04seed\x88\x01\x01\x12/\n\x13\x64\x65terministic_order\x18\x06 \x01(\x08R\x12\x64\x65terministicOrderB\x13\n\x11_with_replacementB\x07\n\x05_seed"\x91\x01\n\x05Range\x12\x19\n\x05start\x18\x01 \x01(\x03H\x00R\x05start\x88\x01\x01\x12\x10\n\x03\x65nd\x18\x02 \x01(\x03R\x03\x65nd\x12\x12\n\x04step\x18\x03 \x01(\x03R\x04step\x12*\n\x0enum_partitions\x18\x04 \x01(\x05H\x01R\rnumPartitions\x88\x01\x01\x42\x08\n\x06_startB\x11\n\x0f_num_partitions"r\n\rSubqueryAlias\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05\x61lias\x18\x02 \x01(\tR\x05\x61lias\x12\x1c\n\tqualifier\x18\x03 \x03(\tR\tqualifier"\x8e\x01\n\x0bRepartition\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12%\n\x0enum_partitions\x18\x02 \x01(\x05R\rnumPartitions\x12\x1d\n\x07shuffle\x18\x03 \x01(\x08H\x00R\x07shuffle\x88\x01\x01\x42\n\n\x08_shuffle"\x8e\x01\n\nShowString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate\x12\x1a\n\x08vertical\x18\x04 \x01(\x08R\x08vertical"r\n\nHtmlString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate"\\\n\x0bStatSummary\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1e\n\nstatistics\x18\x02 \x03(\tR\nstatistics"Q\n\x0cStatDescribe\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols"e\n\x0cStatCrosstab\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"`\n\x07StatCov\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"\x89\x01\n\x08StatCorr\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2\x12\x1b\n\x06method\x18\x04 \x01(\tH\x00R\x06method\x88\x01\x01\x42\t\n\x07_method"\xa4\x01\n\x12StatApproxQuantile\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12$\n\rprobabilities\x18\x03 \x03(\x01R\rprobabilities\x12%\n\x0erelative_error\x18\x04 \x01(\x01R\rrelativeError"}\n\rStatFreqItems\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x1d\n\x07support\x18\x03 \x01(\x01H\x00R\x07support\x88\x01\x01\x42\n\n\x08_support"\xb5\x02\n\x0cStatSampleBy\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03\x63ol\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x42\n\tfractions\x18\x03 \x03(\x0b\x32$.spark.connect.StatSampleBy.FractionR\tfractions\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x00R\x04seed\x88\x01\x01\x1a\x63\n\x08\x46raction\x12;\n\x07stratum\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x07stratum\x12\x1a\n\x08\x66raction\x18\x02 \x01(\x01R\x08\x66ractionB\x07\n\x05_seed"\x86\x01\n\x06NAFill\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x39\n\x06values\x18\x03 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values"\x86\x01\n\x06NADrop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\'\n\rmin_non_nulls\x18\x03 \x01(\x05H\x00R\x0bminNonNulls\x88\x01\x01\x42\x10\n\x0e_min_non_nulls"\xa8\x02\n\tNAReplace\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12H\n\x0creplacements\x18\x03 \x03(\x0b\x32$.spark.connect.NAReplace.ReplacementR\x0creplacements\x1a\x8d\x01\n\x0bReplacement\x12>\n\told_value\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08oldValue\x12>\n\tnew_value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08newValue"X\n\x04ToDF\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames"\xef\x01\n\x12WithColumnsRenamed\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x65\n\x12rename_columns_map\x18\x02 \x03(\x0b\x32\x37.spark.connect.WithColumnsRenamed.RenameColumnsMapEntryR\x10renameColumnsMap\x1a\x43\n\x15RenameColumnsMapEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"w\n\x0bWithColumns\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x07\x61liases\x18\x02 \x03(\x0b\x32\x1f.spark.connect.Expression.AliasR\x07\x61liases"\x86\x01\n\rWithWatermark\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1d\n\nevent_time\x18\x02 \x01(\tR\teventTime\x12\'\n\x0f\x64\x65lay_threshold\x18\x03 \x01(\tR\x0e\x64\x65layThreshold"\x84\x01\n\x04Hint\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x39\n\nparameters\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\nparameters"\xc7\x02\n\x07Unpivot\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03ids\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x03ids\x12:\n\x06values\x18\x03 \x01(\x0b\x32\x1d.spark.connect.Unpivot.ValuesH\x00R\x06values\x88\x01\x01\x12\x30\n\x14variable_column_name\x18\x04 \x01(\tR\x12variableColumnName\x12*\n\x11value_column_name\x18\x05 \x01(\tR\x0fvalueColumnName\x1a;\n\x06Values\x12\x31\n\x06values\x18\x01 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x06valuesB\t\n\x07_values"j\n\x08ToSchema\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12/\n\x06schema\x18\x02 \x01(\x0b\x32\x17.spark.connect.DataTypeR\x06schema"\xcb\x01\n\x17RepartitionByExpression\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x0fpartition_exprs\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0epartitionExprs\x12*\n\x0enum_partitions\x18\x03 \x01(\x05H\x00R\rnumPartitions\x88\x01\x01\x42\x11\n\x0f_num_partitions"\xb5\x01\n\rMapPartitions\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x04\x66unc\x18\x02 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12"\n\nis_barrier\x18\x03 \x01(\x08H\x00R\tisBarrier\x88\x01\x01\x42\r\n\x0b_is_barrier"\xcb\x01\n\x08GroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc"\xe0\x02\n\nCoGroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12W\n\x1ainput_grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18inputGroupingExpressions\x12-\n\x05other\x18\x03 \x01(\x0b\x32\x17.spark.connect.RelationR\x05other\x12W\n\x1aother_grouping_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18otherGroupingExpressions\x12\x42\n\x04\x66unc\x18\x05 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc"\xe5\x02\n\x16\x41pplyInPandasWithState\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12#\n\routput_schema\x18\x04 \x01(\tR\x0coutputSchema\x12!\n\x0cstate_schema\x18\x05 \x01(\tR\x0bstateSchema\x12\x1f\n\x0boutput_mode\x18\x06 \x01(\tR\noutputMode\x12!\n\x0ctimeout_conf\x18\x07 \x01(\tR\x0btimeoutConf"\x88\x01\n\x0e\x43ollectMetrics\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x33\n\x07metrics\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07metrics"\x84\x03\n\x05Parse\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x38\n\x06\x66ormat\x18\x02 \x01(\x0e\x32 .spark.connect.Parse.ParseFormatR\x06\x66ormat\x12\x34\n\x06schema\x18\x03 \x01(\x0b\x32\x17.spark.connect.DataTypeH\x00R\x06schema\x88\x01\x01\x12;\n\x07options\x18\x04 \x03(\x0b\x32!.spark.connect.Parse.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"X\n\x0bParseFormat\x12\x1c\n\x18PARSE_FORMAT_UNSPECIFIED\x10\x00\x12\x14\n\x10PARSE_FORMAT_CSV\x10\x01\x12\x15\n\x11PARSE_FORMAT_JSON\x10\x02\x42\t\n\x07_schemaB"\n\x1eorg.apache.spark.connect.protoP\x01\x62\x06proto3' + b'\n\x1dspark/connect/relations.proto\x12\rspark.connect\x1a\x19google/protobuf/any.proto\x1a\x1fspark/connect/expressions.proto\x1a\x19spark/connect/types.proto\x1a\x1bspark/connect/catalog.proto"\x99\x16\n\x08Relation\x12\x35\n\x06\x63ommon\x18\x01 \x01(\x0b\x32\x1d.spark.connect.RelationCommonR\x06\x63ommon\x12)\n\x04read\x18\x02 \x01(\x0b\x32\x13.spark.connect.ReadH\x00R\x04read\x12\x32\n\x07project\x18\x03 \x01(\x0b\x32\x16.spark.connect.ProjectH\x00R\x07project\x12/\n\x06\x66ilter\x18\x04 \x01(\x0b\x32\x15.spark.connect.FilterH\x00R\x06\x66ilter\x12)\n\x04join\x18\x05 \x01(\x0b\x32\x13.spark.connect.JoinH\x00R\x04join\x12\x34\n\x06set_op\x18\x06 \x01(\x0b\x32\x1b.spark.connect.SetOperationH\x00R\x05setOp\x12)\n\x04sort\x18\x07 \x01(\x0b\x32\x13.spark.connect.SortH\x00R\x04sort\x12,\n\x05limit\x18\x08 \x01(\x0b\x32\x14.spark.connect.LimitH\x00R\x05limit\x12\x38\n\taggregate\x18\t \x01(\x0b\x32\x18.spark.connect.AggregateH\x00R\taggregate\x12&\n\x03sql\x18\n \x01(\x0b\x32\x12.spark.connect.SQLH\x00R\x03sql\x12\x45\n\x0elocal_relation\x18\x0b \x01(\x0b\x32\x1c.spark.connect.LocalRelationH\x00R\rlocalRelation\x12/\n\x06sample\x18\x0c \x01(\x0b\x32\x15.spark.connect.SampleH\x00R\x06sample\x12/\n\x06offset\x18\r \x01(\x0b\x32\x15.spark.connect.OffsetH\x00R\x06offset\x12>\n\x0b\x64\x65\x64uplicate\x18\x0e \x01(\x0b\x32\x1a.spark.connect.DeduplicateH\x00R\x0b\x64\x65\x64uplicate\x12,\n\x05range\x18\x0f \x01(\x0b\x32\x14.spark.connect.RangeH\x00R\x05range\x12\x45\n\x0esubquery_alias\x18\x10 \x01(\x0b\x32\x1c.spark.connect.SubqueryAliasH\x00R\rsubqueryAlias\x12>\n\x0brepartition\x18\x11 \x01(\x0b\x32\x1a.spark.connect.RepartitionH\x00R\x0brepartition\x12*\n\x05to_df\x18\x12 \x01(\x0b\x32\x13.spark.connect.ToDFH\x00R\x04toDf\x12U\n\x14with_columns_renamed\x18\x13 \x01(\x0b\x32!.spark.connect.WithColumnsRenamedH\x00R\x12withColumnsRenamed\x12<\n\x0bshow_string\x18\x14 \x01(\x0b\x32\x19.spark.connect.ShowStringH\x00R\nshowString\x12)\n\x04\x64rop\x18\x15 \x01(\x0b\x32\x13.spark.connect.DropH\x00R\x04\x64rop\x12)\n\x04tail\x18\x16 \x01(\x0b\x32\x13.spark.connect.TailH\x00R\x04tail\x12?\n\x0cwith_columns\x18\x17 \x01(\x0b\x32\x1a.spark.connect.WithColumnsH\x00R\x0bwithColumns\x12)\n\x04hint\x18\x18 \x01(\x0b\x32\x13.spark.connect.HintH\x00R\x04hint\x12\x32\n\x07unpivot\x18\x19 \x01(\x0b\x32\x16.spark.connect.UnpivotH\x00R\x07unpivot\x12\x36\n\tto_schema\x18\x1a \x01(\x0b\x32\x17.spark.connect.ToSchemaH\x00R\x08toSchema\x12\x64\n\x19repartition_by_expression\x18\x1b \x01(\x0b\x32&.spark.connect.RepartitionByExpressionH\x00R\x17repartitionByExpression\x12\x45\n\x0emap_partitions\x18\x1c \x01(\x0b\x32\x1c.spark.connect.MapPartitionsH\x00R\rmapPartitions\x12H\n\x0f\x63ollect_metrics\x18\x1d \x01(\x0b\x32\x1d.spark.connect.CollectMetricsH\x00R\x0e\x63ollectMetrics\x12,\n\x05parse\x18\x1e \x01(\x0b\x32\x14.spark.connect.ParseH\x00R\x05parse\x12\x36\n\tgroup_map\x18\x1f \x01(\x0b\x32\x17.spark.connect.GroupMapH\x00R\x08groupMap\x12=\n\x0c\x63o_group_map\x18 \x01(\x0b\x32\x19.spark.connect.CoGroupMapH\x00R\ncoGroupMap\x12\x45\n\x0ewith_watermark\x18! \x01(\x0b\x32\x1c.spark.connect.WithWatermarkH\x00R\rwithWatermark\x12\x63\n\x1a\x61pply_in_pandas_with_state\x18" \x01(\x0b\x32%.spark.connect.ApplyInPandasWithStateH\x00R\x16\x61pplyInPandasWithState\x12<\n\x0bhtml_string\x18# \x01(\x0b\x32\x19.spark.connect.HtmlStringH\x00R\nhtmlString\x12\x30\n\x07\x66ill_na\x18Z \x01(\x0b\x32\x15.spark.connect.NAFillH\x00R\x06\x66illNa\x12\x30\n\x07\x64rop_na\x18[ \x01(\x0b\x32\x15.spark.connect.NADropH\x00R\x06\x64ropNa\x12\x34\n\x07replace\x18\\ \x01(\x0b\x32\x18.spark.connect.NAReplaceH\x00R\x07replace\x12\x36\n\x07summary\x18\x64 \x01(\x0b\x32\x1a.spark.connect.StatSummaryH\x00R\x07summary\x12\x39\n\x08\x63rosstab\x18\x65 \x01(\x0b\x32\x1b.spark.connect.StatCrosstabH\x00R\x08\x63rosstab\x12\x39\n\x08\x64\x65scribe\x18\x66 \x01(\x0b\x32\x1b.spark.connect.StatDescribeH\x00R\x08\x64\x65scribe\x12*\n\x03\x63ov\x18g \x01(\x0b\x32\x16.spark.connect.StatCovH\x00R\x03\x63ov\x12-\n\x04\x63orr\x18h \x01(\x0b\x32\x17.spark.connect.StatCorrH\x00R\x04\x63orr\x12L\n\x0f\x61pprox_quantile\x18i \x01(\x0b\x32!.spark.connect.StatApproxQuantileH\x00R\x0e\x61pproxQuantile\x12=\n\nfreq_items\x18j \x01(\x0b\x32\x1c.spark.connect.StatFreqItemsH\x00R\tfreqItems\x12:\n\tsample_by\x18k \x01(\x0b\x32\x1b.spark.connect.StatSampleByH\x00R\x08sampleBy\x12\x33\n\x07\x63\x61talog\x18\xc8\x01 \x01(\x0b\x32\x16.spark.connect.CatalogH\x00R\x07\x63\x61talog\x12\x35\n\textension\x18\xe6\x07 \x01(\x0b\x32\x14.google.protobuf.AnyH\x00R\textension\x12\x33\n\x07unknown\x18\xe7\x07 \x01(\x0b\x32\x16.spark.connect.UnknownH\x00R\x07unknownB\n\n\x08rel_type"\t\n\x07Unknown"[\n\x0eRelationCommon\x12\x1f\n\x0bsource_info\x18\x01 \x01(\tR\nsourceInfo\x12\x1c\n\x07plan_id\x18\x02 \x01(\x03H\x00R\x06planId\x88\x01\x01\x42\n\n\x08_plan_id"\xa9\x01\n\x03SQL\x12\x14\n\x05query\x18\x01 \x01(\tR\x05query\x12\x30\n\x04\x61rgs\x18\x02 \x03(\x0b\x32\x1c.spark.connect.SQL.ArgsEntryR\x04\x61rgs\x1aZ\n\tArgsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x37\n\x05value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x05value:\x02\x38\x01"\x97\x05\n\x04Read\x12\x41\n\x0bnamed_table\x18\x01 \x01(\x0b\x32\x1e.spark.connect.Read.NamedTableH\x00R\nnamedTable\x12\x41\n\x0b\x64\x61ta_source\x18\x02 \x01(\x0b\x32\x1e.spark.connect.Read.DataSourceH\x00R\ndataSource\x12!\n\x0cis_streaming\x18\x03 \x01(\x08R\x0bisStreaming\x1a\xc0\x01\n\nNamedTable\x12/\n\x13unparsed_identifier\x18\x01 \x01(\tR\x12unparsedIdentifier\x12\x45\n\x07options\x18\x02 \x03(\x0b\x32+.spark.connect.Read.NamedTable.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x1a\x95\x02\n\nDataSource\x12\x1b\n\x06\x66ormat\x18\x01 \x01(\tH\x00R\x06\x66ormat\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x12\x45\n\x07options\x18\x03 \x03(\x0b\x32+.spark.connect.Read.DataSource.OptionsEntryR\x07options\x12\x14\n\x05paths\x18\x04 \x03(\tR\x05paths\x12\x1e\n\npredicates\x18\x05 \x03(\tR\npredicates\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x42\t\n\x07_formatB\t\n\x07_schemaB\x0b\n\tread_type"u\n\x07Project\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12;\n\x0b\x65xpressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0b\x65xpressions"p\n\x06\x46ilter\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x37\n\tcondition\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\tcondition"\xd7\x03\n\x04Join\x12+\n\x04left\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x04left\x12-\n\x05right\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\x05right\x12@\n\x0ejoin_condition\x18\x03 \x01(\x0b\x32\x19.spark.connect.ExpressionR\rjoinCondition\x12\x39\n\tjoin_type\x18\x04 \x01(\x0e\x32\x1c.spark.connect.Join.JoinTypeR\x08joinType\x12#\n\rusing_columns\x18\x05 \x03(\tR\x0cusingColumns"\xd0\x01\n\x08JoinType\x12\x19\n\x15JOIN_TYPE_UNSPECIFIED\x10\x00\x12\x13\n\x0fJOIN_TYPE_INNER\x10\x01\x12\x18\n\x14JOIN_TYPE_FULL_OUTER\x10\x02\x12\x18\n\x14JOIN_TYPE_LEFT_OUTER\x10\x03\x12\x19\n\x15JOIN_TYPE_RIGHT_OUTER\x10\x04\x12\x17\n\x13JOIN_TYPE_LEFT_ANTI\x10\x05\x12\x17\n\x13JOIN_TYPE_LEFT_SEMI\x10\x06\x12\x13\n\x0fJOIN_TYPE_CROSS\x10\x07"\xdf\x03\n\x0cSetOperation\x12\x36\n\nleft_input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\tleftInput\x12\x38\n\x0bright_input\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\nrightInput\x12\x45\n\x0bset_op_type\x18\x03 \x01(\x0e\x32%.spark.connect.SetOperation.SetOpTypeR\tsetOpType\x12\x1a\n\x06is_all\x18\x04 \x01(\x08H\x00R\x05isAll\x88\x01\x01\x12\x1c\n\x07\x62y_name\x18\x05 \x01(\x08H\x01R\x06\x62yName\x88\x01\x01\x12\x37\n\x15\x61llow_missing_columns\x18\x06 \x01(\x08H\x02R\x13\x61llowMissingColumns\x88\x01\x01"r\n\tSetOpType\x12\x1b\n\x17SET_OP_TYPE_UNSPECIFIED\x10\x00\x12\x19\n\x15SET_OP_TYPE_INTERSECT\x10\x01\x12\x15\n\x11SET_OP_TYPE_UNION\x10\x02\x12\x16\n\x12SET_OP_TYPE_EXCEPT\x10\x03\x42\t\n\x07_is_allB\n\n\x08_by_nameB\x18\n\x16_allow_missing_columns"L\n\x05Limit\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"O\n\x06Offset\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x16\n\x06offset\x18\x02 \x01(\x05R\x06offset"K\n\x04Tail\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"\xc6\x04\n\tAggregate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x41\n\ngroup_type\x18\x02 \x01(\x0e\x32".spark.connect.Aggregate.GroupTypeR\tgroupType\x12L\n\x14grouping_expressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12N\n\x15\x61ggregate_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x14\x61ggregateExpressions\x12\x34\n\x05pivot\x18\x05 \x01(\x0b\x32\x1e.spark.connect.Aggregate.PivotR\x05pivot\x1ao\n\x05Pivot\x12+\n\x03\x63ol\x18\x01 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x39\n\x06values\x18\x02 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values"\x81\x01\n\tGroupType\x12\x1a\n\x16GROUP_TYPE_UNSPECIFIED\x10\x00\x12\x16\n\x12GROUP_TYPE_GROUPBY\x10\x01\x12\x15\n\x11GROUP_TYPE_ROLLUP\x10\x02\x12\x13\n\x0fGROUP_TYPE_CUBE\x10\x03\x12\x14\n\x10GROUP_TYPE_PIVOT\x10\x04"\xa0\x01\n\x04Sort\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x05order\x18\x02 \x03(\x0b\x32#.spark.connect.Expression.SortOrderR\x05order\x12 \n\tis_global\x18\x03 \x01(\x08H\x00R\x08isGlobal\x88\x01\x01\x42\x0c\n\n_is_global"\x8d\x01\n\x04\x44rop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x33\n\x07\x63olumns\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07\x63olumns\x12!\n\x0c\x63olumn_names\x18\x03 \x03(\tR\x0b\x63olumnNames"\xf0\x01\n\x0b\x44\x65\x64uplicate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames\x12\x32\n\x13\x61ll_columns_as_keys\x18\x03 \x01(\x08H\x00R\x10\x61llColumnsAsKeys\x88\x01\x01\x12.\n\x10within_watermark\x18\x04 \x01(\x08H\x01R\x0fwithinWatermark\x88\x01\x01\x42\x16\n\x14_all_columns_as_keysB\x13\n\x11_within_watermark"Y\n\rLocalRelation\x12\x17\n\x04\x64\x61ta\x18\x01 \x01(\x0cH\x00R\x04\x64\x61ta\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x42\x07\n\x05_dataB\t\n\x07_schema"\x91\x02\n\x06Sample\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1f\n\x0blower_bound\x18\x02 \x01(\x01R\nlowerBound\x12\x1f\n\x0bupper_bound\x18\x03 \x01(\x01R\nupperBound\x12.\n\x10with_replacement\x18\x04 \x01(\x08H\x00R\x0fwithReplacement\x88\x01\x01\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x01R\x04seed\x88\x01\x01\x12/\n\x13\x64\x65terministic_order\x18\x06 \x01(\x08R\x12\x64\x65terministicOrderB\x13\n\x11_with_replacementB\x07\n\x05_seed"\x91\x01\n\x05Range\x12\x19\n\x05start\x18\x01 \x01(\x03H\x00R\x05start\x88\x01\x01\x12\x10\n\x03\x65nd\x18\x02 \x01(\x03R\x03\x65nd\x12\x12\n\x04step\x18\x03 \x01(\x03R\x04step\x12*\n\x0enum_partitions\x18\x04 \x01(\x05H\x01R\rnumPartitions\x88\x01\x01\x42\x08\n\x06_startB\x11\n\x0f_num_partitions"r\n\rSubqueryAlias\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05\x61lias\x18\x02 \x01(\tR\x05\x61lias\x12\x1c\n\tqualifier\x18\x03 \x03(\tR\tqualifier"\x8e\x01\n\x0bRepartition\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12%\n\x0enum_partitions\x18\x02 \x01(\x05R\rnumPartitions\x12\x1d\n\x07shuffle\x18\x03 \x01(\x08H\x00R\x07shuffle\x88\x01\x01\x42\n\n\x08_shuffle"\x8e\x01\n\nShowString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate\x12\x1a\n\x08vertical\x18\x04 \x01(\x08R\x08vertical"r\n\nHtmlString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate"\\\n\x0bStatSummary\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1e\n\nstatistics\x18\x02 \x03(\tR\nstatistics"Q\n\x0cStatDescribe\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols"e\n\x0cStatCrosstab\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"`\n\x07StatCov\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"\x89\x01\n\x08StatCorr\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2\x12\x1b\n\x06method\x18\x04 \x01(\tH\x00R\x06method\x88\x01\x01\x42\t\n\x07_method"\xa4\x01\n\x12StatApproxQuantile\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12$\n\rprobabilities\x18\x03 \x03(\x01R\rprobabilities\x12%\n\x0erelative_error\x18\x04 \x01(\x01R\rrelativeError"}\n\rStatFreqItems\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x1d\n\x07support\x18\x03 \x01(\x01H\x00R\x07support\x88\x01\x01\x42\n\n\x08_support"\xb5\x02\n\x0cStatSampleBy\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03\x63ol\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x42\n\tfractions\x18\x03 \x03(\x0b\x32$.spark.connect.StatSampleBy.FractionR\tfractions\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x00R\x04seed\x88\x01\x01\x1a\x63\n\x08\x46raction\x12;\n\x07stratum\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x07stratum\x12\x1a\n\x08\x66raction\x18\x02 \x01(\x01R\x08\x66ractionB\x07\n\x05_seed"\x86\x01\n\x06NAFill\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x39\n\x06values\x18\x03 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values"\x86\x01\n\x06NADrop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\'\n\rmin_non_nulls\x18\x03 \x01(\x05H\x00R\x0bminNonNulls\x88\x01\x01\x42\x10\n\x0e_min_non_nulls"\xa8\x02\n\tNAReplace\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12H\n\x0creplacements\x18\x03 \x03(\x0b\x32$.spark.connect.NAReplace.ReplacementR\x0creplacements\x1a\x8d\x01\n\x0bReplacement\x12>\n\told_value\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08oldValue\x12>\n\tnew_value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08newValue"X\n\x04ToDF\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames"\xef\x01\n\x12WithColumnsRenamed\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x65\n\x12rename_columns_map\x18\x02 \x03(\x0b\x32\x37.spark.connect.WithColumnsRenamed.RenameColumnsMapEntryR\x10renameColumnsMap\x1a\x43\n\x15RenameColumnsMapEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"w\n\x0bWithColumns\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x07\x61liases\x18\x02 \x03(\x0b\x32\x1f.spark.connect.Expression.AliasR\x07\x61liases"\x86\x01\n\rWithWatermark\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1d\n\nevent_time\x18\x02 \x01(\tR\teventTime\x12\'\n\x0f\x64\x65lay_threshold\x18\x03 \x01(\tR\x0e\x64\x65layThreshold"\x84\x01\n\x04Hint\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x39\n\nparameters\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\nparameters"\xc7\x02\n\x07Unpivot\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03ids\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x03ids\x12:\n\x06values\x18\x03 \x01(\x0b\x32\x1d.spark.connect.Unpivot.ValuesH\x00R\x06values\x88\x01\x01\x12\x30\n\x14variable_column_name\x18\x04 \x01(\tR\x12variableColumnName\x12*\n\x11value_column_name\x18\x05 \x01(\tR\x0fvalueColumnName\x1a;\n\x06Values\x12\x31\n\x06values\x18\x01 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x06valuesB\t\n\x07_values"j\n\x08ToSchema\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12/\n\x06schema\x18\x02 \x01(\x0b\x32\x17.spark.connect.DataTypeR\x06schema"\xcb\x01\n\x17RepartitionByExpression\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x0fpartition_exprs\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0epartitionExprs\x12*\n\x0enum_partitions\x18\x03 \x01(\x05H\x00R\rnumPartitions\x88\x01\x01\x42\x11\n\x0f_num_partitions"\xb5\x01\n\rMapPartitions\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x04\x66unc\x18\x02 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12"\n\nis_barrier\x18\x03 \x01(\x08H\x00R\tisBarrier\x88\x01\x01\x42\r\n\x0b_is_barrier"\xcb\x01\n\x08GroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc"\xe0\x02\n\nCoGroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12W\n\x1ainput_grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18inputGroupingExpressions\x12-\n\x05other\x18\x03 \x01(\x0b\x32\x17.spark.connect.RelationR\x05other\x12W\n\x1aother_grouping_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18otherGroupingExpressions\x12\x42\n\x04\x66unc\x18\x05 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc"\xe5\x02\n\x16\x41pplyInPandasWithState\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12#\n\routput_schema\x18\x04 \x01(\tR\x0coutputSchema\x12!\n\x0cstate_schema\x18\x05 \x01(\tR\x0bstateSchema\x12\x1f\n\x0boutput_mode\x18\x06 \x01(\tR\noutputMode\x12!\n\x0ctimeout_conf\x18\x07 \x01(\tR\x0btimeoutConf"\x88\x01\n\x0e\x43ollectMetrics\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x33\n\x07metrics\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07metrics"\x84\x03\n\x05Parse\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x38\n\x06\x66ormat\x18\x02 \x01(\x0e\x32 .spark.connect.Parse.ParseFormatR\x06\x66ormat\x12\x34\n\x06schema\x18\x03 \x01(\x0b\x32\x17.spark.connect.DataTypeH\x00R\x06schema\x88\x01\x01\x12;\n\x07options\x18\x04 \x03(\x0b\x32!.spark.connect.Parse.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"X\n\x0bParseFormat\x12\x1c\n\x18PARSE_FORMAT_UNSPECIFIED\x10\x00\x12\x14\n\x10PARSE_FORMAT_CSV\x10\x01\x12\x15\n\x11PARSE_FORMAT_JSON\x10\x02\x42\t\n\x07_schemaB"\n\x1eorg.apache.spark.connect.protoP\x01\x62\x06proto3' ) @@ -806,81 +806,81 @@ _DROP._serialized_start = 6124 _DROP._serialized_end = 6265 _DEDUPLICATE._serialized_start = 6268 - _DEDUPLICATE._serialized_end = 6439 - _LOCALRELATION._serialized_start = 6441 - _LOCALRELATION._serialized_end = 6530 - _SAMPLE._serialized_start = 6533 - _SAMPLE._serialized_end = 6806 - _RANGE._serialized_start = 6809 - _RANGE._serialized_end = 6954 - _SUBQUERYALIAS._serialized_start = 6956 - _SUBQUERYALIAS._serialized_end = 7070 - _REPARTITION._serialized_start = 7073 - _REPARTITION._serialized_end = 7215 - _SHOWSTRING._serialized_start = 7218 - _SHOWSTRING._serialized_end = 7360 - _HTMLSTRING._serialized_start = 7362 - _HTMLSTRING._serialized_end = 7476 - _STATSUMMARY._serialized_start = 7478 - _STATSUMMARY._serialized_end = 7570 - _STATDESCRIBE._serialized_start = 7572 - _STATDESCRIBE._serialized_end = 7653 - _STATCROSSTAB._serialized_start = 7655 - _STATCROSSTAB._serialized_end = 7756 - _STATCOV._serialized_start = 7758 - _STATCOV._serialized_end = 7854 - _STATCORR._serialized_start = 7857 - _STATCORR._serialized_end = 7994 - _STATAPPROXQUANTILE._serialized_start = 7997 - _STATAPPROXQUANTILE._serialized_end = 8161 - _STATFREQITEMS._serialized_start = 8163 - _STATFREQITEMS._serialized_end = 8288 - _STATSAMPLEBY._serialized_start = 8291 - _STATSAMPLEBY._serialized_end = 8600 - _STATSAMPLEBY_FRACTION._serialized_start = 8492 - _STATSAMPLEBY_FRACTION._serialized_end = 8591 - _NAFILL._serialized_start = 8603 - _NAFILL._serialized_end = 8737 - _NADROP._serialized_start = 8740 - _NADROP._serialized_end = 8874 - _NAREPLACE._serialized_start = 8877 - _NAREPLACE._serialized_end = 9173 - _NAREPLACE_REPLACEMENT._serialized_start = 9032 - _NAREPLACE_REPLACEMENT._serialized_end = 9173 - _TODF._serialized_start = 9175 - _TODF._serialized_end = 9263 - _WITHCOLUMNSRENAMED._serialized_start = 9266 - _WITHCOLUMNSRENAMED._serialized_end = 9505 - _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_start = 9438 - _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_end = 9505 - _WITHCOLUMNS._serialized_start = 9507 - _WITHCOLUMNS._serialized_end = 9626 - _WITHWATERMARK._serialized_start = 9629 - _WITHWATERMARK._serialized_end = 9763 - _HINT._serialized_start = 9766 - _HINT._serialized_end = 9898 - _UNPIVOT._serialized_start = 9901 - _UNPIVOT._serialized_end = 10228 - _UNPIVOT_VALUES._serialized_start = 10158 - _UNPIVOT_VALUES._serialized_end = 10217 - _TOSCHEMA._serialized_start = 10230 - _TOSCHEMA._serialized_end = 10336 - _REPARTITIONBYEXPRESSION._serialized_start = 10339 - _REPARTITIONBYEXPRESSION._serialized_end = 10542 - _MAPPARTITIONS._serialized_start = 10545 - _MAPPARTITIONS._serialized_end = 10726 - _GROUPMAP._serialized_start = 10729 - _GROUPMAP._serialized_end = 10932 - _COGROUPMAP._serialized_start = 10935 - _COGROUPMAP._serialized_end = 11287 - _APPLYINPANDASWITHSTATE._serialized_start = 11290 - _APPLYINPANDASWITHSTATE._serialized_end = 11647 - _COLLECTMETRICS._serialized_start = 11650 - _COLLECTMETRICS._serialized_end = 11786 - _PARSE._serialized_start = 11789 - _PARSE._serialized_end = 12177 + _DEDUPLICATE._serialized_end = 6508 + _LOCALRELATION._serialized_start = 6510 + _LOCALRELATION._serialized_end = 6599 + _SAMPLE._serialized_start = 6602 + _SAMPLE._serialized_end = 6875 + _RANGE._serialized_start = 6878 + _RANGE._serialized_end = 7023 + _SUBQUERYALIAS._serialized_start = 7025 + _SUBQUERYALIAS._serialized_end = 7139 + _REPARTITION._serialized_start = 7142 + _REPARTITION._serialized_end = 7284 + _SHOWSTRING._serialized_start = 7287 + _SHOWSTRING._serialized_end = 7429 + _HTMLSTRING._serialized_start = 7431 + _HTMLSTRING._serialized_end = 7545 + _STATSUMMARY._serialized_start = 7547 + _STATSUMMARY._serialized_end = 7639 + _STATDESCRIBE._serialized_start = 7641 + _STATDESCRIBE._serialized_end = 7722 + _STATCROSSTAB._serialized_start = 7724 + _STATCROSSTAB._serialized_end = 7825 + _STATCOV._serialized_start = 7827 + _STATCOV._serialized_end = 7923 + _STATCORR._serialized_start = 7926 + _STATCORR._serialized_end = 8063 + _STATAPPROXQUANTILE._serialized_start = 8066 + _STATAPPROXQUANTILE._serialized_end = 8230 + _STATFREQITEMS._serialized_start = 8232 + _STATFREQITEMS._serialized_end = 8357 + _STATSAMPLEBY._serialized_start = 8360 + _STATSAMPLEBY._serialized_end = 8669 + _STATSAMPLEBY_FRACTION._serialized_start = 8561 + _STATSAMPLEBY_FRACTION._serialized_end = 8660 + _NAFILL._serialized_start = 8672 + _NAFILL._serialized_end = 8806 + _NADROP._serialized_start = 8809 + _NADROP._serialized_end = 8943 + _NAREPLACE._serialized_start = 8946 + _NAREPLACE._serialized_end = 9242 + _NAREPLACE_REPLACEMENT._serialized_start = 9101 + _NAREPLACE_REPLACEMENT._serialized_end = 9242 + _TODF._serialized_start = 9244 + _TODF._serialized_end = 9332 + _WITHCOLUMNSRENAMED._serialized_start = 9335 + _WITHCOLUMNSRENAMED._serialized_end = 9574 + _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_start = 9507 + _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_end = 9574 + _WITHCOLUMNS._serialized_start = 9576 + _WITHCOLUMNS._serialized_end = 9695 + _WITHWATERMARK._serialized_start = 9698 + _WITHWATERMARK._serialized_end = 9832 + _HINT._serialized_start = 9835 + _HINT._serialized_end = 9967 + _UNPIVOT._serialized_start = 9970 + _UNPIVOT._serialized_end = 10297 + _UNPIVOT_VALUES._serialized_start = 10227 + _UNPIVOT_VALUES._serialized_end = 10286 + _TOSCHEMA._serialized_start = 10299 + _TOSCHEMA._serialized_end = 10405 + _REPARTITIONBYEXPRESSION._serialized_start = 10408 + _REPARTITIONBYEXPRESSION._serialized_end = 10611 + _MAPPARTITIONS._serialized_start = 10614 + _MAPPARTITIONS._serialized_end = 10795 + _GROUPMAP._serialized_start = 10798 + _GROUPMAP._serialized_end = 11001 + _COGROUPMAP._serialized_start = 11004 + _COGROUPMAP._serialized_end = 11356 + _APPLYINPANDASWITHSTATE._serialized_start = 11359 + _APPLYINPANDASWITHSTATE._serialized_end = 11716 + _COLLECTMETRICS._serialized_start = 11719 + _COLLECTMETRICS._serialized_end = 11855 + _PARSE._serialized_start = 11858 + _PARSE._serialized_end = 12246 _PARSE_OPTIONSENTRY._serialized_start = 3597 _PARSE_OPTIONSENTRY._serialized_end = 3655 - _PARSE_PARSEFORMAT._serialized_start = 12078 - _PARSE_PARSEFORMAT._serialized_end = 12166 + _PARSE_PARSEFORMAT._serialized_start = 12147 + _PARSE_PARSEFORMAT._serialized_end = 12235 # @@protoc_insertion_point(module_scope) diff --git a/python/pyspark/sql/connect/proto/relations_pb2.pyi b/python/pyspark/sql/connect/proto/relations_pb2.pyi index b847378d78b53..3dab4f8525eba 100644 --- a/python/pyspark/sql/connect/proto/relations_pb2.pyi +++ b/python/pyspark/sql/connect/proto/relations_pb2.pyi @@ -1436,6 +1436,7 @@ class Deduplicate(google.protobuf.message.Message): INPUT_FIELD_NUMBER: builtins.int COLUMN_NAMES_FIELD_NUMBER: builtins.int ALL_COLUMNS_AS_KEYS_FIELD_NUMBER: builtins.int + WITHIN_WATERMARK_FIELD_NUMBER: builtins.int @property def input(self) -> global___Relation: """(Required) Input relation for a Deduplicate.""" @@ -1452,22 +1453,29 @@ class Deduplicate(google.protobuf.message.Message): This field does not co-use with `column_names`. """ + within_watermark: builtins.bool + """(Optional) Deduplicate within the time range of watermark.""" def __init__( self, *, input: global___Relation | None = ..., column_names: collections.abc.Iterable[builtins.str] | None = ..., all_columns_as_keys: builtins.bool | None = ..., + within_watermark: builtins.bool | None = ..., ) -> None: ... def HasField( self, field_name: typing_extensions.Literal[ "_all_columns_as_keys", b"_all_columns_as_keys", + "_within_watermark", + b"_within_watermark", "all_columns_as_keys", b"all_columns_as_keys", "input", b"input", + "within_watermark", + b"within_watermark", ], ) -> builtins.bool: ... def ClearField( @@ -1475,18 +1483,27 @@ class Deduplicate(google.protobuf.message.Message): field_name: typing_extensions.Literal[ "_all_columns_as_keys", b"_all_columns_as_keys", + "_within_watermark", + b"_within_watermark", "all_columns_as_keys", b"all_columns_as_keys", "column_names", b"column_names", "input", b"input", + "within_watermark", + b"within_watermark", ], ) -> None: ... + @typing.overload def WhichOneof( self, oneof_group: typing_extensions.Literal["_all_columns_as_keys", b"_all_columns_as_keys"], ) -> typing_extensions.Literal["all_columns_as_keys"] | None: ... + @typing.overload + def WhichOneof( + self, oneof_group: typing_extensions.Literal["_within_watermark", b"_within_watermark"] + ) -> typing_extensions.Literal["within_watermark"] | None: ... global___Deduplicate = Deduplicate diff --git a/python/pyspark/sql/tests/connect/test_connect_basic.py b/python/pyspark/sql/tests/connect/test_connect_basic.py index b316f0f3b4c30..d414316c2f9ff 100644 --- a/python/pyspark/sql/tests/connect/test_connect_basic.py +++ b/python/pyspark/sql/tests/connect/test_connect_basic.py @@ -1213,6 +1213,14 @@ def test_deduplicate(self): df.dropDuplicates(["name"]).toPandas(), df2.dropDuplicates(["name"]).toPandas() ) + def test_deduplicate_within_watermark_in_batch(self): + df = self.connect.read.table(self.tbl_name) + with self.assertRaisesRegex( + AnalysisException, + "dropDuplicatesWithinWatermark is not supported with batch DataFrames/DataSets", + ): + df.dropDuplicatesWithinWatermark().toPandas() + def test_first(self): # SPARK-41002: test `first` API in Python Client df = self.connect.read.table(self.tbl_name) @@ -1761,7 +1769,6 @@ def test_hint(self): self.connect.read.table(self.tbl_name).hint("REPARTITION", "id", 3).toPandas() def test_join_hint(self): - cdf1 = self.connect.createDataFrame([(2, "Alice"), (5, "Bob")], schema=["age", "name"]) cdf2 = self.connect.createDataFrame( [Row(height=80, name="Tom"), Row(height=85, name="Bob")] @@ -2284,7 +2291,6 @@ def test_crossjoin(self): ) def test_grouped_data(self): - query = """ SELECT * FROM VALUES ('James', 'Sales', 3000, 2020),