This is an automated email from the ASF dual-hosted git repository. wenchen pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push: new c7878850f55 [SPARK-41306][CONNECT] Improve Connect Expression proto documentation c7878850f55 is described below commit c7878850f55643fa061e25f9ffba60edf4f37275 Author: Rui Wang <rui.w...@databricks.com> AuthorDate: Tue Nov 29 09:02:03 2022 +0800 [SPARK-41306][CONNECT] Improve Connect Expression proto documentation ### What changes were proposed in this pull request? Improve Connect Expression proto documentation by following https://github.com/apache/spark/blob/master/connector/connect/docs/adding-proto-messages.md. ### Why are the changes needed? Proto Documentation. ### Does this PR introduce _any_ user-facing change? NO ### How was this patch tested? N/A Closes #38825 from amaliujia/improve_proto_expr_documentation. Authored-by: Rui Wang <rui.w...@databricks.com> Signed-off-by: Wenchen Fan <wenc...@databricks.com> --- .../main/protobuf/spark/connect/expressions.proto | 14 +++++++++++++- .../pyspark/sql/connect/proto/expressions_pb2.pyi | 21 ++++++++++++++++----- 2 files changed, 29 insertions(+), 6 deletions(-) diff --git a/connector/connect/src/main/protobuf/spark/connect/expressions.proto b/connector/connect/src/main/protobuf/spark/connect/expressions.proto index 85049f1d14b..595758f0443 100644 --- a/connector/connect/src/main/protobuf/spark/connect/expressions.proto +++ b/connector/connect/src/main/protobuf/spark/connect/expressions.proto @@ -142,18 +142,24 @@ message Expression { // An unresolved attribute that is not explicitly bound to a specific column, but the column // is resolved during analysis by name. message UnresolvedAttribute { + // (Required) An identifier that will be parsed by Catalyst parser. This should follow the + // Spark SQL identifier syntax. string unparsed_identifier = 1; } // An unresolved function is not explicitly bound to one explicit function, but the function // is resolved during analysis following Sparks name resolution rules. message UnresolvedFunction { + // (Required) Names parts for the unresolved function. repeated string parts = 1; + + // (Optional) Function arguments. Empty arguments are allowed. repeated Expression arguments = 2; } // Expression as string. message ExpressionString { + // (Required) A SQL expression that will be parsed by Catalyst parser. string expression = 1; } @@ -162,9 +168,15 @@ message Expression { } message Alias { + // (Required) The expression that alias will be added on. Expression expr = 1; + + // (Required) a list of name parts for the alias. + // + // Scalar columns only has one name that presents. repeated string name = 2; - // Alias metadata expressed as a JSON map. + + // (Optional) Alias metadata expressed as a JSON map. optional string metadata = 3; } } diff --git a/python/pyspark/sql/connect/proto/expressions_pb2.pyi b/python/pyspark/sql/connect/proto/expressions_pb2.pyi index bf2dc06b685..23ef99c6c48 100644 --- a/python/pyspark/sql/connect/proto/expressions_pb2.pyi +++ b/python/pyspark/sql/connect/proto/expressions_pb2.pyi @@ -538,6 +538,9 @@ class Expression(google.protobuf.message.Message): UNPARSED_IDENTIFIER_FIELD_NUMBER: builtins.int unparsed_identifier: builtins.str + """(Required) An identifier that will be parsed by Catalyst parser. This should follow the + Spark SQL identifier syntax. + """ def __init__( self, *, @@ -560,13 +563,15 @@ class Expression(google.protobuf.message.Message): @property def parts( self, - ) -> google.protobuf.internal.containers.RepeatedScalarFieldContainer[builtins.str]: ... + ) -> google.protobuf.internal.containers.RepeatedScalarFieldContainer[builtins.str]: + """(Required) Names parts for the unresolved function.""" @property def arguments( self, ) -> google.protobuf.internal.containers.RepeatedCompositeFieldContainer[ global___Expression - ]: ... + ]: + """(Optional) Function arguments. Empty arguments are allowed.""" def __init__( self, *, @@ -585,6 +590,7 @@ class Expression(google.protobuf.message.Message): EXPRESSION_FIELD_NUMBER: builtins.int expression: builtins.str + """(Required) A SQL expression that will be parsed by Catalyst parser.""" def __init__( self, *, @@ -610,13 +616,18 @@ class Expression(google.protobuf.message.Message): NAME_FIELD_NUMBER: builtins.int METADATA_FIELD_NUMBER: builtins.int @property - def expr(self) -> global___Expression: ... + def expr(self) -> global___Expression: + """(Required) The expression that alias will be added on.""" @property def name( self, - ) -> google.protobuf.internal.containers.RepeatedScalarFieldContainer[builtins.str]: ... + ) -> google.protobuf.internal.containers.RepeatedScalarFieldContainer[builtins.str]: + """(Required) a list of name parts for the alias. + + Scalar columns only has one name that presents. + """ metadata: builtins.str - """Alias metadata expressed as a JSON map.""" + """(Optional) Alias metadata expressed as a JSON map.""" def __init__( self, *, --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org