(spark-connect-swift) branch main updated: [SPARK-52317] Identify `InvalidTypeException` in `SparkConnectClient`

[dongjoon]

This is an automated email from the ASF dual-hosted git repository.

dongjoon pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/spark-connect-swift.git


The following commit(s) were added to refs/heads/main by this push:
     new af7b0c9  [SPARK-52317] Identify `InvalidTypeException` in 
`SparkConnectClient`
af7b0c9 is described below

commit af7b0c9867d2a8aa523a34c87a9477d8f14ead2b
Author: Dongjoon Hyun <dongj...@apache.org>
AuthorDate: Mon May 26 18:02:41 2025 -0700

    [SPARK-52317] Identify `InvalidTypeException` in `SparkConnectClient`
    
    ### What changes were proposed in this pull request?
    
    This PR aims to identify `InvalidTypeException` in `SparkConnectClient`.
    
    ### Why are the changes needed?
    
    To centralize the `InvalidTypeException` handling into a single place. 
Previously, three actors do the same error handling logic redundantly.
    - `DataFrame`
    - `DataFrameReader`
    - `DataStreamReader`
    
    ### Does this PR introduce _any_ user-facing change?
    
    No.
    
    ### How was this patch tested?
    
    Pass the CIs.
    
    ### Was this patch authored or co-authored using generative AI tooling?
    
    No.
    
    Closes #176 from dongjoon-hyun/SPARK-52317.
    
    Authored-by: Dongjoon Hyun <dongj...@apache.org>
    Signed-off-by: Dongjoon Hyun <dongj...@apache.org>
---
 Sources/SparkConnect/DataFrame.swift          |  9 ++-------
 Sources/SparkConnect/DataFrameReader.swift    |  7 +------
 Sources/SparkConnect/DataStreamReader.swift   |  7 +------
 Sources/SparkConnect/SparkConnectClient.swift | 13 +++++++++++--
 4 files changed, 15 insertions(+), 21 deletions(-)

diff --git a/Sources/SparkConnect/DataFrame.swift 
b/Sources/SparkConnect/DataFrame.swift
index 760ece3..e52226a 100644
--- a/Sources/SparkConnect/DataFrame.swift
+++ b/Sources/SparkConnect/DataFrame.swift
@@ -489,13 +489,8 @@ public actor DataFrame: Sendable {
   /// - Parameter schema: The given schema.
   /// - Returns: A ``DataFrame`` with the given schema.
   public func to(_ schema: String) async throws -> DataFrame {
-    // Validate by parsing.
-    do {
-      let dataType = try await sparkSession.client.ddlParse(schema)
-      return DataFrame(spark: self.spark, plan: 
SparkConnectClient.getToSchema(self.plan.root, dataType))
-    } catch {
-      throw SparkConnectError.InvalidTypeException
-    }
+    let dataType = try await sparkSession.client.ddlParse(schema)
+    return DataFrame(spark: self.spark, plan: 
SparkConnectClient.getToSchema(self.plan.root, dataType))
   }
 
   /// Returns the content of the Dataset as a Dataset of JSON strings.
diff --git a/Sources/SparkConnect/DataFrameReader.swift 
b/Sources/SparkConnect/DataFrameReader.swift
index 58567db..274efdf 100644
--- a/Sources/SparkConnect/DataFrameReader.swift
+++ b/Sources/SparkConnect/DataFrameReader.swift
@@ -123,12 +123,7 @@ public actor DataFrameReader: Sendable {
   /// - Returns: A ``DataFrameReader``.
   @discardableResult
   public func schema(_ schema: String) async throws -> DataFrameReader {
-    // Validate by parsing.
-    do {
-      try await sparkSession.client.ddlParse(schema)
-    } catch {
-      throw SparkConnectError.InvalidTypeException
-    }
+    try await sparkSession.client.ddlParse(schema)
     self.userSpecifiedSchemaDDL = schema
     return self
   }
diff --git a/Sources/SparkConnect/DataStreamReader.swift 
b/Sources/SparkConnect/DataStreamReader.swift
index e90a1c1..da87505 100644
--- a/Sources/SparkConnect/DataStreamReader.swift
+++ b/Sources/SparkConnect/DataStreamReader.swift
@@ -50,12 +50,7 @@ public actor DataStreamReader: Sendable {
   /// - Returns: A ``DataStreamReader``.
   @discardableResult
   public func schema(_ schema: String) async throws -> DataStreamReader {
-    // Validate by parsing.
-    do {
-      try await sparkSession.client.ddlParse(schema)
-    } catch {
-      throw SparkConnectError.InvalidTypeException
-    }
+    try await sparkSession.client.ddlParse(schema)
     self.userSpecifiedSchemaDDL = schema
     return self
   }
diff --git a/Sources/SparkConnect/SparkConnectClient.swift 
b/Sources/SparkConnect/SparkConnectClient.swift
index 5c6b4cc..f8a0073 100644
--- a/Sources/SparkConnect/SparkConnectClient.swift
+++ b/Sources/SparkConnect/SparkConnectClient.swift
@@ -781,8 +781,17 @@ public actor SparkConnectClient {
         ddlParse.ddlString = ddlString
         return OneOf_Analyze.ddlParse(ddlParse)
       })
-      let response = try await service.analyzePlan(request)
-      return response.ddlParse.parsed
+      do {
+        let response = try await service.analyzePlan(request)
+        return response.ddlParse.parsed
+      } catch let error as RPCError where error.code == .internalError {
+        switch error.message {
+        case let m where m.contains("UNSUPPORTED_DATATYPE") || 
m.contains("INVALID_IDENTIFIER"):
+          throw SparkConnectError.InvalidTypeException
+        default:
+          throw error
+        }
+      }
     }
   }
 


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org