This is an automated email from the ASF dual-hosted git repository.
dongjoon-hyun 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 972244e [SPARK-57060] Support `analyzeTable` in `Catalog`
972244e is described below
commit 972244e9c7cfd0c6ad4d641f3801d8425cfc098b
Author: Dongjoon Hyun <[email protected]>
AuthorDate: Mon May 25 18:33:58 2026 -0700
[SPARK-57060] Support `analyzeTable` in `Catalog`
### What changes were proposed in this pull request?
This PR aims to support `Spark_Connect_AnalyzeTable` message added in
Apache Spark Connect 4.2.0-preview5.
- https://github.com/apache/spark/pull/55025
### Why are the changes needed?
For feature parity with Spark Connect.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Pass the CIs with the newly added test case.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Claude Opus 4.7
Closes #388 from dongjoon-hyun/SPARK-57060.
Authored-by: Dongjoon Hyun <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>
---
Sources/SparkConnect/Catalog.swift | 16 ++++++++++++++++
Tests/SparkConnectTests/CatalogTests.swift | 18 ++++++++++++++++++
2 files changed, 34 insertions(+)
diff --git a/Sources/SparkConnect/Catalog.swift
b/Sources/SparkConnect/Catalog.swift
index bb3f617..eea6755 100644
--- a/Sources/SparkConnect/Catalog.swift
+++ b/Sources/SparkConnect/Catalog.swift
@@ -584,6 +584,22 @@ public actor Catalog: Sendable {
try await df.count()
}
+ /// Analyzes the given table to compute statistics that can be used by the
query optimizer.
+ /// - Parameters:
+ /// - tableName: A qualified or unqualified name that designates a table.
+ /// - noScan: If true, only basic statistics (row count) are computed
without scanning the data.
+ public func analyzeTable(_ tableName: String, noScan: Bool = false) async
throws {
+ let df = getDataFrame({
+ var analyzeTable = Spark_Connect_AnalyzeTable()
+ analyzeTable.tableName = tableName
+ analyzeTable.noScan = noScan
+ var catalog = Spark_Connect_Catalog()
+ catalog.catType = .analyzeTable(analyzeTable)
+ return catalog
+ })
+ try await df.count()
+ }
+
/// Invalidates and refreshes all the cached data (and the associated
metadata) for any ``DataFrame``
/// that contains the given data source path. Path matching is by checking
for sub-directories,
/// i.e. "/" would invalidate everything that is cached and "/test/parent"
would invalidate
diff --git a/Tests/SparkConnectTests/CatalogTests.swift
b/Tests/SparkConnectTests/CatalogTests.swift
index 1456bba..eba3e9e 100644
--- a/Tests/SparkConnectTests/CatalogTests.swift
+++ b/Tests/SparkConnectTests/CatalogTests.swift
@@ -608,6 +608,24 @@ struct CatalogTests {
await spark.stop()
}
+ @Test
+ func analyzeTable() async throws {
+ let spark = try await SparkSession.builder.getOrCreate()
+ if await spark.version >= "4.2" {
+ let tableName = "TABLE_" + UUID().uuidString.replacingOccurrences(of:
"-", with: "")
+ try await SQLHelper.withTable(spark, tableName)({
+ try await spark.range(10).write.saveAsTable(tableName)
+ try await spark.catalog.analyzeTable(tableName)
+ try await spark.catalog.analyzeTable(tableName, noScan: true)
+ })
+
+ try await #require(throws: SparkConnectError.TableOrViewNotFound) {
+ try await spark.catalog.analyzeTable("not_exist_table")
+ }
+ }
+ await spark.stop()
+ }
+
@Test
func refreshByPath() async throws {
let spark = try await SparkSession.builder.getOrCreate()
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
