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 7fe4882 [SPARK-51858] Support `SPARK_REMOTE`
7fe4882 is described below
commit 7fe48821dedc2d04942b5d81ef114aa67336faff
Author: Dongjoon Hyun <dongj...@apache.org>
AuthorDate: Mon Apr 21 23:57:09 2025 +0900
[SPARK-51858] Support `SPARK_REMOTE`
### What changes were proposed in this pull request?
This PR aims to support `SPARK_REMOTE` environment variable.
### Why are the changes needed?
For feature parity.
### Does this PR introduce _any_ user-facing change?
No behavior change. This is an additional way to set Spark connect remote
string.
### How was this patch tested?
Pass the CIs with the revised test pipeline.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #79 from dongjoon-hyun/SPARK-51858.
Authored-by: Dongjoon Hyun <dongj...@apache.org>
Signed-off-by: Dongjoon Hyun <dongj...@apache.org>
---
.github/workflows/build_and_test.yml | 4 +++-
Sources/SparkConnect/SparkSession.swift | 3 ++-
Tests/SparkConnectTests/BuilderTests.swift | 8 ++++++--
Tests/SparkConnectTests/RuntimeConfTests.swift | 10 ++++++----
Tests/SparkConnectTests/SparkConnectClientTests.swift | 14 ++++++++------
5 files changed, 25 insertions(+), 14 deletions(-)
diff --git a/.github/workflows/build_and_test.yml
b/.github/workflows/build_and_test.yml
index f0d64b2..a785839 100644
--- a/.github/workflows/build_and_test.yml
+++ b/.github/workflows/build_and_test.yml
@@ -67,13 +67,15 @@ jobs:
integration-test-linux:
runs-on: ubuntu-latest
+ env:
+ SPARK_REMOTE: "sc://localhost:15003"
services:
spark:
image: apache/spark:4.0.0-preview2
env:
SPARK_NO_DAEMONIZE: 1
ports:
- - 15002:15002
+ - 15003:15002
options: --entrypoint /opt/spark/sbin/start-connect-server.sh
steps:
- uses: actions/checkout@v4
diff --git a/Sources/SparkConnect/SparkSession.swift
b/Sources/SparkConnect/SparkSession.swift
index 480f55f..b57ec76 100644
--- a/Sources/SparkConnect/SparkSession.swift
+++ b/Sources/SparkConnect/SparkSession.swift
@@ -221,7 +221,8 @@ public actor SparkSession {
/// Create a new ``SparkSession``. If `spark.remote` is not given,
`sc://localhost:15002` is used.
/// - Returns: A newly created `SparkSession`.
func create() async throws -> SparkSession {
- let session = SparkSession(sparkConf["spark.remote"] ??
"sc://localhost:15002")
+ let remote = ProcessInfo.processInfo.environment["SPARK_REMOTE"] ??
"sc://localhost:15002"
+ let session = SparkSession(sparkConf["spark.remote"] ?? remote)
let response = try await session.client.connect(session.sessionID)
await session.setVersion(response.sparkVersion.version)
let isSuccess = try await session.client.setConf(map: sparkConf)
diff --git a/Tests/SparkConnectTests/BuilderTests.swift
b/Tests/SparkConnectTests/BuilderTests.swift
index 91fee76..de2b31d 100644
--- a/Tests/SparkConnectTests/BuilderTests.swift
+++ b/Tests/SparkConnectTests/BuilderTests.swift
@@ -17,6 +17,7 @@
// under the License.
//
+import Foundation
import Testing
@testable import SparkConnect
@@ -24,12 +25,15 @@ import Testing
/// A test suite for `SparkSession.Builder`
@Suite(.serialized)
struct BuilderTests {
+ let TEST_REMOTE = ProcessInfo.processInfo.environment["SPARK_REMOTE"] ??
"sc://localhost:15002"
+
@Test
func builderDefault() async throws {
+ let url = URL(string: self.TEST_REMOTE)!
let spark = try await SparkSession.builder.getOrCreate()
#expect(await spark.client.clientType == "swift")
- #expect(await spark.client.url.host() == "localhost")
- #expect(await spark.client.url.port == 15002)
+ #expect(await spark.client.url.host() == url.host())
+ #expect(await spark.client.url.port == url.port)
await spark.stop()
}
diff --git a/Tests/SparkConnectTests/RuntimeConfTests.swift
b/Tests/SparkConnectTests/RuntimeConfTests.swift
index 4452085..cedab9d 100644
--- a/Tests/SparkConnectTests/RuntimeConfTests.swift
+++ b/Tests/SparkConnectTests/RuntimeConfTests.swift
@@ -25,9 +25,11 @@ import Testing
/// A test suite for `RuntimeConf`
@Suite(.serialized)
struct RuntimeConfTests {
+ let TEST_REMOTE = ProcessInfo.processInfo.environment["SPARK_REMOTE"] ??
"sc://localhost"
+
@Test
func get() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
_ = try await client.connect(UUID().uuidString)
let conf = RuntimeConf(client)
@@ -42,7 +44,7 @@ struct RuntimeConfTests {
@Test
func set() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
_ = try await client.connect(UUID().uuidString)
let conf = RuntimeConf(client)
try await conf.set("spark.test.key1", "value1")
@@ -52,7 +54,7 @@ struct RuntimeConfTests {
@Test
func reset() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
_ = try await client.connect(UUID().uuidString)
let conf = RuntimeConf(client)
@@ -73,7 +75,7 @@ struct RuntimeConfTests {
@Test
func getAll() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
_ = try await client.connect(UUID().uuidString)
let conf = RuntimeConf(client)
let map = try await conf.getAll()
diff --git a/Tests/SparkConnectTests/SparkConnectClientTests.swift
b/Tests/SparkConnectTests/SparkConnectClientTests.swift
index a1ef083..a9c1c22 100644
--- a/Tests/SparkConnectTests/SparkConnectClientTests.swift
+++ b/Tests/SparkConnectTests/SparkConnectClientTests.swift
@@ -25,9 +25,11 @@ import Testing
/// A test suite for `SparkConnectClient`
@Suite(.serialized)
struct SparkConnectClientTests {
+ let TEST_REMOTE = ProcessInfo.processInfo.environment["SPARK_REMOTE"] ??
"sc://localhost"
+
@Test
func createAndStop() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
await client.stop()
}
@@ -44,7 +46,7 @@ struct SparkConnectClientTests {
@Test
func connectWithInvalidUUID() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
try await #require(throws: SparkConnectError.InvalidSessionIDException) {
let _ = try await client.connect("not-a-uuid-format")
}
@@ -53,14 +55,14 @@ struct SparkConnectClientTests {
@Test
func connect() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
let _ = try await client.connect(UUID().uuidString)
await client.stop()
}
@Test
func tags() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
let _ = try await client.connect(UUID().uuidString)
let plan = await client.getPlanRange(0, 1, 1)
@@ -76,7 +78,7 @@ struct SparkConnectClientTests {
@Test
func ddlParse() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
let _ = try await client.connect(UUID().uuidString)
#expect(try await client.ddlParse("a int").simpleString == "struct<a:int>")
await client.stop()
@@ -85,7 +87,7 @@ struct SparkConnectClientTests {
#if !os(Linux) // TODO: Enable this with the offical Spark 4 docker image
@Test
func jsonToDdl() async throws {
- let client = SparkConnectClient(remote: "sc://localhost")
+ let client = SparkConnectClient(remote: TEST_REMOTE)
let _ = try await client.connect(UUID().uuidString)
let json =
#"{"type":"struct","fields":[{"name":"id","type":"long","nullable":false,"metadata":{}}]}"#
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
