(texera) branch main updated: test(workflow-operator): cover User-Agent header in URLFetchUtilSpec (#5710)

[gi...@apache.org]

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

github-merge-queue[bot] pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/texera.git


The following commit(s) were added to refs/heads/main by this push:
     new a53d95a9a3 test(workflow-operator): cover User-Agent header in URLFetchUtilSpec (#5710)
a53d95a9a3 is described below

commit a53d95a9a32dd38815dcfc3e75f4157a45a2997b
Author: Justin Siek <13...@users.noreply.github.com>
AuthorDate: Fri Jul 3 12:25:36 2026 +0800

    test(workflow-operator): cover User-Agent header in URLFetchUtilSpec (#5710)
    
    ### What changes were proposed in this PR?
    
    Adds `URLFetchUtilSpec`, a unit test for
    `URLFetchUtil.getInputStreamFromURL`. A stub `URLStreamHandler` scripts
    per attempt success/failure, so nothing hits the network. No production
    code changed.
    
    ### Any related issues, documentation, discussions?
    
    Closes #5661
    
    ### How was this PR tested?
    
    No production code changed, just new unit tests for existing code.
    
    ### Was this PR authored or co-authored using generative AI tooling?
    
    Generated-by: Claude Code (Claude Opus 4.8)
    
    Co-authored-by: Justin Siek <ju...@Justins-MacBook-Air.local>
    Co-authored-by: Meng Wang <me...@uci.edu>
---
 .../operator/source/fetcher/URLFetchUtilSpec.scala      | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/source/fetcher/URLFetchUtilSpec.scala b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/source/fetcher/URLFetchUtilSpec.scala
index a64d21cc3f..ec16567970 100644
--- a/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/source/fetcher/URLFetchUtilSpec.scala
+++ b/common/workflow-operator/src/test/scala/org/apache/texera/amber/operator/source/fetcher/URLFetchUtilSpec.scala
@@ -55,11 +55,15 @@ class URLFetchUtilSpec extends AnyFlatSpec {
   private class CountingStreamHandler(succeedWithBytes: Option[Array[Byte]])
       extends URLStreamHandler {
     val openConnectionCount = new AtomicInteger(0)
+    // Captures the most recent User-Agent request property set on a connection.
+    var userAgent: Option[String] = None
 
     override def openConnection(u: URL): URLConnection = {
       openConnectionCount.incrementAndGet()
       new URLConnection(u) {
         override def connect(): Unit = ()
+        override def setRequestProperty(key: String, value: String): Unit =
+          if (key == "User-Agent") userAgent = Some(value)
         override def getInputStream: InputStream =
           succeedWithBytes match {
             case Some(bytes) => new ByteArrayInputStream(bytes)
@@ -135,4 +139,17 @@ class URLFetchUtilSpec extends AnyFlatSpec {
     assert(result.isEmpty)
     assert(handler.openConnectionCount.get() == 2)
   }
+
+  // ---------------------------------------------------------------------------
+  // Request headers
+  // ---------------------------------------------------------------------------
+
+  it should "set a User-Agent request property before reading the stream" in {
+    val handler =
+      new CountingStreamHandler(Some("ok".getBytes(StandardCharsets.UTF_8)))
+    val result = URLFetchUtil.getInputStreamFromURL(countingUrl(handler))
+    result.foreach(_.close())
+    // Pin only that the header is set, not its specific (randomized) value.
+    assert(handler.userAgent.isDefined)
+  }
 }