(texera) 01/02: test(workflow-core): cover isFileResolved and parse owner (#6699)

[gi...@apache.org]

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

github-merge-queue[bot] pushed a commit to branch gh-readonly-queue/main/pr-6697-166555d0daf587f6f75b22f324a16ea06963cc39
in repository https://gitbox.apache.org/repos/asf/texera.git

commit 166555d0daf587f6f75b22f324a16ea06963cc39
Author: Matthew B. <mg...@uci.edu>
AuthorDate: Tue Jul 21 18:38:01 2026 -0700

    test(workflow-core): cover isFileResolved and parse owner (#6699)
    
    ### What changes were proposed in this PR?
    - Add unit tests for FileResolver.isFileResolved covering non-empty
    scheme, missing scheme, and malformed URI cases.
    - Add unit tests for FileResolver.parseDatasetOwnerAndName covering
    valid paths, too few segments, and a null path.
    ### Any related issues, documentation, discussions?
    Closes: #6698
    ### How was this PR tested?
    - Run: `sbt "WorkflowCore/testOnly *FileResolverSpec"`, expect all 9
    tests passing.
    - Test-only change; no production code is modified.
    ### Was this PR authored or co-authored using generative AI tooling?
    Co-authored with Claude Opus 4.8 in compliance with ASF
---
 .../texera/amber/storage/FileResolverSpec.scala    | 38 ++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/common/workflow-core/src/test/scala/org/apache/texera/amber/storage/FileResolverSpec.scala b/common/workflow-core/src/test/scala/org/apache/texera/amber/storage/FileResolverSpec.scala
index 593ac8d347..62daa811d3 100644
--- a/common/workflow-core/src/test/scala/org/apache/texera/amber/storage/FileResolverSpec.scala
+++ b/common/workflow-core/src/test/scala/org/apache/texera/amber/storage/FileResolverSpec.scala
@@ -124,6 +124,44 @@ class FileResolverSpec
     }
   }
 
+  "isFileResolved" should "return true when the path has a non-empty scheme" in {
+    assert(FileResolver.isFileResolved("s3://bucket/key"))
+    assert(
+      FileResolver.isFileResolved(s"${FileResolver.DATASET_FILE_URI_SCHEME}:///repo/hash/file.csv")
+    )
+  }
+
+  it should "return false when the path has no scheme" in {
+    assert(!FileResolver.isFileResolved("some/random/path"))
+    assert(!FileResolver.isFileResolved("/test_user@test.com/test_dataset/v1/1.txt"))
+  }
+
+  it should "return false for a malformed URI" in {
+    // a space is illegal in a URI and makes the java.net.URI constructor throw
+    assert(!FileResolver.isFileResolved("has a space"))
+  }
+
+  "parseDatasetOwnerAndName" should "extract owner email and dataset name from a valid path" in {
+    assert(
+      FileResolver.parseDatasetOwnerAndName("/test_user@test.com/test_dataset/v1/1.txt")
+        == Some(("test_user@test.com", "test_dataset"))
+    )
+    // extra segments beyond the file-relative path are ignored
+    assert(
+      FileResolver.parseDatasetOwnerAndName("/owner@x.com/ds/v2/directory/nested/a.csv")
+        == Some(("owner@x.com", "ds"))
+    )
+  }
+
+  it should "return None when the path has fewer than four segments" in {
+    assert(FileResolver.parseDatasetOwnerAndName("/owner@x.com/ds/v1").isEmpty)
+    assert(FileResolver.parseDatasetOwnerAndName("owner/dataset").isEmpty)
+  }
+
+  it should "return None for a null path" in {
+    assert(FileResolver.parseDatasetOwnerAndName(null).isEmpty)
+  }
+
   override protected def afterAll(): Unit = {
     shutdownDB()
   }