feat(storage): singularize the resource-type prefix on logical paths

amber/src/main/python/pytexera/storage/dataset_file_document.py

@@ -59,18 +59,18 @@ def __init__(self, file_path: str):
 
         :param file_path:
            Expected format -
-             "/datasets/ownerEmail/datasetName/versionName/fileRelativePath"
+             "/dataset/ownerEmail/datasetName/versionName/fileRelativePath"
            Example:
-             "/datasets/bob@texera.com/twitterDataset/v1/california/tw1.csv"
+             "/dataset/bob@texera.com/twitterDataset/v1/california/tw1.csv"
         """
         parts = file_path.strip("/").split("/")
 
         invalid_format = ValueError(
             "Invalid file path format. Expected: "
-            "/datasets/ownerEmail/datasetName/versionName/fileRelativePath"
+            "/dataset/ownerEmail/datasetName/versionName/fileRelativePath"
         )
 
-        # TODO(datasets-prefix): require the prefix once all stored paths are migrated (36.sql) and ml model support work is completed.
+        # TODO(dataset-prefix): require the prefix once all stored paths are migrated (36.sql) and ml model support work is completed.
         if parts and parts[0] in {t.value for t in ResourceType}:
             if len(parts) < 5:
                 raise invalid_format
@@ -80,7 +80,7 @@ def __init__(self, file_path: str):
             self.version_name = parts[3]
             self.file_relative_path = "/".join(parts[4:])
         elif len(parts) >= 4:
-            self.resource_type = ResourceType.DATASETS
+            self.resource_type = ResourceType.DATASET
             self.owner_email = parts[0]
             self.dataset_name = parts[1]
             self.version_name = parts[2]

amber/src/main/python/pytexera/storage/resource_type.py

@@ -21,4 +21,4 @@
 class ResourceType(str, Enum):
     """The leading segment of a logical file path, identifying the resource kind"""
 
-    DATASETS = "datasets"
+    DATASET = "dataset"

amber/src/main/scala/org/apache/texera/web/resource/dashboard/SearchQueryBuilder.scala

@@ -19,6 +19,7 @@
 
 package org.apache.texera.web.resource.dashboard
 
+import org.apache.texera.amber.core.storage.ResourceType
 import org.apache.texera.dao.SqlServer
 import org.apache.texera.web.resource.dashboard.DashboardResource.{
   DashboardClickableFileEntry,
@@ -36,7 +37,7 @@ object SearchQueryBuilder {
   val FILE_RESOURCE_TYPE = "file"
   val WORKFLOW_RESOURCE_TYPE = "workflow"
   val PROJECT_RESOURCE_TYPE = "project"
-  val DATASET_RESOURCE_TYPE = "dataset"
+  val DATASET_RESOURCE_TYPE = ResourceType.Dataset.toString
   val ALL_RESOURCE_TYPE = ""
 }
 

amber/src/main/scala/org/apache/texera/web/resource/dashboard/hub/EntityType.scala

@@ -20,6 +20,7 @@
 package org.apache.texera.web.resource.dashboard.hub
 
 import com.fasterxml.jackson.annotation.{JsonCreator, JsonValue}
+import org.apache.texera.amber.core.storage.ResourceType
 
 /**
   * Defines all supported entity types for Hub resources.
@@ -34,7 +35,7 @@ sealed trait EntityType {
 
 object EntityType {
   case object Workflow extends EntityType { val value = "workflow" }
-  case object Dataset extends EntityType { val value = "dataset" }
+  case object Dataset extends EntityType { val value: String = ResourceType.Dataset.toString }
 
   private val values = Seq(Workflow, Dataset)
 

amber/src/test/python/pytexera/storage/test_dataset_file_document.py

@@ -47,18 +47,18 @@ def make_response(status_code: int, body=None, content: bytes = b""):
 
 class TestDatasetFileDocumentInit:
     def test_parses_prefixed_path(self, auth_env):
-        doc = DatasetFileDocument("/datasets/bob@x.com/ds/v1/file.csv")
+        doc = DatasetFileDocument("/dataset/bob@x.com/ds/v1/file.csv")
         assert doc.owner_email == "bob@x.com"
         assert doc.dataset_name == "ds"
         assert doc.version_name == "v1"
         assert doc.file_relative_path == "file.csv"
 
     def test_joins_nested_relative_path_back_with_slashes(self, auth_env):
-        doc = DatasetFileDocument("/datasets/bob@x.com/ds/v1/a/b/c/file.csv")
+        doc = DatasetFileDocument("/dataset/bob@x.com/ds/v1/a/b/c/file.csv")
         assert doc.file_relative_path == "a/b/c/file.csv"
 
     def test_strips_leading_and_trailing_slashes_before_parsing(self, auth_env):
-        doc = DatasetFileDocument("///datasets/bob@x.com/ds/v1/file.csv///")
+        doc = DatasetFileDocument("///dataset/bob@x.com/ds/v1/file.csv///")
         assert doc.owner_email == "bob@x.com"
         assert doc.file_relative_path == "file.csv"
 
@@ -80,7 +80,7 @@ def test_unknown_leading_segment_is_read_as_a_legacy_owner(self, auth_env):
 
     def test_rejects_prefixed_path_with_too_few_segments(self, auth_env):
         with pytest.raises(ValueError, match="Invalid file path format"):
-            DatasetFileDocument("/datasets/bob@x.com/ds/v1")
+            DatasetFileDocument("/dataset/bob@x.com/ds/v1")
 
     def test_rejects_legacy_path_with_too_few_segments(self, auth_env):
         with pytest.raises(ValueError, match="Invalid file path format"):
@@ -92,29 +92,29 @@ def test_requires_jwt_token_in_environment(self, monkeypatch):
             "FILE_SERVICE_GET_DATASET_PRESIGNED_URL_ENDPOINT", CUSTOM_ENDPOINT
         )
         with pytest.raises(ValueError, match="JWT token is required"):
-            DatasetFileDocument("/datasets/bob@x.com/ds/v1/file.csv")
+            DatasetFileDocument("/dataset/bob@x.com/ds/v1/file.csv")
 
     def test_treats_empty_jwt_as_missing(self, monkeypatch):
         # An empty string is falsy and should be rejected just like an unset var.
         monkeypatch.setenv("USER_JWT_TOKEN", "")
         with pytest.raises(ValueError, match="JWT token is required"):
-            DatasetFileDocument("/datasets/bob@x.com/ds/v1/file.csv")
+            DatasetFileDocument("/dataset/bob@x.com/ds/v1/file.csv")
 
     def test_falls_back_to_default_endpoint_when_env_missing(self, monkeypatch):
         monkeypatch.setenv("USER_JWT_TOKEN", "tok")
         monkeypatch.delenv(
             "FILE_SERVICE_GET_DATASET_PRESIGNED_URL_ENDPOINT", raising=False
         )
-        doc = DatasetFileDocument("/datasets/bob@x.com/ds/v1/file.csv")
+        doc = DatasetFileDocument("/dataset/bob@x.com/ds/v1/file.csv")
         assert doc.presign_endpoint == DEFAULT_ENDPOINT
 
     def test_uses_explicit_endpoint_from_environment(self, auth_env):
-        doc = DatasetFileDocument("/datasets/bob@x.com/ds/v1/file.csv")
+        doc = DatasetFileDocument("/dataset/bob@x.com/ds/v1/file.csv")
         assert doc.presign_endpoint == CUSTOM_ENDPOINT
 
 
 class TestGetPresignedUrl:
-    def _make_doc(self, monkeypatch, path="/datasets/bob@x.com/ds/v1/file.csv"):
+    def _make_doc(self, monkeypatch, path="/dataset/bob@x.com/ds/v1/file.csv"):
         monkeypatch.setenv("USER_JWT_TOKEN", "test-jwt-token")
         monkeypatch.setenv(
             "FILE_SERVICE_GET_DATASET_PRESIGNED_URL_ENDPOINT", CUSTOM_ENDPOINT
@@ -144,9 +144,7 @@ def test_sends_bearer_authorization_header_with_jwt(self, monkeypatch):
     def test_url_encodes_filepath_query_parameter(self, monkeypatch):
         # urllib.parse.quote keeps "/" as safe by default, but encodes "@"
         # and " " — pin both pieces so the contract is explicit.
-        doc = self._make_doc(
-            monkeypatch, path="/datasets/bob@x.com/ds/v1/data file.csv"
-        )
+        doc = self._make_doc(monkeypatch, path="/dataset/bob@x.com/ds/v1/data file.csv")
         with patch(
             "pytexera.storage.dataset_file_document.requests.Session.get"
         ) as mock_get:
@@ -158,16 +156,16 @@ def test_url_encodes_filepath_query_parameter(self, monkeypatch):
             assert "bob%40x.com" in file_path
             assert file_path.startswith("/")
 
-    def test_sends_datasets_prefixed_filepath(self, monkeypatch):
-        # The reconstructed filePath sent to the file-service carries the "datasets" prefix.
-        doc = self._make_doc(monkeypatch, path="/datasets/bob@x.com/ds/v1/file.csv")
+    def test_sends_dataset_prefixed_filepath(self, monkeypatch):
+        # The reconstructed filePath sent to the file-service carries the "dataset" prefix.
+        doc = self._make_doc(monkeypatch, path="/dataset/bob@x.com/ds/v1/file.csv")
         with patch(
             "pytexera.storage.dataset_file_document.requests.Session.get"
         ) as mock_get:
             mock_get.return_value = make_response(200, body={"presignedUrl": "u"})
             doc.get_presigned_url()
             _, kwargs = mock_get.call_args
-            assert kwargs["params"]["filePath"].startswith("/datasets/")
+            assert kwargs["params"]["filePath"].startswith("/dataset/")
 
     def test_calls_configured_endpoint(self, monkeypatch):
         doc = self._make_doc(monkeypatch)
@@ -235,7 +233,7 @@ def _make_doc(self, monkeypatch):
         monkeypatch.setenv(
             "FILE_SERVICE_GET_DATASET_PRESIGNED_URL_ENDPOINT", CUSTOM_ENDPOINT
         )
-        return DatasetFileDocument("/datasets/bob@x.com/ds/v1/file.csv")
+        return DatasetFileDocument("/dataset/bob@x.com/ds/v1/file.csv")
 
     def test_returns_bytesio_with_downloaded_content(self, monkeypatch):
         doc = self._make_doc(monkeypatch)
@@ -291,7 +289,7 @@ def _make_doc(self, monkeypatch):
         monkeypatch.setenv(
             "FILE_SERVICE_GET_DATASET_PRESIGNED_URL_ENDPOINT", CUSTOM_ENDPOINT
         )
-        return DatasetFileDocument("/datasets/bob@x.com/ds/v1/file.csv")
+        return DatasetFileDocument("/dataset/bob@x.com/ds/v1/file.csv")
 
     def test_presigned_url_request_passes_request_timeout(self, monkeypatch):
         doc = self._make_doc(monkeypatch)

amber/src/test/scala/org/apache/texera/web/resource/dashboard/user/workflow/WorkflowExecutionsResourceSpec.scala

@@ -910,7 +910,7 @@ class WorkflowExecutionsResourceSpec
     val content =
       """{
         |  "operators": [
-        |    {"operatorID": "scanA", "operatorProperties": {"fileName": "/datasets/owner@example.com/LockedDS/v1/data.csv"}},
+        |    {"operatorID": "scanA", "operatorProperties": {"fileName": "/dataset/owner@example.com/LockedDS/v1/data.csv"}},
         |    {"operatorID": "downstreamB", "operatorProperties": {}}
         |  ],
         |  "links": [
@@ -969,7 +969,7 @@ class WorkflowExecutionsResourceSpec
     val content =
       """{
         |  "operators": [
-        |    {"operatorID": "scan", "operatorProperties": {"fileName": "/datasets/test@example.com/MyDS/v1/data.csv"}}
+        |    {"operatorID": "scan", "operatorProperties": {"fileName": "/dataset/test@example.com/MyDS/v1/data.csv"}}
         |  ],
         |  "links": []
         |}""".stripMargin
@@ -1408,7 +1408,7 @@ class WorkflowExecutionsResourceSpec
 
   private def scanOperator(operatorId: String, datasetName: String): String =
     s"""{"operatorID": "$operatorId", "operatorProperties": """ +
-      s"""{"fileName": "/datasets/$foreignOwnerEmail/$datasetName/v1/data.csv"}}"""
+      s"""{"fileName": "/dataset/$foreignOwnerEmail/$datasetName/v1/data.csv"}}"""
 
   // Seeds three datasets owned by somebody other than testUser and wires the workflow as
   //

bin/single-node/examples/workflows/[Example] Data Exploration on Movies Dataset.json

@@ -8,7 +8,7 @@
         "fileEncoding": "UTF_8",
         "customDelimiter": ",",
         "hasHeader": true,
-        "fileName": "/datasets/texera/popular-movies-of-imdb/v1/TMDb_updated.csv",
+        "fileName": "/dataset/texera/popular-movies-of-imdb/v1/TMDb_updated.csv",
         "offset": 0,
         "limit": 1000
       },

bin/single-node/examples/workflows/[Example] Machine Learning on Iris Dataset.json

@@ -8,7 +8,7 @@
         "fileEncoding": "UTF_8",
         "customDelimiter": ",",
         "hasHeader": true,
-        "fileName": "/datasets/texera/iris-species/v1/Iris.csv"
+        "fileName": "/dataset/texera/iris-species/v1/Iris.csv"
       },
       "inputPorts": [],
       "outputPorts": [

common/workflow-core/src/main/scala/org/apache/texera/amber/core/storage/FileResolver.scala

@@ -93,7 +93,7 @@ object FileResolver {
     *     caller can dispatch to the right backing table.
     *   - Legacy unprefixed (datasets only, backward compat): /ownerEmail/datasetName/versionName/
     *     fileRelativePath (>= 4 segments), resolved as a dataset. Models are new and always require
-    *     the /models/ prefix.
+    *     the /model/ prefix.
     *
     * @param fileName the file path to parse
     * @return Some((resourceType, ownerEmail, resourceName, versionName, fileRelativePath)) if valid,
@@ -115,11 +115,11 @@ object FileResolver {
           )
       case None =>
         // Legacy unprefixed dataset path (backward compat): /ownerEmail/datasetName/versionName/<file>.
-        // TODO(datasets-prefix): require the prefix once all stored paths are migrated (36.sql).
+        // TODO(dataset-prefix): require the prefix once all stored paths are migrated (36.sql).
         if (pathSegments.length >= 4)
           Some(
             (
-              ResourceType.Datasets,
+              ResourceType.Dataset,
               pathSegments(0),
               pathSegments(1),
               pathSegments(2),
@@ -139,8 +139,8 @@ object FileResolver {
     *
     * Input:  /<prefix>/ownerEmail/resourceName/versionName/fileRelativePath (or legacy unprefixed)
     * Output: {scheme}:///{repositoryName}/{versionHash}/fileRelativePath
-    *   e.g. /datasets/bob@x.com/twitter/v1/dir/f.csv -> dataset:///dataset-15/adeq233td/dir/f.csv
-    *        /models/bob@x.com/resnet/v1/weights/m.pt -> model:///model-15/adeq233td/weights/m.pt
+    *   e.g. /dataset/bob@x.com/twitter/v1/dir/f.csv -> dataset:///dataset-15/adeq233td/dir/f.csv
+    *        /model/bob@x.com/resnet/v1/weights/m.pt -> model:///model-15/adeq233td/weights/m.pt
     *
     * @throws java.io.FileNotFoundException if the path is not a valid versioned-resource path, the
     *                                       resource/version does not exist, or the URI is malformed
@@ -152,10 +152,10 @@ object FileResolver {
       )
 
     val (scheme, repositoryName, versionHash) = resourceType match {
-      case ResourceType.Datasets =>
+      case ResourceType.Dataset =>
         val (repo, hash) = lookupDataset(ownerEmail, resourceName, versionName, fileName)
         (DATASET_FILE_URI_SCHEME, repo, hash)
-      case ResourceType.Models =>
+      case ResourceType.Model =>
         val (repo, hash) = lookupModel(ownerEmail, resourceName, versionName, fileName)
         (MODEL_FILE_URI_SCHEME, repo, hash)
       case other =>
@@ -306,7 +306,7 @@ object FileResolver {
       return None
     }
     parsePrefixedPath(path).collect {
-      case (ResourceType.Datasets, ownerEmail, datasetName, _, _) => (ownerEmail, datasetName)
+      case (ResourceType.Dataset, ownerEmail, datasetName, _, _) => (ownerEmail, datasetName)
     }
   }
 }

common/workflow-core/src/main/scala/org/apache/texera/amber/core/storage/ResourceType.scala

@@ -26,8 +26,8 @@ package org.apache.texera.amber.core.storage
   * Path shape: /<prefix>/ownerEmail/resourceName/versionName/fileRelativePath
   */
 object ResourceType extends Enumeration {
-  val Datasets: Value = Value("datasets")
-  val Models: Value = Value("models")
+  val Dataset: Value = Value("dataset")
+  val Model: Value = Value("model")
 
   /**
     * Returns the resource type named by the given path segment, or None if it is not a known

common/workflow-core/src/test/scala/org/apache/texera/amber/storage/FileResolverSpec.scala

@@ -122,13 +122,13 @@ class FileResolverSpec
 
   private val localCsvFilePath = "common/workflow-core/src/test/resources/country_sales_small.csv"
 
-  private val datasetACsvFilePath = "/datasets/test_user@test.com/test_dataset/v2/directory/a.csv"
+  private val datasetACsvFilePath = "/dataset/test_user@test.com/test_dataset/v2/directory/a.csv"
 
-  private val dataset1TxtFilePath = "/datasets/test_user@test.com/test_dataset/v1/1.txt"
+  private val dataset1TxtFilePath = "/dataset/test_user@test.com/test_dataset/v1/1.txt"
 
-  private val modelWeightsFilePath = "/models/test_user@test.com/test_model/v2/weights/model.pt"
+  private val modelWeightsFilePath = "/model/test_user@test.com/test_model/v2/weights/model.pt"
 
-  private val modelReadmeFilePath = "/models/test_user@test.com/test_model/v1/README.md"
+  private val modelReadmeFilePath = "/model/test_user@test.com/test_model/v1/README.md"
 
   // Legacy unprefixed form — still resolvable as a dataset (backward compat).
   private val unprefixedDataset1TxtFilePath = "/test_user@test.com/test_dataset/v1/1.txt"
@@ -137,11 +137,11 @@ class FileResolverSpec
   private val unknownResourceTypeFilePath =
     "/notAResourceType/test_user@test.com/test_dataset/v1/1.txt"
 
-  // A model name presented under the datasets prefix must not resolve as a dataset.
-  private val modelNameUnderDatasetPrefix = "/datasets/test_user@test.com/test_model/v1/README.md"
+  // A model name presented under the dataset prefix must not resolve as a dataset.
+  private val modelNameUnderDatasetPrefix = "/dataset/test_user@test.com/test_model/v1/README.md"
 
-  // A dataset name presented under the models prefix must not resolve as a model.
-  private val datasetNameUnderModelPrefix = "/models/test_user@test.com/test_dataset/v1/1.txt"
+  // A dataset name presented under the model prefix must not resolve as a model.
+  private val datasetNameUnderModelPrefix = "/model/test_user@test.com/test_dataset/v1/1.txt"
 
   override protected def beforeAll(): Unit = {
     initializeDBAndReplaceDSLContext()
@@ -225,7 +225,7 @@ class FileResolverSpec
 
   "FileResolver" should "throw not found exception when a prefixed path has too few segments" in {
     assertThrows[FileNotFoundException] {
-      FileResolver.resolve("/datasets/test_user@test.com/test_dataset")
+      FileResolver.resolve("/dataset/test_user@test.com/test_dataset")
     }
   }
 
@@ -254,12 +254,12 @@ class FileResolverSpec
 
   "parseDatasetOwnerAndName" should "extract owner email and dataset name from a valid path" in {
     assert(
-      FileResolver.parseDatasetOwnerAndName("/datasets/test_user@test.com/test_dataset/v1/1.txt")
+      FileResolver.parseDatasetOwnerAndName("/dataset/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("/datasets/owner@x.com/ds/v2/directory/nested/a.csv")
+      FileResolver.parseDatasetOwnerAndName("/dataset/owner@x.com/ds/v2/directory/nested/a.csv")
         == Some(("owner@x.com", "ds"))
     )
   }
@@ -272,7 +272,7 @@ class FileResolverSpec
   }
 
   it should "return None when the prefixed path has too few segments" in {
-    assert(FileResolver.parseDatasetOwnerAndName("/datasets/owner@x.com/ds").isEmpty)
+    assert(FileResolver.parseDatasetOwnerAndName("/dataset/owner@x.com/ds").isEmpty)
     assert(FileResolver.parseDatasetOwnerAndName("owner/dataset").isEmpty)
   }
 

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/source/dataset/FileListerSourceOpExec.scala

@@ -32,7 +32,7 @@ import org.apache.texera.dao.jooq.generated.tables.User.USER
 object FileListerSourceOpExec {
 
   /**
-    * Parses a dataset version path (/datasets/ownerEmail/datasetName/versionName) into its
+    * Parses a dataset version path (/dataset/ownerEmail/datasetName/versionName) into its
     * (resourceTypePrefix, ownerEmail, datasetName, versionName) components.
     *
     * @throws IllegalArgumentException if the path is not a well-formed dataset version path
@@ -42,14 +42,14 @@ object FileListerSourceOpExec {
   ): (String, String, String, String) = {
     val segments = datasetVersionPath.split("/").filter(_.nonEmpty)
     val invalidPath = s"Invalid dataset version path '$datasetVersionPath'; " +
-      "expected /datasets/ownerEmail/datasetName/versionName"
+      "expected /dataset/ownerEmail/datasetName/versionName"
 
     if (segments.headOption.exists(ResourceType.isValidPrefix)) {
       require(segments.length >= 4, invalidPath)
       (segments(0), segments(1), segments(2), segments(3))
     } else {
       require(segments.length >= 3, invalidPath)
-      (ResourceType.Datasets.toString, segments(0), segments(1), segments(2))
+      (ResourceType.Dataset.toString, segments(0), segments(1), segments(2))
     }
   }