feat: searching data connector by their DOI (#1182)

* feat: allow using doi to create/get data connector links to projects

* address review comments

* address review comments

Author: mohammad-alisafaee

components/renku_data_services/data_connectors/api.spec.yaml

@@ -96,6 +96,33 @@ paths:
           $ref: "#/components/responses/Error"
       tags:
         - data_connectors
+  /data_connectors/search:
+    get:
+      summary: Get data connector details by DOI
+      parameters:
+        - in: query
+          name: doi
+          required: true
+          schema:
+            $ref: "#/components/schemas/DOI"
+          description: The DOI of the data connector
+      responses:
+        "200":
+          description: The data connector
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/DataConnector"
+        "404":
+          description: The data connector with the given DOI does not exist or user does not have access to it
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        default:
+          $ref: "#/components/responses/Error"
+      tags:
+        - data_connectors
   /data_connectors/{data_connector_id}:
     parameters:
       - in: path
@@ -286,7 +313,7 @@ paths:
         required: true
         schema:
           $ref: "#/components/schemas/Ulid"
-        description: the ID of the data connector
+        description: the ID of the data connector that can be ULID or DOI
     get:
       summary: Get all links from a given data connector to projects
       parameters:
@@ -668,6 +695,10 @@ components:
       type: array
       items:
         $ref: "#/components/schemas/DataConnectorToProjectLink"
+    ProjectPath:
+      description: The path to the project page
+      type: string
+      example: "namespace/project-slug"
     DataConnectorToProjectLink:
       description: A link from a data connector to a project in Renku 2.0
       type: object
@@ -679,6 +710,8 @@ components:
           $ref: "#/components/schemas/Ulid"
         project_id:
           $ref: "#/components/schemas/Ulid"
+        project_path:
+          $ref: "#/components/schemas/ProjectPath"
         creation_date:
           $ref: "#/components/schemas/CreationDate"
         created_by:
@@ -687,6 +720,7 @@ components:
         - id
         - data_connector_id
         - project_id
+        - project_path
         - creation_date
         - created_by
     DataConnectorToProjectLinkPost:
@@ -990,7 +1024,6 @@ components:
           type: integer
           minimum: 0
           description: The number of data links the user does not have access to
-
   responses:
     Error:
       description: The schema for all 4xx and 5xx responses

components/renku_data_services/data_connectors/apispec.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  api.spec.yaml
-#   timestamp: 2025-12-03T09:49:11+00:00
+#   timestamp: 2026-01-27T08:42:00+00:00
 
 from __future__ import annotations
 
@@ -129,6 +129,14 @@ class InaccessibleDataConnectorLinks(BaseAPISpec):
     )
 
 
+class DataConnectorsSearchGetParametersQuery(BaseAPISpec):
+    doi: str = Field(..., description="A DOI.", examples=["10.16904/envidat.33"])
+
+
+class DataConnectorsDataConnectorIdProjectLinksGetParametersQuery(BaseAPISpec):
+    params: Optional[PaginationRequest] = None
+
+
 class CloudStorageCore(BaseAPISpec):
     model_config = ConfigDict(
         extra="forbid",
@@ -241,6 +249,11 @@ class DataConnectorToProjectLink(BaseAPISpec):
         min_length=26,
         pattern="^[0-7][0-9A-HJKMNP-TV-Z]{25}$",
     )
+    project_path: str = Field(
+        ...,
+        description="The path to the project page",
+        examples=["namespace/project-slug"],
+    )
     creation_date: datetime = Field(
         ...,
         description="The date and time the resource was created (in UTC and ISO-8601 format)",

components/renku_data_services/data_connectors/blueprints.py

@@ -308,6 +308,25 @@ async def _get_permissions(_: Request, user: base_models.APIUser, data_connector
 
         return "/data_connectors/<data_connector_id:ulid>/permissions", ["GET"], _get_permissions
 
+    def get_one_by_doi(self) -> BlueprintFactoryResponse:
+        """Get data connector by DOI."""
+
+        @authenticate(self.authenticator)
+        @validate(query=apispec.DataConnectorsSearchGetParametersQuery)
+        async def _get_one_by_doi(
+            _: Request,
+            user: base_models.APIUser,
+            query: apispec.DataConnectorsSearchGetParametersQuery,
+            validator: RCloneValidator,
+        ) -> JSONResponse:
+            data_connector = await self.data_connector_repo.get_data_connector_by_doi(user=user, doi=query.doi)
+            return validated_json(
+                apispec.DataConnector,
+                self._dump_data_connector(data_connector, validator=validator),
+            )
+
+        return "/data_connectors/search", ["GET"], _get_one_by_doi
+
     def get_all_project_links(self) -> BlueprintFactoryResponse:
         """List all links from a given data connector to projects."""
 
@@ -533,6 +552,7 @@ def _dump_data_connector_to_project_link(link: models.DataConnectorToProjectLink
             id=str(link.id),
             data_connector_id=str(link.data_connector_id),
             project_id=str(link.project_id),
+            project_path=link.project_path,
             creation_date=link.creation_date,
             created_by=link.created_by,
         )

components/renku_data_services/data_connectors/db.py

@@ -195,6 +195,33 @@ async def get_data_connector_by_slug(
 
             return data_connector.dump()
 
+    async def get_data_connector_by_doi(
+        self,
+        user: base_models.APIUser,
+        doi: str,
+    ) -> models.DataConnector | models.GlobalDataConnector:
+        """Get a data connector from the database by DOI."""
+        not_found_msg = f"Data connector with DOI '{doi}' does not exist or you do not have access to it."
+
+        async with self.session_maker() as session:
+            stmt = select(schemas.DataConnectorORM).where(schemas.DataConnectorORM.doi == doi)
+            result = await session.scalars(stmt)
+            data_connector = result.one_or_none()
+
+            if data_connector is None:
+                raise errors.MissingResourceError(message=not_found_msg)
+
+            authorized = await self.authz.has_permission(
+                user=user,
+                resource_type=ResourceType.data_connector,
+                resource_id=data_connector.id,
+                scope=Scope.READ,
+            )
+            if not authorized:
+                raise errors.MissingResourceError(message=not_found_msg)
+
+            return data_connector.dump()
+
     async def get_global_data_connector_by_slug(
         self,
         user: base_models.APIUser,

components/renku_data_services/data_connectors/models.py

@@ -174,6 +174,7 @@ class DataConnectorToProjectLink(UnsavedDataConnectorToProjectLink):
     """A link from a data connector to a project."""
 
     id: ULID
+    project_path: str
     created_by: str
     creation_date: datetime
     updated_at: datetime

components/renku_data_services/data_connectors/orm.py

@@ -193,12 +193,18 @@ class DataConnectorToProjectLinkORM(BaseORM):
         nullable=False,
     )
 
+    project: Mapped["ProjectORM"] = relationship(init=False, repr=False, viewonly=True, lazy="joined")
+    """The project this link points to."""
+
     def dump(self) -> models.DataConnectorToProjectLink:
         """Create a link model from the DataConnectorProjectLinkORM."""
+        project_path = f"{self.project.slug.namespace.slug}/{self.project.slug.slug}"
+
         return models.DataConnectorToProjectLink(
             id=self.id,
             data_connector_id=self.data_connector_id,
             project_id=self.project_id,
+            project_path=project_path,
             created_by=self.created_by_id,
             creation_date=self.creation_date,
             updated_at=self.updated_at,

components/renku_data_services/project/api.spec.yaml

@@ -992,32 +992,6 @@ components:
       type: string
       description: Entity Tag
       example: "9EE498F9D565D0C41E511377425F32F3"
-    DataConnectorToProjectLinksList:
-      description: A list of links from a data connector to a project
-      type: array
-      items:
-        $ref: "#/components/schemas/DataConnectorToProjectLink"
-    DataConnectorToProjectLink:
-      description: A link from a data connector to a project in Renku 2.0
-      type: object
-      additionalProperties: false
-      properties:
-        id:
-          $ref: "#/components/schemas/Ulid"
-        data_connector_id:
-          $ref: "#/components/schemas/Ulid"
-        project_id:
-          $ref: "#/components/schemas/Ulid"
-        creation_date:
-          $ref: "#/components/schemas/CreationDate"
-        created_by:
-          $ref: "#/components/schemas/UserId"
-      required:
-        - id
-        - data_connector_id
-        - project_id
-        - creation_date
-        - created_by
     ProjectGetQuery:
       description: Query params for project get request
       allOf:

components/renku_data_services/project/apispec.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  api.spec.yaml
-#   timestamp: 2025-05-06T08:33:41+00:00
+#   timestamp: 2026-01-23T15:08:41+00:00
 
 from __future__ import annotations
 
@@ -27,44 +27,6 @@ class Role(Enum):
     owner = "owner"
 
 
-class DataConnectorToProjectLink(BaseAPISpec):
-    model_config = ConfigDict(
-        extra="forbid",
-    )
-    id: str = Field(
-        ...,
-        description="ULID identifier",
-        max_length=26,
-        min_length=26,
-        pattern="^[0-7][0-9A-HJKMNP-TV-Z]{25}$",
-    )
-    data_connector_id: str = Field(
-        ...,
-        description="ULID identifier",
-        max_length=26,
-        min_length=26,
-        pattern="^[0-7][0-9A-HJKMNP-TV-Z]{25}$",
-    )
-    project_id: str = Field(
-        ...,
-        description="ULID identifier",
-        max_length=26,
-        min_length=26,
-        pattern="^[0-7][0-9A-HJKMNP-TV-Z]{25}$",
-    )
-    creation_date: datetime = Field(
-        ...,
-        description="The date and time the resource was created (in UTC and ISO-8601 format)",
-        examples=["2023-11-01T17:32:28Z"],
-    )
-    created_by: str = Field(
-        ...,
-        description="Keycloak user ID",
-        examples=["f74a228b-1790-4276-af5f-25c2424e9b0c"],
-        pattern="^[A-Za-z0-9]{1}[A-Za-z0-9-]+$",
-    )
-
-
 class ProjectMigrationInfo(BaseAPISpec):
     project_id: str = Field(
         ...,
@@ -138,22 +100,22 @@ class ErrorResponse(BaseAPISpec):
     error: Error
 
 
-class NamespacesNamespaceProjectsSlugGetParametersQuery(BaseAPISpec):
+class ProjectsProjectIdGetParametersQuery(BaseAPISpec):
     with_documentation: Optional[bool] = Field(
         None, description="Projects with or without possibly extensive documentation?"
     )
 
 
-class ProjectsProjectIdCopiesGetParametersQuery(BaseAPISpec):
-    writable: bool = False
-
-
-class ProjectsProjectIdGetParametersQuery(BaseAPISpec):
+class NamespacesNamespaceProjectsSlugGetParametersQuery(BaseAPISpec):
     with_documentation: Optional[bool] = Field(
         None, description="Projects with or without possibly extensive documentation?"
     )
 
 
+class ProjectsProjectIdCopiesGetParametersQuery(BaseAPISpec):
+    writable: bool = False
+
+
 class MigrationSessionLauncherPost(BaseAPISpec):
     model_config = ConfigDict(
         extra="forbid",
@@ -235,12 +197,6 @@ class ProjectMemberResponse(BaseAPISpec):
     role: Role
 
 
-class DataConnectorToProjectLinksList(RootModel[List[DataConnectorToProjectLink]]):
-    root: List[DataConnectorToProjectLink] = Field(
-        ..., description="A list of links from a data connector to a project"
-    )
-
-
 class ProjectGetQuery(PaginationRequest):
     namespace: str = Field("", description="A namespace, used as a filter.")
     direct_member: bool = Field(
@@ -386,11 +342,6 @@ class ProjectsGetParametersQuery(BaseAPISpec):
     params: Optional[ProjectGetQuery] = None
 
 
-class RenkuV1ProjectsMigrationsGetParametersQuery(BaseAPISpec):
-    """This class no longer includes any parameters."""
-    pass
-
-
 class Project(BaseAPISpec):
     id: str = Field(
         ...,

pyproject.toml

@@ -274,6 +274,10 @@ module = [
 ]
 ignore_missing_imports = true
 
+[[tool.mypy.overrides]]
+module = ["test.*"]
+disable_error_code = ["no-untyped-def"]
+
 [tool.coverage.run]
 source = ["bases/", "components/"]
 omit = ["components/renku_data_services/notebooks"]