Merge branch 'main' into pitch/connect-renkulab-and-openbis-datasets

.github/workflows/acceptance-tests.yml

@@ -31,7 +31,7 @@ jobs:
       extra-values: ${{ steps.deploy-comment.outputs.extra-values}}
     steps:
       - id: deploy-comment
-        uses: SwissDataScienceCenter/renku-actions/[email protected].2
+        uses: SwissDataScienceCenter/renku-actions/[email protected].3
         with:
           string: /deploy
           pr_ref: ${{ github.event.number }}
@@ -46,22 +46,22 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Find deplyoment url
-        uses: peter-evans/find-comment@v1
+        uses: peter-evans/find-comment@v3
         id: deploymentUrlMessage
         with:
           issue-number: ${{ github.event.pull_request.number }}
           comment-author: "RenkuBot"
           body-includes: "You can access the deployment of this PR at"
       - name: Create comment deployment url
         if: steps.deploymentUrlMessage.outputs.comment-id == 0
-        uses: peter-evans/create-or-update-comment@v1
+        uses: peter-evans/create-or-update-comment@v4
         with:
           token: ${{ secrets.RENKUBOT_GITHUB_TOKEN }}
           issue-number: ${{ github.event.pull_request.number }}
           body: |
             You can access the deployment of this PR at https://renku-ci-ds-${{ github.event.number }}.dev.renku.ch
       - name: Build and deploy
-        uses: SwissDataScienceCenter/renku-actions/[email protected].2
+        uses: SwissDataScienceCenter/renku-actions/[email protected].3
         env:
           RANCHER_PROJECT_ID: ${{ secrets.CI_RANCHER_PROJECT }}
           DOCKER_PASSWORD: ${{ secrets.RENKU_DOCKER_PASSWORD }}
@@ -91,7 +91,7 @@ jobs:
     if: github.event.action != 'closed' && needs.check-deploy.outputs.pr-contains-string == 'true' && needs.check-deploy.outputs.test-enabled == 'true'
     runs-on: ubuntu-22.04
     steps:
-      - uses: SwissDataScienceCenter/renku-actions/[email protected].2
+      - uses: SwissDataScienceCenter/renku-actions/[email protected].3
         with:
           kubeconfig: ${{ secrets.RENKUBOT_DEV_KUBECONFIG }}
           renku-release: renku-ci-ds-${{ github.event.number }}
@@ -118,7 +118,7 @@ jobs:
     steps:
       - name: Extract Renku repository reference
         run: echo "RENKU_REFERENCE=`echo '${{ needs.check-deploy.outputs.renku }}' | cut -d'@' -f2`" >> $GITHUB_ENV
-      - uses: SwissDataScienceCenter/renku-actions/[email protected].2
+      - uses: SwissDataScienceCenter/renku-actions/[email protected].3
         with:
           e2e-target: ${{ matrix.tests }}
           renku-reference: ${{ env.RENKU_REFERENCE }}
@@ -131,22 +131,22 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Find deplyoment url
-        uses: peter-evans/find-comment@v1
+        uses: peter-evans/find-comment@v3
         id: deploymentUrlMessage
         with:
           issue-number: ${{ github.event.pull_request.number }}
           comment-author: "RenkuBot"
           body-includes: "Tearing down the temporary RenkuLab deplyoment"
       - name: Create comment deployment url
         if: steps.deploymentUrlMessage.outputs.comment-id == 0
-        uses: peter-evans/create-or-update-comment@v1
+        uses: peter-evans/create-or-update-comment@v4
         with:
           token: ${{ secrets.RENKUBOT_GITHUB_TOKEN }}
           issue-number: ${{ github.event.pull_request.number }}
           body: |
             Tearing down the temporary RenkuLab deplyoment for this PR.
       - name: renku teardown
-        uses: SwissDataScienceCenter/renku-actions/[email protected].2
+        uses: SwissDataScienceCenter/renku-actions/[email protected].3
         env:
           HELM_RELEASE_REGEX: "^renku-ci-ds-${{ github.event.number }}$"
           GITLAB_TOKEN: ${{ secrets.DEV_GITLAB_TOKEN }}

.github/workflows/test_publish.yml

@@ -206,7 +206,7 @@ jobs:
         uses: actions/checkout@v4
       - name: Docker meta data services
         id: meta
-        uses: docker/metadata-action@v4
+        uses: docker/metadata-action@v5
         with:
           # list of Docker images to use as base name for tags
           images: |
@@ -240,7 +240,7 @@ jobs:
           cache-to: type=registry,ref=renku/renku-data-service:buildcache,mode=max
       - name: Docker meta background jobs
         id: meta-background-jobs
-        uses: docker/metadata-action@v4
+        uses: docker/metadata-action@v5
         with:
           # list of Docker images to use as base name for tags
           images: |
@@ -265,7 +265,7 @@ jobs:
           cache-to: type=registry,ref=renku/data-service-background-jobs:buildcache,mode=max
       - name: Docker meta secrets
         id: meta-secrets-storage
-        uses: docker/metadata-action@v4
+        uses: docker/metadata-action@v5
         with:
           # list of Docker images to use as base name for tags
           images: |

components/renku_data_services/app_config/config.py

@@ -63,7 +63,7 @@
 from renku_data_services.users.db import UserRepo as KcUserRepo
 from renku_data_services.users.dummy_kc_api import DummyKeycloakAPI
 from renku_data_services.users.kc_api import IKeycloakAPI, KeycloakAPI
-from renku_data_services.users.models import UserInfo
+from renku_data_services.users.models import UnsavedUserInfo
 from renku_data_services.utils.core import merge_api_specs, oidc_discovery
 
 default_resource_pool = models.ResourcePool(
@@ -436,8 +436,8 @@ def from_env(cls, prefix: str = "") -> "Config":
             user_store = DummyUserStore(user_always_exists=user_always_exists)
             gitlab_client = DummyGitlabAPI()
             dummy_users = [
-                UserInfo("user1", "user1", "doe", "[email protected]"),
-                UserInfo("user2", "user2", "doe", "[email protected]"),
+                UnsavedUserInfo(id="user1", first_name="user1", last_name="doe", email="[email protected]"),
+                UnsavedUserInfo(id="user2", first_name="user2", last_name="doe", email="[email protected]"),
             ]
             kc_api = DummyKeycloakAPI(users=[i._to_keycloak_dict() for i in dummy_users])
             redis = RedisConfig.fake()

components/renku_data_services/authz/authz.py

@@ -35,7 +35,7 @@
 from renku_data_services.errors import errors
 from renku_data_services.namespace.models import Group, GroupUpdate, Namespace, NamespaceKind, NamespaceUpdate
 from renku_data_services.project.models import Project, ProjectUpdate
-from renku_data_services.users.models import UserWithNamespace, UserWithNamespaceUpdate
+from renku_data_services.users.models import UserInfo, UserInfoUpdate
 
 _P = ParamSpec("_P")
 
@@ -51,7 +51,7 @@ def authz(self) -> "Authz":
 
 _AuthzChangeFuncResult = TypeVar(
     "_AuthzChangeFuncResult",
-    bound=Project | ProjectUpdate | Group | UserWithNamespaceUpdate | list[UserWithNamespace] | None,
+    bound=Project | ProjectUpdate | Group | UserInfoUpdate | list[UserInfo] | None,
 )
 _T = TypeVar("_T")
 _WithAuthz = TypeVar("_WithAuthz", bound=WithAuthz)
@@ -493,14 +493,14 @@ async def _get_authz_change(
                 case AuthzOperation.delete, ResourceType.group if result is None:
                     # NOTE: This means that the group does not exist in the first place so nothing was deleted
                     pass
-                case AuthzOperation.update_or_insert, ResourceType.user if isinstance(result, UserWithNamespaceUpdate):
+                case AuthzOperation.update_or_insert, ResourceType.user if isinstance(result, UserInfoUpdate):
                     if result.old is None:
                         authz_change = db_repo.authz._add_user_namespace(result.new.namespace)
                 case AuthzOperation.insert_many, ResourceType.user_namespace if isinstance(result, list):
                     for res in result:
-                        if not isinstance(res, UserWithNamespace):
+                        if not isinstance(res, UserInfo):
                             raise errors.ProgrammingError(
-                                message="Expected list of UserWithNamespace when generating authorization "
+                                message="Expected list of UserInfo when generating authorization "
                                 f"database updates for inserting namespaces but found {type(res)}"
                             )
                         authz_change.extend(db_repo.authz._add_user_namespace(res.namespace))

components/renku_data_services/base_models/core.py

@@ -4,7 +4,7 @@
 import unicodedata
 from dataclasses import dataclass, field
 from enum import Enum, StrEnum
-from typing import ClassVar, Optional, Protocol
+from typing import ClassVar, Optional, Protocol, Self
 
 from sanic import Request
 
@@ -122,7 +122,7 @@ def __init__(self, value: str) -> None:
         object.__setattr__(self, "value", value.lower())
 
     @classmethod
-    def from_name(cls, name: str) -> "Slug":
+    def from_name(cls, name: str) -> Self:
         """Takes a name with any amount of invalid characters and transforms it in a valid slug."""
         lower_case = name.lower()
         no_space = re.sub(r"\s+", "-", lower_case)
@@ -139,6 +139,24 @@ def from_name(cls, name: str) -> "Slug":
             )
         return cls(no_dot_git_or_dot_atom_at_end)
 
+    @classmethod
+    def from_user(cls, email: str | None, first_name: str | None, last_name: str | None, keycloak_id: str) -> Self:
+        """Create a slug from a user."""
+        if email:
+            slug = email.split("@")[0]
+        elif first_name and last_name:
+            slug = first_name + "-" + last_name
+        elif last_name:
+            slug = last_name
+        elif first_name:
+            slug = first_name
+        else:
+            slug = "user_" + keycloak_id
+        # The length limit is 99 but leave some space for modifications that may be added down the line
+        # to filter out invalid characters or to generate a unique name
+        slug = slug[:80]
+        return cls.from_name(slug)
+
     def __true_div__(self, other: "Slug") -> str:
         """Joins two slugs into a path fraction without dashes at the beginning or end."""
         if type(self) is not type(other):

components/renku_data_services/crc/blueprints.py

@@ -16,7 +16,7 @@
 from renku_data_services.crc.db import ResourcePoolRepository, UserRepository
 from renku_data_services.k8s.quota import QuotaRepository
 from renku_data_services.users.db import UserRepo as KcUserRepo
-from renku_data_services.users.models import UserWithNamespace
+from renku_data_services.users.models import UserInfo
 
 
 @dataclass(kw_only=True)
@@ -183,10 +183,10 @@ async def _put_post(
         self, api_user: base_models.APIUser, resource_pool_id: int, body: apispec.PoolUsersWithId, post: bool = True
     ) -> HTTPResponse:
         user_ids_to_add = set([user.id for user in body.root])
-        users_checks: list[UserWithNamespace | None] = await asyncio.gather(
+        users_checks: list[UserInfo | None] = await asyncio.gather(
             *[self.kc_user_repo.get_user(id=id) for id in user_ids_to_add]
         )
-        existing_user_ids = set([user.user.id for user in users_checks if user is not None])
+        existing_user_ids = set([user.id for user in users_checks if user is not None])
         if existing_user_ids != user_ids_to_add:
             missing_ids = user_ids_to_add.difference(existing_user_ids)
             raise errors.MissingResourceError(message=f"The users with IDs {missing_ids} cannot be found")

components/renku_data_services/message_queue/converters.py

@@ -94,38 +94,38 @@ def to_events(
 class _UserEventConverter:
     @staticmethod
     def to_events(
-        user: user_models.UserInfo | user_models.UserWithNamespace | user_models.UserWithNamespaceUpdate,
+        user: user_models.UserInfo | user_models.UserInfoUpdate | str,
         event_type: type[AvroModel] | type[events.AmbiguousEvent],
     ) -> list[Event]:
         match event_type:
             case v2.UserAdded | events.InsertUserNamespace:
-                user = cast(user_models.UserWithNamespace, user)
+                user = cast(user_models.UserInfo, user)
                 return [
                     _make_event(
                         "user.added",
                         v2.UserAdded(
-                            id=user.user.id,
-                            firstName=user.user.first_name,
-                            lastName=user.user.last_name,
-                            email=user.user.email,
+                            id=user.id,
+                            firstName=user.first_name,
+                            lastName=user.last_name,
+                            email=user.email,
                             namespace=user.namespace.slug,
                         ),
                     )
                 ]
             case v2.UserRemoved:
-                user = cast(user_models.UserInfo, user)
-                return [_make_event("user.removed", v2.UserRemoved(id=user.id))]
+                user_id = cast(str, user)
+                return [_make_event("user.removed", v2.UserRemoved(id=user_id))]
             case events.UpdateOrInsertUser:
-                user = cast(user_models.UserWithNamespaceUpdate, user)
+                user = cast(user_models.UserInfoUpdate, user)
                 if user.old is None:
                     return [
                         _make_event(
                             "user.added",
                             v2.UserAdded(
-                                id=user.new.user.id,
-                                firstName=user.new.user.first_name,
-                                lastName=user.new.user.last_name,
-                                email=user.new.user.email,
+                                id=user.new.id,
+                                firstName=user.new.first_name,
+                                lastName=user.new.last_name,
+                                email=user.new.email,
                                 namespace=user.new.namespace.slug,
                             ),
                         )
@@ -135,10 +135,10 @@ def to_events(
                         _make_event(
                             "user.updated",
                             v2.UserUpdated(
-                                id=user.new.user.id,
-                                firstName=user.new.user.first_name,
-                                lastName=user.new.user.last_name,
-                                email=user.new.user.email,
+                                id=user.new.id,
+                                firstName=user.new.first_name,
+                                lastName=user.new.last_name,
+                                email=user.new.email,
                                 namespace=user.new.namespace.slug,
                             ),
                         )
@@ -328,16 +328,16 @@ def to_events(input: _T, event_type: type[AvroModel] | type[events.AmbiguousEven
                 group_authz = cast(list[authz_models.MembershipChange], input)
                 return _GroupAuthzEventConverter.to_events(group_authz)
             case v2.UserAdded:
-                user_with_namespace = cast(user_models.UserWithNamespace, input)
+                user_with_namespace = cast(user_models.UserInfo, input)
                 return _UserEventConverter.to_events(user_with_namespace, event_type)
             case v2.UserRemoved:
-                user_info = cast(user_models.UserInfo, input)
+                user_info = cast(str, input)
                 return _UserEventConverter.to_events(user_info, event_type)
             case events.UpdateOrInsertUser:
-                user_with_namespace_update = cast(user_models.UserWithNamespaceUpdate, input)
+                user_with_namespace_update = cast(user_models.UserInfoUpdate, input)
                 return _UserEventConverter.to_events(user_with_namespace_update, event_type)
             case events.InsertUserNamespace:
-                user_namespaces = cast(list[user_models.UserWithNamespace], input)
+                user_namespaces = cast(list[user_models.UserInfo], input)
                 output: list[Event] = []
                 for namespace in user_namespaces:
                     output.extend(_UserEventConverter.to_events(namespace, event_type))