Update template and remove cmempy usage

.copier-answers.yml

@@ -1,5 +1,5 @@
 # Changes here will be overwritten by Copier
-_commit: v7.3.0-24-g169e035
+_commit: v8.5.0-4-gd5f8597
 _src_path: gh:eccenca/cmem-plugin-template
 author_mail: cmempy-developer@eccenca.com
 author_name: eccenca GmbH

.github/workflows/check.yml

@@ -22,6 +22,13 @@ jobs:
       - name: Check out repository
         uses: actions/checkout@v5
 
+      - name: Cache Trivy DB
+        id: cache-trivydb
+        uses: actions/cache@v4
+        with:
+          path: .trivycache
+          key: ${{ runner.os }}-trivydb
+
       - name: Install Task
         uses: arduino/setup-task@v2
 
@@ -38,10 +45,6 @@ jobs:
           virtualenvs-in-project: true
           installer-parallel: true
 
-      - name: Install dynamic versioning plugin
-        run: |
-          poetry self add "poetry-dynamic-versioning[plugin]"
-
       - name: mypy
         run: |
           task check:mypy
@@ -61,9 +64,13 @@ jobs:
         run: |
           task check:deptry
 
-      - name: safety
+      - name: trivy
+        env:
+          TRIVY_NO_PROGRESS: "true"
+          TRIVY_CACHE_DIR: ".trivycache/"
+          TRIVY_DISABLE_VEX_NOTICE: "true"
         run: |
-          task check:safety
+          task check:trivy
 
       - name: Publish Test Report in Action
         uses: mikepenz/action-junit-report@v4

.github/workflows/publish.yml

@@ -35,10 +35,6 @@ jobs:
           virtualenvs-in-project: true
           installer-parallel: true
 
-      - name: Install dynamic versioning plugin
-        run: |
-          poetry self add "poetry-dynamic-versioning[plugin]"
-
       - name: Publish Package
         env:
           PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}

.gitignore

@@ -138,6 +138,9 @@ dmypy.json
 # Cython debug symbols
 cython_debug/
 
+# Claude code specifics
+.claude/settings.local.json
+
 # project build plan specific ignores
 version.py
 co

.gitlab-ci.yml

@@ -1,6 +1,6 @@
 ---
 default:
-  image: docker-registry.eccenca.com/eccenca-python:v3.13.8
+  image: docker-registry.eccenca.com/eccenca-python:v3.13.13
   # all jobs can be interrupted in case a new commit is pushed
   interruptible: true
   before_script:
@@ -60,17 +60,24 @@ deptry:
   script:
     - task check:deptry
 
-safety:
+trivy:
   stage: test
+  variables:
+    TRIVY_NO_PROGRESS: "true"
+    TRIVY_CACHE_DIR: ".trivycache/"
+    TRIVY_DISABLE_VEX_NOTICE: "true"
   script:
-    - task check:safety
+    - task check:trivy
+  cache:
+    paths:
+      - .trivycache/
 
 build:
   stage: build
   needs:
     - mypy
     - pytest
-    - safety
+    - trivy
     - deptry
   script:
     - task build

.pre-commit-config.yaml

@@ -1,4 +1,7 @@
 ---
+default_language_version:
+  python: python3.13
+
 repos:
   - repo: local
     hooks:
@@ -36,3 +39,9 @@ repos:
         stages: [post-checkout, post-merge]
         always_run: true
 
+      - id: trivy
+        name: check:trivy
+        description: run trivy to scan for vulnerabilities
+        entry: task check:trivy
+        language: python
+        pass_filenames: false

.trivyignore

@@ -0,0 +1,4 @@
+# .trivyignore
+
+# ignore 51358 safety - dev dependency only
+CVE-2022-39280

Taskfile.yaml

@@ -44,36 +44,9 @@ tasks:
     cmds:
       - mkdir -p {{.DIST_DIR}}/coverage
 
-  poetry:check:
-    internal: true
-    platforms: [darwin, linux]
-    summary: |
-      Check poetry versioning plugin. Currently not under Windows
-    run: once
-    preconditions:
-      - sh: '[ -d .git ]'
-        msg: >
-          Your newly created project directory needs to be initialized
-          as a git repository.
-      - sh: '[[ {{.PDV_VERSION}} > {{.PDV_VERSION_MIN}} ]]'
-        msg: >
-          This project needs the poetry-dynamic-versioning
-          plugin > v{{.PDV_VERSION_MIN}}.
-
-          You can install it with the following command:
-          poetry self add "poetry-dynamic-versioning[plugin]"
-    vars:
-      PDV_VERSION_MIN: 0.20
-      PDV_VERSION:
-        sh: >
-            poetry self show --addons poetry-dynamic-versioning --tree
-            | head -1 | cut -d " " -f 2 | cut -d "." -f 1-2
-
   poetry:install:
     desc: Install dependencies managed by Poetry
     run: once
-    deps:
-      - poetry:check
     cmds:
       - poetry install
 
@@ -112,7 +85,7 @@ tasks:
       - task: check:ruff
       - task: check:mypy
       - task: check:deptry
-      - task: check:safety
+      - task: check:trivy
 
   check:pytest:
     desc: Run unit and integration tests
@@ -154,12 +127,17 @@ tasks:
     vars:
       JUNIT_FILE: ./{{.DIST_DIR}}/junit-mypy.xml
 
-  check:safety:
-    desc: Complain about vulnerabilities in dependencies
+  check:trivy:
+    desc: Scan for vulnerabilities using Trivy
     <<: *preparation
     cmds:
-      # ignore 51358 safety - dev dependency only
-      - poetry run safety check -i 51358
+      - >
+        poetry run trivy fs
+        --include-dev-deps
+        --scanners vuln
+        --skip-files .poetry/plugins/poetry.lock
+        --exit-code 1
+        .
 
   check:deptry:
     desc: Complain about unused or missing dependencies
@@ -185,7 +163,7 @@ tasks:
     <<: *preparation
     deps:
       - clean
-      - poetry:check
     cmds:
       - poetry build
+      - poetry export --without=dev -f requirements.txt >dist/requirements.txt
 

cmem_plugin_validation/validate_entities/task.py

@@ -7,12 +7,10 @@
 from types import SimpleNamespace
 from typing import Any
 
-from cmem.cmempy.workspace.projects.resources.resource import get_resource_response
-from cmem.cmempy.workspace.tasks import get_task
+from cmem_client.client import Client
 from cmem_plugin_base.dataintegration.context import (
     ExecutionContext,
     ExecutionReport,
-    UserContext,
 )
 from cmem_plugin_base.dataintegration.description import Icon, Plugin, PluginParameter
 from cmem_plugin_base.dataintegration.entity import Entities
@@ -24,11 +22,6 @@
     FlexibleNumberOfInputs,
     UnknownSchemaPort,
 )
-from cmem_plugin_base.dataintegration.utils import (
-    setup_cmempy_user_access,
-    split_task_id,
-    write_to_dataset,
-)
 from cmem_plugin_base.dataintegration.utils.entity_builder import build_entities_from_data
 from jsonschema import validate
 from jsonschema.exceptions import ValidationError
@@ -77,13 +70,6 @@
 
 DEFAULT_FAIL_ON_VIOLATION = False
 
-
-def get_task_metadata(project: str, task: str, context: UserContext) -> dict:
-    """Get metadata information of a task"""
-    setup_cmempy_user_access(context=context)
-    return dict(get_task(project=project, task=task))
-
-
 SOURCE = SimpleNamespace()
 SOURCE.entities = "entities"
 SOURCE.dataset = "dataset"
@@ -172,7 +158,7 @@ class ValidateEntity(WorkflowPlugin):
     inputs: Sequence[Entities]
     execution_context: ExecutionContext
 
-    def __init__(  #  noqa: PLR0913
+    def __init__(  #  noqa: PLR0913 PLR0917
         self,
         source_mode: str,
         target_mode: str,
@@ -297,10 +283,10 @@ def execute(
             )
         )
         if self.target_mode == TARGET.dataset:
-            write_to_dataset(
-                dataset_id=f"{context.task.project_id()}:{self.target_dataset}",
-                file_resource=io.StringIO(json.dumps(valid_json_objects)),
-                context=context.user,
+            Client.from_context(context=context).datasets.post_file_resource(
+                project_id=context.task.project_id(),
+                dataset_id=self.target_dataset,
+                file_resource=io.BytesIO(json.dumps(valid_json_objects).encode("utf-8")),
             )
             return None
 
@@ -319,16 +305,18 @@ def _validate_json(self, json: dict, schema: dict) -> bool:
     @staticmethod
     def _get_json_dataset_content(context: ExecutionContext, dataset: str) -> dict | list[dict]:
         """Get json dataset content"""
-        dataset_id = f"{context.task.project_id()}:{dataset}"
-        project_id, task_id = split_task_id(dataset_id)
-        task_meta_data = get_task_metadata(project_id, task_id, context.user)
-        resource_name = str(task_meta_data["data"]["parameters"]["file"]["value"])
-        response = get_resource_response(project_id, resource_name)
-        return response.json()  # type: ignore[no-any-return]
+        client = Client.from_context(context=context)
+        project_id = context.task.project_id()
+        resource_name = str(
+            client.datasets.get_item(project_id=project_id, dataset_id=dataset).data.parameters[
+                "file"
+            ]
+        )
+        return json.loads(client.files.read(f"{project_id}:{resource_name}"))  # type: ignore[no-any-return]
 
     def _convert_entities_to_json(
         self, inputs: Sequence[Entities], path_to_entities: dict[str, Entities], path: str = ""
-    ) -> Generator[dict[str, Any], None, None]:
+    ) -> Generator[dict[str, Any]]:
         """Convert a sequence of Entities into JSON-like dictionaries using recursive traversal."""
         for entities in inputs:
             # Initialize path-to-entities map for the root level

cmem_plugin_validation/validate_graph/state.py

@@ -1,11 +1,12 @@
 """Graph validation process state"""
 
-from cmem.cmempy.dp.shacl import validation
+from cmem_client.client import Client
 
 
 class State:
     """State of a validation process"""
 
+    client: Client
     id_: str
     data: dict
     status: str
@@ -14,15 +15,17 @@ class State:
     with_violations: int
     violations: int
 
-    def __init__(self, id_: str):
+    def __init__(self, client: Client, id_: str):
+        self.client = client
         self.id_ = id_
         self.refresh()
 
     def refresh(self) -> None:
         """Refresh state of validation process"""
-        self.data = validation.get_aggregation(batch_id=self.id_)
-        self.status = self.data.get("state", "UNKNOWN")
-        self.completed = self.data.get("resourceProcessedCount", 0)
-        self.total = self.data.get("resourceCount", 0)
-        self.with_violations = self.data.get("resourcesWithViolationsCount", 0)
-        self.violations = self.data.get("violationsCount", 0)
+        aggregation = self.client.validations.get_aggregation(batch_id=self.id_)
+        self.data = aggregation.model_dump(by_alias=True, exclude_none=True)
+        self.status = aggregation.state
+        self.completed = aggregation.resource_processed_count
+        self.total = aggregation.resource_count
+        self.with_violations = aggregation.resources_with_violations_count
+        self.violations = aggregation.violations_count