Refactor/project structure

.github/workflows/python-CI.yml

@@ -18,24 +18,17 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v3
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v5
       with:
-        python-version: "3.10"
+        python-version: "3.11"
     - uses: Gr1N/setup-poetry@v8 #install poetry
-    - name: Install parts of toolchain 
-      run: |
-        python -m pip install --upgrade pip
-        pip install flake8 pytest
+    - name: Upgrade pip
+      run: python -m pip install --upgrade pip
     - name: Install requirements with poetry
       run: poetry install
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Lint with Ruff
+      run: poetry run ruff check --output-format=github .
     - name: Test with pytest
-      run: |
-        poetry run pytest
+      run: poetry run pytest

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.10-slim
+FROM python:3.11-slim
 
 WORKDIR /data
 

README.md

@@ -20,6 +20,9 @@ Command-line and Python client for downloading and deploying datasets on DBpedia
   - [Delete](#cli-delete)
 - [Module Usage](#module-usage)
   - [Deploy](#module-deploy)
+- [Development & Contributing](#development--contributing)
+  - [Linting](#linting)
+  - [Testing](#testing)
 
 
 ## Quickstart
@@ -30,7 +33,7 @@ You can use either **Python** or **Docker**. Both methods support all client fea
 
 ### Python
 
-Requirements: [Python](https://www.python.org/downloads/) and [pip](https://pip.pypa.io/en/stable/installation/)
+Requirements: [Python 3.11+](https://www.python.org/downloads/) and [pip](https://pip.pypa.io/en/stable/installation/)
 
 Before using the client, install it via pip:
 
@@ -43,6 +46,7 @@ You can then use the client in the command line:
 ```bash
 databusclient --help
 databusclient deploy --help
+databusclient delete --help
 databusclient download --help
 ```
 
@@ -183,6 +187,8 @@ Options:
                       e.g. https://databus.dbpedia.org/sparql)
   --vault-token TEXT  Path to Vault refresh token file
   --databus-key TEXT  Databus API key to download from protected databus
+  --all-versions      When downloading artifacts, download all versions
+                      instead of only the latest
   --authurl TEXT      Keycloak token endpoint URL  [default:
                       https://auth.dbpedia.org/realms/dbpedia/protocol/openid-
                       connect/token]
@@ -551,3 +557,45 @@ from databusclient import deploy
 # API key can be found (or generated) at https://$$DATABUS_BASE$$/$$USER$$#settings
 deploy(dataset, "mysterious API key")
 ```
+
+## Development & Contributing
+
+Install development dependencies yourself or via [Poetry](https://python-poetry.org/):
+
+```bash
+poetry install --with dev
+```
+
+### Linting
+
+The used linter is [Ruff](https://ruff.rs/). Ruff is configured in `pyproject.toml` and is enforced in CI (`.github/workflows/ruff.yml`).
+
+For development, you can run linting locally with `ruff check .` and optionally auto-format with `ruff format .`.
+
+To ensure compatibility with the `pyproject.toml` configured dependencies, run Ruff via Poetry:
+
+```bash
+# To check for linting issues:
+poetry run ruff check .
+
+# To auto-format code:
+poetry run ruff format .
+```
+
+### Testing
+
+When developing new features please make sure to add appropriate tests and ensure that all tests pass. Tests are under `tests/` and use [pytest](https://docs.pytest.org/en/7.4.x/) as test framework.
+
+When fixing bugs or refactoring existing code, please make sure to add tests that cover the affected functionality. The current test coverage is very low, so any additional tests are highly appreciated.
+
+To run tests locally, use:
+
+```bash
+pytest tests/
+```
+
+Or to ensure compatibility with the `pyproject.toml` configured dependencies, run pytest via Poetry:
+
+```bash
+poetry run pytest tests/
+```

databusclient/__init__.py

@@ -1,7 +1,8 @@
 from databusclient import cli
-from databusclient.client import create_dataset, deploy, create_distribution
+from databusclient.api.deploy import create_dataset, create_distribution, deploy
 
 __all__ = ["create_dataset", "deploy", "create_distribution"]
 
+
 def run():
     cli.app()

databusclient/api/__init__.py

@@ -0,0 +1 @@
+

databusclient/api/delete.py

@@ -1,8 +1,13 @@
 import json
-import requests
 from typing import List
 
-from databusclient.api.utils import get_databus_id_parts_from_uri, get_json_ld_from_databus
+import requests
+
+from databusclient.api.utils import (
+    fetch_databus_jsonld,
+    get_databus_id_parts_from_file_url,
+)
+
 
 def _confirm_delete(databusURI: str) -> str:
     """
@@ -17,9 +22,17 @@ def _confirm_delete(databusURI: str) -> str:
     - "cancel" if the user chooses to cancel the entire deletion process
     """
     print(f"Are you sure you want to delete: {databusURI}?")
-    print("\nThis action is irreversible and will permanently remove the resource and all its data.")
+    print(
+        "\nThis action is irreversible and will permanently remove the resource and all its data."
+    )
     while True:
-        choice = input("Type 'yes'/'y' to confirm, 'skip'/'s' to skip this resource, or 'cancel'/'c' to abort: ").strip().lower()
+        choice = (
+            input(
+                "Type 'yes'/'y' to confirm, 'skip'/'s' to skip this resource, or 'cancel'/'c' to abort: "
+            )
+            .strip()
+            .lower()
+        )
         if choice in ("yes", "y"):
             return "confirm"
         elif choice in ("skip", "s"):
@@ -30,7 +43,9 @@ def _confirm_delete(databusURI: str) -> str:
             print("Invalid input. Please type 'yes'/'y', 'skip'/'s', or 'cancel'/'c'.")
 
 
-def _delete_resource(databusURI: str, databus_key: str, dry_run: bool = False, force: bool = False):
+def _delete_resource(
+    databusURI: str, databus_key: str, dry_run: bool = False, force: bool = False
+):
     """
     Delete a single Databus resource (version, artifact, group).
 
@@ -56,10 +71,7 @@ def _delete_resource(databusURI: str, databus_key: str, dry_run: bool = False, f
     if databus_key is None:
         raise ValueError("Databus API key must be provided for deletion")
 
-    headers = {
-        "accept": "*/*",
-        "X-API-KEY": databus_key
-    }
+    headers = {"accept": "*/*", "X-API-KEY": databus_key}
 
     if dry_run:
         print(f"[DRY RUN] Would delete: {databusURI}")
@@ -70,10 +82,14 @@ def _delete_resource(databusURI: str, databus_key: str, dry_run: bool = False, f
     if response.status_code in (200, 204):
         print(f"Successfully deleted: {databusURI}")
     else:
-        raise Exception(f"Failed to delete {databusURI}: {response.status_code} - {response.text}")
+        raise Exception(
+            f"Failed to delete {databusURI}: {response.status_code} - {response.text}"
+        )
 
 
-def _delete_list(databusURIs: List[str], databus_key: str, dry_run: bool = False, force: bool = False):
+def _delete_list(
+    databusURIs: List[str], databus_key: str, dry_run: bool = False, force: bool = False
+):
     """
     Delete a list of Databus resources.
 
@@ -85,7 +101,9 @@ def _delete_list(databusURIs: List[str], databus_key: str, dry_run: bool = False
         _delete_resource(databusURI, databus_key, dry_run=dry_run, force=force)
 
 
-def _delete_artifact(databusURI: str, databus_key: str, dry_run: bool = False, force: bool = False):
+def _delete_artifact(
+    databusURI: str, databus_key: str, dry_run: bool = False, force: bool = False
+):
     """
     Delete an artifact and all its versions.
 
@@ -97,7 +115,7 @@ def _delete_artifact(databusURI: str, databus_key: str, dry_run: bool = False, f
     - databus_key: Databus API key to authenticate the deletion requests
     - dry_run: If True, do not perform the deletion but only print what would be deleted
     """
-    artifact_body = get_json_ld_from_databus(databusURI, databus_key)
+    artifact_body = fetch_databus_jsonld(databusURI, databus_key)
 
     json_dict = json.loads(artifact_body)
     versions = json_dict.get("databus:hasVersion")
@@ -121,7 +139,10 @@ def _delete_artifact(databusURI: str, databus_key: str, dry_run: bool = False, f
     # Finally, delete the artifact itself
     _delete_resource(databusURI, databus_key, dry_run=dry_run, force=force)
 
-def _delete_group(databusURI: str, databus_key: str, dry_run: bool = False, force: bool = False):
+
+def _delete_group(
+    databusURI: str, databus_key: str, dry_run: bool = False, force: bool = False
+):
     """
     Delete a group and all its artifacts and versions.
 
@@ -133,7 +154,7 @@ def _delete_group(databusURI: str, databus_key: str, dry_run: bool = False, forc
     - databus_key: Databus API key to authenticate the deletion requests
     - dry_run: If True, do not perform the deletion but only print what would be deleted
     """
-    group_body = get_json_ld_from_databus(databusURI, databus_key)
+    group_body = fetch_databus_jsonld(databusURI, databus_key)
 
     json_dict = json.loads(group_body)
     artifacts = json_dict.get("databus:hasArtifact", [])
@@ -143,7 +164,7 @@ def _delete_group(databusURI: str, databus_key: str, dry_run: bool = False, forc
         uri = item.get("@id")
         if not uri:
             continue
-        _, _, _, _, version, _ = get_databus_id_parts_from_uri(uri)
+        _, _, _, _, version, _ = get_databus_id_parts_from_file_url(uri)
         if version is None:
             artifact_uris.append(uri)
 
@@ -154,13 +175,14 @@ def _delete_group(databusURI: str, databus_key: str, dry_run: bool = False, forc
     # Finally, delete the group itself
     _delete_resource(databusURI, databus_key, dry_run=dry_run, force=force)
 
+
 def delete(databusURIs: List[str], databus_key: str, dry_run: bool, force: bool):
     """
     Delete a dataset from the databus.
 
     Delete a group, artifact, or version identified by the given databus URI.
     Will recursively delete all data associated with the dataset.
-    
+
     Parameters:
     - databusURIs: List of full databus URIs of the resources to delete
     - databus_key: Databus API key to authenticate the deletion requests
@@ -169,7 +191,9 @@ def delete(databusURIs: List[str], databus_key: str, dry_run: bool, force: bool)
     """
 
     for databusURI in databusURIs:
-        _host, _account, group, artifact, version, file = get_databus_id_parts_from_uri(databusURI)
+        _host, _account, group, artifact, version, file = (
+            get_databus_id_parts_from_file_url(databusURI)
+        )
 
         if group == "collections" and artifact is not None:
             print(f"Deleting collection: {databusURI}")