feat: ruff linter & formatter

Author: Integer-Ctrl

.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

README.md

@@ -20,6 +20,8 @@ Command-line and Python client for downloading and deploying datasets on DBpedia
   - [Delete](#cli-delete)
 - [Module Usage](#module-usage)
   - [Deploy](#module-deploy)
+- [Contributing](#contributing)
+  - [Linting](#linting)
 
 
 ## Quickstart
@@ -43,6 +45,7 @@ You can then use the client in the command line:
 ```bash
 databusclient --help
 databusclient deploy --help
+databusclient delete --help
 databusclient download --help
 ```
 
@@ -553,3 +556,27 @@ from databusclient import deploy
 # API key can be found (or generated) at https://$$DATABUS_BASE$$/$$USER$$#settings
 deploy(dataset, "mysterious API key")
 ```
+
+## Development
+
+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 ensuere 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 .
+```

databusclient/__init__.py

@@ -1,7 +1,8 @@
 from databusclient import cli
-from databusclient.api.deploy 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/delete.py

@@ -1,8 +1,10 @@
 import json
-import requests
 from typing import List
 
-from databusclient.api.utils import get_databus_id_parts_from_uri, fetch_databus_jsonld
+import requests
+
+from databusclient.api.utils import fetch_databus_jsonld, get_databus_id_parts_from_uri
+
 
 def _confirm_delete(databusURI: str) -> str:
     """
@@ -17,9 +19,17 @@ 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 +40,9 @@ 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 +68,7 @@ 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 +79,14 @@ 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 +98,9 @@ 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.
 
@@ -121,7 +136,10 @@ 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.
 
@@ -154,13 +172,14 @@ 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 +188,9 @@ 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_uri(
+            databusURI
+        )
 
         if group == "collections" and artifact is not None:
             print(f"Deleting collection: {databusURI}")

databusclient/api/deploy.py

@@ -1,8 +1,9 @@
-from enum import Enum
-from typing import List, Dict, Tuple, Optional, Union
-import requests
 import hashlib
 import json
+from enum import Enum
+from typing import Dict, List, Optional, Tuple, Union
+
+import requests
 
 __debug = False
 
@@ -153,7 +154,7 @@ def get_file_info(distribution_str: str) -> Tuple[Dict[str, str], str, str, str,
     cvs = _get_content_variants(distribution_str)
     extension_part, format_extension, compression = _get_extensions(distribution_str)
 
-    content_variant_part = "_".join([f"{key}={value}" for key, value in cvs.items()])
+    # content_variant_part = "_".join([f"{key}={value}" for key, value in cvs.items()])
 
     if __debug:
         print("DEBUG", distribution_str, extension_part)
@@ -200,7 +201,10 @@ def create_distribution(
 
     return f"{url}|{meta_string}"
 
-def _create_distributions_from_metadata(metadata: List[Dict[str, Union[str, int]]]) -> List[str]:
+
+def _create_distributions_from_metadata(
+    metadata: List[Dict[str, Union[str, int]]],
+) -> List[str]:
     """
     Create distributions from metadata entries.
 
@@ -233,24 +237,30 @@ def _create_distributions_from_metadata(metadata: List[Dict[str, Union[str, int]
         size = entry["size"]
         url = entry["url"]
         if not isinstance(size, int) or size <= 0:
-            raise ValueError(f"Invalid size for {url}: expected positive integer, got {size}")
+            raise ValueError(
+                f"Invalid size for {url}: expected positive integer, got {size}"
+            )
         # Validate SHA-256 hex digest (64 hex chars)
-        if not isinstance(checksum, str) or len(checksum) != 64 or not all(
-            c in '0123456789abcdefABCDEF' for c in checksum):
-                raise ValueError(f"Invalid checksum for {url}")
+        if (
+            not isinstance(checksum, str)
+            or len(checksum) != 64
+            or not all(c in "0123456789abcdefABCDEF" for c in checksum)
+        ):
+            raise ValueError(f"Invalid checksum for {url}")
 
         distributions.append(
             create_distribution(
                 url=url,
                 cvs={"count": f"{counter}"},
                 file_format=entry.get("file_format"),
                 compression=entry.get("compression"),
-                sha256_length_tuple=(checksum, size)
+                sha256_length_tuple=(checksum, size),
             )
         )
         counter += 1
     return distributions
 
+
 def create_dataset(
     version_id: str,
     title: str,
@@ -361,7 +371,7 @@ def create_dataset(
         "@type": "Artifact",
         "title": title,
         "abstract": abstract,
-        "description": description
+        "description": description,
     }
     graphs.append(artifact_graph)
 
@@ -445,7 +455,7 @@ def deploy_from_metadata(
     abstract: str,
     description: str,
     license_url: str,
-    apikey: str
+    apikey: str,
 ) -> None:
     """
     Deploy a dataset from metadata entries.
@@ -475,7 +485,7 @@ def deploy_from_metadata(
         abstract=abstract,
         description=description,
         license_url=license_url,
-        distributions=distributions
+        distributions=distributions,
     )
 
     print(f"Deploying dataset version: {version_id}")