Merge pull request #26 from DACCS-Climate/devops-enforcement

add devops tools

Author: mishaschwartz

.github/dependabot.yml

@@ -0,0 +1,9 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/precommit.yml

@@ -0,0 +1,13 @@
+name: pre-commit
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v3
+    - uses: pre-commit/[email protected]

.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.9.5
+    hooks:
+      # Run the linter.
+      - id: ruff
+      # Run the formatter.
+      - id: ruff-format
+  

README.md

@@ -151,3 +151,43 @@ access the resource if you have permission:
 ```python
 >>> session.get(f"{client.this_node.url}/some/protected/subpath")
 ```
+
+## Contributing
+
+We welcome any contributions to this codebase. To submit suggested changes, please do the following:
+
+- create a new feature branch off of `main`
+- update the code, write/update tests, write/update documentation
+- submit a pull request targetting the `main` branch
+
+To develop this project locally, first clone this repository and install the testing and development
+dependencies:
+
+```sh
+pip install -e .[dev,test]
+```
+
+### Testing
+
+Tests are located in the `tests/` folder can be run using `pytest`:
+
+```sh
+pytest tests/
+```
+
+### Coding Style
+
+This codebase uses the [`ruff`](https://docs.astral.sh/ruff/) formatter and linter to enforce style policies.
+
+To check that your changes conform to these policies please run:
+
+```sh
+ruff format
+ruff check
+```
+
+You can also set up pre-commit hooks that will run these checks before you create any commit in this repo:
+
+```sh
+pre-commit install
+```

marble_client/__init__.py

@@ -1,4 +1,14 @@
 from .client import MarbleClient
-from .exceptions import MarbleBaseError, ServiceNotAvailableError, UnknownNodeError, JupyterEnvironmentError
+from .exceptions import JupyterEnvironmentError, MarbleBaseError, ServiceNotAvailableError, UnknownNodeError
 from .node import MarbleNode
 from .services import MarbleService
+
+__all__ = [
+    "MarbleClient",
+    "JupyterEnvironmentError",
+    "MarbleBaseError",
+    "ServiceNotAvailableError",
+    "UnknownNodeError",
+    "MarbleNode",
+    "MarbleService",
+]

marble_client/client.py

@@ -3,22 +3,24 @@
 import os
 import shutil
 import warnings
-from functools import wraps, cache
-from typing import Optional, Any
+from functools import cache, wraps
+from typing import Any, Callable, Optional
 from urllib.parse import urlparse
 
 import dateutil.parser
 import requests
 
 from marble_client.constants import CACHE_FNAME, NODE_REGISTRY_URL
-from marble_client.exceptions import UnknownNodeError, JupyterEnvironmentError
+from marble_client.exceptions import JupyterEnvironmentError, UnknownNodeError
 from marble_client.node import MarbleNode
 
 __all__ = ["MarbleClient"]
 
 
-def check_jupyterlab(f):
+def check_jupyterlab(f: Callable) -> Callable:
     """
+    Raise an error if not running in a Jupyterlab instance.
+
     Wraps the function f by first checking if the current script is running in a
     Marble Jupyterlab environment and raising a JupyterEnvironmentError if not.
 
@@ -28,22 +30,27 @@ def check_jupyterlab(f):
     Note that this checks if either the BIRDHOUSE_HOST_URL or PAVICS_HOST_URL are present to support
     versions of birdhouse-deploy prior to 2.4.0.
     """
+
     @wraps(f)
-    def wrapper(*args, **kwargs):
+    def wrapper(*args, **kwargs) -> Any:
         birdhouse_host_var = ("PAVICS_HOST_URL", "BIRDHOUSE_HOST_URL")
         jupyterhub_env_vars = ("JUPYTERHUB_API_URL", "JUPYTERHUB_USER", "JUPYTERHUB_API_TOKEN")
         if any(os.getenv(var) for var in birdhouse_host_var) and all(os.getenv(var) for var in jupyterhub_env_vars):
             return f(*args, **kwargs)
         raise JupyterEnvironmentError("Not in a Marble jupyterlab environment")
+
     return wrapper
 
 
 class MarbleClient:
+    """Client object representing the information in the Marble registry."""
+
     _registry_cache_key = "marble_client_python:cached_registry"
     _registry_cache_last_updated_key = "marble_client_python:last_updated"
 
     def __init__(self, fallback: bool = True) -> None:
-        """Constructor method
+        """
+        Initialize a MarbleClient instance.
 
         :param fallback: If True, then fall back to a cached version of the registry
             if the cloud registry cannot be accessed, defaults to True
@@ -64,6 +71,7 @@ def __init__(self, fallback: bool = True) -> None:
 
     @property
     def nodes(self) -> dict[str, MarbleNode]:
+        """Return nodes in the current registry."""
         return self._nodes
 
     @property
@@ -87,15 +95,18 @@ def this_node(self) -> MarbleNode:
     def this_session(self, session: Optional[requests.Session] = None) -> requests.Session:
         """
         Add the login session cookies of the user who is currently logged in to the session object.
+
         If a session object is not passed as an argument to this function, create a new session
         object as well.
 
         Note that this function only works in a Marble Jupyterlab environment.
         """
         if session is None:
             session = requests.Session()
-        r = requests.get(f"{os.getenv('JUPYTERHUB_API_URL')}/users/{os.getenv('JUPYTERHUB_USER')}",
-                         headers={"Authorization": f"token {os.getenv('JUPYTERHUB_API_TOKEN')}"})
+        r = requests.get(
+            f"{os.getenv('JUPYTERHUB_API_URL')}/users/{os.getenv('JUPYTERHUB_USER')}",
+            headers={"Authorization": f"token {os.getenv('JUPYTERHUB_API_TOKEN')}"},
+        )
         try:
             r.raise_for_status()
         except requests.HTTPError as err:
@@ -105,17 +116,20 @@ def this_session(self, session: Optional[requests.Session] = None) -> requests.S
         return session
 
     @property
-    def registry_uri(self):
+    def registry_uri(self) -> str:
+        """Return the URL of the currently used Marble registry."""
         return self._registry_uri
 
     def __getitem__(self, node: str) -> MarbleNode:
+        """Return the node with the given name."""
         try:
             return self.nodes[node]
         except KeyError as err:
             raise UnknownNodeError(f"No node named '{node}' in the Marble network.") from err
 
     def __contains__(self, node: str) -> bool:
-        """Check if a node is available
+        """
+        Check if a node is available.
 
         :param node: ID of the Marble node
         :type node: str
@@ -175,8 +189,10 @@ def _save_registry_as_cache(self, registry: dict[str, Any]) -> None:
 
         try:
             with open(CACHE_FNAME, "w") as f:
-                data = {self._registry_cache_key: registry,
-                        self._registry_cache_last_updated_key: datetime.datetime.now(tz=datetime.timezone.utc).isoformat()}
+                data = {
+                    self._registry_cache_key: registry,
+                    self._registry_cache_last_updated_key: datetime.datetime.now(tz=datetime.timezone.utc).isoformat(),
+                }
                 json.dump(data, f)
         except OSError:
             # If the cache file cannot be written, then restore from backup files

marble_client/exceptions.py

@@ -1,14 +1,14 @@
 class MarbleBaseError(Exception):
-    pass
+    """Base Error for all exceptions for this package."""
 
 
 class ServiceNotAvailableError(MarbleBaseError):
-    pass
+    """Indicates that a given service is not available."""
 
 
 class UnknownNodeError(MarbleBaseError):
-    pass
+    """Indicates that the given node cannot be found."""
 
 
 class JupyterEnvironmentError(MarbleBaseError):
-    pass
+    """Indicates that there is an issue detecting features only available in Jupyterlab."""

marble_client/node.py

@@ -12,6 +12,8 @@
 
 
 class MarbleNode:
+    """A node in the Marble network."""
+
     def __init__(self, nodeid: str, jsondata: dict[str]) -> None:
         self._nodedata = jsondata
         self._id = nodeid
@@ -34,6 +36,7 @@ def __init__(self, nodeid: str, jsondata: dict[str]) -> None:
             self._services[s.name] = s
 
     def is_online(self) -> bool:
+        """Return True iff the node is currently online."""
         try:
             registry = requests.get(self.url)
             registry.raise_for_status()
@@ -43,68 +46,89 @@ def is_online(self) -> bool:
 
     @property
     def id(self) -> str:
+        """Return the unique id for this node in the Marble network."""
         return self._id
 
     @property
     def name(self) -> str:
+        """
+        Return the name of the node.
+
+        Note that this is not guarenteed to be unique (like the id) but represents
+        how the node is often referred to in other documentation.
+        """
         return self._name
 
     @property
     def description(self) -> str:
+        """Return a description of the node."""
         return self._nodedata["description"]
 
     @property
     def url(self) -> Optional[str]:
+        """Return the root URL of the node."""
         return self._links_service
 
     @property
     def collection_url(self) -> Optional[str]:
+        """Return a URL to the node's services endpoint."""
         warnings.warn("collection_url has been renamed to services_url", DeprecationWarning, 2)
         return self._links_collection
 
     @property
     def services_url(self) -> Optional[str]:
+        """Return a URL to the node's services endpoint."""
         return self._links_collection
 
     @property
     def version_url(self) -> Optional[str]:
+        """Return a URL to the node's version endpoint."""
         return self._links_version
 
     @property
     def date_added(self) -> datetime:
+        """Return datetime representing when the node was added to the Marble network."""
         return dateutil.parser.isoparse(self._nodedata["date_added"])
 
     @property
     def affiliation(self) -> str:
+        """Return affiliation information for the node."""
         return self._nodedata["affiliation"]
 
     @property
     def location(self) -> dict[str, float]:
+        """Return the geographical location of the node."""
         return self._nodedata["location"]
 
     @property
     def contact(self) -> str:
+        """Return contact information for the node."""
         return self._nodedata["contact"]
 
     @property
     def last_updated(self) -> datetime:
+        """Return datetime representing the last time the node's metadata was updated."""
         return dateutil.parser.isoparse(self._nodedata["last_updated"])
 
     @property
     def marble_version(self) -> str:
+        """Return node version."""
         warnings.warn("marble_version has been renamed to version", DeprecationWarning, 2)
         return self._nodedata["version"]
 
     @property
     def version(self) -> str:
+        """Return node version."""
         return self._nodedata["version"]
 
     @property
     def services(self) -> list[str]:
+        """Return node services."""
         return list(self._services)
 
     @property
     def links(self) -> list[dict[str, str]]:
+        """Return node links."""
         return self._nodedata["links"]
 
     def __getitem__(self, service: str) -> MarbleService:
@@ -122,7 +146,8 @@ def __getitem__(self, service: str) -> MarbleService:
             raise ServiceNotAvailableError(f"A service named '{service}' is not available on this node.") from e
 
     def __contains__(self, service: str) -> bool:
-        """Check if a service is available at a node
+        """
+        Check if a service is available at a node.
 
         :param service: Name of the Marble service
         :type service: str
@@ -132,4 +157,5 @@ def __contains__(self, service: str) -> bool:
         return service in self._services
 
     def __repr__(self) -> str:
+        """Return a repr containing id and name."""
         return f"<{self.__class__.__name__}(id: '{self.id}', name: '{self.name}')>"