Use Ruff linter and formatter

.github/workflows/test_suite.yml

@@ -45,6 +45,13 @@ jobs:
       - name: 'Reinstall PyGEM'
         run: pip install --break-system-packages -e .
 
+      - name: 'Run ruff linting check'
+        run: ruff check .
+
+      - name: 'Run ruff formatting check'
+        if: ${{ !cancelled() }}
+        run: ruff format . --check
+
       - name: 'Initialize PyGEM'
         run: initialize
 

.gitignore

@@ -1,7 +1,6 @@
-# pycache
+# Subdirectories
 __pycache__/
-
-# vscode
+sample_data/
 .vscode/
 
 # python bytecode

docs/conf.py

@@ -8,47 +8,49 @@
 
 import os
 import sys
+
 import tomllib
+
 sys.path.insert(0, os.path.abspath('../pygem/'))
 
 # source pyproject.toml to get release
-with open("../pyproject.toml", "rb") as f:
+with open('../pyproject.toml', 'rb') as f:
     pyproject = tomllib.load(f)
 
 project = 'PyGEM'
 copyright = '2023, David Rounce'
 author = 'David Rounce'
-release = pyproject["tool"]["poetry"]["version"]
+release = pyproject['tool']['poetry']['version']
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
-extensions = ['sphinx_book_theme',
-              'myst_parser',
-              'sphinx.ext.autodoc',
-              'sphinx.ext.autosummary',
-              'sphinx.ext.intersphinx',
-              'numpydoc',
-              'sphinx.ext.viewcode',
-              'sphinx_togglebutton',
-              ]
+extensions = [
+    'sphinx_book_theme',
+    'myst_parser',
+    'sphinx.ext.autodoc',
+    'sphinx.ext.autosummary',
+    'sphinx.ext.intersphinx',
+    'numpydoc',
+    'sphinx.ext.viewcode',
+    'sphinx_togglebutton',
+]
 
 myst_enable_extensions = [
-    "amsmath",
-    "attrs_inline",
-    "colon_fence",
-    "deflist",
-    "dollarmath",
-    "fieldlist",
-    "html_admonition",
-    "html_image",
+    'amsmath',
+    'attrs_inline',
+    'colon_fence',
+    'deflist',
+    'dollarmath',
+    'fieldlist',
+    'html_admonition',
+    'html_image',
 ]
 
-#templates_path = ['_templates']
+# templates_path = ['_templates']
 exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
 
 
-
 # -- Options for HTML output -------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
 
@@ -57,8 +59,8 @@
 html_static_path = ['_static']
 
 html_theme_options = {
-    "repository_url": "https://github.com/PyGEM-Community/PyGEM",
-    "use_repository_button": True,
-    "show_nav_level":2,
-    "navigation_depth":3,
-    }
+    'repository_url': 'https://github.com/PyGEM-Community/PyGEM',
+    'use_repository_button': True,
+    'show_nav_level': 2,
+    'navigation_depth': 3,
+}

docs/contributing.md

@@ -45,6 +45,7 @@ Installing a package in editable mode creates a symbolic link to your source cod
 - First, open a Draft PR. Then consider:
     - Have you finished making changes?
     - Have you added tests for all new functionalities you introduced?
+    - Have you run the ruff linter and formatter? See [the linting and formatting section below](ruff_target) on how to do that.
     - Have all tests passed in the CI? (Check the progress in the Checks tab of the PR.)
 
   If the answer to all of the above is "yes", mark the PR as "Ready for review" and request a review from an appropriate reviewer. If in doubt of which reviewer to assign, assign [drounce](https://github.com/drounce).
@@ -56,3 +57,22 @@ Installing a package in editable mode creates a symbolic link to your source cod
   - After responding to a reviewer's comment, do not mark it as resolved.
   - Once all comments are addressed, request a new review from the same reviewer. The reviewer should then resolve the comments they are satisfied with.
 - After approving someone else's PR, do not merge it. Let the original author of the PR merge it when they are ready, as they might notice necessary last-minute changes.
+
+(ruff_target)=
+## Code linting and formatting
+PyGEM **requires** all code to be linted and formatted using [ruff](https://docs.astral.sh/ruff/formatter). Ruff enforces a consistent coding style (based on [Black](https://black.readthedocs.io/en/stable/the_black_code_style/index.html)) and helps prevent potential errors, stylistic issues, or deviations from coding standards. The configuration for Ruff can be found in the `pyproject.toml` file.
+
+⚠️ **Both linting and formatting must be completed before code is merged.** These checks are run automatically in the CI pipeline. If any issues are detected, the pipeline will fail.
+
+### Lint the codebase
+To lint the codebase using Ruff, run the following command:
+```
+ruff check /path/to/code
+```
+Please address all reported errors. Many errors may be automatically and safely fixed by passing `--fix` to the above command. Other errors will need to be manually addressed.
+
+### Format the codebase
+To automatically format the codebase using Ruff, run the following command:
+```
+ruff format /path/to/code
+```

pygem/__init__.py

@@ -5,8 +5,10 @@
 
 Distrubted under the MIT lisence
 """
+
 from importlib.metadata import version
+
 try:
     __version__ = version(__name__)
 except:
-    __version__ = None
+    __version__ = None

pygem/bin/op/duplicate_gdirs.py

@@ -7,43 +7,62 @@
 
 duplicate OGGM glacier directories
 """
+
 import argparse
 import os
 import shutil
+
 # pygem imports
 from pygem.setup.config import ConfigManager
+
 # instantiate ConfigManager
 config_manager = ConfigManager()
 # read the config
 pygem_prms = config_manager.read_config()
 
+
 def main():
-    parser = argparse.ArgumentParser(description="Script to make duplicate oggm glacier directories - primarily to avoid corruption if parellelizing runs on a single glacier")
+    parser = argparse.ArgumentParser(
+        description='Script to make duplicate oggm glacier directories - primarily to avoid corruption if parellelizing runs on a single glacier'
+    )
     # add arguments
-    parser.add_argument('-rgi_glac_number', type=str, default=None,
-                        help='Randoph Glacier Inventory region')
-    parser.add_argument('-num_copies', type=int, default=1,
-                        help='Number of copies to create of the glacier directory data')
+    parser.add_argument(
+        '-rgi_glac_number',
+        type=str,
+        default=None,
+        help='Randoph Glacier Inventory region',
+    )
+    parser.add_argument(
+        '-num_copies',
+        type=int,
+        default=1,
+        help='Number of copies to create of the glacier directory data',
+    )
     args = parser.parse_args()
     num_copies = args.num_copies
     glac_num = args.rgi_glac_number
 
-    if (glac_num is not None) and (num_copies)>1:
-        reg,id = glac_num.split('.')
+    if (glac_num is not None) and (num_copies) > 1:
+        reg, id = glac_num.split('.')
         reg = reg.zfill(2)
         thous = id[:2]
-        
+
         root = pygem_prms['root'] + '/' + pygem_prms['oggm']['oggm_gdir_relpath']
         sfix = '/per_glacier/' + f'RGI60-{reg}/' + f'RGI60-{reg}.{thous}/'
 
         for n in range(num_copies):
-            nroot = os.path.abspath(root.replace('gdirs',f'gdirs_{n+1}'))
+            nroot = os.path.abspath(root.replace('gdirs', f'gdirs_{n + 1}'))
             # duplicate structure
             os.makedirs(nroot + sfix + f'RGI60-{reg}.{id}', exist_ok=True)
             # copy directory data
-            shutil.copytree(root + sfix + f'RGI60-{reg}.{id}', nroot + sfix + f'RGI60-{reg}.{id}', dirs_exist_ok=True)
+            shutil.copytree(
+                root + sfix + f'RGI60-{reg}.{id}',
+                nroot + sfix + f'RGI60-{reg}.{id}',
+                dirs_exist_ok=True,
+            )
 
     return
 
+
 if __name__ == '__main__':
-    main()
+    main()

pygem/bin/op/initialize.py

@@ -7,79 +7,90 @@
 
 initialization script (ensure config.yaml and get sample datasets)
 """
-import requests
-import zipfile
-import os,sys
+
+import os
 import shutil
+import zipfile
+
+import requests
+
 from pygem.setup.config import ConfigManager
+
 # instantiate ConfigManager
 config_manager = ConfigManager(overwrite=True)
 # read the config
 pygem_prms = config_manager.read_config()
 
-def print_file_tree(start_path, indent=""):
+
+def print_file_tree(start_path, indent=''):
     # Loop through all files and directories in the current directory
     for item in os.listdir(start_path):
         path = os.path.join(start_path, item)
-        
+
         # Print the current item with indentation
-        print(indent + "|-- " + item)
-        
+        print(indent + '|-- ' + item)
+
         # Recursively call this function if the item is a directory
         if os.path.isdir(path):
-            print_file_tree(path, indent + "    ")
-
+            print_file_tree(path, indent + '    ')
+
+
 def get_confirm_token(response):
     """Extract confirmation token for Google Drive large file download."""
     for key, value in response.cookies.items():
-        if key.startswith("download_warning"):
+        if key.startswith('download_warning'):
             return value
     return None
 
+
 def save_response_content(response, destination):
     """Save the response content to a file."""
     chunk_size = 32768
-    with open(destination, "wb") as file:
+    with open(destination, 'wb') as file:
         for chunk in response.iter_content(chunk_size):
             if chunk:  # Filter out keep-alive chunks
                 file.write(chunk)
 
+
 def get_unique_folder_name(dir):
     """Generate a unique folder name by appending a suffix if the folder already exists."""
     counter = 1
     unique_dir = dir
     while os.path.exists(unique_dir):
-        unique_dir = f"{dir}_{counter}"
+        unique_dir = f'{dir}_{counter}'
         counter += 1
     return unique_dir
 
+
 def download_and_unzip_from_google_drive(file_id, output_dir):
     """
     Download a ZIP file from Google Drive and extract its contents.
-    
+
     Args:
         file_id (str): The Google Drive file ID.
         output_dir (str): The directory to save and extract the contents of the ZIP file.
-    
+
     Returns:
         int: 1 if the ZIP file was successfully downloaded and extracted, 0 otherwise.
     """
     # Google Drive URL template
-    base_url = "https://drive.google.com/uc?export=download"
+    base_url = 'https://drive.google.com/uc?export=download'
 
     # Make sure the output directory exists
     os.makedirs(output_dir, exist_ok=True)
 
     # Path to save the downloaded file
-    zip_path = os.path.join(output_dir, "tmp_download.zip")
+    zip_path = os.path.join(output_dir, 'tmp_download.zip')
 
     try:
         # Start the download process
         with requests.Session() as session:
-            response = session.get(base_url, params={"id": file_id}, stream=True)
+            response = session.get(base_url, params={'id': file_id}, stream=True)
             token = get_confirm_token(response)
             if token:
-                response = session.get(base_url, params={"id": file_id, "confirm": token}, stream=True)
+                response = session.get(
+                    base_url, params={'id': file_id, 'confirm': token}, stream=True
+                )
             save_response_content(response, zip_path)
 
         # Unzip the file
@@ -88,7 +99,11 @@ def download_and_unzip_from_google_drive(file_id, output_dir):
             zip_ref.extractall(tmppath)
 
         # get root dir name of zipped files
-        dir = [item for item in os.listdir(tmppath) if os.path.isdir(os.path.join(tmppath, item))][0]
+        dir = [
+            item
+            for item in os.listdir(tmppath)
+            if os.path.isdir(os.path.join(tmppath, item))
+        ][0]
         unzip_dir = os.path.join(tmppath, dir)
         # get unique name if root dir name already exists in output_dir
         output_dir = get_unique_folder_name(os.path.join(output_dir, dir))
@@ -100,31 +115,33 @@ def download_and_unzip_from_google_drive(file_id, output_dir):
 
     except (requests.RequestException, zipfile.BadZipFile, Exception) as e:
         return None  # Failure
-
+
+
 def main():
     # Define the base directory
     basedir = os.path.join(os.path.expanduser('~'), 'PyGEM')
     # Google Drive file id for sample dataset
-    file_id = "1Wu4ZqpOKxnc4EYhcRHQbwGq95FoOxMfZ"
+    file_id = '1Wu4ZqpOKxnc4EYhcRHQbwGq95FoOxMfZ'
     # download and unzip
     out = download_and_unzip_from_google_drive(file_id, basedir)
 
     if out:
-        print(f"Downloaded PyGEM sample dataset:")
+        print('Downloaded PyGEM sample dataset:')
         print(os.path.abspath(out))
         try:
             print_file_tree(out)
         except:
             pass
 
     else:
-        print(f'Error downloading PyGEM sample dataset.')
+        print('Error downloading PyGEM sample dataset.')
 
     # update root path in config.yaml
     try:
-        config_manager.update_config(updates={'root':f'{out}/sample_data'})
+        config_manager.update_config(updates={'root': f'{out}/sample_data'})
     except:
         pass
-
-if __name__ == "__main__":
-    main()
+
+
+if __name__ == '__main__':
+    main()