Add ruff code formatting and linting github action (#170)

* add ruff action

* apply ruff check --fix

* apply ruff format

* run ruff with import sorting

* style fixes by ruff

* fix e402

* add sort import properly

* add some noqa and fix easy ones

* reformat

* add info to the contributing guidelines

---------

Co-authored-by: bdpedigo <bdpedigo@users.noreply.github.com>

.github/workflows/format.yml

@@ -0,0 +1,22 @@
+name: Lint and Format
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches: master
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+  # Allows other workflows to trigger this workflow
+  workflow_call:
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: chartboost/ruff-action@v1
+        with: # the --extend-select flag adds import sorting
+          args: check . --extend-select I
+      - uses: chartboost/ruff-action@v1
+        with:
+          args: format . --check

caveclient/base.py

@@ -1,15 +1,16 @@
-import urllib
-import requests
+import datetime
 import json
 import logging
-
-logger = logging.getLogger(__name__)
+import urllib
 import webbrowser
 
-from .session_config import patch_session
 import numpy as np
-import datetime
 import pandas as pd
+import requests
+
+from .session_config import patch_session
+
+logger = logging.getLogger(__name__)
 
 
 class BaseEncoder(json.JSONEncoder):
@@ -149,7 +150,7 @@ def _api_endpoints(
                 verify=verify,
             )
             avail_vs_server = set(avail_vs_server)
-        except:
+        except:  # noqa: E722
             avail_vs_server = None
 
         avail_vs_client = set(endpoint_versions.keys())

caveclient/chunkedgraph.py

@@ -1,4 +1,5 @@
 """PyChunkedgraph service python interface"""
+
 import datetime
 import json
 import logging
@@ -785,11 +786,11 @@ def level2_chunk_graph(self, root_id, bounds=None) -> list:
             Root id of object
         bounds : np.array
             3x2 bounding box (x,y,z) x (min,max) in chunked graph coordinates (use
-            `client.chunkedgraph.base_resolution` to view this default resolution for 
-            your chunkedgraph client). Note that the result will include any level 2 
-            nodes which have chunk boundaries within some part of this bounding box, 
-            meaning that the representative point for a given level 2 node could still 
-            be slightly outside of these bounds. If None, returns all level 2 chunks 
+            `client.chunkedgraph.base_resolution` to view this default resolution for
+            your chunkedgraph client). Note that the result will include any level 2
+            nodes which have chunk boundaries within some part of this bounding box,
+            meaning that the representative point for a given level 2 node could still
+            be slightly outside of these bounds. If None, returns all level 2 chunks
             for the root ID.
 
         Returns
@@ -807,7 +808,7 @@ def level2_chunk_graph(self, root_id, bounds=None) -> list:
 
         url = self._endpoints["lvl2_graph"].format_map(endpoint_mapping)
         response = self.session.get(url, params=query_d)
-        
+
         r = handle_response(response)
 
         used_bounds = response.headers.get("Used-Bounds")

caveclient/datastack_lookup.py

@@ -1,7 +1,8 @@
-import os
 import json
-from . import auth
 import logging
+import os
+
+from . import auth
 
 logger = logging.getLogger(__name__)
 
@@ -16,7 +17,7 @@ def read_map(filename=None):
         with open(os.path.expanduser(filename), "r") as f:
             data = json.load(f)
         return data
-    except:
+    except:  # noqa E722
         return {}
 
 

caveclient/emannotationschemas.py

@@ -1,9 +1,13 @@
 from __future__ import annotations
+
+import logging
+
+from requests import HTTPError
+
+from .auth import AuthClient
 from .base import ClientBase, _api_endpoints, handle_response
 from .endpoints import schema_api_versions, schema_endpoints_common
-from .auth import AuthClient
-from requests import HTTPError
-import logging
+
 logger = logging.getLogger(__name__)
 
 server_key = "emas_server_address"
@@ -81,7 +85,7 @@ def get_schemas(self) -> list[str]:
         url = self._endpoints["schema"].format_map(endpoint_mapping)
         response = self.session.get(url)
         return handle_response(response)
-    
+
     def schema_definition(self, schema_type: str) -> dict[str]:
         """Get the definition of a specified schema_type
 
@@ -108,20 +112,22 @@ def schema_definition_multi(self, schema_types: list[str]) -> dict:
         ----------
         schema_types : list
             List of schema names
-        
+
         Returns
         -------
         dict
             Dictionary of schema definitions. Keys are schema names, values are definitions.
         """
         endpoint_mapping = self.default_url_mapping
         url = self._endpoints["schema_definition_multi"].format_map(endpoint_mapping)
-        data={'schema_names': ','.join(schema_types)}
+        data = {"schema_names": ",".join(schema_types)}
         response = self.session.post(url, params=data)
         try:
             return handle_response(response)
         except HTTPError:
-            logger.warning('Client requested an schema service endpoint (see "schema_definition_multi") not yet available on your deployment. Please talk to your admin about updating your deployment')
+            logger.warning(
+                'Client requested an schema service endpoint (see "schema_definition_multi") not yet available on your deployment. Please talk to your admin about updating your deployment'
+            )
             return None
 
     def schema_definition_all(self) -> dict[str]:
@@ -138,11 +144,12 @@ def schema_definition_all(self) -> dict[str]:
         try:
             return handle_response(response)
         except HTTPError:
-            logger.warning('Client requested an schema service endpoint (see "schema_definition_all") not yet available on your deployment. Please talk to your admin about updating your deployment')
+            logger.warning(
+                'Client requested an schema service endpoint (see "schema_definition_all") not yet available on your deployment. Please talk to your admin about updating your deployment'
+            )
             return None
 
 
-
 client_mapping = {
     1: SchemaClientLegacy,
     2: SchemaClientLegacy,

caveclient/materializationengine.py

@@ -3,17 +3,17 @@
 import logging
 import re
 import warnings
+from concurrent.futures import ThreadPoolExecutor
 from datetime import datetime, timezone
 from typing import Iterable, Optional, Union
-from requests import HTTPError
 
 import numpy as np
 import pandas as pd
 import pyarrow as pa
 import pytz
-from concurrent.futures import ThreadPoolExecutor
 from cachetools import TTLCache, cached
 from IPython.display import HTML
+from requests import HTTPError
 
 from .auth import AuthClient
 from .base import (
@@ -258,7 +258,7 @@ def __init__(
     @property
     def datastack_name(self):
         return self._datastack_name
-    
+
     @property
     def cg_client(self):
         if self._cg_client is None:
@@ -296,7 +296,7 @@ def tables(self) -> TableManager:
             else:
                 raise ValueError("No full CAVEclient specified")
         return self._tables
-    
+
     @property
     def views(self) -> ViewManager:
         if self._views is None:
@@ -1894,25 +1894,15 @@ def __init__(self, *args, **kwargs):
                     self.get_tables_metadata,
                 )
             )
-            metadata.append(
-                executor.submit(
-                    self.fc.schema.schema_definition_all
-                )
-            )
-            metadata.append(
-                executor.submit(
-                    self.get_views
-                )
-            )
-            metadata.append(
-                executor.submit(
-                    self.get_view_schemas
-                )
-            )
+            metadata.append(executor.submit(self.fc.schema.schema_definition_all))
+            metadata.append(executor.submit(self.get_views))
+            metadata.append(executor.submit(self.get_view_schemas))
         tables = None
         if self.fc is not None:
             if metadata[0].result() is not None and metadata[1].result() is not None:
-                tables = TableManager(self.fc, metadata[0].result(), metadata[1].result())
+                tables = TableManager(
+                    self.fc, metadata[0].result(), metadata[1].result()
+                )
         self._tables = tables
         if self.fc is not None:
             views = ViewManager(self.fc, metadata[2].result(), metadata[3].result())

caveclient/mytimer.py

@@ -1,5 +1,5 @@
-from time import time
 import logging
+from time import time
 
 logger = logging.getLogger(__name__)
 

caveclient/tools/caching.py

@@ -1,6 +1,7 @@
-from caveclient import CAVEclient
 from cachetools import TTLCache, cached, keys
 
+from caveclient import CAVEclient
+
 info_cache_cache = TTLCache(maxsize=32, ttl=3600)
 
 

caveclient/tools/stage.py

@@ -1,7 +1,7 @@
-import jsonschema
 import attrs
-import pandas as pd
+import jsonschema
 import numpy as np
+import pandas as pd
 
 SPATIAL_POINT_CLASSES = ["SpatialPoint", "BoundSpatialPoint"]