Replace flake8/isort with ruff (#6441)

There's a few advantages of using ruff over these tools:

* It's way faster
* It's easier to configure
* It includes support for a bunch of other linters (for example bugbear)
  right out of the box, which catches some things and makes our code
  more consistent.

Ruff works great with black, which I'd recommend we continue using.

Fixed a few minor issues that the new linter combo picked up.

Author: wlach

.github/workflows/ci.yml

@@ -16,10 +16,9 @@ jobs:
       - uses: actions/setup-python@v4
         with:
           python-version: '3.8'
-      - run: sudo pip install flake8==6.1.0 black==23.1.0 isort==5.12.0
-      - run: flake8 .
+      - run: sudo pip install black==23.1.0 ruff==0.0.287
+      - run: ruff check .
       - run: black --check .
-      - run: isort --check-only --diff .
 
   backend-unit-tests:
     runs-on: ubuntu-22.04

.pre-commit-config.yaml

@@ -1,15 +1,10 @@
 repos:
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
-    hooks:
-      - id: isort
   - repo: https://github.com/psf/black
     rev: 23.1.0
     hooks:
       - id: black
         language_version: python3
-  - repo: https://github.com/pycqa/flake8
-    rev: 6.1.0
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: "v0.0.287"
     hooks:
-      - id: flake8
-        exclude: "migration/.*|.git|viz-lib|node_modules|migrations|bin/upgrade"
+      - id: ruff

Makefile

@@ -34,7 +34,8 @@ tests:
 	docker-compose run server tests
 
 lint:
-	./bin/flake8_tests.sh
+	ruff check .
+	black --check . --diff
 
 backend-unit-tests: up test_db
 	docker-compose run --rm --name tests server tests
@@ -43,15 +44,15 @@ frontend-unit-tests:
 	CYPRESS_INSTALL_BINARY=0 PUPPETEER_SKIP_CHROMIUM_DOWNLOAD=1 yarn --frozen-lockfile
 	yarn test
 
-test: lint backend-unit-tests frontend-unit-tests
+test: backend-unit-tests frontend-unit-tests lint
 
-build: 
+build:
 	yarn build
 
-watch: 
+watch:
 	yarn watch
 
-start: 
+start:
 	yarn start
 
 redis-cli:

bin/flake8_tests.sh

@@ -117,7 +117,7 @@ def restart_services():
     green("Restarting...")
     try:
         run("sudo /etc/init.d/redash_supervisord restart")
-    except subprocess.CalledProcessError as e:
+    except subprocess.CalledProcessError:
         run("sudo service supervisor restart")
 
 

bin/upgrade

@@ -10,13 +10,6 @@ force-exclude = '''
 )/
 '''
 
-[tool.isort]
-py_version = 38
-multi_line_output = 3
-include_trailing_comma = true
-use_parentheses = true
-skip = "migrations"
-
 [tool.poetry]
 name = "redash"
 version = "23.09.0-dev"
@@ -123,7 +116,7 @@ pyexasol = "0.12.0"
 pygridgain = "1.4.0"
 pyhive = "0.6.1"
 pyignite = "0.6.1"
-pymongo = {version = "4.3.3", extras = ["srv", "tls"]}
+pymongo = { version = "4.3.3", extras = ["srv", "tls"] }
 pymssql = "2.2.8"
 pyodbc = "4.0.28"
 python-arango = "6.1.0"
@@ -164,3 +157,14 @@ watchdog = "3.0.0"
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
+
+[tool.ruff]
+exclude = [".git", "viz-lib", "node_modules", "migrations"]
+ignore = ["E501"]
+select = ["C9", "E", "F", "W", "I001"]
+
+[tool.ruff.mccabe]
+max-complexity = 15
+
+[tool.ruff.per-file-ignores]
+"__init__.py" = ["F401"]

pyproject.toml

@@ -8,9 +8,9 @@
     BaseResource,
     filter_by_tags,
     get_object_or_404,
+    paginate,
 )
 from redash.handlers.base import order_results as _order_results
-from redash.handlers.base import paginate
 from redash.permissions import (
     can_modify,
     require_admin_or_owner,

redash/handlers/dashboards.py

@@ -11,9 +11,11 @@
     BaseResource,
     filter_by_tags,
     get_object_or_404,
+    org_scoped_rule,
+    paginate,
+    routes,
 )
 from redash.handlers.base import order_results as _order_results
-from redash.handlers.base import org_scoped_rule, paginate, routes
 from redash.handlers.query_results import run_query
 from redash.models.parameterized_query import ParameterizedQuery
 from redash.permissions import (

redash/handlers/queries.py

@@ -13,9 +13,13 @@
     send_password_reset_email,
     send_verify_email,
 )
-from redash.handlers.base import BaseResource, get_object_or_404
+from redash.handlers.base import (
+    BaseResource,
+    get_object_or_404,
+    paginate,
+    require_fields,
+)
 from redash.handlers.base import order_results as _order_results
-from redash.handlers.base import paginate, require_fields
 from redash.permissions import (
     is_admin_or_owner,
     require_admin,

redash/handlers/users.py

@@ -14,12 +14,12 @@
 def reduce_item(reduced_item, key, value):
     """From https://github.com/vinay20045/json-to-csv"""
     # Reduction Condition 1
-    if type(value) is list:
+    if isinstance(value, list):
         for i, sub_item in enumerate(value):
             reduce_item(reduced_item, "{}.{}".format(key, i), sub_item)
 
     # Reduction Condition 2
-    elif type(value) is dict:
+    elif isinstance(value, dict):
         sub_keys = value.keys()
         for sub_key in sub_keys:
             reduce_item(reduced_item, "{}.{}".format(key, sub_key), value[sub_key])

redash/query_runner/dgraph.py

@@ -133,12 +133,12 @@ def parse_worksheet(worksheet):
 
 def parse_spreadsheet(spreadsheet, worksheet_num_or_title):
     worksheet = None
-    if type(worksheet_num_or_title) is int:
+    if isinstance(worksheet_num_or_title, int):
         worksheet = spreadsheet.get_worksheet_by_index(worksheet_num_or_title)
         if worksheet is None:
             worksheet_count = len(spreadsheet.worksheets())
             raise WorksheetNotFoundError(worksheet_num_or_title, worksheet_count)
-    elif type(worksheet_num_or_title) is str:
+    elif isinstance(worksheet_num_or_title, str):
         worksheet = spreadsheet.get_worksheet_by_title(worksheet_num_or_title)
         if worksheet is None:
             raise WorksheetNotFoundByTitleError(worksheet_num_or_title)

redash/query_runner/google_spreadsheets.py

@@ -102,7 +102,7 @@ def _get_tables(self, schema):
 
     def normalise_column(self, col):
         # if it's a datetime, just return the milliseconds
-        if type(col) is tuple and len(col) == 2 and type(col[0]) is datetime.datetime and type(col[1]) is int:
+        if type(col) is tuple and len(col) == 2 and type(col[0]) is datetime.datetime and isinstance(col[1], int):
             return col[0]
         else:
             return col

redash/query_runner/ignite.py

@@ -55,7 +55,7 @@ def convert_query_range(payload):
             continue
         value = payload[key][0]
 
-        if type(value) is str:
+        if isinstance(value, str):
             # Don't convert timestamp string
             try:
                 int(value)

redash/query_runner/prometheus.py

@@ -10,8 +10,8 @@
 from rq.utils import utcnow
 from rq.worker import (
     HerokuWorker,  # HerokuWorker implements graceful shutdown on SIGTERM
+    Worker,
 )
-from rq.worker import Worker
 
 from redash import statsd_client