Switch to Ruff for Python linting

Ruff is a new all-in-one Python linter that combines several previous
tools and implements them more quickly. This PR switches to Ruff and
cleans up various parts of the code that Ruff has flagged.

.github/workflows/basic-tests.yml

@@ -26,7 +26,7 @@ jobs:
       - name: Install Python3
         uses: actions/setup-python@v4
         with:
-          python-version: '3.9.x'
+          python-version: '3.10.x'
           cache: 'pip'
           cache-dependency-path: requirements.txt
 
@@ -59,7 +59,7 @@ jobs:
       - name: Install Python3
         uses: actions/setup-python@v4
         with:
-          python-version: '3.9.x'
+          python-version: '3.10.x'
           cache: 'pip'
 
       - name: Install dependencies

Makefile

@@ -181,29 +181,14 @@ docker-logs:
 # Lint commands
 # ===============================================
 
-# Check imports in Python code
-lint-isort:
-	@echo "Running Python isort to organize module imports"
-	@git ls-files '*.py' | xargs isort --check 2>&1
-
-# Check formatting in Python code
-lint-black:
-	@echo "Running Python Black to check formatting"
-	@git ls-files '*.py' | xargs black 2>&1
-
-# Check Python code complyies with PEP8
-lint-flake8:
-	@echo "Running Python flake8 to conform with PEP8"	
-	@git ls-files '*.py' | xargs flake8 --config=./.flake8 2>&1
-
 # Link checks on Python code
-py-lint: py-venv-check lint-black lint-isort lint-flake8
-	@echo "Python lint completed"
+py-lint: py-venv-check
+	ruff . --fix
+	black .
 
 # Lint our Python and JavaScript code. Fail on any issues.
-lint-check: js-lint py-lint
+lint-check: js-lint
 	black . --diff
-	@echo 'Lint completed'
 
 
 # Test, coverage and documentation commands

ambuda/admin.py

@@ -16,7 +16,7 @@ def index(self):
             # Abort so that a malicious scraper can't infer that there's an
             # interesting page here.
             abort(404)
-        return super(AmbudaIndexView, self).index()
+        return super().index()
 
 
 class BaseView(sqla.ModelView):

ambuda/auth.py

@@ -1,7 +1,6 @@
 """Manages the auth/authentication data flow."""
 
 from http import HTTPStatus
-from typing import Optional
 
 from flask import abort, redirect, request, url_for
 from flask_login import LoginManager
@@ -11,7 +10,7 @@
 from ambuda.utils.user_mixins import AmbudaAnonymousUser
 
 
-def _load_user(user_id: int) -> Optional[User]:
+def _load_user(user_id: int) -> User | None:
     """Load a user from the database.
 
     Flask-Login uses this function to populate the `current_user` variable.

ambuda/checks.py

@@ -6,9 +6,8 @@
 from sqlalchemy import create_engine, inspect
 from sqlalchemy.schema import Column
 
-from ambuda import consts
+from ambuda import consts, enums
 from ambuda import database as db
-from ambuda import enums
 from ambuda import queries as q
 from ambuda.models.base import Base
 

ambuda/queries.py

@@ -5,7 +5,6 @@
 """
 
 import functools
-from typing import Optional
 
 from flask import current_app
 from sqlalchemy import create_engine
@@ -66,7 +65,7 @@ def page_statuses() -> list[db.PageStatus]:
     return session.query(db.PageStatus).all()
 
 
-def text(slug: str) -> Optional[db.Text]:
+def text(slug: str) -> db.Text | None:
     session = get_session()
     return (
         session.query(db.Text)
@@ -99,17 +98,17 @@ def text_meta(slug: str) -> db.Text:
     )
 
 
-def text_section(text_id: int, slug: str) -> Optional[db.TextSection]:
+def text_section(text_id: int, slug: str) -> db.TextSection | None:
     session = get_session()
     return session.query(db.TextSection).filter_by(text_id=text_id, slug=slug).first()
 
 
-def block(text_id: int, slug: str) -> Optional[db.TextBlock]:
+def block(text_id: int, slug: str) -> db.TextBlock | None:
     session = get_session()
     return session.query(db.TextBlock).filter_by(text_id=text_id, slug=slug).first()
 
 
-def block_parse(block_id: int) -> Optional[db.BlockParse]:
+def block_parse(block_id: int) -> db.BlockParse | None:
     session = get_session()
     return session.query(db.BlockParse).filter_by(block_id=block_id).first()
 
@@ -153,17 +152,17 @@ def projects() -> list[db.Project]:
     return session.query(db.Project).all()
 
 
-def project(slug: str) -> Optional[db.Project]:
+def project(slug: str) -> db.Project | None:
     session = get_session()
     return session.query(db.Project).filter(db.Project.slug == slug).first()
 
 
-def thread(*, id: int) -> Optional[db.Thread]:
+def thread(*, id: int) -> db.Thread | None:
     session = get_session()
     return session.query(db.Thread).filter_by(id=id).first()
 
 
-def post(*, id: int) -> Optional[db.Post]:
+def post(*, id: int) -> db.Post | None:
     session = get_session()
     return session.query(db.Post).filter_by(id=id).first()
 
@@ -197,7 +196,7 @@ def create_post(*, board_id: int, thread: db.Thread, user_id: int, content: str)
     session.commit()
 
 
-def page(project_id, page_slug: str) -> Optional[db.Page]:
+def page(project_id, page_slug: str) -> db.Page | None:
     session = get_session()
     return (
         session.query(db.Page)
@@ -206,7 +205,7 @@ def page(project_id, page_slug: str) -> Optional[db.Page]:
     )
 
 
-def user(username: str) -> Optional[db.User]:
+def user(username: str) -> db.User | None:
     session = get_session()
     return (
         session.query(db.User)
@@ -233,7 +232,7 @@ def create_user(*, username: str, email: str, raw_password: str) -> db.User:
     return user
 
 
-def blog_post(slug: str) -> Optional[db.BlogPost]:
+def blog_post(slug: str) -> db.BlogPost | None:
     """Fetch the given blog post."""
     session = get_session()
     return session.query(db.BlogPost).filter_by(slug=slug).first()

ambuda/scripts/analysis/dcs_utils.py

@@ -4,8 +4,8 @@
 """
 
 import re
+from collections.abc import Iterator
 from dataclasses import dataclass
-from typing import Iterator
 
 import conllu
 from indic_transliteration import sanscript

ambuda/scripts/analysis/mahabharata.py

@@ -1,8 +1,8 @@
 """Add the Mahabharata parse data from DCS."""
 
 
+from collections.abc import Iterator
 from pathlib import Path
-from typing import Iterator
 
 import ambuda.scripts.analysis.dcs_utils as dcs
 from ambuda.scripts.analysis.ramayana import get_kanda_and_sarga, map_and_write

ambuda/scripts/analysis/ramayana.py

@@ -1,8 +1,8 @@
 """Add the Ramayana parse data from DCS."""
 
 import xml.etree.ElementTree as ET
+from collections.abc import Iterator
 from pathlib import Path
-from typing import Iterator
 
 from indic_transliteration import sanscript
 from sqlalchemy.orm import Session

ambuda/scripts/analysis/single_file_text.py

@@ -1,8 +1,8 @@
 """Add parse data from DCS for a simple text."""
 
 import argparse
+from collections.abc import Iterator
 from pathlib import Path
-from typing import Iterator
 
 from sqlalchemy.orm import Session
 
@@ -23,8 +23,7 @@ def iter_sections(dcs_text_name):
         / "files"
         / f"{dcs_text_name}-all.conllu"
     )
-    for section in dcs.parse_file(text_path):
-        yield section
+    yield from dcs.parse_file(text_path)
 
 
 def iter_parsed_blocks(dcs_text_name) -> Iterator[tuple[str, str]]:

ambuda/seed/dcs.py

@@ -11,7 +11,7 @@
 DATA_DIR = PROJECT_DIR / "data" / "ambuda-dcs"
 
 
-class UpdateException(Exception):
+class UpdateError(Exception):
     pass
 
 
@@ -80,7 +80,7 @@ def add_parse_data(text_slug: str, path: Path):
     with Session(engine) as session:
         text = session.query(db.Text).filter_by(slug=text_slug).first()
         if not text:
-            raise UpdateException()
+            raise UpdateError()
 
         drop_existing_parse_data(session, text.id)
 
@@ -102,7 +102,7 @@ def run():
             try:
                 add_parse_data(path.stem, path)
                 log(f"- Added {path.stem} parse data to the database.")
-            except UpdateException:
+            except UpdateError:
                 log(f"- Skipped {path.stem}.")
                 skipped.append(path.stem)
 

ambuda/seed/dictionaries/amarakosha.py

@@ -16,7 +16,7 @@
 """
 
 import re
-from typing import Iterator
+from collections.abc import Iterator
 
 import click
 from indic_transliteration import sanscript

ambuda/seed/dictionaries/apte.py

@@ -55,7 +55,7 @@ def _make_compounds(first_word, groups):
     for group in groups:
         child = group[0]
         # Case 1: simple and well-formed
-        if re.fullmatch("\w+", child.text):
+        if re.fullmatch(r"\w+", child.text):
             samasa = sandhi_utils.apply(first_word, child.text)
             group[0].text = first_word + "\u2014" + group[0].text
             yield samasa, group

ambuda/seed/dictionaries/apte_sanskrit_hindi.py

@@ -24,7 +24,7 @@
 """
 
 import xml.etree.ElementTree as ET
-from typing import Iterator
+from collections.abc import Iterator
 
 import click
 from indic_transliteration import sanscript

ambuda/seed/dictionaries/shabdartha_kaustubha.py

@@ -18,7 +18,7 @@
 """
 
 import re
-from typing import Iterator
+from collections.abc import Iterator
 
 import click
 from indic_transliteration import sanscript
@@ -41,9 +41,9 @@ def create_entries(key: str, body: str) -> Iterator[tuple[str, str]]:
     body = re.sub(r"\[(.*)\]", r"<lb/><b>\1</b>", body)
 
     # Per Vishvas, '|' divides headwords.
-    for key in key.split("|"):
-        key = standardize_key(key)
-        yield key, f"<s>{body}</s>"
+    for k in key.split("|"):
+        k = standardize_key(k)
+        yield k, f"<s>{body}</s>"
 
 
 def sak_generator(dict_blob: str):

ambuda/seed/lookup/__init__.py

@@ -14,4 +14,4 @@ def run():
             "Error: Failed to create page statuses, "
             "create roles, and creat bot user."
             f"Error: {ex}"
-        )
+        ) from ex

ambuda/seed/lookup/create_bot_user.py

@@ -11,8 +11,10 @@
 def _create_bot_user(session):
     try:
         password = os.environ["AMBUDA_BOT_PASSWORD"]
-    except KeyError:
-        raise ValueError("Please set the AMBUDA_BOT_PASSWORD environment variable.")
+    except KeyError as e:
+        raise ValueError(
+            "Please set the AMBUDA_BOT_PASSWORD environment variable."
+        ) from e
 
     user = db.User(username=consts.BOT_USERNAME, email="[email protected]")
     user.set_password(password)

ambuda/seed/texts/gretil.py

@@ -116,7 +116,7 @@ def run():
         for spec in ALLOW:
             add_document(engine, spec)
     except Exception as ex:
-        raise Exception("Error: Failed to get latest from GRETIL. " f"Error: {ex}")
+        raise Exception("Error: Failed to get latest from GRETIL.") from ex
 
     log("Done.")
 

ambuda/seed/utils/itihasa_utils.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
 """Database utility functions."""
 
+from collections.abc import Iterator
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Iterator
 
 from dotenv import load_dotenv
 from indic_transliteration import sanscript

ambuda/tasks/ocr.py

@@ -1,6 +1,5 @@
 """Background tasks for proofing projects."""
 
-from typing import Optional
 
 from celery import group
 from celery.result import GroupResult
@@ -53,8 +52,10 @@ def _run_ocr_for_page_inner(
                 version=0,
                 author_id=bot_user.id,
             )
-        except Exception:
-            raise ValueError(f'OCR failed for page "{project.slug}/{page.slug}".')
+        except Exception as e:
+            raise ValueError(
+                f'OCR failed for page "{project.slug}/{page.slug}".'
+            ) from e
 
 
 @app.task(bind=True)
@@ -75,7 +76,7 @@ def run_ocr_for_page(
 def run_ocr_for_project(
     app_env: str,
     project: db.Project,
-) -> Optional[GroupResult]:
+) -> GroupResult | None:
     """Create a `group` task to run OCR on a project.
 
     Usage:

ambuda/utils/auth.py

@@ -1,5 +1,5 @@
+from collections.abc import Callable
 from functools import wraps
-from typing import Callable
 
 from flask import current_app
 from flask_login import current_user