[MAINT] switch to ruff (#338)

* apply ruff

* fix

* fix

Author: Remi-Gau

.flake8

@@ -20,27 +20,12 @@ repos:
     -   id: mixed-line-ending
     -   id: trailing-whitespace
 
-# Sorts Python imports alphabetically and by section with `isort`.
--   repo: https://github.com/pycqa/isort
-    rev: 6.0.1
-    hooks:
-    -   id: isort
-        args: [--profile, black, --settings-path, pyproject.toml]
-
 # Automatically upgrade syntax for newer versions of the language.
 -   repo: https://github.com/asottile/pyupgrade
     rev: v3.20.0
     hooks:
     -   id: pyupgrade
-        args: [--py38-plus]
-
-# Aplly black formatting to python code
-# https://github.com/psf/black
--   repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 25.1.0
-    hooks:
-    -   id: black
-        args: [--config, pyproject.toml]
+        args: [--py310-plus]
 
 # Checks for spelling errors
 -   repo: https://github.com/codespell-project/codespell
@@ -84,15 +69,13 @@ repos:
     -   id: prettier
         types_or: [css, html, json]
 
-# Check that Python code complies with PEP8 guidelines
-# flake8 uses pydocstyle to check docstrings: https://flake8.pycqa.org/en/latest/
-# flake8-docstrings: https://pypi.org/project/flake8-docstrings/
-# flake8-use-fstring forces to use fstrings: https://pypi.org/project/flake8-use-fstring/
-# flake8-functions checks functions quality: https://pypi.org/project/flake8-functions/
-# flake8-bugbear detects some common bugs: https://github.com/PyCQA/flake8-bugbear
--   repo: https://github.com/pyCQA/flake8
-    rev: 7.3.0
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.7
     hooks:
-    -   id: flake8
-        args: [--config, .flake8, --verbose, ecobidas, tests, macros]
-        additional_dependencies: [flake8-docstrings, flake8-use-fstring, flake8-functions, flake8-bugbear]
+    # Run the linter.
+    -   id: ruff-check
+        # args: [--statistics]
+        args: [--fix, --show-fixes]
+    # Run the formatter.
+    -   id: ruff-format
+        # args: [--diff]

.pre-commit-config.yaml

@@ -32,7 +32,7 @@ def cli(argv: Sequence[str] = sys.argv) -> None:
     args, unknowns = parser.parse_known_args(argv[1:])
     if unknowns:
         logger.error(f"The following arguments are unknown: {unknowns}")
-        exit(1)
+        sys.exit(1)
 
     verbosity = args.verbosity
     set_verbosity(verbosity)
@@ -46,21 +46,20 @@ def cli(argv: Sequence[str] = sys.argv) -> None:
         if isinstance(output_dir, list):
             output_dir = output_dir[0]
         convert(schema, output_dir, repo, branch)
-        exit(0)
+        sys.exit(0)
 
     if args.command in ["update"]:
         schema = args.schema[0]
         download_spreadsheet(schema=schema)
-        exit(0)
+        sys.exit(0)
 
     if args.command in ["serve"]:
         folder = args.folder if args.folder is None else args.folder[0]
         serve(folder=folder)
-        exit(0)
+        sys.exit(0)
 
 
 def convert(schema: str, output_dir: str, repo: str, branch: str) -> None:
-
     logger.debug(f"{schema=}, {output_dir=}, {repo=}, {branch=}")
 
     spreadsheets_info = get_spreadsheets_info()
@@ -69,7 +68,7 @@ def convert(schema: str, output_dir: str, repo: str, branch: str) -> None:
 
     if not schema_list:
         logger.error(
-            f"No known schema for: {schema=}" f"Known schemas are: {list(spreadsheets_info.keys())}"
+            f"No known schema for: {schema=}Known schemas are: {list(spreadsheets_info.keys())}"
         )
 
     for this_schema in schema_list:

ecobidas/cli.py

@@ -1,5 +1,4 @@
 import math
-import os
 from pathlib import Path
 
 import pandas as pd
@@ -59,8 +58,8 @@ def create_schema(
     if debug:
         activities = [1]
 
-    for i, activity_idx in enumerate(activities):
-        this_activity = df["activity_order"] == activities[i]
+    for activity_idx in activities:
+        this_activity = df["activity_order"] == activity_idx
         items = df[this_activity]
         included_items = items["include"] == 1
         items = items[included_items]
@@ -85,14 +84,14 @@ def create_schema(
 
             item_info = get_item_info(this_item)
 
-            if "message" in item_info and item_info["message"]:
+            if item_info.get("message"):
                 activity.messages.append(item_info["message"])
 
-            print_item_info(activity_idx, item_idx, item_info)
+            print_item_info(str(activity_idx), item_idx, item_info)
 
             item = define_new_item(item_info)
 
-            item.write(os.path.join(activity_path, "items"))
+            item.write(Path(activity_path) / "items")
 
             activity.append_item(item)
 
@@ -150,7 +149,7 @@ def initialize_activity(items: pd.DataFrame, output_dir: str | Path) -> tuple[Ac
 
 
 def get_activity_preamble(items: pd.DataFrame) -> str:
-    if "preamble" not in items.keys():
+    if "preamble" not in items:
         return ""
 
     not_nan = items["preamble"].notna()
@@ -182,7 +181,7 @@ def create_response_options(
     print_info(
         "response options",
         schema_info["basename"],
-        os.path.join(output_dir, response_options.at_id),
+        str(Path(output_dir) / response_options.at_id),
     )
 
 
@@ -197,12 +196,12 @@ def make_preamble(schema_info: dict[str, str], items: pd.DataFrame) -> str:
     if not preamble:
         return preamble
 
-    info = dict(
-        preamble=preamble,
-        xls=schema_info["link"],
-        repo="",
-        citation="",
-    )
+    info = {
+        "preamble": preamble,
+        "xls": schema_info["link"],
+        "repo": "",
+        "citation": "",
+    }
 
     if schema_info["repo"]:
         info["repo"] = schema_info["repo"]

ecobidas/create_schema.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 """Download the content of the different google spreadsheet in the inputs folder."""
+
 import ast
 import json
 from pathlib import Path
@@ -12,8 +13,7 @@
 
 
 # Function to download spreadsheet
-def download_spreadsheet(schema: str, output_dir: Path = None) -> None:
-
+def download_spreadsheet(schema: str, output_dir: Path | None = None) -> None:
     if output_dir is None:
         output_dir = get_input_dir()
 
@@ -33,7 +33,6 @@ def download_spreadsheet(schema: str, output_dir: Path = None) -> None:
 
     # Iterate through entries and download spreadsheets
     for google_id, subfolder, output_filename in zip(google_ids, subfolders, output_filenames):
-
         output_folder = output_dir / subfolder
         output_folder.mkdir(exist_ok=True, parents=True)
         output_file = output_folder / f"{output_filename}.tsv"
@@ -48,7 +47,7 @@ def download_spreadsheet(schema: str, output_dir: Path = None) -> None:
             f"https://docs.google.com/spreadsheets/d/{google_id}/export?format=tsv"
         )
         if response.status_code == 200:
-            with open(output_file, "wb") as tsv_file:
+            with output_file.open("wb") as tsv_file:
                 tsv_file.write(response.content)
         else:
             logger.error("Error downloading the spreadsheet.")
@@ -69,7 +68,7 @@ def validate_downloaded_file(file: str | Path) -> None:
     df = pd.read_csv(file, sep="\t")
 
     data_dictionary_file = get_input_dir() / "data-dictionary.json"
-    with open(data_dictionary_file) as f:
+    with data_dictionary_file.open() as f:
         data_dictionary = json.load(f)
 
     columns = {x for x in df.columns if "Unnamed:" not in x}
@@ -96,11 +95,8 @@ def validate_downloaded_file(file: str | Path) -> None:
             f"\nThe following columns are missing from the data dictionary: {sorted(extra_columns)}"
         )
 
-    invalid_vis = []
-    visibility = df.visibility.values
-    for vis in visibility:
-        if not is_valid_python(vis):
-            invalid_vis.append(vis)
+    visibility = df.visibility.to_numpy()
+    invalid_vis = [vis for vis in visibility if not is_valid_python(vis)]
     if invalid_vis:
         logger.warning(f"\nThe following visibility are not valid python:\n{invalid_vis}")
 

ecobidas/download_tsv.py

@@ -8,11 +8,11 @@
 
 
 def set_item_name(this_item: dict) -> str:
-    if "item" not in this_item.keys():
-        item_name = convert_to_str(this_item["item_pref_label"])
-    elif isinstance(convert_to_str(this_item["item"]), float):
-        item_name = convert_to_str(this_item["item_pref_label"])
-    elif convert_to_str(this_item["item"]) == "":
+    if (
+        "item" not in this_item
+        or isinstance(convert_to_str(this_item["item"]), float)
+        or convert_to_str(this_item["item"]) == ""
+    ):
         item_name = convert_to_str(this_item["item_pref_label"])
     else:
         item_name = convert_to_str(this_item["item"])

ecobidas/item.py

@@ -28,23 +28,23 @@ def main(output_dir: Path | None = None) -> None:
         output_dir = Path() / "output"
     output_dir.mkdir(exist_ok=True, parents=True)
 
-    with open(output_dir / "preset_responses_table.md", "w") as out:
+    with (output_dir / "preset_responses_table.md").open("w") as out:
         out.write(f"{table_preset_responses()}")
 
-    with open(output_dir / "apps_table.md", "w") as out:
+    with (output_dir / "apps_table.md").open("w") as out:
         out.write(f"{table_apps()}")
 
-    with open(output_dir / "spreadsheets_table.md", "w") as out:
+    with (output_dir / "spreadsheets_table.md").open("w") as out:
         out.write(f"{table_spreadsheets()}")
 
-    with open(output_dir / "data_dictionary_table.md", "w") as out:
+    with (output_dir / "data_dictionary_table.md").open("w") as out:
         out.write(f"{table_data_dictionary()}")
 
 
 def table_data_dictionary() -> str:
     """Create markdown table for list of apps."""
     data_dictionary_file = get_input_dir() / "data-dictionary.json"
-    with open(data_dictionary_file) as f:
+    with data_dictionary_file.open() as f:
         data_dictionary = list(json.load(f).values())
     data_dictionary = sorted(data_dictionary, key=itemgetter("VariableName"))
     for i, _ in enumerate(data_dictionary):
@@ -74,9 +74,9 @@ def table_spreadsheets() -> str:
     for i, value in enumerate(sheets):
         if "meeg" in value["dir"]:
             continue
-        sheets[i][
-            "preview"
-        ] = f"{PREVIEW_BASE}{BASE_RAW_URL}/{value['dir']}/activities/{value['basename']}/{value['basename']}_schema.jsonld"
+        sheets[i]["preview"] = (
+            f"{PREVIEW_BASE}{BASE_RAW_URL}/{value['dir']}/activities/{value['basename']}/{value['basename']}_schema.jsonld"
+        )
 
     TemplateManager.initialize()
     template = TemplateManager.env.get_template("spreadsheet_table.j2")
@@ -86,7 +86,7 @@ def table_spreadsheets() -> str:
 def table_apps() -> str:
     """Create markdown table for spreadsheets that are not apps or preset responses."""
     spreadsheets_info = get_spreadsheets_info()
-    apps = [value for key, value in spreadsheets_info.items() if spreadsheets_info[key]["app_link"]]
+    apps = [value for key, value in spreadsheets_info.items() if value["app_link"]]
     apps = sorted(apps, key=itemgetter("basename"))
 
     TemplateManager.initialize()

ecobidas/macros.py

@@ -32,7 +32,7 @@ def get_output_dir(this_schema: str | Path, output_dir: str | Path) -> Path:
 @lru_cache
 def get_spreadsheets_info() -> dict[str, dict[str, str]]:
     """Load info about all the spreadsheets."""
-    with open(get_input_dir() / "spreadsheet_google_id.yml") as f:
+    with (get_input_dir() / "spreadsheet_google_id.yml").open() as f:
         spreadsheets_info = yaml.load(f)
 
     for key in spreadsheets_info:
@@ -87,7 +87,7 @@ def load_data(this_schema: str) -> pd.DataFrame:
         schema_info = get_schema_info(this_schema)
         input_file = get_input_file(schema_info)
 
-    logger.info(f"\nLoading: {str(input_file)}\n")
+    logger.info(f"\nLoading: {input_file!s}\n")
 
     return pd.read_csv(input_file, sep="\t")
 
@@ -112,7 +112,9 @@ def print_info(type: str, pref_label: str, file: str) -> None:
 
 def print_item_info(activity_idx: str, item_idx: str, item_info: dict[str, str]) -> None:
     logger.debug(
-        f"Activity: {int(activity_idx)} Item: {int(item_idx)}\t{item_info['name']}\t{item_info['field_type']}\t{item_info['visibility']}"
+        f"Activity: {int(activity_idx)} "
+        f"Item: {int(item_idx)}\t{item_info['name']}"
+        f"\t{item_info['field_type']}\t{item_info['visibility']}"
     )
 
 

ecobidas/utils.py

@@ -10,7 +10,7 @@
 __all__ = [
     "define_env",
     "table_apps",
+    "table_data_dictionary",
     "table_preset_responses",
     "table_spreadsheets",
-    "table_data_dictionary",
 ]