ci: pre-commit checks

.github/workflows/code-checks.yaml

@@ -0,0 +1,18 @@
+name: Code Checks
+
+on:
+  workflow_dispatch:
+  push:
+    branches: ['main', 'dev-*']
+  pull_request:
+  release:
+    types: [published]
+
+jobs:
+  pre-commit:
+    name: "Run pre-commit"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+      - uses: pre-commit/[email protected]

.pre-commit-config.yaml

@@ -0,0 +1,22 @@
+exclude: "(.*\\.svg)|(.*\\.qmd)|(.*\\.ambr)|(.*\\.csv)|(.*\\.txt)"
+repos:
+  - repo: https://github.com/pycqa/flake8
+    rev: 6.0.0
+    hooks:
+      - id: flake8
+        types:
+          - python
+        additional_dependencies:
+          - flake8-pyproject
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.4.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+        args: ["--unsafe"]
+      - id: check-added-large-files
+  - repo: https://github.com/psf/black
+    rev: 23.11.0
+    hooks:
+      - id: black

.vscode/launch.json

@@ -13,4 +13,4 @@
             "justMyCode": true
         }
     ]
-}
+}

great_tables/_formats.py

@@ -1869,7 +1869,7 @@ def _value_to_decimal_notation(
         result = result.rstrip(dec_mark)
 
     # Add in a trailing decimal mark under specific circumstances
-    if drop_trailing_dec_mark is False and not dec_mark in result:
+    if drop_trailing_dec_mark is False and dec_mark not in result:
         result = result + dec_mark
 
     # Force the positive sign to be present if the `force_sign` option is taken
@@ -1957,7 +1957,7 @@ def _format_number_n_sigfig(
     formatted_integer = ""
     formatted_decimal = dec_mark + decimal_part if decimal_part else ""
 
-    if preserve_integer and not "." in formatted_value:
+    if preserve_integer and "." not in formatted_value:
         formatted_value = "{:0.0f}".format(value)
 
     # Insert grouping separators within the integer part
@@ -2833,7 +2833,7 @@ def _validate_date_style(date_style: str) -> None:
     Returns:
         None
     """
-    if not date_style in _get_date_formats_dict():
+    if date_style not in _get_date_formats_dict():
         raise ValueError(f"date_style must be one of: {', '.join(_get_date_formats_dict().keys())}")
 
     return
@@ -2852,7 +2852,7 @@ def _validate_time_style(time_style: str) -> None:
     Returns:
         None
     """
-    if not time_style in _get_time_formats_dict():
+    if time_style not in _get_time_formats_dict():
         raise ValueError(f"time_style must be one of: {', '.join(_get_time_formats_dict().keys())}")
 
     return

great_tables/_gt_data.py

@@ -144,7 +144,7 @@ class Body:
     def __init__(self, body: Union[pd.DataFrame, TblData]):
         self.body = body
 
-    def render_formats(self, data_tbl: TblData, formats: List[FormatInfo], context: Context):
+    def render_formats(self, data_tbl: TblData, formats: List[FormatInfo], context: Any):
         for fmt in formats:
             eval_func = getattr(fmt.func, context, fmt.func.default)
             if eval_func is None:

great_tables/_utils.py

@@ -84,7 +84,7 @@ def _as_css_font_family_attr(fonts: List[str], value_only: bool = False) -> str:
 def _object_as_dict(v: Any) -> Any:
     try:
         return v.object_as_dict()
-    except:
+    except Exception:
         pass
     if type(v) == pd.DataFrame:
         return v.to_dict()

great_tables/_utils_render_html.py

@@ -328,17 +328,20 @@ def create_columns_component_h(data: GTData) -> str:
             table_col_headings = tags.tr(level_1_spanners, class_="gt_col_headings gt_spanner_row")
 
     if _get_spanners_matrix_height(data=data) > 2:
-        higher_spanner_rows_idx = seq_len(nrow(spanner_ids) - 2)
+        # TODO: functions like seq_len don't exist
+        higher_spanner_rows_idx = seq_len(nrow(spanner_ids) - 2)  # noqa
 
         higher_spanner_rows = TagList()
 
         for i in higher_spanner_rows_idx:
             spanner_ids_row = spanner_ids[i]
             spanners_row = spanners[i]
-            spanners_vars = list(set(spanner_ids_row[~np.isnan(spanner_ids_row)].tolist()))
+            # TODO: shouldn't use np here
+            spanners_vars = list(set(spanner_ids_row[~np.isnan(spanner_ids_row)].tolist()))  # noqa
 
             # Replace NA values in spanner_ids_row with an empty string
-            spanner_ids_row[np.isnan(spanner_ids_row)] = ""
+            # TODO: shouldn't use np here
+            spanner_ids_row[np.isnan(spanner_ids_row)] = ""  # noqa
 
             spanners_rle = [(k, len(list(g))) for k, g in groupby(list(spanner_ids_row))]
 
@@ -490,7 +493,7 @@ def create_body_component_h(data: GTData) -> str:
                 cell_styles = ""
 
             if is_stub_cell:
-                body_cells.append(f'  <th class="gt_row gt_left gt_stub">' + cell_str + "</th>")
+                body_cells.append('  <th class="gt_row gt_left gt_stub">' + cell_str + "</th>")
             else:
                 body_cells.append(
                     f'  <td {cell_styles}class="gt_row gt_{cell_alignment}">' + cell_str + "</td>"

pyproject.toml

@@ -66,7 +66,19 @@ dev = [
 ]
 
 [tool.flake8]
-exclude = ["docs", ".venv"]
+exclude = ["docs", ".venv", "tests/*"]
+
+ignore = [
+    "E402",    # module level import not at top of file
+    "E501",    # line too long (maximum 100 characters)
+    "W503",    # line break before binary operator
+    "F811",    # redefinition of unused name
+    "E203",    # whitespace before ':'
+    "F401",    # 'module' imported but unused
+    "F841",    # local variable 'name' is assigned to but never used
+]
+
+max-line-length = 100
 
 [tool.pytest.ini_options]
 minversion = "6.0"
@@ -75,5 +87,6 @@ asyncio_mode = "strict"
 testpaths = [
     "tests"
 ]
+
 [tool.black]
 line-length = 100