Add Python and YAML linting to CI pipeline

.github/workflows/test.yml

@@ -28,6 +28,15 @@ jobs:
       - name: Install dependencies
         run: uv sync --dev
 
+      - name: Lint Python code with Ruff
+        run: uv run ruff check .
+
+      - name: Check Python formatting with Ruff
+        run: uv run ruff format --check .
+
+      - name: Lint YAML files
+        run: uv run yamllint .
+
       - name: Run unit tests
         run: uv run pytest tests/ -v --cov=scripts --cov-report=term-missing
 

.yamllint

@@ -0,0 +1,38 @@
+---
+# yamllint configuration for named-functions project
+# Validates both formula YAMLs and GitHub workflow YAMLs
+
+extends: default
+
+rules:
+  # Line length - allow long lines for formulas
+  line-length:
+    max: 120
+    level: warning
+
+  # Indentation - 2 spaces (GitHub Actions standard)
+  indentation:
+    spaces: 2
+    indent-sequences: true
+
+  # Allow inline mappings (common in GitHub Actions)
+  braces:
+    min-spaces-inside: 0
+    max-spaces-inside: 1
+
+  # Document start (---) not required
+  document-start: disable
+
+  # Allow truthy values (yes/no, on/off) in GitHub Actions
+  truthy:
+    allowed-values: ['true', 'false', 'yes', 'no', 'on', 'off']
+    check-keys: false
+
+  # Comments - allow reasonable comment formatting
+  comments:
+    min-spaces-from-content: 1
+
+  # Allow empty values (common in formulas)
+  empty-values:
+    forbid-in-block-mappings: false
+    forbid-in-flow-mappings: false

README.md

@@ -2332,22 +2332,22 @@ v1.0.2 Transforms wide-format data into long-format (tidy data) by unpivoting sp
   ac, IF(OR(attributecol = "", ISBLANK(attributecol)), "Attribute", attributecol),
   vc, IF(OR(valuecol = "", ISBLANK(valuecol)), "Value", valuecol),
   fillna_val, (MAP(fillna, LAMBDA(v, IF(ISBLANK(v), "", v)))),
-  
+
   num_rows, ROWS(data),
   num_cols, COLUMNS(data),
-  
+
   _validate_dims, IF(OR(num_rows < 2, num_cols < 2),
     (XLOOKUP("Data must have at least 2 rows and 2 columns", IF(FALSE, {1}), IF(FALSE, {1}))),
     TRUE
   ),
-  
+
   _validate_fc, IF(OR(fc < 1, fc >= num_cols),
     (XLOOKUP("fixedcols must be between 1 and " & (num_cols - 1), IF(FALSE, {1}), IF(FALSE, {1}))),
     TRUE
   ),
-  
+
   all_headers, INDEX(data, 1, SEQUENCE(1, num_cols)),
-  
+
   selected_cols, IF(OR(select_columns = "", ISBLANK(select_columns)),
     SEQUENCE(1, num_cols - fc, fc + 1),
     IF(ISTEXT(INDEX(select_columns, 1, 1)),
@@ -2379,39 +2379,39 @@ v1.0.2 Transforms wide-format data into long-format (tidy data) by unpivoting sp
       )
     )
   ),
-  
+
   ncols, COLUMNS(selected_cols),
   nrows, num_rows - 1,
   total_output, nrows * ncols,
-  
+
   unpivoted, MAKEARRAY(total_output, fc + 2, LAMBDA(r, c,
     LET(
       source_row, INT((r - 1) / ncols) + 2,
       col_idx, MOD(r - 1, ncols) + 1,
       value_col_num, INDEX(selected_cols, 1, col_idx),
-      
+
       cell_value, IF(c <= fc,
         INDEX(data, source_row, c),
         IF(c = fc + 1,
           INDEX(data, 1, value_col_num),
           INDEX(data, source_row, value_col_num)
         )
       ),
-      
+
       IF(AND(c = fc + 2, cell_value = "", fillna_val <> ""),
         fillna_val,
         cell_value
       )
     )
   )),
-  
+
   output_headers, MAKEARRAY(1, fc + 2, LAMBDA(r, c,
     IF(c <= fc,
       INDEX(data, 1, c),
       IF(c = fc + 1, ac, vc)
     )
   )),
-  
+
   VSTACK(output_headers, unpivoted)
 )
 ```

formulas/unpivot.yaml

@@ -41,22 +41,22 @@ formula: |
     ac, IF(OR(attributecol = "", ISBLANK(attributecol)), "Attribute", attributecol),
     vc, IF(OR(valuecol = "", ISBLANK(valuecol)), "Value", valuecol),
     fillna_val, BLANKTOEMPTY(fillna),
-    
+
     num_rows, ROWS(data),
     num_cols, COLUMNS(data),
-    
+
     _validate_dims, IF(OR(num_rows < 2, num_cols < 2),
       ERROR("Data must have at least 2 rows and 2 columns"),
       TRUE
     ),
-    
+
     _validate_fc, IF(OR(fc < 1, fc >= num_cols),
       ERROR("fixedcols must be between 1 and " & (num_cols - 1)),
       TRUE
     ),
-    
+
     all_headers, INDEX(data, 1, SEQUENCE(1, num_cols)),
-    
+
     selected_cols, IF(OR(select_columns = "", ISBLANK(select_columns)),
       SEQUENCE(1, num_cols - fc, fc + 1),
       IF(ISTEXT(INDEX(select_columns, 1, 1)),
@@ -88,38 +88,38 @@ formula: |
         )
       )
     ),
-    
+
     ncols, COLUMNS(selected_cols),
     nrows, num_rows - 1,
     total_output, nrows * ncols,
-    
+
     unpivoted, MAKEARRAY(total_output, fc + 2, LAMBDA(r, c,
       LET(
         source_row, INT((r - 1) / ncols) + 2,
         col_idx, MOD(r - 1, ncols) + 1,
         value_col_num, INDEX(selected_cols, 1, col_idx),
-        
+
         cell_value, IF(c <= fc,
           INDEX(data, source_row, c),
           IF(c = fc + 1,
             INDEX(data, 1, value_col_num),
             INDEX(data, source_row, value_col_num)
           )
         ),
-        
+
         IF(AND(c = fc + 2, cell_value = "", fillna_val <> ""),
           fillna_val,
           cell_value
         )
       )
     )),
-    
+
     output_headers, MAKEARRAY(1, fc + 2, LAMBDA(r, c,
       IF(c <= fc,
         INDEX(data, 1, c),
         IF(c = fc + 1, ac, vc)
       )
     )),
-    
+
     VSTACK(output_headers, unpivoted)
   )

pyproject.toml

@@ -13,6 +13,8 @@ dependencies = [
 dev = [
     "pytest>=7.0",
     "pytest-cov>=4.0",
+    "ruff>=0.8.0",
+    "yamllint>=1.35.0",
 ]
 
 [build-system]
@@ -39,3 +41,60 @@ markers = [
     "integration: Integration tests for complete workflows",
     "slow: Tests that take significant time to run",
 ]
+
+[tool.ruff]
+# Line length to match common Python standards
+line-length = 100
+
+# Target Python 3.8+ (matching project requirements)
+target-version = "py38"
+
+# Exclude common directories
+exclude = [
+    ".git",
+    ".pytest_cache",
+    "__pycache__",
+    "*.egg-info",
+]
+
+[tool.ruff.lint]
+# Enable recommended rulesets
+select = [
+    "E",      # pycodestyle errors
+    "W",      # pycodestyle warnings
+    "F",      # pyflakes
+    "I",      # isort (import sorting)
+    "N",      # pep8-naming
+    "UP",     # pyupgrade (modern Python syntax)
+    "B",      # flake8-bugbear (common bugs)
+    "C4",     # flake8-comprehensions
+    "SIM",    # flake8-simplify
+    "RET",    # flake8-return
+]
+
+# Disable specific rules that conflict with project style
+ignore = [
+    "E501",   # Line too long (handled by formatter)
+    "RET504", # Unnecessary variable assignment before return (sometimes clearer)
+    "SIM108", # Use ternary operator (sometimes if/else is clearer)
+]
+
+# Allow auto-fixing for safe rules
+fixable = ["ALL"]
+unfixable = []
+
+[tool.ruff.lint.isort]
+# Import sorting configuration
+known-first-party = ["scripts"]
+force-single-line = false
+lines-after-imports = 2
+
+[tool.ruff.format]
+# Use double quotes for strings
+quote-style = "double"
+
+# Indent with spaces
+indent-style = "space"
+
+# Unix-style line endings
+line-ending = "lf"