coulomb/markitect-main
4
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(schema): add semantic schema generation as default mode

Browse source 
schema-generate now builds content-aware schemas from the document's
section hierarchy instead of counting markdown syntax elements. Detects
key-value tables, data tables, link lists, and mixed content patterns
to produce schemas that reflect the actual document outline.

Old behavior preserved via --mode syntactic. Validator and visualization
tools pinned to syntactic mode for compatibility.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
tegwick 2026-02-16 18:49:50 +01:00
parent 120ed89780
commit 60f33443ae
8 changed files with 408 additions and 55 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/test_issue_51_outline_mode.py
View file

@ -290,7 +290,7 @@ This is a test document.
output_file.unlink()
def test_cli_maintains_backward_compatibility_with_max_depth(self):
"""Test that existing --max-depth option still works with default mode."""
"""Test that existing --max-depth option still works with default (semantic) mode."""
# Arrange
markdown_content = """# Test Document
@ -317,9 +317,9 @@ Some details here.
assert result.exit_code == 0, f"CLI should maintain backward compatibility with --max-depth, got: {result.output}"
schema = json.loads(result.output)
# Should use old title format for backward compatibility
expected_title = f"Schema for {temp_file.name}"
assert schema["title"] == expected_title, f"Default mode should use 'for' in title"
# Default mode is now semantic, which uses 'from' in title
expected_title = f"Schema from {temp_file.name}"
assert schema["title"] == expected_title, f"Default (semantic) mode should use 'from' in title"
finally:
temp_file.unlink()

12
tests/test_issue_5_schema_generation.py
View file

@ -50,8 +50,8 @@ Some text here.
temp_file = Path(f.name)
try:
# Act - Generate schema with unlimited depth
result = self.schema_generator.generate_schema_from_file(temp_file)
# Act - Generate schema in syntactic mode (element counting)
result = self.schema_generator.generate_schema_from_file(temp_file, mode='syntactic')
# Assert - Schema should be valid JSON and contain expected structure
assert isinstance(result, dict)
@ -105,8 +105,8 @@ Very deep content.
temp_file = Path(f.name)
try:
# Act - Generate schema with depth limit of 2
result = self.schema_generator.generate_schema_from_file(temp_file, max_depth=2)
# Act - Generate schema in syntactic mode with depth limit of 2
result = self.schema_generator.generate_schema_from_file(temp_file, max_depth=2, mode='syntactic')
# Assert - Only levels 1 and 2 should be included
properties = result.get("properties", {})
@ -173,8 +173,8 @@ Some implementation notes here.
temp_file = Path(f.name)
try:
# Act - Generate schema
result = self.schema_generator.generate_schema_from_file(temp_file)
# Act - Generate schema in syntactic mode
result = self.schema_generator.generate_schema_from_file(temp_file, mode='syntactic')
# Assert - Schema should capture complex structures
properties = result.get("properties", {})

12
tests/test_l4_service_schema_generation.py
View file

@ -47,8 +47,8 @@ Some text here.
temp_file = Path(f.name)
try:
# Act - Generate schema with unlimited depth
result = self.schema_generator.generate_schema_from_file(temp_file)
# Act - Generate schema in syntactic mode (element counting)
result = self.schema_generator.generate_schema_from_file(temp_file, mode='syntactic')
# Assert - Schema should be valid JSON and contain expected structure
assert isinstance(result, dict)
@ -104,8 +104,8 @@ Very deep content.
temp_file = Path(f.name)
try:
# Act - Generate schema with depth limit of 2
result = self.schema_generator.generate_schema_from_file(temp_file, max_depth=2)
# Act - Generate schema in syntactic mode with depth limit of 2
result = self.schema_generator.generate_schema_from_file(temp_file, max_depth=2, mode='syntactic')
# Assert - Only levels 1 and 2 should be included
properties = result.get("properties", {})
@ -238,8 +238,8 @@ def api_function():
temp_file = Path(f.name)
try:
# Act - Generate schema
result = self.schema_generator.generate_schema_from_file(temp_file)
# Act - Generate schema in syntactic mode
result = self.schema_generator.generate_schema_from_file(temp_file, mode='syntactic')
# Assert - Should capture comprehensive structure
properties = result.get("properties", {})