mirror of
https://github.com/safishamsi/graphify.git
synced 2026-07-17 12:57:18 +00:00
Safi
a78d25d4fc
- Add Objective-C extractor (.m/.mm) with @interface, @implementation, @protocol, imports, calls - Add C# inheritance extraction via base_list nodes (inherits edges) - Add --obsidian-dir flag to skill.md and skill-windows.md - Add graphify query CLI command with --dfs, --budget, --graph flags - Add follow_symlinks parameter to detect() and collect_files() with cycle detection - Fix semantic cache relative path resolution (was saving only 4/17 files) - Fix validate.py missing rationale file_type causing 75 warnings per run - Add tree-sitter-objc dependency - Update README with .m/.mm extensions, --obsidian-dir usage, Codex $ skill trigger - 367 tests passing Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
72 lines
3.1 KiB
Python
72 lines
3.1 KiB
Python
# validate extraction JSON against the graphify schema before graph assembly
|
|
from __future__ import annotations
|
|
|
|
VALID_FILE_TYPES = {"code", "document", "paper", "image", "rationale"}
|
|
VALID_CONFIDENCES = {"EXTRACTED", "INFERRED", "AMBIGUOUS"}
|
|
REQUIRED_NODE_FIELDS = {"id", "label", "file_type", "source_file"}
|
|
REQUIRED_EDGE_FIELDS = {"source", "target", "relation", "confidence", "source_file"}
|
|
|
|
|
|
def validate_extraction(data: dict) -> list[str]:
|
|
"""
|
|
Validate an extraction JSON dict against the graphify schema.
|
|
Returns a list of error strings - empty list means valid.
|
|
"""
|
|
if not isinstance(data, dict):
|
|
return ["Extraction must be a JSON object"]
|
|
|
|
errors: list[str] = []
|
|
|
|
# Nodes
|
|
if "nodes" not in data:
|
|
errors.append("Missing required key 'nodes'")
|
|
elif not isinstance(data["nodes"], list):
|
|
errors.append("'nodes' must be a list")
|
|
else:
|
|
for i, node in enumerate(data["nodes"]):
|
|
if not isinstance(node, dict):
|
|
errors.append(f"Node {i} must be an object")
|
|
continue
|
|
for field in REQUIRED_NODE_FIELDS:
|
|
if field not in node:
|
|
errors.append(f"Node {i} (id={node.get('id', '?')!r}) missing required field '{field}'")
|
|
if "file_type" in node and node["file_type"] not in VALID_FILE_TYPES:
|
|
errors.append(
|
|
f"Node {i} (id={node.get('id', '?')!r}) has invalid file_type "
|
|
f"'{node['file_type']}' - must be one of {sorted(VALID_FILE_TYPES)}"
|
|
)
|
|
|
|
# Edges
|
|
if "edges" not in data:
|
|
errors.append("Missing required key 'edges'")
|
|
elif not isinstance(data["edges"], list):
|
|
errors.append("'edges' must be a list")
|
|
else:
|
|
node_ids = {n["id"] for n in data.get("nodes", []) if isinstance(n, dict) and "id" in n}
|
|
for i, edge in enumerate(data["edges"]):
|
|
if not isinstance(edge, dict):
|
|
errors.append(f"Edge {i} must be an object")
|
|
continue
|
|
for field in REQUIRED_EDGE_FIELDS:
|
|
if field not in edge:
|
|
errors.append(f"Edge {i} missing required field '{field}'")
|
|
if "confidence" in edge and edge["confidence"] not in VALID_CONFIDENCES:
|
|
errors.append(
|
|
f"Edge {i} has invalid confidence '{edge['confidence']}' "
|
|
f"- must be one of {sorted(VALID_CONFIDENCES)}"
|
|
)
|
|
if "source" in edge and node_ids and edge["source"] not in node_ids:
|
|
errors.append(f"Edge {i} source '{edge['source']}' does not match any node id")
|
|
if "target" in edge and node_ids and edge["target"] not in node_ids:
|
|
errors.append(f"Edge {i} target '{edge['target']}' does not match any node id")
|
|
|
|
return errors
|
|
|
|
|
|
def assert_valid(data: dict) -> None:
|
|
"""Raise ValueError with all errors if extraction is invalid."""
|
|
errors = validate_extraction(data)
|
|
if errors:
|
|
msg = f"Extraction JSON has {len(errors)} error(s):\n" + "\n".join(f" • {e}" for e in errors)
|
|
raise ValueError(msg)
|