Files
graphify/graphify/cache.py
T
Safi 01fb51ba78 Fix 9 issues: kiro package data, betweenness perf, wiki step, opencode plugin, cache root, PHP missing edges, Windows stability, cross-file calls
- #352: add skill-kiro.md to pyproject.toml package-data
- #341: guard edge_betweenness at >5000 nodes; use approximate k=100 for suggest_questions on large graphs
- #354/#229: add Step 6b in skill.md to call to_wiki() when --wiki given (before Step 9 cleanup)
- #356: call _install_opencode_plugin() from install --platform opencode path
- #350: add cache_root param to extract() so subdirectory runs keep cache at ./graphify-out/cache/
- #230: PHP class_constant_access_expression emits references_constant edges
- #232: PHP scoped_call_expression (static method calls) emits calls edges
- #287: os.replace fallback for Windows WinError 5; graphify update exits 1 on failure; templates use graphify update . instead of python3 -c
- #348: cross-file call resolution for all languages via raw_calls + global label map pass in extract()

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-15 00:26:11 +01:00

170 lines
5.4 KiB
Python

# per-file extraction cache - skip unchanged files on re-run
from __future__ import annotations
import hashlib
import json
import os
from pathlib import Path
def _body_content(content: bytes) -> bytes:
"""Strip YAML frontmatter from Markdown content, returning only the body."""
text = content.decode(errors="replace")
if text.startswith("---"):
end = text.find("\n---", 3)
if end != -1:
return text[end + 4:].encode()
return content
def file_hash(path: Path, root: Path = Path(".")) -> str:
"""SHA256 of file contents + path relative to root.
Using a relative path (not absolute) makes cache entries portable across
machines and checkout directories, so shared caches and CI work correctly.
Falls back to the resolved absolute path if the file is outside root.
For Markdown files (.md), only the body below the YAML frontmatter is hashed,
so metadata-only changes (e.g. reviewed, status, tags) do not invalidate the cache.
"""
p = Path(path)
raw = p.read_bytes()
content = _body_content(raw) if p.suffix.lower() == ".md" else raw
h = hashlib.sha256()
h.update(content)
h.update(b"\x00")
try:
rel = p.resolve().relative_to(Path(root).resolve())
h.update(str(rel).encode())
except ValueError:
h.update(str(p.resolve()).encode())
return h.hexdigest()
def cache_dir(root: Path = Path(".")) -> Path:
"""Returns graphify-out/cache/ - creates it if needed."""
d = Path(root) / "graphify-out" / "cache"
d.mkdir(parents=True, exist_ok=True)
return d
def load_cached(path: Path, root: Path = Path(".")) -> dict | None:
"""Return cached extraction for this file if hash matches, else None.
Cache key: SHA256 of file contents.
Cache value: stored as graphify-out/cache/{hash}.json
Returns None if no cache entry or file has changed.
"""
try:
h = file_hash(path, root)
except OSError:
return None
entry = cache_dir(root) / f"{h}.json"
if not entry.exists():
return None
try:
return json.loads(entry.read_text(encoding="utf-8"))
except (json.JSONDecodeError, OSError):
return None
def save_cached(path: Path, result: dict, root: Path = Path(".")) -> None:
"""Save extraction result for this file.
Stores as graphify-out/cache/{hash}.json where hash = SHA256 of current file contents.
result should be a dict with 'nodes' and 'edges' lists.
"""
h = file_hash(path, root)
entry = cache_dir(root) / f"{h}.json"
tmp = entry.with_suffix(".tmp")
try:
tmp.write_text(json.dumps(result), encoding="utf-8")
try:
os.replace(tmp, entry)
except PermissionError:
# Windows: os.replace can fail with WinError 5 if the target is
# briefly locked. Fall back to copy-then-delete.
import shutil
shutil.copy2(tmp, entry)
tmp.unlink(missing_ok=True)
except Exception:
tmp.unlink(missing_ok=True)
raise
def cached_files(root: Path = Path(".")) -> set[str]:
"""Return set of file paths that have a valid cache entry (hash still matches)."""
d = cache_dir(root)
return {p.stem for p in d.glob("*.json")}
def clear_cache(root: Path = Path(".")) -> None:
"""Delete all graphify-out/cache/*.json files."""
d = cache_dir(root)
for f in d.glob("*.json"):
f.unlink()
def check_semantic_cache(
files: list[str],
root: Path = Path("."),
) -> tuple[list[dict], list[dict], list[dict], list[str]]:
"""Check semantic extraction cache for a list of absolute file paths.
Returns (cached_nodes, cached_edges, cached_hyperedges, uncached_files).
Uncached files need Claude extraction; cached files are merged directly.
"""
cached_nodes: list[dict] = []
cached_edges: list[dict] = []
cached_hyperedges: list[dict] = []
uncached: list[str] = []
for fpath in files:
result = load_cached(Path(fpath), root)
if result is not None:
cached_nodes.extend(result.get("nodes", []))
cached_edges.extend(result.get("edges", []))
cached_hyperedges.extend(result.get("hyperedges", []))
else:
uncached.append(fpath)
return cached_nodes, cached_edges, cached_hyperedges, uncached
def save_semantic_cache(
nodes: list[dict],
edges: list[dict],
hyperedges: list[dict] | None = None,
root: Path = Path("."),
) -> int:
"""Save semantic extraction results to cache, keyed by source_file.
Groups nodes and edges by source_file, then saves one cache entry per file.
Returns the number of files cached.
"""
from collections import defaultdict
by_file: dict[str, dict] = defaultdict(lambda: {"nodes": [], "edges": [], "hyperedges": []})
for n in nodes:
src = n.get("source_file", "")
if src:
by_file[src]["nodes"].append(n)
for e in edges:
src = e.get("source_file", "")
if src:
by_file[src]["edges"].append(e)
for h in (hyperedges or []):
src = h.get("source_file", "")
if src:
by_file[src]["hyperedges"].append(h)
saved = 0
for fpath, result in by_file.items():
p = Path(fpath)
if not p.is_absolute():
p = Path(root) / p
if p.exists():
save_cached(p, result, root)
saved += 1
return saved