212 lines
8.3 KiB
Python
212 lines
8.3 KiB
Python
"""wiki 健檢（AGENTS.md §7）：schema 完整性、過期主張、覆蓋缺口、孤兒頁、
|
||
重複/矛盾頁偵測（LLM）。產出 markdown 報告；絕不修改或刪除任何檔案，
|
||
所有項目一律標記待人工核准。
|
||
|
||
用法：python tools/lint.py [--output reports] [--no-llm] [--root DIR]
|
||
結束碼：0 = 無發現，1 = 有發現（供 CI 判斷）。
|
||
"""
|
||
import argparse
|
||
import datetime
|
||
import difflib
|
||
import itertools
|
||
import json
|
||
import pathlib
|
||
import re
|
||
import sys
|
||
|
||
sys.path.insert(0, str(pathlib.Path(__file__).parent))
|
||
import kb
|
||
|
||
# ponytail: 過期門檻寫死 180 天（naive heuristic）；若各類頁面需要不同節奏，
|
||
# 升級路徑：依 type/tags 分級門檻。
|
||
STALE_DAYS = 180
|
||
# ponytail: LLM 逐對比較上限 15 對，避免 O(n²) 呼叫爆量；升級路徑：以 embedding
|
||
# 預篩（Phase 6 之後評估 EmbeddingGemma / snowflake-arctic-embed）。
|
||
MAX_LLM_PAIRS = 15
|
||
SIM_THRESHOLD = 0.6
|
||
|
||
PAIR_PROMPT = """判斷以下兩個 QA 知識庫 wiki 頁是否「重複」（描述同一事物，應合併）或「矛盾」（對同一事實給出不相容的主張）。只輸出 JSON：
|
||
{{"relation": "duplicate" 或 "contradiction" 或 "none", "explanation": "一句話理由（繁體中文）"}}
|
||
|
||
頁 A：{a_title} — {a_desc}
|
||
內文節錄：
|
||
<<<
|
||
{a_body}
|
||
>>>
|
||
|
||
頁 B：{b_title} — {b_desc}
|
||
內文節錄：
|
||
<<<
|
||
{b_body}
|
||
>>>"""
|
||
|
||
|
||
def validate_pair(obj):
|
||
if obj.get("relation") not in ("duplicate", "contradiction", "none"):
|
||
return "relation 須為 duplicate|contradiction|none"
|
||
if not isinstance(obj.get("explanation"), str):
|
||
return "explanation 須為字串"
|
||
return None
|
||
|
||
|
||
def load_pages(root, findings):
|
||
pages = []
|
||
for p in kb.iter_pages(root):
|
||
rel = p.relative_to(root).as_posix()
|
||
try:
|
||
meta, body = kb.parse_page(p.read_text(encoding="utf-8"))
|
||
pages.append((rel, meta, body))
|
||
except Exception as e:
|
||
findings.append(("schema", rel, f"無法解析：{e}"))
|
||
return pages
|
||
|
||
|
||
def check_schema(pages, manifest, findings):
|
||
for rel, meta, _ in pages:
|
||
for err in kb.validate_meta(meta):
|
||
findings.append(("schema", rel, err))
|
||
for s in meta.get("sources") or []:
|
||
path, _, sha8 = str(s).rpartition("#")
|
||
entry = manifest["files"].get(path)
|
||
if entry is None:
|
||
findings.append(("schema", rel, f"source_ref 不在 manifest：{s}"))
|
||
elif not entry["sha256"].startswith(sha8):
|
||
findings.append(("schema", rel, f"source_ref hash 與 manifest 不符：{s}"))
|
||
|
||
|
||
def check_stale(pages, findings):
|
||
today = datetime.date.today()
|
||
for rel, meta, _ in pages:
|
||
try:
|
||
ts = datetime.date.fromisoformat(str(meta.get("timestamp")))
|
||
except ValueError:
|
||
continue # schema 檢查已報
|
||
age = (today - ts).days
|
||
if meta.get("status") == "stale":
|
||
findings.append(("stale", rel, "已標記 stale，待人工複審或更新"))
|
||
elif age > STALE_DAYS:
|
||
findings.append(("stale", rel, f"最後更新 {age} 天前，建議人工複審後標記 stale"))
|
||
|
||
|
||
def check_coverage(pages, manifest, findings):
|
||
referenced = {str(s).rsplit("#", 1)[-1]
|
||
for _, meta, _ in pages for s in meta.get("sources") or []}
|
||
for path, e in manifest["files"].items():
|
||
if e["kind"] == "converted" and e["sha256"][:8] not in referenced:
|
||
findings.append(("coverage", path, "已轉換但沒有任何 wiki 頁引用（攝入缺口）"))
|
||
if e["kind"] == "original" and e.get("status") == "needs_ocr":
|
||
findings.append(("coverage", path, "needs_ocr：掃描件待人工決定 OCR 方案"))
|
||
|
||
|
||
def check_orphans(root, pages, findings):
|
||
# ponytail: 以「檔名出現在任何連結目標中」判斷被連結，不解析相對路徑；
|
||
# 升級路徑：正規化解析所有 markdown 連結。
|
||
link_targets = ""
|
||
idx = root / "index.md"
|
||
if idx.is_file():
|
||
link_targets += idx.read_text(encoding="utf-8")
|
||
for _, _, body in pages:
|
||
link_targets += body
|
||
linked = set(re.findall(r"\(([^)]+\.md)\)", link_targets))
|
||
linked_names = {pathlib.PurePosixPath(t).name for t in linked}
|
||
for rel, _, _ in pages:
|
||
if pathlib.PurePosixPath(rel).name not in linked_names:
|
||
findings.append(("orphan", rel, "不被 index.md 或任何其他頁連結"))
|
||
|
||
|
||
def candidate_pairs(pages):
|
||
cands = {}
|
||
for (ra, ma, ba), (rb, mb, bb) in itertools.combinations(pages, 2):
|
||
sim = difflib.SequenceMatcher(
|
||
None, f"{ma['title']} {ma['description']}",
|
||
f"{mb['title']} {mb['description']}").ratio()
|
||
shared_tags = len(set(ma.get("tags") or []) & set(mb.get("tags") or []))
|
||
if sim >= SIM_THRESHOLD or shared_tags >= 2:
|
||
cands[(ra, rb)] = (sim, (ma, ba), (mb, bb))
|
||
ranked = sorted(cands.items(), key=lambda kv: -kv[1][0])
|
||
return ranked[:MAX_LLM_PAIRS]
|
||
|
||
|
||
def check_pairs_llm(cfg, pages, findings):
|
||
for (ra, rb), (sim, (ma, ba), (mb, bb)) in candidate_pairs(pages):
|
||
try:
|
||
obj, _ = kb.llm_json(cfg, "lint", PAIR_PROMPT.format(
|
||
a_title=ma["title"], a_desc=ma["description"], a_body=ba[:1500],
|
||
b_title=mb["title"], b_desc=mb["description"], b_body=bb[:1500]),
|
||
validate_pair)
|
||
except RuntimeError as e:
|
||
findings.append(("llm-pair", f"{ra} ↔ {rb}", f"LLM 比對失敗：{e}"))
|
||
continue
|
||
if obj["relation"] == "duplicate":
|
||
findings.append(("duplicate", f"{ra} ↔ {rb}", f"疑似重複：{obj['explanation']}"))
|
||
elif obj["relation"] == "contradiction":
|
||
findings.append(("contradiction", f"{ra} ↔ {rb}", f"疑似矛盾：{obj['explanation']}"))
|
||
|
||
|
||
SECTION_TITLES = {
|
||
"schema": "Schema 完整性", "stale": "過期主張（staleness）",
|
||
"coverage": "覆蓋缺口", "orphan": "孤兒頁",
|
||
"duplicate": "重複頁（LLM 判定）", "contradiction": "矛盾頁（LLM 判定）",
|
||
"llm-pair": "LLM 比對失敗（需重跑）",
|
||
}
|
||
|
||
|
||
def write_report(out_dir, findings, n_pages, llm_note):
|
||
now = datetime.datetime.now()
|
||
out_dir.mkdir(parents=True, exist_ok=True)
|
||
path = out_dir / f"lint-{now.strftime('%Y%m%d-%H%M%S')}.md"
|
||
counts = {}
|
||
for check, _, _ in findings:
|
||
counts[check] = counts.get(check, 0) + 1
|
||
lines = [f"# Lint 報告 — {now.strftime('%Y-%m-%d %H:%M')}", "",
|
||
f"- 檢查頁面數：{n_pages}",
|
||
f"- 發現項目：{len(findings)}（" + "、".join(
|
||
f"{SECTION_TITLES[k]} {v}" for k, v in counts.items()) + "）"
|
||
if findings else "- 發現項目：0",
|
||
f"- LLM 比對：{llm_note}", "",
|
||
"> lint 絕不修改或刪除任何檔案；以下所有項目皆**待人工核准**後才處置。", ""]
|
||
for check in SECTION_TITLES:
|
||
items = [(w, msg) for c, w, msg in findings if c == check]
|
||
if not items:
|
||
continue
|
||
lines += [f"## {SECTION_TITLES[check]}", ""]
|
||
lines += [f"- [ ] `{w}` — {msg}" for w, msg in items]
|
||
lines.append("")
|
||
path.write_text("\n".join(lines), encoding="utf-8")
|
||
return path
|
||
|
||
|
||
def main(argv=None):
|
||
ap = argparse.ArgumentParser(description=__doc__)
|
||
ap.add_argument("--output", default="reports")
|
||
ap.add_argument("--no-llm", action="store_true", help="跳過重複/矛盾的 LLM 比對")
|
||
ap.add_argument("--root", default=str(kb.ROOT))
|
||
a = ap.parse_args(argv)
|
||
root = pathlib.Path(a.root).resolve()
|
||
cfg = kb.load_config(root)
|
||
manifest = json.loads((root / "raw" / "manifest.json").read_text(encoding="utf-8"))
|
||
|
||
findings = []
|
||
pages = load_pages(root, findings)
|
||
check_schema(pages, manifest, findings)
|
||
check_stale(pages, findings)
|
||
check_coverage(pages, manifest, findings)
|
||
check_orphans(root, pages, findings)
|
||
if a.no_llm:
|
||
llm_note = "已略過（--no-llm）"
|
||
else:
|
||
llm_note = f"model={cfg['tasks']['lint']['model']}，上限 {MAX_LLM_PAIRS} 對"
|
||
check_pairs_llm(cfg, pages, findings)
|
||
|
||
out = pathlib.Path(a.output)
|
||
report = write_report(out if out.is_absolute() else root / out,
|
||
findings, len(pages), llm_note)
|
||
print(f"報告：{report}")
|
||
print(f"發現 {len(findings)} 項" if findings else "無發現")
|
||
if findings:
|
||
raise SystemExit(1)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|