feat: 新增 diag_refs — source_ref↔manifest 對帳診斷
lint 的「source_ref 不在 manifest」只報對不上、不辨成因。diag_refs 把每個 對不上的 source_ref 分成五類(hash 不符/路徑字串岔開/檔名 hash 後綴岔開/ 檔在磁碟未登記/完全無對應),各附修法,讓「補帳本(§14.3)」與「修規則 (§12)」的相反處置不再混為一談。純唯讀、結束碼 0/1,可當搬機或改 manifest 後的閘門。附 selfcheck 驗五型別分類、結束碼與零寫檔。README §3.3/§6/§7/§8 同步。 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
134
tools/diag_refs.py
Normal file
134
tools/diag_refs.py
Normal file
@@ -0,0 +1,134 @@
|
||||
"""source_ref ↔ manifest 對帳診斷(AGENTS.md §7 schema / §14 對帳的輔助工具)。
|
||||
|
||||
lint.py 對「source_ref 不在 manifest」只報一句,無法區分成因;本工具把每個
|
||||
對不上的 source_ref 分類成可據以修復的型別(見 CAT_TITLE / FIX),讓「帳本掉
|
||||
條目」「路徑字串岔開」「檔名 hash 後綴岔開」「檔真的遺失」彼此不再混為一談。
|
||||
|
||||
純唯讀——不改任何檔(含 manifest),有對不上以結束碼 1 表示(可當搬機/改
|
||||
manifest 後的閘門)。分類邏輯與 lint 一致:以最後一個 '#' 切出 path 與 sha8。
|
||||
|
||||
用法:python tools/diag_refs.py [--root DIR]
|
||||
結束碼:0 = 全部解得開,1 = 有對不上。
|
||||
"""
|
||||
import argparse
|
||||
import json
|
||||
import pathlib
|
||||
import re
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, str(pathlib.Path(__file__).parent))
|
||||
import kb
|
||||
|
||||
CAT_TITLE = {
|
||||
"hash-mismatch": "Hash 不符(帳本有此路徑,但 sha256 與 ref 不同)",
|
||||
"normalize": "路徑字串岔開(正規化後與帳本 key 相同:斜線/前綴/大小寫)",
|
||||
"stem": "檔名 hash 後綴岔開(帳本有同檔名幹、hash 後綴不同的 key)",
|
||||
"unregistered": "檔在磁碟、帳本無此條目",
|
||||
"absent": "完全無對應(帳本、磁碟、檔名幹皆無)",
|
||||
}
|
||||
FIX = {
|
||||
"hash-mismatch": "raw 被就地改動或重轉(違反 §1.4);還原檔案,或連同 source_ref 走 PR(§14.2)。",
|
||||
"normalize": "修產生岔開字串的那一個環節(路徑正規化),別逐頁改 source_ref(§12 change the ruler)。",
|
||||
"stem": "source_ref 指到不同 hash 後綴的檔名;核對正確檔名,別改帳本去遷就(§14.2)。",
|
||||
"unregistered": "帳本掉了條目、檔還在;走 branch+PR 補登 manifest(§14.3),別動 wiki 頁。",
|
||||
"absent": "source_ref 可能攝入時寫歪,或原始檔真的遺失;上報 HITL 據實記錄(§14.2)。",
|
||||
}
|
||||
# 分類輸出順序(愈可機械修復的排愈前)
|
||||
ORDER = ["hash-mismatch", "normalize", "stem", "unregistered", "absent"]
|
||||
|
||||
|
||||
def _norm(path):
|
||||
"""正規化路徑字串以偵測「同一檔、不同寫法」:反斜線→斜線、去開頭 ./、轉小寫。"""
|
||||
s = path.replace("\\", "/")
|
||||
if s.startswith("./"):
|
||||
s = s[2:]
|
||||
return s.lower()
|
||||
|
||||
|
||||
def _stem(path):
|
||||
"""取檔名幹:去目錄、去 .md、去結尾的 -<8 碼 hex>(convert 的檔名 hash 後綴)。"""
|
||||
name = path.replace("\\", "/").rsplit("/", 1)[-1]
|
||||
name = re.sub(r"\.md$", "", name, flags=re.I)
|
||||
return re.sub(r"-[0-9a-f]{8}$", "", name, flags=re.I).lower()
|
||||
|
||||
|
||||
def classify_ref(source_ref, files, exists):
|
||||
"""把單一 source_ref 分類。files:manifest['files'](path→entry);
|
||||
exists(path)→bool 判磁碟是否有該檔。回傳 (category, detail)。
|
||||
category 為 "resolved" 或 CAT_TITLE 的任一鍵。"""
|
||||
path, _, sha8 = str(source_ref).rpartition("#")
|
||||
entry = files.get(path)
|
||||
if entry is not None:
|
||||
if entry["sha256"].startswith(sha8):
|
||||
return "resolved", path
|
||||
return "hash-mismatch", f"帳本 sha256={entry['sha256'][:8]} ≠ ref #{sha8}"
|
||||
norm = _norm(path)
|
||||
for k in files:
|
||||
if _norm(k) == norm:
|
||||
return "normalize", f"帳本 key = '{k}'"
|
||||
stem = _stem(path)
|
||||
for k, e in files.items():
|
||||
if e.get("kind") == "converted" and _stem(k) == stem:
|
||||
return "stem", f"帳本 key = '{k}'"
|
||||
if exists(path):
|
||||
return "unregistered", f"磁碟有 '{path}',帳本無此 key"
|
||||
return "absent", f"'{path}' 帳本無、磁碟無、無同名幹 key"
|
||||
|
||||
|
||||
def collect(root, files, exists):
|
||||
"""掃全庫 wiki 頁,回傳 (findings, n_refs)。findings:category→[(page, ref, detail)]。"""
|
||||
findings = {c: [] for c in ORDER}
|
||||
n_refs = 0
|
||||
for p in kb.iter_pages(root):
|
||||
rel = p.relative_to(root).as_posix()
|
||||
try:
|
||||
meta, _ = kb.parse_page(p.read_text(encoding="utf-8"))
|
||||
except Exception as e:
|
||||
findings["absent"].append((rel, "(無法解析頁面)", str(e)))
|
||||
continue
|
||||
for s in meta.get("sources") or []:
|
||||
n_refs += 1
|
||||
cat, detail = classify_ref(s, files, exists)
|
||||
if cat != "resolved":
|
||||
findings[cat].append((rel, str(s), detail))
|
||||
return findings, n_refs
|
||||
|
||||
|
||||
def format_report(findings, n_refs):
|
||||
total = sum(len(v) for v in findings.values())
|
||||
lines = [f"檢查 source_ref:{n_refs},對不上:{total}", ""]
|
||||
if total == 0:
|
||||
lines.append("全部解得開(source_ref 與 manifest 一致)。")
|
||||
return "\n".join(lines)
|
||||
for cat in ORDER:
|
||||
items = findings[cat]
|
||||
if not items:
|
||||
continue
|
||||
lines.append(f"## {CAT_TITLE[cat]}({len(items)})")
|
||||
lines.append(f"→ 修法:{FIX[cat]}")
|
||||
for page, ref, detail in items:
|
||||
lines.append(f" - [{page}] {ref}")
|
||||
lines.append(f" {detail}")
|
||||
lines.append("")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main(argv=None):
|
||||
ap = argparse.ArgumentParser(description=__doc__)
|
||||
ap.add_argument("--root", default=str(kb.ROOT))
|
||||
a = ap.parse_args(argv)
|
||||
root = pathlib.Path(a.root).resolve()
|
||||
mpath = root / "raw" / "manifest.json"
|
||||
try:
|
||||
files = json.loads(mpath.read_text(encoding="utf-8"))["files"]
|
||||
except (OSError, KeyError, json.JSONDecodeError) as e:
|
||||
raise SystemExit(f"讀不到 / 解析不了 manifest:{mpath}({e})")
|
||||
|
||||
findings, n_refs = collect(root, files, lambda p: (root / p).is_file())
|
||||
print(format_report(findings, n_refs))
|
||||
if sum(len(v) for v in findings.values()):
|
||||
raise SystemExit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user