#!/usr/bin/env python3"""つまずき集から「移す側の確認」欄だけを抜き、番号つきの小さな索引にする。"""import jsonimport reimport sysfrom pathlib import Pathfrom lint_pitfalls import parse_numberCHECK_HEADS = ("iOS チェック", "iOS 監視ポイント")CODE_TOKEN = re.compile(r"`([^`]{3,60})`") # 本文中のバッククォート語を検索キーに使うIDENT = re.compile(r"\b(?:[A-Z][a-z]+[A-Z]\w+|[a-z]+[A-Z]\w+)\b") # コード中の型名・メソッド名CODE_KEEP = 6FENCE = "`" * 3 # 記事や文書の中で囲みが閉じないよう、文字を並べて作るdef build(src: Path) -> list[dict]: entries, cur, in_check, in_code, code_lines = [], None, False, False, 0 for line in src.read_text(encoding="utf-8").splitlines(): if line.startswith("## "): num = parse_number(line) cur = None if num: n, sfx = num cur = {"id": f"{n}{sfx}", "title": re.sub(r"^\S+\s*", "", line[3:]).strip(), "checks": [], "keys": set()} entries.append(cur) in_check = in_code = False continue if cur is None: continue if line.startswith("### ") and not in_code: in_check = line[4:].startswith(CHECK_HEADS) continue if not in_check: continue stripped = line.strip() if stripped.startswith(FENCE): in_code, code_lines = not in_code, 0 cur["checks"].append(stripped) continue if in_code: cur["keys"].update(k.lower() for k in IDENT.findall(line)) code_lines += 1 if code_lines <= CODE_KEEP: # 長いコードは先頭だけ残す cur["checks"].append(line.rstrip()) continue if stripped and stripped != "---": # 箇条書きでない地の文も「確認」に含まれる cur["checks"].append(stripped) cur["keys"].update(t.lower() for t in CODE_TOKEN.findall(line)) for e in entries: e["keys"] = sorted(e["keys"]) return entriesif __name__ == "__main__": src, out = Path(sys.argv[1]), Path(sys.argv[2]) data = build(src) out.write_text(json.dumps(data, ensure_ascii=False, indent=1), encoding="utf-8") empty = [e["id"] for e in data if not e["checks"]] print(f"items={len(data)} src={src.stat().st_size}B index={out.stat().st_size}B empty={empty}")
#!/usr/bin/env python3"""編集するファイルの識別子から、該当しそうな「移す側の確認」だけを引く。"""import jsonimport reimport sysfrom pathlib import PathPINNED = ("1", "12") # 語彙では引けないが毎回読む項目(つまずき集で「最重要」の2件)WORD = re.compile(r"[A-Za-z_][A-Za-z0-9_]{3,}")# チェック欄は SwiftUI の語彙で書かれている。手元が Objective-C なら、ここで語彙をつなぐ。ALIASES = { "scenephase": ["sceneDidBecomeActive", "applicationDidBecomeActive", "sceneWillEnterForeground"], "transaction.currententitlements": ["SKPaymentQueue", "restoreCompletedTransactions", "paymentQueueRestoreCompletedTransactionsFinished"], "transaction.updates": ["addTransactionObserver", "updatedTransactions"], "@mainactor": ["dispatch_get_main_queue", "isMainThread", "performSelectorOnMainThread"], "dispatchqueue.main.async": ["dispatch_get_main_queue"], "uipageviewcontroller.setviewcontrollers(...)": ["setViewControllers"], "traitcollectiondidchange": ["traitCollectionDidChange", "hasDifferentColorAppearanceComparedToTraitCollection"], "removeall": ["removeAllObjects"],}def file_words(path: Path) -> set[str]: return {w.lower() for w in WORD.findall(path.read_text(encoding="utf-8", errors="ignore"))}def common_words(corpus: Path, ratio: float) -> set[str]: """プロジェクトの多くのファイルに出る語(viewController など)は手がかりにならない。""" files = [f for f in corpus.rglob("*") if f.suffix in (".m", ".swift") and "_backup" not in f.parts] df: dict[str, int] = {} for f in files: for w in file_words(f): df[w] = df.get(w, 0) + 1 return {w for w, n in df.items() if n / max(len(files), 1) > ratio}def match(index, words, use_alias, common=frozenset()): hits = [] for e in index: why = [] for key in e["keys"]: parts = [p.lower() for p in WORD.findall(key)] # 'gadappopenad.present(...)' → 語に分ける if parts and all(p in common for p in parts): continue # ありふれた語だけのキーは捨てる if parts and all(p in words for p in parts): why.append(key) elif use_alias: for alias in ALIASES.get(key, []): if alias.lower() in words and alias.lower() not in common: why.append(f"{key}≈{alias}") if why: hits.append((e["id"], why)) return hitsif __name__ == "__main__": index = json.loads(Path(sys.argv[1]).read_text(encoding="utf-8")) use_alias = "--no-alias" not in sys.argv args = [a for a in sys.argv[2:] if not a.startswith("--")] corpus = next((a.split("=", 1)[1] for a in sys.argv if a.startswith("--corpus=")), None) common = common_words(Path(corpus), 0.2) if corpus else set() for target in args: hits = match(index, file_words(Path(target)), use_alias, common) ids = [i for i, _ in hits] print(f"{Path(target).name}: {len(hits)} items", " ".join(f"#{i}" for i in ids)) by_id = {e["id"]: e for e in index} for i in list(PINNED) + [i for i in ids if i not in PINNED]: why = dict(hits).get(i, ["pinned"]) print(f"\n#{i} {by_id[i]['title'][:50]} ({', '.join(why[:2])})") for line in by_id[i]["checks"][:5]: print(" " + line)