Step 10c: extract cache I/O into rcjav/cache.py

Pulls CACHE_PATH, CACHE_VERSION, CACHE_STALE_HOURS, load_cache,
save_cache, cache_age_hours, and fmt_age out of rc-jav.py and into a
new self-contained module. No behavior change.

rc-jav.py: 2019 → 1972 lines.

The new module's `CACHE_PATH = Path(__file__).resolve().parents[1] /
"cache.json"` keeps the file at the repo root next to rc-jav.py (one
directory above the package), matching the legacy `Path(__file__).
resolve().parent / "cache.json"` location.

rcjav/__init__.py now re-exports the cache public surface alongside
the model and ids surface.

Verified:
  - python rc-jav.py --help              → ok
  - python fixtures/run.py               → 17/17 cases pass
  - python -m unittest tests.test_rules  → 5/5 OK

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

rc-jav.py

@@ -161,9 +161,15 @@ CATALOG_COL_PATH = ("path", "full path", "location", "folder")
 CATALOG_COL_SIZE = ("size", "file size", "bytes", "size (bytes)")
 CATALOG_COL_DISC = ("disc", "disc name", "disc label", "volume", "source", "catalog", "media")
 
-CACHE_PATH = Path(__file__).resolve().parent / "cache.json"
+from rcjav.cache import (
-CACHE_VERSION = 3  # bumped: extract_id handles bracket-wrapped IDs + no-hyphen fallback
+    CACHE_PATH,
-CACHE_STALE_HOURS = 24
+    CACHE_VERSION,
+    CACHE_STALE_HOURS,
+    load_cache,
+    save_cache,
+    cache_age_hours,
+    fmt_age,
+)
 
 DEFAULT_KEEP_RANKING: dict = {
     "priority_folders": ["ClearJAV"],
@@ -202,59 +208,6 @@ def save_config(cfg: dict) -> None:
     os.replace(tmp, CONFIG_PATH)
 
 
-def load_cache() -> dict:
-    if not CACHE_PATH.exists():
-        return {"version": CACHE_VERSION, "remotes": {}}
-    try:
-        data = json.loads(CACHE_PATH.read_text(encoding="utf-8"))
-        if (
-            not isinstance(data, dict)
-            or data.get("version") != CACHE_VERSION
-            or not isinstance(data.get("remotes"), dict)
-        ):
-            if isinstance(data, dict) and "version" in data and data["version"] != CACHE_VERSION:
-                sys.stderr.write(
-                    f"[warn] cache version mismatch (got {data['version']}, "
-                    f"expected {CACHE_VERSION}); forcing full rescan.\n"
-                )
-            return {"version": CACHE_VERSION, "remotes": {}}
-        return data
-    except (json.JSONDecodeError, OSError):
-        return {"version": CACHE_VERSION, "remotes": {}}
-
-
-def save_cache(cache: dict) -> None:
-    # Write to a sibling tmp file then atomically replace, so a killed mid-write
-    # (Ctrl-C, power loss, concurrent --scan) can't leave a half-written
-    # cache.json — load_cache would otherwise see invalid JSON and fall back to
-    # an empty cache, forcing a full re-scan.
-    tmp = CACHE_PATH.with_suffix(CACHE_PATH.suffix + ".tmp")
-    tmp.write_text(json.dumps(cache, indent=2), encoding="utf-8")
-    try:
-        os.replace(tmp, CACHE_PATH)
-    except PermissionError:
-        # Windows: destination may be briefly locked by antivirus or a concurrent reader.
-        time.sleep(0.5)
-        os.replace(tmp, CACHE_PATH)
-
-
-def cache_age_hours(scanned_at: str) -> float | None:
-    try:
-        dt = datetime.fromisoformat(scanned_at.replace("Z", "+00:00"))
-    except ValueError:
-        return None
-    now = datetime.now(dt.tzinfo) if dt.tzinfo else datetime.now()
-    return (now - dt).total_seconds() / 3600.0
-
-
-def fmt_age(hours: float) -> str:
-    if hours < 1:
-        return f"{int(hours * 60)}m"
-    if hours < 24:
-        return f"{hours:.1f}h"
-    return f"{hours / 24:.1f}d"
-
-
 # ---------- WinCatalog ingest ----------
 
 def _pick_col(headers_lower: list[str], synonyms: tuple[str, ...]) -> str | None:

rcjav/__init__.py

@@ -6,6 +6,15 @@ find at the top level. Adding a new submodule does not change the
 public surface — only this file does.
 """
 from rcjav.model import FileEntry  # noqa: F401
+from rcjav.cache import (  # noqa: F401
+    CACHE_PATH,
+    CACHE_VERSION,
+    CACHE_STALE_HOURS,
+    load_cache,
+    save_cache,
+    cache_age_hours,
+    fmt_age,
+)
 from rcjav.ids import (  # noqa: F401
     PRIMARY_ID_RE,
     FALLBACK_ID_RE,

rcjav/cache.py

@@ -0,0 +1,76 @@
+"""cache.json I/O.
+
+This module owns the on-disk cache contract: where the file lives,
+what the header looks like, and how mismatches are handled. The
+current shape predates the two-tier `cache_schema` + `id_rules` split
+documented in docs/CACHE_CONTRACT.md (extension repo) — step 10j
+implements that contract; until then this is the legacy
+`version: 3` reader.
+"""
+from __future__ import annotations
+
+import json
+import os
+import sys
+import time
+from datetime import datetime
+from pathlib import Path
+
+
+# Lives next to rc-jav.py at the repo root.
+CACHE_PATH = Path(__file__).resolve().parents[1] / "cache.json"
+CACHE_VERSION = 3  # bumped: extract_id handles bracket-wrapped IDs + no-hyphen fallback
+CACHE_STALE_HOURS = 24
+
+
+def load_cache() -> dict:
+    if not CACHE_PATH.exists():
+        return {"version": CACHE_VERSION, "remotes": {}}
+    try:
+        data = json.loads(CACHE_PATH.read_text(encoding="utf-8"))
+        if (
+            not isinstance(data, dict)
+            or data.get("version") != CACHE_VERSION
+            or not isinstance(data.get("remotes"), dict)
+        ):
+            if isinstance(data, dict) and "version" in data and data["version"] != CACHE_VERSION:
+                sys.stderr.write(
+                    f"[warn] cache version mismatch (got {data['version']}, "
+                    f"expected {CACHE_VERSION}); forcing full rescan.\n"
+                )
+            return {"version": CACHE_VERSION, "remotes": {}}
+        return data
+    except (json.JSONDecodeError, OSError):
+        return {"version": CACHE_VERSION, "remotes": {}}
+
+
+def save_cache(cache: dict) -> None:
+    # Write to a sibling tmp file then atomically replace, so a killed mid-write
+    # (Ctrl-C, power loss, concurrent --scan) can't leave a half-written
+    # cache.json — load_cache would otherwise see invalid JSON and fall back to
+    # an empty cache, forcing a full re-scan.
+    tmp = CACHE_PATH.with_suffix(CACHE_PATH.suffix + ".tmp")
+    tmp.write_text(json.dumps(cache, indent=2), encoding="utf-8")
+    try:
+        os.replace(tmp, CACHE_PATH)
+    except PermissionError:
+        # Windows: destination may be briefly locked by antivirus or a concurrent reader.
+        time.sleep(0.5)
+        os.replace(tmp, CACHE_PATH)
+
+
+def cache_age_hours(scanned_at: str) -> float | None:
+    try:
+        dt = datetime.fromisoformat(scanned_at.replace("Z", "+00:00"))
+    except ValueError:
+        return None
+    now = datetime.now(dt.tzinfo) if dt.tzinfo else datetime.now()
+    return (now - dt).total_seconds() / 3600.0
+
+
+def fmt_age(hours: float) -> str:
+    if hours < 1:
+        return f"{int(hours * 60)}m"
+    if hours < 24:
+        return f"{hours:.1f}h"
+    return f"{hours / 24:.1f}d"