guard high-extent tile reencoding

navsea_extent_shift_audit.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+from typing import Any
+
+from navsea_tile_reencode_guard import validate_reencoded_tile
+
+
+DEFAULT_SOURCE_ROOT = Path(
+    "/home/wwwroot/newpec/exported_auto/"
+    "tile.mapple-on.jp__newpec-mvt-20260106__z___x___y_.pbf/tiles"
+)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="审计 PBF 是否存在高 extent 被 4096 口径重编码的几何错移。")
+    parser.add_argument("--target-root", type=Path, required=True)
+    parser.add_argument("--source-root", type=Path, default=DEFAULT_SOURCE_ROOT)
+    parser.add_argument("--output-json", type=Path)
+    parser.add_argument("--zoom", action="append", type=int)
+    parser.add_argument("--sample-limit", type=int, default=50)
+    return parser.parse_args()
+
+
+def should_include(rel: Path, zoom_filter: set[int] | None) -> bool:
+    if not zoom_filter:
+        return True
+    try:
+        return int(rel.parts[0]) in zoom_filter
+    except Exception:
+        return False
+
+
+def main() -> None:
+    args = parse_args()
+    zoom_filter = set(args.zoom or [])
+    suspicious_tiles: list[dict[str, Any]] = []
+    checked = 0
+
+    for tile_path in sorted(args.target_root.glob("*/*/*.pbf")):
+        rel = tile_path.relative_to(args.target_root)
+        if not should_include(rel, zoom_filter or None):
+            continue
+        source_tile = args.source_root / rel
+        if not source_tile.exists():
+            continue
+        checked += 1
+        verdict = validate_reencoded_tile(source_tile, tile_path)
+        if verdict["suspicious"]:
+            suspicious_tiles.append(
+                {
+                    "tile": str(rel),
+                    **verdict,
+                }
+            )
+
+    suspicious_tiles.sort(
+        key=lambda item: (
+            item["output_max_overflow"] - item["source_max_overflow"],
+            item["tile"],
+        ),
+        reverse=True,
+    )
+    summary = {
+        "target_root": str(args.target_root),
+        "source_root": str(args.source_root),
+        "zoom_filter": sorted(zoom_filter),
+        "tiles_checked": checked,
+        "suspicious_tile_count": len(suspicious_tiles),
+        "samples": suspicious_tiles[: args.sample_limit],
+    }
+    if args.output_json:
+        args.output_json.parent.mkdir(parents=True, exist_ok=True)
+        args.output_json.write_text(json.dumps(summary, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    print(json.dumps(summary, ensure_ascii=False, indent=2))
+
+
+if __name__ == "__main__":
+    main()