Initial SQL-only 1C adapter baseline

scripts/index_1c_sql_cas.py

@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+"""Index exported 1C ConfigCAS files for GUID/string lookup.
+
+This is a mechanical content index: decompress, decode when possible, collect
+GUIDs and string hits. It does not infer semantic object kinds.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+from typing import Any
+
+from inspect_1c_sql_files import GUID_RE, try_decode, try_decompress
+
+
+def inspect_cas_file(path: Path, target_guids: set[str], target_strings: list[str]) -> dict[str, Any]:
+    data = path.read_bytes()
+    payload, compression = try_decompress(data)
+    text, encoding = try_decode(payload)
+    item: dict[str, Any] = {
+        "file_name": path.name,
+        "bytes": len(data),
+        "payload_bytes": len(payload),
+        "compression": compression,
+        "encoding": encoding,
+        "guid_count": 0,
+        "target_guid_hits": [],
+        "target_string_hits": [],
+        "guids_sample": [],
+        "text_preview": "",
+    }
+    if text is None:
+        return item
+    clean = text.replace("\x00", "").replace("\ufeff", "")
+    guids = sorted(set(match.lower() for match in GUID_RE.findall(clean)))
+    item["guid_count"] = len(guids)
+    item["guids_sample"] = guids[:50]
+    item["target_guid_hits"] = sorted(target_guids.intersection(guids))
+    item["target_string_hits"] = [value for value in target_strings if value and value in clean]
+    if item["target_guid_hits"] or item["target_string_hits"]:
+        item["text_preview"] = clean[:2000]
+    else:
+        item["text_preview"] = clean[:300]
+    return item
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Index exported ConfigCAS files.")
+    parser.add_argument("cas_dir", type=Path)
+    parser.add_argument("--output", type=Path, required=True)
+    parser.add_argument("--target-guid", action="append", default=[])
+    parser.add_argument("--target-string", action="append", default=[])
+    args = parser.parse_args()
+
+    target_guids = {value.lower() for value in args.target_guid}
+    files = sorted(path for path in args.cas_dir.iterdir() if path.is_file())
+    items = [inspect_cas_file(path, target_guids, args.target_string) for path in files]
+    guid_hits = [item for item in items if item["target_guid_hits"]]
+    string_hits = [item for item in items if item["target_string_hits"]]
+    compression_counts: dict[str, int] = {}
+    encoding_counts: dict[str, int] = {}
+    for item in items:
+        compression_counts[item["compression"]] = compression_counts.get(item["compression"], 0) + 1
+        encoding = item["encoding"] or "<binary>"
+        encoding_counts[encoding] = encoding_counts.get(encoding, 0) + 1
+    report = {
+        "schema": "onec_sql_cas_index.v1",
+        "cas_dir": str(args.cas_dir),
+        "file_count": len(items),
+        "target_guids": sorted(target_guids),
+        "target_strings": args.target_string,
+        "compression_counts": dict(sorted(compression_counts.items())),
+        "encoding_counts": dict(sorted(encoding_counts.items())),
+        "target_guid_hit_count": len(guid_hits),
+        "target_string_hit_count": len(string_hits),
+        "target_guid_hits": guid_hits,
+        "target_string_hits": string_hits,
+        "files": items,
+    }
+    args.output.parent.mkdir(parents=True, exist_ok=True)
+    args.output.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    print(
+        json.dumps(
+            {
+                "output": str(args.output),
+                "files": len(items),
+                "guid_hits": len(guid_hits),
+                "string_hits": len(string_hits),
+                "compression_counts": report["compression_counts"],
+            },
+            ensure_ascii=False,
+        )
+    )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())