Initial commit

importers/file_scan.py

@@ -0,0 +1,21 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Dict, Iterator
+
+RESUME_EXTS = {".pdf", ".docx", ".doc", ".txt", ".html", ".htm"}
+
+def iter_files(root: Path) -> Iterator[Dict]:
+    for p in root.rglob("*"):
+        if p.is_file() and p.suffix.lower() in RESUME_EXTS:
+            yield {
+                "origin_type": "file_scan",
+                "export_path": str(root),
+                "chat_title": None,
+                "message_id": None,
+                "message_date": None,
+                "message_text": "",
+                "file_path": str(p.resolve()),
+                "original_name": p.name,
+                "extra": {},
+            }