updated scan.py to help us error handle the weird searches and alos build an ignore list

README.md

@@ -34,7 +34,12 @@ Extracts and organizes documents from FileCabinet CS (Thomson Reuters) using GUI
 python fccs_scan.py
 ```
 
-Reads the restored FCCS backup directory and writes all drawer IDs (subfolder names) to `drawer_ids.txt`.
+Reads the restored FCCS backup directory and writes all drawer IDs (subfolder names) to `drawer_ids.txt`. It also:
+
+- **Flags prefix clashes** — if one drawer ID is a prefix of another (e.g. `02218` and `02218A`), searching the shorter ID in FCCS pops up a selection box that breaks automated navigation. These are reported so you can export them manually or ignore the shorter ID.
+- **Reports ignored drawers** — any IDs listed in `ignore.txt` that exist in this backup are shown as ones the export will skip.
+
+**Ignoring drawers:** To exclude specific drawers from export (e.g. password-protected folders that would stall the automation), add their IDs to the file at `ignore_file` (default `C:\Migration\ignore.txt`), one per line. `drawer_ids.txt` stays a full inventory; the export skips anything in the ignore list. Lines starting with `#` are treated as comments.
 
 ### Step 2: Export Documents
 
@@ -88,6 +93,6 @@ Exported filenames follow the format `{drawer_id}_{client_name}_{folder_name}_{c
 
 All scripts read from `config.ini` (or specify `--config path\to\config.ini`).
 
-- **`[paths]`** -- backup_dir, export_dir, output_dir, drawer_id_file, completed_file, log_file, screenshot_dir, folder_list
+- **`[paths]`** -- backup_dir, export_dir, output_dir, drawer_id_file, completed_file, ignore_file, log_file, screenshot_dir, manifest_dir, folder_list
 - **`[timeouts]`** -- nav_timeout, dialog_timeout, progress_appear, progress_finish, settle, confirm_timeout
 - **`[controls]`** -- FCCS window class names and button titles (rarely need changing)

config.ini

@@ -5,6 +5,7 @@ export_dir     = C:\Migration\Export
 output_dir     = C:\Migration\Output
 drawer_id_file = C:\Migration\drawer_ids.txt
 completed_file = C:\Migration\completed.txt
+ignore_file    = C:\Migration\ignore.txt
 log_file       = C:\Migration\run_log.txt
 screenshot_dir = C:\Migration\screenshots
 manifest_dir   = C:\Migration\manifests

fccs_config.py

@@ -137,3 +137,23 @@ def load_lines(path):
         return []
     with open(path, "r", encoding="utf-8") as f:
         return [line.strip() for line in f if line.strip() and not line.strip().startswith("#")]
+
+
+def check_for_clashes(drawer_ids):
+    """Find drawer IDs that are a prefix of another drawer ID.
+
+    FCCS searches by prefix, so searching the shorter ID (e.g. '02218')
+    pops up a selection box when a longer ID exists (e.g. '02218A'),
+    which breaks the automated navigation.
+
+    Returns a list of (short_id, [longer_ids...]) tuples, sorted by short_id.
+    Empty list means no clashes.
+    """
+    ids = sorted(set(drawer_ids))
+    clashes = []
+    for short in ids:
+        matches = [other for other in ids
+                   if other != short and other.startswith(short)]
+        if matches:
+            clashes.append((short, matches))
+    return clashes

fccs_export.py

@@ -354,6 +354,7 @@ def main():
     paths = {
         "drawer_id_file": cfg.get("paths", "drawer_id_file"),
         "completed_file": cfg.get("paths", "completed_file"),
+        "ignore_file":    cfg.get("paths", "ignore_file"),
         "screenshot_dir": cfg.get("paths", "screenshot_dir"),
         "manifest_dir":   cfg.get("paths", "manifest_dir"),
     }
@@ -391,10 +392,12 @@ def main():
         sys.exit(1)
 
     completed = load_completed(paths["completed_file"])
+    ignored   = set(load_lines(paths["ignore_file"]))
 
-    pending = [d for d in all_ids if d not in completed]
+    pending = [d for d in all_ids if d not in completed and d not in ignored]
     log(f"Total drawers in list : {len(all_ids)}")
     log(f"Already completed     : {len(completed)}")
+    log(f"Ignored (skipped)     : {len(ignored & set(all_ids))}")
     log(f"Remaining to process  : {len(pending)}")
 
     if not pending:

fccs_scan.py

@@ -8,7 +8,9 @@ Writes the sorted list of drawer IDs to the configured drawer_id_file.
 import os
 import sys
 
-from fccs_config import parse_args, load_config, make_logger
+from fccs_config import (
+    parse_args, load_config, make_logger, load_lines, check_for_clashes,
+)
 
 
 def main():
@@ -18,6 +20,7 @@ def main():
 
     backup_dir = cfg.get("paths", "backup_dir")
     output_file = cfg.get("paths", "drawer_id_file")
+    ignore_file = cfg.get("paths", "ignore_file")
 
     if not os.path.isdir(backup_dir):
         log(f"ERROR: backup directory not found: {backup_dir}")
@@ -34,6 +37,30 @@ def main():
 
     log(f"Found {len(drawer_ids)} drawers, written to {output_file}")
 
+    # Report which drawers are set to be ignored (skipped by the export).
+    ignored = set(load_lines(ignore_file))
+    if ignored:
+        present = sorted(ignored & set(drawer_ids))
+        log(f"Ignore list ({ignore_file}): {len(ignored)} IDs, "
+            f"{len(present)} present in this backup — these will be SKIPPED "
+            f"by fccs_export.py: {', '.join(present) if present else '(none present)'}")
+
+    # Flag prefix clashes: FCCS search on the shorter ID pops a selection box.
+    clashes = check_for_clashes(drawer_ids)
+    if clashes:
+        log("-" * 60)
+        log(f"WARNING: {len(clashes)} potential drawer ID clash(es) found.")
+        log("Searching the shorter ID in FCCS may show a selection box "
+            "instead of navigating directly, which breaks the export.")
+        log("Consider exporting these manually, or add the shorter ID to "
+            f"the ignore list ({ignore_file}).")
+        for short, matches in clashes:
+            flag = " [ignored]" if short in ignored else ""
+            log(f"  {short}{flag}  ->  also matches: {', '.join(matches)}")
+        log("-" * 60)
+    else:
+        log("No drawer ID prefix clashes found.")
+
 
 if __name__ == "__main__":
     main()