From 60cc36893e2a94c9f8611e97b98f1ac0b1db085b Mon Sep 17 00:00:00 2001
From: dat972 <wayoung12@gmail.com>
Date: Thu, 9 Jul 2026 16:21:20 -0500
Subject: [PATCH] updated scan.py to help us error handle the weird searches
 and alos build an ignore list

---
 README.md                               |   9 ++++++--
 __pycache__/fccs_config.cpython-313.pyc | Bin 6959 -> 7844 bytes
 config.ini                              |   1 +
 fccs_config.py                          |  20 ++++++++++++++++
 fccs_export.py                          |   5 +++-
 fccs_scan.py                            |  29 +++++++++++++++++++++++-
 6 files changed, 60 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 7d1b134..d9de38d 100644
--- a/README.md
+++ b/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)
diff --git a/__pycache__/fccs_config.cpython-313.pyc b/__pycache__/fccs_config.cpython-313.pyc
index e50ec3bcc7fffbab75607bb8b83a446f56a3ab7e..413bac701b1f873d6285e1c56c7ab03e73ebbad8 100644
GIT binary patch
delta 947
zcmY*Y&1(}u9G%@{6T0~@X<}Ma#8GS0#jw$0t1T3)v9*GUwIxz4Ql`lyyEd6!cDANH
zCC7SELo5_eDqcm3mtOr3`~Vx*gEu`1wGqUdv-z+%urog%@4erf-|oI1dpYTE`g|f_
z>%cd6&kWc6{hV2g&2qk)J|r%9qrf;);3fag(;r;qbVAWeI8jC$iFvGRG%=G*E+pP;
z@gMr?JAIMLH)gX1mN?taUQ3Sl2|xyncF^ugxC9`4h6{n&n*b1pUEOw4J^?7tutA17
z7n2iZ0CGG4DHbu~oEN%&hiAsobsVmX{hmtdl+B#uQ$qlF00cxJ&WteJ5wyG}8H1m9
zA9{4F#nB6V*A0Tyt+qpkA7q&zdx$d+Bo3w6Rc2I@gE<40u>r4NrO;H636X&-5JBC*
zd37CXd5DN+Dva@uD2t*!Ge|KqvI?efWurrnL#lOPl@ypChE&lEv*izmv0RX0?A*x6
z`AacL)HR*LHJ$aMxQMf+su8%Nt;4c%0~3Z8HBx8`@w!S)`k#I(CdI|FqGlDiVqmmt
zhsO}DnOX^%I0p&3uNIK)S@#Dbl~#&nH5Z3VZCh4TS(fig&|K4tnA*u%&YXRhE?E|*
zOS-uMi>x~=VMHh-8q5|EWtWyk$!WRTBFjOsX^gWsU`()0a#><~Saui7q2?;oa(8r=
z(6YCL)=(`si)+u2x|k5Qmf>Ti6=Z03bvdsY%N?ab82*qwlzmU23VwxwC-@}v_)h)A
zNAYAe+3*Ld*S-Y9o5JTIsR_8y74AiLJJW~^)N-Wh0O4Z|N#2vj-%I1WXZEDazisGw
zcGJDz;(qt^ZeDD7LyyuA(%aMT2F`x+#((yJ-lO{>@P?}CKL<UwB@M9V&w8e0*Q+qw
u-U=?ZOI%tC)QizMj?{Of$3>lS>|ceZ>R+SNfrBxDLtHZu<U)p@!G8fe`S>&d

delta 102
zcmZ2tyWWiNGcPX}0}%X`_Q^^Vn#d=?m^V?~gOO)qff`FXlP2%R1#cPoq?4^;obyvs
zW89pbgJU)?X1XNKs>$f5$v^qJY`|n4IZ3WGpb?BfT<kH~U(S{Lvl%O6B4ZIBPy_&}
Cuo^7@

diff --git a/config.ini b/config.ini
index 5118c90..39bd760 100644
--- a/config.ini
+++ b/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
diff --git a/fccs_config.py b/fccs_config.py
index 9f4fa4b..f26d3ca 100644
--- a/fccs_config.py
+++ b/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
diff --git a/fccs_export.py b/fccs_export.py
index 15b06cc..93e3f22 100755
--- a/fccs_export.py
+++ b/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:
diff --git a/fccs_scan.py b/fccs_scan.py
index 3cf1d18..666cc6d 100644
--- a/fccs_scan.py
+++ b/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()