updated the organizer logic so that unparased files at least still get put in the correct client folder

README.md

@@ -84,12 +84,16 @@ output/
         2008 Form 1040 Filing Instructions.doc
     Permanent File/
       Driver's License.pdf
+    _unparsed/
+      (files for this client that couldn't be fully parsed, kept for review)
   _unparsed/
-    (files that couldn't be parsed go here for manual review)
+    (only files whose client couldn't be recovered from the filename)
 ```
 
 Exported filenames follow the format `{drawer_id}_{client_name}_{folder_name}_{creation_date}_{document_name}.ext`. The parser uses folder templates from `fccs_folders.txt` (with `YYYY` expanded via regex) and the creation date (`MM-DD-YYYY`) as anchors to reliably split the underscore-delimited fields. Folder names are decomposed into nested paths that match the FCCS UI structure (e.g. `2025 Tax Documents` becomes `Tax Documents/2025/`). UltraTax CS folders are matched by a built-in pattern.
 
+Files that can't be fully parsed still keep their client: the drawer ID and client name are the first two underscore-delimited tokens and stay recoverable even when the folder/date parse fails, so those files are filed under `{client_name}/_unparsed/` (retaining their original filename). Only files whose client can't be recovered at all fall back to the top-level `_unparsed/`.
+
 ### Step 4 (optional): Verify Export Completeness
 
 During export, each drawer's document list is captured from the FCCS dialog and saved as a manifest (in `manifest_dir`). These tools compare the manifests against the files actually in the export folder to confirm nothing was missed.

fccs_config.py

@@ -229,19 +229,30 @@ def exported_doc_name(filename):
     return stem[anchors[-1].end():]
 
 
-def client_name_from_files(files):
-    """Best-effort client name from a drawer's export filenames, or None.
+def client_name_from_filename(filename):
+    """Best-effort client name from a single export filename, or None.
 
     Filenames are '{drawer}_{client}_{folder}_{MM-DD-YYYY}_{doc}.ext', so the
     client name is the second underscore-delimited token. Client names carry
-    commas/spaces but not underscores; the most common value across the drawer's
-    files is returned to shrug off any oddball filename.
+    commas/spaces but not underscores, so this token is reliable even when the
+    fuller parse (folder/date matching) fails.
+    """
+    parts = filename.split("_")
+    if len(parts) >= 2 and parts[1].strip():
+        return parts[1].strip()
+    return None
+
+
+def client_name_from_files(files):
+    """Best-effort client name from a drawer's export filenames, or None.
+
+    The most common per-file client name is returned to shrug off any oddball
+    filename.
     """
     counts = {}
     for f in files:
-        parts = f.split("_")
-        if len(parts) >= 2 and parts[1].strip():
-            name = parts[1].strip()
+        name = client_name_from_filename(f)
+        if name:
             counts[name] = counts.get(name, 0) + 1
     if not counts:
         return None

fccs_reorganize.py

@@ -13,11 +13,14 @@ Examples:
   01069_ABRAHAM, REBEKAH L._UltraTax CS 12-31-2008_02-12-2009_2008 Form 1040 Filing Instructions.doc
 
 Output structure (recreates FCCS UI nesting):
-  output/{drawer_id}_{client_name}/Tax Documents/2025/{original_filename}
-  output/{drawer_id}_{client_name}/UltraTax CS/12-31-2008/{original_filename}
-  output/{drawer_id}_{client_name}/Permanent File/{original_filename}
+  output/{client_name}/Tax Documents/2025/{original_filename}
+  output/{client_name}/UltraTax CS/12-31-2008/{original_filename}
+  output/{client_name}/Permanent File/{original_filename}
 
-Files that cannot be parsed go to output/_unparsed/ for manual review.
+Files that cannot be parsed are still filed under their client:
+  output/{client_name}/_unparsed/{original_filename}
+Only files whose client can't be recovered from the leading tokens fall back to
+the top-level output/_unparsed/ for manual review.
 """
 
 import os
@@ -28,6 +31,7 @@ import sys
 from fccs_config import (
     parse_args, load_config, make_logger,
     load_folder_list, build_folder_patterns, decompose_folder_path,
+    client_name_from_filename,
 )
 
 # Regex for the creation date field (MM-DD-YYYY) bounded by underscores
@@ -126,8 +130,17 @@ def main():
         result = parse_filename(filename, folder_patterns)
 
         if result is None:
-            log(f"  UNPARSED: {filename}")
-            dest_dir = os.path.join(output_dir, "_unparsed")
+            # Still recover the client from the leading tokens so the file lands
+            # in that client's folder (in an _unparsed subfolder to flag it),
+            # rather than a single top-level bucket. Fall back to the top-level
+            # _unparsed only when even the client can't be determined.
+            client_name = client_name_from_filename(filename)
+            if client_name:
+                dest_dir = os.path.join(output_dir, client_name, "_unparsed")
+                log(f"  UNPARSED (filed under {client_name}): {filename}")
+            else:
+                dest_dir = os.path.join(output_dir, "_unparsed")
+                log(f"  UNPARSED (no client): {filename}")
             failed += 1
         else:
             drawer_id, client_name, folder_parts, date, doc_name = result
@@ -158,7 +171,9 @@ def main():
     log("=" * 60)
     log(f"Reorganization complete: {success} organized, {failed} unparsed")
     if failed:
-        log(f"Review unparsed files in: {os.path.join(output_dir, '_unparsed')}")
+        log("Review unparsed files in each client's _unparsed subfolder "
+            f"(and {os.path.join(output_dir, '_unparsed')} for any without a "
+            "detectable client).")
     log("=" * 60)