From 07472711e7663dcc37ff2005c75030c1da8ef949 Mon Sep 17 00:00:00 2001
From: dat972 <wayoung12@gmail.com>
Date: Tue, 21 Jul 2026 07:24:50 -0500
Subject: [PATCH] had to error handle the reog script to add safe handling of
 weird folder paths with odd characaters

---
 README.md                                   |   2 +
 __pycache__/fccs_reorganize.cpython-313.pyc | Bin 7875 -> 9235 bytes
 fccs_reorganize.py                          | 109 +++++++++++++-------
 3 files changed, 73 insertions(+), 38 deletions(-)

diff --git a/README.md b/README.md
index e8109ae..4f681ca 100644
--- a/README.md
+++ b/README.md
@@ -94,6 +94,8 @@ Exported filenames follow the format `{drawer_id}_{client_name}_{folder_name}_{c
 
 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/`.
 
+Folder names are sanitized for Windows before use — trailing spaces and periods are stripped from each path component, since Windows can't create a directory ending in a space or dot (e.g. a client named `FARR GROUP, P.L.` becomes `FARR GROUP, P.L`). Reorganization is also resilient per file: if one file can't be placed for any reason, the error is logged and counted (reported as `errored` in the summary) and the run continues with the rest rather than aborting.
+
 ### 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.
diff --git a/__pycache__/fccs_reorganize.cpython-313.pyc b/__pycache__/fccs_reorganize.cpython-313.pyc
index dc228e4a9a260e86513350bab19d761ca4ad9c09..ec4b55aeac18cffb064dc451bf02f801b31bd9b6 100644
GIT binary patch
delta 2832
zcmZuyeQXow8GrBm8Gq+|cI-<Wzxe>;HaI{?0tA90AdX5xLfjkO!e$-z#dw&zaOc!O
zJB+4Qa@uM*x>h7p)#T4;`zI~`c+$2at&{f8Br~%mu_DAKRH@Sb2p_7}PMY?dzXH=v
zdY^mlx!?2ozVGw=;e;|~dv3Lw5Ipb2qd&EGEZRK8XN!TK?Tr{1BsE{8BF1BHA;cLG
zy4c)_`c))67$wLA8EpFetN&QDL{(Oy8ldWWehkPbh(*&c|E)j}iV*!ZsX(yAzM7OH
z5n_pM6d}7&P&5AyKqj~=Jm#>R6cQ;O&vEI?I3`}569ryKW0{-faazRLn8b5w9*Y9L
zkQCx#Mh=-wH4eu(K@iip2H|i#De<wiDBZxB%c9I<fxF6MUWm&$DX5<2xENTHfSu!|
zq!`Elxc#w7ltWh`63~^g#3f~3#-qs;e@;w~it|D?enyf&Wgqyga(%%NK9x$UL8|s;
zEYHU-V@@^&Mn|Tnad>)?o$A3;q47`v?@NQl6eL)47*xGOf-=q|AzcUw05@<0Rf*7)
zmXe7CFX8m%q@3-+vZ%t6bGxv(n3j7hSUH48xl~HVm$=v!wO)Z}04HZbwVJ&tDMJC$
zP?yvV{IZ(qCW%9m8FnW~l=V`@L69tK)s)JHSc>NaJ}#4J42}bqdI49qse2M_Y>_ko
z!Z<A159Bu5p^)8q=gPvBrS6i=e>?oh?aK`owR>0lfJg_G-`l+8N5*?wwy(*lh*hw#
zO->Xh#||STSliJ|2N<b5Z*BC$Sy3Os#@b@<AT-le{e}}{ZJaGTYj2#bqss5-{$B0O
zo(9fd$3<-YnyOTAuw*BSfSwIS9IRFOAvJlhDr;t~Hq=Mfbujo5nj@4zO%AiRc^yRJ
z6zl>mxCFP-OZ%1Ysg{fX&si@SaWaUdosFw>o*2{*AaLylgS0@+RBodh(DdGVu)FV0
z#5y8$#HCC+2hArMWoS{pr2DK6wz(nkKp1_5M`@+|lwY`LS93k|c_^LW6_|)YXsuy>
zO^5e5ST7{)W?OBDWgu1Ut|hiLV%Tp5tvdd!%V%g|n*pzS@n`q%##iT9Pu*X|R_(fD
zG!v>LrVrG)-8W>{0-CkWg(6dp4K%{mnrd;F!sG;;H`ZMJep4`mU=SfQ0u^-!TkFni
z-)*c3g7vXxpzW*$sK3wf62{zc^BR~{Enu~v%BPe$3*e4E%}ZcQ0}OXV1y>AqzH&JJ
zCx`@+NeoLc&Y})9bEuxN0da6Mgtm%HuX@BH4BPff#a;*VwX`jM6anx^8)W+@=%N*V
zmY78+G=4No1iS97xDONA(O9k86)#$#eXyP%0n!BpQk$|9jXA(CG1EY@jh6g2`b3A(
z1XV3(0u5@wG;uCSRBkgg05Wu-Ow7T>-@W%u#}mB3U!RkP%Pk{Uxug&}o)TkRN*)e1
z{`?B?vIodF&<TpJ;V;_OMm`o+&u_Q`MR(wfw(n#$)Sr78LMgQzXmMhEW_o&Z8qY~$
zjF;6BfNzq=6vC6F&3Imz<0P4n_u!jG%&YBJkvysFyr>2>3%z-t9E4FZpNeC({a=FN
zk%G=1$MN~f%&4fyYIDaj4-)8wRd3LVq4jc?#JBk&RSY8{!%I9)@v~`lM5steRFu+q
zR!qftDHLQRwS7nsz4DDGN=gID8E;>Ax#`UH7(bUzibBv=)^bupE^A`5iLxdoCM0z_
zN<+$`H*6>ys`3BL+kUWYjq`FkswPnBvifS4lG;8c_2!hdaTs+{KxH+u6jOW*V=NQA
z>;s81!nl+vM(?S&W39RsQUZQmgC#$_mtqbP*-e}McK8YH%^7#}p(fY1t7~<v<QmS6
zKDN6SZoM!e|B-^R)IO3oKXSHj`#V-L%bAsTm)~7`W4q^AVW`v--s~BCt|Rf${Mb`H
za(Rl(q4lBl{RR2{k^8R|JrjSW&pmlrtza(sPv^(B=oS^3J+cm<6A$U(O}sB}-SoCE
z>K}(E9ym_to0f*wEbH;Y*mkRLWpH_L<@hg;Z_@4Cbm!_&iSFIeY1=69=sx**8wC8!
z0H1l|jtO-HRXe`C{)xqQ=j;b(myBzN|6)0?P0@D)i-Eg6i#<y>OVr`qDOHlKi>|Nv
zO4MNP)C)awP<Jv5nLD=@ZY{+&?41wno!dVD%7x_%8@~MyeEZj~mVCz-O?hoTzR9%a
z4cl(d-Na(zuCOSqMmF5R2kziD)3y>=4y^Pn_pDxDKfOLsXf6yEg7;6~A1EGtqr{xe
zpW38bm#!_2XY=6~I@IEQ#X`v)gv6TZqWkr=iM5l3?%zsZW`2{|I63*?<YaLwQabr&
zahNUAKX~Z4@Wevh8UJ8>$+;AJXzBdchAh;k#hJghF#ciqv4zTW3uiwZeJT>j#XOY=
zq%-D>?@erJ4MkJeYIyZ1vo>CE7mWAKn`SB(%pcj&5KX=ph|slvtz>+m?6-Pkv~L;B
zxlAs(g9uNU0BQ{r0BIT{{;oCTjPFl;_w2`{#;X6<3vl4@K1Z4+*OtXzr1q>{Uj5OU
zwBE7qEIRrhS_W#7<-(6F^uKoufcsun$HiC15#5wa`^RRzN{7NNQw;fMdW4)h%8*6I
zbY7z?b~~qrb;V&F@MU8(s-ER&H0UfFqS3e*i$*0I*eR0|FHHg?g_VE$!Z1mJO(=)k
vyG?2@Q2U$w6XjC-sV)-{c*bx9LG6rbkk*pBS<-m7w8r;Gci@we4g&JOyw=oo

delta 1368
zcmZ8hOH3PA6n!)P4ff1<JoeZg+ZdORTt~rt95CUhM6{T1DY&D8Nb9<MTp}~HV+c``
zidCd>HrRa&!wN4gRaG6Kszi#~^ru!`nVJe>SrH4AWeX{rY^pwkq0lG2tNZRf_ug~w
zdwQ_%$1eJBiqZnKzJB%oZPA{jt=L-9{h8~QA*g8|2OvxUaEqx1EhP+EE)c;ZxQBT3
z+dmX!3>^N0X47qWfe#54Mi9XJSO7$F^0iYi0OP;3;HSDs3DlGXz+}ytPas>cvX2(%
z*URQ`0|0Q_)a)34D@eB}$^gB9SA(ElplJ|f1QLF48u6Xl3<605AAXj~1q5ACQ%@lp
zx{(HfT2dj65oysNvZ4{*<XUS5x&apqqnKaa3Pio2EyJ~wCvzwj9IJ(4j;qiI*`V<{
z?mFR9J>GfVib<f(>7w@DHI85cDRPLmkJ1a=InInMRhSzdnT(hj#?3ysXf|=&8P_Eg
zD_TTrP$Tk}kh~>Orxz@!SChcgK(L|?mH%ZG_%h|oQI9Q^8cyI))Ja|V#B4%U4OWZp
zYI(L`%v)-#!z7r`vboTu4RZkK(9NFA*mB0Me6|W&l#v&7NZNcV_{ds`*%8}rFETiM
zivPhcghxOO%`S$E#4PYsZhpgG!{8V8MywNJjz-8hNZ91KLR7ex#E-*L3@$jLxW@`d
zD?ftYRyOh;TR|C?BC&#EYBo|(L>D4b=?zM)kaY&&hfaq_sw$nmNEDRQ;l&xrT~ZY>
zX{ta?&%_o(vvbiIF+4v5zjE5}m<|3#TH(G^1^;xC+6jc6MmyHKsjO<oRt`+OOcV`O
zX(DfEm(}|^L%jP~3+&gjeR*4#JosF1E7~hJ{OkUW&h^fW_NhH@A5IX@7-P=t&D_h(
zZ~3<FZr#qA`u|`C4lW|IgL(UnbL8C&!d%~B+V@B{5snYWd-r?#x5<?oa)07pdMI1F
zMHDT3YB{-_y8rq8J;t`j*bh}oD}AU2tn;M?X>#A87Eq?dC-EUUa6o8Rbq{rkzVzbn
z#ML6rtVZII)o47r)}E&uWyOoyE9*p-kg1EVw)A^>+9xZH)qtc|{c->5N_V__t!7u}
z+}1gZynVy6ZrSBM+q@@JpXb}+1M(Y*+C8&H4is5a%AItlyh(4`xXadUvvozYH5Exl
zQqg2I-Ii5m?qo-^%h|c7%B?%O`rf=bkWlO~mbIoNna~`ofRVeDAkWqvsX+(D<XCrx
zO0Q(6pEQ5xf9&7w7~Jj{{Iw_F@pi6#G{=nXkii3jUL_xri6Ej%IFCj#z}b%8fv#$v
zsK^lmJIcZ5aH!fFKnYcZOgtEV^>PVQQ0f@^4!}>uP1T4)`LjWdWPu2U=EHMhDCA)a
znowwZVJZ}o=+Xnir5Wi>q)1(`xh8;3z?GU>Z5SC!pH*xEep%Dw9L6yA@B<tuN%_;f
Sf`6tY9`qh6fYK&4A<(}r=VS!{

diff --git a/fccs_reorganize.py b/fccs_reorganize.py
index 0f01c9b..9f68d9d 100644
--- a/fccs_reorganize.py
+++ b/fccs_reorganize.py
@@ -97,6 +97,19 @@ def parse_filename(filename, folder_patterns):
     return None
 
 
+def safe_component(name):
+    """Make a single path component safe to create on Windows.
+
+    Windows cannot create a directory whose name ends in a space or a period —
+    os.makedirs raises FileNotFoundError (WinError 3). Client names such as
+    'FARR GROUP, P.L.' (trailing period) or ones with a stray trailing space
+    trigger this, so strip trailing dots/spaces. Falls back to '_' if the name
+    is entirely dots/spaces.
+    """
+    cleaned = name.rstrip(" .")
+    return cleaned if cleaned else "_"
+
+
 def main():
     args = parse_args()
     cfg = load_config(args.config)
@@ -125,55 +138,75 @@ def main():
 
     success = 0
     failed = 0
+    errored = 0
 
     for filename in files:
-        result = parse_filename(filename, folder_patterns)
+        # Defensive per-file: a single bad path (e.g. an un-creatable name) must
+        # not abort the whole run — log it and move on to the next file.
+        try:
+            result = parse_filename(filename, folder_patterns)
 
-        if result is None:
-            # 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}")
+            if result is None:
+                # 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 is unknown.
+                client_name = client_name_from_filename(filename)
+                if client_name:
+                    dest_dir = os.path.join(output_dir,
+                                            safe_component(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}")
+                dest_filename = filename   # keep original name for review
+                parsed = False
             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
-            dest_dir = os.path.join(
-                output_dir,
-                client_name,
-                *folder_parts,
-            )
+                drawer_id, client_name, folder_parts, date, doc_name = result
+                dest_dir = os.path.join(
+                    output_dir,
+                    safe_component(client_name),
+                    *(safe_component(p) for p in folder_parts),
+                )
+                dest_filename = doc_name
+                parsed = True
+
+            os.makedirs(dest_dir, exist_ok=True)
+            src = os.path.join(export_dir, filename)
+            dst = os.path.join(dest_dir, dest_filename)
+
+            # Handle duplicate filenames
+            if os.path.exists(dst):
+                base, fext = os.path.splitext(dest_filename)
+                counter = 1
+                while os.path.exists(dst):
+                    dst = os.path.join(dest_dir, f"{base}_{counter}{fext}")
+                    counter += 1
+                log(f"  DUPLICATE renamed: {dest_filename} -> {os.path.basename(dst)}")
+
+            shutil.copy2(src, dst)
+        except Exception as e:
+            log(f"  ERROR processing {filename}: {e}")
+            errored += 1
+            continue
+
+        # Count only after a successful copy so the totals stay accurate.
+        if parsed:
             success += 1
-
-        os.makedirs(dest_dir, exist_ok=True)
-        src = os.path.join(export_dir, filename)
-        # For parsed files, use just the document name; for unparsed, keep original
-        dest_filename = doc_name if result else filename
-        dst = os.path.join(dest_dir, dest_filename)
-
-        # Handle duplicate filenames
-        if os.path.exists(dst):
-            base, fext = os.path.splitext(dest_filename)
-            counter = 1
-            while os.path.exists(dst):
-                dst = os.path.join(dest_dir, f"{base}_{counter}{fext}")
-                counter += 1
-            log(f"  DUPLICATE renamed: {dest_filename} -> {os.path.basename(dst)}")
-
-        shutil.copy2(src, dst)
+        else:
+            failed += 1
 
     log("=" * 60)
-    log(f"Reorganization complete: {success} organized, {failed} unparsed")
+    log(f"Reorganization complete: {success} organized, {failed} unparsed, "
+        f"{errored} errored")
     if failed:
         log("Review unparsed files in each client's _unparsed subfolder "
             f"(and {os.path.join(output_dir, '_unparsed')} for any without a "
             "detectable client).")
+    if errored:
+        log(f"{errored} file(s) could not be placed due to errors — see the "
+            "ERROR lines above; these were left in the export folder.")
     log("=" * 60)