fix(sysco): fall back to PAPER & DISP category when description is unmapped

The Sysco importer codes each line item by exact description match against
resources/sysco_line_item_mapping.csv, silently defaulting to GL 50000 (Food
Costs) when the description is absent. Every new or renamed Sysco SKU
therefore leaks into Food Costs until someone hand-patches the CSV, which is
what 38575aa5 did for 34 descriptions.

Add a category-level fallback consulted after the description map and before
the 50000 default, enabled for PAPER & DISP only. The description mapping
still wins wherever it exists, so nothing already mapped changes.

PAPER & DISP is safe to generalize: all 454 mapped PAPER & DISP rows point at
55000, with no exceptions. Of the 852 distinct descriptions ever invoiced
under that category, only 3 resolved elsewhere, each because a row with a
different category shared the description and won the later-wins (into {}).
One of those, DESSERT CUP, was simply mis-categorized -- it is paper, and its
own lid (id 1782 LID DOME DESSERT CUP) was already 55000 -- so correct id 1772
to PAPER & DISP / 55000. The remaining two stay at 50000 on purpose, since
they are not paper: PAD SCRUB S-S 35 GRAM 1.25 OZ (SUPP & EQUIP) and TEST
STRIP SANITIZER QUAT (CHEMICAL/JANTRL).

Verified by replaying both changes over all 1,022,732 DET lines in the 56,010
CSVs under sysco-poller/: every resulting transition is 50000 -> 55000 (10,994
lines, $728,106.62). No line that already resolved to a non-default account
moved.

Note this only affects clients carrying the code-sysco-items feature flag, and
only on import -- already-imported invoices need a separate recode.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

resources/sysco_line_item_mapping.csv

@@ -1770,7 +1770,7 @@ Id,Sysco Category,Sysco Description,Integreat Account,Integreat Account Code,Nic
 1769,PAPER & DISP,CONTAINER PAPER 4/110OZ NTG,Paper Costs,55000,
 1770,PAPER & DISP,CUP PAPER COLD 22 OZ LOGO NTG,Paper Costs,55000,
 1771,PAPER & DISP,CUP PORTION PLAS CLR 1.50 OZ,Paper Costs,55000,
-1772,CANNED AND DRY,DESSERT CUP,Food Costs,50000,
+1772,PAPER & DISP,DESSERT CUP,Paper Costs,55000,
 1773,FROZEN,DESSERT MINI PLAIN BEIGNET,Food Costs,50000,
 1774,CANNED AND DRY,DIP GARLIC TOUM,Food Costs,50000,
 1775,CANNED AND DRY,DRINK ENERGY ORANGE SPRKLNG,Soft Beverage Costs,52000,

src/clj/auto_ap/jobs/sysco.clj

@@ -35,20 +35,34 @@
                      (into {}))))))
   @sysco-name->line)
 
-(defn get-line-account [item-name]
+(defn get-account-by-code [numeric-code]
-  (get (get-sysco->line)
-       item-name
   (ffirst (dc/q '[:find ?a
                   :in $ ?an
                   :where [?a :account/numeric-code ?an]]
                 (dc/db conn)
-                     50000))))
+                numeric-code)))
 
+;; Sysco categories that are unambiguous at the category level, so a line item
+;; whose description is missing from sysco_line_item_mapping.csv still codes
+;; correctly instead of silently defaulting to Food Costs. Only PAPER & DISP
+;; qualifies: all 454 mapped PAPER & DISP descriptions point at 55000, and the
+;; description mapping still wins where it exists.
+(def category->numeric-code {"PAPER & DISP" 55000})
+
+(def default-numeric-code 50000)
+
+(defn get-line-account
+  ([item-name] (get-line-account item-name nil))
+  ([item-name sysco-category]
+   (or (get (get-sysco->line) item-name)
+       (some-> (category->numeric-code sysco-category) get-account-by-code)
+       (get-account-by-code default-numeric-code))))
 
 (def ^:dynamic bucket-name (:data-bucket env))
 
 (def header-keys ["TransCode" "GroupID" "Company" "CustomerNumber" "InvoiceNumber" "RecordType" "Item" "InvoiceDocument" "AccountName" "AccountDunsNo" "InvoiceDate" "AccountDate" "CustomerPONo" "PaymentTerms" "TermsDescription" "StoreNumber" "CustomerName" "AddressLine1" "AddressLine2" "City1" "State1" "Zip1" "Phone1" "Duns1" "Hin1" "Dea1" "TIDCustomer" "ChainNumber" "BidNumber" "ContractNumber" "CompanyNumber" "BriefName" "Address" "Address2" "City2" "State2" "Zip2" "Phone2" "Duns2" "Hin2" "Dea2" "Tid_OPCO" "ObligationIndicator" "Manifest" "Route" "Stop" "TermsDiscountPercent" "TermsDiscountDueDate" "TermsNetDueDate" "TermsDiscountAmount" "TermsDiscountCode" "OrderDate" "DepartmentCode"])
 (def item-price-index 15)
+(def item-category-index 25)
 (def item-name-index 29)
 
 (def summary-keys ["TranCode" "GroupID" "Company" "CustomerNumber" "InvoiceNumber" "RecordType" "Item" "InvoiceDocument" "TotalLines" "TotalQtyInvoice" "TotalQty" "TotalQtySplit" "TotalQtyPounds" "TotalExtendedPrice" "TotalTaxAmount" "TotalInvoiceAmount" "AccountDate"])
@@ -64,7 +78,6 @@
      first
      first)))
 
-
 (defn read-sysco-csv [k]
   (-> (s3/get-object {:bucket-name bucket-name
                       :key k})
@@ -82,13 +95,12 @@
                    butlast
                    (reduce
                     (fn [acc row]
-                       (update acc (get-line-account (nth row item-name-index))
+                      (update acc (get-line-account (nth row item-name-index)
+                                                    (nth row item-category-index))
                               (fnil + 0.0)
-                               (Double/parseDouble (nth row item-price-index))
+                              (Double/parseDouble (nth row item-price-index))))
-                               )
+
-                       )
+                    {}))
-                    {})
-                   )
         items-with-tax (update items (get-line-account "TAX")
                                (fnil + 0.0)
                                tax)
@@ -186,22 +198,16 @@
    (nth (->> (s3/list-objects-v2 {:bucket-name "data.prod.app.integreatconsult.com"
                                   :prefix      "sysco/imported"})
              :object-summaries
-             (map :key)
+             (map :key))
-             )
         i)))
 
-
-
-
-
 (comment
   (with-bindings {#'bucket-name "data.prod.app.integreatconsult.com"}
     (doall
      (for [n (range 930 940)
            :let [result (-> (get-test-invoice-file n)
                             read-sysco-csv
-             (extract-invoice-details (get-sysco-vendor))
+                            (extract-invoice-details (get-sysco-vendor)))]
-             )] 
            #_#_:when (not (check-okay-amount? result))]
 
        result)))
@@ -209,12 +215,9 @@
   (with-bindings {#'bucket-name "data.prod.app.integreatconsult.com"}
     (let [result (-> "sysco/error/SYSCO050_00175962_20241010122639019.csv"
                      read-sysco-csv
-                     (extract-invoice-details (get-sysco-vendor))
+                     (extract-invoice-details (get-sysco-vendor)))]
-                     )]
 
-      result))
+      result)))
-
-  )
 
 (defn import-sysco []
   (let [sysco-vendor (get-sysco-vendor)
@@ -223,7 +226,6 @@
                           :object-summaries
                           (map :key))]
 
-
     (alog/info ::importing-sysco
                :count (count keys)
                :keys (pr-str keys))
@@ -256,6 +258,5 @@
     (doseq [k keys]
       (mark-key k))))
 
-
 (defn -main [& _]
   (execute "sysco" import-sysco))