fix(parse): extract Bonanza bill-to lines with mixed case and punctuation

The Bonanza Produce invoice template captured the bill-to name and street
with [A-Z\s] / [A-Z0-9\s] classes, so any store name or address containing
a lowercase letter or punctuation failed to match and came back nil. On the
McCarran invoice that meant both :customer-identifier and :account-number
were empty, leaving the import with nothing to look a client up by.

Anchor instead on the B/I/L/L letters printed down the left margin at the
start of a line (the ship-to block on the right reuses the same letters
mid-line) and take the whole column up to the next column gap, without
restricting the character set. The leading \d on the account-number capture
is what selects the street L line over the name L line.

Every value the template already extracted is unchanged; only the nils
moved. Adds regression tests for both Reno locations, covering the address
that used to drop out and the sibling one that already worked.

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

src/clj/auto_ap/parse/templates.clj

@@ -771,8 +771,22 @@
     :keywords [#"530-544-4136"]
     :extract {:invoice-number #"NO\s+(\d{8,})\s+\d{2}/\d{2}/\d{2}"
               :date #"NO\s+\d{8,}\s+(\d{2}/\d{2}/\d{2})"
-              :customer-identifier #"(?s)I\s+([A-Z][A-Z\s]+?)\s{2,}.*?L\s+([0-9][A-Z0-9\s]+?)(?=\s{2,}|\n)"
-              :account-number #"(?s)L\s+([0-9][A-Z0-9\s]+?)(?=\s{2,}|\n)"
+              ;; The bill-to block spells BILL TO down the left margin, one letter
+              ;; per line, with the customer's details in the column to its right:
+              ;;     B     NICKGK
+              ;;     I     NICK THE GREEK <<McCARRAN>>
+              ;;     L     NICK THE GREEK <<McCARRAN>>
+              ;;     L     10310 N McCARRAN BLVD STE.400
+              ;;           RENO, NV 89503
+              ;; Anchor on those margin letters at the start of a line -- the ship-to
+              ;; block to the right reuses the same letters mid-line -- and take the
+              ;; whole column up to the next column gap. That column carries mixed
+              ;; case and punctuation, so it must not be restricted to [A-Z0-9\s];
+              ;; doing so dropped store names like McCARRAN entirely.
+              :customer-identifier #"(?m)^\s+I\s{2,}(\S.*?)(?:\s{2,}|$)"
+              ;; Both the name and the street sit on an L line; the street is the
+              ;; one that starts with a house number.
+              :account-number #"(?m)^\s+L\s{2,}(\d\S*.*?)(?:\s{2,}|$)"
               :total #"SHIPPED\s+[\d\.]+\s+TOTAL\s+([\d\.]+)"}
     :parser {:date [:clj-time "MM/dd/yy"]
              :total [:trim-commas nil]}}

test/clj/auto_ap/parse/templates_test.clj

@@ -71,6 +71,48 @@
         (is (= "600 VISTA WAY" (str/trim (:account-number result))))
         (is (= "946.24" (:total result)))))))
 
+(deftest parse-bonanza-produce-invoice-03932070
+  (testing "Should parse a Bonanza invoice whose bill-to block carries a mixed-case, punctuated street address"
+    (let [pdf-file (io/file "dev-resources/Bonanza Sample Reno 2.pdf")
+          pdf-text (:out (clojure.java.shell/sh "pdftotext" "-layout" (str pdf-file) "-"))
+          results (sut/parse pdf-text)
+          result (first results)]
+      (is (some? result) "Template should match and return a result")
+      (when result
+        (is (= "Bonanza Produce" (:vendor-code result)))
+        (is (= "03932070" (:invoice-number result)))
+        (let [d (:date result)]
+          (is (= 2026 (time/year d)))
+          (is (= 8 (time/month d)))
+          (is (= 4 (time/day d))))
+        ;; "10310 N McCARRAN BLVD STE.400" has both lowercase letters and a
+        ;; period; an uppercase/digit-only capture used to drop it entirely,
+        ;; leaving the invoice with no identifier to match a client against.
+        (is (= "10310 N McCARRAN BLVD STE.400" (str/trim (:account-number result))))
+        (is (str/starts-with? (:customer-identifier result) "NICK THE GREEK"))
+        (is (str/includes? (:customer-identifier result) "McCARRAN"))
+        (is (= "524.17" (:total result)))))))
+
+(deftest parse-bonanza-produce-invoice-03933054
+  (testing "Should keep parsing the sibling Reno location whose address was already extractable"
+    (let [pdf-file (io/file "dev-resources/Bonanza Sample Reno.pdf")
+          pdf-text (:out (clojure.java.shell/sh "pdftotext" "-layout" (str pdf-file) "-"))
+          results (sut/parse pdf-text)
+          result (first results)]
+      (is (some? result) "Template should match and return a result")
+      (when result
+        (is (= "Bonanza Produce" (:vendor-code result)))
+        (is (= "03933054" (:invoice-number result)))
+        (let [d (:date result)]
+          (is (= 2026 (time/year d)))
+          (is (= 8 (time/month d)))
+          (is (= 7 (time/day d))))
+        (is (= "5140 KIETZKE" (str/trim (:account-number result))))
+        (is (str/starts-with? (:customer-identifier result) "NICK THE GREEK"))
+        (is (str/includes? (:customer-identifier result) "KIETZKE"))
+        ;; Two-page invoice: the totals only appear on the final page.
+        (is (= "955.75" (:total result)))))))
+
 (deftest parse-reel-produce-statement-28676
   (testing "Should parse the Reel Produce statement layout that no longer prints 'Reel Produce' on the page"
     (let [pdf-file (io/file "dev-resources/Statement1_from_REEL_Produce_Inc.28676.pdf")