Attach Costco discounts to purchase rows

enrich_costco.py

@@ -1,6 +1,7 @@
 import csv
 import json
 import re
+from collections import defaultdict
 from pathlib import Path
 
 import click
@@ -29,6 +30,7 @@ HASH_SIZE_RE = re.compile(r"(?<![A-Z0-9])(\d+(?:\.\d+)?)#\b")
 PACK_DASH_RE = re.compile(r"(?<![A-Z0-9])(\d+)\s*-\s*PACK\b")
 PACK_WORD_RE = re.compile(r"(?<![A-Z0-9])(\d+)\s*PACK\b")
 SIZE_RE = re.compile(r"(?<![A-Z0-9])(\d+(?:\.\d+)?)\s*(OZ|LB|LBS|CT|KG|G)\b")
+DISCOUNT_TARGET_RE = re.compile(r"^/\s*(\d+)\b")
 
 
 def clean_costco_name(name):
@@ -156,6 +158,13 @@ def is_discount_item(item):
     return amount < 0 or unit < 0 or description.startswith("/")
 
 
+def discount_target_id(raw_name):
+    match = DISCOUNT_TARGET_RE.match(normalize_whitespace(raw_name))
+    if not match:
+        return ""
+    return match.group(1)
+
+
 def parse_costco_item(order_id, order_date, raw_path, line_no, item):
     raw_name = combine_description(item)
     cleaned_name = clean_costco_name(raw_name)
@@ -190,6 +199,8 @@ def parse_costco_item(order_id, order_date, raw_path, line_no, item):
         "reward_savings": "",
         "coupon_savings": str(item.get("amount", "")) if is_discount_line else "",
         "coupon_price": "",
+        "matched_discount_amount": "",
+        "net_line_total": str(item.get("amount", "")) if not is_discount_line else "",
         "image_url": "",
         "raw_order_path": raw_path.as_posix(),
         "item_name_norm": item_name_norm,
@@ -211,6 +222,51 @@ def parse_costco_item(order_id, order_date, raw_path, line_no, item):
     }
 
 
+def match_costco_discounts(rows):
+    rows_by_order = defaultdict(list)
+    for row in rows:
+        rows_by_order[row["order_id"]].append(row)
+
+    for order_rows in rows_by_order.values():
+        purchase_rows_by_item_id = defaultdict(list)
+        for row in order_rows:
+            if row.get("is_discount_line") == "true":
+                continue
+            retailer_item_id = row.get("retailer_item_id", "")
+            if retailer_item_id:
+                purchase_rows_by_item_id[retailer_item_id].append(row)
+
+        for row in order_rows:
+            if row.get("is_discount_line") != "true":
+                continue
+            target_id = discount_target_id(row.get("item_name", ""))
+            if not target_id:
+                continue
+            matches = purchase_rows_by_item_id.get(target_id, [])
+            if len(matches) != 1:
+                row["parse_notes"] = normalize_whitespace(
+                    f"{row.get('parse_notes', '')};discount_target_unmatched={target_id}"
+                ).strip(";")
+                continue
+
+            purchase_row = matches[0]
+            matched_discount = to_decimal(row.get("line_total"))
+            gross_total = to_decimal(purchase_row.get("line_total"))
+            existing_discount = to_decimal(purchase_row.get("matched_discount_amount")) or 0
+            if matched_discount is None or gross_total is None:
+                continue
+
+            total_discount = existing_discount + matched_discount
+            purchase_row["matched_discount_amount"] = format_decimal(total_discount)
+            purchase_row["net_line_total"] = format_decimal(gross_total + total_discount)
+            purchase_row["parse_notes"] = normalize_whitespace(
+                f"{purchase_row.get('parse_notes', '')};matched_discount={target_id}"
+            ).strip(";")
+            row["parse_notes"] = normalize_whitespace(
+                f"{row.get('parse_notes', '')};matched_to_item={target_id}"
+            ).strip(";")
+
+
 def iter_costco_rows(raw_dir):
     for path in discover_json_files(raw_dir):
         if path.name in {"summary.json", "summary_requests.json"}:
@@ -238,6 +294,7 @@ def discover_json_files(raw_dir):
 
 def build_items_enriched(raw_dir):
     rows = list(iter_costco_rows(raw_dir))
+    match_costco_discounts(rows)
     rows.sort(key=lambda row: (row["order_date"], row["order_id"], int(row["line_no"])))
     return rows