Dagster Orchestration

app/services/category_registry.py

@@ -53,7 +53,12 @@ from typing import Dict, List, Optional, Tuple
 #                   this category when sanitizing cross-category language
 #                   out of a generated description.
 CATEGORY_REGISTRY: List[Dict[str, object]] = [
-    {"category": "Biscuits & Cookies", "keywords": ["biscuits", "biscuit", "biscit", "biskut", "cookies", "cookie"], "generic_term": "biscuit"},
+    # "bikis" is here so that "Britannia Milk Bikis" resolves as the biscuit it
+    # is. Without it the only keyword in that name is Dairy's "milk", which not
+    # only mislabels the product but hands stage 4 a volume unit rulebook - the
+    # exact "Britannia Milk Bikis - 200ml, 500ml, 1L" defect category_units.py
+    # was written to stop.
+    {"category": "Biscuits & Cookies", "keywords": ["biscuits", "biscuit", "biscit", "biskut", "cookies", "cookie", "bikis"], "generic_term": "biscuit"},
     {"category": "Rusk", "keywords": ["rusks", "rusk"], "generic_term": "rusk"},
     {"category": "Crackers", "keywords": ["crackers", "cracker", "saltine"], "generic_term": "cracker"},
     {"category": "Cakes & Muffins", "keywords": ["cakes", "cake", "muffins", "muffin"], "generic_term": "bakery item"},
@@ -62,6 +67,13 @@ CATEGORY_REGISTRY: List[Dict[str, object]] = [
     {"category": "Candy & Confectionery", "keywords": ["candy", "candies", "toffee", "toffees", "lollipop", "lollipops", "confectionery", "mints", "chewing gum"], "generic_term": "candy"},
     {"category": "Snacks", "keywords": ["snacks", "snack", "chips", "namkeen", "wafers", "wafer", "kurkure", "lays"], "generic_term": "snack"},
     {"category": "Chocolates", "keywords": ["chocolates", "chocolate", "chocate", "choclate", "cocoa", "cadbury chocolate", "dairy milk"], "generic_term": "chocolate"},
+    # Listed ahead of "Cooking Oils" so a drink is resolved before that entry's
+    # very broad bare "oil" keyword gets a chance, and ahead of "Dairy" only in
+    # keywords it does not share - "milk", "lassi" and "buttermilk" are
+    # deliberately left to Dairy. Kept free of "soda" (baking soda is a staple,
+    # not a drink) and of "tea"/"coffee" on their own (those are sold as leaves
+    # and grounds far more often than as a drink).
+    {"category": "Beverages", "keywords": ["beverages", "beverage", "soft drink", "soft drinks", "cold drink", "cold drinks", "carbonated", "aerated drink", "cola", "coke", "juice", "juices", "squash", "sharbat", "energy drink", "sports drink", "mineral water", "packaged drinking water", "lemonade", "iced tea", "thums up", "sprite", "fanta", "limca", "maaza", "pepsi", "mirinda"], "generic_term": "beverage"},
     {"category": "Cooking Oils", "keywords": ["cooking oil", "edible oil", "sunflower oil", "mustard oil", "vanaspati", "refined oil", "oil", "oils"], "generic_term": "cooking oil"},
     {"category": "Atta & Staples", "keywords": ["atta", "wheat flour", "flour", "rice", "dal", "pulses", "staples", "suji", "maida"], "generic_term": "staple product"},
     {"category": "Dairy", "keywords": ["milk", "dairy", "cheese", "paneer", "panner", "paner", "paneerr", "curd", "yogurt", "butter", "ghee", "dahi"], "generic_term": "dairy product"},