Better bruteforce parsing for units (#3066)

* try to match units when brute parsing and no amount is matched

* brute parser: better handle multiple word food items

Also checks the case when a food might have been split in a unit + ingredient

* fix formatting

* add test cases for ingredient parsing that don't start with an amount

* parametrized tests and added ingredient data fixture

* fixed group_id ref in tests

* fixed test inputs

* add extra tests for units as third token

---------

Co-authored-by: Michael Genson <71845777+michael-genson@users.noreply.github.com>

mealie/services/parser_services/brute/process.py

@@ -132,7 +132,7 @@ def parse_ingredient(tokens) -> tuple[str, str]:
     return ingredient, note
 
 
-def parse(ing_str) -> BruteParsedIngredient:
+def parse(ing_str, parser) -> BruteParsedIngredient:
     amount = 0.0
     unit = ""
     ingredient = ""
@@ -192,12 +192,20 @@ def parse(ing_str) -> BruteParsedIngredient:
             # which means this is the ingredient
             ingredient = tokens[1]
     except ValueError:
-        try:
-            # can't parse first argument as amount
-            # -> no unit -> parse everything as ingredient
-            ingredient, note = parse_ingredient(tokens)
-        except ValueError:
-            ingredient = " ".join(tokens[1:])
+        # can't parse first argument as amount
+        # try to parse as unit and ingredient (e.g. "a tblsp salt"), with unit in first three tokens
+        # won't work for units that have spaces
+        for index, token in enumerate(tokens[:3]):
+            if parser.find_unit_match(token):
+                unit = token
+                ingredient, note = parse_ingredient(tokens[index + 1 :])
+                break
+        if not unit:
+            try:
+                # no unit -> parse everything as ingredient
+                ingredient, note = parse_ingredient(tokens)
+            except ValueError:
+                ingredient = " ".join(tokens[1:])
 
     if unit_note not in note:
         note += " " + unit_note

mealie/services/parser_services/ingredient_parser.py

@@ -126,22 +126,24 @@ class ABCIngredientParser(ABC):
 
         return store_map[fuzz_result[0]]
 
-    def find_food_match(self, food: IngredientFood | CreateIngredientFood) -> IngredientFood | None:
+    def find_food_match(self, food: IngredientFood | CreateIngredientFood | str) -> IngredientFood | None:
         if isinstance(food, IngredientFood):
             return food
 
-        match_value = IngredientFoodModel.normalize(food.name)
+        food_name = food if isinstance(food, str) else food.name
+        match_value = IngredientFoodModel.normalize(food_name)
         return self.find_match(
             match_value,
             store_map=self.foods_by_alias,
             fuzzy_match_threshold=self.food_fuzzy_match_threshold,
         )
 
-    def find_unit_match(self, unit: IngredientUnit | CreateIngredientUnit) -> IngredientUnit | None:
+    def find_unit_match(self, unit: IngredientUnit | CreateIngredientUnit | str) -> IngredientUnit | None:
         if isinstance(unit, IngredientUnit):
             return unit
 
-        match_value = IngredientUnitModel.normalize(unit.name)
+        unit_name = unit if isinstance(unit, str) else unit.name
+        match_value = IngredientUnitModel.normalize(unit_name)
         return self.find_match(
             match_value,
             store_map=self.units_by_alias,
@@ -155,6 +157,16 @@ class ABCIngredientParser(ABC):
         if ingredient.ingredient.unit and (unit_match := self.find_unit_match(ingredient.ingredient.unit)):
             ingredient.ingredient.unit = unit_match
 
+        # Parser might have wrongly split a food into a unit and food.
+        if isinstance(ingredient.ingredient.food, CreateIngredientFood) and isinstance(
+            ingredient.ingredient.unit, CreateIngredientUnit
+        ):
+            if food_match := self.find_food_match(
+                f"{ingredient.ingredient.unit.name} {ingredient.ingredient.food.name}"
+            ):
+                ingredient.ingredient.food = food_match
+                ingredient.ingredient.unit = None
+
         return ingredient
 
 
@@ -164,7 +176,7 @@ class BruteForceParser(ABCIngredientParser):
     """
 
     def parse_one(self, ingredient: str) -> ParsedIngredient:
-        bfi = brute.parse(ingredient)
+        bfi = brute.parse(ingredient, self)
 
         parsed_ingredient = ParsedIngredient(
             input=ingredient,