mirror of
https://github.com/mealie-recipes/mealie.git
synced 2025-07-24 15:49:42 +02:00
feat: Improved Ingredient Matching (#2535)
* added normalization to foods and units
* changed search to reference new normalized fields
* fix tests
* added parsed food matching to backend
* prevent pagination from ordering when searching
* added extra fuzzy matching to sqlite ing matching
* added tests
* only apply search ordering when order_by is null
* enabled post-search fuzzy matching for postgres
* fixed postgres fuzzy search test
* idk why this is failing
* 🤦
* simplified frontend ing matching
and restored automatic unit creation
* tightened food fuzzy threshold
* change to rapidfuzz
* sped up fuzzy matching with process
* fixed units not matching by abbreviation
* fast return for exact matches
* replace db searching with pure fuzz
* added fuzzy normalization
* tightened unit fuzzy matching thresh
* cleaned up comments/var names
* ran matching logic through the dryer
* oops
* simplified order by application logic
This commit is contained in:
Michael Genson
GitHub
parent
084ad4228b
commit
2dfbe9f08d
17 changed files with 738 additions and 97 deletions
|
|
@ -3,9 +3,25 @@ from dataclasses import dataclass
|
|||
from fractions import Fraction
|
||||
|
||||
import pytest
|
||||
from pydantic import UUID4
|
||||
|
||||
from mealie.db.db_setup import session_context
|
||||
from mealie.repos.repository_factory import AllRepositories
|
||||
from mealie.schema.recipe.recipe_ingredient import (
|
||||
CreateIngredientFood,
|
||||
CreateIngredientUnit,
|
||||
IngredientFood,
|
||||
IngredientUnit,
|
||||
ParsedIngredient,
|
||||
RecipeIngredient,
|
||||
SaveIngredientFood,
|
||||
SaveIngredientUnit,
|
||||
)
|
||||
from mealie.schema.user.user import GroupBase
|
||||
from mealie.services.parser_services import RegisteredParser, get_parser
|
||||
from mealie.services.parser_services.crfpp.processor import CRFIngredient, convert_list_to_crf_model
|
||||
from tests.utils.factories import random_int, random_string
|
||||
from tests.utils.fixture_schemas import TestUser
|
||||
|
||||
|
||||
@dataclass
|
||||
|
|
@ -21,6 +37,70 @@ def crf_exists() -> bool:
|
|||
return shutil.which("crf_test") is not None
|
||||
|
||||
|
||||
def build_parsed_ing(food: str | None, unit: str | None) -> ParsedIngredient:
|
||||
ing = RecipeIngredient(unit=None, food=None)
|
||||
if food:
|
||||
ing.food = CreateIngredientFood(name=food)
|
||||
if unit:
|
||||
ing.unit = CreateIngredientUnit(name=unit)
|
||||
|
||||
return ParsedIngredient(input=None, ingredient=ing)
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def unique_local_group_id(database: AllRepositories) -> UUID4:
|
||||
return str(database.groups.create(GroupBase(name=random_string())).id)
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def parsed_ingredient_data(
|
||||
database: AllRepositories, unique_local_group_id: UUID4
|
||||
) -> tuple[list[IngredientFood], list[IngredientUnit]]:
|
||||
foods = database.ingredient_foods.create_many(
|
||||
[
|
||||
SaveIngredientFood(name="potatoes", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="onion", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="green onion", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="frozen pearl onions", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="bell peppers", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="red pepper flakes", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="fresh ginger", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="ground ginger", group_id=unique_local_group_id),
|
||||
SaveIngredientFood(name="ñör̃m̈ãl̈ĩz̈ẽm̈ẽ", group_id=unique_local_group_id),
|
||||
]
|
||||
)
|
||||
|
||||
foods.extend(
|
||||
database.ingredient_foods.create_many(
|
||||
[
|
||||
SaveIngredientFood(name=f"{random_string()} food", group_id=unique_local_group_id)
|
||||
for _ in range(random_int(10, 15))
|
||||
]
|
||||
)
|
||||
)
|
||||
|
||||
units = database.ingredient_units.create_many(
|
||||
[
|
||||
SaveIngredientUnit(name="Cups", group_id=unique_local_group_id),
|
||||
SaveIngredientUnit(name="Tablespoon", group_id=unique_local_group_id),
|
||||
SaveIngredientUnit(name="Teaspoon", group_id=unique_local_group_id),
|
||||
SaveIngredientUnit(name="Stalk", group_id=unique_local_group_id),
|
||||
SaveIngredientUnit(name="My Very Long Unit Name", abbreviation="mvlun", group_id=unique_local_group_id),
|
||||
]
|
||||
)
|
||||
|
||||
units.extend(
|
||||
database.ingredient_foods.create_many(
|
||||
[
|
||||
SaveIngredientUnit(name=f"{random_string()} unit", group_id=unique_local_group_id)
|
||||
for _ in range(random_int(10, 15))
|
||||
]
|
||||
)
|
||||
)
|
||||
|
||||
return foods, units
|
||||
|
||||
|
||||
# TODO - add more robust test cases
|
||||
test_ingredients = [
|
||||
TestIngredient("½ cup all-purpose flour", 0.5, "cup", "all-purpose flour", ""),
|
||||
|
|
@ -47,7 +127,7 @@ def test_nlp_parser():
|
|||
assert model.unit == test_ingredient.unit
|
||||
|
||||
|
||||
def test_brute_parser():
|
||||
def test_brute_parser(unique_user: TestUser):
|
||||
# input: (quantity, unit, food, comments)
|
||||
expectations = {
|
||||
# Dutch
|
||||
|
|
@ -67,12 +147,161 @@ def test_brute_parser():
|
|||
"fresh or frozen",
|
||||
),
|
||||
}
|
||||
parser = get_parser(RegisteredParser.brute)
|
||||
|
||||
for key, val in expectations.items():
|
||||
parsed = parser.parse_one(key)
|
||||
with session_context() as session:
|
||||
parser = get_parser(RegisteredParser.brute, unique_user.group_id, session)
|
||||
|
||||
assert parsed.ingredient.quantity == val[0]
|
||||
assert parsed.ingredient.unit.name == val[1]
|
||||
assert parsed.ingredient.food.name == val[2]
|
||||
assert parsed.ingredient.note in {val[3], None}
|
||||
for key, val in expectations.items():
|
||||
parsed = parser.parse_one(key)
|
||||
|
||||
assert parsed.ingredient.quantity == val[0]
|
||||
assert parsed.ingredient.unit.name == val[1]
|
||||
assert parsed.ingredient.food.name == val[2]
|
||||
assert parsed.ingredient.note in {val[3], None}
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"input, expected_unit_name, expected_food_name, expect_unit_match, expect_food_match",
|
||||
(
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="cup", food="potatoes"),
|
||||
"Cups",
|
||||
"potatoes",
|
||||
True,
|
||||
True,
|
||||
id="basic match",
|
||||
),
|
||||
pytest.param( # this should work in sqlite since "potato" is contained within "potatoes"
|
||||
build_parsed_ing(unit="cup", food="potato"),
|
||||
"Cups",
|
||||
"potatoes",
|
||||
True,
|
||||
True,
|
||||
id="basic fuzzy match",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="tablespoon", food="onion"),
|
||||
"Tablespoon",
|
||||
"onion",
|
||||
True,
|
||||
True,
|
||||
id="nested match 1",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="teaspoon", food="green onion"),
|
||||
"Teaspoon",
|
||||
"green onion",
|
||||
True,
|
||||
True,
|
||||
id="nested match 2",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="cup", food="gren onion"),
|
||||
"Cups",
|
||||
"green onion",
|
||||
True,
|
||||
True,
|
||||
id="nested match 3",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="stalk", food="very unique"),
|
||||
"Stalk",
|
||||
"very unique",
|
||||
True,
|
||||
False,
|
||||
id="no food match",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="cup", food=None),
|
||||
"Cups",
|
||||
None,
|
||||
True,
|
||||
False,
|
||||
id="no food input",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="very unique", food="fresh ginger"),
|
||||
"very unique",
|
||||
"fresh ginger",
|
||||
False,
|
||||
True,
|
||||
id="no unit match",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit=None, food="potatoes"),
|
||||
None,
|
||||
"potatoes",
|
||||
False,
|
||||
True,
|
||||
id="no unit input",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="very unique", food="very unique"),
|
||||
"very unique",
|
||||
"very unique",
|
||||
False,
|
||||
False,
|
||||
id="no matches",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit=None, food=None),
|
||||
None,
|
||||
None,
|
||||
False,
|
||||
False,
|
||||
id="no input",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit="mvlun", food="potatoes"),
|
||||
"My Very Long Unit Name",
|
||||
"potatoes",
|
||||
True,
|
||||
True,
|
||||
id="unit abbreviation",
|
||||
),
|
||||
pytest.param(
|
||||
build_parsed_ing(unit=None, food="n̅ōr̅m̄a̅l̄i̅z̄e̅m̄e̅"),
|
||||
None,
|
||||
"ñör̃m̈ãl̈ĩz̈ẽm̈ẽ",
|
||||
False,
|
||||
True,
|
||||
id="normalization",
|
||||
),
|
||||
),
|
||||
)
|
||||
def test_parser_ingredient_match(
|
||||
expected_food_name: str | None,
|
||||
expected_unit_name: str | None,
|
||||
expect_food_match: bool,
|
||||
expect_unit_match: bool,
|
||||
input: ParsedIngredient,
|
||||
parsed_ingredient_data: tuple[list[IngredientFood], list[IngredientUnit]], # required so database is populated
|
||||
unique_local_group_id: UUID4,
|
||||
):
|
||||
with session_context() as session:
|
||||
parser = get_parser(RegisteredParser.brute, unique_local_group_id, session)
|
||||
parsed_ingredient = parser.find_ingredient_match(input)
|
||||
|
||||
if expected_food_name:
|
||||
assert parsed_ingredient.ingredient.food and parsed_ingredient.ingredient.food.name == expected_food_name
|
||||
else:
|
||||
assert parsed_ingredient.ingredient.food is None
|
||||
|
||||
if expect_food_match:
|
||||
assert isinstance(parsed_ingredient.ingredient.food, IngredientFood)
|
||||
else:
|
||||
assert parsed_ingredient.ingredient.food is None or isinstance(
|
||||
parsed_ingredient.ingredient.food, CreateIngredientFood
|
||||
)
|
||||
|
||||
if expected_unit_name:
|
||||
assert parsed_ingredient.ingredient.unit and parsed_ingredient.ingredient.unit.name == expected_unit_name
|
||||
else:
|
||||
assert parsed_ingredient.ingredient.unit is None
|
||||
|
||||
if expect_unit_match:
|
||||
assert isinstance(parsed_ingredient.ingredient.unit, IngredientUnit)
|
||||
else:
|
||||
assert parsed_ingredient.ingredient.unit is None or isinstance(
|
||||
parsed_ingredient.ingredient.unit, CreateIngredientUnit
|
||||
)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue