fix(normalize): accept unit aliases during conversion (#939)

Convert_units() was validating categories on raw input like "kg" or "ft"
instead of the normalized unit name, so aliases got checked against a
category list that only has canonical names in it. Any alias-based
conversion that should've worked just raised ValidationError instead.

Fixed by normalizing both units before the category check runs.

Also added foot/yard/mile/gallon to the alias map - they already had
conversion factors but weren't mapped to their canonical names, so they'd
still have failed even after the above fix.

Turned out there was a second bug hiding behind the first one: the category
check defaults both sides to None, and None == None is True, so two aliases
from different categories that neither resolved to a real category would
silently pass instead of raising. kg -> ft would just return a number
instead of erroring. Normalizing first fixes this too, since aliases now
resolve to their actual categories and the mismatch gets caught.

Added a regression test locking that second one down - kg->ft and gal->lb
now raise ValidationError instead of silently converting.

Fixes #931.
This commit is contained in:
hari
2026-08-22 13:30:35 +05:00
committed by GitHub
parent 729f4fe932
commit d4fdc1f0d3
2 changed files with 35 additions and 4 deletions
+20 -4
View File
@@ -370,8 +370,12 @@ class UnitConverter:
Raises:
ValidationError: If units are incompatible or not in same category
"""
from_unit = from_unit.lower()
to_unit = to_unit.lower()
# Normalize aliases before validating categories and looking up factors.
# The public API documents abbreviations such as ``kg`` and ``km``;
# validating those raw aliases against the canonical category lists
# incorrectly rejected otherwise supported conversions.
from_unit = self.normalize_unit(from_unit)
to_unit = self.normalize_unit(to_unit)
# Validate units
if not self.validate_units(from_unit, to_unit):
@@ -401,8 +405,8 @@ class UnitConverter:
Returns:
bool: True if units are compatible (same category), False otherwise
"""
from_unit = from_unit.lower()
to_unit = to_unit.lower()
from_unit = self.normalize_unit(from_unit)
to_unit = self.normalize_unit(to_unit)
# Check if both units exist
if (
@@ -498,6 +502,18 @@ class UnitConverter:
"ml": "milliliter",
"milliliter": "milliliter",
"milliliters": "milliliter",
"ft": "foot",
"foot": "foot",
"feet": "foot",
"yd": "yard",
"yard": "yard",
"yards": "yard",
"mi": "mile",
"mile": "mile",
"miles": "mile",
"gal": "gallon",
"gallon": "gallon",
"gallons": "gallon",
}
return unit_map.get(unit_lower, unit_lower)
+15
View File
@@ -1,4 +1,6 @@
import unittest
from semantica.utils.exceptions import ValidationError
from semantica.normalize.number_normalizer import (
NumberNormalizer,
UnitConverter,
@@ -32,6 +34,19 @@ class TestUnitConverter(unittest.TestCase):
# 1 kg = 1000 g
self.assertEqual(self.converter.convert_units(1, "kg", "g"), 1000.0)
def test_convert_accepts_aliases_for_category_validation(self):
# Aliases are part of the documented API, not just parsing syntax.
self.assertEqual(self.converter.convert_units(1, "feet", "m"), 0.3048)
self.assertEqual(self.converter.convert_units(1, "gal", "liter"), 3.78541)
def test_convert_rejects_mismatched_categories_even_for_aliases(self):
# Both units normalize to canonical names first, so the category
# check sees real categories and rejects cross-category conversions.
with self.assertRaises(ValidationError):
self.converter.convert_units(1, "kg", "ft")
with self.assertRaises(ValidationError):
self.converter.convert_units(1, "gal", "lb")
def test_normalize_unit(self):
self.assertEqual(self.converter.normalize_unit("km"), "kilometer")
self.assertEqual(self.converter.normalize_unit("kgs"), "kilogram")