Skip to content

fix(normalize): validate symbol currencies #940

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Mr-Neutr0n wants to merge 3 commits into
base: main
Choose a base branch
from
+30 −5
Open

fix(normalize): validate symbol currencies #940

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4194f3b
fix(normalize): validate symbol currencies
Mr-Neutr0n Aug 12, 2026
9d766d7
fix(normalize): match currency codes by token boundaries
Mr-Neutr0n Aug 12, 2026
9ac24e6
Merge branch 'main' into fix/normalize-currency-symbol-codes
ZohaibHassan16 Aug 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions semantica/normalize/number_normalizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -562,6 +562,11 @@ def __init__(self, **config):
"SEK",
"NOK",
"DKK",
"RUB",
"KRW",
"ILS",
"NGN",
Comment thread
qodo-free-for-open-source-projects[bot] marked this conversation as resolved.
"PKR",
]

self.logger.debug("Currency normalizer initialized")
Expand Down Expand Up @@ -606,13 +611,15 @@ def normalize_currency(
# Check for currency code
if not currency_code:
for code in self.currency_codes:
if code in currency_input.upper():
match = re.search(
rf"(?<![A-Z]){re.escape(code)}(?![A-Z])",
currency_input.upper(),
)
if match:
currency_code = code
amount_str = (
currency_input.replace(code, "")
.replace(code.lower(), "")
.strip()
)
currency_input[: match.start()] + currency_input[match.end() :]
).strip()
amount_str = amount_str.replace(",", "").replace(" ", "")
try:
amount = float(amount_str)
Expand Down
18 changes: 18 additions & 0 deletions tests/normalize/test_number_normalizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,24 @@ def test_parse_currency(self):
self.assertEqual(result["amount"], 100.0)
self.assertEqual(result["currency"], "EUR")

def test_symbol_currencies_are_validated_as_supported_codes(self):
for symbol, expected_code in self.normalizer.currency_symbols.items():
result = self.normalizer.normalize_currency(f"{symbol}100")
self.assertEqual(result["currency"], expected_code)
self.assertTrue(self.normalizer.validate_currency_code(result["currency"]))

def test_currency_codes_match_boundaries_without_matching_words(self):
for value in ("RUB100", "100 RUB", "rub 100"):
result = self.normalizer.normalize_currency(value)
self.assertEqual(result["amount"], 100.0)
self.assertEqual(result["currency"], "RUB")

for value in ("ruby 100", "wilson 100"):
result = self.normalizer.normalize_currency(value)
self.assertEqual(result["amount"], 100.0)
self.assertEqual(result["currency"], "USD")


class TestScientificNotationHandler(unittest.TestCase):
def setUp(self):
self.handler = ScientificNotationHandler()
Expand Down
Loading