Skip to content

Read numbers grouped with no-break, narrow no-break or thin spaces #1478

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
ChrystianSchutz wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Read numbers grouped with no-break, narrow no-break or thin spaces #1478

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 4 additions & 3 deletions src/lighteval/metrics/utils/extractive_match_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,9 +103,10 @@ def lazy_expr_regex(expr_config: ExprExtractionConfig, language: Language) -> li

# Basic number patterns (no LaTeX)
number_re = (
# Format 1: Numbers with thousand separators (e.g., "1,234.56" or "1 234.56")
# Format 1: Numbers with thousand separators (e.g., "1,234.56" or "1 234.56"). The space can also be a no-break,
# narrow no-break or thin space (U+00A0, U+202F, U+2009). The last group must not be followed by another digit.
r"(?:"
r"(?P<integer1>-?\d{1,3}(?:[ ,]\d{3})+)(?P<decimal1>\.\d+)?|"
r"(?P<integer1>-?\d{1,3}(?:[ ,\u00a0\u202f\u2009]\d{3})+(?!\d))(?P<decimal1>\.\d+)?|"
# Format 2: Simple numbers with decimal point or comma (e.g., "123.45" or "123,45")
r"(?P<integer2>-?\d+)(?P<decimal2>[.,]\d+)|"
# Format 3: Decimal part only (e.g., ".123")
Expand Down Expand Up @@ -430,7 +431,7 @@ def extract_expr(match: re.Match, timeout_seconds: int) -> tuple[str | sympy.Exp

if integer or decimal:
# This makes sure we can convert numbers like 0001 to 1. Do note that this can convert 0 to '', so we assume an empty string was 0 and convert it back afterwards.
integer = integer.translate(str.maketrans("", "", ", ")).lstrip("0")
integer = integer.translate(str.maketrans("", "", ", \u00a0\u202f\u2009")).lstrip("0")
if len(integer) == 0:
integer = "0"

Expand Down
23 changes: 23 additions & 0 deletions tests/unit/metrics/test_extractive_match.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1146,3 +1146,26 @@ def test_math_extraction_additional_cases(gold, pred, expected):
)
def test_math_numina_cases(gold, pred, expected):
assert compare_strings(gold, pred, match_types=["latex", "expr"]) == expected


@pytest.mark.parametrize(
"gold,pred,expected",
[
# No-break, narrow no-break and thin spaces are digit-group separators, like the ASCII space and the comma
("2500", "ANSWER: 2\u202f500", 1),
("2", "ANSWER: 2\u202f500", 0),
("2500", "ANSWER: 2\u00a0500", 1),
("2", "ANSWER: 2\u00a0500", 0),
("2500", "The total is 2\u2009500.", 1),
("500", "The total is 2\u2009500.", 0),
("1250000", "ANSWER: 1\u202f250\u202f000", 1),
("1234.5", "ANSWER: 1\u202f234.5", 1),
("2500", "ANSWER: 2 500", 1),
# A group that is not exactly three digits is not joined
("7", "ANSWER: 7\u202f1234", 1),
("7", "ANSWER: 7 1234", 1),
("12", "ANSWER: 12\u202fapples", 1),
],
)
def test_typographic_digit_group_spaces(gold, pred, expected):
assert compare_strings(gold, pred, match_types=["latex", "expr"]) == expected