Skip to content

restrict parser numeric fields to ASCII digits #1316

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
arib06 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

restrict parser numeric fields to ASCII digits #1316

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
26 changes: 15 additions & 11 deletions arrow/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,24 +155,28 @@ class DateTimeParser:
)
_ESCAPE_RE: ClassVar[Pattern[str]] = re.compile(r"\[[^\[\]]*\]")

_ONE_OR_TWO_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"\d{1,2}")
_ONE_OR_TWO_OR_THREE_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"\d{1,3}")
_ONE_OR_MORE_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"\d+")
_TWO_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"\d{2}")
_THREE_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"\d{3}")
_FOUR_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"\d{4}")
_TZ_Z_RE: ClassVar[Pattern[str]] = re.compile(r"([\+\-])(\d{2})(?:(\d{2}))?|Z")
_TZ_ZZ_RE: ClassVar[Pattern[str]] = re.compile(r"([\+\-])(\d{2})(?:\:(\d{2}))?|Z")
_ONE_OR_TWO_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"[0-9]{1,2}")
_ONE_OR_TWO_OR_THREE_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"[0-9]{1,3}")
_ONE_OR_MORE_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"[0-9]+")
_TWO_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"[0-9]{2}")
_THREE_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"[0-9]{3}")
_FOUR_DIGIT_RE: ClassVar[Pattern[str]] = re.compile(r"[0-9]{4}")
_TZ_Z_RE: ClassVar[Pattern[str]] = re.compile(
r"([\+\-])([0-9]{2})(?:([0-9]{2}))?|Z"
)
_TZ_ZZ_RE: ClassVar[Pattern[str]] = re.compile(
r"([\+\-])([0-9]{2})(?:\:([0-9]{2}))?|Z"
)
_TZ_NAME_RE: ClassVar[Pattern[str]] = re.compile(r"\w[\w+\-/]+")
# NOTE: timestamps cannot be parsed from natural language strings (by removing the ^...$) because it will
# break cases like "15 Jul 2000" and a format list (see issue #447)
_TIMESTAMP_RE: ClassVar[Pattern[str]] = re.compile(r"^\-?\d+\.?\d+$")
_TIMESTAMP_EXPANDED_RE: ClassVar[Pattern[str]] = re.compile(r"^\-?\d+$")
_TIME_RE: ClassVar[Pattern[str]] = re.compile(
r"^(\d{2})(?:\:?(\d{2}))?(?:\:?(\d{2}))?(?:([\.\,])(\d+))?$"
r"^([0-9]{2})(?:\:?([0-9]{2}))?(?:\:?([0-9]{2}))?(?:([\.\,])([0-9]+))?$"
)
_WEEK_DATE_RE: ClassVar[Pattern[str]] = re.compile(
r"(?P<year>\d{4})[\-]?W(?P<week>\d{2})[\-]?(?P<day>\d)?"
r"(?P<year>[0-9]{4})[\-]?W(?P<week>[0-9]{2})[\-]?(?P<day>[0-9])?"
)

_BASE_INPUT_RE_MAP: ClassVar[Dict[_FORMAT_TYPE, Pattern[str]]] = {
Expand Down Expand Up @@ -888,7 +892,7 @@ class TzinfoParser:
"""

_TZINFO_RE: ClassVar[Pattern[str]] = re.compile(
r"^(?:\(UTC)*([\+\-])?(\d{2})(?:\:?(\d{2}))?"
r"^(?:\(UTC)*([\+\-])?([0-9]{2})(?:\:?([0-9]{2}))?"
)

@classmethod
Expand Down
14 changes: 14 additions & 0 deletions tests/test_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,20 @@ def test_parse_numbers(self):
== self.expected
)

def test_parse_non_ascii_digits_rejected(self):
# \d matches the whole Unicode decimal category, so non-ASCII numerals
# (fullwidth, Arabic-Indic, ...) used to slip through the numeric tokens.
with pytest.raises(ParserMatchError):
self.parser.parse("２０２１-０１-０２", "YYYY-MM-DD")

with pytest.raises(ParserMatchError):
self.parser.parse("٢٠٢١-٠١-٠٢", "YYYY-MM-DD")

with pytest.raises(ParserMatchError):
self.parser.parse(
"２０２１-０１-０２T１２:３０:４５", "YYYY-MM-DDTHH:mm:ss"
)

def test_parse_am(self):
with pytest.raises(ParserMatchError):
self.parser.parse("2021-01-30 14:00:00 AM", "YYYY-MM-DD HH:mm:ss A")
Expand Down