def test_match_substring_regex():
arr = pa.array(["ab", "abc", "ba", "c", None])
result = pc.match_substring_regex(arr, "^a?b")
expected = pa.array([True, True, True, False, None])
assert expected.equals(result)
arr = pa.array(["aB", "Abc", "BA", "c", None])
result = pc.match_substring_regex(arr, "^a?b", ignore_case=True)
expected = pa.array([True, True, True, False, None])
assert expected.equals(result)
result = pc.match_substring_regex(arr, "^a?b", ignore_case=False)
expected = pa.array([False, False, False, False, None])
assert expected.equals(result)
def _str_endswith(self, pat, na=None):
if hasattr(pc, "match_substring_regex"):
result = pc.match_substring_regex(self._data, re.escape(pat) + "$")
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
else:
return super()._str_endswith(pat, na)
def _str_endswith(self, pat, na=None):
if pa_version_under4p0:
return super()._str_endswith(pat, na)
result = pc.match_substring_regex(self._data, re.escape(pat) + "$")
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
def _str_startswith(self, pat, na=None):
# match_substring_regex added in pyarrow 4.0.0
if hasattr(pc, "match_substring_regex"):
result = pc.match_substring_regex(self._data, "^" + re.escape(pat))
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
else:
return super()._str_startswith(pat, na)
return lib.map_infer_mask(arr, f, mask.view("uint8"))
def _str_contains(self,
pat,
case=True,
flags=0,
na=np.nan,
regex: bool = True):
if flags:
return super()._str_contains(pat, case, flags, na, regex)
if regex:
if pa_version_under4p0 or case is False:
return super()._str_contains(pat, case, flags, na, regex)
else:
result = pc.match_substring_regex(self._data, pat)
else:
if case:
result = pc.match_substring(self._data, pat)
else:
result = pc.match_substring(pc.utf8_upper(self._data),
pat.upper())
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
def _str_startswith(self, pat: str, na=None):
if pa_version_under4p0:
return super()._str_startswith(pat, na)
def test_match_substring_regex():
arr = pa.array(["ab", "abc", "ba", "c", None])
result = pc.match_substring_regex(arr, "^a?b")
expected = pa.array([True, True, True, False, None])
assert expected.equals(result)
