[ArrowStringArray] PERF: use pa.compute.match_substring_regex for str.fullmatch if available (pandas-dev#41332)

Author: simonjayhawkins

asv_bench/benchmarks/strings.py

@@ -85,6 +85,9 @@ def time_find(self, dtype):
     def time_rfind(self, dtype):
         self.s.str.rfind("[A-Z]+")
 
+    def time_fullmatch(self, dtype):
+        self.s.str.fullmatch("A")
+
     def time_get(self, dtype):
         self.s.str.get(0)
 

doc/redirects.csv

@@ -1197,6 +1197,7 @@ generated/pandas.Series.str.extractall,../reference/api/pandas.Series.str.extrac
 generated/pandas.Series.str.extract,../reference/api/pandas.Series.str.extract
 generated/pandas.Series.str.findall,../reference/api/pandas.Series.str.findall
 generated/pandas.Series.str.find,../reference/api/pandas.Series.str.find
+generated/pandas.Series.str.fullmatch,../reference/api/pandas.Series.str.fullmatch
 generated/pandas.Series.str.get_dummies,../reference/api/pandas.Series.str.get_dummies
 generated/pandas.Series.str.get,../reference/api/pandas.Series.str.get
 generated/pandas.Series.str,../reference/api/pandas.Series.str

doc/source/reference/series.rst

@@ -415,6 +415,7 @@ strings and apply several methods to it. These can be accessed like
    Series.str.extractall
    Series.str.find
    Series.str.findall
+   Series.str.fullmatch
    Series.str.get
    Series.str.index
    Series.str.join

pandas/core/arrays/string_arrow.py

@@ -844,6 +844,14 @@ def _str_match(
             pat = "^" + pat
         return self._str_contains(pat, case, flags, na, regex=True)
 
+    def _str_fullmatch(self, pat, case: bool = True, flags: int = 0, na: Scalar = None):
+        if pa_version_under4p0:
+            return super()._str_fullmatch(pat, case, flags, na)
+
+        if not pat.endswith("$") or pat.endswith("//$"):
+            pat = pat + "$"
+        return self._str_match(pat, case, flags, na)
+
     def _str_isalnum(self):
         result = pc.utf8_is_alnum(self._data)
         return BooleanDtype().__from_arrow__(result)

pandas/core/strings/accessor.py

@@ -1170,7 +1170,7 @@ def match(self, pat, case=True, flags=0, na=None):
 
         Returns
         -------
-        Series/array of boolean values
+        Series/Index/array of boolean values
 
         See Also
         --------
@@ -1197,14 +1197,14 @@ def fullmatch(self, pat, case=True, flags=0, na=None):
             If True, case sensitive.
         flags : int, default 0 (no flags)
             Regex module flags, e.g. re.IGNORECASE.
-        na : scalar, optional.
+        na : scalar, optional
             Fill value for missing values. The default depends on dtype of the
             array. For object-dtype, ``numpy.nan`` is used. For ``StringDtype``,
             ``pandas.NA`` is used.
 
         Returns
         -------
-        Series/array of boolean values
+        Series/Index/array of boolean values
 
         See Also
         --------

pandas/tests/strings/test_find_replace.py

@@ -494,10 +494,32 @@ def test_fullmatch(any_string_dtype):
     expected = Series([True, False, np.nan, False], dtype=expected_dtype)
     tm.assert_series_equal(result, expected)
 
+
+def test_fullmatch_na_kwarg(any_string_dtype):
+    ser = Series(
+        ["fooBAD__barBAD", "BAD_BADleroybrown", np.nan, "foo"], dtype=any_string_dtype
+    )
+    result = ser.str.fullmatch(".*BAD[_]+.*BAD", na=False)
+    expected_dtype = np.bool_ if any_string_dtype == "object" else "boolean"
+    expected = Series([True, False, False, False], dtype=expected_dtype)
+    tm.assert_series_equal(result, expected)
+
+
+def test_fullmatch_case_kwarg(any_string_dtype):
     ser = Series(["ab", "AB", "abc", "ABC"], dtype=any_string_dtype)
-    result = ser.str.fullmatch("ab", case=False)
     expected_dtype = np.bool_ if any_string_dtype == "object" else "boolean"
+
+    expected = Series([True, False, False, False], dtype=expected_dtype)
+
+    result = ser.str.fullmatch("ab", case=True)
+    tm.assert_series_equal(result, expected)
+
     expected = Series([True, True, False, False], dtype=expected_dtype)
+
+    result = ser.str.fullmatch("ab", case=False)
+    tm.assert_series_equal(result, expected)
+
+    result = ser.str.fullmatch("ab", flags=re.IGNORECASE)
     tm.assert_series_equal(result, expected)