bpo-32677: Add .isascii() to str, bytes and bytearray (GH-5342)

Doc/library/stdtypes.rst

@@ -1653,6 +1653,15 @@ expression support in the :mod:`re` module).
    from the "Alphabetic" property defined in the Unicode Standard.
 
 
+.. method:: str.isascii()
+
+   Return true if the string is empty or all characters in the string are ASCII,
+   false otherwise.
+   ASCII characters have code points in the range U+0000-U+007F.
+
+   .. versionadded:: 3.7
+
+
 .. method:: str.isdecimal()
 
    Return true if all characters in the string are decimal
@@ -2941,6 +2950,16 @@ place, and instead produce new objects.
       False
 
 
+.. method:: bytes.isascii()
+            bytearray.isascii()
+
+   Return true if the sequence is empty or all bytes in the sequence are ASCII,
+   false otherwise.
+   ASCII bytes are in the range 0-0x7F.
+
+   .. versionadded:: 3.7
+
+
 .. method:: bytes.isdigit()
             bytearray.isdigit()
 

Include/bytes_methods.h

@@ -9,6 +9,7 @@
 extern PyObject* _Py_bytes_isspace(const char *cptr, Py_ssize_t len);
 extern PyObject* _Py_bytes_isalpha(const char *cptr, Py_ssize_t len);
 extern PyObject* _Py_bytes_isalnum(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_isascii(const char *cptr, Py_ssize_t len);
 extern PyObject* _Py_bytes_isdigit(const char *cptr, Py_ssize_t len);
 extern PyObject* _Py_bytes_islower(const char *cptr, Py_ssize_t len);
 extern PyObject* _Py_bytes_isupper(const char *cptr, Py_ssize_t len);
@@ -37,6 +38,7 @@ extern PyObject* _Py_bytes_maketrans(Py_buffer *frm, Py_buffer *to);
 extern const char _Py_isspace__doc__[];
 extern const char _Py_isalpha__doc__[];
 extern const char _Py_isalnum__doc__[];
+extern const char _Py_isascii__doc__[];
 extern const char _Py_isdigit__doc__[];
 extern const char _Py_islower__doc__[];
 extern const char _Py_isupper__doc__[];

Lib/collections/__init__.py

@@ -1214,6 +1214,7 @@ class UserString(Sequence):
         return self.data.index(sub, start, end)
     def isalpha(self): return self.data.isalpha()
     def isalnum(self): return self.data.isalnum()
+    def isascii(self): return self.data.isascii()
     def isdecimal(self): return self.data.isdecimal()
     def isdigit(self): return self.data.isdigit()
     def isidentifier(self): return self.data.isidentifier()

Lib/test/string_tests.py

@@ -909,6 +909,14 @@ class BaseTest:
         self.checkequal(False, 'abc\n', 'isalnum')
         self.checkraises(TypeError, 'abc', 'isalnum', 42)
 
+    def test_isascii(self):
+        self.checkequal(True, '', 'isascii')
+        self.checkequal(True, '\x00', 'isascii')
+        self.checkequal(True, '\x7f', 'isascii')
+        self.checkequal(True, '\x00\x7f', 'isascii')
+        self.checkequal(False, '\x80', 'isascii')
+        self.checkequal(False, '\xe9', 'isascii')
+
     def test_isdigit(self):
         self.checkequal(False, '', 'isdigit')
         self.checkequal(False, 'a', 'isdigit')

Lib/test/test_doctest.py

@@ -659,7 +659,7 @@ plain ol' Python and is guaranteed to be available.
 
     >>> import builtins
     >>> tests = doctest.DocTestFinder().find(builtins)
-    >>> 790 < len(tests) < 810 # approximate number of objects with docstrings
+    >>> 800 < len(tests) < 820 # approximate number of objects with docstrings
     True
     >>> real_tests = [t for t in tests if len(t.examples) > 0]
     >>> len(real_tests) # objects that actually have doctests

Lib/test/test_unicode.py

@@ -638,6 +638,11 @@ class UnicodeTest(string_tests.CommonTest,
         self.assertFalse('\U0001F40D'.isalpha())
         self.assertFalse('\U0001F46F'.isalpha())
 
+    def test_isascii(self):
+        super().test_isascii()
+        self.assertFalse("\u20ac".isascii())
+        self.assertFalse("\U0010ffff".isascii())
+
     def test_isdecimal(self):
         self.checkequalnofix(False, '', 'isdecimal')
         self.checkequalnofix(False, 'a', 'isdecimal')

Misc/NEWS.d/next/Core and Builtins/2018-01-26-20-11-09.bpo-32677.xTGfCq.rst

+Add ``.isascii()`` method to ``str``, ``bytes`` and ``bytearray``.
+It can be used to test that string contains only ASCII characters.

Objects/bytearrayobject.c

@@ -2159,6 +2159,8 @@ bytearray_methods[] = {
      _Py_isalnum__doc__},
     {"isalpha", (PyCFunction)stringlib_isalpha, METH_NOARGS,
      _Py_isalpha__doc__},
+    {"isascii", (PyCFunction)stringlib_isascii, METH_NOARGS,
+     _Py_isascii__doc__},
     {"isdigit", (PyCFunction)stringlib_isdigit, METH_NOARGS,
      _Py_isdigit__doc__},
     {"islower", (PyCFunction)stringlib_islower, METH_NOARGS,

Objects/bytes_methods.c

@@ -92,6 +92,26 @@ _Py_bytes_isalnum(const char *cptr, Py_ssize_t len)
 }
 
 
+PyDoc_STRVAR_shared(_Py_isascii__doc__,
+"B.isascii() -> bool\n\
+\n\
+Return True if B is empty or all characters in B are ASCII,\n\
+False otherwise.");
+
+PyObject*
+_Py_bytes_isascii(const char *cptr, Py_ssize_t len)
+{
+    const unsigned char *p = (unsigned char *) cptr;
+    const unsigned char *e = p + len;
+    for (; p < e; p++) {
+        if (*p >= 128) {
+            Py_RETURN_FALSE;
+        }
+    }
+    Py_RETURN_TRUE;
+}
+
+
 PyDoc_STRVAR_shared(_Py_isdigit__doc__,
 "B.isdigit() -> bool\n\
 \n\

Objects/bytesobject.c

@@ -2459,6 +2459,8 @@ bytes_methods[] = {
      _Py_isalnum__doc__},
     {"isalpha", (PyCFunction)stringlib_isalpha, METH_NOARGS,
      _Py_isalpha__doc__},
+    {"isascii", (PyCFunction)stringlib_isascii, METH_NOARGS,
+     _Py_isascii__doc__},
     {"isdigit", (PyCFunction)stringlib_isdigit, METH_NOARGS,
      _Py_isdigit__doc__},
     {"islower", (PyCFunction)stringlib_islower, METH_NOARGS,

Objects/clinic/unicodeobject.c.h

@@ -165,6 +165,27 @@ exit:
     return return_value;
 }
 
+PyDoc_STRVAR(unicode_isascii__doc__,
+"isascii($self, /)\n"
+"--\n"
+"\n"
+"Return True if all characters in the string are ASCII, False otherwise.\n"
+"\n"
+"ASCII characters have code points in the range U+0000-U+007F.\n"
+"Empty string is ASCII too.");
+
+#define UNICODE_ISASCII_METHODDEF    \
+    {"isascii", (PyCFunction)unicode_isascii, METH_NOARGS, unicode_isascii__doc__},
+
+static PyObject *
+unicode_isascii_impl(PyObject *self);
+
+static PyObject *
+unicode_isascii(PyObject *self, PyObject *Py_UNUSED(ignored))
+{
+    return unicode_isascii_impl(self);
+}
+
 PyDoc_STRVAR(unicode_islower__doc__,
 "islower($self, /)\n"
 "--\n"
@@ -930,4 +951,4 @@ unicode_sizeof(PyObject *self, PyObject *Py_UNUSED(ignored))
 {
     return unicode_sizeof_impl(self);
 }
-/*[clinic end generated code: output=1ad4e81b68194264 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=561c88c912b8fe3b input=a9049054013a1b77]*/

Objects/stringlib/ctype.h

@@ -22,6 +22,12 @@ stringlib_isalnum(PyObject *self)
     return _Py_bytes_isalnum(STRINGLIB_STR(self), STRINGLIB_LEN(self));
 }
 
+static PyObject*
+stringlib_isascii(PyObject *self)
+{
+    return _Py_bytes_isascii(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
 static PyObject*
 stringlib_isdigit(PyObject *self)
 {

Objects/unicodeobject.c

@@ -11611,6 +11611,25 @@ unicode_index(PyObject *self, PyObject *args)
     return PyLong_FromSsize_t(result);
 }
 
+/*[clinic input]
+str.isascii as unicode_isascii
+
+Return True if all characters in the string are ASCII, False otherwise.
+
+ASCII characters have code points in the range U+0000-U+007F.
+Empty string is ASCII too.
+[clinic start generated code]*/
+
+static PyObject *
+unicode_isascii_impl(PyObject *self)
+/*[clinic end generated code: output=c5910d64b5a8003f input=5a43cbc6399621d5]*/
+{
+    if (PyUnicode_READY(self) == -1) {
+        return NULL;
+    }
+    return PyBool_FromLong(PyUnicode_IS_ASCII(self));
+}
+
 /*[clinic input]
 str.islower as unicode_islower
 
@@ -13801,6 +13820,7 @@ static PyMethodDef unicode_methods[] = {
     UNICODE_UPPER_METHODDEF
     {"startswith", (PyCFunction) unicode_startswith, METH_VARARGS, startswith__doc__},
     {"endswith", (PyCFunction) unicode_endswith, METH_VARARGS, endswith__doc__},
+    UNICODE_ISASCII_METHODDEF
     UNICODE_ISLOWER_METHODDEF
     UNICODE_ISUPPER_METHODDEF
     UNICODE_ISTITLE_METHODDEF