bpo-36502: Correct documentation of str.isspace() (GH-15019)
The documented definition was much broader than the real one:
there are tons of characters with general category "Other",
and we don't (and shouldn't) treat most of them as whitespace.
Rewrite the definition to agree with the comment on
_PyUnicode_IsWhitespace, and with the logic in makeunicodedata.py,
which is what generates that function and so ultimately governs.
Add suitable breadcrumbs so that a reader who wants to pin down
exactly what this definition means (what's a "bidirectional class"
of "B"?) can do so. The `unicodedata` module documentation is an
appropriate central place for our references to Unicode's own copious
documentation, so point there.
Also add to the isspace() test a thorough check that the
implementation agrees with the intended definition.
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index 8be16c8..7bd7f51 100644
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -12,6 +12,7 @@
import struct
import sys
import textwrap
+import unicodedata
import unittest
import warnings
from test import support, string_tests
@@ -617,11 +618,21 @@
self.checkequalnofix(True, '\u2000', 'isspace')
self.checkequalnofix(True, '\u200a', 'isspace')
self.checkequalnofix(False, '\u2014', 'isspace')
- # apparently there are no non-BMP spaces chars in Unicode 6
+ # There are no non-BMP whitespace chars as of Unicode 12.
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F']:
self.assertFalse(ch.isspace(), '{!a} is not space.'.format(ch))
+ @support.requires_resource('cpu')
+ def test_isspace_invariant(self):
+ for codepoint in range(sys.maxunicode + 1):
+ char = chr(codepoint)
+ bidirectional = unicodedata.bidirectional(char)
+ category = unicodedata.category(char)
+ self.assertEqual(char.isspace(),
+ (bidirectional in ('WS', 'B', 'S')
+ or category == 'Zs'))
+
def test_isalnum(self):
super().test_isalnum()
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',