Skip to content
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
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
Next Next commit
bpo-40596: Fix str.isidentifier() for non-canonicalized strings conta…
…ining non-BMP characters on Windows.
  • Loading branch information
serhiy-storchaka committed May 12, 2020
commit 4c06f9ea74da809bd352deab0eb97aa757c2c01d
7 changes: 7 additions & 0 deletions Lib/test/test_unicode.py
Original file line number Diff line number Diff line change
Expand Up @@ -720,6 +720,13 @@ def test_isidentifier(self):
self.assertFalse("©".isidentifier())
self.assertFalse("0".isidentifier())

@support.cpython_only
def test_isidentifier_legacy(self):
import _testcapi
u = '𝖀𝖓𝖎𝖈𝖔𝖉𝖊'
self.assertTrue(u.isidentifier())
self.assertTrue(_testcapi.unicode_legacy_string(u).isidentifier())

def test_isprintable(self):
self.assertTrue("".isprintable())
self.assertTrue(" ".isprintable())
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Fixed :meth:`str.isidentifier` for non-canonicalized strings containing
non-BMP characters on Windows.
20 changes: 17 additions & 3 deletions Objects/unicodeobject.c
Original file line number Diff line number Diff line change
Expand Up @@ -12356,20 +12356,34 @@ PyUnicode_IsIdentifier(PyObject *self)
return len && i == len;
}
else {
Py_ssize_t i, len = PyUnicode_GET_SIZE(self);
Py_ssize_t i = 0, len = PyUnicode_GET_SIZE(self);
if (len == 0) {
/* an empty string is not a valid identifier */
return 0;
}

const wchar_t *wstr = _PyUnicode_WSTR(self);
Py_UCS4 ch = wstr[0];
Py_UCS4 ch = wstr[i++];
if (Py_UNICODE_IS_HIGH_SURROGATE(ch)
&& i < len
&& Py_UNICODE_IS_LOW_SURROGATE(wstr[i]))
{
ch = Py_UNICODE_JOIN_SURROGATES(ch, wstr[i]);
i++;
}
if (!_PyUnicode_IsXidStart(ch) && ch != 0x5F /* LOW LINE */) {
return 0;
}

for (i = 1; i < len; i++) {
for (; i < len; i++) {
ch = wstr[i];
if (Py_UNICODE_IS_HIGH_SURROGATE(ch)
&& i < len
&& Py_UNICODE_IS_LOW_SURROGATE(wstr[i]))
{
ch = Py_UNICODE_JOIN_SURROGATES(ch, wstr[i]);
i++;
}
if (!_PyUnicode_IsXidContinue(ch)) {
return 0;
}
Expand Down