Fix PyUnicode_FromFormatV("%c") for non-BMP char
Issue #10830: Fix PyUnicode_FromFormatV("%c") for non-BMP characters on
narrow build.
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index e2d67cd..9ad9eed 100644
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -1427,7 +1427,7 @@
# Test PyUnicode_FromFormat()
def test_from_format(self):
support.import_module('ctypes')
- from ctypes import pythonapi, py_object
+ from ctypes import pythonapi, py_object, c_int
if sys.maxunicode == 65535:
name = "PyUnicodeUCS2_FromFormat"
else:
@@ -1452,6 +1452,9 @@
'string, got a non-ASCII byte: 0xe9$',
PyUnicode_FromFormat, b'unicode\xe9=%s', 'ascii')
+ self.assertEqual(PyUnicode_FromFormat(b'%c', c_int(0xabcd)), '\uabcd')
+ self.assertEqual(PyUnicode_FromFormat(b'%c', c_int(0x10ffff)), '\U0010ffff')
+
# other tests
text = PyUnicode_FromFormat(b'%%A:%A', 'abc\xe9\uabcd\U0010ffff')
self.assertEqual(text, r"%A:'abc\xe9\uabcd\U0010ffff'")
diff --git a/Misc/NEWS b/Misc/NEWS
index 7b55d20..5f2f99c 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,9 @@
Core and Builtins
-----------------
+- Issue #10830: Fix PyUnicode_FromFormatV("%c") for non-BMP characters on
+ narrow build.
+
- Issue #11168: Remove filename debug variable from PyEval_EvalFrameEx().
It encoded the Unicode filename to UTF-8, but the encoding fails on
undecodable filename (on surrogate characters) which raises an unexpected
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 069be7b..57baebd 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -813,8 +813,19 @@
switch (*f) {
case 'c':
+ {
+#ifndef Py_UNICODE_WIDE
+ int ordinal = va_arg(count, int);
+ if (ordinal > 0xffff)
+ n += 2;
+ else
+ n++;
+#else
(void)va_arg(count, int);
- /* fall through... */
+ n++;
+#endif
+ break;
+ }
case '%':
n++;
break;
@@ -992,8 +1003,18 @@
switch (*f) {
case 'c':
- *s++ = va_arg(vargs, int);
+ {
+ int ordinal = va_arg(vargs, int);
+#ifndef Py_UNICODE_WIDE
+ if (ordinal > 0xffff) {
+ ordinal -= 0x10000;
+ *s++ = 0xD800 | (ordinal >> 10);
+ *s++ = 0xDC00 | (ordinal & 0x3FF);
+ } else
+#endif
+ *s++ = ordinal;
break;
+ }
case 'd':
makefmt(fmt, longflag, longlongflag, size_tflag, zeropad,
width, precision, 'd');