mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-26 18:29:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

Issue #25318: Avoid sprintf() in backslashreplace()

Browse source 
Rewrite backslashreplace() to be closer to PyCodec_BackslashReplaceErrors().

Add also unit tests for non-BMP characters.
This commit is contained in:
Victor Stinner 2015-10-09 03:17:30 +02:00
parent b13b97d3b8
commit 797485e101
2 changed files with 22 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Lib/test/test_codecs.py
View file

@ -3155,7 +3155,8 @@ class ASCIITest(unittest.TestCase):
('[\x80\xff\u20ac]', 'ignore', b'[]'), ('[\x80\xff\u20ac]', 'ignore', b'[]'),
('[\x80\xff\u20ac]', 'replace', b'[???]'), ('[\x80\xff\u20ac]', 'replace', b'[???]'),
('[\x80\xff\u20ac]', 'xmlcharrefreplace', b'[€ÿ€]'), ('[\x80\xff\u20ac]', 'xmlcharrefreplace', b'[€ÿ€]'),
('[\x80\xff\u20ac]', 'backslashreplace', b'[\\x80\\xff\\u20ac]'), ('[\x80\xff\u20ac\U000abcde]', 'backslashreplace',
b'[\\x80\\xff\\u20ac\\U000abcde]'),
('[\udc80\udcff]', 'surrogateescape', b'[\x80\xff]'), ('[\udc80\udcff]', 'surrogateescape', b'[\x80\xff]'),
): ):
with self.subTest(data=data, error_handler=error_handler, with self.subTest(data=data, error_handler=error_handler,
@ -3197,7 +3198,8 @@ class Latin1Test(unittest.TestCase):
for data, error_handler, expected in ( for data, error_handler, expected in (
('[\u20ac\udc80]', 'ignore', b'[]'), ('[\u20ac\udc80]', 'ignore', b'[]'),
('[\u20ac\udc80]', 'replace', b'[??]'), ('[\u20ac\udc80]', 'replace', b'[??]'),
('[\u20ac\udc80]', 'backslashreplace', b'[\\u20ac\\udc80]'), ('[\u20ac\U000abcde]', 'backslashreplace',
b'[\\u20ac\\U000abcde]'),
('[\u20ac\udc80]', 'xmlcharrefreplace', b'[€�]'), ('[\u20ac\udc80]', 'xmlcharrefreplace', b'[€�]'),
('[\udc80\udcff]', 'surrogateescape', b'[\x80\xff]'), ('[\udc80\udcff]', 'surrogateescape', b'[\x80\xff]'),
): ):

25
Objects/unicodeobject.c
View file

@ -610,14 +610,25 @@ backslashreplace(_PyBytesWriter *writer, Py_ssize_t prealloc_per_char,
/* generate replacement */ /* generate replacement */
for (i = collstart; i < collend; ++i) { for (i = collstart; i < collend; ++i) {
ch = PyUnicode_READ(kind, data, i); ch = PyUnicode_READ(kind, data, i);
if (ch < 0x100) *str++ = '\\';
str += sprintf(str, "\\x%02x", ch); if (ch >= 0x00010000) {
else if (ch < 0x10000) *str++ = 'U';
str += sprintf(str, "\\u%04x", ch); *str++ = Py_hexdigits[(ch>>28)&0xf];
else { *str++ = Py_hexdigits[(ch>>24)&0xf];
assert(ch <= MAX_UNICODE); *str++ = Py_hexdigits[(ch>>20)&0xf];
str += sprintf(str, "\\U%08x", ch); *str++ = Py_hexdigits[(ch>>16)&0xf];
*str++ = Py_hexdigits[(ch>>12)&0xf];
*str++ = Py_hexdigits[(ch>>8)&0xf];
} }
else if (ch >= 0x100) {
*str++ = 'u';
*str++ = Py_hexdigits[(ch>>12)&0xf];
*str++ = Py_hexdigits[(ch>>8)&0xf];
}
else
*str++ = 'x';
*str++ = Py_hexdigits[(ch>>4)&0xf];
*str++ = Py_hexdigits[ch&0xf];
} }
return str; return str;
} }