traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fix for bug #444493: u'\U00010001' segfaults with current CVS on 

wide builds.
This commit is contained in:
Marc-André Lemburg 2001-07-25 16:05:59 +00:00
parent 784d3df09f
commit 80d1dd5f3b
2 changed files with 23 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
Lib/test/test_unicode.py
View File

@ -455,7 +455,8 @@ for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
u = u'\U00010001\U00020002\U00030003\U00040004\U00050005' u = u'\U00010001\U00020002\U00030003\U00040004\U00050005'
for encoding in ('utf-8', for encoding in ('utf-8',
'utf-16', 'utf-16-le', 'utf-16-be', 'utf-16', 'utf-16-le', 'utf-16-be',
'raw_unicode_escape', 'unicode_escape', 'unicode_internal'): #'raw_unicode_escape',
'unicode_escape', 'unicode_internal'):
verify(unicode(u.encode(encoding),encoding) == u) verify(unicode(u.encode(encoding),encoding) == u)
u = u''.join(map(unichr, range(256))) u = u''.join(map(unichr, range(256)))

27
Objects/unicodeobject.c
View File

@ -1415,7 +1415,6 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
{ {
PyObject *repr; PyObject *repr;
char *p; char *p;
char *q;
static const char *hexdigit = "0123456789abcdef"; static const char *hexdigit = "0123456789abcdef";
@ -1423,7 +1422,7 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
if (repr == NULL) if (repr == NULL)
return NULL; return NULL;
p = q = PyString_AS_STRING(repr); p = PyString_AS_STRING(repr);
if (quotes) { if (quotes) {
*p++ = 'u'; *p++ = 'u';
@ -1432,14 +1431,26 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
} }
while (size-- > 0) { while (size-- > 0) {
Py_UNICODE ch = *s++; Py_UNICODE ch = *s++;
/* Escape quotes */ /* Escape quotes */
if (quotes && (ch == (Py_UNICODE) q[1] || ch == '\\')) { if (quotes &&
(ch == (Py_UNICODE) PyString_AS_STRING(repr)[1] || ch == '\\')) {
*p++ = '\\'; *p++ = '\\';
*p++ = (char) ch; *p++ = (char) ch;
} }
#ifdef Py_UNICODE_WIDE #ifdef Py_UNICODE_WIDE
/* Map 21-bit characters to '\U00xxxxxx' */ /* Map 21-bit characters to '\U00xxxxxx' */
else if (ch >= 0x10000) { else if (ch >= 0x10000) {
int offset = p - PyString_AS_STRING(repr);
/* Resize the string if necessary */
if (offset + 12 > PyString_GET_SIZE(repr)) {
if (_PyString_Resize(&repr, PyString_GET_SIZE(repr) + 100))
goto onError;
p = PyString_AS_STRING(repr) + offset;
}
*p++ = '\\'; *p++ = '\\';
*p++ = 'U'; *p++ = 'U';
*p++ = hexdigit[(ch >> 28) & 0x0000000F]; *p++ = hexdigit[(ch >> 28) & 0x0000000F];
@ -1449,7 +1460,8 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
*p++ = hexdigit[(ch >> 12) & 0x0000000F]; *p++ = hexdigit[(ch >> 12) & 0x0000000F];
*p++ = hexdigit[(ch >> 8) & 0x0000000F]; *p++ = hexdigit[(ch >> 8) & 0x0000000F];
*p++ = hexdigit[(ch >> 4) & 0x0000000F]; *p++ = hexdigit[(ch >> 4) & 0x0000000F];
*p++ = hexdigit[ch & 15]; *p++ = hexdigit[ch & 0x0000000F];
continue;
} }
#endif #endif
/* Map UTF-16 surrogate pairs to Unicode \UXXXXXXXX escapes */ /* Map UTF-16 surrogate pairs to Unicode \UXXXXXXXX escapes */
@ -1487,6 +1499,7 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
*p++ = hexdigit[(ch >> 4) & 0x000F]; *p++ = hexdigit[(ch >> 4) & 0x000F];
*p++ = hexdigit[ch & 0x000F]; *p++ = hexdigit[ch & 0x000F];
} }
/* Map special whitespace to '\t', \n', '\r' */ /* Map special whitespace to '\t', \n', '\r' */
else if (ch == '\t') { else if (ch == '\t') {
*p++ = '\\'; *p++ = '\\';
@ -1500,6 +1513,7 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
*p++ = '\\'; *p++ = '\\';
*p++ = 'r'; *p++ = 'r';
} }
/* Map non-printable US ASCII to '\xhh' */ /* Map non-printable US ASCII to '\xhh' */
else if (ch < ' ' || ch >= 128) { else if (ch < ' ' || ch >= 128) {
*p++ = '\\'; *p++ = '\\';
@ -1507,15 +1521,16 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
*p++ = hexdigit[(ch >> 4) & 0x000F]; *p++ = hexdigit[(ch >> 4) & 0x000F];
*p++ = hexdigit[ch & 0x000F]; *p++ = hexdigit[ch & 0x000F];
} }
/* Copy everything else as-is */ /* Copy everything else as-is */
else else
*p++ = (char) ch; *p++ = (char) ch;
} }
if (quotes) if (quotes)
*p++ = q[1]; *p++ = PyString_AS_STRING(repr)[1];
*p = '\0'; *p = '\0';
if (_PyString_Resize(&repr, p - q)) if (_PyString_Resize(&repr, p - PyString_AS_STRING(repr)))
goto onError; goto onError;
return repr; return repr;