[Python-checkins] CVS: python/dist/src/Objects unicodeobject.c,2.130,2.131

2002年3月21日 00:55:30 -0800

Update of /cvsroot/python/python/dist/src/Objects
In directory usw-pr-cvs1:/tmp/cvs-serv3002/Objects
Modified Files:
	unicodeobject.c 
Log Message:
Do not insert characters for unicode-escape decoders if the error mode
is "ignore". Fixes #529104.
Index: unicodeobject.c
===================================================================
RCS file: /cvsroot/python/python/dist/src/Objects/unicodeobject.c,v
retrieving revision 2.130
retrieving revision 2.131
diff -C2 -d -r2.130 -r2.131
*** unicodeobject.c	28 Feb 2002 11:38:24 -0000	2.130
--- unicodeobject.c	21 Mar 2002 08:55:28 -0000	2.131
***************
*** 1515,1520 ****
 
 static
! int unicodeescape_decoding_error(const char **source,
! Py_UNICODE *x,
 const char *errors,
 const char *details) 
--- 1515,1519 ----
 
 static
! int unicodeescape_decoding_error(Py_UNICODE **x,
 const char *errors,
 const char *details) 
***************
*** 1531,1535 ****
 }
 else if (strcmp(errors,"replace") == 0) {
! *x = Py_UNICODE_REPLACEMENT_CHARACTER;
 return 0;
 }
--- 1530,1535 ----
 }
 else if (strcmp(errors,"replace") == 0) {
! **x = Py_UNICODE_REPLACEMENT_CHARACTER;
! 	(*x)++;
 return 0;
 }
***************
*** 1629,1635 ****
 c = (unsigned char) s[i];
 if (!isxdigit(c)) {
! if (unicodeescape_decoding_error(&s, &x, errors, message))
 goto onError;
! chr = x;
 i++;
 break;
--- 1629,1635 ----
 c = (unsigned char) s[i];
 if (!isxdigit(c)) {
! if (unicodeescape_decoding_error(&p, errors, message))
 goto onError;
! chr = 0xffffffff;
 i++;
 break;
***************
*** 1644,1647 ****
--- 1644,1651 ----
 }
 s += i;
+ 	 if (chr == 0xffffffff)
+ 		 /* _decoding_error will have already written into the
+ 		 target buffer. */
+ 		 break;
 store:
 /* when we get here, chr is a 32-bit unicode character */
***************
*** 1661,1669 ****
 } else {
 if (unicodeescape_decoding_error(
! &s, &x, errors,
 "illegal Unicode character")
 )
 goto onError;
- *p++ = x; /* store replacement character */
 }
 break;
--- 1665,1672 ----
 } else {
 if (unicodeescape_decoding_error(
! &p, errors,
 "illegal Unicode character")
 )
 goto onError;
 }
 break;
***************
*** 1700,1711 ****
 }
 }
! if (unicodeescape_decoding_error(&s, &x, errors, message))
 goto onError;
- *p++ = x;
 break;
 
 default:
! *p++ = '\\';
! *p++ = (unsigned char)s[-1];
 break;
 }
--- 1703,1719 ----
 }
 }
! if (unicodeescape_decoding_error(&p, errors, message))
 goto onError;
 break;
 
 default:
! 	 if (s > end) {
! 		if (unicodeescape_decoding_error(&p, errors, "\\ at end of string"))
! 		 goto onError;
! 	 }
! 	 else {
! 		*p++ = '\\';
! 		*p++ = (unsigned char)s[-1];
! 	 }
 break;
 }
***************
*** 1910,1914 ****
 while (s < end) {
 	unsigned char c;
! 	Py_UNICODE x;
 	int i;
 
--- 1918,1922 ----
 while (s < end) {
 	unsigned char c;
! 	Py_UCS4 x;
 	int i;
 
***************
*** 1939,1945 ****
 	 c = (unsigned char)s[i];
 	 if (!isxdigit(c)) {
! 		if (unicodeescape_decoding_error(&s, &x, errors,
 						 "truncated \\uXXXX"))
 		 goto onError;
 		i++;
 		break;
--- 1947,1954 ----
 	 c = (unsigned char)s[i];
 	 if (!isxdigit(c)) {
! 		if (unicodeescape_decoding_error(&p, errors,
 						 "truncated \\uXXXX"))
 		 goto onError;
+ 		x = 0xffffffff;
 		i++;
 		break;
***************
*** 1954,1958 ****
 	}
 	s += i;
! 	*p++ = x;
 }
 if (_PyUnicode_Resize(&v, (int)(p - buf)))
--- 1963,1968 ----
 	}
 	s += i;
! 	if (x != 0xffffffff)
! 		*p++ = x;
 }
 if (_PyUnicode_Resize(&v, (int)(p - buf)))