[Python-checkins] CVS: python/dist/src/Objects unicodeobject.c,2.124,2.125

2002年2月06日 10:09:04 -0800

Update of /cvsroot/python/python/dist/src/Objects
In directory usw-pr-cvs1:/tmp/cvs-serv6841/Objects
Modified Files:
	unicodeobject.c 
Log Message:
Fix for the UTF-8 memory allocation bug and the UTF-8 encoding
bug related to lone high surrogates.
Index: unicodeobject.c
===================================================================
RCS file: /cvsroot/python/python/dist/src/Objects/unicodeobject.c,v
retrieving revision 2.124
retrieving revision 2.125
diff -C2 -d -r2.124 -r2.125
*** unicodeobject.c	2001年12月06日 20:03:56	2.124
--- unicodeobject.c	2002年02月06日 18:09:02	2.125
***************
*** 1172,1182 ****
 PyObject *v;
 char *p;
! char *q;
! Py_UCS4 ch2;
! unsigned int cbAllocated = 3 * size;
 unsigned int cbWritten = 0;
 int i = 0;
 
! v = PyString_FromStringAndSize(NULL, cbAllocated);
 if (v == NULL)
 return NULL;
--- 1172,1180 ----
 PyObject *v;
 char *p;
! unsigned int cbAllocated = 2 * size;
 unsigned int cbWritten = 0;
 int i = 0;
 
! v = PyString_FromStringAndSize(NULL, cbAllocated + 4);
 if (v == NULL)
 return NULL;
***************
*** 1184,1194 ****
 return v;
 
! p = q = PyString_AS_STRING(v);
 while (i < size) {
 Py_UCS4 ch = s[i++];
 if (ch < 0x80) {
 *p++ = (char) ch;
 cbWritten++;
 }
 else if (ch < 0x0800) {
 *p++ = 0xc0 | (ch >> 6);
--- 1182,1194 ----
 return v;
 
! p = PyString_AS_STRING(v);
 while (i < size) {
 Py_UCS4 ch = s[i++];
+ 
 if (ch < 0x80) {
 *p++ = (char) ch;
 cbWritten++;
 }
+ 
 else if (ch < 0x0800) {
 *p++ = 0xc0 | (ch >> 6);
***************
*** 1196,1230 ****
 cbWritten += 2;
 }
- else if (ch < 0x10000) {
- /* Check for high surrogate */
- if (0xD800 <= ch && ch <= 0xDBFF) {
- if (i != size) {
- ch2 = s[i];
- if (0xDC00 <= ch2 && ch2 <= 0xDFFF) {
 
! if (cbWritten >= (cbAllocated - 4)) {
! 			 /* Provide enough room for some more
! 			 surrogates */
! 			 cbAllocated += 4*10;
! if (_PyString_Resize(&v, cbAllocated))
 				goto onError;
 }
 
! /* combine the two values */
 ch = ((ch - 0xD800)<<10 | (ch2-0xDC00))+0x10000;
- 
 *p++ = (char)((ch >> 18) | 0xf0);
 *p++ = (char)(0x80 | ((ch >> 12) & 0x3f));
 i++;
 cbWritten += 4;
 }
 }
- }
- else {
 *p++ = (char)(0xe0 | (ch >> 12));
- cbWritten += 3;
- }
 *p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
 *p++ = (char)(0x80 | (ch & 0x3f));
 } else {
 *p++ = 0xf0 | (ch>>18);
--- 1196,1233 ----
 cbWritten += 2;
 }
 
! else {
! 	 
! 	 /* Assure that we have enough room for high order Unicode
! 	 ordinals */
! 	 if (cbWritten >= cbAllocated) {
! 		cbAllocated += 4 * 10;
! 		if (_PyString_Resize(&v, cbAllocated + 4))
 				goto onError;
+ 		p = PyString_AS_STRING(v) + cbWritten;
 }
 
! 	 if (ch < 0x10000) {
! 		/* Check for high surrogate */
! 		if (0xD800 <= ch && ch <= 0xDBFF && i != size) {
! 		 Py_UCS4 ch2 = s[i];
! 		 /* Check for low surrogate */
! 		 if (0xDC00 <= ch2 && ch2 <= 0xDFFF) {
 ch = ((ch - 0xD800)<<10 | (ch2-0xDC00))+0x10000;
 *p++ = (char)((ch >> 18) | 0xf0);
 *p++ = (char)(0x80 | ((ch >> 12) & 0x3f));
+ 			*p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
+ 			*p++ = (char)(0x80 | (ch & 0x3f));
 i++;
 cbWritten += 4;
+ 			continue;
 }
+ 		 /* Fall through: handles isolated high surrogates */
 }
 *p++ = (char)(0xe0 | (ch >> 12));
 *p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
 *p++ = (char)(0x80 | (ch & 0x3f));
+ 		cbWritten += 3;
+ 
 } else {
 *p++ = 0xf0 | (ch>>18);
***************
*** 1235,1240 ****
 	}
 }
 *p = '0円';
! if (_PyString_Resize(&v, p - q))
 	goto onError;
 return v;
--- 1238,1244 ----
 	}
 }
+ }
 *p = '0円';
! if (_PyString_Resize(&v, cbWritten))
 	goto onError;
 return v;