[Python-checkins] r67934 - in python/trunk: Lib/test/pickletester.py Modules/cPickle.c

Sat Dec 27 08:08:48 CET 2008

Author: alexandre.vassalotti
Date: Sat Dec 27 08:08:47 2008
New Revision: 67934
Log:
Fix issue #4730: cPickle corrupts high-unicode strings.
Update outdated copy of PyUnicode_EncodeRawUnicodeEscape.
Add a test case.
Modified:
 python/trunk/Lib/test/pickletester.py
 python/trunk/Modules/cPickle.c
Modified: python/trunk/Lib/test/pickletester.py
==============================================================================

--- python/trunk/Lib/test/pickletester.py	(original)
+++ python/trunk/Lib/test/pickletester.py	Sat Dec 27 08:08:47 2008
@@ -480,14 +480,21 @@
 
 if have_unicode:
 def test_unicode(self):
- endcases = [unicode(''), unicode('<\\u>'), unicode('<\\\u1234>'),
- unicode('<\n>'), unicode('<\\>')]
+ endcases = [u'', u'<\\u>', u'<\\\\u1234>', u'<\n>',
+ u'<\\>', u'<\\\\U00012345>']
 for proto in protocols:
 for u in endcases:
 p = self.dumps(u, proto)
 u2 = self.loads(p)
 self.assertEqual(u2, u)
 
+ def test_unicode_high_plane(self):
+ t = u'\U00012345'
+ for proto in protocols:
+ p = self.dumps(t, proto)
+ t2 = self.loads(p)
+ self.assertEqual(t2, t)
+
 def test_ints(self):
 import sys
 for proto in protocols:
Modified: python/trunk/Modules/cPickle.c
==============================================================================
--- python/trunk/Modules/cPickle.c	(original)
+++ python/trunk/Modules/cPickle.c	Sat Dec 27 08:08:47 2008
@@ -1255,42 +1255,91 @@
 /* A copy of PyUnicode_EncodeRawUnicodeEscape() that also translates
 backslash and newline characters to \uXXXX escapes. */
 static PyObject *
-modified_EncodeRawUnicodeEscape(const Py_UNICODE *s, int size)
+modified_EncodeRawUnicodeEscape(const Py_UNICODE *s, Py_ssize_t size)
 {
-	PyObject *repr;
-	char *p;
-	char *q;
+ PyObject *repr;
+ char *p;
+ char *q;
+
+ static const char *hexdigit = "0123456789abcdef";
+#ifdef Py_UNICODE_WIDE
+ const Py_ssize_t expandsize = 10;
+#else
+ const Py_ssize_t expandsize = 6;
+#endif
 
-	static const char *hexdigit = "0123456789ABCDEF";
+ if (size > PY_SSIZE_T_MAX / expandsize)
+ return PyErr_NoMemory();
 
-	repr = PyString_FromStringAndSize(NULL, 6 * size);
-	if (repr == NULL)
-		return NULL;
-	if (size == 0)
-		return repr;
+ repr = PyString_FromStringAndSize(NULL, expandsize * size);
+ if (repr == NULL)
+ return NULL;
+ if (size == 0)
+	return repr;
 
-	p = q = PyString_AS_STRING(repr);
-	while (size-- > 0) {
-		Py_UNICODE ch = *s++;
-		/* Map 16-bit characters to '\uxxxx' */
-		if (ch >= 256 || ch == '\\' || ch == '\n') {
-			*p++ = '\\';
-			*p++ = 'u';
-			*p++ = hexdigit[(ch >> 12) & 0xf];
-			*p++ = hexdigit[(ch >> 8) & 0xf];
-			*p++ = hexdigit[(ch >> 4) & 0xf];
-			*p++ = hexdigit[ch & 15];
-		}
-		/* Copy everything else as-is */
-		else
-			*p++ = (char) ch;
+ p = q = PyString_AS_STRING(repr);
+ while (size-- > 0) {
+ Py_UNICODE ch = *s++;
+#ifdef Py_UNICODE_WIDE
+	/* Map 32-bit characters to '\Uxxxxxxxx' */
+	if (ch >= 0x10000) {
+ *p++ = '\\';
+ *p++ = 'U';
+ *p++ = hexdigit[(ch >> 28) & 0xf];
+ *p++ = hexdigit[(ch >> 24) & 0xf];
+ *p++ = hexdigit[(ch >> 20) & 0xf];
+ *p++ = hexdigit[(ch >> 16) & 0xf];
+ *p++ = hexdigit[(ch >> 12) & 0xf];
+ *p++ = hexdigit[(ch >> 8) & 0xf];
+ *p++ = hexdigit[(ch >> 4) & 0xf];
+ *p++ = hexdigit[ch & 15];
+ }
+ else
+#else
+	/* Map UTF-16 surrogate pairs to '\U00xxxxxx' */
+	if (ch >= 0xD800 && ch < 0xDC00) {
+	 Py_UNICODE ch2;
+	 Py_UCS4 ucs;
+
+	 ch2 = *s++;
+	 size--;
+	 if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
+		ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF)) + 0x00010000;
+		*p++ = '\\';
+		*p++ = 'U';
+		*p++ = hexdigit[(ucs >> 28) & 0xf];
+		*p++ = hexdigit[(ucs >> 24) & 0xf];
+		*p++ = hexdigit[(ucs >> 20) & 0xf];
+		*p++ = hexdigit[(ucs >> 16) & 0xf];
+		*p++ = hexdigit[(ucs >> 12) & 0xf];
+		*p++ = hexdigit[(ucs >> 8) & 0xf];
+		*p++ = hexdigit[(ucs >> 4) & 0xf];
+		*p++ = hexdigit[ucs & 0xf];
+		continue;
+	 }
+	 /* Fall through: isolated surrogates are copied as-is */
+	 s--;
+	 size++;
 	}
-	*p = '0円';
-	_PyString_Resize(&repr, p - q);
-	return repr;
+#endif
+	/* Map 16-bit characters to '\uxxxx' */
+	if (ch >= 256 || ch == '\\' || ch == '\n') {
+ *p++ = '\\';
+ *p++ = 'u';
+ *p++ = hexdigit[(ch >> 12) & 0xf];
+ *p++ = hexdigit[(ch >> 8) & 0xf];
+ *p++ = hexdigit[(ch >> 4) & 0xf];
+ *p++ = hexdigit[ch & 15];
+ }
+	/* Copy everything else as-is */
+	else
+ *p++ = (char) ch;
+ }
+ *p = '0円';
+ _PyString_Resize(&repr, p - q);
+ return repr;
 }
 
-
 static int
 save_unicode(Picklerobject *self, PyObject *args, int doput)
 {
