[Python-checkins] r72208 - in python/branches/py3k: Doc/library/codecs.rst Lib/test/test_bytes.py Lib/test/test_codecs.py Lib/test/test_unicode.py Lib/test/test_unicodedata.py Misc/NEWS Objects/unicodeobject.c Python/codecs.c Python/marshal.c

Sat May 2 20:52:14 CEST 2009

Author: martin.v.loewis
Date: Sat May 2 20:52:14 2009
New Revision: 72208
Log:
Issue #3672: Reject surrogates in utf-8 codec; add surrogates error
handler.
Modified:
 python/branches/py3k/Doc/library/codecs.rst
 python/branches/py3k/Lib/test/test_bytes.py
 python/branches/py3k/Lib/test/test_codecs.py
 python/branches/py3k/Lib/test/test_unicode.py
 python/branches/py3k/Lib/test/test_unicodedata.py
 python/branches/py3k/Misc/NEWS
 python/branches/py3k/Objects/unicodeobject.c
 python/branches/py3k/Python/codecs.c
 python/branches/py3k/Python/marshal.c
Modified: python/branches/py3k/Doc/library/codecs.rst
==============================================================================

--- python/branches/py3k/Doc/library/codecs.rst	(original)
+++ python/branches/py3k/Doc/library/codecs.rst	Sat May 2 20:52:14 2009
@@ -323,6 +323,18 @@
 | | (only for encoding). |
 +-------------------------+-----------------------------------------------+
 
+In addition, the following error handlers are specific to a single codec:
+
++------------------+---------+--------------------------------------------+
+| Value | Codec | Meaning |
++==================+=========+============================================+
+| ``'surrogates'`` | utf-8 | Allow encoding and decoding of surrogate |
+| | | codes in UTF-8. |
++------------------+---------+--------------------------------------------+
+
+.. versionadded:: 3.1
+ The ``'surrogates'`` error handler.
+
 The set of allowed values can be extended via :meth:`register_error`.
 
 
Modified: python/branches/py3k/Lib/test/test_bytes.py
==============================================================================
--- python/branches/py3k/Lib/test/test_bytes.py	(original)
+++ python/branches/py3k/Lib/test/test_bytes.py	Sat May 2 20:52:14 2009
@@ -169,13 +169,13 @@
 self.assertEqual(b[start:stop:step], self.type2test(L[start:stop:step]))
 
 def test_encoding(self):
- sample = "Hello world\n\u1234\u5678\u9abc\udef0"
+ sample = "Hello world\n\u1234\u5678\u9abc"
 for enc in ("utf8", "utf16"):
 b = self.type2test(sample, enc)
 self.assertEqual(b, self.type2test(sample.encode(enc)))
 self.assertRaises(UnicodeEncodeError, self.type2test, sample, "latin1")
 b = self.type2test(sample, "latin1", "ignore")
- self.assertEqual(b, self.type2test(sample[:-4], "utf-8"))
+ self.assertEqual(b, self.type2test(sample[:-3], "utf-8"))
 
 def test_decode(self):
 sample = "Hello world\n\u1234\u5678\u9abc\def0\def0"
Modified: python/branches/py3k/Lib/test/test_codecs.py
==============================================================================
--- python/branches/py3k/Lib/test/test_codecs.py	(original)
+++ python/branches/py3k/Lib/test/test_codecs.py	Sat May 2 20:52:14 2009
@@ -541,6 +541,17 @@
 self.check_state_handling_decode(self.encoding,
 u, u.encode(self.encoding))
 
+ def test_lone_surrogates(self):
+ self.assertRaises(UnicodeEncodeError, "\ud800".encode, "utf-8")
+ self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "utf-8")
+
+ def test_surrogates_handler(self):
+ self.assertEquals("abc\ud800def".encode("utf-8", "surrogates"),
+ b"abc\xed\xa0\x80def")
+ self.assertEquals(b"abc\xed\xa0\x80def".decode("utf-8", "surrogates"),
+ "abc\ud800def")
+ self.assertTrue(codecs.lookup_error("surrogates"))
+
 class UTF7Test(ReadTest):
 encoding = "utf-7"
 
@@ -1023,12 +1034,12 @@
 # Skipped
 continue
 # The Unicode strings are given in UTF-8
- orig = str(orig, "utf-8")
+ orig = str(orig, "utf-8", "surrogates")
 if prepped is None:
 # Input contains prohibited characters
 self.assertRaises(UnicodeError, nameprep, orig)
 else:
- prepped = str(prepped, "utf-8")
+ prepped = str(prepped, "utf-8", "surrogates")
 try:
 self.assertEquals(nameprep(orig), prepped)
 except Exception as e:
Modified: python/branches/py3k/Lib/test/test_unicode.py
==============================================================================
--- python/branches/py3k/Lib/test/test_unicode.py	(original)
+++ python/branches/py3k/Lib/test/test_unicode.py	Sat May 2 20:52:14 2009
@@ -886,10 +886,10 @@
 self.assertEqual('\u20ac'.encode('utf-8'), b'\xe2\x82\xac')
 self.assertEqual('\ud800\udc02'.encode('utf-8'), b'\xf0\x90\x80\x82')
 self.assertEqual('\ud84d\udc56'.encode('utf-8'), b'\xf0\xa3\x91\x96')
- self.assertEqual('\ud800'.encode('utf-8'), b'\xed\xa0\x80')
- self.assertEqual('\udc00'.encode('utf-8'), b'\xed\xb0\x80')
+ self.assertEqual('\ud800'.encode('utf-8', 'surrogates'), b'\xed\xa0\x80')
+ self.assertEqual('\udc00'.encode('utf-8', 'surrogates'), b'\xed\xb0\x80')
 self.assertEqual(
- ('\ud800\udc02'*1000).encode('utf-8'),
+ ('\ud800\udc02'*1000).encode('utf-8', 'surrogates'),
 b'\xf0\x90\x80\x82'*1000
 )
 self.assertEqual(
Modified: python/branches/py3k/Lib/test/test_unicodedata.py
==============================================================================
--- python/branches/py3k/Lib/test/test_unicodedata.py	(original)
+++ python/branches/py3k/Lib/test/test_unicodedata.py	Sat May 2 20:52:14 2009
@@ -13,6 +13,7 @@
 import test.support
 
 encoding = 'utf-8'
+errors = 'surrogates'
 
 
 ### Run tests
@@ -61,7 +62,7 @@
 (char + 'ABC').title(),
 
 ]
- h.update(''.join(data).encode(encoding))
+ h.update(''.join(data).encode(encoding, errors))
 result = h.hexdigest()
 self.assertEqual(result, self.expectedchecksum)
 
Modified: python/branches/py3k/Misc/NEWS
==============================================================================
--- python/branches/py3k/Misc/NEWS	(original)
+++ python/branches/py3k/Misc/NEWS	Sat May 2 20:52:14 2009
@@ -12,6 +12,8 @@
 Core and Builtins
 -----------------
 
+- Issue #3672: Reject surrogates in utf-8 codec; add surrogates error handler.
+
 - Issue #5883: In the io module, the BufferedIOBase and TextIOBase ABCs have
 received a new method, detach(). detach() disconnects the underlying stream
 from the buffer or text IO and returns it.
Modified: python/branches/py3k/Objects/unicodeobject.c
==============================================================================
--- python/branches/py3k/Objects/unicodeobject.c	(original)
+++ python/branches/py3k/Objects/unicodeobject.c	Sat May 2 20:52:14 2009
@@ -154,6 +154,11 @@
 0, 0, 0, 0, 0, 0, 0, 0
 };
 
+static PyObject *unicode_encode_call_errorhandler(const char *errors,
+ PyObject **errorHandler,const char *encoding, const char *reason,
+ const Py_UNICODE *unicode, Py_ssize_t size, PyObject **exceptionObject,
+ Py_ssize_t startpos, Py_ssize_t endpos, Py_ssize_t *newpos);
+
 /* Same for linebreaks */
 static unsigned char ascii_linebreak[] = {
 0, 0, 0, 0, 0, 0, 0, 0,
@@ -2214,14 +2219,7 @@
 goto utf8Error;
 }
 ch = ((s[0] & 0x0f) << 12) + ((s[1] & 0x3f) << 6) + (s[2] & 0x3f);
- if (ch < 0x0800) {
- /* Note: UTF-8 encodings of surrogates are considered
- legal UTF-8 sequences;
-
- XXX For wide builds (UCS-4) we should probably try
- to recombine the surrogates into a single code
- unit.
- */
+ if (ch < 0x0800 || (ch >= 0xd800 && ch <= 0xDFFF)) {
 errmsg = "illegal encoding";
 startinpos = s-starts;
 endinpos = startinpos+3;
@@ -2328,6 +2326,8 @@
 Py_ssize_t nallocated; /* number of result bytes allocated */
 Py_ssize_t nneeded; /* number of result bytes needed */
 char stackbuf[MAX_SHORT_UNICHARS * 4];
+ PyObject *errorHandler = NULL;
+ PyObject *exc = NULL;
 
 assert(s != NULL);
 assert(size >= 0);
@@ -2367,6 +2367,7 @@
 else {
 /* Encode UCS2 Unicode ordinals */
 if (ch < 0x10000) {
+#ifndef Py_UNICODE_WIDE
 /* Special case: check for high surrogate */
 if (0xD800 <= ch && ch <= 0xDBFF && i != size) {
 Py_UCS4 ch2 = s[i];
@@ -2379,6 +2380,36 @@
 }
 /* Fall through: handles isolated high surrogates */
 }
+#endif
+ if (ch >= 0xd800 && ch <= 0xdfff) {
+ Py_ssize_t newpos;
+ PyObject *rep;
+ char *prep;
+ int k;
+ rep = unicode_encode_call_errorhandler
+ (errors, &errorHandler, "utf-8", "surrogates not allowed", 
+ s, size, &exc, i-1, i, &newpos);
+ if (!rep)
+ goto error;
+ /* Implementation limitations: only support error handler that return
+ bytes, and only support up to four replacement bytes. */
+ if (!PyBytes_Check(rep)) {
+ PyErr_SetString(PyExc_TypeError, "error handler should have returned bytes");
+ Py_DECREF(rep);
+ goto error;
+ }
+ if (PyBytes_Size(rep) > 4) {
+ PyErr_SetString(PyExc_TypeError, "error handler returned too many bytes");
+ Py_DECREF(rep);
+ goto error;
+ }
+ prep = PyBytes_AsString(rep);
+ for(k = PyBytes_Size(rep); k > 0; k--)
+ *p++ = *prep++;
+ Py_DECREF(rep);
+ continue;
+ 
+ }
 *p++ = (char)(0xe0 | (ch >> 12));
 *p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
 *p++ = (char)(0x80 | (ch & 0x3f));
@@ -2405,7 +2436,14 @@
 assert(nneeded <= nallocated);
 _PyBytes_Resize(&result, nneeded);
 }
+ Py_XDECREF(errorHandler);
+ Py_XDECREF(exc);
 return result;
+ error:
+ Py_XDECREF(errorHandler);
+ Py_XDECREF(exc);
+ Py_XDECREF(result);
+ return NULL;
 
 #undef MAX_SHORT_UNICHARS
 }
@@ -3897,7 +3935,7 @@
 Py_ssize_t startpos, Py_ssize_t endpos,
 Py_ssize_t *newpos)
 {
- static char *argparse = "O!n;encoding error handler must return (str, int) tuple";
+ static char *argparse = "On;encoding error handler must return (str/bytes, int) tuple";
 
 PyObject *restuple;
 PyObject *resunicode;
@@ -3918,15 +3956,20 @@
 if (restuple == NULL)
 return NULL;
 if (!PyTuple_Check(restuple)) {
- PyErr_SetString(PyExc_TypeError, &argparse[4]);
+ PyErr_SetString(PyExc_TypeError, &argparse[3]);
 Py_DECREF(restuple);
 return NULL;
 }
- if (!PyArg_ParseTuple(restuple, argparse, &PyUnicode_Type,
+ if (!PyArg_ParseTuple(restuple, argparse,
 &resunicode, newpos)) {
 Py_DECREF(restuple);
 return NULL;
 }
+ if (!PyUnicode_Check(resunicode) && !PyBytes_Check(resunicode)) {
+ PyErr_SetString(PyExc_TypeError, &argparse[3]);
+ Py_DECREF(restuple);
+ return NULL;
+ }
 if (*newpos<0)
 *newpos = size+*newpos;
 if (*newpos<0 || *newpos>size) {
@@ -4064,6 +4107,12 @@
 collstart-startp, collend-startp, &newpos);
 if (repunicode == NULL)
 goto onError;
+ if (!PyUnicode_Check(repunicode)) {
+ /* Implementation limitation: byte results not supported yet. */
+ PyErr_SetString(PyExc_TypeError, "error handler should return unicode");
+ Py_DECREF(repunicode);
+ goto onError;
+ }
 /* need more space? (at least enough for what we
 have+the replacement+the rest of the string, so
 we won't have to check space for encodable characters) */
@@ -5027,6 +5076,12 @@
 collstartpos, collendpos, &newpos);
 if (repunicode == NULL)
 return -1;
+ if (!PyUnicode_Check(repunicode)) {
+ /* Implementation limitation: byte results not supported yet. */
+ PyErr_SetString(PyExc_TypeError, "error handler should return unicode");
+ Py_DECREF(repunicode);
+ return -1;
+ }
 /* generate replacement */
 repsize = PyUnicode_GET_SIZE(repunicode);
 for (uni2 = PyUnicode_AS_UNICODE(repunicode); repsize-->0; ++uni2) {
@@ -5588,6 +5643,12 @@
 collstart-s, collend-s, &newpos);
 if (repunicode == NULL)
 goto onError;
+ if (!PyUnicode_Check(repunicode)) {
+ /* Implementation limitation: byte results not supported yet. */
+ PyErr_SetString(PyExc_TypeError, "error handler should return unicode");
+ Py_DECREF(repunicode);
+ goto onError;
+ }
 /* generate replacement */
 repsize = PyUnicode_GET_SIZE(repunicode);
 for (uni2 = PyUnicode_AS_UNICODE(repunicode); repsize-->0; ++uni2) {
Modified: python/branches/py3k/Python/codecs.c
==============================================================================
--- python/branches/py3k/Python/codecs.c	(original)
+++ python/branches/py3k/Python/codecs.c	Sat May 2 20:52:14 2009
@@ -748,6 +748,85 @@
 }
 }
 
+PyObject *PyCodec_SurrogateErrors(PyObject *exc)
+{
+ PyObject *restuple;
+ PyObject *object;
+ Py_ssize_t start;
+ Py_ssize_t end;
+ PyObject *res;
+ if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
+	Py_UNICODE *p;
+	Py_UNICODE *startp;
+	char *outp;
+	if (PyUnicodeEncodeError_GetStart(exc, &start))
+	 return NULL;
+	if (PyUnicodeEncodeError_GetEnd(exc, &end))
+	 return NULL;
+	if (!(object = PyUnicodeEncodeError_GetObject(exc)))
+	 return NULL;
+	startp = PyUnicode_AS_UNICODE(object);
+	res = PyBytes_FromStringAndSize(NULL, 3*(end-start));
+	if (!res) {
+	 Py_DECREF(object);
+	 return NULL;
+	}
+	outp = PyBytes_AsString(res);
+	for (p = startp+start; p < startp+end; p++) {
+	 Py_UNICODE ch = *p;
+	 if (ch < 0xd800 || ch > 0xdfff) {
+		/* Not a surrogate, fail with original exception */
+		PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
+		Py_DECREF(res);
+		Py_DECREF(object);
+		return NULL;
+	 }
+	 *outp++ = (char)(0xe0 | (ch >> 12));
+	 *outp++ = (char)(0x80 | ((ch >> 6) & 0x3f));
+	 *outp++ = (char)(0x80 | (ch & 0x3f));
+	}
+	restuple = Py_BuildValue("(On)", res, end);
+	Py_DECREF(res);
+	Py_DECREF(object);
+	return restuple;
+ }
+ else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
+	unsigned char *p;
+	Py_UNICODE ch = 0;
+	if (PyUnicodeDecodeError_GetStart(exc, &start))
+	 return NULL;
+	if (!(object = PyUnicodeDecodeError_GetObject(exc)))
+	 return NULL;
+	if (!(p = (unsigned char*)PyBytes_AsString(object))) {
+	 Py_DECREF(object);
+	 return NULL;
+	}
+	/* Try decoding a single surrogate character. If
+	 there are more, let the codec call us again. */
+	p += start;
+	if ((p[0] & 0xf0) == 0xe0 || 
+	 (p[1] & 0xc0) == 0x80 ||
+	 (p[2] & 0xc0) == 0x80) {
+	 /* it's a three-byte code */
+	 ch = ((p[0] & 0x0f) << 12) + ((p[1] & 0x3f) << 6) + (p[2] & 0x3f);
+	 if (ch < 0xd800 || ch > 0xdfff)
+		/* it's not a surrogate - fail */
+		ch = 0;
+	}
+	Py_DECREF(object);
+	if (ch == 0) {
+	 PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
+	 return NULL;
+	}
+	return Py_BuildValue("(u#n)", &ch, 1, start+3);
+ }
+ else {
+	wrong_exception_type(exc);
+	return NULL;
+ }
+}
+
+	
 static PyObject *strict_errors(PyObject *self, PyObject *exc)
 {
 return PyCodec_StrictErrors(exc);
@@ -777,6 +856,11 @@
 return PyCodec_BackslashReplaceErrors(exc);
 }
 
+static PyObject *surrogates_errors(PyObject *self, PyObject *exc)
+{
+ return PyCodec_SurrogateErrors(exc);
+}
+
 static int _PyCodecRegistry_Init(void)
 {
 static struct {
@@ -823,6 +907,14 @@
 		backslashreplace_errors,
 		METH_O
 	 }
+	},
+	{
+	 "surrogates",
+	 {
+		"surrogates",
+		surrogates_errors,
+		METH_O
+	 }
 	}
 };
 
Modified: python/branches/py3k/Python/marshal.c
==============================================================================
--- python/branches/py3k/Python/marshal.c	(original)
+++ python/branches/py3k/Python/marshal.c	Sat May 2 20:52:14 2009
@@ -312,7 +312,9 @@
 	}
 	else if (PyUnicode_CheckExact(v)) {
 	 PyObject *utf8;
-		utf8 = PyUnicode_AsUTF8String(v);
+		utf8 = PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(v),
+					 PyUnicode_GET_SIZE(v),
+					 "surrogates");
 		if (utf8 == NULL) {
 			p->depth--;
 			p->error = WFERR_UNMARSHALLABLE;
@@ -810,7 +812,7 @@
 			retval = NULL;
 			break;
 		}
-		v = PyUnicode_DecodeUTF8(buffer, n, NULL);
+		v = PyUnicode_DecodeUTF8(buffer, n, "surrogates");
 		PyMem_DEL(buffer);
 		retval = v;
 		break;
