Merged revisions 59056-59076 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r59064 | christian.heimes | 2007-11-20 02:48:48 +0100 (Tue, 20 Nov 2007) | 1 line

  Fixed bug #1470
........
  r59066 | martin.v.loewis | 2007-11-20 03:46:02 +0100 (Tue, 20 Nov 2007) | 2 lines

  Patch #1468: Package Lib/test/*.pem.
........
  r59068 | christian.heimes | 2007-11-20 04:21:02 +0100 (Tue, 20 Nov 2007) | 1 line

  Another fix for test_shutil. Martin pointed out that it breaks some build bots
........
  r59073 | nick.coghlan | 2007-11-20 15:55:57 +0100 (Tue, 20 Nov 2007) | 1 line

  Backport some main.c cleanup from the py3k branch
........
  r59076 | amaury.forgeotdarc | 2007-11-21 00:31:27 +0100 (Wed, 21 Nov 2007) | 6 lines

  The incremental decoder for utf-7 must preserve its state between calls.
  Solves issue1460.

  Might not be a backport candidate: a new API function was added,
  and some code may rely on details in utf-7.py.
........

Include/unicodeobject.h

@@ -751,6 +751,13 @@ PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(
     const char *errors		/* error handling */
     );
 
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7Stateful(
+    const char *string, 	/* UTF-7 encoded string */
+    Py_ssize_t length,	 	/* size of string */
+    const char *errors,		/* error handling */
+    Py_ssize_t *consumed	/* bytes consumed */
+    );
+
 PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
     const Py_UNICODE *data, 	/* Unicode char buffer */
     Py_ssize_t length,	 	/* number of Py_UNICODE chars to encode */

Lib/encodings/utf_7.py

@@ -6,34 +6,31 @@ import codecs
 
 ### Codec APIs
 
-class Codec(codecs.Codec):
-
-    # Note: Binding these as C functions will result in the class not
-    # converting them to methods. This is intended.
 encode = codecs.utf_7_encode
-    decode = codecs.utf_7_decode
+
+def decode(input, errors='strict'):
+    return codecs.utf_7_decode(input, errors, True)
 
 class IncrementalEncoder(codecs.IncrementalEncoder):
     def encode(self, input, final=False):
         return codecs.utf_7_encode(input, self.errors)[0]
 
 class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
-    def _buffer_decode(self, input, errors, final):
-        return codecs.utf_7_decode(input, self.errors)
+    _buffer_decode = codecs.utf_7_decode
 
-class StreamWriter(Codec,codecs.StreamWriter):
-    pass
+class StreamWriter(codecs.StreamWriter):
+    encode = codecs.utf_7_encode
 
-class StreamReader(Codec,codecs.StreamReader):
-    pass
+class StreamReader(codecs.StreamReader):
+    decode = codecs.utf_7_decode
 
 ### encodings module API
 
 def getregentry():
     return codecs.CodecInfo(
         name='utf-7',
-        encode=Codec.encode,
-        decode=Codec.decode,
+        encode=encode,
+        decode=decode,
         incrementalencoder=IncrementalEncoder,
         incrementaldecoder=IncrementalDecoder,
         streamreader=StreamReader,

Lib/test/test_codecs.py

@@ -544,7 +544,17 @@ class UTF8Test(ReadTest):
 class UTF7Test(ReadTest):
     encoding = "utf-7"
 
-    # No test_partial() yet, because UTF-7 doesn't support it.
+    def test_partial(self):
+        self.check_partial(
+            "a+-b",
+            [
+                "a",
+                "a",
+                "a+",
+                "a+-",
+                "a+-b",
+            ]
+        )
 
 class UTF16ExTest(unittest.TestCase):
 

Modules/_codecsmodule.c

@@ -255,13 +255,20 @@ utf_7_decode(PyObject *self,
     const char *data;
     Py_ssize_t size;
     const char *errors = NULL;
+    int final = 0;
+    Py_ssize_t consumed;
+    PyObject *decoded = NULL;
 
-    if (!PyArg_ParseTuple(args, "t#|z:utf_7_decode",
-			  &data, &size, &errors))
+    if (!PyArg_ParseTuple(args, "t#|zi:utf_7_decode",
+                          &data, &size, &errors, &final))
         return NULL;
+    consumed = size;
 
-    return codec_tuple(PyUnicode_DecodeUTF7(data, size, errors),
-		       size);
+    decoded = PyUnicode_DecodeUTF7Stateful(data, size, errors,
+                                           final ? NULL : &consumed);
+    if (decoded == NULL)
+        return NULL;
+    return codec_tuple(decoded, consumed);
 }
 
 static PyObject *

Objects/unicodeobject.c

@@ -1518,6 +1518,14 @@ char utf7_special[128] = {
 PyObject *PyUnicode_DecodeUTF7(const char *s,
 			       Py_ssize_t size,
 			       const char *errors)
+{
+    return PyUnicode_DecodeUTF7Stateful(s, size, errors, NULL);
+}
+
+PyObject *PyUnicode_DecodeUTF7Stateful(const char *s,
+			       Py_ssize_t size,
+			       const char *errors,
+			       Py_ssize_t *consumed)
 {
     const char *starts = s;
     Py_ssize_t startinpos;
@@ -1537,8 +1545,11 @@ PyObject *PyUnicode_DecodeUTF7(const char *s,
     unicode = _PyUnicode_New(size);
     if (!unicode)
         return NULL;
-    if (size == 0)
+    if (size == 0) {
+        if (consumed)
+            *consumed = 0;
         return (PyObject *)unicode;
+    }
 
     p = unicode->str;
     e = s + size;
@@ -1624,7 +1635,7 @@ PyObject *PyUnicode_DecodeUTF7(const char *s,
         goto onError;
     }
 
-    if (inShift) {
+    if (inShift && !consumed) {
         outpos = p-PyUnicode_AS_UNICODE(unicode);
         endinpos = size;
         if (unicode_decode_call_errorhandler(
@@ -1636,6 +1647,12 @@ PyObject *PyUnicode_DecodeUTF7(const char *s,
         if (s < e)
            goto restart;
     }
+    if (consumed) {
+        if(inShift)
+            *consumed = startinpos;
+        else
+            *consumed = s-starts;
+    }
 
     if (_PyUnicode_Resize(&unicode, p - PyUnicode_AS_UNICODE(unicode)) < 0)
         goto onError;

Tools/msi/msi.py

@@ -974,6 +974,7 @@ def add_files(db):
             lib.add_file("check_soundcard.vbs")
             lib.add_file("empty.vbs")
             lib.glob("*.uue")
+            lib.glob("*.pem")
             lib.add_file("readme.txt", src="README")
         if dir=='decimaltestdata':
             lib.glob("*.decTest")