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.

5 files changed, 61 insertions, 23 deletions

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 3e9dcee..a774d52 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -674,6 +674,13 @@ 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 */
diff --git a/Lib/encodings/utf_7.py b/Lib/encodings/utf_7.py
index d78d192..8e0567f 100644
--- a/Lib/encodings/utf_7.py
+++ b/Lib/encodings/utf_7.py
@@ -6,34 +6,31 @@ import codecs
 
 ### Codec APIs
 
-class Codec(codecs.Codec):
+encode = codecs.utf_7_encode
 
-    # 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,
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index bfb417c..cee819c 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -51,7 +51,7 @@ class ReadTest(unittest.TestCase):
         self.assertEqual(d.decode("", True), u"")
         self.assertEqual(d.buffer, "")
 
-        # Check whether the rest method works properly
+        # Check whether the reset method works properly
         d.reset()
         result = u""
         for (c, partialresult) in zip(input.encode(self.encoding), partialresults):
@@ -491,7 +491,17 @@ 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(
+            u"a+-b",
+            [
+                u"a",
+                u"a",
+                u"a+",
+                u"a+-",
+                u"a+-b",
+            ]
+        )
 
 class UTF16ExTest(unittest.TestCase):
 
diff --git a/Modules/_codecsmodule.c b/Modules/_codecsmodule.c
index 0716f3a..d4eb0d5 100644
--- a/Modules/_codecsmodule.c
+++ b/Modules/_codecsmodule.c
@@ -230,18 +230,25 @@ unicode_internal_decode(PyObject *self,
 
 static PyObject *
 utf_7_decode(PyObject *self,
-	    PyObject *args)
+             PyObject *args)
 {
     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))
-	return NULL;
+    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 *
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 7043d5f..18b861b 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -944,6 +944,14 @@ 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;
     Py_ssize_t endinpos;
@@ -962,8 +970,11 @@ 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;
@@ -1049,7 +1060,7 @@ 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(
@@ -1061,6 +1072,12 @@ 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;