Merged revisions 72283-72284 via svnmerge from

pitrou · pitrou · commit 244651aa2f21 · 2009-05-04T18:56:13.000Z
svn+ssh://pythondev@svn.python.org/python/trunk ........ r72283 | antoine.pitrou | 2009-05-04 20:32:32 +0200 (lun., 04 mai 2009) | 4 lines Issue python#4426: The UTF-7 decoder was too strict and didn't accept some legal sequences. Patch by Nick Barnes and Victor Stinner. ........ r72284 | antoine.pitrou | 2009-05-04 20:32:50 +0200 (lun., 04 mai 2009) | 3 lines Add Nick Barnes to ACKS. ........
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
@@ -858,10 +858,8 @@ PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7Stateful(
 PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
     const Py_UNICODE *data, 	/* Unicode char buffer */
     Py_ssize_t length,	 	/* number of Py_UNICODE chars to encode */
-    int encodeSetO,             /* force the encoder to encode characters in
-                                   Set O, as described in RFC2152 */
-    int encodeWhiteSpace,       /* force the encoder to encode space, tab,
-                                   carriage return and linefeed characters */
+    int base64SetO,		/* Encode RFC2152 Set O characters in base64 */
+    int base64WhiteSpace,	/* Encode whitespace (sp, ht, nl, cr) in base64 */
     const char *errors		/* error handling */
     );
 
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
@@ -867,19 +867,31 @@ def test_codecs_utf7(self):
             ('+?', b'+-?'),
             (r'\\?', b'+AFwAXA?'),
             (r'\\\?', b'+AFwAXABc?'),
-            (r'++--', b'+-+---')
+            (r'++--', b'+-+---'),
+            ('\U000abcde', b'+2m/c3g-'),                  # surrogate pairs
+            ('/', b'/'),
         ]
 
         for (x, y) in utfTests:
             self.assertEqual(x.encode('utf-7'), y)
 
-        # surrogates not supported
+        # Unpaired surrogates not supported
         self.assertRaises(UnicodeError, str, b'+3ADYAA-', 'utf-7')
 
-        self.assertEqual(str(b'+3ADYAA-', 'utf-7', 'replace'), '\ufffd')
+        self.assertEqual(str(b'+3ADYAA-', 'utf-7', 'replace'), '\ufffd\ufffd')
 
         # Issue #2242: crash on some Windows/MSVC versions
-        self.assertRaises(UnicodeDecodeError, b'+\xc1'.decode, 'utf-7')
+        self.assertEqual(b'+\xc1'.decode('utf-7'), '\xc1')
+
+        # Direct encoded characters
+        set_d = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'(),-./:?"
+        # Optional direct characters
+        set_o = '!"#$%&*;<=>@[]^_`{|}'
+        for c in set_d:
+            self.assertEqual(c.encode('utf7'), c.encode('ascii'))
+            self.assertEqual(c.encode('ascii').decode('utf7'), c)
+        for c in set_o:
+            self.assertEqual(c.encode('ascii').decode('utf7'), c)
 
     def test_codecs_utf8(self):
         self.assertEqual(''.encode('utf-8'), b'')
diff --git a/Misc/ACKS b/Misc/ACKS
@@ -35,6 +35,7 @@ Luigi Ballabio
 Jeff Balogh
 Michael J. Barber
 Chris Barker
+Nick Barnes
 Quentin Barnes
 Richard Barran
 Cesar Eduardo Barros
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -12,6 +12,9 @@ What's New in Python 3.1 beta 1?
 Core and Builtins
 -----------------
 
+- Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal
+  sequences. Patch by Nick Barnes and Victor Stinner.
+
 - Issue #3672: Reject surrogates in utf-8 codec; add surrogates error handler.
 
 - Issue #5883: In the io module, the BufferedIOBase and TextIOBase ABCs have
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
