Patch #435971: UTF-7 codec by Brian Quinlan.

malemburg · malemburg · commit c60e6f777114 · 2001-09-20T10:35:46.000Z
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
@@ -607,6 +607,24 @@ extern DL_IMPORT(PyObject*) PyUnicode_AsEncodedString(
     const char *errors		/* error handling */
     );
 
+/* --- UTF-7 Codecs ------------------------------------------------------- */
+
+extern DL_IMPORT(PyObject*) PyUnicode_DecodeUTF7(
+    const char *string, 	/* UTF-7 encoded string */
+    int length,	 		/* size of string */
+    const char *errors		/* error handling */
+    );
+
+extern DL_IMPORT(PyObject*) PyUnicode_EncodeUTF7(
+    const Py_UNICODE *data, 	/* Unicode char buffer */
+    int 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 */
+    const char *errors		/* error handling */
+    );
+
 /* --- UTF-8 Codecs ------------------------------------------------------- */
 
 extern DL_IMPORT(PyObject*) PyUnicode_DecodeUTF8(
diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py
@@ -14,6 +14,10 @@
     'latin': 'latin_1',
     'latin1': 'latin_1',
     
+    # UTF-7
+    'utf7': 'utf_7',
+    'u7': 'utf_7',
+    
     # UTF-8
     'utf': 'utf_8',
     'utf8': 'utf_8',
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
@@ -377,6 +377,32 @@ def test_fixup(s):
 # Test builtin codecs
 print 'Testing builtin codecs...',
 
+# UTF-7 specific encoding tests:
+utfTests = [(u'A\u2262\u0391.', 'A+ImIDkQ.'),  # RFC2152 example
+ (u'Hi Mom -\u263a-!', 'Hi Mom -+Jjo--!'),     # RFC2152 example
+ (u'\u65E5\u672C\u8A9E', '+ZeVnLIqe-'),        # RFC2152 example
+ (u'Item 3 is \u00a31.', 'Item 3 is +AKM-1.'), # RFC2152 example
+ (u'+', '+-'),
+ (u'+-', '+--'),
+ (u'+?', '+-?'),
+ (u'\?', '+AFw?'),
+ (u'+?', '+-?'),
+ (ur'\\?', '+AFwAXA?'),
+ (ur'\\\?', '+AFwAXABc?'),
+ (ur'++--', '+-+---')]
+
+for x,y in utfTests:
+    verify( x.encode('utf-7') == y )
+
+try:        
+    unicode('+3ADYAA-', 'utf-7') # surrogates not supported
+except UnicodeError:
+    pass
+else:
+    raise TestFailed, "unicode('+3ADYAA-', 'utf-7') failed to raise an exception"
+
+verify(unicode('+3ADYAA-', 'utf-7', 'replace') == u'\ufffd')
+
 # UTF-8 specific encoding tests:
 verify(u'\u20ac'.encode('utf-8') == \
        ''.join((chr(0xe2), chr(0x82), chr(0xac))) )
@@ -439,6 +465,7 @@ def __str__(self):
 verify(unicode('Andr\202 x','ascii','replace') == u'Andr\uFFFD x')
 
 verify(u'hello'.encode('ascii') == 'hello')
+verify(u'hello'.encode('utf-7') == 'hello')
 verify(u'hello'.encode('utf-8') == 'hello')
 verify(u'hello'.encode('utf8') == 'hello')
 verify(u'hello'.encode('utf-16-le') == 'h\000e\000l\000l\000o\000')
@@ -447,7 +474,7 @@ def __str__(self):
 
 # Roundtrip safety for BMP (just the first 1024 chars)
 u = u''.join(map(unichr, range(1024)))
-for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
+for encoding in ('utf-7', 'utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
                  'raw_unicode_escape', 'unicode_escape', 'unicode_internal'):
     verify(unicode(u.encode(encoding),encoding) == u)
 
diff --git a/Modules/_codecsmodule.c b/Modules/_codecsmodule.c
@@ -123,6 +123,22 @@ unicode_internal_decode(PyObject *self,
     }
 }
 
+static PyObject *
+utf_7_decode(PyObject *self,
+	    PyObject *args)
+{
+    const char *data;
+    int size;
+    const char *errors = NULL;
+    
+    if (!PyArg_ParseTuple(args, "t#|z:utf_7_decode",
+			  &data, &size, &errors))
+	return NULL;
+
+    return codec_tuple(PyUnicode_DecodeUTF7(data, size, errors),
+		       size);
+}
+
 static PyObject *
 utf_8_decode(PyObject *self,
 	    PyObject *args)
@@ -381,6 +397,30 @@ unicode_internal_encode(PyObject *self,
     }
 }
 
+static PyObject *
+utf_7_encode(PyObject *self,
+	    PyObject *args)
+{
+    PyObject *str, *v;
+    const char *errors = NULL;
+
+    if (!PyArg_ParseTuple(args, "O|z:utf_7_encode",
+			  &str, &errors))
+	return NULL;
+
+    str = PyUnicode_FromObject(str);
+    if (str == NULL)
+	return NULL;
+    v = codec_tuple(PyUnicode_EncodeUTF7(PyUnicode_AS_UNICODE(str),
+					 PyUnicode_GET_SIZE(str),
+                     0,
+                     0,
+					 errors),
+		    PyUnicode_GET_SIZE(str));
+    Py_DECREF(str);
+    return v;
+}
+
 static PyObject *
 utf_8_encode(PyObject *self,
 	    PyObject *args)
@@ -632,6 +672,8 @@ static PyMethodDef _codecs_functions[] = {
 #ifdef Py_USING_UNICODE
     {"utf_8_encode",		utf_8_encode,			1},
     {"utf_8_decode",		utf_8_decode,			1},
+    {"utf_7_encode",		utf_7_encode,			1},
+    {"utf_7_decode",		utf_7_decode,			1},
     {"utf_16_encode",		utf_16_encode,			1},
     {"utf_16_le_encode",	utf_16_le_encode,		1},
     {"utf_16_be_encode",	utf_16_be_encode,		1},
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
