Merge updated a01e449 from al-tonio

2 files changed, 35 insertions, 4 deletions

diff --git a/paramiko/file.py b/paramiko/file.py
index 70243e40..856cc101 100644
--- a/paramiko/file.py
+++ b/paramiko/file.py
@@ -124,9 +124,11 @@ class BufferedFile (object):
         file first).  If the ``size`` argument is negative or omitted, read all
         the remaining data in the file.
 
-        ``'b'`` mode flag is ignored (``self.FLAG_BINARY`` in ``self._flags``),
-        because SSH treats all files as binary, since we have no idea what
-        encoding the file is in, or even if the file is text data.
+        .. note:: 
+            ``'b'`` mode flag is ignored (``self.FLAG_BINARY`` in
+            ``self._flags``), because SSH treats all files as binary, since we
+            have no idea what encoding the file is in, or even if the file is
+            text data.
 
         :param int size: maximum number of bytes to read
         :return:
diff --git a/tests/test_sftp.py b/tests/test_sftp.py
index 720b8215..c70d0cde 100755
--- a/tests/test_sftp.py
+++ b/tests/test_sftp.py
@@ -67,6 +67,18 @@ liver insulin receptors. Their sensitivity to insulin is, however, similarly
 decreased compared with chicken.
 '''
 
+
+# Here is how unicode characters are encoded over 1 to 6 bytes in utf-8
+# U-00000000 - U-0000007F: 0xxxxxxx  
+# U-00000080 - U-000007FF: 110xxxxx 10xxxxxx 
+# U-00000800 - U-0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
+# U-00010000 - U-001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
+# U-00200000 - U-03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+# U-04000000 - U-7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+# Note that: hex(int('11000011',2)) == '0xc3'
+# Thus, the following 2-bytes sequence is not valid utf8: "invalid continuation byte"
+NON_UTF8_DATA = b'\xC3\xC3'
+
 FOLDER = os.environ.get('TEST_FOLDER', 'temp-testing000')
 
 sftp = None
@@ -466,7 +478,7 @@ class SFTPTest (unittest.TestCase):
                 f.write('?\n')
 
             with sftp.open(FOLDER + '/happy.txt', 'r') as f:
-                self.assertEqual(f.readline(), u'full line?\n')
+                self.assertEqual(f.readline(), u('full line?\n'))
                 self.assertEqual(f.read(7), b'partial')
         finally:
             try:
@@ -747,6 +759,23 @@ class SFTPTest (unittest.TestCase):
             sftp.remove(FOLDER + '/test%file')
 
 
+    def test_O_non_utf8_data(self):
+        """Test write() and read() of non utf8 data"""
+        try:
+            with sftp.open('%s/nonutf8data' % FOLDER, 'w') as f:
+                f.write(NON_UTF8_DATA)
+            with sftp.open('%s/nonutf8data' % FOLDER, 'r') as f:
+                data = f.read()
+            self.assertEqual(data, NON_UTF8_DATA)
+            with sftp.open('%s/nonutf8data' % FOLDER, 'wb') as f:
+                f.write(NON_UTF8_DATA)
+            with sftp.open('%s/nonutf8data' % FOLDER, 'rb') as f:
+                data = f.read()
+            self.assertEqual(data, NON_UTF8_DATA)
+        finally:
+            sftp.remove('%s/nonutf8data' % FOLDER)
+
+
 if __name__ == '__main__':
     SFTPTest.init_loopback()
     # logging is required by test_N_file_with_percent