#14645: Generator now emits correct linesep for all parts.

bitdancer · bitdancer · commit e67c6c545b3b · 2013-03-07T16:38:03.000-05:00
Previously the parts of the message retained whatever linesep they had on
read, which means if the messages weren't read in univeral newline mode, the
line endings could well be inconsistent.  In general sending it via smtplib
would result in them getting fixed, but it is better to generate them
correctly to begin with.  Also, the new send_message method of smtplib does
not do the fixup, so that method is producing rfc-invalid output without this
fix.
diff --git a/Lib/email/generator.py b/Lib/email/generator.py
@@ -119,6 +119,19 @@ def _encode(self, s):
         # BytesGenerator overrides this to encode strings to bytes.
         return s
 
+    def _write_lines(self, lines):
+        # We have to transform the line endings.
+        if not lines:
+            return
+        lines = lines.splitlines(True)
+        for line in lines[:-1]:
+            self.write(line.rstrip('\r\n'))
+            self.write(self._NL)
+        laststripped = lines[-1].rstrip('\r\n')
+        self.write(laststripped)
+        if len(lines[-1])!=len(laststripped):
+            self.write(self._NL)
+
     def _write(self, msg):
         # We can't write the headers yet because of the following scenario:
         # say a multipart message includes the boundary string somewhere in
@@ -198,7 +211,7 @@ def _handle_text(self, msg):
                 payload = msg.get_payload()
         if self._mangle_from_:
             payload = fcre.sub('>From ', payload)
-        self.write(payload)
+        self._write_lines(payload)
 
     # Default body handler
     _writeBody = _handle_text
@@ -237,7 +250,8 @@ def _handle_multipart(self, msg):
                 preamble = fcre.sub('>From ', msg.preamble)
             else:
                 preamble = msg.preamble
-            self.write(preamble + self._NL)
+            self._write_lines(preamble)
+            self.write(self._NL)
         # dash-boundary transport-padding CRLF
         self.write('--' + boundary + self._NL)
         # body-part
@@ -259,7 +273,7 @@ def _handle_multipart(self, msg):
                 epilogue = fcre.sub('>From ', msg.epilogue)
             else:
                 epilogue = msg.epilogue
-            self.write(epilogue)
+            self._write_lines(epilogue)
 
     def _handle_multipart_signed(self, msg):
         # The contents of signed parts has to stay unmodified in order to keep
@@ -393,7 +407,7 @@ def _handle_text(self, msg):
         if _has_surrogates(msg._payload):
             if self._mangle_from_:
                 msg._payload = fcre.sub(">From ", msg._payload)
-            self.write(msg._payload)
+            self._write_lines(msg._payload)
         else:
             super(BytesGenerator,self)._handle_text(msg)
 
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
@@ -68,6 +68,7 @@ def _msgobj(self, filename):
         with openfile(findfile(filename)) as fp:
             return email.message_from_file(fp)
 
+    maxDiff = None
 
 
 # Test various aspects of the Message class's API
@@ -2907,6 +2908,40 @@ def test_make_msgid_domain(self):
             email.utils.make_msgid(domain='testdomain-string')[-19:],
             '@testdomain-string>')
 
+    def test_Generator_linend(self):
+        # Issue 14645.
+        with openfile('msg_26.txt', newline='\n') as f:
+            msgtxt = f.read()
+        msgtxt_nl = msgtxt.replace('\r\n', '\n')
+        msg = email.message_from_string(msgtxt)
+        s = StringIO()
+        g = email.generator.Generator(s)
+        g.flatten(msg)
+        self.assertEqual(s.getvalue(), msgtxt_nl)
+
+    def test_BytesGenerator_linend(self):
+        # Issue 14645.
+        with openfile('msg_26.txt', newline='\n') as f:
+            msgtxt = f.read()
+        msgtxt_nl = msgtxt.replace('\r\n', '\n')
+        msg = email.message_from_string(msgtxt_nl)
+        s = BytesIO()
+        g = email.generator.BytesGenerator(s)
+        g.flatten(msg, linesep='\r\n')
+        self.assertEqual(s.getvalue().decode('ascii'), msgtxt)
+
+    def test_BytesGenerator_linend_with_non_ascii(self):
+        # Issue 14645.
+        with openfile('msg_26.txt', 'rb') as f:
+            msgtxt = f.read()
+        msgtxt = msgtxt.replace(b'with attachment', b'fo\xf6')
+        msgtxt_nl = msgtxt.replace(b'\r\n', b'\n')
+        msg = email.message_from_bytes(msgtxt_nl)
+        s = BytesIO()
+        g = email.generator.BytesGenerator(s)
+        g.flatten(msg, linesep='\r\n')
+        self.assertEqual(s.getvalue(), msgtxt)
+
 
 # Test the iterator/generators
 class TestIterators(TestEmailBase):
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -233,6 +233,11 @@ Core and Builtins
 Library
 -------
 
+- Issue #14645: The email generator classes now produce output using the
+  specified linesep throughout.  Previously if the prolog, epilog, or
+  body were stored with a different linesep, that linesep was used.  This
+  fix corrects an RFC non-compliance issue with smtplib.send_message.
+
 - Issue #17278: Fix a crash in heapq.heappush() and heapq.heappop() when
   the list is being resized concurrently.
 
