[Python-checkins] cpython (merge 3.3 -> default): Merge: #14645: Generator now emits correct linesep for all parts.

[r.david.murray]

http://hg.python.org/cpython/rev/6b69c11b0ad0
changeset:   82536:6b69c11b0ad0
parent:      82533:c261b74533bf
parent:      82535:1b9dc00c4d57
user:        R David Murray <rdmurray at bitdance.com>
date:        Thu Mar 07 17:31:21 2013 -0500
summary:
  Merge: #14645: Generator now emits correct linesep for all parts.

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.

files:
  Lib/email/generator.py            |  22 ++++++++++--
  Lib/test/test_email/test_email.py |  34 +++++++++++++++++++
  Misc/NEWS                         |   5 ++
  3 files changed, 57 insertions(+), 4 deletions(-)


diff --git a/Lib/email/generator.py b/Lib/email/generator.py
--- a/Lib/email/generator.py
+++ b/Lib/email/generator.py
@@ -146,6 +146,19 @@
         # 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
@@ -217,7 +230,7 @@
                 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
@@ -256,7 +269,8 @@
                 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
@@ -278,7 +292,7 @@
                 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
@@ -402,7 +416,7 @@
         if _has_surrogates(msg._payload) and not self.policy.cte_type=='7bit':
             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/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -3111,6 +3111,40 @@
             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
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -275,6 +275,11 @@
 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.
 

-- 
Repository URL: http://hg.python.org/cpython