From 29097d5a6aa13729583f98cd09923f97addb7819 Mon Sep 17 00:00:00 2001 From: R David Murray Date: Sun, 11 Sep 2016 17:23:33 -0400 Subject: Merge: #19003: Only replace \r and/or \n line endings in email.generator. --- Lib/email/generator.py | 16 ++++++++++------ Lib/test/test_email/test_email.py | 12 ++++++++++++ 2 files changed, 22 insertions(+), 6 deletions(-) diff --git a/Lib/email/generator.py b/Lib/email/generator.py index 51109f9..ae670c2 100644 --- a/Lib/email/generator.py +++ b/Lib/email/generator.py @@ -18,6 +18,7 @@ from email.utils import _has_surrogates UNDERSCORE = '_' NL = '\n' # XXX: no longer used by the code below. +NLCRE = re.compile(r'\r\n|\r|\n') fcre = re.compile(r'^From ', re.MULTILINE) @@ -149,14 +150,17 @@ class Generator: # We have to transform the line endings. if not lines: return - lines = lines.splitlines(True) + lines = NLCRE.split(lines) 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(line) self.write(self._NL) + if lines[-1]: + self.write(lines[-1]) + # XXX logic tells me this else should be needed, but the tests fail + # with it and pass without it. (NLCRE.split ends with a blank element + # if and only if there was a trailing newline.) + #else: + # self.write(self._NL) def _write(self, msg): # We can't write the headers yet because of the following scenario: diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py index e95f08d..daa1285 100644 --- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -1599,6 +1599,18 @@ class TestMIMEApplication(unittest.TestCase): self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata)) self.assertEqual(msg2.get_payload(decode=True), bytesdata) + def test_binary_body_with_unicode_linend_encode_noop(self): + # Issue 19003: This is a variation on #16564. + bytesdata = b'\x0b\xfa\xfb\xfc\xfd\xfe\xff' + msg = MIMEApplication(bytesdata, _encoder=encoders.encode_noop) + self.assertEqual(msg.get_payload(decode=True), bytesdata) + s = BytesIO() + g = BytesGenerator(s) + g.flatten(msg) + wireform = s.getvalue() + msg2 = email.message_from_bytes(wireform) + self.assertEqual(msg2.get_payload(decode=True), bytesdata) + def test_binary_body_with_encode_quopri(self): # Issue 14360. bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff ' -- cgit v0.12