def _write_headers(self, msg):
# This is almost the same as the string version, except for handling
# strings with 8bit bytes.
for h in msg._headers:
self.write('%s: ' % h.name)
if isinstance(h, str):
v = h.source if h.source is not None else h
if _has_surrogates(v):
if not self.policy.must_be_7bit:
# If we have raw 8bit data in a byte string, we have no idea
# what the encoding is. There is no safe way to split this
# string. If it's ascii-subset, then we could do a normal
# ascii split, but if it's multibyte then we could break the
# string. There's no way to know so the least harm seems to
# be to not split the string and risk it being too long.
self.write(v + NL)
continue
h = Header(v,
charset=_charset.UNKNOWN8BIT,
header_name=h.name)
else:
h = Header(v, header_name=h.name)
self.write(
h.encode(linesep=self._NL, maxlinelen=self._maxheaderlen) +
self._NL)
# A blank line always separates headers from body
self.write(self._NL)
def _write_headers(self, msg):
for h, v in msg.items():
self.write('%s: ' % h)
if isinstance(v, Header):
self.write(
v.encode(maxlinelen=self._maxheaderlen, linesep=self._NL) +
self._NL)
else:
v = v.source if v.source is not None else v
# Header's got lots of smarts, so use it.
header = Header(v,
maxlinelen=self._maxheaderlen,
header_name=h)
self.write(header.encode(linesep=self._NL) + self._NL)
# A blank line always separates headers from body
self.write(self._NL)
def test_japanese_codecs(self):
eq = self.ndiffAssertEqual
jcode = "euc-jp"
gcode = "iso-8859-1"
j = Charset(jcode)
g = Charset(gcode)
h = Header("Hello World!")
jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc'
b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode)
ghello = str(b'Gr\xfc\xdf Gott!', gcode)
h.append(jhello, j)
h.append(ghello, g)
# BAW: This used to -- and maybe should -- fold the two iso-8859-1
# chunks into a single encoded word. However it doesn't violate the
# standard to have them as two encoded chunks and maybe it's
# reasonable <wink> for each .append() call to result in a separate
# encoded word.
eq(h.encode(), """\
Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
=?iso-8859-1?q?Gr=FC=DF_Gott!?=""")
eq(decode_header(h.encode()),
[(b'Hello World!', None),
(b'\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
(b'Gr\xfc\xdf Gott!', gcode)])
subject_bytes = (b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5'
b'\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2'
b'\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3'
b'\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9')
subject = str(subject_bytes, jcode)
h = Header(subject, j, header_name="Subject")
# test a very long header
enc = h.encode()
# TK: splitting point may differ by codec design and/or Header encoding
eq(enc , """\
=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
=?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
# TK: full decode comparison
eq(str(h).encode(jcode), subject_bytes)