#15160: Extend the new email parser to handle MIME headers.
This code passes all the same tests that the existing RFC mime header
parser passes, plus a bunch of additional ones.
There are a couple of commented out tests where there are issues with the
folding. The folding doesn't normally get invoked for headers parsed from
source, and the cases are marginal anyway (headers with invalid binary data)
so I'm not worried about them, but will fix them after the beta.
There are things that can be done to make this API even more convenient, but I
think this is a solid foundation worth having. And the parser is a full RFC
parser, so it handles cases that the current parser doesn't. (There are also
probably cases where it fails when the current parser doesn't, but I haven't
found them yet ;)
Oh, yeah, and there are some really ugly bits in the parser for handling some
'postel' cases that are unfortunately common.
I hope/plan to to eventually refactor a lot of the code in the parser which
should reduce the line count...but there is no escaping the fact that the
error recovery is welter of special cases.
diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index 2161af1..6101e19 100644
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -3,7 +3,7 @@
from email import _header_value_parser as parser
from email import errors
from email import policy
-from test.test_email import TestEmailBase
+from test.test_email import TestEmailBase, parameterize
class TestTokens(TestEmailBase):
@@ -28,7 +28,32 @@
self.assertDefectsEqual(parts[2].all_defects, [errors.UndecodableBytesDefect])
-class TestParser(TestEmailBase):
+class TestParserMixin:
+
+ def _assert_results(self, tl, rest, string, value, defects, remainder,
+ comments=None):
+ self.assertEqual(str(tl), string)
+ self.assertEqual(tl.value, value)
+ self.assertDefectsEqual(tl.all_defects, defects)
+ self.assertEqual(rest, remainder)
+ if comments is not None:
+ self.assertEqual(tl.comments, comments)
+
+ def _test_get_x(self, method, source, string, value, defects,
+ remainder, comments=None):
+ tl, rest = method(source)
+ self._assert_results(tl, rest, string, value, defects, remainder,
+ comments=None)
+ return tl
+
+ def _test_parse_x(self, method, input, string, value, defects,
+ comments=None):
+ tl = method(input)
+ self._assert_results(tl, '', string, value, defects, '', comments)
+ return tl
+
+
+class TestParser(TestParserMixin, TestEmailBase):
# _wsp_splitter
@@ -49,19 +74,6 @@
['foo', ' \t ', 'def jik'])
- # test harness
-
- def _test_get_x(self, method, input, string, value, defects,
- remainder, comments=None):
- token, rest = method(input)
- self.assertEqual(str(token), string)
- self.assertEqual(token.value, value)
- self.assertDefectsEqual(token.all_defects, defects)
- self.assertEqual(rest, remainder)
- if comments is not None:
- self.assertEqual(token.comments, comments)
- return token
-
# get_fws
def test_get_fws_only(self):
@@ -2390,6 +2402,67 @@
str(address_list.mailboxes[2]))
+@parameterize
+class Test_parse_mime_version(TestParserMixin, TestEmailBase):
+
+ def mime_version_as_value(self,
+ value,
+ tl_str,
+ tl_value,
+ major,
+ minor,
+ defects):
+ mime_version = self._test_parse_x(parser.parse_mime_version,
+ value, tl_str, tl_value, defects)
+ self.assertEqual(mime_version.major, major)
+ self.assertEqual(mime_version.minor, minor)
+
+ mime_version_params = {
+
+ 'rfc_2045_1': (
+ '1.0',
+ '1.0',
+ '1.0',
+ 1,
+ 0,
+ []),
+
+ 'RFC_2045_2': (
+ '1.0 (produced by MetaSend Vx.x)',
+ '1.0 (produced by MetaSend Vx.x)',
+ '1.0 ',
+ 1,
+ 0,
+ []),
+
+ 'RFC_2045_3': (
+ '(produced by MetaSend Vx.x) 1.0',
+ '(produced by MetaSend Vx.x) 1.0',
+ ' 1.0',
+ 1,
+ 0,
+ []),
+
+ 'RFC_2045_4': (
+ '1.(produced by MetaSend Vx.x)0',
+ '1.(produced by MetaSend Vx.x)0',
+ '1. 0',
+ 1,
+ 0,
+ []),
+
+ 'empty': (
+ '',
+ '',
+ '',
+ None,
+ None,
+ [errors.HeaderMissingRequiredValue]),
+
+ }
+
+
+
class TestFolding(TestEmailBase):
policy = policy.default