#11684: Complete parser bytes interface by adding BytesHeaderParser
Patch by Steffen Daode Nurpmeso.
diff --git a/Doc/library/email.parser.rst b/Doc/library/email.parser.rst
index 8da0d74d..c72d3d4 100644
--- a/Doc/library/email.parser.rst
+++ b/Doc/library/email.parser.rst
@@ -94,12 +94,14 @@
The :class:`Parser` class, imported from the :mod:`email.parser` module,
provides an API that can be used to parse a message when the complete contents
of the message are available in a string or file. The :mod:`email.parser`
-module also provides a second class, called :class:`HeaderParser` which can be
-used if you're only interested in the headers of the message.
-:class:`HeaderParser` can be much faster in these situations, since it does not
-attempt to parse the message body, instead setting the payload to the raw body
-as a string. :class:`HeaderParser` has the same API as the :class:`Parser`
-class.
+module also provides header-only parsers, called :class:`HeaderParser` and
+:class:`BytesHeaderParser`, which can be used if you're only interested in the
+headers of the message. :class:`HeaderParser` and :class:`BytesHeaderParser`
+can be much faster in these situations, since they do not attempt to parse the
+message body, instead setting the payload to the raw body as a string. They
+have the same API as the :class:`Parser` and :class:`BytesParser` classes.
+
+.. versionadded:: 3.3 BytesHeaderParser
.. class:: Parser(_class=email.message.Message)
diff --git a/Lib/email/generator.py b/Lib/email/generator.py
index f0e7a95..fdd34e4 100644
--- a/Lib/email/generator.py
+++ b/Lib/email/generator.py
@@ -297,10 +297,12 @@
# message/rfc822. Such messages are generated by, for example,
# Groupwise when forwarding unadorned messages. (Issue 7970.) So
# in that case we just emit the string body.
- payload = msg.get_payload()
+ payload = msg._payload
if isinstance(payload, list):
g.flatten(msg.get_payload(0), unixfrom=False, linesep=self._NL)
payload = s.getvalue()
+ else:
+ payload = self._encode(payload)
self._fp.write(payload)
# This used to be a module level function; we use a classmethod for this
diff --git a/Lib/email/parser.py b/Lib/email/parser.py
index ef051fa..fc5090b 100644
--- a/Lib/email/parser.py
+++ b/Lib/email/parser.py
@@ -4,7 +4,7 @@
"""A parser of RFC 2822 and MIME email messages."""
-__all__ = ['Parser', 'HeaderParser']
+__all__ = ['Parser', 'HeaderParser', 'BytesParser', 'BytesHeaderParser']
import warnings
from io import StringIO, TextIOWrapper
@@ -114,3 +114,11 @@
"""
text = text.decode('ASCII', errors='surrogateescape')
return self.parser.parsestr(text, headersonly)
+
+
+class BytesHeaderParser(BytesParser):
+ def parse(self, fp, headersonly=True):
+ return BytesParser.parse(self, fp, headersonly=True)
+
+ def parsebytes(self, text, headersonly=True):
+ return BytesParser.parsebytes(self, text, headersonly=True)
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 404282b..632e0a9 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -177,6 +177,17 @@
gen.flatten(msg, False)
self.assertEqual(out.getvalue(), msgdata)
+ def test_byte_message_rfc822_only(self):
+ # Make sure new bytes header parser also passes this.
+ with openfile('msg_46.txt', 'rb') as fp:
+ msgdata = fp.read()
+ parser = email.parser.BytesHeaderParser()
+ msg = parser.parsebytes(msgdata)
+ out = BytesIO()
+ gen = email.generator.BytesGenerator(out)
+ gen.flatten(msg)
+ self.assertEqual(out.getvalue(), msgdata)
+
def test_get_decoded_payload(self):
eq = self.assertEqual
msg = self._msgobj('msg_10.txt')
@@ -2749,6 +2760,7 @@
class TestParsers(TestEmailBase):
+
def test_header_parser(self):
eq = self.assertEqual
# Parse only the headers of a complex multipart MIME document
@@ -2760,6 +2772,18 @@
self.assertFalse(msg.is_multipart())
self.assertTrue(isinstance(msg.get_payload(), str))
+ def test_bytes_header_parser(self):
+ eq = self.assertEqual
+ # Parse only the headers of a complex multipart MIME document
+ with openfile('msg_02.txt', 'rb') as fp:
+ msg = email.parser.BytesHeaderParser().parse(fp)
+ eq(msg['from'], 'ppp-request@zzz.org')
+ eq(msg['to'], 'ppp@zzz.org')
+ eq(msg.get_content_type(), 'multipart/mixed')
+ self.assertFalse(msg.is_multipart())
+ self.assertTrue(isinstance(msg.get_payload(), str))
+ self.assertTrue(isinstance(msg.get_payload(decode=True), bytes))
+
def test_whitespace_continuation(self):
eq = self.assertEqual
# This message contains a line after the Subject: header that has only
diff --git a/Misc/NEWS b/Misc/NEWS
index 0179467..098497e 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -103,6 +103,8 @@
Library
-------
+- Issue #11684: complete email.parser bytes API by adding BytesHeaderParser.
+
- The bz2 module now handles 4GiB+ input buffers correctly.
- Issue #9233: Fix json.loads('{}') to return a dict (instead of a list), when