cpython: a95d936ce8eb (original) (raw)

Mercurial > cpython

changeset 69334:a95d936ce8eb

#11684: Complete parser bytes interface by adding BytesHeaderParser Patch by Steffen Daode Nurpmeso. [#11684]

R David Murray rdmurray@bitdance.com
date	Wed, 13 Apr 2011 16:46:05 -0400
parents	fafc84b45a9e
children	602d317d2257
files	Doc/library/email.parser.rst Lib/email/generator.py Lib/email/parser.py Lib/test/test_email/test_email.py Misc/NEWS
diffstat	5 files changed, 46 insertions(+), 8 deletions(-)[+] [-] Doc/library/email.parser.rst 14 Lib/email/generator.py 4 Lib/email/parser.py 10 Lib/test/test_email/test_email.py 24 Misc/NEWS 2

line wrap: on

line diff

--- a/Doc/library/email.parser.rst +++ b/Doc/library/email.parser.rst @@ -94,12 +94,14 @@ Parser class API 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)

--- a/Lib/email/generator.py +++ b/Lib/email/generator.py @@ -297,10 +297,12 @@ class Generator: # 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()[](#l2.7)
```

   payload = msg._payload[](#l2.8)
   if isinstance(payload, list):[](#l2.9)
       g.flatten(msg.get_payload(0), unixfrom=False, linesep=self._NL)[](#l2.10)
       payload = s.getvalue()[](#l2.11)

```
   else:[](#l2.12)
```

       payload = self._encode(payload)[](#l2.13)
   self._fp.write(payload)[](#l2.14)

# This used to be a module level function; we use a classmethod for this

--- 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 @@ class BytesParser: """ 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)[](#l3.20)

def parsebytes(self, text, headersonly=True):

   return BytesParser.parsebytes(self, text, headersonly=True)[](#l3.23)

--- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -177,6 +177,17 @@ class TestMessageAPI(TestEmailBase): 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.[](#l4.8)

   with openfile('msg_46.txt', 'rb') as fp:[](#l4.9)

```
       msgdata = fp.read()[](#l4.10)
```

   parser = email.parser.BytesHeaderParser()[](#l4.11)

   msg = parser.parsebytes(msgdata)[](#l4.12)

```
   out = BytesIO()[](#l4.13)
```

   gen = email.generator.BytesGenerator(out)[](#l4.14)

```
   gen.flatten(msg)[](#l4.15)
```

   self.assertEqual(out.getvalue(), msgdata)[](#l4.16)

+ def test_get_decoded_payload(self): eq = self.assertEqual msg = self._msgobj('msg_10.txt') @@ -2749,6 +2760,7 @@ Do you like this message? 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 @@ class TestParsers(TestEmailBase): self.assertFalse(msg.is_multipart()) self.assertTrue(isinstance(msg.get_payload(), str))

def test_bytes_header_parser(self):
```
   eq = self.assertEqual[](#l4.34)
```

   # Parse only the headers of a complex multipart MIME document[](#l4.35)

   with openfile('msg_02.txt', 'rb') as fp:[](#l4.36)

       msg = email.parser.BytesHeaderParser().parse(fp)[](#l4.37)

   eq(msg['from'], 'ppp-request@zzz.org')[](#l4.38)

   eq(msg['to'], 'ppp@zzz.org')[](#l4.39)

   eq(msg.get_content_type(), 'multipart/mixed')[](#l4.40)

   self.assertFalse(msg.is_multipart())[](#l4.41)

   self.assertTrue(isinstance(msg.get_payload(), str))[](#l4.42)

   self.assertTrue(isinstance(msg.get_payload(decode=True), bytes))[](#l4.43)

+ def test_whitespace_continuation(self): eq = self.assertEqual # This message contains a line after the Subject: header that has only

--- a/Misc/NEWS +++ b/Misc/NEWS @@ -103,6 +103,8 @@ Core and Builtins 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