0
0
mirror of https://github.com/python/cpython.git synced 2024-12-01 11:15:56 +01:00
cpython/Lib/email/Parser.py
Barry Warsaw bb11386730 Big email 3.0 API changes, with updated unit tests and documentation.
Briefly (from the NEWS file):

- Updates for the email package:
  + All deprecated APIs that in email 2.x issued warnings have been removed:
    _encoder argument to the MIMEText constructor, Message.add_payload(),
    Utils.dump_address_pair(), Utils.decode(), Utils.encode()
  + New deprecations: Generator.__call__(), Message.get_type(),
    Message.get_main_type(), Message.get_subtype(), the 'strict' argument to
    the Parser constructor.  These will be removed in email 3.1.
  + Support for Python earlier than 2.3 has been removed (see PEP 291).
  + All defect classes have been renamed to end in 'Defect'.
  + Some FeedParser fixes; also a MultipartInvariantViolationDefect will be
    added to messages that claim to be multipart but really aren't.
  + Updates to documentation.
2004-10-03 03:16:19 +00:00

89 lines
3.2 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Copyright (C) 2001-2004 Python Software Foundation
# Author: Barry Warsaw, Thomas Wouters, Anthony Baxter
# Contact: email-sig@python.org
"""A parser of RFC 2822 and MIME email messages."""
import warnings
from cStringIO import StringIO
from email.FeedParser import FeedParser
from email.Message import Message
class Parser:
def __init__(self, *args, **kws):
"""Parser of RFC 2822 and MIME email messages.
Creates an in-memory object tree representing the email message, which
can then be manipulated and turned over to a Generator to return the
textual representation of the message.
The string must be formatted as a block of RFC 2822 headers and header
continuation lines, optionally preceeded by a `Unix-from' header. The
header block is terminated either by the end of the string or by a
blank line.
_class is the class to instantiate for new message objects when they
must be created. This class must have a constructor that can take
zero arguments. Default is Message.Message.
"""
if len(args) >= 1:
if '_class' in kws:
raise TypeError("Multiple values for keyword arg '_class'")
kws['_class'] = args[0]
if len(args) == 2:
if 'strict' in kws:
raise TypeError("Multiple values for keyword arg 'strict'")
kws['strict'] = args[1]
if len(args) > 2:
raise TypeError('Too many arguments')
if '_class' in kws:
self._class = kws['_class']
del kws['_class']
else:
self._class = Message
if 'strict' in kws:
warnings.warn("'strict' argument is deprecated (and ignored)",
DeprecationWarning, 2)
del kws['strict']
if kws:
raise TypeError('Unexpected keyword arguments')
def parse(self, fp, headersonly=False):
"""Create a message structure from the data in a file.
Reads all the data from the file and returns the root of the message
structure. Optional headersonly is a flag specifying whether to stop
parsing after reading the headers or not. The default is False,
meaning it parses the entire contents of the file.
"""
feedparser = FeedParser(self._class)
if headersonly:
feedparser._set_headersonly()
while True:
data = fp.read(8192)
if not data:
break
feedparser.feed(data)
return feedparser.close()
def parsestr(self, text, headersonly=False):
"""Create a message structure from a string.
Returns the root of the message structure. Optional headersonly is a
flag specifying whether to stop parsing after reading the headers or
not. The default is False, meaning it parses the entire contents of
the file.
"""
return self.parse(StringIO(text), headersonly=headersonly)
class HeaderParser(Parser):
def parse(self, fp, headersonly=True):
return Parser.parse(self, fp, True)
def parsestr(self, text, headersonly=True):
return Parser.parsestr(self, text, True)