2006-04-21 07:40:58 -03:00
|
|
|
|
# Copyright (C) 2001-2006 Python Software Foundation
|
2004-10-03 00:16:19 -03:00
|
|
|
|
# Author: Barry Warsaw
|
|
|
|
|
# Contact: email-sig@python.org
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2004-05-09 00:55:11 -03:00
|
|
|
|
"""Miscellaneous utilities."""
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2006-04-21 07:40:58 -03:00
|
|
|
|
__all__ = [
|
|
|
|
|
'collapse_rfc2231_value',
|
|
|
|
|
'decode_params',
|
|
|
|
|
'decode_rfc2231',
|
|
|
|
|
'encode_rfc2231',
|
|
|
|
|
'formataddr',
|
|
|
|
|
'formatdate',
|
|
|
|
|
'getaddresses',
|
|
|
|
|
'make_msgid',
|
|
|
|
|
'parseaddr',
|
|
|
|
|
'parsedate',
|
|
|
|
|
'parsedate_tz',
|
|
|
|
|
'unquote',
|
|
|
|
|
]
|
|
|
|
|
|
2004-05-09 00:55:11 -03:00
|
|
|
|
import os
|
2001-09-23 00:17:28 -03:00
|
|
|
|
import re
|
2004-05-09 00:55:11 -03:00
|
|
|
|
import time
|
|
|
|
|
import base64
|
2002-04-10 18:01:31 -03:00
|
|
|
|
import random
|
2004-05-09 00:55:11 -03:00
|
|
|
|
import socket
|
2002-04-10 18:01:31 -03:00
|
|
|
|
import warnings
|
|
|
|
|
from cStringIO import StringIO
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2002-11-05 15:54:52 -04:00
|
|
|
|
from email._parseaddr import quote
|
|
|
|
|
from email._parseaddr import AddressList as _AddressList
|
|
|
|
|
from email._parseaddr import mktime_tz
|
2002-04-10 18:01:31 -03:00
|
|
|
|
|
|
|
|
|
# We need wormarounds for bugs in these methods in older Pythons (see below)
|
2002-11-05 15:54:52 -04:00
|
|
|
|
from email._parseaddr import parsedate as _parsedate
|
|
|
|
|
from email._parseaddr import parsedate_tz as _parsedate_tz
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
2004-05-09 00:55:11 -03:00
|
|
|
|
from quopri import decodestring as _qdecode
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
# Intrapackage imports
|
2006-04-21 07:40:58 -03:00
|
|
|
|
from email.encoders import _bencode, _qencode
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
COMMASPACE = ', '
|
2002-06-29 02:58:04 -03:00
|
|
|
|
EMPTYSTRING = ''
|
2001-09-23 00:17:28 -03:00
|
|
|
|
UEMPTYSTRING = u''
|
2002-04-10 18:01:31 -03:00
|
|
|
|
CRLF = '\r\n'
|
|
|
|
|
|
2003-03-10 15:20:18 -04:00
|
|
|
|
specialsre = re.compile(r'[][\\()<>@,:;".]')
|
|
|
|
|
escapesre = re.compile(r'[][\\()"]')
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
|
2001-10-04 14:05:11 -03:00
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
# Helpers
|
|
|
|
|
|
|
|
|
|
def _identity(s):
|
|
|
|
|
return s
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _bdecode(s):
|
|
|
|
|
# We can't quite use base64.encodestring() since it tacks on a "courtesy
|
|
|
|
|
# newline". Blech!
|
|
|
|
|
if not s:
|
|
|
|
|
return s
|
|
|
|
|
value = base64.decodestring(s)
|
2002-09-28 17:49:57 -03:00
|
|
|
|
if not s.endswith('\n') and value.endswith('\n'):
|
2001-09-23 00:17:28 -03:00
|
|
|
|
return value[:-1]
|
|
|
|
|
return value
|
|
|
|
|
|
|
|
|
|
|
2002-04-10 18:01:31 -03:00
|
|
|
|
|
|
|
|
|
def fix_eols(s):
|
|
|
|
|
"""Replace all line-ending characters with \r\n."""
|
|
|
|
|
# Fix newlines with no preceding carriage return
|
|
|
|
|
s = re.sub(r'(?<!\r)\n', CRLF, s)
|
|
|
|
|
# Fix carriage returns with no following newline
|
|
|
|
|
s = re.sub(r'\r(?!\n)', CRLF, s)
|
|
|
|
|
return s
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def formataddr(pair):
|
|
|
|
|
"""The inverse of parseaddr(), this takes a 2-tuple of the form
|
|
|
|
|
(realname, email_address) and returns the string value suitable
|
2002-09-28 17:49:57 -03:00
|
|
|
|
for an RFC 2822 From, To or Cc header.
|
2002-05-23 12:15:30 -03:00
|
|
|
|
|
2002-04-10 18:01:31 -03:00
|
|
|
|
If the first element of pair is false, then the second element is
|
|
|
|
|
returned unmodified.
|
|
|
|
|
"""
|
|
|
|
|
name, address = pair
|
|
|
|
|
if name:
|
|
|
|
|
quotes = ''
|
|
|
|
|
if specialsre.search(name):
|
|
|
|
|
quotes = '"'
|
|
|
|
|
name = escapesre.sub(r'\\\g<0>', name)
|
|
|
|
|
return '%s%s%s <%s>' % (quotes, name, quotes, address)
|
|
|
|
|
return address
|
|
|
|
|
|
|
|
|
|
|
2001-10-04 14:05:11 -03:00
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
def getaddresses(fieldvalues):
|
|
|
|
|
"""Return a list of (REALNAME, EMAIL) for each fieldvalue."""
|
|
|
|
|
all = COMMASPACE.join(fieldvalues)
|
2002-04-12 17:50:05 -03:00
|
|
|
|
a = _AddressList(all)
|
2002-05-21 22:52:10 -03:00
|
|
|
|
return a.addresslist
|
2001-09-23 00:17:28 -03:00
|
|
|
|
|
|
|
|
|
|
2001-10-04 14:05:11 -03:00
|
|
|
|
|
2001-09-23 00:17:28 -03:00
|
|
|
|
ecre = re.compile(r'''
|
|
|
|
|
=\? # literal =?
|
|
|
|
|
(?P<charset>[^?]*?) # non-greedy up to the next ? is the charset
|
|
|
|
|
\? # literal ?
|
|
|
|
|
(?P<encoding>[qb]) # either a "q" or a "b", case insensitive
|
|
|
|
|
\? # literal ?
|
|
|
|
|
(?P<atom>.*?) # non-greedy up to the next ?= is the atom
|
|
|
|
|
\?= # literal ?=
|
|
|
|
|
''', re.VERBOSE | re.IGNORECASE)
|
|
|
|
|
|
|
|
|
|
|
2001-11-09 12:59:56 -04:00
|
|
|
|
|
2004-10-11 10:53:08 -03:00
|
|
|
|
def formatdate(timeval=None, localtime=False, usegmt=False):
|
2001-11-09 13:07:28 -04:00
|
|
|
|
"""Returns a date string as specified by RFC 2822, e.g.:
|
2001-11-09 12:59:56 -04:00
|
|
|
|
|
|
|
|
|
Fri, 09 Nov 2001 01:08:47 -0000
|
|
|
|
|
|
2001-11-09 13:07:28 -04:00
|
|
|
|
Optional timeval if given is a floating point time value as accepted by
|
|
|
|
|
gmtime() and localtime(), otherwise the current time is used.
|
|
|
|
|
|
2002-09-28 17:49:57 -03:00
|
|
|
|
Optional localtime is a flag that when True, interprets timeval, and
|
2001-11-09 13:07:28 -04:00
|
|
|
|
returns a date relative to the local timezone instead of UTC, properly
|
|
|
|
|
taking daylight savings time into account.
|
2004-10-11 10:53:08 -03:00
|
|
|
|
|
2004-10-12 18:51:32 -03:00
|
|
|
|
Optional argument usegmt means that the timezone is written out as
|
2004-10-11 10:53:08 -03:00
|
|
|
|
an ascii string, not numeric one (so "GMT" instead of "+0000"). This
|
|
|
|
|
is needed for HTTP, and is only used when localtime==False.
|
2001-11-09 12:59:56 -04:00
|
|
|
|
"""
|
|
|
|
|
# Note: we cannot use strftime() because that honors the locale and RFC
|
|
|
|
|
# 2822 requires that day and month names be the English abbreviations.
|
|
|
|
|
if timeval is None:
|
|
|
|
|
timeval = time.time()
|
|
|
|
|
if localtime:
|
|
|
|
|
now = time.localtime(timeval)
|
|
|
|
|
# Calculate timezone offset, based on whether the local zone has
|
|
|
|
|
# daylight savings time, and whether DST is in effect.
|
|
|
|
|
if time.daylight and now[-1]:
|
|
|
|
|
offset = time.altzone
|
|
|
|
|
else:
|
|
|
|
|
offset = time.timezone
|
2001-11-19 14:36:43 -04:00
|
|
|
|
hours, minutes = divmod(abs(offset), 3600)
|
|
|
|
|
# Remember offset is in seconds west of UTC, but the timezone is in
|
|
|
|
|
# minutes east of UTC, so the signs differ.
|
|
|
|
|
if offset > 0:
|
|
|
|
|
sign = '-'
|
|
|
|
|
else:
|
|
|
|
|
sign = '+'
|
2004-10-03 00:16:19 -03:00
|
|
|
|
zone = '%s%02d%02d' % (sign, hours, minutes // 60)
|
2001-11-09 12:59:56 -04:00
|
|
|
|
else:
|
|
|
|
|
now = time.gmtime(timeval)
|
|
|
|
|
# Timezone offset is always -0000
|
2004-10-11 10:53:08 -03:00
|
|
|
|
if usegmt:
|
|
|
|
|
zone = 'GMT'
|
|
|
|
|
else:
|
|
|
|
|
zone = '-0000'
|
2001-11-09 12:59:56 -04:00
|
|
|
|
return '%s, %02d %s %04d %02d:%02d:%02d %s' % (
|
|
|
|
|
['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][now[6]],
|
|
|
|
|
now[2],
|
|
|
|
|
['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
|
|
|
|
|
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'][now[1] - 1],
|
|
|
|
|
now[0], now[3], now[4], now[5],
|
|
|
|
|
zone)
|
2002-04-10 18:01:31 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def make_msgid(idstring=None):
|
2002-09-30 21:44:13 -03:00
|
|
|
|
"""Returns a string suitable for RFC 2822 compliant Message-ID, e.g:
|
2002-04-10 18:01:31 -03:00
|
|
|
|
|
|
|
|
|
<20020201195627.33539.96671@nightshade.la.mastaler.com>
|
|
|
|
|
|
|
|
|
|
Optional idstring if given is a string used to strengthen the
|
2002-09-30 21:44:13 -03:00
|
|
|
|
uniqueness of the message id.
|
2002-04-10 18:01:31 -03:00
|
|
|
|
"""
|
|
|
|
|
timeval = time.time()
|
|
|
|
|
utcdate = time.strftime('%Y%m%d%H%M%S', time.gmtime(timeval))
|
|
|
|
|
pid = os.getpid()
|
|
|
|
|
randint = random.randrange(100000)
|
|
|
|
|
if idstring is None:
|
|
|
|
|
idstring = ''
|
|
|
|
|
else:
|
|
|
|
|
idstring = '.' + idstring
|
|
|
|
|
idhost = socket.getfqdn()
|
|
|
|
|
msgid = '<%s.%s.%s%s@%s>' % (utcdate, pid, randint, idstring, idhost)
|
|
|
|
|
return msgid
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# These functions are in the standalone mimelib version only because they've
|
|
|
|
|
# subsequently been fixed in the latest Python versions. We use this to worm
|
|
|
|
|
# around broken older Pythons.
|
|
|
|
|
def parsedate(data):
|
|
|
|
|
if not data:
|
|
|
|
|
return None
|
|
|
|
|
return _parsedate(data)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def parsedate_tz(data):
|
|
|
|
|
if not data:
|
|
|
|
|
return None
|
|
|
|
|
return _parsedate_tz(data)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def parseaddr(addr):
|
2002-04-15 19:00:25 -03:00
|
|
|
|
addrs = _AddressList(addr).addresslist
|
|
|
|
|
if not addrs:
|
2002-04-10 18:01:31 -03:00
|
|
|
|
return '', ''
|
2002-04-15 19:00:25 -03:00
|
|
|
|
return addrs[0]
|
2002-06-29 02:58:04 -03:00
|
|
|
|
|
|
|
|
|
|
2002-09-10 23:22:48 -03:00
|
|
|
|
# rfc822.unquote() doesn't properly de-backslash-ify in Python pre-2.3.
|
|
|
|
|
def unquote(str):
|
|
|
|
|
"""Remove quotes from a string."""
|
|
|
|
|
if len(str) > 1:
|
|
|
|
|
if str.startswith('"') and str.endswith('"'):
|
|
|
|
|
return str[1:-1].replace('\\\\', '\\').replace('\\"', '"')
|
|
|
|
|
if str.startswith('<') and str.endswith('>'):
|
|
|
|
|
return str[1:-1]
|
|
|
|
|
return str
|
|
|
|
|
|
|
|
|
|
|
2002-06-29 02:58:04 -03:00
|
|
|
|
|
|
|
|
|
# RFC2231-related functions - parameter encoding and decoding
|
|
|
|
|
def decode_rfc2231(s):
|
|
|
|
|
"""Decode string according to RFC 2231"""
|
|
|
|
|
import urllib
|
2003-03-07 18:46:41 -04:00
|
|
|
|
parts = s.split("'", 2)
|
|
|
|
|
if len(parts) == 1:
|
2003-08-19 00:49:34 -03:00
|
|
|
|
return None, None, urllib.unquote(s)
|
2003-03-07 18:46:41 -04:00
|
|
|
|
charset, language, s = parts
|
|
|
|
|
return charset, language, urllib.unquote(s)
|
2002-06-29 02:58:04 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def encode_rfc2231(s, charset=None, language=None):
|
2002-09-30 21:44:13 -03:00
|
|
|
|
"""Encode string according to RFC 2231.
|
|
|
|
|
|
|
|
|
|
If neither charset nor language is given, then s is returned as-is. If
|
|
|
|
|
charset is given but not language, the string is encoded using the empty
|
|
|
|
|
string for language.
|
|
|
|
|
"""
|
2002-06-29 02:58:04 -03:00
|
|
|
|
import urllib
|
|
|
|
|
s = urllib.quote(s, safe='')
|
|
|
|
|
if charset is None and language is None:
|
|
|
|
|
return s
|
2002-09-30 21:44:13 -03:00
|
|
|
|
if language is None:
|
|
|
|
|
language = ''
|
|
|
|
|
return "%s'%s'%s" % (charset, language, s)
|
2002-06-29 02:58:04 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
rfc2231_continuation = re.compile(r'^(?P<name>\w+)\*((?P<num>[0-9]+)\*?)?$')
|
|
|
|
|
|
|
|
|
|
def decode_params(params):
|
2002-09-30 21:44:13 -03:00
|
|
|
|
"""Decode parameters list according to RFC 2231.
|
|
|
|
|
|
|
|
|
|
params is a sequence of 2-tuples containing (content type, string value).
|
|
|
|
|
"""
|
2002-06-29 02:58:04 -03:00
|
|
|
|
new_params = []
|
|
|
|
|
# maps parameter's name to a list of continuations
|
|
|
|
|
rfc2231_params = {}
|
|
|
|
|
# params is a sequence of 2-tuples containing (content_type, string value)
|
|
|
|
|
name, value = params[0]
|
|
|
|
|
new_params.append((name, value))
|
|
|
|
|
# Cycle through each of the rest of the parameters.
|
|
|
|
|
for name, value in params[1:]:
|
|
|
|
|
value = unquote(value)
|
|
|
|
|
mo = rfc2231_continuation.match(name)
|
|
|
|
|
if mo:
|
|
|
|
|
name, num = mo.group('name', 'num')
|
|
|
|
|
if num is not None:
|
|
|
|
|
num = int(num)
|
|
|
|
|
rfc2231_param1 = rfc2231_params.setdefault(name, [])
|
|
|
|
|
rfc2231_param1.append((num, value))
|
|
|
|
|
else:
|
|
|
|
|
new_params.append((name, '"%s"' % quote(value)))
|
|
|
|
|
if rfc2231_params:
|
|
|
|
|
for name, continuations in rfc2231_params.items():
|
|
|
|
|
value = []
|
|
|
|
|
# Sort by number
|
|
|
|
|
continuations.sort()
|
|
|
|
|
# And now append all values in num order
|
|
|
|
|
for num, continuation in continuations:
|
|
|
|
|
value.append(continuation)
|
|
|
|
|
charset, language, value = decode_rfc2231(EMPTYSTRING.join(value))
|
2003-03-07 18:46:41 -04:00
|
|
|
|
new_params.append(
|
|
|
|
|
(name, (charset, language, '"%s"' % quote(value))))
|
2002-06-29 02:58:04 -03:00
|
|
|
|
return new_params
|
2004-10-03 00:16:19 -03:00
|
|
|
|
|
|
|
|
|
def collapse_rfc2231_value(value, errors='replace',
|
|
|
|
|
fallback_charset='us-ascii'):
|
|
|
|
|
if isinstance(value, tuple):
|
|
|
|
|
rawval = unquote(value[2])
|
|
|
|
|
charset = value[0] or 'us-ascii'
|
|
|
|
|
try:
|
|
|
|
|
return unicode(rawval, charset, errors)
|
|
|
|
|
except LookupError:
|
|
|
|
|
# XXX charset is unknown to Python.
|
|
|
|
|
return unicode(rawval, fallback_charset, errors)
|
|
|
|
|
else:
|
|
|
|
|
return unquote(value)
|