# Copyright (C) 2001-2010 Python Software Foundation
# Contact: email-sig@python.org
"""Miscellaneous utilities."""
'collapse_rfc2231_value',
from email._parseaddr import quote
from email._parseaddr import AddressList as _AddressList
from email._parseaddr import mktime_tz
from email._parseaddr import parsedate, parsedate_tz, _parsedate_tz
from email.charset import Charset
specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')
"""Return True if s contains surrogate-escaped binary data."""
# This check is based on the fact that unless there are surrogates, utf8
# (Python's default encoding) can encode any string. This is the fastest
# way to check for surrogates, see issue 11454 for timings.
except UnicodeEncodeError:
# How to deal with a string containing bytes before handing it to the
# application through the 'normal' interface.
# Turn any escaped bytes into unicode 'unknown' char. If the escaped
# bytes happen to be utf-8 they will instead get decoded, even if they
# were invalid in the charset the source was supposed to be in. This
# seems like it is not a bad thing; a defect was still registered.
original_bytes = string.encode('utf-8', 'surrogateescape')
return original_bytes.decode('utf-8', 'replace')
def formataddr(pair, charset='utf-8'):
"""The inverse of parseaddr(), this takes a 2-tuple of the form
(realname, email_address) and returns the string value suitable
for an RFC 2822 From, To or Cc header.
If the first element of pair is false, then the second element is
The optional charset is the character set that is used to encode
realname in case realname is not ASCII safe. Can be an instance of str or
a Charset-like object which has a header_encode method. Default is
# The address MUST (per RFC) be ascii, so raise a UnicodeError if it isn't.
except UnicodeEncodeError:
if isinstance(charset, str):
charset = Charset(charset)
encoded_name = charset.header_encode(name)
return "%s <%s>" % (encoded_name, address)
if specialsre.search(name):
name = escapesre.sub(r'\\\g<0>', name)
return '%s%s%s <%s>' % (quotes, name, quotes, address)
def getaddresses(fieldvalues):
"""Return a list of (REALNAME, EMAIL) for each fieldvalue."""
all = COMMASPACE.join(fieldvalues)
def _format_timetuple_and_zone(timetuple, zone):
return '%s, %02d %s %04d %02d:%02d:%02d %s' % (
['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][timetuple[6]],
['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'][timetuple[1] - 1],
timetuple[0], timetuple[3], timetuple[4], timetuple[5],
def formatdate(timeval=None, localtime=False, usegmt=False):
"""Returns a date string as specified by RFC 2822, e.g.:
Fri, 09 Nov 2001 01:08:47 -0000
Optional timeval if given is a floating point time value as accepted by
gmtime() and localtime(), otherwise the current time is used.
Optional localtime is a flag that when True, interprets timeval, and
returns a date relative to the local timezone instead of UTC, properly
taking daylight savings time into account.
Optional argument usegmt means that the timezone is written out as
an ascii string, not numeric one (so "GMT" instead of "+0000"). This
is needed for HTTP, and is only used when localtime==False.
# Note: we cannot use strftime() because that honors the locale and RFC
# 2822 requires that day and month names be the English abbreviations.
dt = datetime.datetime.fromtimestamp(timeval, datetime.timezone.utc)
dt = datetime.datetime.utcfromtimestamp(timeval)
return format_datetime(dt, usegmt)
def format_datetime(dt, usegmt=False):
"""Turn a datetime into a date string as specified in RFC 2822.
If usegmt is True, dt must be an aware datetime with an offset of zero. In
this case 'GMT' will be rendered instead of the normal +0000 required by
RFC2822. This is to support HTTP headers involving date stamps.
if dt.tzinfo is None or dt.tzinfo != datetime.timezone.utc:
raise ValueError("usegmt option requires a UTC datetime")
return _format_timetuple_and_zone(now, zone)
def make_msgid(idstring=None, domain=None):
"""Returns a string suitable for RFC 2822 compliant Message-ID, e.g:
<142480216486.20800.16526388040877946887@nightshade.la.mastaler.com>
Optional idstring if given is a string used to strengthen the
uniqueness of the message id. Optional domain if given provides the
portion of the message id after the '@'. It defaults to the locally
timeval = int(time.time()*100)
randint = random.getrandbits(64)
idstring = '.' + idstring
domain = socket.getfqdn()
msgid = '<%d.%d.%d%s@%s>' % (timeval, pid, randint, idstring, domain)
def parsedate_to_datetime(data):
*dtuple, tz = _parsedate_tz(data)
return datetime.datetime(*dtuple[:6])
return datetime.datetime(*dtuple[:6],
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
Parse addr into its constituent realname and email address parts.
Return a tuple of realname and email address, unless the parse fails, in
which case return a 2-tuple of ('', '').
addrs = _AddressList(addr).addresslist
# rfc822.unquote() doesn't properly de-backslash-ify in Python pre-2.3.
"""Remove quotes from a string."""
if str.startswith('"') and str.endswith('"'):
return str[1:-1].replace('\\\\', '\\').replace('\\"', '"')
if str.startswith('<') and str.endswith('>'):
# RFC2231-related functions - parameter encoding and decoding
"""Decode string according to RFC 2231"""
def encode_rfc2231(s, charset=None, language=None):
"""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
s = urllib.parse.quote(s, safe='', encoding=charset or 'ascii')
if charset is None and language is None:
return "%s'%s'%s" % (charset, language, s)
rfc2231_continuation = re.compile(r'^(?P<name>\w+)\*((?P<num>[0-9]+)\*?)?$',
def decode_params(params):
"""Decode parameters list according to RFC 2231.
params is a sequence of 2-tuples containing (param name, string value).
# Copy params so we don't mess with the original
# Map parameter's name to a list of continuations. The values are a
# 3-tuple of the continuation number, the string value, and a flag
# specifying whether a particular segment is %-encoded.
name, value = params.pop(0)
new_params.append((name, value))
name, value = params.pop(0)
mo = rfc2231_continuation.match(name)
name, num = mo.group('name', 'num')
rfc2231_params.setdefault(name, []).append((num, value, encoded))
new_params.append((name, '"%s"' % quote(value)))
for name, continuations in rfc2231_params.items():
# And now append all values in numerical order, converting
# %-encodings for the encoded segments. If any of the
# continuation names ends in a *, then the entire string, after
# decoding segments and concatenating, must have the charset and
# language specifiers at the beginning of the string.
for num, s, encoded in continuations:
# Decode as "latin-1", so the characters in s directly
# represent the percent-encoded octet values.
# collapse_rfc2231_value treats this as an octet sequence.
s = urllib.parse.unquote(s, encoding="latin-1")
value = quote(EMPTYSTRING.join(value))
charset, language, value = decode_rfc2231(value)
new_params.append((name, (charset, language, '"%s"' % value)))
new_params.append((name, '"%s"' % value))
def collapse_rfc2231_value(value, errors='replace',
fallback_charset='us-ascii'):
if not isinstance(value, tuple) or len(value) != 3:
# While value comes to us as a unicode string, we need it to be a bytes
# object. We do not want bytes() normal utf-8 decoder, we want a straight
# interpretation of the string as character bytes.
charset, language, text = value
# Issue 17369: if charset/lang is None, decode_rfc2231 couldn't parse
# the value, so use the fallback_charset.
charset = fallback_charset
rawbytes = bytes(text, 'raw-unicode-escape')
return str(rawbytes, charset, errors)
# charset is not a known codec.
# datetime doesn't provide a localtime function yet, so provide one. Code
# adapted from the patch in issue 9527. This may not be perfect, but it is
# better than not having it.
def localtime(dt=None, isdst=-1):
"""Return local time as an aware datetime object.
If called without arguments, return current time. Otherwise *dt*
argument should be a datetime instance, and it is converted to the
local time zone according to the system time zone database. If *dt* is
naive (that is, dt.tzinfo is None), it is assumed to be in local time.
In this case, a positive or zero value for *isdst* causes localtime to
presume initially that summer time (for example, Daylight Saving Time)
is or is not (respectively) in effect for the specified time. A
negative value for *isdst* causes the localtime() function to attempt
to divine whether summer time is in effect for the specified time.
return datetime.datetime.now(datetime.timezone.utc).astimezone()
if dt.tzinfo is not None:
# We have a naive datetime. Convert to a (localtime) timetuple and pass to
# system mktime together with the isdst hint. System mktime will return
tm = dt.timetuple()[:-1] + (isdst,)
seconds = time.mktime(tm)
localtm = time.localtime(seconds)
delta = datetime.timedelta(seconds=localtm.tm_gmtoff)
tz = datetime.timezone(delta, localtm.tm_zone)
# Compute UTC offset and compare with the value implied by tm_isdst.
# If the values match, use the zone name implied by tm_isdst.
delta = dt - datetime.datetime(*time.gmtime(seconds)[:6])
dst = time.daylight and localtm.tm_isdst > 0
gmtoff = -(time.altzone if dst else time.timezone)
if delta == datetime.timedelta(seconds=gmtoff):
tz = datetime.timezone(delta, time.tzname[dst])
tz = datetime.timezone(delta)
return dt.replace(tzinfo=tz)
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
