Lib/email/utils.py

# Copyright (C) 2001-2007 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org

"""Miscellaneous utilities."""

__all__ = [
    'collapse_rfc2231_value',
    'decode_params',
    'decode_rfc2231',
    'encode_rfc2231',
    'formataddr',
    'formatdate',
    'getaddresses',
    'make_msgid',
    'parseaddr',
    'parsedate',
    'parsedate_tz',
    'unquote',
    ]

import os
import re
import time
import base64
import random
import socket
import urllib
import warnings
from io import StringIO

from email._parseaddr import quote
from email._parseaddr import AddressList as _AddressList
from email._parseaddr import mktime_tz

# We need wormarounds for bugs in these methods in older Pythons (see below)
from email._parseaddr import parsedate as _parsedate
from email._parseaddr import parsedate_tz as _parsedate_tz

from quopri import decodestring as _qdecode

# Intrapackage imports
from email.encoders import _bencode, _qencode

COMMASPACE = ', '
EMPTYSTRING = ''
UEMPTYSTRING = ''
CRLF = '\r\n'
TICK = "'"

specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[][\\()"]')



# 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)
    if not s.endswith('\n') and value.endswith('\n'):
        return value[:-1]
    return value



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
    for an RFC 2822 From, To or Cc header.

    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



def getaddresses(fieldvalues):
    """Return a list of (REALNAME, EMAIL) for each fieldvalue."""
    all = COMMASPACE.join(fieldvalues)
    a = _AddressList(all)
    return a.addresslist



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)



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.
    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
        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 = '+'
        zone = '%s%02d%02d' % (sign, hours, minutes // 60)
    else:
        now = time.gmtime(timeval)
        # Timezone offset is always -0000
        if usegmt:
            zone = 'GMT'
        else:
            zone = '-0000'
    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)



def make_msgid(idstring=None):
    """Returns a string suitable for RFC 2822 compliant Message-ID, e.g:

    <20020201195627.33539.96671@nightshade.la.mastaler.com>

    Optional idstring if given is a string used to strengthen the
    uniqueness of the message id.
    """
    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):
    addrs = _AddressList(addr).addresslist
    if not addrs:
        return '', ''
    return addrs[0]


# 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



# RFC2231-related functions - parameter encoding and decoding
def decode_rfc2231(s):
    """Decode string according to RFC 2231"""
    parts = s.split(TICK, 2)
    if len(parts) <= 2:
        return None, None, s
    return parts


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
    string for language.
    """
    import urllib
    s = urllib.quote(s, safe='')
    if charset is None and language is None:
        return s
    if language is None:
        language = ''
    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
    params = params[:]
    new_params = []
    # 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.
    rfc2231_params = {}
    name, value = params.pop(0)
    new_params.append((name, value))
    while params:
        name, value = params.pop(0)
        if name.endswith('*'):
            encoded = True
        else:
            encoded = False
        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_params.setdefault(name, []).append((num, value, encoded))
        else:
            new_params.append((name, '"%s"' % quote(value)))
    if rfc2231_params:
        for name, continuations in rfc2231_params.items():
            value = []
            extended = False
            # Sort by number
            continuations.sort()
            # 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:
                if encoded:
                    s = urllib.unquote(s)
                    extended = True
                value.append(s)
            value = quote(EMPTYSTRING.join(value))
            if extended:
                charset, language, value = decode_rfc2231(value)
                new_params.append((name, (charset, language, '"%s"' % value)))
            else:
                new_params.append((name, '"%s"' % value))
    return new_params

def collapse_rfc2231_value(value, errors='replace',
                           fallback_charset='us-ascii'):
    if not isinstance(value, tuple) or len(value) != 3:
        return unquote(value)
    # 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
    rawbytes = bytes(ord(c) for c in text)
    try:
        return str(rawbytes, charset, errors)
    except LookupError:
        # charset is not a known codec.
        return unquote(text)