1
 ?÷     # Copyright (C) 2002-2006 Python Software Foundation
# Author: Ben Gertzfield, Barry Warsaw
# Contact: email-sig@python.org

"""Header encoding and decoding functionality."""

__all__ = [
    'Header',
    'decode_header',
    'make_header',
    ]

import re
import binascii

import email.quoprimime
import email.base64mime

from email.errors import HeaderParseError
from email.charset import Charset

NL = '\n'
SPACE = ' '
USPACE = u' '
SPACE8 = ' ' * 8
UEMPTYSTRING = u''

MAXLINELEN = 76

USASCII = Charset('us-ascii')
UTF8 = Charset('utf-8')

# Match encoded-word strings in the form =?charset?q?Hello_World?=
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<encoded>.*?)      # non-greedy up to the next ?= is the encoded string
  \?=                   # literal ?=
  (?=[ \t]|$)           # whitespace or the end of the string
  ''', re.VERBOSE | re.IGNORECASE | re.MULTILINE)

# Field name regexp, including trailing colon, but not separating whitespace,
# according to RFC 2822.  Character range is from tilde to exclamation mark.
# For use with .match()
fcre = re.compile(r'[\041-\176]+:$')

# Find a header embedded in a putative header value.  Used to check for
# header injection attack.
_embeded_header = re.compile(r'\n[^ \t]+:')


# Helpers
_max_append = email.quoprimime._max_append


def decode_header(header):
    """Decode a message header value without converting charset.

    Returns a list of (decoded_string, charset) pairs containing each of the
    decoded parts of the header.  Charset is None for non-encoded parts of the
    header, otherwise a lower-case string containing the name of the character
    set specified in the encoded string.

    An email.errors.HeaderParseError may be raised when certain decoding error
    occurs (e.g. a base64 decoding exception).
    """
    # If no encoding, just return the header
    header = str(header)
    if not ecre.search(header):
        return [(header, None)]
    decoded = []
    dec = ''
    for line in header.splitlines():
        # This line might not have an encoding in it
        if not ecre.search(line):
            decoded.append((line, None))
            continue
        parts = ecre.split(line)
        while parts:
            unenc = parts.pop(0).strip()
            if unenc:
                # Should we continue a long line?
                if decoded and decoded[-1][1] is None:
                    decoded[-1] = (decoded[-1][0] + SPACE + unenc, None)
                else:
                    decoded.append((unenc, None))
            if parts:
                charset, encoding = [s.lower() for s in parts[0:2]]
                encoded = parts[2]
                dec = None
                if encoding == 'q':
                    dec = email.quoprimime.header_decode(encoded)
                elif encoding == 'b':
                    paderr = len(encoded) % 4   # Postel's law: add missing padding
                    if paderr:
                        encoded += '==='[:4 - paderr]
                    try:
                        dec = email.base64mime.decode(encoded)
                    except binascii.Error:
                        # Turn this into a higher level exception.  BAW: Right
                        # now we throw the lower level exception away but
                        # when/if we get exception chaining, we'll preserve it.
                        raise HeaderParseError
                if dec is None:
                    dec = encoded

                if decoded and decoded[-1][1] == charset:
                    decoded[-1] = (decoded[-1][0] + dec, decoded[-1][1])
                else:
                    decoded.append((dec, charset))
            del parts[0:3]
    return decoded


def make_header(decoded_seq, maxlinelen=None, header_name=None,
                continuation_ws=' '):
    """Create a Header from a sequence o