header.py

mallet是自然语言处理、机器学习领域的一个开源项目。

# Copyright (C) 2002 Python Software Foundation
# Author: [e-mail] (Ben Gertzfield), [e-mail] (Barry Warsaw)

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

import re
import binascii
from types import StringType, UnicodeType

import email.quopriMIME
import email.base64MIME
from email.Errors import HeaderParseError
from email.Charset import Charset

try:
    from email._compat22 import _floordiv
except SyntaxError:
    # Python 2.1 spells integer division differently
    from email._compat21 import _floordiv

try:
    True, False
except NameError:
    True = 1
    False = 0

CRLFSPACE = '\r\n '
CRLF = '\r\n'
NL = '\n'
SPACE = ' '
USPACE = u' '
SPACE8 = ' ' * 8
EMPTYSTRING = ''
UEMPTYSTRING = u''

MAXLINELEN = 76

ENCODE = 1
DECODE = 2

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 ?=
  ''', re.VERBOSE | re.IGNORECASE)

pcre = re.compile('([,;])')

# 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]+:$')



# 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':
                    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 of pairs as returned by decode_header()

    decode_header() takes a header value string and returns a sequence of
    pairs of the format (decoded_string, charset) where charset is the string
    name of the character set.

    This function takes one of those sequence of pairs and returns a Header
    instance.  Optional maxlinelen, header_name, and continuation_ws are as in
    the Header constructor.
    """
    h = Header(maxlinelen=maxlinelen, header_name=header_name,
               continuation_ws=continuation_ws)
    for s, charset in decoded_seq:
        # None means us-ascii but we can simply pass it on to h.append()
        if charset is not None and not isinstance(charset, Charset):
            charset = Charset(charset)
        h.append(s, charset)
    return h



class Header:
    def __init__(self, s=None, charset=None,
                 maxlinelen=None, header_name=None,
                 continuation_ws=' ', errors='strict'):
        """Create a MIME-compliant header that can contain many character sets.

        Optional s is the initial header value.  If None, the initial header
        value is not set.  You can later append to the header with .append()
        method calls.  s may be a byte string or a Unicode string, but see the
        .append() documentation for semantics.

        Optional charset serves two purposes: it has the same meaning as the
        charset argument to the .append() method.  It also sets the default
        character set for all subsequent .append() calls that omit the charset
        argument.  If charset is not provided in the constructor, the us-ascii
        charset is used both as s's initial charset and as the default for
        subsequent .append() calls.

        The maximum line length can be specified explicit via maxlinelen.  For
        splitting the first line to a shorter value (to account for the field
        header which isn't included in s, e.g. `Subject') pass in the name of
        the field in header_name.  The default maxlinelen is 76.

        continuation_ws must be RFC 2822 compliant folding whitespace (usually
        either a space or a hard tab) which will be prepended to continuation
        lines.

        errors is passed through to the .append() call.
        """
        if charset is None:
            charset = USASCII
        if not isinstance(charset, Charset):
            charset = Charset(charset)
        self._charset = charset
        self._continuation_ws = continuation_ws
        cws_expanded_len = len(continuation_ws.replace('\t', SPACE8))
        # BAW: I believe `chunks' and `maxlinelen' should be non-public.
        self._chunks = []
        if s is not None:
            self.append(s, charset, errors)
        if maxlinelen is None:
            maxlinelen = MAXLINELEN
        if header_name is None:
            # We don't know anything about the field header so the first line
            # is the same length as subsequent lines.
            self._firstlinelen = maxlinelen
        else:
            # The first line should be shorter to take into account the field
            # header.  Also subtract off 2 extra for the colon and space.
            self._firstlinelen = maxlinelen - len(header_name) - 2
        # Second and subsequent lines should subtract off the length in
        # columns of the continuation whitespace prefix.
        self._maxlinelen = maxlinelen - cws_expanded_len

    def __str__(self):
        """A synonym for self.encode()."""
        return self.encode()

    def __unicode__(self):
        """Helper for the built-in unicode function."""
        uchunks = []
        lastcs = None
        for s, charset in self._chunks:
            # We must preserve spaces between encoded and non-encoded word
            # boundaries, which means for us we need to add a space when we go
            # from a charset to None/us-ascii, or from None/us-ascii to a
            # charset.  Only do this for the second and subsequent chunks.
            nextcs = charset
            if uchunks:
                if lastcs not in (None, 'us-ascii'):
                    if nextcs in (None, 'us-ascii'):
                        uchunks.append(USPACE)
                        nextcs = None
                elif nextcs not in (None, 'us-ascii'):
                    uchunks.append(USPACE)
            lastcs = nextcs
            uchunks.append(unicode(s, str(charset)))
        return UEMPTYSTRING.join(uchunks)

    # Rich comparison operators for equality only.  BAW: does it make sense to
    # have or explicitly disable <, <=, >, >= operators?
    def __eq__(self, other):
        # other may be a Header or a string.  Both are fine so coerce
        # ourselves to a string, swap the args and do another comparison.
        return other == self.encode()

    def __ne__(self, other):
        return not self == other

    def append(self, s, charset=None, errors='strict'):
        """Append a string to the MIME header.

        Optional charset, if given, should be a Charset instance or the name
        of a character set (which will be converted to a Charset instance).  A
        value of None (the default) means that the charset given in the
        constructor is used.

        s may be a byte string or a Unicode string.  If it is a byte string
        (i.e. isinstance(s, StringType) is true), then charset is the encoding
        of that byte string, and a UnicodeError will be raised if the string
        cannot be decoded with that charset.  If s is a Unicode string, then
        charset is a hint specifying the character set of the characters in
        the string.  In this case, when producing an RFC 2822 compliant header
        using RFC 2047 rules, the Unicode string will be encoded using the
        following charsets in order: us-ascii, the charset hint, utf-8.  The
        first character set not to provoke a UnicodeError is used.

        Optional `errors' is passed as the third argument to any unicode() or
        ustr.encode() call.
        """