rfc822.py

来自「mallet是自然语言处理、机器学习领域的一个开源项目。」· Python 代码 · 共 1,011 行 · 第 1/3 页

            elif self.field[self.pos] == '.':
                self.pos = self.pos + 1
                sdlist.append('.')
            elif self.field[self.pos] in self.atomends:
                break
            else: sdlist.append(self.getatom())
        return ''.join(sdlist)

    def getdelimited(self, beginchar, endchars, allowcomments = 1):
        """Parse a header fragment delimited by special characters.

        `beginchar' is the start character for the fragment.  If self is not
        looking at an instance of `beginchar' then getdelimited returns the
        empty string.

        `endchars' is a sequence of allowable end-delimiting characters.
        Parsing stops when one of these is encountered.

        If `allowcomments' is non-zero, embedded RFC 2822 comments are allowed
        within the parsed fragment.
        """
        if self.field[self.pos] != beginchar:
            return ''

        slist = ['']
        quote = 0
        self.pos = self.pos + 1
        while self.pos < len(self.field):
            if quote == 1:
                slist.append(self.field[self.pos])
                quote = 0
            elif self.field[self.pos] in endchars:
                self.pos = self.pos + 1
                break
            elif allowcomments and self.field[self.pos] == '(':
                slist.append(self.getcomment())
            elif self.field[self.pos] == '\\':
                quote = 1
            else:
                slist.append(self.field[self.pos])
            self.pos = self.pos + 1

        return ''.join(slist)

    def getquote(self):
        """Get a quote-delimited fragment from self's field."""
        return self.getdelimited('"', '"\r', 0)

    def getcomment(self):
        """Get a parenthesis-delimited fragment from self's field."""
        return self.getdelimited('(', ')\r', 1)

    def getdomainliteral(self):
        """Parse an RFC 2822 domain-literal."""
        return '[%s]' % self.getdelimited('[', ']\r', 0)

    def getatom(self, atomends=None):
        """Parse an RFC 2822 atom.

        Optional atomends specifies a different set of end token delimiters
        (the default is to use self.atomends).  This is used e.g. in
        getphraselist() since phrase endings must not include the `.' (which
        is legal in phrases)."""
        atomlist = ['']
        if atomends is None:
            atomends = self.atomends

        while self.pos < len(self.field):
            if self.field[self.pos] in atomends:
                break
            else: atomlist.append(self.field[self.pos])
            self.pos = self.pos + 1

        return ''.join(atomlist)

    def getphraselist(self):
        """Parse a sequence of RFC 2822 phrases.

        A phrase is a sequence of words, which are in turn either RFC 2822
        atoms or quoted-strings.  Phrases are canonicalized by squeezing all
        runs of continuous whitespace into one space.
        """
        plist = []

        while self.pos < len(self.field):
            if self.field[self.pos] in self.LWS:
                self.pos = self.pos + 1
            elif self.field[self.pos] == '"':
                plist.append(self.getquote())
            elif self.field[self.pos] == '(':
                self.commentlist.append(self.getcomment())
            elif self.field[self.pos] in self.phraseends:
                break
            else:
                plist.append(self.getatom(self.phraseends))

        return plist

class AddressList(AddrlistClass):
    """An AddressList encapsulates a list of parsed RFC 2822 addresses."""
    def __init__(self, field):
        AddrlistClass.__init__(self, field)
        if field:
            self.addresslist = self.getaddrlist()
        else:
            self.addresslist = []

    def __len__(self):
        return len(self.addresslist)

    def __str__(self):
        return ", ".join(map(dump_address_pair, self.addresslist))

    def __add__(self, other):
        # Set union
        newaddr = AddressList(None)
        newaddr.addresslist = self.addresslist[:]
        for x in other.addresslist:
            if not x in self.addresslist:
                newaddr.addresslist.append(x)
        return newaddr

    def __iadd__(self, other):
        # Set union, in-place
        for x in other.addresslist:
            if not x in self.addresslist:
                self.addresslist.append(x)
        return self

    def __sub__(self, other):
        # Set difference
        newaddr = AddressList(None)
        for x in self.addresslist:
            if not x in other.addresslist:
                newaddr.addresslist.append(x)
        return newaddr

    def __isub__(self, other):
        # Set difference, in-place
        for x in other.addresslist:
            if x in self.addresslist:
                self.addresslist.remove(x)
        return self

    def __getitem__(self, index):
        # Make indexing, slices, and 'in' work
        return self.addresslist[index]

def dump_address_pair(pair):
    """Dump a (name, address) pair in a canonicalized form."""
    if pair[0]:
        return '"' + pair[0] + '" <' + pair[1] + '>'
    else:
        return pair[1]

# Parse a date field

_monthnames = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul',
               'aug', 'sep', 'oct', 'nov', 'dec',
               'january', 'february', 'march', 'april', 'may', 'june', 'july',
               'august', 'september', 'october', 'november', 'december']
_daynames = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun']

# The timezone table does not include the military time zones defined
# in RFC822, other than Z.  According to RFC1123, the description in
# RFC822 gets the signs wrong, so we can't rely on any such time
# zones.  RFC1123 recommends that numeric timezone indicators be used
# instead of timezone names.

_timezones = {'UT':0, 'UTC':0, 'GMT':0, 'Z':0,
              'AST': -400, 'ADT': -300,  # Atlantic (used in Canada)
              'EST': -500, 'EDT': -400,  # Eastern
              'CST': -600, 'CDT': -500,  # Central
              'MST': -700, 'MDT': -600,  # Mountain
              'PST': -800, 'PDT': -700   # Pacific
              }


def parsedate_tz(data):
    """Convert a date string to a time tuple.

    Accounts for military timezones.
    """
    if not data:
        return None
    data = data.split()
    if data[0][-1] in (',', '.') or data[0].lower() in _daynames:
        # There's a dayname here. Skip it
        del data[0]
    if len(data) == 3: # RFC 850 date, deprecated
        stuff = data[0].split('-')
        if len(stuff) == 3:
            data = stuff + data[1:]
    if len(data) == 4:
        s = data[3]
        i = s.find('+')
        if i > 0:
            data[3:] = [s[:i], s[i+1:]]
        else:
            data.append('') # Dummy tz
    if len(data) < 5:
        return None
    data = data[:5]
    [dd, mm, yy, tm, tz] = data
    mm = mm.lower()
    if not mm in _monthnames:
        dd, mm = mm, dd.lower()
        if not mm in _monthnames:
            return None
    mm = _monthnames.index(mm)+1
    if mm > 12: mm = mm - 12
    if dd[-1] == ',':
        dd = dd[:-1]
    i = yy.find(':')
    if i > 0:
        yy, tm = tm, yy
    if yy[-1] == ',':
        yy = yy[:-1]
    if not yy[0].isdigit():
        yy, tz = tz, yy
    if tm[-1] == ',':
        tm = tm[:-1]
    tm = tm.split(':')
    if len(tm) == 2:
        [thh, tmm] = tm
        tss = '0'
    elif len(tm) == 3:
        [thh, tmm, tss] = tm
    else:
        return None
    try:
        yy = int(yy)
        dd = int(dd)
        thh = int(thh)
        tmm = int(tmm)
        tss = int(tss)
    except ValueError:
        return None
    tzoffset = None
    tz = tz.upper()
    if _timezones.has_key(tz):
        tzoffset = _timezones[tz]
    else:
        try:
            tzoffset = int(tz)
        except ValueError:
            pass
    # Convert a timezone offset into seconds ; -0500 -> -18000
    if tzoffset:
        if tzoffset < 0:
            tzsign = -1
            tzoffset = -tzoffset
        else:
            tzsign = 1
        tzoffset = tzsign * ( (tzoffset//100)*3600 + (tzoffset % 100)*60)
    tuple = (yy, mm, dd, thh, tmm, tss, 0, 0, 0, tzoffset)
    return tuple


def parsedate(data):
    """Convert a time string to a time tuple."""
    t = parsedate_tz(data)
    if type(t) == type( () ):
        return t[:9]
    else: return t


def mktime_tz(data):
    """Turn a 10-tuple as returned by parsedate_tz() into a UTC timestamp."""
    if data[9] is None:
        # No zone info, so localtime is better assumption than GMT
        return time.mktime(data[:8] + (-1,))
    else:
        t = time.mktime(data[:8] + (0,))
        return t - data[9] - time.timezone

def formatdate(timeval=None):
    """Returns time format preferred for Internet standards.

    Sun, 06 Nov 1994 08:49:37 GMT  ; RFC 822, updated by RFC 1123

    According to RFC 1123, day and month names must always be in
    English.  If not for that, this code could use strftime().  It
    can't because strftime() honors the locale and could generated
    non-English names.
    """
    if timeval is None:
        timeval = time.time()
    timeval = time.gmtime(timeval)
    return "%s, %02d %s %04d %02d:%02d:%02d GMT" % (
            ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"][timeval[6]],
            timeval[2],
            ["Jan", "Feb", "Mar", "Apr", "May", "Jun",
             "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"][timeval[1]-1],
                                timeval[0], timeval[3], timeval[4], timeval[5])


# When used as script, run a small test program.
# The first command line argument must be a filename containing one
# message in RFC-822 format.

if __name__ == '__main__':
    import sys, os
    file = os.path.join(os.environ['HOME'], 'Mail/inbox/1')
    if sys.argv[1:]: file = sys.argv[1]
    f = open(file, 'r')
    m = Message(f)
    print 'From:', m.getaddr('from')
    print 'To:', m.getaddrlist('to')
    print 'Subject:', m.getheader('subject')
    print 'Date:', m.getheader('date')
    date = m.getdate_tz('date')
    tz = date[-1]
    date = time.localtime(mktime_tz(date))
    if date:
        print 'ParsedDate:', time.asctime(date),
        hhmmss = tz
        hhmm, ss = divmod(hhmmss, 60)
        hh, mm = divmod(hhmm, 60)
        print "%+03d%02d" % (hh, mm),
        if ss: print ".%02d" % ss,
        print
    else:
        print 'ParsedDate:', None
    m.rewindbody()
    n = 0
    while f.readline():
        n = n + 1
    print 'Lines:', n
    print '-'*70
    print 'len =', len(m)
    if m.has_key('Date'): print 'Date =', m['Date']
    if m.has_key('X-Nonsense'): pass
    print 'keys =', m.keys()
    print 'values =', m.values()
    print 'items =', m.items()