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

"""RFC 2822 message manipulation.

Note: This is only a very rough sketch of a full RFC-822 parser; in particular
the tokenizing of addresses does not adhere to all the quoting rules.

Note: RFC 2822 is a long awaited update to RFC 822.  This module should
conform to RFC 2822, and is thus mis-named (it's not worth renaming it).  Some
effort at RFC 2822 updates have been made, but a thorough audit has not been
performed.  Consider any RFC 2822 non-conformance to be a bug.

    RFC 2822: http://www.faqs.org/rfcs/rfc2822.html
    RFC 822 : http://www.faqs.org/rfcs/rfc822.html (obsolete)

Directions for use:

To create a Message object: first open a file, e.g.:

  fp = open(file, 'r')

You can use any other legal way of getting an open file object, e.g. use
sys.stdin or call os.popen().  Then pass the open file object to the Message()
constructor:

  m = Message(fp)

This class can work with any input object that supports a readline method.  If
the input object has seek and tell capability, the rewindbody method will
work; also illegal lines will be pushed back onto the input stream.  If the
input object lacks seek but has an `unread' method that can push back a line
of input, Message will use that to push back illegal lines.  Thus this class
can be used to parse messages coming from a buffered stream.

The optional `seekable' argument is provided as a workaround for certain stdio
libraries in which tell() discards buffered data before discovering that the
lseek() system call doesn't work.  For maximum portability, you should set the
seekable argument to zero to prevent that initial \code{tell} when passing in
an unseekable object such as a a file object created from a socket object.  If
it is 1 on entry -- which it is by default -- the tell() method of the open
file object is called once; if this raises an exception, seekable is reset to
0.  For other nonzero values of seekable, this test is not made.

To get the text of a particular header there are several methods:

  str = m.getheader(name)
  str = m.getrawheader(name)

where name is the name of the header, e.g. 'Subject'.  The difference is that
getheader() strips the leading and trailing whitespace, while getrawheader()
doesn't.  Both functions retain embedded whitespace (including newlines)
exactly as they are specified in the header, and leave the case of the text
unchanged.

For addresses and address lists there are functions

  realname, mailaddress = m.getaddr(name)
  list = m.getaddrlist(name)

where the latter returns a list of (realname, mailaddr) tuples.

There is also a method

  time = m.getdate(name)

which parses a Date-like field and returns a time-compatible tuple,
i.e. a tuple such as returned by time.localtime() or accepted by
time.mktime().

See the class definition for lower level access methods.

There are also some utility functions here.
"""
# Cleanup and extensions by Eric S. Raymond <[e-mail]>

import time

__all__ = ["Message","AddressList","parsedate","parsedate_tz","mktime_tz"]

_blanklines = ('\r\n', '\n')            # Optimization for islast()


class Message:
    """Represents a single RFC 2822-compliant message."""

    def __init__(self, fp, seekable = 1):
        """Initialize the class instance and read the headers."""
        if seekable == 1:
            # Exercise tell() to make sure it works
            # (and then assume seek() works, too)
            try:
                fp.tell()
            except (AttributeError, IOError):
                seekable = 0
            else:
                seekable = 1
        self.fp = fp
        self.seekable = seekable
        self.startofheaders = None
        self.startofbody = None
        #
        if self.seekable:
            try:
                self.startofheaders = self.fp.tell()
            except IOError:
                self.seekable = 0
        #
        self.readheaders()
        #
        if self.seekable:
            try:
                self.startofbody = self.fp.tell()
            except IOError:
                self.seekable = 0

    def rewindbody(self):
        """Rewind the file to the start of the body (if seekable)."""
        if not self.seekable:
            raise IOError, "unseekable file"
        self.fp.seek(self.startofbody)

    def readheaders(self):
        """Read header lines.

        Read header lines up to the entirely blank line that terminates them.
        The (normally blank) line that ends the headers is skipped, but not
        included in the returned list.  If a non-header line ends the headers,
        (which is an error), an attempt is made to backspace over it; it is
        never included in the returned list.

        The variable self.status is set to the empty string if all went well,
        otherwise it is an error message.  The variable self.headers is a
        completely uninterpreted list of lines contained in the header (so
        printing them will reproduce the header exactly as it appears in the
        file).
        """
        self.dict = {}
        self.unixfrom = ''
        self.headers = list = []
        self.status = ''
        headerseen = ""
        firstline = 1
        startofline = unread = tell = None
        if hasattr(self.fp, 'unread'):
            unread = self.fp.unread
        elif self.seekable:
            tell = self.fp.tell
        while 1:
            if tell:
                try:
                    startofline = tell()
                except IOError:
                    startofline = tell = None
                    self.seekable = 0
            line = self.fp.readline()
            if not line:
                self.status = 'EOF in headers'
                break
            # Skip unix From name time lines
            if firstline and line.startswith('From '):
                self.unixfrom = self.unixfrom + line
                continue
            firstline = 0
            if headerseen and line[0] in ' \t':
                # It's a continuation line.
                list.append(line)
                x = (self.dict[headerseen] + "\n " + line.strip())
                self.dict[headerseen] = x.strip()
                continue
            elif self.iscomment(line):
                # It's a comment.  Ignore it.
                continue
            elif self.islast(line):
                # Note! No pushback here!  The delimiter line gets eaten.
                break
            headerseen = self.isheader(line)
            if headerseen:
                # It's a legal header line, save it.
                list.append(line)
                self.dict[headerseen] = line[len(headerseen)+1:].strip()
                continue
            else:
                # It's not a header line; throw it back and stop here.
                if not self.dict:
                    self.status = 'No headers'
                else:
                    self.status = 'Non-header line where header expected'
                # Try to undo the read.
                if unread:
                    unread(line)
                elif tell:
                    self.fp.seek(startofline)
                else:
                    self.status = self.status + '; bad seek'
                break

    def isheader(self, line):
        """Determine whether a given line is a legal header.

        This method should return the header name, suitably canonicalized.
        You may override this method in order to use Message parsing on tagged
        data in RFC 2822-like formats with special header formats.
        """
        i = line.find(':')
        if i > 0:
            return line[:i].lower()
        else:
            return None

    def islast(self, line):
        """Determine whether a line is a legal end of RFC 2822 headers.

        You may override this method if your application wants to bend the
        rules, e.g. to strip trailing whitespace, or to recognize MH template
        separators ('--------').  For convenience (e.g. for code reading from
        sockets) a line consisting of \r\n also matches.
        """
        return line in _blanklines

    def iscomment(self, line):
        """Determine whether a line should be skipped entirely.

        You may override this method in order to use Message parsing on tagged
        data in RFC 2822-like formats that support embedded comments or
        free-text data.
        """
        return None

    def getallmatchingheaders(self, name):
        """Find all header lines matching a given header name.

        Look through the list of headers and find all lines matching a given
        header name (and their continuation lines).  A list of the lines is
        returned, without interpretation.  If the header does not occur, an
        empty list is returned.  If the header occurs multiple times, all
        occurrences are returned.  Case is not important in the header name.
        """
        name = name.lower() + ':'
        n = len(name)
        list = []
        hit = 0
        for line in self.headers:
            if line[:n].lower() == name:
                hit = 1
            elif not line[:1].isspace():
                hit = 0
            if hit:
                list.append(line)
        return list

    def getfirstmatchingheader(self, name):
        """Get the first header line matching name.

        This is similar to getallmatchingheaders, but it returns only the
        first matching header (and its continuation lines).
        """
        name = name.lower() + ':'
        n = len(name)
        list = []
        hit = 0
        for line in self.headers:
            if hit:
                if not line[:1].isspace():
                    break
            elif line[:n].lower() == name:
                hit = 1
            if hit:
                list.append(line)
        return list

    def getrawheader(self, name):
        """A higher-level interface to getfirstmatchingheader().

        Return a string containing the literal text of the header but with the
        keyword stripped.  All leading, trailing and embedded whitespace is
        kept in the string, however.  Return None if the header does not
        occur.
        """

        list = self.getfirstmatchingheader(name)
        if not list:
            return None
        list[0] = list[0][len(name) + 1:]
        return ''.join(list)

    def getheader(self, name, default=None):
        """Get the header value for a name.

        This is the normal interface: it returns a stripped version of the
        header value for a given header name, or None if it doesn't exist.
        This uses the dictionary version which finds the *last* such header.
        """
        try:
            return self.dict[name.lower()]
        except KeyError:
            return default
    get = getheader

    def getheaders(self, name):
        """Get all values for a header.

        This returns a list of values for headers given more than once; each
        value in the result list is stripped in the same way as the result of
        getheader().  If the header is not given, return an empty list.
        """
        result = []
        current = ''
        have_header = 0
        for s in self.getallmatchingheaders(name):
            if s[0].isspace():
                if current:
                    current = "%s\n %s" % (current, s.strip())
                else:
                    current = s.strip()
            else:
                if have_header:
                    result.append(current)
                current = s[s.find(":") + 1:].strip()
                have_header = 1
        if have_header:
            result.append(current)
        return result

    def getaddr(self, name):
        """Get a single address from a header, as a tuple.

        An example return value:
        ('Guido van Rossum', '[e-mail]')
        """
        # New, by Ben Escoto
        alist = self.getaddrlist(name)
        if alist:
            return alist[0]
        else:
            return (None, None)

    def getaddrlist(self, name):
        """Get a list of addresses from a header.