0
      1
  #   	ˆl–ßi~”Ji?u2 \¸®å1hßÂ„ŸÁÀ  "   ˆl–ßi~”*e¶¥8 Ap-\lJbÑ¿Ãƒh¹ÂÁ     ˆ¾Ãƒh¹ÂÁ  "   ˆl–ß=¿J	µ2ÛR‚ œPÜm›€˜´oÄƒh¹ÃÂ ?÷     	# Copyright (C) 2004-2006 Python Software Foundation
# Authors: Baxter, Wouters and Warsaw
# Contact: email-sig@python.org

"""FeedParser - An email feed parser.

The feed parser implements an interface for incrementally parsing an email
message, line by line.  This has advantages for certain applications, such as
those reading email messages off a socket.

FeedParser.feed() is the primary interface for pushing new data into the
parser.  It returns when there's nothing more it can do with the available
data.  When you have no more data to push into the parser, call .close().
This completes the parsing and returns the root message object.

The other advantage of this parser is that it will never raise a parsing
exception.  Instead, when it finds something unexpected, it adds a 'defect' to
the current message.  Defects are just instances that live on the message
object's .defects attribute.
"""

__all__ = ['FeedParser']

import re

from email import errors
from email import message

NLCRE = re.compile('\r\n|\r|\n')
NLCRE_bol = re.compile('(\r\n|\r|\n)')
NLCRE_eol = re.compile('(\r\n|\r|\n)\Z')
NLCRE_crack = re.compile('(\r\n|\r|\n)')
# RFC 2822 $3.6.8 Optional fields.  ftext is %d33-57 / %d59-126, Any character
# except controls, SP, and ":".
headerRE = re.compile(r'^(From |[\041-\071\073-\176]{1,}:|[\t ])')
EMPTYSTRING = ''
NL = '\n'

NeedMoreData = object()



class BufferedSubFile(object):
    """A file-ish object that can have new data loaded into it.

    You can also push and pop line-matching predicates onto a stack.  When the
    current predicate matches the current line, a false EOF response
    (i.e. empty string) is returned instead.  This lets the parser adhere to a
    simple abstraction -- it parses until EOF closes the current message.
    """
    def __init__(self):
        # The last partial line pushed into this object.
        self._partial = ''
        # The list of full, pushed lines, in reverse order
        self._lines = []
        # The stack of false-EOF checking predicates.
        self._eofstack = []
        # A flag indicating whether the file has been closed or not.
        self._closed = False

    def push_eof_matcher(self, pred):
        self._eofstack.append(pred)

    def pop_eof_matcher(self):
        return self._eofstack.pop()

    def close(self):
        # Don't forget any trailing partial line.
        self._lines.append(self._partial)
        self._partial = ''
        self._closed = True

    def readline(self):
        if not self._lines:
            if self._closed:
                return ''
            return NeedMoreData
        # Pop the line off the stack and see if it matches the current
        # false-EOF predicate.
        line = self._lines.pop()
        # RFC 2046, section 5.1.2 requires us to recognize outer level
        # boundaries at any level of inner nesting.  Do this, but be sure it's
        # in the order of most to least nested.
        for ateof in self._eofstack[::-1]:
            if ateof(line):
                # We're at the false EOF.  But push the last line back first.
                self._lines.append(line)
                return ''
        return line

    def unreadline(self, line):
        # Let the consumer push a line back into the buffer.
        assert line is not NeedMoreData
        self._lines.append(line)

    def push(self, data):
        """Push some new data into this object."""
        # Handle any previous leftovers
        data, self._partial = self._partial + data, ''
        # Crack into lines, but preserve the newlines on the end of each
        parts = NLCRE_crack.split(data)
        # The *ahem* interesting behaviour of re.split when supplied grouping
        # parentheses is that the last element of the resulting list is the
        # data after the final RE.  In the case of a NL/CR terminated string,
        # this is the empty string.
        self._partial