1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
|
# Copyright (C) 2001 Python Software Foundation
# Author: barry@zope.com (Barry Warsaw)
"""A parser of RFC 2822 and MIME email messages.
"""
import re
from cStringIO import StringIO
# Intrapackage imports
import Errors
import Message
bcre = re.compile('boundary="?([^"]+)"?', re.IGNORECASE)
EMPTYSTRING = ''
NL = '\n'
class Parser:
def __init__(self, _class=Message.Message):
"""Parser of RFC 2822 and MIME email messages.
Creates an in-memory object tree representing the email message, which
can then be manipulated and turned over to a Generator to return the
textual representation of the message.
The string must be formatted as a block of RFC 2822 headers and header
continuation lines, optionally preceeded by a `Unix-from' header. The
header block is terminated either by the end of the string or by a
blank line.
_class is the class to instantiate for new message objects when they
must be created. This class must have a constructor that can take
zero arguments. Default is Message.Message.
"""
self._class = _class
def parse(self, fp):
root = self._class()
self._parseheaders(root, fp)
self._parsebody(root, fp)
return root
def parsestr(self, text):
return self.parse(StringIO(text))
def _parseheaders(self, container, fp):
# Parse the headers, returning a list of header/value pairs. None as
# the header means the Unix-From header.
lastheader = ''
lastvalue = []
lineno = 0
while 1:
line = fp.readline()[:-1]
if not line or not line.strip():
break
lineno += 1
# Check for initial Unix From_ line
if line.startswith('From '):
if lineno == 1:
container.set_unixfrom(line)
continue
else:
raise Errors.HeaderParseError(
'Unix-from in headers after first rfc822 header')
#
# Header continuation line
if line[0] in ' \t':
if not lastheader:
raise Errors.HeaderParseError(
'Continuation line seen before first header')
lastvalue.append(line)
continue
# Normal, non-continuation header. BAW: this should check to make
# sure it's a legal header, e.g. doesn't contain spaces. Also, we
# should expose the header matching algorithm in the API, and
# allow for a non-strict parsing mode (that ignores the line
# instead of raising the exception).
i = line.find(':')
if i < 0:
raise Errors.HeaderParseError(
'Not a header, not a continuation')
if lastheader:
container[lastheader] = NL.join(lastvalue)
lastheader = line[:i]
lastvalue = [line[i+1:].lstrip()]
# Make sure we retain the last header
if lastheader:
container[lastheader] = NL.join(lastvalue)
def _parsebody(self, container, fp):
# Parse the body, but first split the payload on the content-type
# boundary if present.
boundary = isdigest = None
ctype = container['content-type']
if ctype:
mo = bcre.search(ctype)
if mo:
boundary = mo.group(1)
isdigest = container.get_type() == 'multipart/digest'
# If there's a boundary, split the payload text into its constituent
# parts and parse each separately. Otherwise, just parse the rest of
# the body as a single message. Note: any exceptions raised in the
# recursive parse need to have their line numbers coerced.
if boundary:
preamble = epilogue = None
# Split into subparts. The first boundary we're looking for won't
# have the leading newline since we're at the start of the body
# text.
separator = '--' + boundary
payload = fp.read()
start = payload.find(separator)
if start < 0:
raise Errors.BoundaryError(
"Couldn't find starting boundary: %s" % boundary)
if start > 0:
# there's some pre-MIME boundary preamble
preamble = payload[0:start]
start += len(separator) + 1 + isdigest
terminator = payload.find('\n' + separator + '--', start)
if terminator < 0:
raise Errors.BoundaryError(
"Couldn't find terminating boundary: %s" % boundary)
if terminator+len(separator)+3 < len(payload):
# there's some post-MIME boundary epilogue
epilogue = payload[terminator+len(separator)+3:]
# We split the textual payload on the boundary separator, which
# includes the trailing newline. If the container is a
# multipart/digest then the subparts are by default message/rfc822
# instead of text/plain. In that case, they'll have an extra
# newline before the headers to distinguish the message's headers
# from the subpart headers.
if isdigest:
separator += '\n\n'
else:
separator += '\n'
parts = payload[start:terminator].split('\n' + separator)
for part in parts:
msgobj = self.parsestr(part)
container.preamble = preamble
container.epilogue = epilogue
container.add_payload(msgobj)
elif ctype == 'message/rfc822':
# Create a container for the payload, but watch out for there not
# being any headers left
try:
msg = self.parse(fp)
except Errors.HeaderParseError:
msg = self._class()
self._parsebody(msg, fp)
container.add_payload(msg)
else:
container.add_payload(fp.read())
|
