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
155
|
import os
import email
import tempfile
import re
import shlex
from email.header import Header
import email.charset as charset
charset.add_charset('utf-8', charset.QP, charset.QP, 'utf-8')
from email.iterators import typed_subpart_iterator
import alot.helper as helper
from alot.settings import settings
from alot.helper import string_sanitize
from alot.helper import string_decode
def extract_headers(mail, headers=None):
headertext = u''
if headers == None:
headers = mail.keys()
for key in headers:
value = u''
if key in mail:
value = decode_header(mail.get(key, ''))
headertext += '%s: %s\n' % (key, value)
return headertext
def extract_body(mail, types=None):
"""
returns a body text string for given mail.
If types is `None`, 'text/*' is used:
In case mail has a 'text/html' part, it is prefered over
'text/plain' parts.
:param mail: the mail to use
:type mail: :class:`email.Message`
:param types: mime content types to use for body string
:type types: list of str
"""
html = list(typed_subpart_iterator(mail, 'text', 'html'))
# if no specific types are given, we favor text/html over text/plain
drop_plaintext = False
if html and not types:
drop_plaintext = True
body_parts = []
for part in mail.walk():
ctype = part.get_content_type()
if types is not None:
if ctype not in types:
continue
cd = part.get('Content-Disposition', '')
if cd.startswith('attachment'):
continue
enc = part.get_content_charset() or 'ascii'
raw_payload = part.get_payload(decode=True)
if part.get_content_maintype() == 'text':
raw_payload = string_decode(raw_payload, enc)
if ctype == 'text/plain' and not drop_plaintext:
body_parts.append(string_sanitize(raw_payload))
else:
#get mime handler
handler = settings.get_mime_handler(ctype, key='view',
interactive=False)
if handler:
#open tempfile. Not all handlers accept stuff from stdin
tmpfile = tempfile.NamedTemporaryFile(delete=False,
suffix='.html')
#write payload to tmpfile
if part.get_content_maintype() == 'text':
tmpfile.write(raw_payload.encode('utf8'))
else:
tmpfile.write(raw_payload)
tmpfile.close()
#create and call external command
cmd = handler % tmpfile.name
cmdlist = shlex.split(cmd.encode('utf-8', errors='ignore'))
rendered_payload, errmsg, retval = helper.call_cmd(cmdlist)
#remove tempfile
os.unlink(tmpfile.name)
if rendered_payload: # handler had output
body_parts.append(string_sanitize(rendered_payload))
elif part.get_content_maintype() == 'text':
body_parts.append(string_sanitize(raw_payload))
# else drop
return '\n\n'.join(body_parts)
def decode_header(header, normalize=False):
"""
decode a header value to a unicode string
values are usually a mixture of different substrings
encoded in quoted printable using diffetrent encodings.
This turns it into a single unicode string
:param header: the header value
:type header: str
:param normalize: replace trailing spaces after newlines
:type normalize: bool
:rtype: unicode
"""
# If the value isn't ascii as RFC2822 prescribes,
# we just return the unicode bytestring as is
value = string_decode(header) # convert to unicode
try:
value = value.encode('ascii')
except UnicodeEncodeError:
return value
# otherwise we interpret RFC2822 encoding escape sequences
valuelist = email.header.decode_header(header)
decoded_list = []
for v, enc in valuelist:
v = string_decode(v, enc)
decoded_list.append(string_sanitize(v))
value = u' '.join(decoded_list)
if normalize:
value = re.sub(r'\n\s+', r' ', value)
return value
def encode_header(key, value):
"""
encodes a unicode string as a valid header value
:param key: the header field this value will be stored in
:type key: str
:param value: the value to be encoded
:type value: unicode
"""
# handle list of "realname <email>" entries separately
if key.lower() in ['from', 'to', 'cc', 'bcc']:
rawentries = value.split(',')
encodedentries = []
for entry in rawentries:
m = re.search('\s*(.*)\s+<(.*\@.*\.\w*)>\s*$', entry)
if m: # If a realname part is contained
name, address = m.groups()
# try to encode as ascii, if that fails, revert to utf-8
# name must be a unicode string here
namepart = Header(name)
# append address part encoded as ascii
entry = '%s <%s>' % (namepart.encode(), address)
encodedentries.append(entry)
value = Header(', '.join(encodedentries))
else:
value = Header(value)
return value
|
