summaryrefslogtreecommitdiffstats
path: root/Lib/mimetools.py
blob: 67623ec72081251e0cd9bcd00ea42beb688ed1a0 (plain)
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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
"""Various tools used by MIME-reading or MIME-writing programs."""


import os
import rfc822
import tempfile

__all__ = ["Message","choose_boundary","encode","decode","copyliteral",
           "copybinary"]

class Message(rfc822.Message):
    """A derived class of rfc822.Message that knows about MIME headers and
    contains some hooks for decoding encoded and multipart messages."""

    def __init__(self, fp, seekable = 1):
        rfc822.Message.__init__(self, fp, seekable)
        self.encodingheader = \
                self.getheader('content-transfer-encoding')
        self.typeheader = \
                self.getheader('content-type')
        self.parsetype()
        self.parseplist()

    def parsetype(self):
        str = self.typeheader
        if str is None:
            str = 'text/plain'
        if ';' in str:
            i = str.index(';')
            self.plisttext = str[i:]
            str = str[:i]
        else:
            self.plisttext = ''
        fields = str.split('/')
        for i in range(len(fields)):
            fields[i] = fields[i].strip().lower()
        self.type = '/'.join(fields)
        self.maintype = fields[0]
        self.subtype = '/'.join(fields[1:])

    def parseplist(self):
        str = self.plisttext
        self.plist = []
        while str[:1] == ';':
            str = str[1:]
            if ';' in str:
                # XXX Should parse quotes!
                end = str.index(';')
            else:
                end = len(str)
            f = str[:end]
            if '=' in f:
                i = f.index('=')
                f = f[:i].strip().lower() + \
                        '=' + f[i+1:].strip()
            self.plist.append(f.strip())
            str = str[end:]

    def getplist(self):
        return self.plist

    def getparam(self, name):
        name = name.lower() + '='
        n = len(name)
        for p in self.plist:
            if p[:n] == name:
                return rfc822.unquote(p[n:])
        return None

    def getparamnames(self):
        result = []
        for p in self.plist:
            i = p.find('=')
            if i >= 0:
                result.append(p[:i].lower())
        return result

    def getencoding(self):
        if self.encodingheader is None:
            return '7bit'
        return self.encodingheader.lower()

    def gettype(self):
        return self.type

    def getmaintype(self):
        return self.maintype

    def getsubtype(self):
        return self.subtype




# Utility functions
# -----------------

try:
    import thread
except ImportError:
    import dummy_thread as thread
_counter_lock = thread.allocate_lock()
del thread

_counter = 0
def _get_next_counter():
    global _counter
    _counter_lock.acquire()
    _counter += 1
    result = _counter
    _counter_lock.release()
    return result

_prefix = None

def choose_boundary():
    """Return a string usable as a multipart boundary.

    The string chosen is unique within a single program run, and
    incorporates the user id (if available), process id (if available),
    and current time.  So it's very unlikely the returned string appears
    in message text, but there's no guarantee.

    The boundary contains dots so you have to quote it in the header."""

    global _prefix
    import time
    import random
    if _prefix is None:
        import socket
        hostid = socket.gethostbyname(socket.gethostname())
        try:
            uid = `os.getuid()`
        except AttributeError:
            uid = '1'
        try:
            pid = `os.getpid()`
        except AttributeError:
            pid = '1'
        _prefix = hostid + '.' + uid + '.' + pid
    return "%s.%.3f.%d" % (_prefix, time.time(), _get_next_counter())


# Subroutines for decoding some common content-transfer-types

def decode(input, output, encoding):
    """Decode common content-transfer-encodings (base64, quopri, uuencode)."""
    if encoding == 'base64':
        import base64
        return base64.decode(input, output)
    if encoding == 'quoted-printable':
        import quopri
        return quopri.decode(input, output)
    if encoding in ('uuencode', 'x-uuencode', 'uue', 'x-uue'):
        import uu
        return uu.decode(input, output)
    if encoding in ('7bit', '8bit'):
        return output.write(input.read())
    if encoding in decodetab:
        pipethrough(input, decodetab[encoding], output)
    else:
        raise ValueError, \
              'unknown Content-Transfer-Encoding: %s' % encoding

def encode(input, output, encoding):
    """Encode common content-transfer-encodings (base64, quopri, uuencode)."""
    if encoding == 'base64':
        import base64
        return base64.encode(input, output)
    if encoding == 'quoted-printable':
        import quopri
        return quopri.encode(input, output, 0)
    if encoding in ('uuencode', 'x-uuencode', 'uue', 'x-uue'):
        import uu
        return uu.encode(input, output)
    if encoding in ('7bit', '8bit'):
        return output.write(input.read())
    if encoding in encodetab:
        pipethrough(input, encodetab[encoding], output)
    else:
        raise ValueError, \
              'unknown Content-Transfer-Encoding: %s' % encoding

# The following is no longer used for standard encodings

# XXX This requires that uudecode and mmencode are in $PATH

uudecode_pipe = '''(
TEMP=/tmp/@uu.$$
sed "s%^begin [0-7][0-7]* .*%begin 600 $TEMP%" | uudecode
cat $TEMP
rm $TEMP
)'''

decodetab = {
        'uuencode':             uudecode_pipe,
        'x-uuencode':           uudecode_pipe,
        'uue':                  uudecode_pipe,
        'x-uue':                uudecode_pipe,
        'quoted-printable':     'mmencode -u -q',
        'base64':               'mmencode -u -b',
}

encodetab = {
        'x-uuencode':           'uuencode tempfile',
        'uuencode':             'uuencode tempfile',
        'x-uue':                'uuencode tempfile',
        'uue':                  'uuencode tempfile',
        'quoted-printable':     'mmencode -q',
        'base64':               'mmencode -b',
}

def pipeto(input, command):
    pipe = os.popen(command, 'w')
    copyliteral(input, pipe)
    pipe.close()

def pipethrough(input, command, output):
    (fd, tempname) = tempfile.mkstemp()
    temp = os.fdopen(fd, 'w')
    copyliteral(input, temp)
    temp.close()
    pipe = os.popen(command + ' <' + tempname, 'r')
    copybinary(pipe, output)
    pipe.close()
    os.unlink(tempname)

def copyliteral(input, output):
    while 1:
        line = input.readline()
        if not line: break
        output.write(line)

def copybinary(input, output):
    BUFSIZE = 8192
    while 1:
        line = input.read(BUFSIZE)
        if not line: break
        output.write(line)