summaryrefslogtreecommitdiffstats
path: root/Lib/email/quopriMIME.py
blob: 002034e169c55bd09fc82026888b26a70d443ec0 (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
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
# Copyright (C) 2001,2002 Python Software Foundation
# Author: che@debian.org (Ben Gertzfield)

"""Quoted-printable content transfer encoding per RFCs 2045-2047.

This module handles the content transfer encoding method defined in RFC 2045
to encode US ASCII-like 8-bit data called `quoted-printable'.  It is used to
safely encode text that is in a character set similar to the 7-bit US ASCII
character set, but that includes some 8-bit characters that are normally not
allowed in email bodies or headers.

Quoted-printable is very space-inefficient for encoding binary files; use the
email.base64MIME module for that instead.

This module provides an interface to encode and decode both headers and bodies
with quoted-printable encoding.

RFC 2045 defines a method for including character set information in an
`encoded-word' in a header.  This method is commonly used for 8-bit real names
in To:/From:/Cc: etc. fields, as well as Subject: lines.

This module does not do the line wrapping or end-of-line character
conversion necessary for proper internationalized headers; it only
does dumb encoding and decoding.  To deal with the various line
wrapping issues, use the email.Header module.  
"""

import re
from string import hexdigits
from email.Utils import fix_eols

CRLF = '\r\n'
NL = '\n'

# See also Charset.py
MISC_LEN = 7

hqre = re.compile(r'[^-a-zA-Z0-9!*+/ ]')
bqre = re.compile(r'[^ !-<>-~\t]')



# Helpers
def header_quopri_check(c):
    """Return true if the character should be escaped with header quopri."""
    return hqre.match(c) and 1


def body_quopri_check(c):
    """Return true if the character should be escaped with body quopri."""
    return bqre.match(c) and 1

    
def header_quopri_len(s):
    """Return the length of str when it is encoded with header quopri."""
    count = 0
    for c in s:
        if hqre.match(c):
            count += 3
        else:
            count += 1
    return count


def body_quopri_len(str):
    """Return the length of str when it is encoded with body quopri."""
    count = 0
    for c in str:
        if bqre.match(c):
            count += 3
        else:
            count += 1
    return count


def _max_append(L, s, maxlen, extra=''):
    if not L:
        L.append(s)
    elif len(L[-1]) + len(s) < maxlen:
        L[-1] += extra + s
    else:
        L.append(s)


def unquote(s):
    """Turn a string in the form =AB to the ASCII character with value 0xab"""
    return chr(int(s[1:3], 16))


def quote(c):
    return "=%02X" % ord(c)



def header_encode(header, charset="iso-8859-1", keep_eols=0, maxlinelen=76,
                  eol=NL):
    """Encode a single header line with quoted-printable (like) encoding.

    Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but
    used specifically for email header fields to allow charsets with mostly 7
    bit characters (and some 8 bit) to remain more or less readable in non-RFC
    2045 aware mail clients.

    charset names the character set to use to encode the header.  It defaults
    to iso-8859-1.

    The resulting string will be in the form:

    "=?charset?q?I_f=E2rt_in_your_g=E8n=E8ral_dire=E7tion?\\n
      =?charset?q?Silly_=C8nglish_Kn=EEghts?="

    with each line wrapped safely at, at most, maxlinelen characters (defaults
    to 76 characters).

    End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted
    to the canonical email line separator \\r\\n unless the keep_eols
    parameter is set to true (the default is false).

    Each line of the header will be terminated in the value of eol, which
    defaults to "\\n".  Set this to "\\r\\n" if you are using the result of
    this function directly in email.
    """
    # Return empty headers unchanged
    if not header:
        return header

    if not keep_eols:
        header = fix_eols(header)

    # Quopri encode each line, in encoded chunks no greater than maxlinelen in
    # lenght, after the RFC chrome is added in.
    quoted = []
    max_encoded = maxlinelen - len(charset) - MISC_LEN
    
    for c in header:
        # Space may be represented as _ instead of =20 for readability
        if c == ' ':
            _max_append(quoted, '_', max_encoded)
        # These characters can be included verbatim
        elif not hqre.match(c):
            _max_append(quoted, c, max_encoded)
        # Otherwise, replace with hex value like =E2
        else:
            _max_append(quoted, "=%02X" % ord(c), max_encoded)

    # Now add the RFC chrome to each encoded chunk and glue the chunks
    # together.  BAW: should we be able to specify the leading whitespace in
    # the joiner?
    joiner = eol + ' '
    return joiner.join(['=?%s?q?%s?=' % (charset, line) for line in quoted])



def encode(body, binary=0, maxlinelen=76, eol=NL):
    """Encode with quoted-printable, wrapping at maxlinelen characters.

    If binary is false (the default), end-of-line characters will be converted
    to the canonical email end-of-line sequence \\r\\n.  Otherwise they will
    be left verbatim.

    Each line of encoded text will end with eol, which defaults to "\\n".  Set
    this to "\\r\\n" if you will be using the result of this function directly
    in an email.

    Each line will be wrapped at, at most, maxlinelen characters (defaults to
    76 characters).  Long lines will have the `soft linefeed' quoted-printable
    character "=" appended to them, so the decoded text will be identical to
    the original text.
    """
    if not body:
        return body

    if not binary:
        body = fix_eols(body)

    # BAW: We're accumulating the body text by string concatenation.  That
    # can't be very efficient, but I don't have time now to rewrite it.  It
    # just feels like this algorithm could be more efficient.
    encoded_body = ''
    lineno = -1
    # Preserve line endings here so we can check later to see an eol needs to
    # be added to the output later.
    lines = body.splitlines(1)
    for line in lines:
        # But strip off line-endings for processing this line.
        if line.endswith(CRLF):
            line = line[:-2]
        elif line[-1] in CRLF:
            line = line[:-1]
            
        lineno += 1
        encoded_line = ''
        prev = None
        linelen = len(line)
        # Now we need to examine every character to see if it needs to be
        # quopri encoded.  BAW: again, string concatenation is inefficient.
        for j in range(linelen):
            c = line[j]
            prev = c
            if bqre.match(c):
                c = quote(c)
            elif j+1 == linelen:
                # Check for whitespace at end of line; special case
                if c not in ' \t':
                    encoded_line += c
                prev = c
                continue
            # Check to see to see if the line has reached its maximum length
            if len(encoded_line) + len(c) >= maxlinelen:
                encoded_body += encoded_line + '=' + eol
                encoded_line = ''
            encoded_line += c
        # Now at end of line..
        if prev and prev in ' \t':
            # Special case for whitespace at end of file
            if lineno+1 == len(lines):
                prev = quote(prev)
                if len(encoded_line) + len(prev) > maxlinelen:
                    encoded_body += encoded_line + '=' + eol + prev
                else:
                    encoded_body += encoded_line + prev
            # Just normal whitespace at end of line
            else:
                encoded_body += encoded_line + prev + '=' + eol
            encoded_line = ''
        # Now look at the line we just finished and it has a line ending, we
        # need to add eol to the end of the line.
        if lines[lineno].endswith(CRLF) or lines[lineno][-1] in CRLF:
            encoded_body += encoded_line + eol
        else:
            encoded_body += encoded_line
        encoded_line = ''
    return encoded_body


# For convenience and backwards compatibility w/ standard base64 module
body_encode = encode
encodestring = encode



# BAW: I'm not sure if the intent was for the signature of this function to be
# the same as base64MIME.decode() or not...
def decode(encoded, eol=NL):
    """Decode a quoted-printable string.

    Lines are separated with eol, which defaults to \\n.
    """
    if not encoded:
        return encoded
    # BAW: see comment in encode() above.  Again, we're building up the
    # decoded string with string concatenation, which could be done much more
    # efficiently.
    decoded = ''

    for line in encoded.splitlines():
        line = line.rstrip()
        if not line:
            decoded += eol
            continue

        i = 0
        n = len(line)
        while i < n:
            c = line[i]
            if c <> '=':
                decoded += c
                i += 1
            # Otherwise, c == "=".  Are we at the end of the line?  If so, add
            # a soft line break.
            elif i+1 == n:
                i += 1
                continue
            # Decode if in form =AB
            elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits:
                decoded += unquote(line[i:i+3])
                i += 3
            # Otherwise, not in form =AB, pass literally
            else:
                decoded += c
                i += 1

            if i == n:
                decoded += eol
    # Special case if original string did not end with eol
    if encoded[-1] <> eol and decoded[-1] == eol:
        decoded = decoded[:-1]
    return decoded


# For convenience and backwards compatibility w/ standard base64 module
body_decode = decode
decodestring = decode



def _unquote_match(match):
    """Turn a match in the form =AB to the ASCII character with value 0xab"""
    s = match.group(0)
    return unquote(s)


# Header decoding is done a bit differently
def header_decode(s):
    """Decode a string encoded with RFC 2045 MIME header `Q' encoding.

    This function does not parse a full MIME header value encoded with
    quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use
    the high level email.Header class for that functionality.
    """
    s = s.replace('_', ' ')
    return re.sub(r'=\w{2}', _unquote_match, s)