1 # Copyright (C) 2001-2004 Python Software Foundation
2 # Author: Ben Gertzfield
3 # Contact: email-sig@python.org
5 """Quoted-printable content transfer encoding per RFCs 2045-2047.
7 This module handles the content transfer encoding method defined in RFC 2045
8 to encode US ASCII-like 8-bit data called `quoted-printable'. It is used to
9 safely encode text that is in a character set similar to the 7-bit US ASCII
10 character set, but that includes some 8-bit characters that are normally not
11 allowed in email bodies or headers.
13 Quoted-printable is very space-inefficient for encoding binary files; use the
14 email.base64MIME module for that instead.
16 This module provides an interface to encode and decode both headers and bodies
17 with quoted-printable encoding.
19 RFC 2045 defines a method for including character set information in an
20 `encoded-word' in a header. This method is commonly used for 8-bit real names
21 in To:/From:/Cc: etc. fields, as well as Subject: lines.
23 This module does not do the line wrapping or end-of-line character
24 conversion necessary for proper internationalized headers; it only
25 does dumb encoding and decoding. To deal with the various line
26 wrapping issues, use the email.Header module.
30 from string
import hexdigits
31 from email
.Utils
import fix_eols
39 hqre
= re
.compile(r
'[^-a-zA-Z0-9!*+/ ]')
40 bqre
= re
.compile(r
'[^ !-<>-~\t]')
45 def header_quopri_check(c
):
46 """Return True if the character should be escaped with header quopri."""
47 return bool(hqre
.match(c
))
50 def body_quopri_check(c
):
51 """Return True if the character should be escaped with body quopri."""
52 return bool(bqre
.match(c
))
55 def header_quopri_len(s
):
56 """Return the length of str when it is encoded with header quopri."""
66 def body_quopri_len(str):
67 """Return the length of str when it is encoded with body quopri."""
77 def _max_append(L
, s
, maxlen
, extra
=''):
80 elif len(L
[-1]) + len(s
) <= maxlen
:
87 """Turn a string in the form =AB to the ASCII character with value 0xab"""
88 return chr(int(s
[1:3], 16))
92 return "=%02X" % ord(c
)
96 def header_encode(header
, charset
="iso-8859-1", keep_eols
=False,
97 maxlinelen
=76, eol
=NL
):
98 """Encode a single header line with quoted-printable (like) encoding.
100 Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but
101 used specifically for email header fields to allow charsets with mostly 7
102 bit characters (and some 8 bit) to remain more or less readable in non-RFC
103 2045 aware mail clients.
105 charset names the character set to use to encode the header. It defaults
108 The resulting string will be in the form:
110 "=?charset?q?I_f=E2rt_in_your_g=E8n=E8ral_dire=E7tion?\\n
111 =?charset?q?Silly_=C8nglish_Kn=EEghts?="
113 with each line wrapped safely at, at most, maxlinelen characters (defaults
114 to 76 characters). If maxlinelen is None, the entire string is encoded in
115 one chunk with no splitting.
117 End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted
118 to the canonical email line separator \\r\\n unless the keep_eols
119 parameter is True (the default is False).
121 Each line of the header will be terminated in the value of eol, which
122 defaults to "\\n". Set this to "\\r\\n" if you are using the result of
123 this function directly in email.
125 # Return empty headers unchanged
130 header
= fix_eols(header
)
132 # Quopri encode each line, in encoded chunks no greater than maxlinelen in
133 # length, after the RFC chrome is added in.
135 if maxlinelen
is None:
136 # An obnoxiously large number that's good enough
139 max_encoded
= maxlinelen
- len(charset
) - MISC_LEN
- 1
142 # Space may be represented as _ instead of =20 for readability
144 _max_append(quoted
, '_', max_encoded
)
145 # These characters can be included verbatim
146 elif not hqre
.match(c
):
147 _max_append(quoted
, c
, max_encoded
)
148 # Otherwise, replace with hex value like =E2
150 _max_append(quoted
, "=%02X" % ord(c
), max_encoded
)
152 # Now add the RFC chrome to each encoded chunk and glue the chunks
153 # together. BAW: should we be able to specify the leading whitespace in
156 return joiner
.join(['=?%s?q?%s?=' % (charset
, line
) for line
in quoted
])
160 def encode(body
, binary
=False, maxlinelen
=76, eol
=NL
):
161 """Encode with quoted-printable, wrapping at maxlinelen characters.
163 If binary is False (the default), end-of-line characters will be converted
164 to the canonical email end-of-line sequence \\r\\n. Otherwise they will
167 Each line of encoded text will end with eol, which defaults to "\\n". Set
168 this to "\\r\\n" if you will be using the result of this function directly
171 Each line will be wrapped at, at most, maxlinelen characters (defaults to
172 76 characters). Long lines will have the `soft linefeed' quoted-printable
173 character "=" appended to them, so the decoded text will be identical to
180 body
= fix_eols(body
)
182 # BAW: We're accumulating the body text by string concatenation. That
183 # can't be very efficient, but I don't have time now to rewrite it. It
184 # just feels like this algorithm could be more efficient.
187 # Preserve line endings here so we can check later to see an eol needs to
188 # be added to the output later.
189 lines
= body
.splitlines(1)
191 # But strip off line-endings for processing this line.
192 if line
.endswith(CRLF
):
194 elif line
[-1] in CRLF
:
201 # Now we need to examine every character to see if it needs to be
202 # quopri encoded. BAW: again, string concatenation is inefficient.
203 for j
in range(linelen
):
209 # Check for whitespace at end of line; special case
214 # Check to see to see if the line has reached its maximum length
215 if len(encoded_line
) + len(c
) >= maxlinelen
:
216 encoded_body
+= encoded_line
+ '=' + eol
219 # Now at end of line..
220 if prev
and prev
in ' \t':
221 # Special case for whitespace at end of file
222 if lineno
+ 1 == len(lines
):
224 if len(encoded_line
) + len(prev
) > maxlinelen
:
225 encoded_body
+= encoded_line
+ '=' + eol
+ prev
227 encoded_body
+= encoded_line
+ prev
228 # Just normal whitespace at end of line
230 encoded_body
+= encoded_line
+ prev
+ '=' + eol
232 # Now look at the line we just finished and it has a line ending, we
233 # need to add eol to the end of the line.
234 if lines
[lineno
].endswith(CRLF
) or lines
[lineno
][-1] in CRLF
:
235 encoded_body
+= encoded_line
+ eol
237 encoded_body
+= encoded_line
242 # For convenience and backwards compatibility w/ standard base64 module
244 encodestring
= encode
248 # BAW: I'm not sure if the intent was for the signature of this function to be
249 # the same as base64MIME.decode() or not...
250 def decode(encoded
, eol
=NL
):
251 """Decode a quoted-printable string.
253 Lines are separated with eol, which defaults to \\n.
257 # BAW: see comment in encode() above. Again, we're building up the
258 # decoded string with string concatenation, which could be done much more
262 for line
in encoded
.splitlines():
275 # Otherwise, c == "=". Are we at the end of the line? If so, add
280 # Decode if in form =AB
281 elif i
+2 < n
and line
[i
+1] in hexdigits
and line
[i
+2] in hexdigits
:
282 decoded
+= unquote(line
[i
:i
+3])
284 # Otherwise, not in form =AB, pass literally
291 # Special case if original string did not end with eol
292 if not encoded
.endswith(eol
) and decoded
.endswith(eol
):
293 decoded
= decoded
[:-1]
297 # For convenience and backwards compatibility w/ standard base64 module
299 decodestring
= decode
303 def _unquote_match(match
):
304 """Turn a match in the form =AB to the ASCII character with value 0xab"""
309 # Header decoding is done a bit differently
310 def header_decode(s
):
311 """Decode a string encoded with RFC 2045 MIME header `Q' encoding.
313 This function does not parse a full MIME header value encoded with
314 quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use
315 the high level email.Header class for that functionality.
317 s
= s
.replace('_', ' ')
318 return re
.sub(r
'=\w{2}', _unquote_match
, s
)