Lib/email/quoprimime.py

   1 # Copyright (C) 2001-2006 Python Software Foundation
   2 # Author: Ben Gertzfield
   3 # Contact: email-sig@python.org
   4
   5 """Quoted-printable content transfer encoding per RFCs 2045-2047.
   6
   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.
  12
  13 Quoted-printable is very space-inefficient for encoding binary files; use the
  14 email.base64MIME module for that instead.
  15
  16 This module provides an interface to encode and decode both headers and bodies
  17 with quoted-printable encoding.
  18
  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.
  22
  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.
  27 """
  28
  29 __all__ = [
  30     'body_decode',
  31     'body_encode',
  32     'body_quopri_check',
  33     'body_quopri_len',
  34     'decode',
  35     'decodestring',
  36     'encode',
  37     'encodestring',
  38     'header_decode',
  39     'header_encode',
  40     'header_quopri_check',
  41     'header_quopri_len',
  42     'quote',
  43     'unquote',
  44     ]
  45
  46 import re
  47
  48 from string import hexdigits
  49 from email.utils import fix_eols
  50
  51 CRLF = '\r\n'
  52 NL = '\n'
  53
  54 # See also Charset.py
  55 MISC_LEN = 7
  56
  57 hqre = re.compile(r'[^-a-zA-Z0-9!*+/ ]')
  58 bqre = re.compile(r'[^ !-<>-~\t]')
  59
  60
  61 \f
  62 # Helpers
  63 def header_quopri_check(c):
  64     """Return True if the character should be escaped with header quopri."""
  65     return bool(hqre.match(c))
  66
  67
  68 def body_quopri_check(c):
  69     """Return True if the character should be escaped with body quopri."""
  70     return bool(bqre.match(c))
  71
  72
  73 def header_quopri_len(s):
  74     """Return the length of str when it is encoded with header quopri."""
  75     count = 0
  76     for c in s:
  77         if hqre.match(c):
  78             count += 3
  79         else:
  80             count += 1
  81     return count
  82
  83
  84 def body_quopri_len(str):
  85     """Return the length of str when it is encoded with body quopri."""
  86     count = 0
  87     for c in str:
  88         if bqre.match(c):
  89             count += 3
  90         else:
  91             count += 1
  92     return count
  93
  94
  95 def _max_append(L, s, maxlen, extra=''):
  96     if not L:
  97         L.append(s.lstrip())
  98     elif len(L[-1]) + len(s) <= maxlen:
  99         L[-1] += extra + s
 100     else:
 101         L.append(s.lstrip())
 102
 103
 104 def unquote(s):
 105     """Turn a string in the form =AB to the ASCII character with value 0xab"""
 106     return chr(int(s[1:3], 16))
 107
 108
 109 def quote(c):
 110     return "=%02X" % ord(c)
 111
 112
 113 \f
 114 def header_encode(header, charset="iso-8859-1", keep_eols=False,
 115                   maxlinelen=76, eol=NL):
 116     """Encode a single header line with quoted-printable (like) encoding.
 117
 118     Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but
 119     used specifically for email header fields to allow charsets with mostly 7
 120     bit characters (and some 8 bit) to remain more or less readable in non-RFC
 121     2045 aware mail clients.
 122
 123     charset names the character set to use to encode the header.  It defaults
 124     to iso-8859-1.
 125
 126     The resulting string will be in the form:
 127
 128     "=?charset?q?I_f=E2rt_in_your_g=E8n=E8ral_dire=E7tion?\\n
 129       =?charset?q?Silly_=C8nglish_Kn=EEghts?="
 130
 131     with each line wrapped safely at, at most, maxlinelen characters (defaults
 132     to 76 characters).  If maxlinelen is None, the entire string is encoded in
 133     one chunk with no splitting.
 134
 135     End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted
 136     to the canonical email line separator \\r\\n unless the keep_eols
 137     parameter is True (the default is False).
 138
 139     Each line of the header will be terminated in the value of eol, which
 140     defaults to "\\n".  Set this to "\\r\\n" if you are using the result of
 141     this function directly in email.
 142     """
 143     # Return empty headers unchanged
 144     if not header:
 145         return header
 146
 147     if not keep_eols:
 148         header = fix_eols(header)
 149
 150     # Quopri encode each line, in encoded chunks no greater than maxlinelen in
 151     # length, after the RFC chrome is added in.
 152     quoted = []
 153     if maxlinelen is None:
 154         # An obnoxiously large number that's good enough
 155         max_encoded = 100000
 156     else:
 157         max_encoded = maxlinelen - len(charset) - MISC_LEN - 1
 158
 159     for c in header:
 160         # Space may be represented as _ instead of =20 for readability
 161         if c == ' ':
 162             _max_append(quoted, '_', max_encoded)
 163         # These characters can be included verbatim
 164         elif not hqre.match(c):
 165             _max_append(quoted, c, max_encoded)
 166         # Otherwise, replace with hex value like =E2
 167         else:
 168             _max_append(quoted, "=%02X" % ord(c), max_encoded)
 169
 170     # Now add the RFC chrome to each encoded chunk and glue the chunks
 171     # together.  BAW: should we be able to specify the leading whitespace in
 172     # the joiner?
 173     joiner = eol + ' '
 174     return joiner.join(['=?%s?q?%s?=' % (charset, line) for line in quoted])
 175
 176
 177 \f
 178 def encode(body, binary=False, maxlinelen=76, eol=NL):
 179     """Encode with quoted-printable, wrapping at maxlinelen characters.
 180
 181     If binary is False (the default), end-of-line characters will be converted
 182     to the canonical email end-of-line sequence \\r\\n.  Otherwise they will
 183     be left verbatim.
 184
 185     Each line of encoded text will end with eol, which defaults to "\\n".  Set
 186     this to "\\r\\n" if you will be using the result of this function directly
 187     in an email.
 188
 189     Each line will be wrapped at, at most, maxlinelen characters (defaults to
 190     76 characters).  Long lines will have the `soft linefeed' quoted-printable
 191     character "=" appended to them, so the decoded text will be identical to
 192     the original text.
 193     """
 194     if not body:
 195         return body
 196
 197     if not binary:
 198         body = fix_eols(body)
 199
 200     # BAW: We're accumulating the body text by string concatenation.  That
 201     # can't be very efficient, but I don't have time now to rewrite it.  It
 202     # just feels like this algorithm could be more efficient.
 203     encoded_body = ''
 204     lineno = -1
 205     # Preserve line endings here so we can check later to see an eol needs to
 206     # be added to the output later.
 207     lines = body.splitlines(1)
 208     for line in lines:
 209         # But strip off line-endings for processing this line.
 210         if line.endswith(CRLF):
 211             line = line[:-2]
 212         elif line[-1] in CRLF:
 213             line = line[:-1]
 214
 215         lineno += 1
 216         encoded_line = ''
 217         prev = None
 218         linelen = len(line)
 219         # Now we need to examine every character to see if it needs to be
 220         # quopri encoded.  BAW: again, string concatenation is inefficient.
 221         for j in range(linelen):
 222             c = line[j]
 223             prev = c
 224             if bqre.match(c):
 225                 c = quote(c)
 226             elif j+1 == linelen:
 227                 # Check for whitespace at end of line; special case
 228                 if c not in ' \t':
 229                     encoded_line += c
 230                 prev = c
 231                 continue
 232             # Check to see to see if the line has reached its maximum length
 233             if len(encoded_line) + len(c) >= maxlinelen:
 234                 encoded_body += encoded_line + '=' + eol
 235                 encoded_line = ''
 236             encoded_line += c
 237         # Now at end of line..
 238         if prev and prev in ' \t':
 239             # Special case for whitespace at end of file
 240             if lineno + 1 == len(lines):
 241                 prev = quote(prev)
 242                 if len(encoded_line) + len(prev) > maxlinelen:
 243                     encoded_body += encoded_line + '=' + eol + prev
 244                 else:
 245                     encoded_body += encoded_line + prev
 246             # Just normal whitespace at end of line
 247             else:
 248                 encoded_body += encoded_line + prev + '=' + eol
 249             encoded_line = ''
 250         # Now look at the line we just finished and it has a line ending, we
 251         # need to add eol to the end of the line.
 252         if lines[lineno].endswith(CRLF) or lines[lineno][-1] in CRLF:
 253             encoded_body += encoded_line + eol
 254         else:
 255             encoded_body += encoded_line
 256         encoded_line = ''
 257     return encoded_body
 258
 259
 260 # For convenience and backwards compatibility w/ standard base64 module
 261 body_encode = encode
 262 encodestring = encode
 263
 264
 265 \f
 266 # BAW: I'm not sure if the intent was for the signature of this function to be
 267 # the same as base64MIME.decode() or not...
 268 def decode(encoded, eol=NL):
 269     """Decode a quoted-printable string.
 270
 271     Lines are separated with eol, which defaults to \\n.
 272     """
 273     if not encoded:
 274         return encoded
 275     # BAW: see comment in encode() above.  Again, we're building up the
 276     # decoded string with string concatenation, which could be done much more
 277     # efficiently.
 278     decoded = ''
 279
 280     for line in encoded.splitlines():
 281         line = line.rstrip()
 282         if not line:
 283             decoded += eol
 284             continue
 285
 286         i = 0
 287         n = len(line)
 288         while i < n:
 289             c = line[i]
 290             if c <> '=':
 291                 decoded += c
 292                 i += 1
 293             # Otherwise, c == "=".  Are we at the end of the line?  If so, add
 294             # a soft line break.
 295             elif i+1 == n:
 296                 i += 1
 297                 continue
 298             # Decode if in form =AB
 299             elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits:
 300                 decoded += unquote(line[i:i+3])
 301                 i += 3
 302             # Otherwise, not in form =AB, pass literally
 303             else:
 304                 decoded += c
 305                 i += 1
 306
 307             if i == n:
 308                 decoded += eol
 309     # Special case if original string did not end with eol
 310     if not encoded.endswith(eol) and decoded.endswith(eol):
 311         decoded = decoded[:-1]
 312     return decoded
 313
 314
 315 # For convenience and backwards compatibility w/ standard base64 module
 316 body_decode = decode
 317 decodestring = decode
 318
 319
 320 \f
 321 def _unquote_match(match):
 322     """Turn a match in the form =AB to the ASCII character with value 0xab"""
 323     s = match.group(0)
 324     return unquote(s)
 325
 326
 327 # Header decoding is done a bit differently
 328 def header_decode(s):
 329     """Decode a string encoded with RFC 2045 MIME header `Q' encoding.
 330
 331     This function does not parse a full MIME header value encoded with
 332     quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use
 333     the high level email.Header class for that functionality.
 334     """
 335     s = s.replace('_', ' ')
 336     return re.sub(r'=\w{2}', _unquote_match, s)