source file: /System/Library/Frameworks/Python.framework/Versions/2.3/lib/python2.3/email/quopriMIME.py
file stats: 142 lines, 27 executed: 19.0% covered
   1. # Copyright (C) 2001,2002 Python Software Foundation
   2. # Author: che@debian.org (Ben Gertzfield)
   3. 
   4. """Quoted-printable content transfer encoding per RFCs 2045-2047.
   5. 
   6. This module handles the content transfer encoding method defined in RFC 2045
   7. to encode US ASCII-like 8-bit data called `quoted-printable'.  It is used to
   8. safely encode text that is in a character set similar to the 7-bit US ASCII
   9. character set, but that includes some 8-bit characters that are normally not
  10. allowed in email bodies or headers.
  11. 
  12. Quoted-printable is very space-inefficient for encoding binary files; use the
  13. email.base64MIME module for that instead.
  14. 
  15. This module provides an interface to encode and decode both headers and bodies
  16. with quoted-printable encoding.
  17. 
  18. RFC 2045 defines a method for including character set information in an
  19. `encoded-word' in a header.  This method is commonly used for 8-bit real names
  20. in To:/From:/Cc: etc. fields, as well as Subject: lines.
  21. 
  22. This module does not do the line wrapping or end-of-line character
  23. conversion necessary for proper internationalized headers; it only
  24. does dumb encoding and decoding.  To deal with the various line
  25. wrapping issues, use the email.Header module.
  26. """
  27. 
  28. import re
  29. from string import hexdigits
  30. from email.Utils import fix_eols
  31. 
  32. CRLF = '\r\n'
  33. NL = '\n'
  34. 
  35. # See also Charset.py
  36. MISC_LEN = 7
  37. 
  38. hqre = re.compile(r'[^-a-zA-Z0-9!*+/ ]')
  39. bqre = re.compile(r'[^ !-<>-~\t]')
  40. 
  41. try:
  42.     True, False
  43. except NameError:
  44.     True = 1
  45.     False = 0
  46. 
  47. 
  48. 
  49. # Helpers
  50. def header_quopri_check(c):
  51.     """Return True if the character should be escaped with header quopri."""
  52.     return hqre.match(c) and True
  53. 
  54. 
  55. def body_quopri_check(c):
  56.     """Return True if the character should be escaped with body quopri."""
  57.     return bqre.match(c) and True
  58. 
  59. 
  60. def header_quopri_len(s):
  61.     """Return the length of str when it is encoded with header quopri."""
  62.     count = 0
  63.     for c in s:
  64.         if hqre.match(c):
  65.             count += 3
  66.         else:
  67.             count += 1
  68.     return count
  69. 
  70. 
  71. def body_quopri_len(str):
  72.     """Return the length of str when it is encoded with body quopri."""
  73.     count = 0
  74.     for c in str:
  75.         if bqre.match(c):
  76.             count += 3
  77.         else:
  78.             count += 1
  79.     return count
  80. 
  81. 
  82. def _max_append(L, s, maxlen, extra=''):
  83.     if not L:
  84.         L.append(s.lstrip())
  85.     elif len(L[-1]) + len(s) <= maxlen:
  86.         L[-1] += extra + s
  87.     else:
  88.         L.append(s.lstrip())
  89. 
  90. 
  91. def unquote(s):
  92.     """Turn a string in the form =AB to the ASCII character with value 0xab"""
  93.     return chr(int(s[1:3], 16))
  94. 
  95. 
  96. def quote(c):
  97.     return "=%02X" % ord(c)
  98. 
  99. 
 100. 
 101. def header_encode(header, charset="iso-8859-1", keep_eols=False,
 102.                   maxlinelen=76, eol=NL):
 103.     """Encode a single header line with quoted-printable (like) encoding.
 104. 
 105.     Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but
 106.     used specifically for email header fields to allow charsets with mostly 7
 107.     bit characters (and some 8 bit) to remain more or less readable in non-RFC
 108.     2045 aware mail clients.
 109. 
 110.     charset names the character set to use to encode the header.  It defaults
 111.     to iso-8859-1.
 112. 
 113.     The resulting string will be in the form:
 114. 
 115.     "=?charset?q?I_f=E2rt_in_your_g=E8n=E8ral_dire=E7tion?\\n
 116.       =?charset?q?Silly_=C8nglish_Kn=EEghts?="
 117. 
 118.     with each line wrapped safely at, at most, maxlinelen characters (defaults
 119.     to 76 characters).  If maxlinelen is None, the entire string is encoded in
 120.     one chunk with no splitting.
 121. 
 122.     End-of-line characters (\\r, \\n, \\r\\n) will be automatically converted
 123.     to the canonical email line separator \\r\\n unless the keep_eols
 124.     parameter is True (the default is False).
 125. 
 126.     Each line of the header will be terminated in the value of eol, which
 127.     defaults to "\\n".  Set this to "\\r\\n" if you are using the result of
 128.     this function directly in email.
 129.     """
 130.     # Return empty headers unchanged
 131.     if not header:
 132.         return header
 133. 
 134.     if not keep_eols:
 135.         header = fix_eols(header)
 136. 
 137.     # Quopri encode each line, in encoded chunks no greater than maxlinelen in
 138.     # length, after the RFC chrome is added in.
 139.     quoted = []
 140.     if maxlinelen is None:
 141.         # An obnoxiously large number that's good enough
 142.         max_encoded = 100000
 143.     else:
 144.         max_encoded = maxlinelen - len(charset) - MISC_LEN - 1
 145. 
 146.     for c in header:
 147.         # Space may be represented as _ instead of =20 for readability
 148.         if c == ' ':
 149.             _max_append(quoted, '_', max_encoded)
 150.         # These characters can be included verbatim
 151.         elif not hqre.match(c):
 152.             _max_append(quoted, c, max_encoded)
 153.         # Otherwise, replace with hex value like =E2
 154.         else:
 155.             _max_append(quoted, "=%02X" % ord(c), max_encoded)
 156. 
 157.     # Now add the RFC chrome to each encoded chunk and glue the chunks
 158.     # together.  BAW: should we be able to specify the leading whitespace in
 159.     # the joiner?
 160.     joiner = eol + ' '
 161.     return joiner.join(['=?%s?q?%s?=' % (charset, line) for line in quoted])
 162. 
 163. 
 164. 
 165. def encode(body, binary=False, maxlinelen=76, eol=NL):
 166.     """Encode with quoted-printable, wrapping at maxlinelen characters.
 167. 
 168.     If binary is False (the default), end-of-line characters will be converted
 169.     to the canonical email end-of-line sequence \\r\\n.  Otherwise they will
 170.     be left verbatim.
 171. 
 172.     Each line of encoded text will end with eol, which defaults to "\\n".  Set
 173.     this to "\\r\\n" if you will be using the result of this function directly
 174.     in an email.
 175. 
 176.     Each line will be wrapped at, at most, maxlinelen characters (defaults to
 177.     76 characters).  Long lines will have the `soft linefeed' quoted-printable
 178.     character "=" appended to them, so the decoded text will be identical to
 179.     the original text.
 180.     """
 181.     if not body:
 182.         return body
 183. 
 184.     if not binary:
 185.         body = fix_eols(body)
 186. 
 187.     # BAW: We're accumulating the body text by string concatenation.  That
 188.     # can't be very efficient, but I don't have time now to rewrite it.  It
 189.     # just feels like this algorithm could be more efficient.
 190.     encoded_body = ''
 191.     lineno = -1
 192.     # Preserve line endings here so we can check later to see an eol needs to
 193.     # be added to the output later.
 194.     lines = body.splitlines(1)
 195.     for line in lines:
 196.         # But strip off line-endings for processing this line.
 197.         if line.endswith(CRLF):
 198.             line = line[:-2]
 199.         elif line[-1] in CRLF:
 200.             line = line[:-1]
 201. 
 202.         lineno += 1
 203.         encoded_line = ''
 204.         prev = None
 205.         linelen = len(line)
 206.         # Now we need to examine every character to see if it needs to be
 207.         # quopri encoded.  BAW: again, string concatenation is inefficient.
 208.         for j in range(linelen):
 209.             c = line[j]
 210.             prev = c
 211.             if bqre.match(c):
 212.                 c = quote(c)
 213.             elif j+1 == linelen:
 214.                 # Check for whitespace at end of line; special case
 215.                 if c not in ' \t':
 216.                     encoded_line += c
 217.                 prev = c
 218.                 continue
 219.             # Check to see to see if the line has reached its maximum length
 220.             if len(encoded_line) + len(c) >= maxlinelen:
 221.                 encoded_body += encoded_line + '=' + eol
 222.                 encoded_line = ''
 223.             encoded_line += c
 224.         # Now at end of line..
 225.         if prev and prev in ' \t':
 226.             # Special case for whitespace at end of file
 227.             if lineno + 1 == len(lines):
 228.                 prev = quote(prev)
 229.                 if len(encoded_line) + len(prev) > maxlinelen:
 230.                     encoded_body += encoded_line + '=' + eol + prev
 231.                 else:
 232.                     encoded_body += encoded_line + prev
 233.             # Just normal whitespace at end of line
 234.             else:
 235.                 encoded_body += encoded_line + prev + '=' + eol
 236.             encoded_line = ''
 237.         # Now look at the line we just finished and it has a line ending, we
 238.         # need to add eol to the end of the line.
 239.         if lines[lineno].endswith(CRLF) or lines[lineno][-1] in CRLF:
 240.             encoded_body += encoded_line + eol
 241.         else:
 242.             encoded_body += encoded_line
 243.         encoded_line = ''
 244.     return encoded_body
 245. 
 246. 
 247. # For convenience and backwards compatibility w/ standard base64 module
 248. body_encode = encode
 249. encodestring = encode
 250. 
 251. 
 252. 
 253. # BAW: I'm not sure if the intent was for the signature of this function to be
 254. # the same as base64MIME.decode() or not...
 255. def decode(encoded, eol=NL):
 256.     """Decode a quoted-printable string.
 257. 
 258.     Lines are separated with eol, which defaults to \\n.
 259.     """
 260.     if not encoded:
 261.         return encoded
 262.     # BAW: see comment in encode() above.  Again, we're building up the
 263.     # decoded string with string concatenation, which could be done much more
 264.     # efficiently.
 265.     decoded = ''
 266. 
 267.     for line in encoded.splitlines():
 268.         line = line.rstrip()
 269.         if not line:
 270.             decoded += eol
 271.             continue
 272. 
 273.         i = 0
 274.         n = len(line)
 275.         while i < n:
 276.             c = line[i]
 277.             if c <> '=':
 278.                 decoded += c
 279.                 i += 1
 280.             # Otherwise, c == "=".  Are we at the end of the line?  If so, add
 281.             # a soft line break.
 282.             elif i+1 == n:
 283.                 i += 1
 284.                 continue
 285.             # Decode if in form =AB
 286.             elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits:
 287.                 decoded += unquote(line[i:i+3])
 288.                 i += 3
 289.             # Otherwise, not in form =AB, pass literally
 290.             else:
 291.                 decoded += c
 292.                 i += 1
 293. 
 294.             if i == n:
 295.                 decoded += eol
 296.     # Special case if original string did not end with eol
 297.     if not encoded.endswith(eol) and decoded.endswith(eol):
 298.         decoded = decoded[:-1]
 299.     return decoded
 300. 
 301. 
 302. # For convenience and backwards compatibility w/ standard base64 module
 303. body_decode = decode
 304. decodestring = decode
 305. 
 306. 
 307. 
 308. def _unquote_match(match):
 309.     """Turn a match in the form =AB to the ASCII character with value 0xab"""
 310.     s = match.group(0)
 311.     return unquote(s)
 312. 
 313. 
 314. # Header decoding is done a bit differently
 315. def header_decode(s):
 316.     """Decode a string encoded with RFC 2045 MIME header `Q' encoding.
 317. 
 318.     This function does not parse a full MIME header value encoded with
 319.     quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use
 320.     the high level email.Header class for that functionality.
 321.     """
 322.     s = s.replace('_', ' ')
 323.     return re.sub(r'=\w{2}', _unquote_match, s)