20 from email.charset import Charset
30 USASCII = Charset('us-ascii')
31 UTF8 = Charset('utf-8')
33 # Match encoded-word strings in the form =?charset?q?Hello_World?=
36   (?P<charset>[^?]*?)   # non-greedy up to the next ? is the charset
62     """Decode a message header value without converting charset.
64     Returns a list of (decoded_string, charset) pairs containing each of the
65     decoded parts of the header.  Charset is None for non-encoded parts of the
93                 charset, encoding = [s.lower() for s in parts[0:2]]
112                 if decoded and decoded[-1][1] == charset:
115                     decoded.append((dec, charset))
126     pairs of the format (decoded_string, charset) where charset is the string
135     for s, charset in decoded_seq:
137         if charset is not None and not isinstance(charset, Charset):
138             charset = Charset(charset)
139         h.append(s, charset)
145     def __init__(self, s=None, charset=None,  argument
155         Optional charset serves two purposes: it has the same meaning as the
156         charset argument to the .append() method.  It also sets the default
157         character set for all subsequent .append() calls that omit the charset
158         argument.  If charset is not provided in the constructor, the us-ascii
159         charset is used both as s's initial charset and as the default for
173         if charset is None:
174             charset = USASCII
175         if not isinstance(charset, Charset):
176             charset = Charset(charset)
177         self._charset = charset
183             self.append(s, charset, errors)
206         for s, charset in self._chunks:
209             # from a charset to None/us-ascii, or from None/us-ascii to a
210             # charset.  Only do this for the second and subsequent chunks.
211             nextcs = charset
220             uchunks.append(unicode(s, str(charset)))
233     def append(self, s, charset=None, errors='strict'):  argument
236         Optional charset, if given, should be a Charset instance or the name
237         of a character set (which will be converted to a Charset instance).  A
238         value of None (the default) means that the charset given in the
242         (i.e. isinstance(s, str) is true), then charset is the encoding of
244         cannot be decoded with that charset.  If s is a Unicode string, then
245         charset is a hint specifying the character set of the characters in
248         following charsets in order: us-ascii, the charset hint, utf-8.  The
254         if charset is None:
255             charset = self._charset
256         elif not isinstance(charset, Charset):
257             charset = Charset(charset)
258         # If the charset is our faux 8bit charset, leave the string unchanged
259         if charset != '8bit':
262             # charset.
265                 # converted to a unicode with the input codec of the charset.
266                 incodec = charset.input_codec or 'us-ascii'
271                 outcodec = charset.output_codec or 'us-ascii'
277                 for charset in USASCII, charset, UTF8:
279                         outcodec = charset.output_codec or 'us-ascii'
286         self._chunks.append((s, charset))
288     def _split(self, s, charset, maxlinelen, splitchars):  argument
290         splittable = charset.to_splittable(s)
291         encoded = charset.from_splittable(splittable, True)
292         elen = charset.encoded_header_len(encoded)
295             return [(encoded, charset)]
302         if charset == '8bit':
303             return [(s, charset)]
312         # For now, I can only imagine doing this when the charset is us-ascii,
315         elif charset == 'us-ascii':
316             return self._split_ascii(s, charset, maxlinelen, splitchars)
322             first = charset.from_splittable(splittable[:splitpnt], False)
323             last = charset.from_splittable(splittable[splitpnt:], False)
326             first, last = _binsplit(splittable, charset, maxlinelen)
329         fsplittable = charset.to_splittable(first)
330         fencoded = charset.from_splittable(fsplittable, True)
331         chunk = [(fencoded, charset)]
332         return chunk + self._split(last, charset, self._maxlinelen, splitchars)
334     def _split_ascii(self, s, charset, firstlen, splitchars):  argument
337         return zip(chunks, [charset]*len(chunks))
342         # Given a list of pairs (string, charset), return a MIME-encoded
358         for header, charset in newchunks:
361             if charset is None or charset.header_encoding is None:
364                 s = charset.header_encode(header)
389         If the given charset is not known or an error occurs during
399         for s, charset in self._chunks:
404             if targetlen < charset.encoded_header_len(''):
407             newchunks += self._split(s, charset, targetlen, splitchars)
488 def _binsplit(splittable, charset, maxlinelen):  argument
501         chunk = charset.from_splittable(splittable[:m], True)
502         chunklen = charset.encoded_header_len(chunk)
512     first = charset.from_splittable(splittable[:i], False)
513     last  = charset.from_splittable(splittable[i:], False)