20 from email import charset as _charset
21 Charset = _charset.Charset  variable
31 USASCII = Charset('us-ascii')
32 UTF8 = Charset('utf-8')
34 # Match encoded-word strings in the form =?charset?q?Hello_World?=
37   (?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 (string, charset) pairs containing each of the decoded
65     parts of the header.  Charset is None for non-encoded parts of the header,
77         return [(_charset._encode(string, str(charset)), str(charset))
78                     for string, charset in header._chunks]
79     # If no encoding, just return the header with no charset.
83     # (encoded_string, encoding, charset).  For unencoded strings, the last
97                 charset = parts.pop(0).lower()
100                 words.append((encoded, encoding, charset))
112     # form (decoded_word, charset).
114     for encoded_string, encoding, charset in words:
117             decoded_words.append((encoded_string, charset))
120             decoded_words.append((word, charset))
130                 decoded_words.append((word, charset))
137     for word, charset in decoded_words:
142             last_charset = charset
143         elif charset != last_charset:
146             last_charset = charset
161     pairs of the format (decoded_string, charset) where charset is the string
170     for s, charset in decoded_seq:
172         if charset is not None and not isinstance(charset, Charset):
173             charset = Charset(charset)
174         h.append(s, charset)
180     def __init__(self, s=None, charset=None,  argument
190         Optional charset serves two purposes: it has the same meaning as the
191         charset argument to the .append() method.  It also sets the default
192         character set for all subsequent .append() calls that omit the charset
193         argument.  If charset is not provided in the constructor, the us-ascii
194         charset is used both as s's initial charset and as the default for
209         if charset is None:
210             charset = USASCII
211         elif not isinstance(charset, Charset):
212             charset = Charset(charset)
213         self._charset = charset
217             self.append(s, charset, errors)
233         for string, charset in self._chunks:
236             # from a charset to None/us-ascii, or from None/us-ascii to a
237             # charset.  Only do this for the second and subsequent chunks.
240             nextcs = charset
265     def append(self, s, charset=None, errors='strict'):  argument
268         Optional charset, if given, should be a Charset instance or the name
269         of a character set (which will be converted to a Charset instance).  A
270         value of None (the default) means that the charset given in the
274         (i.e. isinstance(s, str) is false), then charset is the encoding of
276         cannot be decoded with that charset.  If s is a Unicode string, then
277         charset is a hint specifying the character set of the characters in
280         output codec of the charset.  If the string cannot be encoded to the
286         if charset is None:
287             charset = self._charset
288         elif not isinstance(charset, Charset):
289             charset = Charset(charset)
291             input_charset = charset.input_codec or 'us-ascii'
298         output_charset = charset.output_codec or 'us-ascii'
305                 charset = UTF8
306         self._chunks.append((s, charset))
358         for string, charset in self._chunks:
362                     if not hasspace or charset not in (None, 'us-ascii'):
364                 elif charset not in (None, 'us-ascii') and not lastspace:
367             lastcs = charset
371                 formatter.feed('', lines[0], charset)
373                 formatter.feed('', '', charset)
376                 if charset.header_encoding is not None:
378                                    charset)
382                     formatter.feed(fws, sline, charset)
399         for string, charset in self._chunks:
400             if charset == last_charset:
406                 last_charset = charset
443     def feed(self, fws, string, charset):  argument
444         # If the charset has no header encoding (i.e. it is an ASCII encoding)
449         if charset.header_encoding is None:
459         encoded_lines = charset.header_encode_lines(string, self._maxlengths())