if header_name is None: self._headerlen = 0 else: # Take the separating colon and space into account. self._headerlen = len(header_name) + 2 def __str__(self): """Return the string value of the header.""" self._normalize() uchunks = [] lastcs = None lastspace = None for string, charset in self._chunks: # We must preserve spaces between encoded and non-encoded word # boundaries, which means for us we need to add a space when we go # from a charset to None/us-ascii, or from None/us-ascii to a # charset. Only do this for the second and subsequent chunks. # Don't add a space if the None/us-ascii string already has # a space (trailing or leading depending on transition) nextcs = charset if nextcs == _charset.UNKNOWN8BIT: original_bytes = string.encode('ascii', 'surrogateescape') string = original_bytes.decode('ascii', 'replace') if uchunks: hasspace = string and self._nonctext(string[0]) if lastcs not in (None, 'us-ascii'): if nextcs in (None, 'us-ascii') and not hasspace: uchunks.append(SPACE) nextcs = None elif nextcs not in (None, 'us-ascii') and not lastspace: uchunks.append(SPACE) lastspace = string and self._nonctext(string[-1]) lastcs = nextcs uchunks.append(string) return EMPTYSTRING.join(uchunks) # Rich comparison operators for equality only. BAW: does it make sense to # have or explicitly disable <, <=, >, >= operators? def __eq__(self, other): # other may be a Header or a string. Both are fine so coerce # ourselves to a unicode (of the unencoded header value), swap the # args and do another comparison. return other == str(self) def append(self, s, charset=None, errors='strict'): """Append a string to the MIME header. Optional charset, if given, should be a Charset instance or the name of a character set (which will be converted to a Charset instance). A value of None (the default) means that the charset given in the constructor is used. s may be a byte string or a Unicode string. If it is a byte string (i.e. isinstance(s, str) is false), then charset is the encoding of that byte string, and a UnicodeError will be raised if the string cannot be decoded with that charset. If s is a Unicode string, then charset is a hint specifying the character set of the characters in the string. In either case, when producing an RFC 2822 compliant header using RFC 2047 rules, the string will be encoded using the output codec of the charset. If the string cannot be encoded to the output codec, a UnicodeError will be raised. Optional `errors' is passed as the errors argument to the decode call if s is a byte string. """ if charset is None: charset = self._charset elif not isinstance(charset, Charset): charset = Charset(charset) if not isinstance(s, str): input_charset = charset.input_codec or 'us-ascii' if input_charset == _charset.UNKNOWN8BIT: s = s.decode('us-ascii', 'surrogateescape') else: s = s.decode(input_charset, errors) # Ensure that the bytes we're storing can be decoded to the output # character set, otherwise an early error is raised. output_charset = charset.output_codec or 'us-ascii' if output_charset != _charset.UNKNOWN8BIT: try: s.encode(output_charset, errors) except UnicodeEncodeError: if output_charset!='us-ascii': raise charset = UTF8 self._chunks.append((s, charset)) def _nonctext(self, s): """True if string s is not a ctext character of RFC822. """ return s.isspace() or s in ('(', ')', '\\') def encode(self, splitchars=';, \t', maxlinelen=None, linesep='\n'): r"""Encode a message header into an RFC-compliant format. There are many issues involved in converting a given string for use in an email header. Only certain character sets are readable in most email clients, and as header strings can only contain a subset of 7-bit ASCII, care must be taken to properly convert and encode (with Base64 or quoted-printable) header strings. In addition, there is a 75-character length limit on any given encoded header field, so line-wrapping must be performed, even with double-byte character sets. Optional maxlinelen specifies the maximum length of each generated line, exclusive of the linesep string. Individual lines may be longer than maxlinelen if a folding point cannot be found. The first line will be shorter by the length of the header name plus ": " if a header name was specified at Header construction time. The default value for maxlinelen is determined at header construction time. Optional splitchars is a string containing characters which should be given extra weight by the splitting algorithm during normal header wrapping. This is in very rough support of RFC 2822's `higher level syntactic breaks': split points preceded by a splitchar are preferred during line splitting, with the characters preferred in the order in which they appear in the string. Space and tab may be included in the string to indicate whether preference should be given to one over the other as a split point when other split chars do not appear in the line being split. Splitchars does not affect RFC 2047 encoded lines. Optional linesep is a string to be used to separate the lines of the value. The default value is the most useful for typical Python applications, but it can be set to \r\n to produce RFC-compliant line separators when needed. """ self._normalize() if maxlinelen is None: maxlinelen = self._maxlinelen # A maxlinelen of 0 means don't wrap. For all practical purposes, # choosing a huge number here accomplishes that and makes the # _ValueFormatter algorithm much simpler. if maxlinelen == 0: maxlinelen = 1000000 formatter = _ValueFormatter(self._headerlen, maxlinelen, self._continuation_ws, splitchars) lastcs = None hasspace = lastspace = None for string, charset in self._chunks: if hasspace is not None: hasspace = string and self._nonctext(string[0]) if lastcs not in (None, 'us-ascii'): if not hasspace or charset not in (None, 'us-ascii'): formatter.add_transition() elif charset not in (None, 'us-ascii') and not lastspace: formatter.add_transition() lastspace = string and self._nonctext(string[-1]) lastcs = charset hasspace = False lines = string.splitlines() if lines: formatter.feed('', lines[0], charset) else: formatter.feed('', '', charset) for line in lines[1:]: formatter.newline() if charset.header_encoding is not None: formatter.feed(self._continuation_ws, ' ' + line.lstrip(), charset) else: sline = line.lstrip() fws = line[:len(line)-len(sline)] formatter.feed(fws, sline, charset) if len(lines) > 1: formatter.newline() if self._chunks: formatter.add_transition() value = formatter._str(linesep) if _embedded_header.search(value): raise HeaderParseError("header value appears to contain " "an embedded header: {!r}".format(value)) return value def _normalize(self): # Step 1: Normalize the chunks so that all runs of identical charsets # get collapsed into a single unicode string. chunks = [] last_charset = None last_chunk = [] for string, charset in self._chunks: if charset == last_charset: last_chunk.append(string) else: if last_charset is not None: chunks.append((SPACE.join(last_chunk), last_charset)) last_chunk = [string] last_charset = charset if last_chunk: chunks.append((SPACE.join(last_chunk), last_charset)) self._chunks = chunks