def _convertText(self, text): if not self._charset: # charset is still unknown: guess the charset self._charset = guessBytesCharset(text, default=FALLBACK_CHARSET) # Try to convert to Unicode try: return unicode(text, self._charset, "strict") except UnicodeDecodeError, err: pass
def _guessCharset(self): addr = self.absolute_address + self._content_offset * 8 bytes = self._parent.stream.readBytes(addr, self._content_size) return guessBytesCharset(bytes, default=FALLBACK_CHARSET)
def guessStreamCharset(stream, address, size, default=None): size = min(size, 1024*8) bytes = stream.readBytes(address, size//8) return guessBytesCharset(bytes, default)
def guessStreamCharset(stream, address, size, default=None): size = min(size, 1024 * 8) bytes = stream.readBytes(address, size // 8) return guessBytesCharset(bytes, default)