itb_emoji.py 文件源码

def _load_unicode_emoji_data(self):
        '''
        Loads emoji property data from emoji-data.txt

        http://unicode.org/Public/emoji/5.0/emoji-data.txt
        '''
        dirnames = (USER_DATADIR, DATADIR)
        basenames = ('emoji-data.txt',)
        (path, open_function) = _find_path_and_open_function(
            dirnames, basenames)
        if not path:
            sys.stderr.write(
                '_load_unicode_emoji_data(): could not find "%s" in "%s"\n'
                %(basenames, dirnames))
            return
        with open_function(path, mode='rt') as unicode_emoji_data_file:
            for line in unicode_emoji_data_file.readlines():
                unicode_version = ''
                pattern = re.compile(
                    r'[^;]*;[^;]*#\s*(?P<uversion>[0-9]+\.[0-9]+)\s*'
                    + r'\[[0-9]+\]')
                match  = pattern.match(line)
                if match and match.group('uversion'):
                    unicode_version = match.group('uversion')
                line = re.sub(r'#.*$', '', line).strip()
                if not line:
                    continue
                codepoint_string, property = [
                    x.strip() for x in line.split(';')[:2]]
                codepoint_range = [
                    int(x, 16) for x in codepoint_string.split('..')]
                if len(codepoint_range) == 1:
                    codepoint_range.append(codepoint_range[0])
                assert len(codepoint_range) == 2
                for codepoint in range(
                        codepoint_range[0], codepoint_range[1] + 1):
                    emoji_string = chr(codepoint)
                    self._add_to_emoji_dict(
                        (emoji_string, 'en'), 'properties', [property])
                    if unicode_version:
                        self._add_to_emoji_dict(
                            (emoji_string, 'en'), 'uversion', unicode_version)