maybe a better `prepare_query`

[lilydjwg]

对中文查询字符串分词用的。

import re

def intersperse(delimiter, iterable):
    it = iter(iterable)
    yield next(it)
    for x in it:
        yield delimiter
        yield x

def prepare_query(self, qs):
    if isinstance(qs, str):
        qs = qs.decode('utf-8')
    items = re.split(r'(\W+)', qs, flags=re.UNICODE)

    ret = []
    for i, item in enumerate(items):
        logger.debug('processing %d: %s', i, item)
        if i % 2 == 0: # word
            ws = [w.decode('utf-8') for w in _scws(item.encode('utf-8'))]
            if len(ws) > 1:
                logger.debug('word segmenting result: %r', ws)
                ret.append(u'(')
                ret.extend(intersperse(' ', ws))
                ret.append(u')')
                continue
        ret.append(item)

    return ''.join(ret)