class ETLDisFromRawAfterCheck(ETLDisFromRaw): ''' 检查解析表和量化表数据一致性, 这个是粗略处理: 解析表中有的,如果量化表没有,重新解析量化 ''' def __init__(self, channel, q): ETLDisFromRaw.__init__(self, channel, q) self.cv_measure_store = CVRawStore(channel, 'measure') def real_dispatcher(self, from_which): index = 0 for item in self.cv_raw_store.get_all(): index += 1 if not self.cv_measure_store.find_one({'cvId':item['cvId']}): self.queue.put(item) if index % 10000 == 0: print "copied %d items" % index