translation_counter.py 文件源码

def print(self, f, format='counts'):
        for key, counts in self.count_dict.items():
            if (self.source_tf[key] >= self.source_tf_filter) and \
                    (self.source_df[key] / float(self.count_docs) <= self.source_df_filter):
                candidates = [(v, c) for v, c in counts.items() if not self._filtered_trans(v)]
                candidates = sorted(candidates, key=itemgetter(1), reverse=True)
            elif len(self.source_tf) == 0:
                # no tf/df counts - dictionary read from file
                candidates = sorted(counts.items(), key=itemgetter(1), reverse=True)
            else:
                continue

            if self.top_n:
                candidates = candidates[:self.top_n]

            if candidates:
                if format == 'counts':
                    f.write(u'%s\t%s\n' % (key, ' '.join([self._format(v, c) for v, c in candidates])))
                elif format == 'solr':
                    f.write(u'%s => %s\n' % (key, candidates[0][0]))