entity.py 文件源码

def __init__(self, entity_list):
        """
            [{"@id":"1","name":"??"},{"@id":"2","name":"??"}]
            all input text are assumed (or will be converted into) unicode
        """
        # init entity index
        self.entities = collections.defaultdict(list)
        entity_list_unicode = []
        for entity in entity_list:
            entity_list_unicode.append(any2unicode(entity))

        for entity in entity_list_unicode:
            name = entity["name"]
            self.entities[name].append(entity)

        for entity in entity_list_unicode:
            for name in entity.get("alternateName", []):
                self.entities[name].append(entity)

        stat(entity_list_unicode, ["name"])

        # init jieba
        self.tokenizer = jieba.Tokenizer()
        for name in self.entities:
            self.tokenizer.add_word(name)