面试系列-分组Tire树匹配算法

自己写的分组Tire树匹配算法，该算法用于云南省人工智能重点实验室与云南电网合作项目（云南电网敏感信息识别系统），用于快速匹配文本将项目中数据算法抽离出来，特此分享！！!
可以实现动态的插入、删除操作

# 自己写的组Tire树筛选算法
# 该算法用于本实验室和云南电网敏感信息项目，用于快速匹配文本
# 将项目中数据算法抽离出来，特此分享class TireNode:def __init__(self):self.children = {}  # 字典类型，类似与JAVA中的mapself.group_ids = set()  # 初始化组ID为-1，表示未分配# Tire树
class Tire:def __init__(self):self.root = TireNode()# 插入def insert(self, word, group_id):node = self.rootfor char in word:if char not in node.children:node.children[char] = TireNode()node = node.children[char]if group_id  not in node.group_ids:node.group_ids.add(group_id)  # 标记单词所属的组IDreturn Trueelse:return False  # 代表当前Tire树中已经存在# 搜索def search(self, word):node = self.rootfor char in word:if char not in node.children:return None, wordnode = node.children[char]if len(node.group_ids) != 0:  # 如果group_ids不为空，说明已经到达结尾return node.group_ids,wordreturn None, word# 删除def delete(self, group_id, word):node = self.rootfor char in word:if char not in node.children:return False  # 删除失败node = node.children[char]if group_id not in node.group_ids:return Falseelse:node.group_ids.remove(group_id) # 移除集合中的group_idreturn True# 基于TireTree算法的组关键词筛选
class KeyWords(object):def __init__(self):# 创建Tire树self.tire = Tire()# 记录每个group_id 所对应的关键词个数self.tire_group_ids = {}# 从数据库获取数据self.gjc_lists = [["电网信息", "电网"], []]# 将关键词插入Tire树，并记录每个组的关键词数量for group_id, keywords in enumerate(self.gjc_lists):for keyword in keywords:# 向Tire树中插入success = self.tire.insert(keyword, group_id)if success:   # 如果插入成功才进行更新if group_id not in self.tire_group_ids:self.tire_group_ids[group_id] = 1else:self.tire_group_ids[group_id] += self.tire_group_ids[group_id]print()# 文本匹配，必须匹配上某个组中所有关键词才算是匹配上def match(self, text):# 遍历文本，检查关键词group_dict = {}for i in range(len(text)):for j in range(i + 1, len(text) + 1):group_ids, group_word = self.tire.search(text[i:j])if group_ids is not None:# 如果存在，可能有多个，因为不同组可能具有相同的关键词for group_id in group_ids:if group_id not in group_dict:  # 将查到的group_ids都记录下来group_dict[group_id] = 1else:group_dict[group_id] += 1# 如果发现某个组个数已经匹配上，则匹配成功if group_dict[group_id] == self.tire_group_ids[group_id]:return True# 如果都没有匹配上，说明没有匹配成功return False# 传入一个组以及word 来实现删除def delete(self, group_id, word):success = self.tire.delete(group_id, word)if success: # 如果删除成功，更新tire_group_idsif group_id in self.tire_group_ids:self.tire_group_ids[group_id] -= 1return successdef insert(self, group_id, word):success = self.tire.insert(word, group_id)if success:if group_id not in self.tire_group_ids:self.tire_group_ids[group_id] = 1else:self.tire_group_ids[group_id] += 1