针对盘古dll重写词库读取及新词增删改查方法

最新推荐文章于 2023-11-27 23:05:51 发布

FeelUps

最新推荐文章于 2023-11-27 23:05:51 发布

阅读量1.7k

点赞数

CC 4.0 BY-SA版权

分类专栏： B Code

本文链接：https://blog.youkuaiyun.com/feelig/article/details/8234049

B Code 专栏收录该内容

89 篇文章

订阅专栏

本文详细介绍了如何针对盘古DLL进行词库读取的重写，以及新词的增删改查方法。重点参考了PosDisplayCtrl类库中PosCtrl.cs的GetChsPos方法。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#region +对盘古词库执行增删改查 InsertPanGuDict | DeleteWord | UpdateWord | UpdateWord
        /// <summary>
        /// 盘古词库增加新词
        /// </summary>
        /// <param name="name"></param>
        /// <param name="_posStr"></param>
        /// <param name="frequency"></param>
        public static void InsertPanGuDict(string word, double frequency, string _posStr)
        {
            POS _pos = DisplayPos.GetChsPos(_posStr);
            WordDictionary wd = new WordDictionary();
            wd.Load(Dictpath);
            wd.InsertWord(word, frequency, _pos);
            wd.Save(Dictpath);
        }

        /// <summary>
        /// 盘古词库删除指定词汇
        /// </summary>
        /// <param name="word"></param>
        public static void DeleteWord(string word)
        {
            WordDictionary wd = new WordDictionary();
            wd.Load(Dictpath);
            wd.DeleteWord(word);
            wd.Save(Dictpath);
        }

        /// <summary>
        /// 盘古词库修改指定词汇
        /// </summary>
        /// <param name="word"></param>
        /// <param name="frequency"></param>
        /// <param name="_posStr"></param>
        public static void UpdateWord(string word, double frequency, string _posStr)
        {
            POS _pos = DisplayPos.GetChsPos(_posStr);
            WordDictionary wd = new WordDictionary();
            wd.Load(Dictpath);
            wd.UpdateWord(word, frequency, _pos);
            wd.Save(Dictpath);
        }

        public static List<string> SearchWord(string word)
        {
            List<string> wordList = new List<string>();
            WordDictionary wd = new WordDictionary();
            wd.Load(Dictpath);
            List<SearchWordResult> result = wd.Search(word.Trim());
            result.Sort();
            foreach (SearchWordResult w in result)
            {
                wordList.Add(w.ToString());
            }
            return wordList;
        }

        #endregion

POS 参数请参照盘古分词代码中的PosDisplayCtrl类库下面的PosCtrl.cs GetChsPos方法，下文也会贴出

public static string GetChsPosStr(POS pos)
        {
            switch (pos)
            {
                case POS.POS_UNK:
                    return "未知词性";

                case POS.POS_D_K:
                    return "后接成分";

                case POS.POS_D_H:
                    return "前接成分";

                case POS.POS_A_NZ:
                    return "其他专名";

                case POS.POS_A_NX:
                    return "外文字符";

                case POS.POS_A_NR:
                    return "人名";

                case POS.POS_D_Z:
                    return "状态词";

                case POS.POS_A_NT:
                    return "机构团体";

                case POS.POS_A_NS:
                    return "地名";

                case POS.POS_D_Y:
                    return "语气词 语气语素";

                case POS.POS_D_X:
                    return "非语素字";

                case POS.POS_D_W:
                    return "标点符号";

                case POS.POS_D_T:
                    return "时间词";

                case POS.POS_D_S:
                    return "处所词";

                case POS.POS_D_V:
                    return "动词 动语素";

                case POS.POS_D_U:
                    return "助词 助语素";

                case POS.POS_D_R:
                    return "代词 代语素";

                case POS.POS_A_Q:
                    return "量词 量语素";

                case POS.POS_D_P:
                    return "介词";

                case POS.POS_D_MQ:
                    return "数量词";

                case POS.POS_A_M:
                    return "数词 数语素";

                case POS.POS_D_O:
                    return "拟声词";

                case POS.POS_D_N:
                    return "名词 名语素";

                case POS.POS_D_F:
                    return "方位词 方位语素";

                case POS.POS_D_E:
                    return "叹词 叹语素";

                case POS.POS_D_L:
                    return "习语";

                case POS.POS_D_I:
                    return "成语";

                case POS.POS_D_D:
                    return "副词 副语素";

                case POS.POS_D_C:
                    return "连词 连语素";

                case POS.POS_D_B:
                    return "区别词 区别语素";

                case POS.POS_D_A:
                    return "形容词 形语素";
            }
            return "未知词性";

        }