/// <summary>
/// 获取分词之后的字符串集合
/// </summary>
/// <param name="objStr"></param>
/// <param name="type"></param>
/// <returns></returns>
public static IEnumerable <string> GetSplitWords(string objStr, JiebaTypeEnum type = JiebaTypeEnum.Default)
{
var jieba = new JiebaSegmenter();
switch (type)
{
case JiebaTypeEnum.Default:
return(jieba.Cut(objStr)); //精确模式-带HMM
case JiebaTypeEnum.CutAll:
return(jieba.Cut(objStr, cutAll: true)); //全模式
case JiebaTypeEnum.CutForSearch:
return(jieba.CutForSearch(objStr)); //搜索引擎模式
default:
return(jieba.Cut(objStr, false, false)); //精确模式-不带HMM
}
}
/// <summary>
/// 获取分词之后去重的集合
/// </summary>
/// <param name="objStr"></param>
/// <param name="type"></param>
/// <returns></returns>
public static IEnumerable <string> GetSplitWordList(this string objStr, JiebaTypeEnum type = JiebaTypeEnum.Default)
{
var words = GetSplitWords(objStr, type);
//没结果则返回空字符串
if (words == null || words.Count() < 1)
{
return(null);
}
for (int i = 0; i < words.Count(); i++)
{
if (words.ToArray()[i].Length < 2)
{
words = DeleteArr(i, words.ToArray());
}
}
words = words.Distinct();//去重
return(words);
}
/// <summary>
/// 获取分词之后的字符串
/// </summary>
/// <param name="objStr"></param>
/// <param name="type"></param>
/// <returns></returns>
public static string GetSplitWordStr(this string objStr, JiebaTypeEnum type = JiebaTypeEnum.Default)
{
var words = GetSplitWords(objStr, type);
//没结果则返回空字符串
if (words == null || words.Count() < 1)
{
return(string.Empty);
}
for (int i = 0; i < words.Count(); i++)
{
if (words.ToArray()[i].Length < 2)
{
words = DeleteArr(i, words.ToArray());
}
}
words = words.Distinct();//去重
return(string.Join(",", words));
}
/// <summary>
/// 获取分词之后的字符串
/// </summary>
/// <param name="objStr"></param>
/// <param name="type"></param>
/// <returns></returns>
public static string GetSplitWordStr(this string objStr, JiebaTypeEnum type = JiebaTypeEnum.Default)
{
var words = GetSplitWords(objStr, type);
return(JoinKeyWords(words));
}
