public static List <string> PanGuSplitWord(string msg)
{
Analyzer analyzer = new PanGuAnalyzer();
TokenStream tokenStream = analyzer.TokenStream("", new StringReader(msg));
ITermAttribute ita;
bool hasNext = true;
List <string> list = new List <string>();
while (hasNext)
{
ita = tokenStream.GetAttribute <ITermAttribute>();
list.Add(ita.Term);
hasNext = tokenStream.IncrementToken();
}
analyzer.Close();
return(list);
/*Token token;
* List<string> list = new List<string>();
* while ((token = tokenStream.) != null)
* {
* list.Add(token.TermText());
* }
* return list;*/
}
// main search method
private static IEnumerable <SearchData> _search(int pageIndex, int pageSize, out int totalCount, string searchQuery, string searchField = "")
{
// validation
if (string.IsNullOrEmpty(searchQuery.Replace("*", "").Replace("?", "")))
{
totalCount = 0;
return(new List <SearchData>());
}
// set up lucene searcher
using (var searcher = new IndexSearcher(_directory, false))
{
var hits_limit = 1000;
var analyzer = new PanGuAnalyzer(); //new StandardAnalyzer(Version.LUCENE_30);
// search by single field
if (!string.IsNullOrEmpty(searchField))
{
var parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, searchField, analyzer);
var query = parseQuery(searchQuery, parser);
var hits = searcher.Search(query, hits_limit).ScoreDocs;
totalCount = hits.Length;
var results = _mapLuceneToDataList(pageIndex, pageSize, hits, searcher);
analyzer.Close();
searcher.Dispose();
return(results);
}
// search by multiple fields (ordered by RELEVANCE)
else
{
var parser = new MultiFieldQueryParser
(Lucene.Net.Util.Version.LUCENE_30, new[] { "Id", "Name", "Url", "ImageUrl", "Description", "CreatedDate" }, analyzer);
var query = parseQuery(searchQuery, parser);
var hits = searcher.Search(query, null, hits_limit, Sort.INDEXORDER).ScoreDocs;
totalCount = hits.Length;
var results = _mapLuceneToDataList(pageIndex, pageSize, hits, searcher);
analyzer.Close();
searcher.Dispose();
return(results);
}
}
}
public static void Optimize()
{
var analyzer = new PanGuAnalyzer(); //new StandardAnalyzer(Version.LUCENE_30);
using (var writer = new IndexWriter(_directory, analyzer, IndexWriter.MaxFieldLength.UNLIMITED))
{
analyzer.Close();
writer.Optimize();
writer.Dispose();
}
}
public void CreateSearchIndex()
{
//路径判断
if (!System.IO.Directory.Exists(SearchIndexPath))
{
System.IO.Directory.CreateDirectory(SearchIndexPath);
}
Directory indexDirectory = FSDirectory.Open(new System.IO.DirectoryInfo(SearchIndexPath));
var analyzer = new PanGuAnalyzer();
IndexWriter writer = null;
try
{
//重新创建索引
bool isCreate = true;// !IndexReader.IndexExists(indexDirectory);
writer = new IndexWriter(indexDirectory, analyzer, isCreate, IndexWriter.MaxFieldLength.UNLIMITED);
//所有的上架已审核的商品
var goodses = _goodsQueryService.Goodses().Where(
g => g.IsPublished && g.Status == GoodsStatus.Verifyed);
//开始添加索引
foreach (var goods in goodses)
{
AddIndex(writer, goods);
}
writer.Optimize();
}
catch (Exception)
{
throw;
}
finally
{
if (analyzer != null)
{
analyzer.Close();
}
if (writer != null)
{
writer.Dispose();
}
if (indexDirectory != null)
{
indexDirectory.Dispose();
}
}
}
public static void ClearLuceneIndexRecord(string record_id)
{
// init lucene
var analyzer = new PanGuAnalyzer(); //new StandardAnalyzer(Version.LUCENE_30);
using (var writer = new IndexWriter(_directory, analyzer, IndexWriter.MaxFieldLength.UNLIMITED))
{
// remove older index entry
var searchQuery = new TermQuery(new Term("Id", record_id));
writer.DeleteDocuments(searchQuery);
// close handles
analyzer.Close();
writer.Dispose();
}
}
public static void AddUpdateLuceneIndex(IEnumerable <SearchData> sampleDatas)
{
// init lucene
var analyzer = new PanGuAnalyzer(); //new StandardAnalyzer(Version.LUCENE_30);
using (var writer = new IndexWriter(_directory, analyzer, IndexWriter.MaxFieldLength.UNLIMITED))
{
// add data to lucene search index (replaces older entries if any)
foreach (var sampleData in sampleDatas)
{
_addToLuceneIndex(sampleData, writer);
}
// close handles
analyzer.Close();
writer.Dispose();
}
}
/// <summary>
/// 生成LUCENE索引数据
/// </summary>
/// <param name="indexDocList">索引数据文档列表</param>
/// <param name="directoryPath">索引文件路径</param>
/// <param name="callback">回调方法</param>
public static void MakeIndex(List <Document> indexDocList, string directoryPath, Action <Document> callback)
{
try
{
PanGuAnalyzer analyzer = new PanGuAnalyzer(true);
string textIndexDir = directoryPath;
if (!System.IO.Directory.Exists(textIndexDir))
{
System.IO.Directory.CreateDirectory(textIndexDir);
}
Lucene.Net.Store.Directory indexDirectory = Lucene.Net.Store.FSDirectory.Open(new System.IO.DirectoryInfo(textIndexDir), new NativeFSLockFactory());
if (IndexReader.IndexExists(indexDirectory))
{
if (IndexWriter.IsLocked(indexDirectory))
{
IndexWriter.Unlock(indexDirectory);
}
}
IndexWriter indexWriter = new IndexWriter(indexDirectory, analyzer, true, Lucene.Net.Index.IndexWriter.MaxFieldLength.LIMITED);
if (indexDocList != null && indexDocList.Count > 0)
{
foreach (var item in indexDocList)
{
indexWriter.AddDocument(item, analyzer);
if (callback != null)
{
callback(item);
}
}
}
indexWriter.Optimize();
indexWriter.Close();
analyzer.Close();
}
catch (Exception ex)
{
LogHelper.Info(typeof(LuceneManager), ex.ToString());
}
}
public ActionResult Cut_2(string str)
{
//盘古分词
StringBuilder sb = new StringBuilder();
Analyzer analyzer = new PanGuAnalyzer();
TokenStream tokenStream = analyzer.TokenStream("", new StringReader(str));
ITermAttribute item = tokenStream.GetAttribute <ITermAttribute>();
while (tokenStream.IncrementToken())
{
sb.Append(item.Term + "|");
}
tokenStream.CloneAttributes();
analyzer.Close();
return(Content(sb.ToString()));
}
public static bool ClearLuceneIndex()
{
try
{
var analyzer = new PanGuAnalyzer(); //new StandardAnalyzer(Version.LUCENE_30);
using (var writer = new IndexWriter(_directory, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED))
{
// remove older index entries
writer.DeleteAll();
// close handles
analyzer.Close();
writer.Dispose();
}
}
catch (Exception)
{
return(false);
}
return(true);
}
//private static IndexSearcher searcher = new IndexSearcher(reader);
#region 分词测试
/// <summary>
/// 分词测试
/// </summary>
/// <param name="keyword"></param>
/// <returns></returns>
public static string Token(string keyword)
{
string ret = "";
System.IO.StringReader reader = new System.IO.StringReader(keyword);
PanGuAnalyzer analyzer = new PanGuAnalyzer();
Lucene.Net.Analysis.TokenStream ts = analyzer.TokenStream(keyword, reader);
bool hasNext = ts.IncrementToken();
Lucene.Net.Analysis.Tokenattributes.ITermAttribute ita;
while (hasNext)
{
ita = ts.GetAttribute <Lucene.Net.Analysis.Tokenattributes.ITermAttribute>();
ret += ita.Term + "|";
hasNext = ts.IncrementToken();
}
ts.CloneAttributes();
reader.Close();
analyzer.Close();
return(ret);
}
/// <summary>
/// 对keyword进行分词，将分词的结果返回
/// </summary>
public static IEnumerable <string> SplitWords(string keyword)
{
IList <string> list = new List <string>();
System.IO.StringReader reader = new System.IO.StringReader(keyword);
Analyzer analyzer = new PanGuAnalyzer();
TokenStream tokenStream = analyzer.TokenStream("", reader);
bool hasNext = tokenStream.IncrementToken();
Lucene.Net.Analysis.Tokenattributes.ITermAttribute ita;
while (hasNext)
{
//为当前分的词
ita = tokenStream.GetAttribute <Lucene.Net.Analysis.Tokenattributes.ITermAttribute>();
string word = ita.Term;
hasNext = tokenStream.IncrementToken();
list.Add(word);
}
tokenStream.CloneAttributes();
reader.Close();
analyzer.Close();
return(list);
}
/// <summary>
/// 重新生成所有院校索引
/// </summary>
/// <param name="itemCallback"></param>
public void MakeAllSchoolIndex(MakeSchoolItemIndexCallback itemCallback)
{
#region 海外大学
try
{
OverseaUniversityDao overseaUniversityDao = new OverseaUniversityDao();
List <OverseaUniversity> universityList = overseaUniversityDao.Backstage_GetAllUniversityList();
PanGuAnalyzer analyzer = new PanGuAnalyzer(true);
string textIndexDir = Utilities.GetLuceneTextIndexDirectoryPath(LuceneTextIndexType.AllSchool, null);
if (!System.IO.Directory.Exists(textIndexDir))
{
System.IO.Directory.CreateDirectory(textIndexDir);
}
Lucene.Net.Store.Directory indexDirectory = Lucene.Net.Store.FSDirectory.Open(new System.IO.DirectoryInfo(textIndexDir), new NativeFSLockFactory());
if (IndexReader.IndexExists(indexDirectory))
{
if (IndexWriter.IsLocked(indexDirectory))
{
IndexWriter.Unlock(indexDirectory);
}
}
IndexWriter indexWriter = new IndexWriter(indexDirectory, analyzer, false, Lucene.Net.Index.IndexWriter.MaxFieldLength.LIMITED);
foreach (OverseaUniversity university in universityList)
{
try
{
Document indexDoc = new Document();
#region 数据列
indexDoc.Add(new Field("Key", string.Concat("OverseaUniversity_", university.UniversityId), Field.Store.YES, Field.Index.ANALYZED));
indexDoc.Add(new NumericField("SchoolId", Field.Store.YES, true).SetIntValue(university.UniversityId));
indexDoc.Add(new NumericField("Type", Field.Store.YES, true).SetIntValue((int)SchoolType.OverseaUniversity));
indexDoc.Add(new Field("Name", university.Name, Field.Store.YES, Field.Index.ANALYZED));
indexDoc.Add(new Field("LC_Name", university.Name.ToLower(), Field.Store.NO, Field.Index.ANALYZED));
indexDoc.Add(new Field("CnName", university.CnName, Field.Store.YES, Field.Index.ANALYZED));
indexDoc.Add(new Field("LC_CnName", university.CnName.ToLower(), Field.Store.NO, Field.Index.ANALYZED));
indexDoc.Add(new Field("Pinyin", university.Pinyin, Field.Store.YES, Field.Index.ANALYZED));
indexDoc.Add(new Field("LC_Pinyin", university.Pinyin.ToLower(), Field.Store.NO, Field.Index.ANALYZED));
indexDoc.Add(new NumericField("RegionId", Field.Store.YES, true).SetIntValue(university.CountryId));
indexDoc.Add(new NumericField("StateId", Field.Store.YES, true).SetIntValue(university.StateId));
indexDoc.Add(new NumericField("CityId", Field.Store.YES, true).SetIntValue(university.CityId));
#endregion
indexWriter.AddDocument(indexDoc, analyzer);
if (itemCallback != null)
{
itemCallback(indexDoc);
}
}
catch (Exception ex)
{
LogHelper.WriteLog(ex);
}
}
indexWriter.Optimize();
indexWriter.Close();
analyzer.Close();
}
catch (Exception ex)
{
LogHelper.WriteLog(ex);
}
#endregion
}
/// <summary>
/// 提交内容
/// </summary>
/// <param name="id"></param>
/// <param name="title"></param>
/// <param name="content"></param>
/// <param name="date"></param>
/// <param name="param"></param>
/// <param name="modcode"></param>
/// <returns></returns>
public static string CommitContent(string id, string title, string content, DateTime?date, string param, string modcode, string searchparam1, string searchparam2, string searchparam3)
{
#region 验证输入参数是否合格
if (string.IsNullOrEmpty(id))
{
throw new Exception("参数id不能为空");
}
if (string.IsNullOrEmpty(title))
{
throw new Exception("参数title不能为空");
}
if (string.IsNullOrEmpty(content))
{
throw new Exception("参数content和filepathList不能同时为空");
}
#endregion
if (date == null)
{
date = DateTime.Now; //日期为null时使用当前时间
}
//Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29);
Analyzer analyzer = new PanGuAnalyzer();
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NativeFSLockFactory());
bool isUpdate = IndexReader.IndexExists(directory);
if (isUpdate)
{
//如果索引目录被锁定（比如索引过程中程序异常退出），则首先解锁
if (IndexWriter.IsLocked(directory))
{
IndexWriter.Unlock(directory);
}
}
IndexWriter writer = new IndexWriter(directory, analyzer, !isUpdate, IndexWriter.MaxFieldLength.UNLIMITED);
//为避免重复索引，所以先删除id=id的记录，再重新添加
writer.DeleteDocuments(new Term("id", id));
string result = "";
try
{
Document doc = new Document();
doc.Add(new Field("id", id, Field.Store.YES, Field.Index.NOT_ANALYZED)); //存储
doc.Add(new Field("title", title, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS)); //分词建立索引
doc.Add(new Field("content", content, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS)); //分词建立索引
doc.Add(new Field("date", date.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED)); //不分词建立索引
doc.Add(new Field("param", param, Field.Store.YES, Field.Index.NO)); //存储
doc.Add(new Field("modcode", modcode, Field.Store.YES, Field.Index.NOT_ANALYZED)); //存储
doc.Add(new Field("searchparam1", searchparam1, Field.Store.YES, Field.Index.NOT_ANALYZED)); //存储
doc.Add(new Field("searchparam2", searchparam2, Field.Store.YES, Field.Index.NOT_ANALYZED)); //存储
doc.Add(new Field("searchparam3", searchparam3, Field.Store.YES, Field.Index.NOT_ANALYZED)); //存储
writer.AddDocument(doc);
//输出api调用记录
string EnableApiLog = Util.GetAppSetting("EnableApiLog");
if (EnableApiLog == "1")
{
string logMsg = GetParamList(id, title, content, date, param, modcode) + "\r\n" + Utility.Util.GetClientInfo();
Utility.Util.WriteApiLog(logMsg);
}
}
catch (Exception ex)
{
result = ex.Message;
string errMsg = ex.Message + "\r\n" + GetParamList(id, title, content, date, param, modcode) + "\r\n" + Utility.Util.GetClientInfo();
Utility.Util.WriteLog(errMsg);
}
//对索引文件进行优化
//writer.Optimize();
analyzer.Close();
writer.Dispose();
directory.Dispose();
return(result);
}
/// <summary>
/// 搜索内容
/// </summary>
/// <param name="word">搜索关键字</param>
/// <param name="pagesize">每页显示记录数</param>
/// <param name="pageindex">当前页码</param>
/// <returns></returns>
public static SearchResult SearchContent(string modcode, string word, int pagesize, int pageindex, string searchparam1, string searchparam2, string searchparam3)
{
SearchResult searchResult = new SearchResult();
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NativeFSLockFactory());
IndexSearcher searcher = new IndexSearcher(directory, true);
var analyzer = new PanGuAnalyzer();
//初始化MultiFieldQueryParser以便同时查询多列
Lucene.Net.QueryParsers.MultiFieldQueryParser parser = new Lucene.Net.QueryParsers.MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_29, new string[] { "title", "content" }, analyzer);
Lucene.Net.Search.Query query = parser.Parse(word);//初始化Query
parser.DefaultOperator = QueryParser.AND_OPERATOR;
Lucene.Net.Search.BooleanQuery boolQuery = new Lucene.Net.Search.BooleanQuery();
boolQuery.Add(query, Occur.MUST);
if (!string.IsNullOrEmpty(modcode))
{
PhraseQuery queryModCode = new PhraseQuery();
queryModCode.Add(new Term("modcode", modcode));
boolQuery.Add(queryModCode, Occur.MUST);
}
if (!string.IsNullOrEmpty(searchparam1))
{
WildcardQuery query1 = new WildcardQuery(new Term("searchparam1", "*" + searchparam1 + "*"));
boolQuery.Add(query1, Occur.MUST);
}
if (!string.IsNullOrEmpty(searchparam2))
{
WildcardQuery query1 = new WildcardQuery(new Term("searchparam2", "*" + searchparam2 + "*"));
boolQuery.Add(query1, Occur.MUST);
}
if (!string.IsNullOrEmpty(searchparam3))
{
WildcardQuery query1 = new WildcardQuery(new Term("searchparam3", "*" + searchparam3 + "*"));
boolQuery.Add(query1, Occur.MUST);
}
Sort sort = new Sort(new SortField("date", SortField.STRING, true));
var result = searcher.Search(boolQuery, null, 1000, sort);
if (result.TotalHits == 0)
{
searchResult.count = 0;
}
else
{
searchResult.count = result.TotalHits;
int startNum = 0, endNum = result.TotalHits;
if (pagesize > 0)
{
//当pagesize>0时使用分页功能
startNum = (pageindex - 1) * pagesize;
endNum = startNum + pagesize;
}
ScoreDoc[] docs = result.ScoreDocs;
List <JObject> dataList = new List <JObject>();
for (int i = 0; i < docs.Length; i++)
{
if (i < startNum)
{
continue;
}
if (i >= endNum)
{
break;
}
Document doc = searcher.Doc(docs[i].Doc);
string id = doc.Get("id").ToString();
string title = doc.Get("title").ToString();
string content = doc.Get("content").ToString();
string date = doc.Get("date").ToString();
string param = doc.Get("param").ToString();
string mcode = doc.Get("modcode").ToString();
string param1 = doc.Get("searchparam1").ToString();
string param2 = doc.Get("searchparam2").ToString();
string param3 = doc.Get("searchparam3").ToString();
JObject obj = new JObject();
obj["id"] = id;
//创建HTMLFormatter,参数为高亮单词的前后缀
string highLightTag = Util.GetAppSetting("HighLightTag", "<font color=\"red\">|</font>");
string[] tarArr = highLightTag.Split('|');
var simpleHTMLFormatter = new SimpleHTMLFormatter(tarArr[0], tarArr[1]);
//创建 Highlighter ，输入HTMLFormatter 和 盘古分词对象Semgent
var highlighter = new Highlighter(simpleHTMLFormatter, new PanGu.Segment());
//设置每个摘要段的字符数
int highlightFragmentSize = Util.GetAppSetting("HighlightFragmentSize", "100").ToInt();
highlighter.FragmentSize = highlightFragmentSize;
//获取最匹配的摘要段
String bodyPreview = highlighter.GetBestFragment(word, content);
string newTitle = highlighter.GetBestFragment(word, title);
if (!string.IsNullOrEmpty(newTitle))
{
title = newTitle;
}
obj["title"] = title;
obj["content"] = bodyPreview;
obj["date"] = date;
obj["param"] = param;
obj["modcode"] = mcode;
obj["searchparam1"] = param1;
obj["searchparam2"] = param2;
obj["searchparam3"] = param3;
dataList.Add(obj);
}
searchResult.data = dataList;
}
analyzer.Close();
searcher.Dispose();
directory.Dispose();
return(searchResult);
}
/*
* 分词函数
* @srcdata:待分词的文本
* 返回值:按照学长格式定义的分词结果的string表示
* 即{<分词1>}{<分词2>}...{<分词n>}
*/
// 这个函数是核心
// 输入是待分词的内容
// 输出是分词结果
// 分词结果的格式是{<word>}
// 这个格式是学长定义的，我们为了不破坏既定的接口，沿用了这个格式
// 这个函数的工作原理主要是调用了Lucene.Net.Analysis和Lucene.China的接口
// 调用这两个接口的配置工作很简单：1.在引用中加入dll文件 2.在可执行程序的目录下放置一个data文件夹，文件夹内有两个文件，分别是sDict和sNoise
// 存放词库和噪声
/*private bool isChineseWord(string word)
* {
* if (word == null)
* {
* return false;
* }
* for (int i = 0; i < word.Length; i++)
* {
* char chr = word[i];
* if (!(chr >= 0x4E00 && chr <= 0x9FFF))
* {
* return false;
* }
* }
*
* return true;
* }*/
/*private string word_seg(string srcdata)
* {
* //StringBuilder sb = new StringBuilder();
* //sb.Remove(0, sb.Length);
* string t1 = "";
* ChineseAnalyzer analyzer = new Lucene.China.ChineseAnalyzer();
* //string FilePath = @"C:\Users\梁亦清\Documents\Visual Studio 2013\Projects\中科院分词简例\1.htm";
*
* StringReader sr = new StringReader(srcdata);
* //Console.WriteLine(sr.ToString());
* //Environment.Exit(0);
* TokenStream stream = analyzer.TokenStream("", sr);
*
* //long begin = System.DateTime.Now.Ticks;
* Lucene.Net.Analysis.Token t = stream.Next();
* while (t != null)
* {
* /*
* t1 = t.ToString(); //显示格式： (关键词,0,2) ，需要处理
* t1 = t1.Replace("(", "");
* char[] separator = { ',' };
* t1 = t1.Split(separator)[0];
* if (isChineseWord(t1))
* {
* sb.Append("{<" + t1 + ">}");
* }
* t = stream.Next();
* }
* //return sb.ToString()
* }*/
// 这个函数是学长代码的对外接口，我们沿用了这个接口，但使用的分词方法不是朴素贝叶斯
/*public string DoWordSegment(string strIn)
* {
* return word_seg(strIn);
*
* }*/
public List <string> cutwords(string words, string analyzer = "Lucene.China.ChineseAnalyzer")
{
List <string> results = new List <string>();
switch (analyzer)
{
case "Lucene.Net.Analysis.SimpleAnalyzer":
SimpleAnalyzer analyzerInstance0 = new SimpleAnalyzer();
TokenStream ts0 = analyzerInstance0.ReusableTokenStream("", new StringReader(words));
Lucene.Net.Analysis.Token token0;
while ((token0 = ts0.Next()) != null)
{
results.Add(token0.TermText());
}
ts0.Close();
analyzerInstance0.Close();
break;
case "Lucene.Net.Analysis.KeywordAnalyzer":
KeywordAnalyzer analyzerInstance1 = new KeywordAnalyzer();
TokenStream ts1 = analyzerInstance1.ReusableTokenStream("", new StringReader(words));
Lucene.Net.Analysis.Token token1;
while ((token1 = ts1.Next()) != null)
{
results.Add(token1.TermText());
}
ts1.Close();
analyzerInstance1.Close();
break;
case "Lucene.Net.Analysis.StopAnalyzer":
StopAnalyzer analyzerInstance2 = new StopAnalyzer();
TokenStream ts2 = analyzerInstance2.ReusableTokenStream("", new StringReader(words));
Lucene.Net.Analysis.Token token2;
while ((token2 = ts2.Next()) != null)
{
results.Add(token2.TermText());
}
ts2.Close();
analyzerInstance2.Close();
break;
case "Lucene.Net.Analysis.WhitespaceAnalyzer":
WhitespaceAnalyzer analyzerInstance3 = new WhitespaceAnalyzer();
TokenStream ts3 = analyzerInstance3.ReusableTokenStream("", new StringReader(words));
Lucene.Net.Analysis.Token token3;
while ((token3 = ts3.Next()) != null)
{
results.Add(token3.TermText());
}
ts3.Close();
analyzerInstance3.Close();
break;
case "Lucene.Net.Analysis.PanGu.PanGuAnalyzer":
PanGu.Segment.Init(@"G:\CProjects\Pipeline\pipeline\Pipeline\bin\Release\PanGu.xml");
PanGuAnalyzer analyzerInstance4 = new PanGuAnalyzer();
TokenStream ts4 = analyzerInstance4.TokenStream("", new StringReader(words));
Lucene.Net.Analysis.Token token4;
while ((token4 = ts4.Next()) != null)
{
results.Add(token4.TermText());
}
ts4.Close();
analyzerInstance4.Close();
break;
case "Lucene.Net.Analysis.Standard.StandardAnalyzer":
StandardAnalyzer analyzerInstance5 = new StandardAnalyzer();
TokenStream ts5 = analyzerInstance5.ReusableTokenStream("", new StringReader(words));
Lucene.Net.Analysis.Token token5;
while ((token5 = ts5.Next()) != null)
{
results.Add(token5.TermText());
}
ts5.Close();
analyzerInstance5.Close();
break;
case "Lucene.China.ChineseAnalyzer":
default:
ChineseAnalyzer analyzerInstance6 = new ChineseAnalyzer();
TokenStream ts6 = analyzerInstance6.ReusableTokenStream("", new StringReader(words));
Lucene.Net.Analysis.Token token6;
while ((token6 = ts6.Next()) != null)
{
results.Add(token6.TermText());
}
ts6.Close();
analyzerInstance6.Close();
break;
}
return(results);
}