基于ASP.NET的lucene.net全文搜索实现步骤

 
//提取txt文件
public static string FileReaderAll(FileInfo fileName)
{
//读取文本内容，并且默认编码格式，防止出现乱码
StreamReader reader = new StreamReader(fileName.FullName, System.Text.Encoding.Default);
string line = "";
string temp = "";
//循环读取文本内容
while ((line = reader.ReadLine()) != null)
{
temp += line;
}
reader.Close();
//返回字符串，用于lucene.net生成索引
return temp;
}

 
protected void Button2_Click(object sender, EventArgs e)
{
//判断存放文本的文件夹是否存在
if (!System.IO.Directory.Exists(filesDirectory))
{
Response.Write("<script>alert('指定的目录不存在');</script>");
return;
}
//读取文件夹内容
DirectoryInfo dirInfo = new DirectoryInfo(filesDirectory);
FileInfo[] files = dirInfo.GetFiles("*.*");
//文件夹判空
if (files.Count() == 0)
{
Response.Write("<script>alert('Files目录下没有文件');</script>");
return;
}
//判断存放索引的文件夹是否存在，不存在创建
if (!System.IO.Directory.Exists(indexDirectory))
{
System.IO.Directory.CreateDirectory(indexDirectory);
}
//创建索引
IndexWriter writer = new IndexWriter(FSDirectory.Open(new DirectoryInfo(indexDirectory)),
analyzer, true, IndexWriter.MaxFieldLength.LIMITED);

for (int i = 0; i < files.Count(); i++)
{
string str = "";
FileInfo fileInfo = files[i];
//判断文件格式，为以后其他文件格式做准备
if (fileInfo.FullName.EndsWith(".txt") || fileInfo.FullName.EndsWith(".xml"))
{
//获取文本
str = FileReaderAll(fileInfo);
}
Lucene.Net.Documents.Document doc = new Lucene.Net.Documents.Document();
doc.Add(new Lucene.Net.Documents.Field("FileName", fileInfo.Name, Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.ANALYZED));
//根据文本生成索引
doc.Add(new Lucene.Net.Documents.Field("Content", str, Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.ANALYZED));
doc.Add(new Lucene.Net.Documents.Field("Path", fileInfo.FullName, Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.NO));
//添加生成的索引
writer.AddDocument(doc);
writer.Optimize();
}
writer.Dispose();
Response.Write("<script>alert('索引创建成功');</script>");
}

 
protected void Button1_Click(object sender, EventArgs e)
{
//获取关键字
string keyword = TextBox1.Text.Trim();
int num = 10;
//关键字判空
if (string.IsNullOrEmpty(keyword))
{
Response.Write("<script>alert('请输入要查找的关键字');</script>");
return;
}

IndexReader reader = null;
IndexSearcher searcher = null;
try
{
reader = IndexReader.Open(FSDirectory.Open(new DirectoryInfo(indexDirectory)), true);
searcher = new IndexSearcher(reader);
//创建查询
PerFieldAnalyzerWrapper wrapper = new PerFieldAnalyzerWrapper(analyzer);
wrapper.AddAnalyzer("FileName", analyzer);
wrapper.AddAnalyzer("Path", analyzer);
wrapper.AddAnalyzer("Content", analyzer);
string[] fields = { "FileName", "Path", "Content" };

QueryParser parser = new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_30, fields, wrapper);
//根据关键字查询
Query query = parser.Parse(keyword);

TopScoreDocCollector collector = TopScoreDocCollector.Create(num, true);

searcher.Search(query, collector);
//这里会根据权重排名查询顺序
var hits = collector.TopDocs().ScoreDocs;

int numTotalHits = collector.TotalHits;

//以后就可以对获取到的collector数据进行操作
for (int i = 0; i < hits.Count(); i++)
{
var hit = hits[i];
Lucene.Net.Documents.Document doc = searcher.Doc(hit.Doc);
Lucene.Net.Documents.Field fileNameField = doc.GetField("FileName");
Lucene.Net.Documents.Field pathField = doc.GetField("Path");
Lucene.Net.Documents.Field contentField = doc.GetField("Content");
//在页面循环输出表格
strTable.Append("<tr>");
strTable.Append("<td>" + fileNameField.StringValue + "</td>");
strTable.Append("</tr>");
strTable.Append("<tr>");
strTable.Append("<td>" + pathField.StringValue + "</td>");
strTable.Append("</tr>");
strTable.Append("<tr>");
strTable.Append("<td>" + contentField.StringValue.Substring(0, 300) + "</td>");
strTable.Append("</tr>");
}
}
finally
{
if (searcher != null)
searcher.Dispose();

if (reader != null)
reader.Dispose();
}
}