Lucene搜索代码示例

 

 

    //创建分析器
            StandardAnalyzer standardAnalyzer = new StandardAnalyzer();
            // 创建一个IndexWriter
            //IndexWriter(生产索引文件的目录；索引分析器；是否覆盖原有索引的文件，如果是true，在建立索引之前先将目录清空)
            IndexWriter writer = new IndexWriter(@"E:/Winform/LuceneDemo/Index/", standardAnalyzer, true);

            using (StreamReader sr = new StreamReader(@"E:/Winform/LuceneDemo/Index.txt", Encoding.GetEncoding("GBK")))
            {
                String line;
                while ((line = sr.ReadLine()) != null)
                {
                    Document doc = new Document();
                    doc.Add(new Field("title", line, Field.Store.YES, Field.Index.TOKENIZED));
                    doc.Add(new Field("time", DateTools.TimeToString(DateTime.Now.Ticks, DateTools.Resolution.MILLISECOND), Field.Store.YES, Field.Index.UN_TOKENIZED));
                    writer.AddDocument(doc);
                    Thread.Sleep(1000);
                }
            }

            //优化索引
            writer.Optimize();
            //关闭输入索引，这一步非常的重要只有调用这个方法索引才会被写入索引的目录里
            writer.Close();

            MessageBox.Show("索引创建成功！！");

 

 

      // 搜索查询

       if (txtKW.Text.Trim() == "")
            {
                MessageBox.Show("关键词不能为空！！");
                return;
            }

            StandardAnalyzer standarAnalyzer = new StandardAnalyzer();
            Query query = new QueryParser("title", standarAnalyzer).Parse(txtKW.Text.Trim());

            IndexSearcher searcher = new IndexSearcher(@"E:/Winform/LuceneDemo/Index/");
            Sort sort = new Sort(new SortField[] { new SortField("time", SortField.STRING, true) });

            Hits hits = searcher.Search(query, sort);

            DataTable dt = new DataTable();
            dt.Columns.Add("title");
            for (int i = 0; i < hits.Length(); i++)
            {
                Document doc = new Document();
                doc = hits.Doc(i);
                DataRow dr = dt.NewRow();
                dr["Title"] = doc.Get("title");
                dt.Rows.Add(dr);
            }

            lblTotal.ForeColor = Color.Red;
            lblTotal.Text = string.Format("共有记录：{0}条", hits.Length());
            gvResult.DataSource = dt;

 

      

 

    

lucene 的搜索相当强大，它提供了很多辅助查询类，每个类都继承自Query类，各自完成一种特殊的查询，你可以像搭积木一样将它们任意组合使用，完成一些复杂操作；
lucene还提供了Sort类对结果进行排序，提供了Filter类对查询条件进行限制。你或许会不自觉地拿它跟SQL语句进行比较： “lucene能执行and、or、order by、where、like ‘%xx%’操作吗？”回答是：“当然没问题！”

 

IndexSearcher:是lucene中最基本的检索工具.

Query:查询，lucene中支持模糊查询，短语查询，组合查询等等

QueryParser: 是一个解析用户输入的工具，可以通过扫描用户输入的字符串，生成Query对象。

 

Hits:在搜索完成之后，需要把搜索结果返回并显示给用户。在lucene中，搜索的结果的集合是用Hits类的实例来表示的。Hits对象中主要方法有：
    length(): 返回搜索结果的总数,下面简单的用法中有用到Hit的这一个方法
 doc(int n): 返回第n个文档
 iterator(): 返回一个迭代器

 

各种各样的Query

TermQuery
Term t = new Term("content", " lucene";
Query query = new TermQuery(t);
BooleanQuery
BooleanQuery boolQuery = new BooleanQuery();
boolQuery.add(termQuery1, booleanClause.Occur.SHOULD);
boolQuery.add(termQuery2, booleanClause.Occur.SHOULD);
RangeQuery
RangeQuery query = new RangeQuery(new Term(“time”, “20060101”), new Term(“time”, “20060130”), true);

QueryParser

TermQuery可以用“field:key”方式，例如“content:lucene”。
BooleanQuery中‘与’用‘+’，‘或’用‘ ’，例如“content:java contenterl”。
RangeQuery用‘[]’或‘{}’，前者表示闭区间，后者表示开区间，例如“time:[20060101 TO 20060130]”，注意TO区分大小写。

 

Filter

 

RangeFilter：设定只搜索指定范围内的索引。

QueryFilter：在上次查询的结果中搜索

 

//例子:
 

Directory dir = FSDirectory.getDirectory(PATH, false);
IndexSearcher is = new IndexSearcher(dir);
QueryParser parser = new QueryParser("content", new StandardAnalyzer());
Query query = parser.parse("title:lucene content:lucene";
RangeFilter filter = new RangeFilter("time", "20060101", "20060230", true, true);
Hits hits = is.search(query, filter);
for (int i = 0; i < hits.length(); i++)
{
Document doc = hits.doc(i);
System.out.println(doc.get("title");
}
is.close();

 

 

sort
 

结果集排序
Sort sort = new Sort(“time”); //相当于SQL的“order by time”
Sort sort = new Sort(“time”, true); // 相当于SQL的“order by time desc”

 

 

Directory dir = FSDirectory.getDirectory(PATH, false);
IndexSearcher is = new IndexSearcher(dir);
QueryParser parser = new QueryParser("content", new StandardAnalyzer());
Query query = parser.parse("title:lucene content:lucene";
RangeFilter filter = new RangeFilter("time", "20060101", "20060230", true, true);
Sort sort = new Sort(“time”);
Hits hits = is.search(query, filter, sort);
for (int i = 0; i < hits.length(); i++)
{
    Document doc = hits.doc(i);
    System.out.println(doc.get("title");
}
is.close();