Lucence_Curd

Posted 2020-09-24 白杨无忧

设置Field的类型

 

new StringField 不分词(id,身份证号,电话...)

new StoredField 不分词(链接)

new TextField 分词(文本)

new FloadField 不分词(数字,单价)

 

接着上篇文章    说说Lucene的怎删改查操作

import java.io.File;
import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexableField;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class LuceneCRM {
    
    /**
     * 添加
     * @throws Exception
     */
    @Test
    public void add() throws Exception{
        //获得文档
        Document document = new Document();
        document.add(new StringField("id", "6", Store.YES));
        document.add(new TextField("Name", "柳岩",Store.YES));
        document.add(new StoredField("url", "www.baidu.com"));
        
        //获得分析器
        Analyzer analyzer = new IKAnalyzer();
//        5. 创建Directory对象，声明索引库存储位置
        Directory directory =  FSDirectory.open(new File("H:\\\\temp"));
//        4. 创建IndexWriterConfig配置信息类
        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
//        6. 创建IndexWriter写入对象
        IndexWriter indexWriter = new IndexWriter(directory, config);
        
        indexWriter.addDocument(document);
        indexWriter.close();
     }
    
    /**
     * 修改
     * 更新索引是先删除再添加，建议对更新需求采用此方法并且要保证对已存在的索引执行更新，
     * 可以先查询出来，确定更新记录存在执行更新操作
     * 如果更新索引的目标文档对象不存在，则执行添加。
     * @throws Exception 
     */
    @Test
    public void update() throws Exception{
        //获得分析器
        Analyzer analyzer = new IKAnalyzer();
        // 创建搜索解析器，第一个参数：默认Field域，第二个参数：分词器
        QueryParser queryParser = new QueryParser("name",analyzer);
        // 1. 创建Query搜索对象
        Query query = queryParser.parse("id:6");
        
//        5. 创建Directory对象，声明索引库存储位置
        Directory directory =  FSDirectory.open(new File("H:\\\\temp"));
        
        // 3. 创建索引读取对象IndexReader
        IndexReader indexReader = DirectoryReader.open(directory);
        
        // 4. 创建索引搜索对象IndexSearcher
        IndexSearcher searcher = new IndexSearcher(indexReader);
        
        // 5. 使用索引搜索对象，执行搜索，返回结果集TopDocs
        TopDocs topDocs = searcher.search(query, 1);
        System.out.println("查询到的数据总条数是：" + topDocs.totalHits);
        
        
        
        //获得结果集
        ScoreDoc[] docs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : docs) {
            //获得文档
            Document document = searcher.doc(scoreDoc.doc);
            //如果文档存在就修改
            if(document!=null){
//                4. 创建IndexWriterConfig配置信息类
                IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
//                6. 创建IndexWriter写入对象
                IndexWriter indexWriter = new IndexWriter(directory, config);
                
                Document document2 = new Document();
                //修改
                document2.add(new TextField("name", "刘亦菲4", Store.YES));
                document2.add(new TextField("Name", "柳岩4",Store.YES));
                /*document2.add(new StringField("id", document.getField("id").stringValue(), Store.YES));
                document2.add(new StoredField("url", document.getField("url").stringValue()));*/
                document2.add(document.getField("id"));
                document2.add(document.getField("url"));
                
                indexWriter.updateDocument(new Term("id", "6"), document2);
                indexWriter.close();
            }
        }
        
        indexReader.close();
        
    }
    
    
    /**
     * 这个没有先做查询直接修改的 
     * 符合的doc文档>>这样这里加几个Field,修改的就是Field  其他的Field就不存在了
     * (比如原来5个Field)
     * @throws Exception
     */
    @Test
    public void testIndexUpdate() throws Exception {
        // 创建分词器
        Analyzer analyzer = new IKAnalyzer();
        // 创建Directory流对象
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
        // 创建写入对象
        IndexWriter indexWriter = new IndexWriter(directory, config);

        // 创建Document
        Document document = new Document();
        document.add(new TextField("id", "1003", Store.YES));
        document.add(new TextField("Name", "lucene测试test 004", Store.YES));
        /*document.add(new TextField("desc", "啊哈哈哈哈哈哈哈",Store.YES));*/           //这里修改他会把这条数据给删除了

        // 执行更新，会把所有符合条件的Document删除，再新增。
        indexWriter.updateDocument(new Term("id", "1002"), document); //找到Field域为Name的中值为柳岩的所有的文档

        // 释放资源
        indexWriter.close();
    }

    
    
    /**
     * 删除部分
     * @throws Exception 
     */
    @Test
    public void delete() throws Exception{
        //解析器
        Analyzer analyzer = new IKAnalyzer();
        //磁盘位置
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
//        4. 创建IndexWriterConfig配置信息类
        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
        //写入对象
        IndexWriter indexWriter = new IndexWriter(directory,config );
        
        indexWriter.deleteDocuments(new Term("id","6"));
        
        indexWriter.close();
    }
    
    /**
     * 查询  第一种方式
     * @throws Exception 
     */
    @Test
    public void find01() throws Exception{
        Analyzer analyzer = new IKAnalyzer();
        QueryParser parser = new QueryParser("name", analyzer);
        //parser.parse()
        Query query = parser.parse("Name:柳岩");
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexReader reader =  DirectoryReader.open(directory);
        IndexSearcher indexSearcher = new IndexSearcher(reader);
        TopDocs topDocs = indexSearcher.search(query, 10);
        ScoreDoc[] docs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : docs) {
            Document document = indexSearcher.doc(scoreDoc.doc);
            System.out.println(document.get("Name"));
        }
        reader.close();
    }
    
    /**
     * 查询  第二种方式
     * @throws Exception 
     */
    @Test
    public void find02() throws Exception{
        Query query = new TermQuery(new Term("Name","柳岩"));
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexReader indexReader = DirectoryReader.open(directory);
        IndexSearcher indexSearcher = new IndexSearcher(indexReader);
        TopDocs topDocs = indexSearcher.search(query, 10);
        ScoreDoc[] docs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : docs) {
            Document document = indexSearcher.doc(scoreDoc.doc);
            System.out.println(document.get("Name"));
        }
        indexReader.close();
    }
    
    /**
     * 查询 第三种方式
     * NumericRangeQuery，指定数字范围查询
     */
    @Test
    public void find03() throws Exception{
        Query query = NumericRangeQuery.newFloatRange("price",50f, 70f, false, true);//(50f,70f]
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexReader indexReader = DirectoryReader.open(directory);
        IndexSearcher indexSearcher = new IndexSearcher(indexReader);
        TopDocs topDocs = indexSearcher.search(query, 10);
        ScoreDoc[] docs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : docs) {
            Document document = indexSearcher.doc(scoreDoc.doc);
            System.out.println(document.get("name"));
        }
        indexReader.close();
    }
    
    /**
     * 查询 第四种方式
     * BooleanQuery，指定数字范围查询
     */
    @Test
    public void find04() throws Exception{
        Query query1 = new TermQuery(new Term("desc","java"));
        Query query2 = NumericRangeQuery.newFloatRange("price",50f, 70f, false, true);//(50f,70f]
        
        BooleanQuery booleanQuery  = new BooleanQuery();
        /**
         *   1、MUST和MUST表示“与”的关系，即“交集”。 
             2、MUST和MUST_NOT前者包含后者不包含。 
             3、MUST_NOT和MUST_NOT没意义 
             4、SHOULD与MUST表示MUST，SHOULD失去意义； 
             5、SHOULD与MUST_NOT相当于MUST与MUST_NOT。 
             6、SHOULD与SHOULD表示“或”的关系，即“并集”。

         */
        booleanQuery.add(query1, Occur.MUST);
        booleanQuery.add(query2, Occur.MUST);
        
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexReader indexReader = DirectoryReader.open(directory);
        IndexSearcher indexSearcher = new IndexSearcher(indexReader);
        TopDocs topDocs = indexSearcher.search(booleanQuery, 10);
        ScoreDoc[] docs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : docs) {
            Document document = indexSearcher.doc(scoreDoc.doc);
            System.out.println(document.get("name"));
        }
        indexReader.close();
    }
    
    /**
     * 组合查询
     */
    @Test
    public void find05() throws Exception{
        Analyzer analyzer = new IKAnalyzer();
        QueryParser queryParser = new QueryParser("desc", analyzer);
        //QueryParser提供一个Parse方法，此方法可以直接根据查询语法来查询
        //它支持字符串范围。数字范围搜索建议使用NumericRangeQuery
        Query query = queryParser.parse("desc:java AND lucene");
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexReader indexReader = DirectoryReader.open(directory);
        IndexSearcher indexSearcher = new IndexSearcher(indexReader);
        TopDocs topDocs = indexSearcher.search(query, 10);
        ScoreDoc[] docs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : docs) {
            Document document = indexSearcher.doc(scoreDoc.doc);
            System.out.println(document.get("name"));
        }
        indexReader.close();
    }
    
    /**
     * 通过MultiFieldQueryParse对多个域查询。
     */
    @Test
    public void find06() throws Exception{
        Analyzer analyzer = new IKAnalyzer();
        MultiFieldQueryParser multiFieldQueryParser = new MultiFieldQueryParser(new String[]{"name","desc"}, analyzer);
        //通过MultiFieldQueryParse对多个域查询
        //搜索这两个域中包含lucene域
        Query query = multiFieldQueryParser.parse("lucene");  //name:lucene desc:lucene
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexReader indexReader = DirectoryReader.open(directory);
        IndexSearcher indexSearcher = new IndexSearcher(indexReader);
        TopDocs topDocs = indexSearcher.search(query, 10);
        ScoreDoc[] docs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : docs) {
            Document document = indexSearcher.doc(scoreDoc.doc);
            System.out.println(document.get("name"));
        }
        indexReader.close();
    }
    
    /**
     * 相关度排序(boost是一个加权值（默认加权值为1.0f）)
     * Lucene对查询关键字和索引文档的相关度进行打分，得分高的就排在前边
     *     1）计算出词（Term）的权重   
        2）根据词的权重值，计算文档相关度得分。
            Term Frequency (tf)：
                指此Term在此文档中出现了多少次。tf 越大说明越重要。 
                词(Term)在文档中出现的次数越多，说明此词(Term)对该文档越重要，如“Lucene”这个词，
                在文档中出现的次数很多，说明该文档主要就是讲Lucene技术的。
            Document Frequency (df)：
                指有多少文档包含此Term。df 越大说明越不重要。     
                比如，在一篇英语文档中，this出现的次数更多，就说明越重要吗？
                不是的，有越多的文档包含此词(Term), 说明此词(Term)太普通，不足以区分这些文档，因而重要性越低。
     * @throws Exception 
     */
    @Test
    public void addS() throws Exception{
        Analyzer analyzer = new IKAnalyzer();
        Directory directory = FSDirectory.open(new File("H:\\\\temp"));
        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
        IndexWriter indexWriter = new IndexWriter(directory, config);
        
        Document document = new Document();
        document.add(new StringField("id", "7", Store.YES));
        document.add(new TextField("desc", "哈哈哈哈哈哈", Store.YES));
        document.add(new TextField("name", "柳岩", Store.YES));
        //添加权重   
        TextField field = new TextField("Name", "柳岩", Store.YES);  //在做查询柳岩是  这个就排在第一个了  无敌了
        field.setBoost(100f);  //设置权重
        document.add(field);
        
        indexWriter.addDocument(document);
        
        indexWriter.close();
    }
    
}

说说我对权重的解释,这个经常baidu的人很有感触,一些广告总是出现在最前面,个人觉得就是(你懂得,调整了权重...哈哈)