luceneAPI的简单使用（java）

谁践踏了优雅 2022-07-15 10:14 31阅读 0赞

lucene是一个全文检索引擎工具包，下面来简单的介绍下Lucene常用的API介绍

**1：对一个文件下面的所有文件进行索引创建：**

import java.io.BufferedReader;
    import java.io.File;
    import java.io.FileReader;
    
    import org.apache.lucene.analysis.Analyzer;
    import org.apache.lucene.analysis.standard.StandardAnalyzer;
    import org.apache.lucene.document.Document;
    import org.apache.lucene.document.Field;
    import org.apache.lucene.document.Field.Store;
    import org.apache.lucene.document.StringField;
    import org.apache.lucene.document.TextField;
    import org.apache.lucene.index.IndexWriter;
    import org.apache.lucene.index.IndexWriterConfig;
    import org.apache.lucene.store.Directory;
    import org.apache.lucene.store.FSDirectory;
    import org.apache.lucene.util.Version;
    import org.wltea.analyzer.lucene.IKAnalyzer;
    /** * 对一个文件里面的内容建立索引，包括文件名和文件的内容 * 1：创建分词器。标准分词器 * 2：创建IndexWriter IndexWriter是索引过程中的核心组件 * 3：创建document 创建Field * 4：写入 * 5：关闭资源 * @author 韩利鹏 */
    public class CreateLocal {
    
        private static String file_dir = "D:/decstop/luceneTxt";// 带索引的本地文件目录
        // 索引存放目录
        private static String index_dir = "D:/decstop/index";
    
        public static void index(String filedir) throws Exception {
            //1：创建中文分词器
            //Analyzer analyzer = new StandardAnalyzer(); //lucene自带的标准分词器，对中文的分词支持不好，做中文的分词不建议使用
            Analyzer analyzer = new IKAnalyzer(); //IKAnalyzer是一个中文分词器，有中文的时候建议使用这个
            File indexfile = new File(index_dir);
            Directory directorty = FSDirectory.open(indexfile);
            IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
            //2:创建indexwriter
            IndexWriter writer = new IndexWriter(directorty, cfg);
    
            // 遍历目录 循环读取文件 逐个建立文件索引
            File file = new File(filedir);
            File[] files = file.listFiles();
            for (File f : files) {
                if (f.isDirectory()) {
                    index(f.getPath());
                } else {
                    Document doc = new Document();
                    // 文件名字
                    // Store:如果是yes 则说明存储到文档中
                    //Field name = new StringField("fileName", f.getName(), Store.YES);
                    Field name = new TextField("fileName", f.getName(), Store.YES);
                    // 文件内容
                    BufferedReader reader = new BufferedReader(new FileReader(f));
                    String temp = null;
                    StringBuffer sb = new StringBuffer();
                    while ((temp = reader.readLine()) != null) {
                        sb.append(temp);
                    }
                    reader.close();
                    String context = sb.toString();
    
                    // 把文件内容读到索引中去 这样在搜索索引时就能看到
                    Field body = new TextField("context", context, Store.YES);
                    doc.add(name);
                    doc.add(body);
                    writer.addDocument(doc);
                }
            }
            writer.close();
    
        }
        public static void main(String[] args) throws Exception {
    
            index(file_dir);
        }
    }

**2：搜索**

package lucene;
    
    import java.io.File;
    
    import org.apache.lucene.analysis.standard.StandardAnalyzer;
    import org.apache.lucene.document.Document;
    import org.apache.lucene.index.DirectoryReader;
    import org.apache.lucene.index.IndexReader;
    import org.apache.lucene.queryparser.classic.ParseException;
    import org.apache.lucene.queryparser.classic.QueryParser;
    import org.apache.lucene.search.IndexSearcher;
    import org.apache.lucene.search.Query;
    import org.apache.lucene.search.ScoreDoc;
    import org.apache.lucene.search.TopDocs;
    import org.apache.lucene.store.Directory;
    import org.apache.lucene.store.FSDirectory;
    
    /** * 搜索 * 1：创建indexSercher 指定索引库的地址 * 2：创建Query （查询条件） * 3：执行查询 * 4：遍历得出结果 * 5：关闭资源 * @author 韩利鹏 */
    public class SearchIndexOnLocal {
        public static void doSearch() throws Exception{
            //创建indexSearch     指定索引库的地址
            File indexFile =new File("D:/decstop/index");
            Directory directory =FSDirectory.open(indexFile);
            IndexReader reader = DirectoryReader.open(directory);
            IndexSearcher search = new IndexSearcher(reader);
    
    
            //创建query    参数一：搜索域 field name    第二个参数： 分词器 与添加的分词器一致
            QueryParser parser = new QueryParser("fileName", new StandardAnalyzer());
            //通过QueryParser对象创建query     参数为lucene的查询语句
            Query query = parser.parse("text1 OR text2");
    
            //通过indexSearcher来搜索索引     int 条数
            TopDocs topDocs = search.search(query, 10);
            //根据查询条件匹配出的记录总数
            int count= topDocs.totalHits;
            System.out.println("查询出来的记录："+count);
            ScoreDoc[] scoreDocs = topDocs.scoreDocs; 
            for(ScoreDoc scoreDoc:scoreDocs){
                //获取当前scoreDoc的id
                int docId = scoreDoc.doc;
                //通过document的id来获取每个Field域的值
                Document doc = search.doc(docId);
                System.out.println("文件名字："+doc.get("fileName"));
                System.out.println("文件的内容："+doc.get("context"));
            }
            reader.close();
        }
    
        public static void main(String[] args) throws Exception {
            doSearch();
        }
    
    }

**3删除和修改索引**

package lucene;
    
    import java.io.File;
    import java.io.IOException;
    
    import org.apache.lucene.analysis.Analyzer;
    import org.apache.lucene.analysis.standard.StandardAnalyzer;
    import org.apache.lucene.document.Document;
    import org.apache.lucene.document.Field.Store;
    import org.apache.lucene.document.TextField;
    import org.apache.lucene.index.IndexWriter;
    import org.apache.lucene.index.IndexWriterConfig;
    import org.apache.lucene.index.Term;
    import org.apache.lucene.store.Directory;
    import org.apache.lucene.store.FSDirectory;
    import org.apache.lucene.util.Version;
    
    /** * 删除和修改 */
    public class UpdateIndexOnLocal { 
        /** * 根据条件删除 */
        public static void deleteIndex() throws Exception{
            //创建IndexWriter
            Analyzer analyzer = new StandardAnalyzer();
            File indexfile = new File("D:/decstop/index");
            Directory directorty = FSDirectory.open(indexfile);// cun chu
            IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
            IndexWriter writer = new IndexWriter(directorty, cfg);
            //writer.deleteAll(); //工作中不要用，且用且珍惜
            //参数，域名 对应删除的值
            //删除时，最好根据document 中的唯一值
            writer.deleteDocuments(new Term("fileName", "text1"));
            writer.close();
        }
    
        /** * 修改索引 */
        public static void updateIndex() throws Exception{
            //创建IndexWriter
            Analyzer analyzer = new StandardAnalyzer();
            File indexfile = new File("D:/decstop/index");
            Directory directorty = FSDirectory.open(indexfile);// cun chu
            IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
            IndexWriter writer = new IndexWriter(directorty, cfg);
    
            //创建一个文档域，再创建一个File域进行更新
            Document doc = new Document();
            doc.add(new TextField("content", "abcdefghigk",Store.YES));
            //进行更新
            writer.updateDocument(new Term("fileName","text1"), doc);
            writer.close();
    
        }
    
        public static void main(String[] args) throws Exception {
            //deleteIndex();
            updateIndex();
        }
    
    }

Lucene的搜索语法：