Lucene3.5 之 索引删除和更新

package com.ethan.index;

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

import org.apache.commons.io.FileUtils;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexReader.FieldOption;
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.store.LockObtainFailedException;
import org.apache.lucene.util.Version;

public class IndexUtil {
    private String[] ids = {"1","2","3","4","5","6"};
    private String[] emails = {"[email protected]","[email protected]","[email protected]","[email protected]","[email protected]","[email protected]"};
    private String[] contents = {
            "welcome to nba hot",
            "my name is ethan",
            "someone like you ",
            "rolling in the deep, you like",
            "i like fast........",
            "l like sports"
    };

    private int[] attachs = {2,3,1,5,4,6};
    private String[] names = {"ethan","sara","michael","wade","lin","paul"};

    private Directory directory = null;

    public IndexUtil() {
         try {
            directory = FSDirectory.open(new File("C:\\Users\\ETHAN\\workspace\\hellolucene\\index02"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public void index() {
        IndexWriter writer = null;

        try {
            writer = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)) );
            Document doc = null;
            for(int i=0;i
                doc = new Document();
                doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
                doc.add(new Field("email",emails[i],Field.Store.YES,Field.Index.NOT_ANALYZED));

                doc.add(new Field("content",contents[i],Field.Store.NO,Field.Index.ANALYZED));
                doc.add(new Field("name",names[i],Field.Store.YES,Field.Index.ANALYZED_NO_NORMS));

                writer.addDocument(doc);
            }
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(writer!=null) {
                try {
                    writer.close();
                } catch (CorruptIndexException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }

    }

    public void query() {

        try {
            IndexReader reader = IndexReader.open(directory);
            //被存储的
            System.out.println("numDocs: "+reader.numDocs());

            //文档总量
            System.out.println("maxDocs: "+reader.maxDoc());
            //删除的文档
            System.out.println("deleteDocs: "+reader.numDeletedDocs());;
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public void delete() {
        IndexWriter writer = null;

        try {
            writer = new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));

            //参数是一个选项，可以是一个Query,也可以是一个term,term是一个精确查找的值
            //这里删除id=1的文档，还会留在”回收站“。xxx.del
            writer.deleteDocuments(new Term("id","1"));
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(writer!=null) {
                try {
                    writer.close();
                } catch (CorruptIndexException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }

    }

    public void undelete() {
        //使用IndexReader进行恢复
        IndexReader reader = null;
        try {
            //set readOnly=false
            reader = IndexReader.open(directory,false);
            reader.undeleteAll();
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
             if(reader!=null) {
                 try {
                    reader.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
             }
        }

    }

    public void forceDelete() {
        IndexWriter writer = null;

        try {
            writer = new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));

            //强制优化，del文件就没了，回收站清空
            writer.forceMergeDeletes();
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(writer!=null) {
                try {
                    writer.close();
                } catch (CorruptIndexException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }

    /*
     * 自己手动merge
     * 多次创建索引，文件会增多，
     * 比如 5次的话，5个id=1的
     *
     * merge后合并为n段
     */

    public void merge() {
        IndexWriter writer = null;
        try {
            writer = new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));

            //将索引合并为2段，这两段中的del文件会被清空
            //3.5后不建议使用，开销大，lucene会根据情况自动处理
            writer.forceMerge(2);
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(writer!=null) {
                try {
                    writer.close();
                } catch (CorruptIndexException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }

    /*
     * 更新操作
     */
    public void update() {
        IndexWriter writer = null;
        try {
            writer = new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));

            //lucene没有提供更新方法，这里操作分为两步
            //匹配后删除 和 添加新的

            Document doc = new Document();
            doc.add(new Field("id","11",Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
            doc.add(new Field("email",emails[0],Field.Store.YES,Field.Index.NOT_ANALYZED));

            doc.add(new Field("content",contents[0],Field.Store.NO,Field.Index.ANALYZED));
            doc.add(new Field("name",names[0],Field.Store.YES,Field.Index.ANALYZED_NO_NORMS));

            writer.updateDocument(new Term("id","1"),doc);
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(writer!=null) {
                try {
                    writer.close();
                } catch (CorruptIndexException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
}

package com.ethan.test;

import org.junit.Test;

import com.ethan.index.IndexUtil;

public class IndexTest {

    @Test
    public void testIndex() {
        IndexUtil iu = new IndexUtil();
        iu.index();
    }
    /*
     * numDocs: 24
        maxDocs: 24
        deleteDocs: 0
     */
    @Test
    public void testQuery() {
        IndexUtil iu = new IndexUtil();
        iu.query();
    }
    /*
     * numDocs: 20
        maxDocs: 24
        deleteDocs: 4 (id=1 4条)
     */
    @Test
    public void testDelete() {
        IndexUtil iu = new IndexUtil();
        iu.delete();
    }

    /*
     * numDocs: 7
        maxDocs: 7
        deleteDocs: 0
     */
    @Test
    public void testUnDelete() {
        IndexUtil iu = new IndexUtil();
        iu.undelete();
    }

    /*
     * numDocs: 6
        maxDocs: 6(7)
        deleteDocs: 0(1)
     */
    @Test
    public void testForceDelete() {
        IndexUtil iu = new IndexUtil();
        iu.forceDelete();
    }

    /*
     * merge后：
     * numDocs: 20
        maxDocs: 21
        deleteDocs: 1（因为强制合并为2段，所以_0_1.del没删）
        _0为第一段，不动，把后边的合并为一段
     */
    @Test
    public void testMerge() {
        IndexUtil iu = new IndexUtil();
        iu.merge();
    }

    /*
     * numDocs: 6
        maxDocs: 7
        deleteDocs: 1

        删除后 add
     */
    @Test
    public void testUpdate() {
        IndexUtil iu = new IndexUtil();
        iu.update();
    }
}

索引文件中文件 表示含义：


0.fnm: 保存的field的信息，有哪几个字段


0.fdt,0.fdx:  Store.YES的对应字段的值

0.frq:单词出现的频率

0.nrm: 存储评分信息，权重

0.prx: 偏移量


0.tii,0.tis: 存储索引信息

文档和域的概念：

文档相当于表中的一条记录，域相当于表中每一个字段

optimize() 已被启用，开销比较大
forceMergeDeletes() 强制把回收站的内容给删掉


当segment比较多时，lucene会自动优化处理