Lucene3.5自学系列1-建立索引

备注：

Field.Store.YES, 标志该数据源（字段）被存储，如果为NO当然闪不存储

Field.Index.ANALYZED标志该数据源（字段）被索引，如果为NO当然是不索引，注意这里索引闪经过了分词解释器处理后得结果

API解释为：

Enum Constant Summary

ANALYZED 
          Index the tokens produced by running the field's value through an Analyzer.

ANALYZED_NO_NORMS 
          Expert: Index the tokens produced by running the field's value through an Analyzer, and also separately disable the storing of norms.

NO 
          Do not index the field value.

NOT_ANALYZED 
          Index the field's value without using an Analyzer, so it can be searched.

NOT_ANALYZED_NO_NORMS 
          Expert: Index the field's value without an Analyzer, and also disable the indexing of norms.

在3.5以前得版本中还有Field是发分词的选项

//////////////////////////////////////源码//////////////////////////////////////

package cn.swust.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;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

import cn.swust.tool.ToolUtil;

/**
 * 创建文档索引类
 * @author qingfeideyi
 *
 */
public class IndexProcessor {
    private String INDEX_STORe_PATH = "/home/qingfeideyi/文档/indexstore/";
    public IndexProcessor(){};
    public IndexProcessor(String index_path)
    {
        this.INDEX_STORe_PATH = index_path;
    }
    
    //创建索引
    public void createIndex(String inputDir) throws IOException
    {
        boolean isCreate = true;
        //待创建得文档目录
        Directory dir = FSDirectory.open(new File(INDEX_STORe_PATH));
        //选择得分词工具
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_34);
        //建立索引的配置类，包含了一个解析器
        IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_34, analyzer);
         //设置我们的解析器是新建还是追加更新
        if(isCreate){
            iwc.setOpenMode(OpenMode.CREATE);//每次建立都覆盖原来的索引
        }
        else
            iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);//每次都追加更新
//索引的建立类 第一个参数索引的存放位置，第二个参数索引的配置对象
        IndexWriter writer = new IndexWriter(dir, iwc);
        
        File fileDir = new File(inputDir);
        File[] files = fileDir.listFiles();
        for (int i = 0; i < files.length; i++) 
        {
            String fileName = files[i].getName();
            if(fileName.endsWith(".txt"))
            {
                System.out.println(fileName);
                Document doc = new Document();
                Field f0 = new Field("FileName", fileName, Field.Store.YES, Field.Index.ANALYZED);
                doc.add(f0);
                Field f1 = new Field("Content",ToolUtil.loadFileToString(files[i]),Field.Store.YES,Field.Index.NOT_ANALYZED);
                doc.add(f1);
                /**
                 * 同理还可以建立其他的Field：如时间，文件大小，等等字段
*/
                writer.addDocument(doc);
                writer.close();
            }
            //这个方法在新增索引的情况会很有用，就是讲原来散落的索引文件重新进行整理合并！
//  writer.forceMerge(1);
        }
    }
    public static void main(String[] args) {
        String inputPath = "/home/qingfeideyi/文档/lucene";
        IndexProcessor ip = new IndexProcessor();
        try {
            ip.createIndex(inputPath);
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
}