lucene3.0学习笔记(二)index

luceneApacheF#

1。IndexWriter的学习

IndexWriter writer = new IndexWriter(FSDirectory.open("E:\\test\\index"),
                new StandardAnalyzer(Version.LUCENE_CURRENT), true,
                IndexWriter.MaxFieldLength.LIMITED);

IndexWriter writer = new IndexWriter(FSDirectory.open("E:\\test\\index"),
				new StandardAnalyzer(Version.LUCENE_CURRENT), true,
				IndexWriter.MaxFieldLength.LIMITED);

IndexWriter类的构造函数共四个参数：
(1).Directory dir:FSDirectory:表示对文件系统目录的操作;RAMDirectory:内存中的目录操作,一般FSDirectory用的较多。
(2).Analyzer a: 用来对文档进行词法分析和语言处理(StandardAnalyzer对中文分词的支持不是很好)
(3).boolean b :如果没有该索引就创建，否则覆盖原有索引
(4).

2.document的学习

    Document是lucene自己定义的一种文件格式，lucene使用docement来代替对应的物理文件或者保存在数据库中的数据。因此Document只能作为数据源在Lucene中的数据存贮的一种文件形式。
　　Document只是负责收集数据源，因为不同的文件可以构建同一个Document。只要用户将不同的文件创建成Document类型的文件，Lucene就能快速找到查找并且使用他们。
　　对于一个Document文件，可以同时增加多个Field。Lucene中对于每个数据源是使用Field类来表示的。多个Field组成一个Document，多个Document组成一个索引文件。

Document doc = new Document();
        doc.add(new Field("contents", new FileReader(f)));
        doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES,
                Field.Index.ANALYZED));
        writer.addDocument(doc);

Document doc = new Document();
		doc.add(new Field("contents", new FileReader(f)));
		doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES,
				Field.Index.ANALYZED));
		writer.addDocument(doc);

3。

int numIndexed = writer.numDocs();//当前索引中文档的个数
        writer.optimize();
        writer.close();

int numIndexed = writer.numDocs();//当前索引中文档的个数
		writer.optimize();
		writer.close();

4。搜索

搜索过程如下：

创建IndexSearcher准备进行搜索
创建Analyer用来对查询语句进行词法分析和语言处理
创建QueryParser用来对查询语句进行语法分析
QueryParser调用parser进行语法分析，形成查询语法树，放到Query中
IndexSearcher调用search对查询语法树Query进行搜索，得到结果TopScoreDocCollector

IndexSearcher is = new IndexSearcher(FSDirectory.open(indexDir), true);// read-only
        String field = "contents";
        QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, field,
                new StandardAnalyzer(Version.LUCENE_CURRENT));
        Query query = parser.parse(q);
        TopScoreDocCollector collector = TopScoreDocCollector.create(TOP_NUM,
                false);
        long start = new Date().getTime();// start time
        is.search(query, collector);

IndexSearcher is = new IndexSearcher(FSDirectory.open(indexDir), true);// read-only
		String field = "contents";
		QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, field,
				new StandardAnalyzer(Version.LUCENE_CURRENT));
		Query query = parser.parse(q);
		TopScoreDocCollector collector = TopScoreDocCollector.create(TOP_NUM,
				false);
		long start = new Date().getTime();// start time
		is.search(query, collector);

附上例子：
(1)创建索引

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.Date;

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.store.FSDirectory;
import org.apache.lucene.util.Version;

public class Indexer {
    private static String INDEX_DIR = "E:\\test\\index";// 索引存放目录
    private static String DATA_DIR = "E:\\test\\file\\";// 文件存放的目录

    public static void main(String[] args) throws Exception {
        long start = new Date().getTime();
        int numIndexed = index(new File(INDEX_DIR), new File(DATA_DIR));// 调用index方法
        long end = new Date().getTime();
        System.out.println("Indexing " + numIndexed + " files took "
                + (end - start) + " milliseconds");
    }

    /**
     * 索引dataDir下的.txt文件，并储存在indexDir下，返回索引的文件数量
     * @param indexDir
     * @param dataDir
     * @return int
     * @throws IOException
     */
    public static int index(File indexDir, File dataDir) throws IOException {
        if (!dataDir.exists() || !dataDir.isDirectory()) {
            throw new IOException(dataDir
                    + " does not exist or is not a directory");
        }
        IndexWriter writer = new IndexWriter(FSDirectory.open(indexDir),
                new StandardAnalyzer(Version.LUCENE_CURRENT), true,
                IndexWriter.MaxFieldLength.LIMITED);
        indexDirectory(writer, dataDir);// 调用indexDirectory方法
        int numIndexed = writer.numDocs();//当前索引中文档的个数
        writer.optimize();
        writer.close();
        return numIndexed;
    }

    /**
     * 循环遍历目录下的所有.txt文件并进行索引
     * @param writer
     * @param dir
     * @throws IOException
     */
    private static void indexDirectory(IndexWriter writer, File dir)
            throws IOException {
        File[] files = dir.listFiles();
        for (int i = 0; i < files.length; i++) {
            File f = files[i];
            if (f.isDirectory()) {
                indexDirectory(writer, f); // recurse
            } else if (f.getName().endsWith(".txt")) {
                indexFile(writer, f);
            }
        }
    }

    /**
     * 对单个txt文件进行索引
     * @param writer
     * @param f
     * @throws IOException
     */
    private static void indexFile(IndexWriter writer, File f)
            throws IOException {
        if (f.isHidden() || !f.exists() || !f.canRead()) {
            return;
        }
        System.out.println("Indexing " + f.getCanonicalPath());
        Document doc = new Document();//针对参数文件建立索引文档
        doc.add(new Field("contents", new FileReader(f)));
        doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES,
                Field.Index.ANALYZED));
        writer.addDocument(doc);//在writer中加入此文档
    }

}

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.Date;

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.store.FSDirectory;
import org.apache.lucene.util.Version;

public class Indexer {
	private static String INDEX_DIR = "E:\\test\\index";// 索引存放目录
	private static String DATA_DIR = "E:\\test\\file\\";// 文件存放的目录

	public static void main(String[] args) throws Exception {
		long start = new Date().getTime();
		int numIndexed = index(new File(INDEX_DIR), new File(DATA_DIR));// 调用index方法
		long end = new Date().getTime();
		System.out.println("Indexing " + numIndexed + " files took "
				+ (end - start) + " milliseconds");
	}

	/**
	 * 索引dataDir下的.txt文件，并储存在indexDir下，返回索引的文件数量
	 * @param indexDir
	 * @param dataDir
	 * @return int
	 * @throws IOException
	 */
	public static int index(File indexDir, File dataDir) throws IOException {
		if (!dataDir.exists() || !dataDir.isDirectory()) {
			throw new IOException(dataDir
					+ " does not exist or is not a directory");
		}
		IndexWriter writer = new IndexWriter(FSDirectory.open(indexDir),
				new StandardAnalyzer(Version.LUCENE_CURRENT), true,
				IndexWriter.MaxFieldLength.LIMITED);
		indexDirectory(writer, dataDir);// 调用indexDirectory方法
		int numIndexed = writer.numDocs();//当前索引中文档的个数
		writer.optimize();
		writer.close();
		return numIndexed;
	}

	/**
	 * 循环遍历目录下的所有.txt文件并进行索引
	 * @param writer
	 * @param dir
	 * @throws IOException
	 */
	private static void indexDirectory(IndexWriter writer, File dir)
			throws IOException {
		File[] files = dir.listFiles();
		for (int i = 0; i < files.length; i++) {
			File f = files[i];
			if (f.isDirectory()) {
				indexDirectory(writer, f); // recurse
			} else if (f.getName().endsWith(".txt")) {
				indexFile(writer, f);
			}
		}
	}

	/**
	 * 对单个txt文件进行索引
	 * @param writer
	 * @param f
	 * @throws IOException
	 */
	private static void indexFile(IndexWriter writer, File f)
			throws IOException {
		if (f.isHidden() || !f.exists() || !f.canRead()) {
			return;
		}
		System.out.println("Indexing " + f.getCanonicalPath());
		Document doc = new Document();//针对参数文件建立索引文档
		doc.add(new Field("contents", new FileReader(f)));
		doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES,
				Field.Index.ANALYZED));
		writer.addDocument(doc);//在writer中加入此文档
	}

}

2。搜索

import java.io.File;
import java.util.Date;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class Searcher {
    private static String INDEX_DIR = "E:\\test\\index\\";// 索引所在的路径
    private static String KEYWORD = "接受";// 关键词
    private static int TOP_NUM = 100;// 显示前100条结果

    public static void main(String[] args) throws Exception {
        File indexDir = new File(INDEX_DIR);
        if (!indexDir.exists() || !indexDir.isDirectory()) {
            throw new Exception(indexDir
                    + " does not exist or is not a directory.");
        }
        search(indexDir, KEYWORD);// 调用search方法进行查询
    }

    /**
     * 查询
     *
     * @param indexDir
     * @param q
     * @throws Exception
     */
    public static void search(File indexDir, String q) throws Exception {
        IndexSearcher is = new IndexSearcher(FSDirectory.open(indexDir), true);// read-only
        String field = "contents";
        QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, field,
                new StandardAnalyzer(Version.LUCENE_CURRENT));
        Query query = parser.parse(q);
        TopScoreDocCollector collector = TopScoreDocCollector.create(TOP_NUM,
                false);
        long start = new Date().getTime();// start time
        is.search(query, collector);
        ScoreDoc[] hits = collector.topDocs().scoreDocs;
        System.out.println(hits.length);
        for (int i = 0; i < hits.length; i++) {
            Document doc = is.doc(hits[i].doc);// new method is.doc()
            System.out.println(doc.getField("filename") + "   "
                    + hits[i].toString() + " ");
        }
        long end = new Date().getTime();// end time
        System.out.println("Found " + collector.getTotalHits()
                + " document(s) (in " + (end - start)
                + " milliseconds) that matched query '" + q + "':");
    }
}