简单的lucene实例

package TestLucene;
import java.io.File;
import java.io.FileReader;
import java.io.Reader;
import java.util.Date;
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;
/**
 * This class demonstrate the process of creating index with Lucene
 * for text files
 */
public class TxtFileIndex {
    public static void main(String[] args) throws Exception{
        //设置索引地址
        File   indexDir = new File("D:\\luceneIndex");
        //设置数据地址
        File   dataDir  = new File("D:\\luceneData");
        //建立分词
        Analyzer luceneAnalyzer = new StandardAnalyzer();
        //取得目录下所有Files
        File[] dataFiles  = dataDir.listFiles();
        //建立indexWrite  indexWrite主要作用是添加索引
        IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);
        //取得程序开启时间
        long startTime = new Date().getTime();
        //循环文件
        for(int i = 0; i < dataFiles.length; i++){
            //取出txt后缀的文档
            if(dataFiles[i].isFile() && dataFiles[i].getName().endsWith(".txt")){
                System.out.println("Indexing file " + dataFiles[i].getCanonicalPath());
                //新建一个Document
                Document document = new Document();
                //读取数据
                Reader txtReader = new FileReader(dataFiles[i]);
                //Document添加path
                document.add(new Field("path", dataFiles[i].getCanonicalPath(), Field.Store.YES, Field.Index.UN_TOKENIZED));
                //Document添加正文
                document.add(new Field("contents",txtReader));
                //添加索引
                indexWriter.addDocument(document);
            }
        }
        indexWriter.optimize();
        indexWriter.close();
        long endTime = new Date().getTime();

        //输出程序所用时间
        System.out.println("It takes " + (endTime - startTime)
                           + " milliseconds to create index for the files in directory "
                           + dataDir.getPath());
    }
}

//pizza
package TestLucene;
import java.io.File;

import org.apache.log4j.Logger;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.FSDirectory;
/**
 * This class is used to demonstrate the
 * process of searching on an existing
 * Lucene index
 *
 */
public class TxtFileSearcher {
    public static void main(String[] args) throws Exception{
        Logger logger=Logger.getLogger(TxtFileSearcher.class);
        //要查询的词组
        String queryStr = "com.log4j.test.TestLog.main";
        //索引地址
        File indexDir = new File("D:\\luceneIndex");
        //取得索引字典
        FSDirectory directory = FSDirectory.getDirectory(indexDir,false);
        //建立查询
        IndexSearcher searcher = new IndexSearcher(directory);
        //查询的索引地址是否存在
        if(!indexDir.exists()){
            System.out.println("The Lucene index is not exist");
            return;
        }
        //建立term 查询docuemnt中contents中的内容（内容要转为大字）
        Term term = new Term("contents",queryStr.toLowerCase());
        //进行查询
        TermQuery luceneQuery = new TermQuery(term);
        //生成结果
        Hits hits = searcher.search(luceneQuery);
        for(int i = 0; i < hits.length(); i++){
            //取得结果中的dowuemnt
            Document document = hits.doc(i);
            //取得返回的path属性
            System.out.println("File: " + document.get("path"));
        }
    }
}

Lucene 的四大索引查询
清单1：使用布尔操作符

//Test boolean operator
blic void testOperator(String indexDirectory) throws Exception{
 Directory dir = FSDirectory.getDirectory(indexDirectory,false);
 IndexSearcher indexSearcher = new IndexSearcher(dir);
 String[] searchWords = {"Java AND Lucene", "Java NOT Lucene", "Java OR Lucene",
                  "+Java +Lucene", "+Java -Lucene"};
 Analyzer language = new StandardAnalyzer();
 Query query;
 for(int i = 0; i < searchWords.length; i++){
    query = QueryParser.parse(searchWords[i], "title", language);
    Hits results = indexSearcher.search(query);
    System.out.println(results.length() + "search results for query " + searchWords[i]);
 }

域搜索(Field Search)

Lucene 支持域搜索，你可以指定一次查询是在哪些域(Field)上进行。例如，如果索引的文档包含两个域，Title 和 Content，你就可以使用查询 “Title: Lucene AND Content: Java” 来返回所有在 Title 域上包含 Lucene 并且在 Content 域上包含 Java 的文档。清单 2 显示了如何利用 Lucene 的 API 来实现域搜索。


清单2：实现域搜索

//Test field search
public void testFieldSearch(String indexDirectory) throws Exception{
    Directory dir = FSDirectory.getDirectory(indexDirectory,false);
    IndexSearcher indexSearcher = new IndexSearcher(dir);
    String searchWords = "title:Lucene AND content:Java";
    Analyzer language = new StandardAnalyzer();
    Query query = QueryParser.parse(searchWords, "title", language);
    Hits results = indexSearcher.search(query);
    System.out.println(results.length() + "search results for query " + searchWords);
}

通配符搜索(Wildcard Search)

Lucene 支持两种通配符：问号（？）和星号（*）。你可以使用问号（？）来进行单字符的通配符查询，或者利用星号（*）进行多字符的通配符查询。例如，如果你想搜索 tiny 或者 tony，你就可以使用查询语句 “t?ny”；如果你想查询 Teach, Teacher 和 Teaching，你就可以使用查询语句 “Teach*”。清单3 显示了通配符查询的过程。


清单3：进行通配符查询

//Test wildcard search
public void testWildcardSearch(String indexDirectory)throws Exception{
   Directory dir = FSDirectory.getDirectory(indexDirectory,false);
   IndexSearcher indexSearcher = new IndexSearcher(dir);
   String[] searchWords = {"tex*", "tex?", "?ex*"};
   Query query;
   for(int i = 0; i < searchWords.length; i++){
      query = new WildcardQuery(new Term("title",searchWords[i]));
      Hits results = indexSearcher.search(query);
      System.out.println(results.length() + "search results for query " + searchWords[i]);
   }
}

模糊查询

Lucene 提供的模糊查询基于编辑距离算法(Edit distance algorithm)。你可以在搜索词的尾部加上字符 ~ 来进行模糊查询。例如，查询语句 “think~” 返回所有包含和 think 类似的关键词的文档。清单 4 显示了如果利用 Lucene 的 API 进行模糊查询的代码。


清单4：实现模糊查询

//Test fuzzy search
public void testFuzzySearch(String indexDirectory)throws Exception{
   Directory dir = FSDirectory.getDirectory(indexDirectory,false);
   IndexSearcher indexSearcher = new IndexSearcher(dir);
   String[] searchWords = {"text", "funny"};
   Query query;
   for(int i = 0; i < searchWords.length; i++){
      query = new FuzzyQuery(new Term("title",searchWords[i]));
      Hits results = indexSearcher.search(query);
      System.out.println(results.length() + "search results for query " + searchWords[i]);
   }
}

范围搜索(Range Search)

范围搜索匹配某个域上的值在一定范围的文档。例如，查询 “age:[18 TO 35]” 返回所有 age 域上的值在 18 到 35 之间的文档。清单5显示了利用 Lucene 的 API 进行返回搜索的过程。


清单5：测试范围搜索

//Test range search
public void testRangeSearch(String indexDirectory)throws Exception{
    Directory dir = FSDirectory.getDirectory(indexDirectory,false);
    IndexSearcher indexSearcher = new IndexSearcher(dir);
    Term begin = new Term("birthDay","20000101");
    Term end   = new Term("birthDay","20060606");
    Query query = new RangeQuery(begin,end,true);
    Hits results = indexSearcher.search(query);
    System.out.println(results.length() + "search results is returned");
}