Lucene初识

public class Indexer {

  public static void main(String[] args) throws Exception {
    if (args.length != 2) {
      throw new IllegalArgumentException("Usage: java " + Indexer.class.getName()
        + " <index dir> <data dir>");
    }
    String indexDir = args[0];         //1
    String dataDir = args[1];          //2

    long start = System.currentTimeMillis();
    Indexer indexer = new Indexer(indexDir);
    int numIndexed;
    try {
      numIndexed = indexer.index(dataDir, new TextFilesFilter());
    } finally {
      indexer.close();
    }
    long end = System.currentTimeMillis();

    System.out.println("Indexing " + numIndexed + " files took "
      + (end - start) + " milliseconds");
  }

  private IndexWriter writer;

  public Indexer(String indexDir) throws IOException {
    Directory dir = FSDirectory.open(new File(indexDir));
    writer = new IndexWriter(dir,            //3
                 new StandardAnalyzer(       //3
                     Version.LUCENE_30),//3
                 true,                       //3
                             IndexWriter.MaxFieldLength.UNLIMITED); //3
  }

  public void close() throws IOException {
    writer.close();                             //4
  }

  public int index(String dataDir, FileFilter filter)
    throws Exception {

    File[] files = new File(dataDir).listFiles();

    for (File f: files) {
      if (!f.isDirectory() &&
          !f.isHidden() &&
          f.exists() &&
          f.canRead() &&
          (filter == null || filter.accept(f))) {
        indexFile(f);
      }
    }

    return writer.numDocs();                     //5
  }

  private static class TextFilesFilter implements FileFilter {
    public boolean accept(File path) {
      return path.getName().toLowerCase()        //6
             .endsWith(".txt");                  //6
    }
  }

  protected Document getDocument(File f) throws Exception {
    Document doc = new Document();
    doc.add(new Field("contents", new FileReader(f)));      //7
    doc.add(new Field("filename", f.getName(),              //8
                Field.Store.YES, Field.Index.NOT_ANALYZED));//8
    doc.add(new Field("fullpath", f.getCanonicalPath(),     //9
                Field.Store.YES, Field.Index.NOT_ANALYZED));//9
    return doc;
  }

  private void indexFile(File f) throws Exception {
    System.out.println("Indexing " + f.getCanonicalPath());
    Document doc = getDocument(f);
    writer.addDocument(doc);                              //10
  }
}
建立索引的过程
/*
#1 Create index in this directory
#2 Index *.txt files from this directory
#3 Create Lucene IndexWriter
#4 Close IndexWriter
#5 Return number of documents indexed
#6 Index .txt files only, using FileFilter
#7 Index file content
#8 Index file name
#9 Index file full path
#10 Add document to Lucene index
*/

 

public class Searcher {

  public static void main(String[] args) throws IllegalArgumentException,
        IOException, ParseException {
    if (args.length != 2) {
      throw new IllegalArgumentException("Usage: java " + Searcher.class.getName()
        + " <index dir> <query>");
    }

    String indexDir = args[0];               //1 
    String q = args[1];                      //2   

    search(indexDir, q);
  }

  public static void search(String indexDir, String q)
    throws IOException, ParseException {

    Directory dir = FSDirectory.open(new File(indexDir)); //3
    IndexSearcher is = new IndexSearcher(dir);   //3   

    QueryParser parser = new QueryParser(Version.LUCENE_30, // 4
                                         "contents",  //4
                     new StandardAnalyzer(          //4
                       Version.LUCENE_30));  //4
    Query query = parser.parse(q);              //4   
    long start = System.currentTimeMillis();
    TopDocs hits = is.search(query, 10); //5
    long end = System.currentTimeMillis();

    System.err.println("Found " + hits.totalHits +   //6  
      " document(s) (in " + (end - start) +        // 6
      " milliseconds) that matched query '" +     // 6
      q + "':");                                   // 6

    for(ScoreDoc scoreDoc : hits.scoreDocs) {
      Document doc = is.doc(scoreDoc.doc);               //7      
      System.out.println(doc.get("fullpath"));  //8
    }

    is.close();                                //9
  }
}
查询过程
/*
#1 Parse provided index directory
#2 Parse provided query string
#3 Open index
#4 Parse query
#5 Search index
#6 Write search stats
#7 Retrieve matching document
#8 Display filename
#9 Close IndexSearcher
*/

Lucene索引过程的核心类

IndexWriter

索引过程的核心组件，创建新索引和打开已有索引，以及向索引中添加删除更新被索引文档的信息。为你提供针对索引文件的写入操作，但不能用于读取或搜索索引，由Directory开辟一定空间来存储索引

Directory 

子类负责具体指定索引的存储路径，IndexWriter不能直接索引文件，需要由Analyzer将文本分割成独立的单词才行

Analyzer

从被索引文件中提取语汇单元，Tika

Document

代表一些域的集合，代表文档或者和文档相关的一些元数据。Lucene只处理从二进制文档中提取的以Field实例形式出现的文本，作为文档的不同域单独存储并索引。

Field

 

 

搜索过程的核心类

IndexSearcher

连接索引的中心环节，只读方式打开索引的类，利用Directory实例来掌控前期创建的索引，

Term

搜索功能的基本单元，包含一对字符串元素：域名和单词。

Query

 

TermQuery

TopDocs

简单地指针容器，指向前N个排名的搜索结果（匹配查询条件的文档）。类记载前N个结果中的每个结果的int docID（用来恢复文档）和浮点型分数。