《Lucene In Action》 02 Hello Lucene World

標籤：

Indexer：

import org.apache.lucene.index.IndexWriter;import org.apache.lucene.analysis.standard.StandardAnalyzer;import org.apache.lucene.document.Document;import org.apache.lucene.document.Field;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.store.Directory;import org.apache.lucene.util.Version;import java.io.File;import java.io.FileFilter;import java.io.IOException;import java.io.FileReader;// From chapter 1/** * This code was originally written for * Erik‘s Lucene intro java.net article */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  }}

索引過程核心類：

IndexWriter

　　負責建立或開啟已有索引，以及向索引中添加、刪除或更新被索引文檔資訊，一般要通過構造器傳入Directory和Analyzer

Directory

　　抽象類別，描述了索引的存放位置

Analyzer

　　負責從被索引文本中提取語彙單元，只能處理純文字檔案，如果不是純文字，需要先轉換（如使用Tika）

Document

　　Document對象代表一些Field的集合

Field

　　Lucene只處理從二進位文檔中提取的一Field形式出現的文本，文檔的中繼資料作為文檔的不同域單獨儲存並索引

題外話：Lucene核心本身只處理java.lang.String、java.io.Reader和本地數字類型（int、float等）

Searcher：

import org.apache.lucene.document.Document;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.search.ScoreDoc;import org.apache.lucene.search.TopDocs;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.store.Directory;import org.apache.lucene.queryParser.QueryParser;import org.apache.lucene.queryParser.ParseException;import org.apache.lucene.analysis.standard.StandardAnalyzer;import org.apache.lucene.util.Version;import java.io.File;import java.io.IOException;// From chapter 1/** * This code was originally written for * Erik‘s Lucene intro java.net article */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  }}

搜尋過程核心類：

IndexSearcher

　　用於搜尋由IndexWriter建立的索引，構造器需要傳入Directory擷取建立的索引。然後提供搜尋方法

Term

　　Term對象是搜尋的基本單元（與Field類似）

Query q = new TermQuery(new Term("contents","lucene"));TopDocs hits = searcher.search(q,10);

Query

　　Query是所有查詢類的基類，如TermQuery、BooleanQuery

TermQuery

　　TermQuery是最基本最簡單的查詢類型之一，用於匹配指定域中包含指定項的文檔

TopDocs

　　是一個簡單的指標容器，容納查詢結果

 

湯能養身整理，轉載註明

 

《Lucene In Action》 02 Hello Lucene World