Parse XML + Index + Search

Lucene

import org.apache.commons.digester3.*;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
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.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.xml.sax.SAXException;
import org.apache.lucene.index.LogMergePolicy;
import org.apache.lucene.index.MergePolicy;

import java.io.File;
import java.io.FileFilter;
import java.io.FileReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Scanner;


/**
 * Parses the contents of doc XML file.  The name of the file to
 * parse must be specified as the first command line argument.
 */
public class PathTest
{
	public static StandardAnalyzer analyzer;
	public static IndexWriter writer;
	public static IndexSearcher searcher;
	public static IndexReader reader;
	public static String indexDir = "C:/Users/tkeshelashvilg/workspace/LuceneDemo/test"; 
	public static String dataDir = "C:/Users/tkeshelashvilg/workspace/LuceneDemo/medplus"; 
	public static QueryParser parser;
	public static Query query;
	public static Directory   dir;
	public static IndexWriterConfig config;
	public static String currentFile;
	/**
	 * Prints the contact information to standard output.
	 *
	 * @param contact the <code>Contact</code> to print out
	 */

	/**
	 * Configures Digester rules and actions, parses the XML file specified
	 * as the first argument.
	 *
	 * @param args command line arguments
	 * @throws Exception 
	 */
	public static void main(String[] args) throws Exception
	{
		parseAndIndex();
		
		//Searching	
		System.out.println("search:  ");
		Scanner input = new Scanner(System.in);
		String s = input.nextLine();
		search(dataDir, s);
	}
	
	public static void parseAndIndex() throws SAXException, Exception{
		Digester digester = new Digester();
		dir = FSDirectory.open(new File(indexDir));

		analyzer = new StandardAnalyzer(Version.LUCENE_43);
		config = new IndexWriterConfig(Version.LUCENE_43, analyzer);
		writer = new IndexWriter(dir, config);
		long startTime = System.currentTimeMillis();

		digester.setValidating(false);     
		digester.addObjectCreate("doc", PathTest.class );
		digester.addObjectCreate("doc/", TextDoc.class );
		digester.addCallMethod("doc/title",       "setTitle", 0);
		digester.addCallMethod("doc/sections/section/title",   "addsectionTitle", 0);
		digester.addCallMethod("doc/sections/section/text",       "addText", 0);
		//indexing
		digester.addSetNext("doc",               "indexDoc" );
		//    TextParser tp = (TextParser) digester.parse(new File(args[0]));
		parseXML(dataDir, new TextFilesFilter(), digester);
		writer.close();
		long stopTime = System.currentTimeMillis();
		System.out.println("It took " + (stopTime - startTime)/1000 + " seconds to parse and index the documents");   
		
	}

	public static void parseXML(String dataDir, FileFilter filter, Digester digester) throws Exception, SAXException{
		PathTest tp;
		File [] files = new File(dataDir).listFiles();
		for(File f : files){
			if(!f.isDirectory()&&
					!f.isHidden()&&
					f.exists()&&
					f.canRead()&&
					(filter == null || filter.accept(f))){
				currentFile = f.getCanonicalPath();
				tp = (PathTest) digester.parse(f);
			}
		}
	}

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

	@SuppressWarnings("deprecation")
	public static void indexDoc(TextDoc textDoc) throws Exception{
		Document doc = new Document();
		doc.add(new Field("pageTitle",textDoc.getTitle(), Field.Store.YES, Index.ANALYZED));
		doc.add(new Field("sectionTitle", textDoc.getSectionArray(), Field.Store.YES, Index.ANALYZED));
		doc.add(new Field("content", textDoc.getText(), Field.Store.YES, Index.ANALYZED));
		doc.add(new Field("uri", currentFile, Field.Store.YES, Index.NOT_ANALYZED_NO_NORMS));
		System.out.println("Indexing " + currentFile);
		writer.addDocument(doc);
		System.out.println(" number of docs indexed: " + writer.numDocs());

	}

	public static void printAll(TextDoc textDoc){
		System.out.println("Page Title: " + textDoc.getTitle());
		System.out.println("Section Title: " + textDoc.getSectionArray());
		System.out.println("Content: " + textDoc.getText());
	}

	public static void search(String indexDir, String s) throws IOException, ParseException{
		System.out.println("Trying to search: ");
		System.out.println(dir);
		reader = DirectoryReader.open(dir);
		searcher = new IndexSearcher(reader);    
		parser = new QueryParser(Version.LUCENE_43,"content",analyzer);
		query = parser.parse(s);
		System.out.println("query: " +query);
		TopDocs hits = searcher.search(query, 10);
		System.out.println("Found: " + hits.totalHits);

		for(ScoreDoc scoreDoc : hits.scoreDocs){
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println( doc.get("pageTitle"));
			System.out.println(doc.get("uri"));
		}
		reader.close();	 
	}

	public static class TextDoc{
		public String title;
		public List<String> textArr = new ArrayList<String>();
		public List<String> sectionTitleArray = new ArrayList<String>();
		public void setTitle(String title)
		{
			this.title = title;
		}
		public String getTitle(){
			return this.title;
		}
		public void addText(String text){
			textArr.add(text);
		}
		public String getText(){
			return this.textArr.toString();
		}
		public void addsectionTitle(String title){
			this.sectionTitleArray.add(title);
		}
		public String getSectionArray(){
			return this.sectionTitleArray.toString();
		}
	}  
}

Hello, i have an XML file, and I would like to index and parse it with Lucene, how to procced?. This is an example of my Xml file:

                               <num>number </num>
                              <title> title </title>
                              <querytime> time</querytime>
                              <querytweettime>number</querytweettime>