Can't search the same word again in Lucene search - apache

Question

I'm new to Lucene so i downloaded an example from http://www.lucenetutorial.com/sample-apps/textfileindexer-java.html .
The code currently works, however, I think I am not correctly making use of Lucene. I can search a word (ex : is student) for the first time, but after that (still in the loop), if i search the same word, it will return an exception. (java.lang.NullPointerException)
Please help me fix it.
Here's my problem
Here's the code
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
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.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;
import java.io.*;
import java.util.ArrayList;
public class TextFileIndexer {
private static StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);
private IndexWriter writer;
private ArrayList<File> queue = new ArrayList<File>();
public static void main(String[] args) throws IOException {
System.out.println("Enter the path where the index will be created: (e.g. /tmp/index or c:\temp\index)");
String indexLocation = null;
BufferedReader br = new BufferedReader(
new InputStreamReader(System.in));
String s = br.readLine();
TextFileIndexer indexer = null;
try {
indexLocation = s;
indexer = new TextFileIndexer(s);
} catch (Exception ex) {
System.out.println("Cannot create index..." + ex.getMessage());
System.exit(-1);
}
while (!s.equalsIgnoreCase("q")) {
try {
System.out.println("Enter the full path to add into the index (q=quit): (e.g. /home/ron/mydir or c:\Users\ron\mydir)");
System.out.println("[Acceptable file types: .xml, .html, .html, .txt]");
s = br.readLine();
if (s.equalsIgnoreCase("q")) {
break;
}
indexer.indexFileOrDirectory(s);
} catch (Exception e) {
System.out.println("Error indexing " + s + " : " + e.getMessage());
}
}
indexer.closeIndex();
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexLocation)));
IndexSearcher searcher = new IndexSearcher(reader);
TopScoreDocCollector collector = TopScoreDocCollector.create(5, true);
s = "";
while (!s.equalsIgnoreCase("q")) {
try {
System.out.println("Enter the search query (q=quit):");
s = br.readLine();
if (s.equalsIgnoreCase("q")) {
break;
}
Query q = new QueryParser(Version.LUCENE_40, "contents", analyzer).parse(s);
searcher.search(q, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
// 4. display results
System.out.println("Found " + hits.length + " hits.");
for(int i=0;i<hits.length;++i) {
int docId = hits[i].doc;
Document d = searcher.doc(docId);
System.out.println((i + 1) + ". " + d.get("path") + " score=" + hits[i].score);
}
} catch (Exception e) {
System.out.println("Error searching " + s + " : " + e.getMessage());
}
}
}
/**
* Constructor
* #param indexDir the name of the folder in which the index should be created
* #throws java.io.IOException when exception creating index.
*/
TextFileIndexer(String indexDir) throws IOException {
FSDirectory dir = FSDirectory.open(new File(indexDir));
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);
writer = new IndexWriter(dir, config);
}
/**
* Indexes a file or directory
* #param fileName the name of a text file or a folder we wish to add to the index
* #throws java.io.IOException when exception
*/
public void indexFileOrDirectory(String fileName) throws IOException {
addFiles(new File(fileName));
int originalNumDocs = writer.numDocs();
for (File f : queue) {
FileReader fr = null;
try {
Document doc = new Document();
fr = new FileReader(f);
doc.add(new TextField("contents", fr));
doc.add(new StringField("path", f.getPath(), Field.Store.YES));
doc.add(new StringField("filename", f.getName(), Field.Store.YES));
writer.addDocument(doc);
System.out.println("Added: " + f);
} catch (Exception e) {
System.out.println("Could not add: " + f);
} finally {
fr.close();
}
}
int newNumDocs = writer.numDocs();
System.out.println("");
System.out.println("************************");
System.out.println((newNumDocs - originalNumDocs) + " documents added.");
System.out.println("************************");
queue.clear();
}
private void addFiles(File file) {
if (!file.exists()) {
System.out.println(file + " does not exist.");
}
if (file.isDirectory()) {
for (File f : file.listFiles()) {
addFiles(f);
}
} else {
String filename = file.getName().toLowerCase();
if (filename.endsWith(".htm") || filename.endsWith(".html") ||
filename.endsWith(".xml") || filename.endsWith(".txt")) {
queue.add(file);
} else {
System.out.println("Skipped " + filename);
}
}
}
public void closeIndex() throws IOException {
writer.close();
}
}
p/s: English is not my mother tongue so please ignore my grammar or word mistake.

Answer 1

I have checked your code. Simply you must instantiate the TopScoreDocCollector in the cycle before the method search. Below a snippet of your code with the comments where I changed the code:
...
//REMOVE AND INSTANTIATE IN THE CYCLE! TopScoreDocCollector collector = TopScoreDocCollector.create ( 5, true );
s = "";
while ( !s.equalsIgnoreCase ( "q" ) ) {
try {
System.out.println ( "Enter the search query (q=quit):" );
s = br.readLine ();
if ( s.equalsIgnoreCase ( "q" ) ) {
break;
}
// INTANTIATE HERE!!!
TopScoreDocCollector collector = TopScoreDocCollector.create ( 5, true );
Query q = new QueryParser ( Version.LUCENE_40, "contents", analyzer ).parse ( s );
searcher.search ( q, collector );
...
Otherwise you can use another signature of the method search and remove definitely the explicit instance of TopScoreDocCollector. For example:
TopDocs topDocs = searcher.search ( q, 5);
ScoreDoc[] hits = topDocs.scoreDocs;
I think you can solve your problem.