Hi,
currently i created a lucene project and currently having a problem with the codes. Here are my codes (which i also refer to some useful websites explain lucene)
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.index.*;
import java.io.*;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.Scanner;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.search.Hit;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.RAMDirectory;
/**
* This terminal application creates an Apache Lucene index in a folder and adds files into this index
* based on the input of the user.
*/
public class TextFileIndexer {
//declare all the fields
public static final String FIELD_PATH = "path";
public static final String FIELD_CONTENTS = "contents";
public static final String FIELD_ID = "docno";
public static final String FIELD_DATE = "date";
private IndexWriter writer;
private ArrayList<File> queue = new ArrayList<File>();
@SuppressWarnings("static-access")
public static void main(String[] args) throws IOException, ParseException {
String s = null;
Scanner sc = new Scanner(System.in);
//Menu selections
int choice;
do {
System.out.println("Welcome Search Engine. Please choose" + " your selections below\n" + "(1) Build index collection\n" + "(2) Search for the documents ids\n" + "(3) Exit\n");
System.out.print("Enter your choice: ");
choice = sc.nextInt();
//switch statements
switch (choice) {
case 1:
System.out.println("Enter the path where the index will be created: ");
BufferedReader br = new BufferedReader(
new InputStreamReader(System.in));
s = br.readLine();
TextFileIndexer indexer = null;
try {
indexer = new TextFileIndexer(s);
} catch (Exception ex) {
System.out.println("Cannot create index..." + ex.getMessage());
System.exit(-1);
}
try {
System.out.println("Enter the file or folder name to add into the index (q=quit):");
System.out.println("[Acceptable file types: .xml, .html, .html, .txt]");
s = br.readLine();
//try to add file into the index
indexer.indexFileOrDirectory(s);
} catch (Exception e) {
System.out.println("Error indexing " + s + " : " + e.getMessage());
}
indexer.closeIndex();
break;
case 2:
System.out.println("your query?");
br = new BufferedReader(
new InputStreamReader(System.in));
String a = br.readLine();
searchIndex(a);
break;
case 3:
//exit the program
System.out.println("Program exiting..");
break;
default:
//display invalid selection
System.err.println("Err: Invalid selection");
}
} while (choice != 3);
}
public TextFileIndexer(String index) throws IOException, ParseException {
// the boolean true parameter means to create a new index everytime,
// potentially overwriting any existing files there.
writer = new IndexWriter(index, new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
}
public static void searchIndex(String words) throws IOException, ParseException{
System.out.println("Searching for '" + words + "'" );
Directory directory = FSDirectory.getDirectory(INDEX_COLLECTION);
IndexReader indexReader = IndexReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);
Analyzer analyzer = new StandardAnalyzer();
QueryParser queryParser = new QueryParser(FIELD_ID, analyzer);
Query query = queryParser.parse(words);
Hits hits = indexSearcher.search(query);
System.out.println("Number of hits: " + hits.length());
Iterator<Hit> it = hits.iterator();
while (it.hasNext()) {
Hit hit = it.next();
Document document = hit.getDocument();
String text = document.get(FIELD_ID);
System.out.println("Hit: " + text);
}
}
public void indexFileOrDirectory(String fileName) throws IOException {
listFiles(new File(fileName));
int originalNumDocs = writer.numDocs();
for (File file : queue) {
FileReader fr = null;
try {
Document doc = new Document();
fr = new FileReader(file);
doc.add(new Field(FIELD_CONTENTS, fr));
String path = file.getCanonicalPath();
doc.add(new Field(FIELD_PATH, path, Field.Store.YES, Field.Index.UN_TOKENIZED));
String docno = file.getName();
doc.add(new Field(FIELD_ID, docno, Field.Store.YES, Field.Index.UN_TOKENIZED));
String date = file.getPath();
doc.add(new Field(FIELD_DATE, date, Field.Store.YES, Field.Index.UN_TOKENIZED));
writer.addDocument(doc);
System.out.println("Added: " + file);
} catch (Exception e) {
System.out.println("Could not add: " + file);
} 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 listFiles(File file) {
if (!file.exists()) {
System.out.println(file + " does not exist.");
}
if (file.isDirectory()) {
for (File f : file.listFiles()) {
listFiles(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.optimize();
writer.close();
}
}highlighted in red is the issue here, I would like to get the directory of the files and subfiles of from the index that i just built. do give a feedback or suggestions. Thanks.