Super-cursory look over the code... the following doesn't look good:
try {
writer.addDocument(FileDocument.Document(file));
}
// at least on windows, some temporary files raise this
exception with an "access denied" message
// checking if the file can be read doesn't help
catch (FileNotFoundException fnfe) {
;
}
Who knows, maybe some files are skipped here. Code that comes with
Lucene in Action includes a working file indexer application. You can
get the code from lucenebook.com.
Otis
--- Sushil Sureka <[EMAIL PROTECTED]> wrote:
> I am trying to learn Lucene by going through tutorials and article. I
> took a sample program and modified it a little to index all the file
> names on my local file system to allow me to search for a file
> quickly.
>
> I am not sure what's happening, for some file names the search is
> working where as for others it does not work. I had let the program
> run all the way to the end meaning I am sure it should have indexed
> all the files on my local hard drive. Is there a way to debug the
> issue in any way. The sample programs are attached.
>
> --
> Thanks
> Sushil
>
>
>
>
> --
> Thanks
> Sushil
> >
> import java.io.File;
> import java.io.Reader;
> import java.io.FileInputStream;
> import java.io.BufferedReader;
> import java.io.InputStreamReader;
>
> import org.apache.lucene.document.Document;
> import org.apache.lucene.document.Field;
> import org.apache.lucene.document.DateField;
> import org.apache.lucene.index.Term;
> import org.apache.lucene.search.*;
>
> /** A utility for making Lucene Documents from a File. */
>
> public class FileDocument {
>
> public static Document Document(File f)
> throws java.io.FileNotFoundException {
>
> // make a new, empty document
> Document doc = new Document();
>
> doc.add(Field.Text("path", f.getPath()));
> doc.add(Field.Text("filename", f.getName()));
>
> return doc;
> }
>
> private FileDocument() {
> }
> }
>
>
> >
> import java.io.File;
> import java.io.FileNotFoundException;
> import java.io.IOException;
> import java.util.Date;
>
> import org.apache.lucene.analysis.WhitespaceAnalyzer;
> import org.apache.lucene.index.IndexWriter;
>
> class FileNameIndexer {
> public static void main(String[] args) throws IOException {
> String usage = "java " + FileNameIndexer.class + "
> <root_directory>";
> if (args.length == 0) {
> System.err.println("Usage: " + usage);
> System.exit(1);
> }
>
> Date start = new Date();
> try {
> IndexWriter writer = new IndexWriter("filepath", new
> WhitespaceAnalyzer(), true);
> indexDocs(writer, new File(args[0]));
>
> writer.optimize();
> writer.close();
>
> Date end = new Date();
>
> System.out.print(end.getTime() - start.getTime());
> System.out.println(" total milliseconds");
>
> } catch (IOException e) {
> System.out.println(" caught a " + e.getClass() +
> "\n with message: " + e.getMessage());
> }
> }
>
> public static void indexDocs(IndexWriter writer, File file)
> throws IOException {
> // do not try to index files that cannot be read
> if (file.canRead()) {
> if (file.isDirectory()) {
> String[] files = file.list();
> // an IO error could occur
> if (files != null) {
> for (int i = 0; i < files.length; i++) {
> indexDocs(writer, new File(file, files[i]));
> }
> }
> } else {
> try {
> writer.addDocument(FileDocument.Document(file));
> }
> // at least on windows, some temporary files raise this
> exception with an "access denied" message
> // checking if the file can be read doesn't help
> catch (FileNotFoundException fnfe) {
> ;
> }
> }
> }
> }
> }
>
> >
> import java.io.BufferedReader;
> import java.io.InputStreamReader;
>
> import org.apache.lucene.analysis.Analyzer;
> import org.apache.lucene.analysis.WhitespaceAnalyzer;
> import org.apache.lucene.analysis.standard.StandardAnalyzer;
> import org.apache.lucene.document.Document;
> import org.apache.lucene.index.Term;
> import org.apache.lucene.queryParser.QueryParser;
> import org.apache.lucene.search.*;
>
> class SearchFileName {
> public static void main(String[] args) {
> try {
> Searcher searcher = new IndexSearcher("filepath");
> BufferedReader in = new BufferedReader(new
> InputStreamReader(
> System.in));
> while (true) {
> System.out.print("filename: ");
> String line = in.readLine();
>
> if (line.length() == -1)
> break;
>
> System.out.println("line <<" + line + ">>");
> // Query query = new WildcardQuery(new
> Term("filename", line));
> Query query = QueryParser.parse(line, "filename", new
> StandardAnalyzer());
>
> Hits hits = searcher.search(query);
> System.out.println(hits.length() + " total matching
> documents");
>
> final int HITS_PER_PAGE = 10;
> for (int start = 0; start < hits.length(); start +=
> HITS_PER_PAGE) {
> int end = Math.min(hits.length(), start +
> HITS_PER_PAGE);
> for (int i = start; i < end; i++) {
> Document doc = hits.doc(i);
> String path = doc.get("path");
> if (path != null) {
> System.out.println(i + ". " + path);
> } else {
> System.out.println("file not found");
> }
> }
> if (hits.length() > end) {
> System.out.print("more (y/n) ? ");
> line = in.readLine();
> if (line.length() == 0 || line.charAt(0) ==
> 'n')
> break;
> }
> }
> if(hits.length() == 0)
> System.out.println("file " + line + " not found");
>
>
>
> }
> searcher.close();
>
> } catch (Exception e) {
> e.printStackTrace();
> System.out.println(" caught a " + e.getClass()
> + "\n with message: " + e.getMessage());
> }
> }
> }
>
> >
---------------------------------------------------------------------
> To unsubscribe, e-mail: [EMAIL PROTECTED]
> For additional commands, e-mail: [EMAIL PROTECTED]
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
