We Keep Coding

Lucene what i can replace iterator in metod?

I have an idea:
looking for a pattern in the text,
if I found a pattern, then I want to take its position from the text.
Now i have 1.
Part 2 done, but it use iterator, it's this means that we will go through all terms before we get to the template I need, how can i get my term right away and possition ones of text?
My code:
public void methodFromStack() throws Exception {
Directory directory = new RAMDirectory();
IndexWriterConfig indexWriterConfig = new IndexWriterConfig(new StandardAnalyzer());
IndexWriter writer = new IndexWriter(directory, indexWriterConfig);
Document doc = new Document();
// Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES
FieldType type = new FieldType();
type.setStoreTermVectors(true);
type.setStoreTermVectorPositions(true);
type.setStoreTermVectorOffsets(true);
type.setStored(true);
type.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
Field fieldStore = new Field("tags", "Kite good world.", type);
doc.add(fieldStore);
writer.addDocument(doc);
writer.close();
DirectoryReader reader = DirectoryReader.open(directory);
IndexSearcher searcher = new IndexSearcher(reader);
//Поиск по словосочетанию с учетом отступа
QueryParser queryParser = new QueryParser("tags", new StandardAnalyzer());
Query query = queryParser.parse("\"Kite World\"~1");
TopDocs results = searcher.search(query, 1);
for ( ScoreDoc scoreDoc : results.scoreDocs) {
Fields termVs = reader.getTermVectors(scoreDoc.doc);
Terms f = termVs.terms("tags");
TermsEnum te = f.iterator();
PostingsEnum docsAndPosEnum = null;
BytesRef bytesRef;
//Here iterator, output all terms, but i need get one my result term and possition
while ((bytesRef = te.next()) != null) {
docsAndPosEnum = te.postings(docsAndPosEnum, PostingsEnum.ALL);
// for each term (iterator next) in this field (field)
// iterate over the docs (should only be one)
int nextDoc = docsAndPosEnum.nextDoc();
assert nextDoc != DocIdSetIterator.NO_MORE_DOCS;
final int fr = docsAndPosEnum.freq();
final int p = docsAndPosEnum.nextPosition();
final int o = docsAndPosEnum.startOffset();
System.out.println("Word: " + bytesRef.utf8ToString());
System.out.println("Position: "+ p + ", startOffset: " + o + " length: "
+bytesRef.length + " Freg: " + fr);
if(fr > 1){
for(int iter = 1; iter <= fr-1; iter++) {
System.out.println("Possition: "+ docsAndPosEnum.nextPosition());
}
}
}
}
}
(I know that in the old version of the library Lucene there were class TermFreqVector and class TermPositionVector?, but then with the transition to the new version from 3 to 4 there were changes. After these changes, all I found was the adoption of an iterator.
Use: Windows+NetBeans+maven+Lucene 7.4.0)

The way to solve the problem: use the method seekExact and you can use that code to test:
TermsEnum te = f.iterator();
PostingsEnum docsAndPosEnum = null;
if (te.seekExact(ref)) {
docsAndPosEnum = te.postings(docsAndPosEnum, PostingsEnum.ALL);
int nextDoc = docsAndPosEnum.nextDoc();
assert nextDoc != DocIdSetIterator.NO_MORE_DOCS;
final int freg = docsAndPosEnum.freq();
final int pos = docsAndPosEnum.nextPosition();
final int o = docsAndPosEnum.startOffset();
System.out.println("Word: " + ref.utf8ToString());
System.out.println("Position: " + pos + ", startOffset: " + o + " length: " + ref.length + " Freg: " + freg);

Lucene issues in indexing processus

I have a problem with lucene indexing, my documments conains TEXT and FIELD and DocNO. AND my queries containt Title and description. I have a Judgment of relevance. the problem is when i have calculating the MAP, it is very small (0.017). however my frieds have fiding a value of 0.13. I think that i have a problrm with IndexFiles class?? can you help me ? ^-^
public class IndexFiles {
public IndexFiles() {}
public static void main(String[] args) throws IOException, ParseException {
ReadDocuments t = new ReadDocuments();
List<DocumentsParser> docs = new ArrayList<>();
t.readXml(docs, "documents");
final String FIELD_PATH = "path";
final String FIELD_CONTENTS = "contents";
String indexPath = "index1";
Directory dir = FSDirectory.open(new File(indexPath));
Reader r=new FileReader(new File("stopwords.txt"));
StandardAnalyzer analyzer=new StandardAnalyzer(Version.LUCENE_40,r);
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_40,analyzer);
/* use BM25 similarity*/
Similarity bm25similarity = new BM25Similarity();
iwc.setSimilarity(bm25similarity);
IndexWriter indexWriter = new IndexWriter(dir, iwc);
for (DocumentsParser doc : docs){
Document document = new Document();
document.add(new StringField("DocNo", doc.getDOCNO(), Field.Store.YES));
document.add(new TextField("TEXT", doc.getTEXT()+" "+doc.getHEAD(),Field.Store.YES));
indexWriter.addDocument(document); }
indexWriter.close();}}
/class SearchFiles/
public class SearchFiles {
public static void main(String[] args) throws Exception {
SearchFiles ch=new SearchFiles();
searchStemTfidfQLong();
}
SearchFiles() {}
public static void searchStemTfidfQLong() throws ParseException, IOException{
String index = "index1";
String field = "TEXT";
int hitsPerPage = 1000;
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
IndexSearcher searcher = new IndexSearcher(reader);
/* use BM25 similarity*/
Similarity bm25similarity = new BM25Similarity();
searcher.setSimilarity(bm25similarity);
Reader r=new FileReader(new File("stopwords.txt"));
StandardAnalyzer analyzer=new StandardAnalyzer(Version.LUCENE_40,r);
QueryParser parser = new QueryParser(Version.LUCENE_40,field,analyzer);
int i=0;
File file = new File("fichier.txt");
FileWriter writere=new FileWriter(file.getAbsoluteFile(), true);
for(Topic topic : Parser.getQuerysTopics(Parser.filename)){
/*query chort*/
String queryChort=topic.getTitle();
queryChort=queryChort.replaceAll("([<>\\(\\):/\\\\',\\s\"])", " ").trim();
i++;
//writere.write(queryChort+"\n");
Query query = parser.parse(queryChort);
System.out.println("Query number : "+(i));
searcher.search(query,1000);
doSearch(i, searcher, query, hitsPerPage);
}
reader.close();
writere.close();
}
public static void doSearch(int idReq, IndexSearcher searcher, Query query, int hitsPerPage) throws IOException {
TopDocs results = searcher.search(query, null, hitsPerPage);
System.out.println(query);
ScoreDoc[] hits = results.scoreDocs;
int numTotalHits = results.totalHits;
System.out.println(numTotalHits + " total matching documents");
int start = 1;
int end = Math.min(numTotalHits, hitsPerPage);
File file = new File("file.txt");
FileWriter writer=new FileWriter(file.getAbsoluteFile(), true);
File file1 = new File("fichier.txt");
FileWriter writere=new FileWriter(file1.getAbsoluteFile(), true);
for (int i = start; i < end; i++) {
Document doc = searcher.doc(hits[i].doc);
String DocNo = doc.get("DocNo");
writere.write(DocNo+"\n");
if (DocNo != null) {
writer.write(idReq+" 0 "+DocNo+" "+String.format("%.6f", new Double(hits[i].score))+" "+ i + " "+"ScoreID"+"\n");
} else {
System.out.println((i + 1) + ". " + "No DocNo for this document"); } }
writer.close();
writere.close();}}

How does regex query work on lucene?

I am trying to implement luecene search engine in my application.
I am using lucene 5.4.1
I have successfully implemented wildequeries and normal queries of lucene.
But my main focus is to search specific text in a text file with regex patterns.
Index Writer code:
public IndexWriter generateIndex(String docsPath) throws IOException {
String indexPath = System.getProperty("java.io.tmpdir") +File.separator+"indexDirectory";
if (indexPath == null) {
throw new IOException("System property 'java.io.tmpdir' does not specify a tmp dir");
}
File tmpDir = new File(indexPath);
if (!tmpDir.exists()) {
boolean created = tmpDir.mkdirs();
if (!created) {
throw new IOException("Unable to create tmp dir " + tmpDir);
}
}
boolean create = true;
final Path docDir = Paths.get(docsPath);
if (!Files.isReadable(docDir)) {
System.out.println("Document directory '" + docDir.toAbsolutePath()
+ "' does not exist or is not readable, please check the path");
System.exit(1);
}
Date start = new Date();
try {
System.out.println("Indexing to directory '" + indexPath + "'...");
Directory dir = FSDirectory.open(Paths.get(indexPath));
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
if (create) {
iwc.setOpenMode(OpenMode.CREATE);
} else {
iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
}
IndexWriter writer = new IndexWriter(dir, iwc);
indexDocs(writer, docDir);
setIndexWriter(writer);
Date end = new Date();
System.out.println(end.getTime() - start.getTime() + " total milliseconds");
writer.close();
} catch (IOException e) {
System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
}
return getIndexWriter();
}
static void indexDocs(final IndexWriter writer, Path path) throws IOException {
if (Files.isDirectory(path)) {
Files.walkFileTree(path, new SimpleFileVisitor<Path>() {
#Override
public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
try {
indexDoc(writer, file, attrs.lastModifiedTime().toMillis());
} catch (IOException ignore) {
// don't index files that can't be read.
}
return FileVisitResult.CONTINUE;
}
});
} else {
indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
}
}
static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
try (InputStream stream = Files.newInputStream(file)) {
Document doc = new Document();
Field pathField = new StringField("path", file.toString(), Field.Store.NO);
doc.add(pathField);
doc.add(new LongField("modified", lastModified, Field.Store.NO));
doc.add(new TextField("contents",
new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));
if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
System.out.println("adding " + file);
writer.addDocument(doc);
} else {
System.out.println("updating " + file);
writer.updateDocument(new Term("path", file.toString()), doc);
}
}
}
Index Searching Code:
public IndexReader searchExecutor(String index, String queryString, RegexCapabilities capability) throws Exception {
String field = "contents";
String queries = null;
boolean raw = false;
int hitsPerPage = Integer.MAX_VALUE;
IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
IndexSearcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new StandardAnalyzer();
BufferedReader in = null;
Query q = new RegexpQuery(new Term("text", queryString));
q = q.rewrite(reader);
RegexQuery query = new RegexQuery(new Term("\\s*(FIND|find)"));
if (capability != null)
query.setRegexImplementation(capability);
System.out.println("Searching for: " + query.toString(field));
searcher.search(query, null, 1000);
doSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);
//reader.close();
return reader;
}
public static void doSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage, boolean raw,
boolean interactive)
throws IOException {
TopDocs results = searcher.search(query, 5 * hitsPerPage);
ScoreDoc[] hits = results.scoreDocs;
//generateIndex.deleteDocuments(query);
//generateIndex.getDirectory();
// TermsEnum.totalTermFreq();
int numTotalHits = results.totalHits;
System.out.println(numTotalHits + " total matching documents");
int start = 0;
int end = Math.min(numTotalHits, hitsPerPage);
for (int i = start; i < end; i++) {
Document doc = searcher.doc(hits[i].doc);
String path = doc.get("path");
File file = new File(path);
if (path != null) {
System.out.println((i + 1) + ". " + path);
String title = doc.get("title");
if (title != null) {
System.out.println(" Title: " + doc.get("title"));
}
} else {
System.out.println((i + 1) + ". " + "No path for this document");
}
}
}
Please help.

Your question is about search with regular expressions in lucene.
You are using RegexQuery which is deprecated so try RegexpQuery
Your regEx-example starts with \s* but you do not use KeywordTokenizer. Most other tokenizer will remove (aka "split at") whitespace
Your regEx-example is not purely lower case. But standard analyzer contains LowerCaseFilter. Be aware: your regEx will go directly against the tokens of your index (not against the original text)
--> read Supported RegExp syntax and syntax in ES and TestRegexpRandom (test class) and play with https://github.com/DmitryKey/luke on your index.

Getting TF-IDF values from index

The below code is for getting tf-idf value from indexes. But I get an error while running it, on the line with Correct_ME.
Using Lucene 4.8.
DocIndexing.java
public class DocIndexing {
private DocIndexing() {}
/** Index all text files under a directory.
* #param args
* #throws java.io.IOException */
public static void main(String[] args) throws IOException {
String usage = "java org.apache.lucene.demo.IndexFiles"
+ " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
+ "This indexes the documents in DOCS_PATH, creating a Lucene index"
+ "in INDEX_PATH that can be searched with Searching";
String indexPath = "C:/Users/dell/Documents/NetBeansProjects/IndexingSearching/Index";
String docsPath = "C:/Users/dell/Documents/NetBeansProjects/IndexingSearching/ToBeIndexed";
boolean create = true;
for(int i=0;i<args.length;i++) {
if (null != args[i]) switch (args[i]) {
case "-index":
indexPath = args[i+1];
i++;
break;
case "-docs":
docsPath = args[i+1];
i++;
break;
case "-update":
create = false;
break;
}
}
if (docsPath == null) {
System.err.println("Usage: " + usage);
System.exit(1);
}
final File docDir = new File(docsPath);
if (!docDir.canRead() && !docDir.isDirectory() &&
!docDir.isHidden() &&
!docDir.exists()) {
System.out.println("Document directory '" +docDir.getAbsolutePath()+ "' does not exist or is not readable, please check the path");
System.exit(1);
}
Date start = new Date();
try {
System.out.println("Indexing to directory '" + indexPath + "'...");
Directory dir = FSDirectory.open(new File(indexPath));
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_48);
//Filter filter = new PorterStemFilter();
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_48, analyzer);
if (create) {
iwc.setOpenMode(OpenMode.CREATE);
} else {
// Add new documents to an existing index:
iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
}
try (
IndexWriter writer = new IndexWriter(dir, iwc)) {
indexDocs(writer, docDir);
}
Date end = new Date();
System.out.println(end.getTime() - start.getTime() + " total milliseconds");
} catch (IOException e) {
System.out.println(" caught a " + e.getClass() +
"\n with message: " + e.getMessage());
}
Tf_Idf tfidf = new Tf_Idf();
String field = null,term = null;
tfidf.scoreCalculator(field, term);
}
/*
* #param writer Writer to the index where the given file/dir info will be stored
* #param file The file to index, or the directory to recurse into to find files to index
* #throws IOException If there is a low-level I/O error
*/
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 {
FileInputStream fis;
try {
fis = new FileInputStream(file);
} catch (FileNotFoundException fnfe) {
return;
}
try {
// make a new, empty document
Document doc = new Document();
// Field termV = new LongField("termVector", file.g)
Field pathField = new StringField("path", file.getPath(), Field.Store.YES);
doc.add(pathField);
Field modifiedField = new LongField("modified", file.lastModified(), Field.Store.NO);
doc.add(modifiedField);
Field titleField = new TextField("title", file.getName(), Field.Store.YES);
doc.add(titleField);
Field contentsField = new TextField("contents", new BufferedReader(new InputStreamReader(fis, StandardCharsets.UTF_8)));
doc.add(contentsField);
//contentsField.setBoost((float)0.5);
//titleField.setBoost((float)2.5);
/* doc.add(new LongField("modified", file.lastModified(), Field.Store.NO));
doc.add(new TextField("title", file.getName(), Field.Store.YES));
doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(fis, StandardCharsets.UTF_8))));
*/
// StringField..setBoost(1.2F);
if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
// New index, so we just add the document (no old document can be there):
System.out.println("adding " + file);
writer.addDocument(doc);
} else {
// Existing index (an old copy of this document may have been indexed) so
// we use updateDocument instead to replace the old one matching the exact
// path, if present:
System.out.println("updating " + file);
writer.updateDocument(new Term("path", file.getPath()), doc);
}
} finally {
fis.close();
}
}
}
}
}
Tf-idf.java
public class Tf_Idf {
static float tf = 1;
static float idf = 0;
private float tfidf_score;
static float [] tfidf = null;
IndexReader indexReader;
public Tf_Idf() throws IOException {
this.indexReader = DirectoryReader.open(FSDirectory.open(new File("C:/Users/dell/Documents/NetBeansProjects/IndexingSearching/Index")));
}
public void scoreCalculator (String field, String term) throws IOException
{
TFIDFSimilarity tfidfSIM = new DefaultSimilarity();
Bits liveDocs = MultiFields.getLiveDocs(indexReader);
TermsEnum termEnum = MultiFields.getTerms(indexReader, field).iterator(null);
BytesRef bytesRef=null;
while ((bytesRef = termEnum.next()) != null) {
if(bytesRef.utf8ToString().trim().equals(term.trim())) {
if(termEnum.seekExact(bytesRef)) {
idf = tfidfSIM.idf(termEnum.docFreq(), indexReader.numDocs());
DocsEnum docsEnum = termEnum.docs(liveDocs, null);
if(docsEnum != null) {
int doc=0;
while((doc = docsEnum.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
tf = tfidfSIM.tf(docsEnum.freq());
tfidf_score = tf * idf ;
System.out.println(" -tfidf_score-" + tfidf_score);
}
}
}
}
}
}
}

It's obvious that you pass to MultiFields method a null IndexReader
IndexReader reader = null;
tfidf.scoreCalculator( reader, field,term);
You need to write something like this:
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(PATH_TO_LUCENE_INDEX)));
tfidf.scoreCalculator( reader, field,term);
You need to repalce PATH_TO_LUCENE_INDEX with real path, of course.
Another problem, that I see - you open IndexReader in Tf_Idf, but don't use it anywhere, may be it's a good idea to remove it or use it, inside of scoreCalculator method, e.g.
tfidf.scoreCalculator(field,term);
but in method use field of this class, - this.indexReader instead of just indexReader that you try to pass inside method scoreCalculator
UPD
public Tf_Idf() throws IOException {
this.reader = DirectoryReader.open(FSDirectory.open(new File("Index")));
}
In this code, you need to replace "Index" with real path to your Lucene index, e.g. - /home/user/index or C://index or wherever you have it.

Creating a jsp search form to run a java Search program

The background info here is that I have a working Indexer and Search (in java) that indexes and searches a file directory for the filenames and then copies the files to a "Results" Directory.
What I need/ don't have much experience in is writing jsp files. I need the jsp file to have a search bar for the text and then a search button. When text is entered in the bar, and the button is clicked, I need it to run my search program with the entered text as an arg.
I have added the IndexFiles and the SearchFiles classes for reference.
Please explain with a good example if you can help out!
public class SearchFiles {
static File searchDirectory = new File(
"C:\\Users\\flood.j.2\\Desktop\\IndexSearch\\Results");
static String v = new String();
static String path = null;
String title = null;
File addedFile = null;
OutputStream out = null;
String dirName = "C:\\Users\\flood.j.2\\Desktop\\IndexSearch\\Results";
public static void main(String[] args) throws Exception {
String usage = "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string]";
if (args.length > 0
&& ("-h".equals(args[0]) || "-help".equals(args[0]))) {
System.out.println(usage);
System.exit(0);
}
for (int j = 5; j < args.length; j++) {
v += args[j] + " ";
}
String index = "index";
String field = "contents";
String queries = null;
boolean raw = false;
String queryString = null;
int hits = 100;
for (int i = 0; i < args.length; i++) {
if ("-index".equals(args[i])) {
index = args[i + 1];
i++;
} else if ("-field".equals(args[i])) {
field = args[i + 1];
i++;
} else if ("-queries".equals(args[i])) {
queries = args[i + 1];
i++;
} else if ("-query".equals(args[i])) {
queryString = v;
i++;
}
}
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(
index)));
IndexSearcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);
BufferedReader in = null;
if (queries != null) {
in = new BufferedReader(new InputStreamReader(new FileInputStream(
queries), "UTF-8"));
} else {
in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
}
QueryParser parser = new QueryParser(Version.LUCENE_40, field, analyzer);
for (int m = 0; m < 2; m++) {
if (queries == null && queryString == null) {
System.out.println("Enter query: ");
}
String line = queryString != null ? queryString : in.readLine();
if (line == null || line.length() == -1) {
break;
}
line = line.trim();
if (line.length() == 0) {
break;
}
Query query = parser.parse(line);
System.out.println("Searching for: " + query.toString(field));
doPagingSearch(in, searcher, query, hits, raw, queries == null
&& queryString == null);
if (queryString == null) {
break;
}
}
reader.close();
}
public static void doPagingSearch(BufferedReader in,
IndexSearcher searcher, Query query, int hitsPerPage, boolean raw,
boolean interactive) throws IOException {
// Collect enough docs to show 500 pages
TopDocs results = searcher.search(query, 5 * hitsPerPage);
ScoreDoc[] hits = results.scoreDocs;
int numTotalHits = results.totalHits;
System.out.println(numTotalHits + " total matching documents");
int start = 0;
int end = Math.min(numTotalHits, hitsPerPage);
FileUtils.deleteDirectory(searchDirectory);
while (true) {
for (int i = start; i < end; i++) {
Document doc = searcher.doc(hits[i].doc);
path = doc.get("path");
if (path != null) {
System.out.println((i + 1) + ". " + path);
File addFile = new File(path);
try {
FileUtils.copyFileToDirectory(addFile, searchDirectory);
} catch (IOException e) {
e.printStackTrace();
}
}
}
if (!interactive || end == 0) {
break;
}
System.exit(0);
}
}
}
public class IndexFiles {
private IndexFiles() {
}
public static void main(String[] args) {
String usage = "java org.apache.lucene.demo.IndexFiles"
+ " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
+ "This indexes the documents in DOCS_PATH, creating a Lucene index"
+ "in INDEX_PATH that can be searched with SearchFiles";
String indexPath = null;
String docsPath = null;
boolean create = true;
for (int i = 0; i < args.length; i++) {
if ("-index".equals(args[i])) {
indexPath = args[i + 1];
i++;
} else if ("-docs".equals(args[i])) {
docsPath = args[i + 1];
i++;
} else if ("-update".equals(args[i])) {
create = false;
}
}
if (docsPath == null) {
System.err.println("Usage: " + usage);
System.exit(1);
}
final File docDir = new File(docsPath);
if (!docDir.exists() || !docDir.canRead()) {
System.out
.println("Document directory '"
+ docDir.getAbsolutePath()
+ "' does not exist or is not readable, please check the path");
System.exit(1);
}
Date start = new Date();
try {
System.out.println("Indexing to directory '" + indexPath + "'...");
Directory dir = FSDirectory.open(new File(indexPath));
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_40,
analyzer);
if (create) {
iwc.setOpenMode(OpenMode.CREATE);
} else {
iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
}
IndexWriter writer = new IndexWriter(dir, iwc);
indexDocs(writer, docDir);
writer.close();
Date end = new Date();
System.out.println(end.getTime() - start.getTime()
+ " total milliseconds");
} catch (IOException e) {
System.out.println(" caught a " + e.getClass()
+ "\n with message: " + e.getMessage());
}
}
static void indexDocs(IndexWriter writer, File file) throws IOException {
if (file.canRead()) {
if (file.isDirectory()) {
String[] files = file.list();
if (files != null) {
for (int i = 0; i < files.length; i++) {
indexDocs(writer, new File(file, files[i]));
}
}
} else {
FileInputStream fis;
try {
fis = new FileInputStream(file);
} catch (FileNotFoundException fnfe) {
return;
}
try {
Document doc = new Document();
Field pathField = new StringField("path",
file.getAbsolutePath(), Field.Store.YES);
doc.add(pathField);
doc.add(new LongField("modified", file.lastModified(),
Field.Store.NO));
doc.add(new TextField("title", file.getName(), null));
System.out.println(pathField);
if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
System.out.println("adding " + file);
writer.addDocument(doc);
} else {
System.out.println("updating " + file);
writer.updateDocument(new Term("path", file.getPath()),
doc);
}
} finally {
fis.close();
}
}
}
}
}

First, you should definitely do this in a servlet rather than a JSP. Putting lots of logic in JSP is bad practice. (See the servlets info page).
Second, it would probably be better on performance to make a cronjob (Linux) or Task (Windows) to run the search program every hour and store the results in a database and just have your servlet pull from there rather than allow the user to initiate the search program.