We Keep Coding

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();}}

Why indexer doesn't search Persian files?

I use lucene 3 for indexing some txt file like this.
public static void main(String[] args) throws Exception {
String indexDir = "file input";
String dataDir = "file input";
long start = System.currentTimeMillis();
indexer indexer = new indexer(indexDir);
int numIndexed, cnt;
try {
numIndexed = indexer.index(dataDir, new TextFilesFilter());
cnt = indexer.getHitCount("mycontents", "شهردار");
System.out.println("count of search in contents: " + cnt);
} finally {
indexer.close();
}
long end = System.currentTimeMillis();
System.out.println("Indexing " + numIndexed + " files took "
+ (end - start) + " milliseconds");
}
getHitCount function returns number of hits by an English word but by Persian word, it returns zero!
public int getHitCount(String fieldName, String searchString)
throws IOException, ParseException {
IndexSearcher searcher = new IndexSearcher(directory);
Term t = new Term(fieldName, searchString);
Query query = new TermQuery(t);
int hitCount = searcher.search(query, 1).totalHits;
searcher.close();
return hitCount;
}
How to set utf-8 in my project? I use netbeans and create a simple java project.
I just need a simple search in files!
It's my indexer class:
private IndexWriter writer;
private Directory directory;
public indexer(String indexDir) throws IOException {
directory = FSDirectory.open(new File(indexDir));
writer = new IndexWriter(directory,
new StandardAnalyzer(
Version.LUCENE_30),
true,
IndexWriter.MaxFieldLength.UNLIMITED);
}
public void close() throws IOException {
writer.close();
}
public int index(String dataDir, FileFilter filter)
throws Exception {
File[] files = new File(dataDir).listFiles();
for (File f : files) {
if (!f.isDirectory()
&& !f.isHidden()
&& f.exists()
&& f.canRead()
&& (filter == null || filter.accept(f))) {
indexFile(f);
}
}
return writer.numDocs();
}
private static class TextFilesFilter implements FileFilter {
public boolean accept(File path) {
return path.getName().toLowerCase()
.endsWith(".txt");
}
}
protected Document getDocument(File f) throws Exception {
Document doc = new Document();
doc.add(new Field("mycontents", new FileReader(f)));
doc.add(new Field("filename", f.getName(),
Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("fullpath", f.getCanonicalPath(),
Field.Store.YES, Field.Index.NOT_ANALYZED));
return doc;
}
private void indexFile(File f) throws Exception {
System.out.println("Indexing " + f.getCanonicalPath());
Document doc = getDocument(f);
writer.addDocument(doc);
}

I suspect that the issue isn't Lucene's encoding, per se, but the FileReader. From the FileReader docs:
The constructors of this class assume that the default character encoding and the default byte-buffer size are appropriate.
The default character encoding is probably not appropriate, in this case.
Instead of:
doc.add(new Field("mycontents", new FileReader(f)));
try (assuming the file to be indexed is UTF-8 encoded):
doc.add(new Field("mycontents", new InputStreamReader(new FileInputStream(f), "UTF8")));

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.

PhraseQuery Not working Lucene 4.5.0

I tried to work with PhraseQuery but could not get hits from search. I am using Lucene 4.5.0.
My Indexing code
private IndexWriter writer;
public LuceneIndexSF(final String indexDir) throws IOException {
Analyzer analyzer = new KeywordAnalyzer();
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_45,
analyzer);
Directory directory = FSDirectory.open(new File(indexDir));
writer = new IndexWriter(directory, config);
}
private Document getDocument(File f, String line, int lineNum)
throws IOException {
Document doc = new Document();
Field field = null;
if (line != null && line.split(DELIMITER).length >= 5) {
String[] lineValues = line.split(DELIMITER);
field = new Field("name", line.split("\t")[1],
TextField.TYPE_STORED);
doc.add(field);
if (lineValues[2] != null && !lineValues[2].trim().isEmpty()) {
field = new Field("ref", lineValues[2], TextField.TYPE_STORED);
doc.add(field);
}
field = new Field("type", lineValues[3], TextField.TYPE_STORED);
doc.add(field);
field = new LongField("code", Long.parseLong(lineValues[4]),
LongField.TYPE_STORED);
doc.add(field);
if (lineValues.length == 7 && lineValues[5] != null
&& !lineValues[5].trim().isEmpty()) {
field = new Field("alias1", lineValues[5],
TextField.TYPE_STORED);
doc.add(field);
}
if (lineValues.length == 7 && lineValues[6] != null
&& !lineValues[6].trim().isEmpty()) {
field = new Field("alias2", lineValues[6],
TextField.TYPE_STORED);
doc.add(field);
}
}
field = new IntField("linenum", lineNum, IntField.TYPE_STORED);
doc.add(field);
return doc;
}
.... and other code where i add document in writer using writer.addDocument(doc);
My Searching Code
private static void search(String indexDir, String quer) throws IOException,
ParseException {
IndexReader inxRead = DirectoryReader.open(FSDirectory.open(new File(
indexDir)));
IndexSearcher is = new IndexSearcher(inxRead);
String[] termArr = quer.split(" ");
PhraseQuery phraseQuery= new PhraseQuery();
for(int inx = 0; inx < termArr.length; inx++){
phraseQuery.add(new Term("name", termArr[inx]));
}
phraseQuery.setSlop(4);
long start = System.currentTimeMillis();
TopDocs hits = is.search(phraseQuery, 1000);
long end = System.currentTimeMillis();
System.err.println("Parser> Found " + hits.totalHits
+ " document(s) (in " + (end - start)
+ " milliseconds) that matched query '" + multiQuery + "':");
for (ScoreDoc scoreDoc : hits.scoreDocs) {
Document doc = is.doc(scoreDoc.doc);
System.out.println("Parser> " + scoreDoc.score + " :: "
+ doc.get("type") + " - " + doc.get("code") + " - "
+ doc.get("name") + ", " + doc.get("linenum"));
}
inxRead.close();
}
Please tell me if i am doing any thing wrong.
Edit
also tried with Standard Analyzer still not results
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);
Solution
According to Arun's answer PhraseQuery to work properly requires Analyzer which Tokenize each word in Document's Field for my case i used LowerCaseFilter with making all queries lower case so that it can work without case sensitivity. And used EdgeNGramTokenFilter which for auto completion purposes.
public LuceneIndexSF(final String indexDir) throws IOException {
Analyzer analyzer = new Analyzer() {
#Override
protected TokenStreamComponents createComponents(String fieldName,
java.io.Reader reader) {
Tokenizer source = new StandardTokenizer(Version.LUCENE_45,
reader);
TokenStream result = new StandardFilter(Version.LUCENE_45,
source);
result = new LowerCaseFilter(Version.LUCENE_45, result);
result = new EdgeNGramTokenFilter(Version.LUCENE_45, result, 1,
20);
return new TokenStreamComponents(source, result);
}
};
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_45,
analyzer);
Directory directory = FSDirectory.open(new File(indexDir));
writer = new IndexWriter(directory, config);
}
My final search method
private static void search(String indexDir, String quer) throws IOException,
ParseException {
IndexReader inxRead = DirectoryReader.open(FSDirectory.open(new File(
indexDir)));
IndexSearcher is = new IndexSearcher(inxRead);
String[] termArr = quer.split(" ");
PhraseQuery query1 = new PhraseQuery();
PhraseQuery query2 = new PhraseQuery();
PhraseQuery query3 = new PhraseQuery();
for (int inx = 0; inx < termArr.length; inx++) {
query1.add(new Term(SchoolFinderConstant.ENTITY_NAME,termArr[inx]),inx);
query2.add(new Term(SchoolFinderConstant.ENTITY_ALIAS1,termArr[inx]),inx);
query3.add(new Term(SchoolFinderConstant.ENTITY_ALIAS2,termArr[inx]),inx);
}
BooleanQuery mainQuery = new BooleanQuery();
mainQuery.add(query1, Occur.SHOULD);
mainQuery.add(query2, Occur.SHOULD);
mainQuery.add(query3, Occur.SHOULD);
long start = System.currentTimeMillis();
TopDocs hits = is.search(mainQuery, 1000);
long end = System.currentTimeMillis();
System.err.println("Parser> Found " + hits.totalHits
+ " document(s) (in " + (end - start)
+ " milliseconds) that matched query '" + multiQuery + "':");
for (ScoreDoc scoreDoc : hits.scoreDocs) {
Document doc = is.doc(scoreDoc.doc);
System.out.println("Parser> " + scoreDoc.score + " :: "
+ doc.get("type") + " - " + doc.get("code") + " - "
+ doc.get("name") + ", " + doc.get("linenum"));
}
inxRead.close();
}

I played with your code with KeywordAnalyzer, obviously it did not work as the KeywordAnalyzer "Tokenizes" the entire stream as a single token. This is useful for data like zip codes, ids, and some product names. http://lucene.apache.org/core/4_5_0/analyzers-common/org/apache/lucene/analysis/core/KeywordAnalyzer.html , for this to work you need to specify entire token without any change.
Then i used WhitespaceAnalyzer it worked and able to find matches for your PhraseQuery. No change to rest of the code. Let me know if this worked for you.
The reason search worked with MultiFieldQueryParser is you are forced to use the analyzer at the time of query which matches to your index. So in short , you need to make sure your index analyzer and query time analyzers are similar.