org.nuiton.topia.index.LuceneIndexer Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of topia-service-index Show documentation
Show all versions of topia-service-index Show documentation
Hibernate based index service
The newest version!
/* *##%
* ToPIA :: Service Index
* Copyright (C) 2004 - 2009 CodeLutin
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as
* published by the Free Software Foundation, either version 3 of the
* License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Lesser Public License for more details.
*
* You should have received a copy of the GNU General Lesser Public
* License along with this program. If not, see
* .
* ##%*/
/* *
* LuceneIndexer.java
*
* Created: 8 oct. 06 15:48:37
*
* @author poussin
* @version $Revision: 1459 $
*
* Last update: $Date: 2009-05-16 09:56:47 +0200 (Sat, 16 May 2009) $
* by : $Author: tchemit $
*/
package org.nuiton.topia.index;
import java.io.File;
import java.io.IOException;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;
import java.util.Properties;
import java.util.SortedSet;
import java.util.TreeSet;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.NIOFSDirectory;
import org.apache.lucene.util.Version;
import org.hibernate.HibernateException;
import org.hibernate.metadata.ClassMetadata;
import org.nuiton.topia.TopiaNotFoundException;
import org.nuiton.topia.framework.TopiaContextImplementor;
import org.nuiton.topia.persistence.TopiaId;
/**
* To use this indexer you must have two properties defined in config file:
* topia.index.engin=org.nuiton.topia.framework.LuceneIndexer
* topia.index.lucene.directory=[/path/to/index/directory]
*
* Pour l'utilisation:
*
* SortedSet<IndexEntry> result = context.getIndexEngin().search("quelque chose")
* SortedSet<IndexEntry> result = context.getIndexEngin().search("class:org.nuiton.chorem.entities.Person name:poussin")
* // ou equivalent avec une map
* Map m = new HashMap();
* m.put("class", "org.nuiton.chorem.entities.Person");
* m.put("name", "poussin");
* SortedSet<IndexEntry> result = context.getIndexEngin().search(m);
*
*
* @author poussin
*
*/
public class LuceneIndexer implements TopiaIndexImplementor {
/** to use log facility, just put in your code: log.info(\"...\"); */
static private Log log = LogFactory.getLog(LuceneIndexer.class);
private static final String TOPIA_ID = "topiaId";
protected File directory = null;
protected TopiaContextImplementor context;
/** contient les objets a reindexer car creer, modifier ou supprimer. key: id, value: fields values or null for deletion */
protected Map indexationMap = new HashMap();
/*
* @see org.nuiton.topia.framework.TopiaService#getServiceName()
*/
@Override
public String getServiceName() {
return TopiaIndexService.SERVICE_NAME;
}
/*
* @see org.nuiton.topia.framework.TopiaService#getPersistenceClasses()
*/
@Override
public Class[] getPersistenceClasses() {
return null;
}
@Override
public void recordForIndexation(Object id, Object[] fields) {
if (id == null) {
log.warn("Id must not be null, this object will be not indexed");
} else {
indexationMap.put(id, fields);
}
}
/*
* @see org.nuiton.topia.framework.TopiaService#init(org.nuiton.topia.framework.TopiaContextImplementor)
*/
@Override
public boolean preInit(TopiaContextImplementor context) {
return true;
}
@Override
public boolean postInit(TopiaContextImplementor context) {
this.context = context;
Properties prop = context.getConfig();
String dirname = prop.getProperty("topia.index.lucene.directory");
directory = new File(dirname);
directory.mkdirs();
return true;
}
@Override
public void clearLastRecordedIndexation() {
indexationMap.clear();
}
@Override
public void doIndexation() {
try {
Directory indexDirectory = new NIOFSDirectory(directory);
// TODO maybe put in configuration to allow localized analysers
Analyzer analyzer = new SimpleAnalyzer();
boolean create = false;
if (!IndexReader.indexExists(indexDirectory)) {
// si l'index n'existe pas, on force la creation
create = true;
} else {
IndexReader reader = IndexReader.open(indexDirectory);
for (Map.Entry e : indexationMap.entrySet()) {
String id = e.getKey().toString();
removeIndex(reader, id);
}
reader.close();
}
IndexWriter writer = new IndexWriter(indexDirectory, analyzer, create, IndexWriter.MaxFieldLength.LIMITED);
for (Map.Entry e : indexationMap.entrySet()) {
String id = e.getKey().toString();
Object[] fields = e.getValue();
if (fields != null) {
try {
index(writer, id, fields);
} catch (HibernateException eee) {
if (log.isWarnEnabled()) {
log.warn("Can't index: " + id);
if (log.isDebugEnabled()) {
log.debug("StackTrace", eee);
}
}
} catch (TopiaNotFoundException eee) {
if (log.isWarnEnabled()) {
log.warn("Can't index: " + id);
if (log.isDebugEnabled()) {
log.debug("StackTrace", eee);
}
}
}
}
}
writer.close();
} catch (IOException eee) {
if (log.isWarnEnabled()) {
log.warn("Can't index");
if (log.isDebugEnabled()) {
log.debug("StackTrace", eee);
}
}
}
}
/**
* @param id identifiant de l'objet a indexer
* @param fields les champs de l'objet
* @throws IOException
* @throws TopiaNotFoundException
* @throws HibernateException
*/
private void index(IndexWriter writer, String id, Object[] fields) throws IOException, HibernateException, TopiaNotFoundException {
String classname = TopiaId.getClassNameAsString(id);
ClassMetadata cm = context.getHibernateFactory().getClassMetadata(classname + "Impl");
String[] names = cm.getPropertyNames();
org.apache.lucene.document.Document doc = new org.apache.lucene.document.Document();
doc.add(new Field("class", classname, Store.YES, Index.ANALYZED));
doc.add(new Field("topiaId", id, Store.YES, Index.ANALYZED));
StringBuffer all = new StringBuffer();
for (int i = 0; i < fields.length; i++) {
String name = names[i];
Object o = fields[i];
if (o == null) {
// do nothing
} else {
String val = String.valueOf(o);
doc.add(new Field(name, val, Store.YES, Index.ANALYZED));
all.append(val);
all.append(" ");
}
}
if (all.length() > 0) {
doc.add(new Field("__all__", all.toString(), Field.Store.NO, Index.ANALYZED));
}
writer.addDocument(doc);
}
/**
* @param ididentifiant de l'objet a supprimer
* @throws IOException
*/
private void removeIndex(IndexReader reader, String id) throws IOException {
Term term = new Term(TOPIA_ID, id);
reader.deleteDocuments(term);
}
public SortedSet search(String queryText) {
TopDocs topDocs = null;
Searcher searcher = null;
try {
Directory indexDirectory = new NIOFSDirectory(directory);
// TODO maybe put in configuration to allow localized analysers
Analyzer analyzer = new SimpleAnalyzer();
if (IndexReader.indexExists(indexDirectory)) {
searcher = new IndexSearcher(indexDirectory);
if (queryText.equals("") || queryText.length() == 0) {
// la chaine passée en parametre est vide !
log.debug("requete vide, pas de resultat a renvoyer.");
} else {
QueryParser parser = new QueryParser(Version.LUCENE_30, "__all__", analyzer);
Query luceneQuery = parser.parse(queryText);
if (log.isDebugEnabled()) {
log.debug("Recherche du terme : " + luceneQuery.toString());
}
// TODO improve doc collectors using
topDocs = searcher.search(luceneQuery, null /*filter*/, 100);
searcher.close();
}
} else {
// l'index n'a pas encore ete créé !
if (log.isDebugEnabled()) {
log.debug("Index inexistant, pas de resultats à renvoyer !");
}
}
} catch (IOException ioe) {
if (log.isDebugEnabled()) {
log.debug(ioe.getMessage(), ioe);
}
} catch (ParseException pe) {
if (log.isDebugEnabled()) {
log.debug(pe.getMessage(), pe);
}
}
//retourne les resultats trouves
TreeSet result = new TreeSet();
if (searcher != null && topDocs != null) {
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for (ScoreDoc scoreDoc : scoreDocs) {
try {
Document doc = searcher.doc(scoreDoc.doc);
String topiaId = doc.get(TOPIA_ID);
IndexEntry ie = new IndexEntry(scoreDoc.score, topiaId);
result.add(ie);
} catch (IOException eee) {
if (log.isWarnEnabled()) {
log.warn("Can't get result");
if (log.isDebugEnabled()) {
log.debug("StackTrace is", eee);
}
}
}
}
}
return result;
}
/**
* @param query Map that contains field name as key and query in value for
* this field
* @return ?
*/
@Override
public SortedSet search(Map query) {
SortedSet result = null;
// construction de la requete lucene
String queryText = "";
Iterator keys = query.keySet().iterator();
while (keys.hasNext()) {
String key = (String) keys.next();
String value = (String) query.get(key);
if (value != null) {
// on decoupe la valeur pour separer les chaines,
// sinon lucene cherche la chaine complete au lieu
// des mots
String[] st = value.split("\\s");
for (int i = 0; i < st.length; i++) {
String token = st[i];
if ((token != null) && (!token.equals(""))) {
queryText += key + ":" + st[i] + " ";
}
}
}
}
result = search(queryText);
//retourne les resultats trouves
return result;
}
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy