Metacat

package edu.ucsb.nceas.metacat.index;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.document.StringField;

import org.apache.lucene.document.TextField;

import org.apache.lucene.index.*;

import org.apache.lucene.queryparser.classic.ParseException;

import org.apache.lucene.queryparser.classic.QueryParser;

import org.apache.lucene.search.IndexSearcher;

import org.apache.lucene.search.ScoreDoc;

import org.apache.lucene.search.TopDocs;

import org.apache.lucene.store.Directory;

import org.apache.lucene.store.FSDirectory;

import org.apache.lucene.util.Version;

import java.io.File;

import java.io.IOException;

import java.util.Map;

public class LuceneIndex implements GenericIndex {

	protected final StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_41);

	protected final IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_41, analyzer);

	protected final QueryParser parser = new QueryParser(Version.LUCENE_41, MetacatIndex.MCIDFIELD, analyzer);

	protected IndexWriter writer = null;

	protected DirectoryReader reader = null;

	protected Directory index = null;

	public LuceneIndex(File fsIndex) {

		try {

			this.index = FSDirectory.open(fsIndex);

			this.cfg.setOpenMode(IndexWriterConfig.OpenMode.APPEND);

			this.writer = new IndexWriter(this.index, this.cfg);

			this.reader = DirectoryReader.open(this.index);

		} catch (Exception e) {

			e.printStackTrace();

		}

	}

	public void insert(String docID, Map<String, String[]> fields) throws IOException {

		this.update(docID, fields);

	}

	public void update(String docID, Map<String, String[]> fields) throws IOException {

		Document d = new Document();

		d.add(new StringField(MetacatIndex.MCIDFIELD, docID, Field.Store.YES));

		for (String k : fields.keySet()) {

			for (String v : fields.get(k)) {

				d.add(new TextField(k, v, Field.Store.NO));

			}

		}

		this.writer.addDocument(d);

		this.writer.commit();

	}

	public void remove(String docID) throws IOException {

		this.writer.deleteDocuments(new Term(MetacatIndex.MCIDFIELD, docID));

		this.writer.commit();

	}

	public String[] query(String q) {

		try {

			DirectoryReader newReader = DirectoryReader.openIfChanged(this.reader);

			if (newReader != null) { // not sure if this is right...

				this.reader.close();

				this.reader = newReader;

			}

			IndexSearcher searcher = new IndexSearcher(this.reader);

			TopDocs docs = searcher.search(this.parser.parse(q), 100);

			String docIDs[] = new String[docs.scoreDocs.length];

			int i = 0;

			for (ScoreDoc sd : docs.scoreDocs) {

				Document d = searcher.doc(sd.doc);

				docIDs[i++] = d.getField(MetacatIndex.MCIDFIELD).toString();

			}

			return docIDs;

		} catch (IOException e) {

			e.printStackTrace();

		} catch (ParseException e) {

			e.printStackTrace();

		}

		return new String[0];

	}

}