Professional Documents
Culture Documents
Lucene in 5 Minutes
Lucene in 5 Minutes
Lucene in 5 Minutes
Now updated for Lucene 3.5.0! Lucene makes it easy to add full-text search capability to your application. In fact, its so easy, I'm going to show you how in 5 minutes!
1. Index
For this simple case, we're going to create an in-memory index from some strings. Directory index = new RAMDirectory(); IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35, analyzer); IndexWriter w = new IndexWriter(index, config); addDoc(w, "Lucene in Action"); addDoc(w, "Lucene for Dummies"); addDoc(w, "Managing Gigabytes"); addDoc(w, "The Art of Computer Science"); w.close(); addDoc() takes a string and adds it to the index: private static void addDoc(IndexWriter w, String value) throws IOException { Document doc = new Document(); doc.add(new Field("title", value, Field.Store.YES, Field.Index.ANALYZED)); w.addDocument(doc); } } addDoc() takes a string and adds it to the index: private static void addDoc(IndexWriter w, String value) throws IOException { Document doc = new Document(); doc.add(new Field("title", value, Field.Store.YES, Field.Index.ANALYZED)); w.addDocument(doc); } }
2. Query
We read the query from stdin, parse it and build a lucene Query out of it.
String querystr = args.length > 0 ? args[0] : "lucene"; Query q = new QueryParser(Version.LUCENE_35, "title", analyzer).parse(querystr);
3. Search
Using the Query we create a Searcher to search the index. Then instantiate a TopScoreDocCollector to collect the top 10 scoring hits. int hitsPerPage = 10; IndexReader reader = IndexReader.open(index); IndexSearcher searcher = new IndexSearcher(reader); TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true); searcher.search(q, collector); ScoreDoc[] hits = collector.topDocs().scoreDocs;
4. Display
Now that we have results from our search, we display the results to the user. System.out.println("Found " + hits.length + " hits."); for(int i=0;i<hits.length;++i) { int docId = hits[i].doc; Document d = searcher.doc(docId); System.out.println((i + 1) + ". " + d.get("title")); }
import java.io.IOException; public class HelloLucene { public static void main(String[] args) throws IOException, ParseException { // 0. Specify the analyzer for tokenizing text. // The same analyzer should be used for indexing and searching StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_35); // 1. create the index Directory index = new RAMDirectory(); IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35, analyzer); IndexWriter w = new IndexWriter(index, config); addDoc(w, "Lucene in Action"); addDoc(w, "Lucene for Dummies"); addDoc(w, "Managing Gigabytes"); addDoc(w, "The Art of Computer Science"); w.close(); // 2. query String querystr = args.length > 0 ? args[0] : "lucene"; // the "title" arg specifies the default field to use // when no field is explicitly specified in the query. Query q = new QueryParser(Version.LUCENE_35, "title", analyzer).parse(querystr); // 3. search int hitsPerPage = 10; IndexReader reader = IndexReader.open(index); IndexSearcher searcher = new IndexSearcher(reader); TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true); searcher.search(q, collector); ScoreDoc[] hits = collector.topDocs().scoreDocs; // 4. display results System.out.println("Found " + hits.length + " hits."); for(int i=0;i<hits.length;++i) { int docId = hits[i].doc; Document d = searcher.doc(docId);
System.out.println((i + 1) + ". " + d.get("title")); } // searcher can only be closed when there // is no need to access the documents any more. searcher.close(); } private static void addDoc(IndexWriter w, String value) throws IOException { Document doc = new Document(); doc.add(new Field("title", value, Field.Store.YES, Field.Index.ANALYZED)); w.addDocument(doc); } } To use this app from the command line, type java HelloLucene <query>