List of usage examples for org.apache.lucene.index IndexWriter IndexWriter
public IndexWriter(Directory d, IndexWriterConfig conf) throws IOException
conf. From source file:br.usp.icmc.gazetteer.SemanticSearchTest.LuceneSearcher.java
License:Open Source License
public void similaridade2() throws IOException { IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_36, a); conf.setSimilarity(similaritylnc()); writer = new IndexWriter(dir, conf); }
From source file:br.usp.icmc.gazetteer.SemanticSearchTest.LuceneSearcher.java
License:Open Source License
public void similaridade3() throws IOException { IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_36, a); conf.setSimilarity(similaritynnc()); writer = new IndexWriter(dir, conf); }
From source file:buscador.IndexFiles.java
License:Apache License
/** * Index all text files under a directory. *///www . j a v a 2s. c om 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 = "Zaguan1"; 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 SpanishAnalyzer(Version.LUCENE_44); IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_44, analyzer); if (create) { // Create a new index in the directory, removing any // previously indexed documents: iwc.setOpenMode(OpenMode.CREATE); } else { // Add new documents to an existing index: iwc.setOpenMode(OpenMode.CREATE_OR_APPEND); } // Optional: for better indexing performance, if you // are indexing many documents, increase the RAM // buffer. But if you do this, increase the max heap // size to the JVM (eg add -Xmx512m or -Xmx1g): // // iwc.setRAMBufferSizeMB(256.0); IndexWriter writer = new IndexWriter(dir, iwc); indexDocs(writer, docDir); // NOTE: if you want to maximize search performance, // you can optionally call forceMerge here. This can be // a terribly costly operation, so generally it's only // worth it when your index is relatively static (ie // you're done adding documents to it): // // writer.forceMerge(1); 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()); } }
From source file:bzh.terrevirtuelle.navisu.gazetteer.impl.lucene.GeoNameResolver.java
License:Apache License
/** * Build the gazetteer index line by line * * @param gazetteerPath path of the gazetteer file * @param indexerPath path to the created Lucene index directory. * @param reverseGeocodingEnabled/*from w w w .j av a2 s .com*/ * @throws IOException * @throws RuntimeException */ public void buildIndex(String gazetteerPath, String indexerPath, boolean reverseGeocodingEnabled) throws IOException { File indexfile = new File(indexerPath); indexDir = FSDirectory.open(indexfile.toPath()); if (!DirectoryReader.indexExists(indexDir)) { IndexWriterConfig config = new IndexWriterConfig(analyzer); indexWriter = new IndexWriter(indexDir, config); Logger logger = Logger.getLogger(this.getClass().getName()); logger.log(Level.WARNING, "Start Building Index for Gazatteer"); BufferedReader filereader = new BufferedReader( new InputStreamReader(new FileInputStream(gazetteerPath), "UTF-8")); String line; int count = 0; while ((line = filereader.readLine()) != null) { try { count += 1; if (count % 100000 == 0) { logger.log(Level.INFO, "Indexed Row Count: " + count); } addDoc(indexWriter, line, reverseGeocodingEnabled); } catch (RuntimeException re) { logger.log(Level.WARNING, "Skipping... Error on line: {0}", line); re.printStackTrace(); } } logger.log(Level.WARNING, "Building Finished"); filereader.close(); indexWriter.close(); } }
From source file:ca.dracode.ais.indexer.FileIndexer.java
License:Open Source License
public FileIndexer() { super();//from ww w . jav a 2 s .co m this.searcher = new FileSearcher(); Directory dir; try { dir = FSDirectory.open(new File(FileIndexer.getRootStorageDir())); Analyzer analyzer = new SimpleAnalyzer(Version.LUCENE_47); IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_47, analyzer); iwc.setOpenMode(OpenMode.CREATE_OR_APPEND); this.writer = new IndexWriter(dir, iwc); this.writer.commit(); } catch (IOException e) { e.printStackTrace(); } }
From source file:ca.gnewton.lusql.core.IndexTermFreqCache.java
License:Apache License
/** * Describe <code>main</code> method here. * * @param args a <code>String</code> value *///from w w w . j av a2 s . c o m public static final void main(final String[] args) { String dir = "itfcTestIndex"; String cachedField = "title"; try { IndexWriterConfig config = new IndexWriterConfig(LuSql.luceneVersion, new StandardAnalyzer(LuSql.luceneVersion)).setOpenMode(IndexWriterConfig.OpenMode.CREATE); IndexWriter writer = new IndexWriter(FSDirectory.open(new File(dir)), config); // Doc #1 Document doc1 = new Document(); Field title1 = new org.apache.lucene.document.Field(cachedField, "The Rain in Spain is plain", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES); doc1.add(title1); org.apache.lucene.document.Field ab1 = new org.apache.lucene.document.Field("ab", "This is the test abstract", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES); doc1.add(ab1); writer.addDocument(doc1); // Doc #2 Document doc2 = new Document(); Field title2 = new org.apache.lucene.document.Field(cachedField, "This is the test plain title", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES); doc2.add(title2); org.apache.lucene.document.Field ab2 = new org.apache.lucene.document.Field("ab", "This is the test abstract", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES); doc2.add(ab2); writer.addDocument(doc2); writer.close(); IndexReader reader = IndexReader.open(FSDirectory.open(new File(dir))); IndexTermFreqCache cache = new IndexTermFreqCache(reader, cachedField, 100, true); System.err.println(cache); } catch (Throwable t) { t.printStackTrace(); } }
From source file:ca.mcgill.cs.creco.logic.search.CategorySearch.java
License:Apache License
private void buildCategoryIndex() throws IOException { IndexWriter writer = new IndexWriter(aDirectory, new IndexWriterConfig(VERSION, aAnalyzer)); for (Category category : aDataStore.getCategories()) { String flattenedText = category.getName(); for (Product product : category.getProducts()) { flattenedText += product.getName() + " "; }//from www . j a v a2 s .c o m Document doc = new Document(); doc.add(new TextField(CATEGORY_ID, category.getId(), Field.Store.YES)); doc.add(new TextField(CATEGORY_NAME, category.getName(), Field.Store.YES)); doc.add(new TextField(FLATTENED_TEXT, flattenedText, Field.Store.YES)); writer.addDocument(doc); } writer.close(); }
From source file:ca.pgon.freenetknowledge.search.impl.LuceneIndexerThread.java
License:Apache License
private IndexWriter genIndexWriter() throws CorruptIndexException, LockObtainFailedException, IOException { IndexWriterConfig indexWriterConfig = new IndexWriterConfig(LuceneSearchEngine.LUCENE_VERSION, analyzer); indexWriterConfig.setOpenMode(OpenMode.CREATE_OR_APPEND); return new IndexWriter(directory, indexWriterConfig); }
From source file:ca.ualberta.entitylinking.common.indexing.AliasLuceneIndex.java
License:Open Source License
public void initWriter(String dirLoc) { Directory dir = null;/*w w w. java 2 s . co m*/ IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_34, analyzer); try { dir = new MMapDirectory(new File(dirLoc)); writer = new IndexWriter(dir, conf); } catch (Exception e) { e.printStackTrace(); } }
From source file:ca.ualberta.entitylinking.common.indexing.DocumentIndexer.java
License:Open Source License
public void initWriter(String indexDir, boolean create) { try {/* w w w .j a v a2 s. com*/ Directory dir = FSDirectory.open(new File(indexDir)); IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_34, null); // create a new index if (create) iwc.setOpenMode(OpenMode.CREATE); else iwc.setOpenMode(OpenMode.CREATE_OR_APPEND); writer = new IndexWriter(dir, iwc); } catch (IOException e) { e.printStackTrace(); } }