List of usage examples for org.apache.lucene.index IndexWriter IndexWriter
public IndexWriter(Directory d, IndexWriterConfig conf) throws IOException
conf. From source file:com.github.alvanson.xltsearch.IndexTask.java
License:Apache License
@Override protected Boolean call() { IndexWriter iwriter = null;/*from www .j a v a 2 s .c om*/ boolean result = false; updateMessage("started"); try { int count = 0; Docket docket; IndexWriterConfig iwconfig = new IndexWriterConfig(config.getVersion(), config.getAnalyzer()); iwconfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND); iwconfig.setSimilarity(config.getSimilarity()); iwriter = new IndexWriter(config.getDirectory(), iwconfig); while ((docket = inQueue.take()) != Docket.DONE) { count++; updateMessage(docket.relPath); switch (docket.status) { case PARSED: // index parsed file Document doc = new Document(); // store relative path ** must be indexed for updateDocument doc.add(new StringField(config.pathField, docket.relPath, Field.Store.YES)); // index content doc.add(new TextField(config.contentField, docket.content.toString(), Field.Store.NO)); // index standard metadata for (Map.Entry<String, Property> e : config.metadataFields.entrySet()) { for (String value : docket.metadata.getValues(e.getValue())) { doc.add(new TextField(e.getKey(), value, Field.Store.YES)); } } // store hashsum doc.add(new StringField(config.hashSumField, docket.hashSum, Field.Store.YES)); // add/update document iwriter.updateDocument(new Term(config.pathField, docket.relPath), doc); // fall through case PASS: break; case DELETE: iwriter.deleteDocuments(new Term(config.pathField, docket.relPath)); break; default: logger.error("Unexpected docket state while processing {}: {}", docket.relPath, docket.status.toString()); cancel(true); // cancel task } updateProgress(count, count + docket.workLeft); } // end of queue updateMessage("complete"); updateProgress(count, count + docket.workLeft); result = true; } catch (IOException ex) { updateMessage("I/O exception"); logger.error("I/O exception while writing to index", ex); } catch (InterruptedException ex) { if (isCancelled()) { updateMessage("cancelled"); } else { updateMessage("interrupted"); logger.error("Interrupted", ex); } } // close iwriter if (iwriter != null) { try { iwriter.close(); } catch (IOException ex) { logger.warn("I/O exception while closing index writer", ex); } } return result; }
From source file:com.github.buzztaiki.lucene.lastuni.CJKSingleCharQueryTest.java
License:Apache License
private IndexWriter newWriter(Directory dir, Analyzer analyzer) throws IOException { return new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer).setOpenMode(OpenMode.CREATE)); }
From source file:com.github.cmisbox.persistence.Storage.java
License:Open Source License
private Storage() { this.log = LogFactory.getLog(this.getClass()); this.config = Config.getInstance(); File file = new File(this.config.getConfigHome(), Storage.indexFolderName); if (!file.exists()) { file.mkdirs();//w ww. ja va 2 s.c om this.log.info(Messages.createdIndexFolder); } try { this.directory = FSDirectory.open(file); this.writer = new IndexWriter(this.directory, new IndexWriterConfig(Version.LUCENE_33, new StandardAnalyzer(Version.LUCENE_33))); this.reader = IndexReader.open(this.writer, false); List<String> roots = this.getRootPaths(); for (String root : roots) { Watcher.getInstance().addWatch(root); } } catch (Exception e) { this.log.fatal(e); Main.exit(1); } }
From source file:com.github.flaxsearch.testutil.Fixtures.java
License:Apache License
private static void populateIndex(Directory directory) { try (IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig())) { {// w w w . j a v a 2s .c o m Document doc = new Document(); doc.add(new TextField("field2", "here is some text", Field.Store.YES)); doc.add(new StringField("field1", "value1", Field.Store.YES)); doc.add(new IntPoint("point", 2, 4)); doc.add(new IntPoint("point", 0, 1)); doc.add(new IntPoint("point", 2, 1)); doc.add(new IntPoint("point", 14, 4)); writer.addDocument(doc); // more than one segment writer.commit(); } { Document doc = new Document(); doc.add(new StringField("field1", "value2", Field.Store.YES)); doc.add(new BinaryDocValuesField("field1", new BytesRef("some bytes"))); doc.add(new TextField("field3", "this is some more text in a different field value1 value11 value12 value21", Field.Store.YES)); writer.addDocument(doc); } } catch (IOException e) { throw new RuntimeException("We're a RAMDirectory, this should never happen!"); } }
From source file:com.github.flaxsearch.testutil.GutenbergIndex.java
License:Apache License
public static void main(String... args) throws IOException { Path source = Paths.get("src/test/resources/gutenberg"); Path index = Paths.get("src/test/resources/index"); clearDirectory(index);// w w w.j a va 2 s .c o m try (Directory directory = FSDirectory.open(index); IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig())) { writeDocuments(writer, source); } }
From source file:com.github.hotware.lucene.extension.manager.LuceneManagerImpl.java
License:BEER-WARE LICENSE
@Override public final IndexWriter getIndexWriter(IndexWriterConfig config) throws IOException { return new IndexWriter(this.directory, config); }
From source file:com.github.jiloc.USTweetsAnalyzer.Store.java
public Store() throws IOException { states = new HashSet<String>(); //first we empty our directory resetDir(new File("tweet_idex")); // The process of writing indexing dir = new SimpleFSDirectory(new File("tweet_index")); analyzer = new StandardAnalyzer(LUCENE_41); cfg = new IndexWriterConfig(LUCENE_41, analyzer); writer = new IndexWriter(dir, cfg); // a document contains a list of field(s) doc = new Document(); s = new StringField("STATE", "", Field.Store.YES); l = new TextField("LOC", "", Field.Store.YES); doc.add(s);//from w ww. ja va2s . com doc.add(l); }
From source file:com.github.le11.nls.lucene.UIMABaseAnalyzerTest.java
License:Apache License
@Before public void setUp() throws Exception { dir = new RAMDirectory(); analyzer = new UIMABaseAnalyzer("/WhitespaceTokenizer.xml", "org.apache.uima.TokenAnnotation"); writer = new IndexWriter(dir, new IndexWriterConfig(Version.LUCENE_32, analyzer)); }
From source file:com.github.le11.nls.lucene.UIMAPayloadsAnalyzerTest.java
License:Apache License
@Before public void setUp() throws Exception { dir = new RAMDirectory(); analyzer = new UIMAPayloadsAnalyzer("/HmmTaggerAggregate.xml"); writer = new IndexWriter(dir, new IndexWriterConfig(Version.LUCENE_33, analyzer)); }
From source file:com.github.le11.nls.lucene.UIMATypeBasedSimilarityTest.java
License:Apache License
@Before public void setUp() throws Exception { dir = new RAMDirectory(); analyzer = new UIMAPayloadsAnalyzer("/HmmTaggerAggregate.xml"); writer = new IndexWriter(dir, new IndexWriterConfig(Version.LUCENE_33, analyzer)); Document doc = new Document(); doc.add(new Field("title", "this is a dummy title containing an entity for London", Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("contents", "there is some content written here about the british city", Field.Store.YES, Field.Index.ANALYZED)); writer.addDocument(doc, analyzer);/*from w ww.ja v a2s. c om*/ writer.commit(); // try the search over the first doc IndexSearcher indexSearcher = new IndexSearcher(writer.getReader()); TopDocs result = indexSearcher.search(new MatchAllDocsQuery("contents"), 10); assertTrue(result.totalHits > 0); Document d = indexSearcher.doc(result.scoreDocs[0].doc); assertNotNull(d); assertNotNull(d.getFieldable("title")); assertNotNull(d.getFieldable("contents")); // add a second doc doc = new Document(); doc.add(new Field("title", "some title regarding some article written in English", Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("contents", "this is the content of the article about", Field.Store.YES, Field.Index.ANALYZED)); writer.addDocument(doc, analyzer); writer.commit(); }