List of usage examples for org.apache.lucene.index IndexWriterConfig IndexWriterConfig
public IndexWriterConfig(Analyzer analyzer)
From source file:com.github.tteofili.looseen.Test20NewsgroupsClassification.java
License:Apache License
@Test public void test20Newsgroups() throws Exception { String indexProperty = System.getProperty("index"); if (indexProperty != null) { try {//ww w. ja v a2 s . c om index = Boolean.valueOf(indexProperty); } catch (Exception e) { // ignore } } String splitProperty = System.getProperty("split"); if (splitProperty != null) { try { split = Boolean.valueOf(splitProperty); } catch (Exception e) { // ignore } } Path mainIndexPath = Paths.get(INDEX + "/original"); Directory directory = FSDirectory.open(mainIndexPath); Path trainPath = Paths.get(INDEX + "/train"); Path testPath = Paths.get(INDEX + "/test"); Path cvPath = Paths.get(INDEX + "/cv"); FSDirectory cv = null; FSDirectory test = null; FSDirectory train = null; IndexReader testReader = null; if (split) { cv = FSDirectory.open(cvPath); test = FSDirectory.open(testPath); train = FSDirectory.open(trainPath); } if (index) { delete(mainIndexPath); if (split) { delete(trainPath, testPath, cvPath); } } IndexReader reader = null; List<Classifier<BytesRef>> classifiers = new LinkedList<>(); try { Analyzer analyzer = new StandardAnalyzer(); if (index) { System.out.format("Indexing 20 Newsgroups...%n"); long startIndex = System.currentTimeMillis(); IndexWriter indexWriter = new IndexWriter(directory, new IndexWriterConfig(analyzer)); buildIndex(new File(PREFIX + "/20n/20_newsgroups"), indexWriter); long endIndex = System.currentTimeMillis(); System.out.format("Indexed %d pages in %ds %n", indexWriter.maxDoc(), (endIndex - startIndex) / 1000); indexWriter.close(); } if (split && !index) { reader = DirectoryReader.open(train); } else { reader = DirectoryReader.open(directory); } if (index && split) { // split the index System.out.format("Splitting the index...%n"); long startSplit = System.currentTimeMillis(); DatasetSplitter datasetSplitter = new DatasetSplitter(0.1, 0); datasetSplitter.split(reader, train, test, cv, analyzer, false, CATEGORY_FIELD, BODY_FIELD, SUBJECT_FIELD, CATEGORY_FIELD); reader.close(); reader = DirectoryReader.open(train); // using the train index from now on long endSplit = System.currentTimeMillis(); System.out.format("Splitting done in %ds %n", (endSplit - startSplit) / 1000); } final long startTime = System.currentTimeMillis(); classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 1, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, null, analyzer, null, 1, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new AxiomaticF1EXP(), analyzer, null, 3, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new AxiomaticF1LOG(), analyzer, null, 3, 0, 0, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new LMDirichletSimilarity(), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new LMJelinekMercerSimilarity(0.3f), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, null, analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new DFRSimilarity(new BasicModelG(), new AfterEffectB(), new NormalizationH1()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new DFRSimilarity(new BasicModelP(), new AfterEffectL(), new NormalizationH3()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new IBSimilarity(new DistributionSPL(), new LambdaDF(), new Normalization.NoNormalization()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new IBSimilarity(new DistributionLL(), new LambdaTTF(), new NormalizationH1()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new MinHashClassifier(reader, BODY_FIELD, CATEGORY_FIELD, 15, 1, 100)); classifiers.add(new MinHashClassifier(reader, BODY_FIELD, CATEGORY_FIELD, 30, 3, 300)); classifiers.add(new MinHashClassifier(reader, BODY_FIELD, CATEGORY_FIELD, 10, 1, 100)); classifiers.add(new KNearestFuzzyClassifier(reader, new LMJelinekMercerSimilarity(0.3f), analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new IBSimilarity(new DistributionLL(), new LambdaTTF(), new NormalizationH1()), analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers .add(new KNearestFuzzyClassifier(reader, null, analyzer, null, 1, CATEGORY_FIELD, BODY_FIELD)); classifiers .add(new KNearestFuzzyClassifier(reader, null, analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new AxiomaticF1EXP(), analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new AxiomaticF1LOG(), analyzer, null, 3, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new BM25NBClassifier(reader, analyzer, null, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new CachingNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, BODY_FIELD)); classifiers.add(new SimpleNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, BODY_FIELD)); int maxdoc; if (split) { testReader = DirectoryReader.open(test); maxdoc = testReader.maxDoc(); } else { maxdoc = reader.maxDoc(); } System.out.format("Starting evaluation on %d docs...%n", maxdoc); ExecutorService service = Executors.newCachedThreadPool(); List<Future<String>> futures = new LinkedList<>(); for (Classifier<BytesRef> classifier : classifiers) { testClassifier(reader, startTime, testReader, service, futures, classifier); } for (Future<String> f : futures) { System.out.println(f.get()); } Thread.sleep(10000); service.shutdown(); } finally { if (reader != null) { reader.close(); } directory.close(); if (test != null) { test.close(); } if (train != null) { train.close(); } if (cv != null) { cv.close(); } if (testReader != null) { testReader.close(); } for (Classifier c : classifiers) { if (c instanceof Closeable) { ((Closeable) c).close(); } } } }
From source file:com.github.tteofili.looseen.TestWikipediaClassification.java
License:Apache License
@Test public void testItalianWikipedia() throws Exception { String indexProperty = System.getProperty("index"); if (indexProperty != null) { try {//from ww w . j a v a2 s . c o m index = Boolean.valueOf(indexProperty); } catch (Exception e) { // ignore } } String splitProperty = System.getProperty("split"); if (splitProperty != null) { try { split = Boolean.valueOf(splitProperty); } catch (Exception e) { // ignore } } Path mainIndexPath = Paths.get(INDEX + "/original"); Directory directory = FSDirectory.open(mainIndexPath); Path trainPath = Paths.get(INDEX + "/train"); Path testPath = Paths.get(INDEX + "/test"); Path cvPath = Paths.get(INDEX + "/cv"); FSDirectory cv = null; FSDirectory test = null; FSDirectory train = null; DirectoryReader testReader = null; if (split) { cv = FSDirectory.open(cvPath); test = FSDirectory.open(testPath); train = FSDirectory.open(trainPath); } if (index) { delete(mainIndexPath); if (split) { delete(trainPath, testPath, cvPath); } } IndexReader reader = null; try { Collection<String> stopWordsList = Arrays.asList("di", "a", "da", "in", "per", "tra", "fra", "il", "lo", "la", "i", "gli", "le"); CharArraySet stopWords = new CharArraySet(stopWordsList, true); Analyzer analyzer = new ItalianAnalyzer(stopWords); if (index) { System.out.format("Indexing Italian Wikipedia...%n"); long startIndex = System.currentTimeMillis(); IndexWriter indexWriter = new IndexWriter(directory, new IndexWriterConfig(analyzer)); importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current1.xml"), indexWriter); importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current2.xml"), indexWriter); importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current3.xml"), indexWriter); importWikipedia(new File(PREFIX + "/itwiki/itwiki-20150405-pages-meta-current4.xml"), indexWriter); long endIndex = System.currentTimeMillis(); System.out.format("Indexed %d pages in %ds %n", indexWriter.maxDoc(), (endIndex - startIndex) / 1000); indexWriter.close(); } if (split && !index) { reader = DirectoryReader.open(train); } else { reader = DirectoryReader.open(directory); } if (index && split) { // split the index System.out.format("Splitting the index...%n"); long startSplit = System.currentTimeMillis(); DatasetSplitter datasetSplitter = new DatasetSplitter(0.1, 0); for (LeafReaderContext context : reader.leaves()) { datasetSplitter.split(context.reader(), train, test, cv, analyzer, false, CATEGORY_FIELD, TEXT_FIELD, CATEGORY_FIELD); } reader.close(); reader = DirectoryReader.open(train); // using the train index from now on long endSplit = System.currentTimeMillis(); System.out.format("Splitting done in %ds %n", (endSplit - startSplit) / 1000); } final long startTime = System.currentTimeMillis(); List<Classifier<BytesRef>> classifiers = new LinkedList<>(); classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 1, 0, 0, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new BM25Similarity(), analyzer, null, 1, 0, 0, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, null, analyzer, null, 1, 0, 0, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new LMDirichletSimilarity(), analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new LMJelinekMercerSimilarity(0.3f), analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, 0, 0, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new DFRSimilarity(new BasicModelG(), new AfterEffectB(), new NormalizationH1()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new DFRSimilarity(new BasicModelP(), new AfterEffectL(), new NormalizationH3()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new IBSimilarity(new DistributionSPL(), new LambdaDF(), new Normalization.NoNormalization()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestNeighborClassifier(reader, new IBSimilarity(new DistributionLL(), new LambdaTTF(), new NormalizationH1()), analyzer, null, 3, 1, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 5, 1, 100)); classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 10, 1, 100)); classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 15, 1, 100)); classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 15, 3, 100)); classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 15, 3, 300)); classifiers.add(new MinHashClassifier(reader, TEXT_FIELD, CATEGORY_FIELD, 5, 3, 100)); classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 3, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new ClassicSimilarity(), analyzer, null, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new BM25Similarity(), analyzer, null, 3, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new KNearestFuzzyClassifier(reader, new BM25Similarity(), analyzer, null, 1, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new BM25NBClassifier(reader, analyzer, null, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new CachingNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, TEXT_FIELD)); classifiers.add(new SimpleNaiveBayesClassifier(reader, analyzer, null, CATEGORY_FIELD, TEXT_FIELD)); int maxdoc; if (split) { testReader = DirectoryReader.open(test); maxdoc = testReader.maxDoc(); } else { maxdoc = reader.maxDoc(); } System.out.format("Starting evaluation on %d docs...%n", maxdoc); ExecutorService service = Executors.newCachedThreadPool(); List<Future<String>> futures = new LinkedList<>(); for (Classifier<BytesRef> classifier : classifiers) { final IndexReader finalReader = reader; final DirectoryReader finalTestReader = testReader; futures.add(service.submit(() -> { ConfusionMatrixGenerator.ConfusionMatrix confusionMatrix; if (split) { confusionMatrix = ConfusionMatrixGenerator.getConfusionMatrix(finalTestReader, classifier, CATEGORY_FIELD, TEXT_FIELD, 60000 * 30); } else { confusionMatrix = ConfusionMatrixGenerator.getConfusionMatrix(finalReader, classifier, CATEGORY_FIELD, TEXT_FIELD, 60000 * 30); } final long endTime = System.currentTimeMillis(); final int elapse = (int) (endTime - startTime) / 1000; return " * " + classifier + " \n * accuracy = " + confusionMatrix.getAccuracy() + "\n * precision = " + confusionMatrix.getPrecision() + "\n * recall = " + confusionMatrix.getRecall() + "\n * f1-measure = " + confusionMatrix.getF1Measure() + "\n * avgClassificationTime = " + confusionMatrix.getAvgClassificationTime() + "\n * time = " + elapse + " (sec)\n "; })); } for (Future<String> f : futures) { System.out.println(f.get()); } Thread.sleep(10000); service.shutdown(); } finally { try { if (reader != null) { reader.close(); } if (directory != null) { directory.close(); } if (test != null) { test.close(); } if (train != null) { train.close(); } if (cv != null) { cv.close(); } if (testReader != null) { testReader.close(); } } catch (Throwable e) { e.printStackTrace(); } } }
From source file:com.github.wxiaoqi.search.lucene.LuceneDao.java
License:Open Source License
public void create(IndexObject indexObject) { IndexWriter indexWriter = null;/* ww w . j a v a 2 s. co m*/ try { IndexWriterConfig config = new IndexWriterConfig(this.getAnalyzer()); indexWriter = new IndexWriter(this.getDirectory(), config); indexWriter.addDocument(DocumentUtil.IndexObject2Document(indexObject)); indexWriter.commit(); } catch (Exception e) { e.printStackTrace(); try { indexWriter.rollback(); } catch (IOException e1) { e1.printStackTrace(); } } finally { try { indexWriter.close(); } catch (IOException e1) { e1.printStackTrace(); } } }
From source file:com.github.wxiaoqi.search.lucene.LuceneDao.java
License:Open Source License
public void deleteAll() { IndexWriter indexWriter = null;//from w ww . ja va2s . c o m try { IndexWriterConfig config = new IndexWriterConfig(this.getAnalyzer()); indexWriter = new IndexWriter(this.getDirectory(), config); Long result = indexWriter.deleteAll(); /**/ indexWriter.forceMergeDeletes(); log.info("deleted:{}", result); } catch (Exception e) { e.printStackTrace(); try { indexWriter.rollback(); } catch (IOException e1) { e1.printStackTrace(); } } finally { try { indexWriter.close(); } catch (IOException e1) { e1.printStackTrace(); } } }
From source file:com.github.wxiaoqi.search.lucene.LuceneDao.java
License:Open Source License
public void update(IndexObject indexObject) { IndexWriter indexWriter = null;/* w w w . java 2 s .c o m*/ try { Term term = new Term("id", indexObject.getId().toString()); IndexWriterConfig config = new IndexWriterConfig(this.getAnalyzer()); indexWriter = new IndexWriter(this.getDirectory(), config); indexWriter.updateDocument(term, DocumentUtil.IndexObject2Document(indexObject)); } catch (Exception e) { e.printStackTrace(); try { indexWriter.rollback(); } catch (IOException e1) { e1.printStackTrace(); } } finally { try { indexWriter.close(); } catch (IOException e1) { e1.printStackTrace(); } } }
From source file:com.github.wxiaoqi.search.lucene.LuceneDao.java
License:Open Source License
public void delete(IndexObject indexObject) { IndexWriter indexWriter = null;/*from w ww.j a v a2 s .c o m*/ try { Term term = new Term("id", indexObject.getId().toString()); IndexWriterConfig config = new IndexWriterConfig(this.getAnalyzer()); indexWriter = new IndexWriter(this.getDirectory(), config); indexWriter.deleteDocuments(term); } catch (Exception e) { e.printStackTrace(); try { indexWriter.rollback(); } catch (IOException e1) { e1.printStackTrace(); } } finally { try { indexWriter.close(); } catch (IOException e1) { e1.printStackTrace(); } } }
From source file:com.google.gerrit.lucene.GerritIndexWriterConfig.java
License:Apache License
GerritIndexWriterConfig(Config cfg, String name) {
analyzer = new CustomMappingAnalyzer(new StandardAnalyzer(CharArraySet.EMPTY_SET), CUSTOM_CHAR_MAPPING);
luceneConfig = new IndexWriterConfig(analyzer).setOpenMode(OpenMode.CREATE_OR_APPEND)
.setCommitOnClose(true);//w w w .j a v a2 s. c o m
double m = 1 << 20;
luceneConfig.setRAMBufferSizeMB(cfg.getLong("index", name, "ramBufferSize",
(long) (IndexWriterConfig.DEFAULT_RAM_BUFFER_SIZE_MB * m)) / m);
luceneConfig.setMaxBufferedDocs(
cfg.getInt("index", name, "maxBufferedDocs", IndexWriterConfig.DEFAULT_MAX_BUFFERED_DOCS));
try {
commitWithinMs = ConfigUtil.getTimeUnit(cfg, "index", name, "commitWithin",
MILLISECONDS.convert(5, MINUTES), MILLISECONDS);
} catch (IllegalArgumentException e) {
commitWithinMs = cfg.getLong("index", name, "commitWithin", 0);
}
}
From source file:com.google.gerrit.server.change.ReviewerSuggestionCache.java
License:Apache License
private IndexSearcher index() throws IOException, OrmException { RAMDirectory idx = new RAMDirectory(); IndexWriterConfig config = new IndexWriterConfig(new StandardAnalyzer(CharArraySet.EMPTY_SET)); config.setOpenMode(OpenMode.CREATE); try (IndexWriter writer = new IndexWriter(idx, config)) { for (Account a : db.get().accounts().all()) { if (a.isActive()) { addAccount(writer, a);/*from w ww . j av a2 s. co m*/ } } } return new IndexSearcher(DirectoryReader.open(idx)); }
From source file:com.gprasad.searchwithlucene.Indexer.java
private static void createIndex(String indexPath) throws IOException { Directory dir = FSDirectory.open(Paths.get(indexPath)); Analyzer analyzer = new StandardAnalyzer(); IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); indexWriterConfig.setOpenMode(OpenMode.CREATE); writer = new IndexWriter(dir, indexWriterConfig); }
From source file:com.helger.pd.indexer.lucene.PDLucene.java
License:Apache License
public PDLucene() throws IOException { // Where to store the index files final Path aPath = getLuceneIndexDir().toPath(); m_aDir = FSDirectory.open(aPath);// w ww .java2s . c om // Analyzer to use m_aAnalyzer = createAnalyzer(); // Create the index writer final IndexWriterConfig aWriterConfig = new IndexWriterConfig(m_aAnalyzer); aWriterConfig.setOpenMode(OpenMode.CREATE_OR_APPEND); m_aIndexWriter = new IndexWriter(m_aDir, aWriterConfig); // Reader and searcher are opened on demand s_aLogger.info("Lucene index operating on " + aPath); }