/** * Instantiates a new job settings. * * @param jCas the jcas */ public JobSettings(final JCas jCas) { this.jCas = jCas; metadata = new JCasMetadata(jCas); }
/** * Instantiates a new job settings. * * @param jCas the jcas */ public JobSettings(final JCas jCas) { this.jCas = jCas; metadata = new JCasMetadata(jCas); }
private void testJcasTable1(JCas jCas, int row) { assertTrue(jCas.getDocumentText().startsWith("TEXT BLOCK")); JCasMetadata metadata = new JCasMetadata(jCas); Optional<String> find = metadata.find("resourceName"); assertTrue(find.get().toLowerCase().startsWith("h2:mem:test.my_table#" + row)); }
private void testJcasTable2(JCas jCas, int row) { JCasMetadata metadata = new JCasMetadata(jCas); Optional<String> find = metadata.find("resourceName").map(String::toLowerCase); assertTrue(find.get().startsWith("h2:mem:test.my_table2#" + row)); if (find.get().endsWith("ignore_me")) { assertEquals("IGNORE", jCas.getDocumentText()); } else { assertTrue(jCas.getDocumentText().startsWith("TEXT BLOCK")); } }
@Before public void setup() throws AnalysisEngineProcessException, ResourceInitializationException { jCas.setDocumentText(DOCUMENT); processJCas(); jCasMetadata = new JCasMetadata(jCas); }
@Before public void setup() throws AnalysisEngineProcessException, ResourceInitializationException { jCas.setDocumentText(DOCUMENT); processJCas(); metadata = new JCasMetadata(jCas); }
@Test public void testProcess() throws Exception { jCas.setDocumentText( new String(Files.readAllBytes(Paths.get(getClass().getResource("turing.txt").toURI())))); processJCas(KEY_STOPWORDS, erd, PARAM_STEMMING, "ENGLISH"); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY); assertEquals(5, keywords.size()); assertTrue(keywords.contains("machine")); assertTrue(keywords.contains("computer")); assertTrue(keywords.contains("digital computers")); assertTrue(keywords.contains("state")); // Same score so either is valid assertTrue(keywords.contains("question") || keywords.contains("digital")); assertTrue(JCasUtil.select(jCas, Buzzword.class).size() > 0); Set<String> buzzwords = new HashSet<>(); for (Buzzword bw : JCasUtil.select(jCas, Buzzword.class)) { assertEquals("keyword", bw.getTags(0)); buzzwords.add(bw.getValue()); } assertTrue(buzzwords.contains("machines")); assertTrue(buzzwords.contains("computing")); assertTrue(buzzwords.contains("questioning")); }
@Test public void testLongDocument() throws Exception { ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription( STOPWORDS, SharedStopwordResource.class); AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription( RakeKeywords.class, STOPWORDS, erd, RakeKeywords.PARAM_MAX_KEYWORDS, 12, RakeKeywords.PARAM_ADD_BUZZWORDS, true); AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed); jCas.setDocumentText( new String(Files.readAllBytes(Paths.get(getClass().getResource("turing.txt").toURI())))); ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Optional<String> keyword = metadata.find(KEYWORD_METADATA_KEY); assertTrue(keyword.isPresent()); ae.destroy(); }
ae.process(jCas); JCasMetadata metadata1 = new JCasMetadata(jCas); Set<String> fullDocKeywords = metadata1.findAll(KEYWORD_METADATA_KEY); ae.process(jCas); JCasMetadata metadata2 = new JCasMetadata(jCas); Set<String> textKeywords = metadata2.findAll(KEYWORD_METADATA_KEY); assertFalse(textKeywords.isEmpty());
processJCas(KEY_STOPWORDS, erd); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY);
@Before public void setUp() throws UIMAException { JCas jCas = JCasFactory.createJCas(); addMetadata(jCas, KEY1, VALUE1); addMetadata(jCas, KEY2, VALUE2); addMetadata(jCas, KEY2, VALUE3); metadata = new JCasMetadata(jCas); }
@Test public void testCustomStoplist() throws ResourceInitializationException, AnalysisEngineProcessException { ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription( STOPWORDS, SharedStopwordResource.class); AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription( RakeKeywords.class, STOPWORDS, erd, RakeKeywords.PARAM_MAX_KEYWORDS, 12, RakeKeywords.PARAM_ADD_BUZZWORDS, false, RakeKeywords.PARAM_STOPLIST, getClass().getResource("exampleStoplist.txt").getPath()); AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed); jCas.setDocumentText("Bill and Ben went off to the shops in London town."); ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY); assertEquals(1, keywords.size()); assertTrue(keywords.contains("london town")); ae.destroy(); }
ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY);
ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY);
ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY);
@Test public void testMaxNumber() throws ResourceInitializationException, AnalysisEngineProcessException { ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription( STOPWORDS, SharedStopwordResource.class); AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription( RakeKeywords.class, STOPWORDS, erd, RakeKeywords.PARAM_MAX_KEYWORDS, 3, RakeKeywords.PARAM_ADD_BUZZWORDS, false); AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed); jCas.setDocumentText( "Compatibility of systems of linear constraints over the set of natural numbers. Criteria of compatibility of a system of linear Diophantine equations, strict inequations, and nonstrict inequations are considered. Upper bounds for components of a minimal set of solutions and algorithms of construction of minimal generating sets of solutions for all types of systems are given. These criteria and the corresponding algorithms for contructing a minimal supporting set of solutions can be used in solving all the considered types of systems and systems of mixed types."); ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY); assertEquals(3, keywords.size()); assertTrue(keywords.contains("minimal generating sets")); assertTrue(keywords.contains("linear diophantine equations")); assertTrue(keywords.contains("minimal supporting set")); ae.destroy(); }
@Test public void testCharacters() throws ResourceInitializationException, AnalysisEngineProcessException { ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription( STOPWORDS, SharedStopwordResource.class); AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription( RakeKeywords.class, STOPWORDS, erd, RakeKeywords.PARAM_MAX_KEYWORDS, 12, RakeKeywords.PARAM_ADD_BUZZWORDS, false); AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed); jCas.setDocumentText( "Thursday 28th January - Test Report\n\n\tMichelle was seen meeting Katie at the Diner (Mary's Diner, on Main Street), at approximately 6:00pm. Michelle was later seen to be leaving the Diner, carrying a black folder of unknown contents. Katie is a known sympathiser, and it is hypothesised that she passed training materials to Michelle. When questioned later, Michelle stated: \"I know nothing of any training materials/folder!\"."); ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY); for (String keyword : keywords) { assertEquals("", keyword.replaceAll("[a-z0-9 ]", "")); } ae.destroy(); }
ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY);
ae.process(jCas); JCasMetadata metadata = new JCasMetadata(jCas); Set<String> keywords = metadata.findAll(KEYWORD_METADATA_KEY);