本文整理汇总了Java中org.apache.uima.collection.CollectionReader.getNext方法的典型用法代码示例。如果您正苦于以下问题:Java CollectionReader.getNext方法的具体用法?Java CollectionReader.getNext怎么用?Java CollectionReader.getNext使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.uima.collection.CollectionReader
的用法示例。
在下文中一共展示了CollectionReader.getNext方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: readWebAnnoTSV
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
public static JCas readWebAnnoTSV(String aPath, TypeSystemDescription aType)
throws UIMAException, IOException
{
CollectionReader reader = createReader(WebannoTsv2Reader.class,
WebannoTsv2Reader.PARAM_SOURCE_LOCATION, "src/test/resources/" + aPath);
JCas jcas;
if (aType != null) {
TypeSystemDescription builtInTypes = TypeSystemDescriptionFactory
.createTypeSystemDescription();
List<TypeSystemDescription> allTypes = new ArrayList<>();
allTypes.add(builtInTypes);
allTypes.add(aType);
jcas = JCasFactory.createJCas(CasCreationUtils.mergeTypeSystems(allTypes));
}
else {
jcas = JCasFactory.createJCas();
}
reader.getNext(jcas.getCas());
return jcas;
}
示例2: readXMI
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
public static JCas readXMI(String aPath, TypeSystemDescription aType)
throws UIMAException, IOException
{
CollectionReader reader = createReader(XmiReader.class, XmiReader.PARAM_SOURCE_LOCATION,
"src/test/resources/" + aPath);
JCas jcas;
if (aType != null) {
TypeSystemDescription builtInTypes = TypeSystemDescriptionFactory
.createTypeSystemDescription();
List<TypeSystemDescription> allTypes = new ArrayList<>();
allTypes.add(builtInTypes);
allTypes.add(aType);
jcas = JCasFactory.createJCas(CasCreationUtils.mergeTypeSystems(allTypes));
}
else {
jcas = JCasFactory.createJCas();
}
reader.getNext(jcas.getCas());
return jcas;
}
示例3: test
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void test()
throws Exception
{
JCas doc = JCasFactory.createJCas();
CollectionReader reader = createReader(LineOrientedTextReader.class,
LineOrientedTextReader.PARAM_SOURCE_LOCATION, "LICENSE.txt");
reader.getNext(doc.getCas());
// select(doc, Sentence.class).forEach(s -> System.out.println(s.getCoveredText()));
assertEquals(169, select(doc, Sentence.class).size());
assertEquals(0, select(doc, Token.class).size());
}
示例4: test
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void test() throws Exception, JDOMException {
CollectionReader reader = FilesCollectionReader.getCollectionReaderWithView(
this.inputFile.getPath(),
TimeMlGoldAnnotator.TIMEML_VIEW_NAME);
AnalysisEngine annotator = AnalysisEngineFactory.createEngine(TimeMlGoldAnnotator.getDescription());
AnalysisEngine writer = AnalysisEngineFactory.createEngine(TempEval2007Writer.getDescription(this.outputDirectory.getPath()));
reader.getNext(this.jCas.getCas());
annotator.process(this.jCas);
writer.process(this.jCas);
reader.close();
annotator.collectionProcessComplete();
writer.collectionProcessComplete();
String expected = FileUtils.file2String(this.inputFile);
String actual = FileUtils.file2String(this.outputFile);
this.assertEquals(this.getRoot(expected), this.getRoot(actual));
}
示例5: testGetNext
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void testGetNext() throws Exception{
CollectionReader ecr = new ExternalCollectionReader(descriptor).produceCollectionReader();
AnalysisEngine ae = UIMAFramework.produceAnalysisEngine(SampleService
.simpleServiceDefinition()
.getAnalysisEngineDescription());
CAS mockCas = ae.newCAS();
ecr.getNext(mockCas);
FSIterator<AnnotationFS> csiIterator = mockCas.getAnnotationIndex(mockCas.getTypeSystem().getType(CSI.class.getCanonicalName())).iterator();
assertTrue(csiIterator.hasNext());
CSI csi = (CSI) csiIterator.next();
assertTrue("text1.txt".equals(csi.getID()));
//System.out.println(csi.getLocator());
assertTrue(csi.getLocator().endsWith(rootDirectory + "src/test/resources/inputDirectory/text1.txt"));
assertNull(csi.getPropertiesKeys());
assertNull(csi.getRowData());
assertTrue(RESULTS.equals(mockCas.getDocumentText()));
}
示例6: test
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void test() throws Exception {
String out = "target/BinaryCasWriterTest_" + currentTimeMillis() + "/";
// WRITING
CollectionReader cr = createReader(SingleAbstractReader.class);
AnalysisEngine writer = createEngine(BinaryCasWriter.class,
PARAM_OUTPUT_DIR, out);
runPipeline(cr, createEngine(NaiveSentenceSplitterAnnotator.class),
createEngine(RegexTokenizerAnnotator.class), writer);
assertTrue(new File(out + "1/957/687.gz").exists());
// READING
CollectionReader reader = createReader(BinaryCasReader.class,
PARAM_INPUT_DIRECTORY, out);
CAS cas = createCas(createTypeSystemDescription(), null, null);
reader.getNext(cas);
assertEquals(SingleAbstractReader.getText(), cas.getDocumentText());
assertEquals(SingleAbstractReader.getPmId(),
getHeaderIntDocId(cas.getJCas()));
}
示例7: test
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void test() throws Exception {
CollectionReader cr = createReader(PubmedWholeDatabaseCR.class);
CAS cas = createCas(cr.getProcessingResourceMetaData());
cr.getNext(cas);
for (int i = 0; i < 10000; i++) {
cr.hasNext();
cas = createCas(cr.getProcessingResourceMetaData());
cr.getNext(cas);
System.err.println(cas.getDocumentText());
}
// FIXME hangs up cr.close();
Collection<Header> h = select(cas.getJCas(), Header.class);
assertResultsContains(h, "DocId", "1");
}
示例8: testCount
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
@Ignore
// FIXME
public void testCount() throws Exception {
CollectionReader cr = PubmedCentralCollectionReader.getCR("pmc_test_archive");
int i = 0;
while (cr.hasNext()) {
CAS cas = CasCreationUtils.createCas(cr
.getProcessingResourceMetaData());
cr.getNext(cas);
i++;
}
cr.close();
assertEquals(6, i);
}
示例9: testCount
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void testCount() throws Exception {
CollectionReader cr = CollectionReaderFactory.createReader(
BioNLPGeniaEventsCollectionReader.class,
BlueUima.PARAM_INPUT_DIRECTORY, TEST_DIR);
int i = 0;
while (cr.hasNext()) {
CAS cas = CasCreationUtils.createCas(cr
.getProcessingResourceMetaData());
cr.getNext(cas);
LOG.debug(To.string("cas nr " + i, cas.getJCas()));
i++;
}
cr.close();
assertEquals(3, i);
}
示例10: test
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void test() throws Exception {
CollectionReader cr = CollectionReaderFactory.createReader(
BioNLPGeniaEventsCollectionReader.class);
int i = 0;
while (cr.hasNext()) {
CAS cas = CasCreationUtils.createCas(cr
.getProcessingResourceMetaData());
cr.getNext(cas);
// if (createHtml)
// viewer.createHtml(cas.getJCas(), cas.getTypeSystem(),
// styleMapFile, new File("target/" + i));
i++;
}
cr.close();
assertEquals(259, i);
}
示例11: test
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void test() throws Exception {
CollectionReader cr = createReader(XmlTestcaseCollectionReader.class,
PARAM_INPUT_FILE, "testcases/example.xml");
CAS cas = CasCreationUtils
.createCas(cr.getProcessingResourceMetaData());
cr.getNext(cas);
cr.close();
Collection<CellTypeProteinConcentration> prots = JCasUtil.select(
cas.getJCas(), CellTypeProteinConcentration.class);
assertTrue(prots.size() > 1);
Prin.t(prots);
// TODO assert on object
}
示例12: testTestCorpus
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void testTestCorpus() throws Exception {
CollectionReader cr = CollectionReaderFactory.createReader(
Biocreative2GeneCollectionReader.class, BlueUima.PARAM_MODE,
"test");
CAS cas = CasCreationUtils
.createCas(cr.getProcessingResourceMetaData());
cr.getNext(cas);
Collection<BioEntityMention> genes = JCasUtil.select(cas.getJCas(),
BioEntityMention.class);
assertEquals(2, genes.size());
cr.close();
}
示例13: runPipeline
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
/**
* Provides a simple way to run a pipeline for a given collection reader and sequence of
* analysis engines. After processing all CASes provided by the reader, the method calls
* {@link AnalysisEngine#collectionProcessComplete() collectionProcessComplete()} on the
* engines.
*
* @param reader
* a collection reader
* @param engines
* a sequence of analysis engines
* @throws UIMAException
* @throws IOException
*/
public static void runPipeline(final CollectionReader reader, final AnalysisEngine... engines)
throws UIMAException, IOException {
final List<ResourceMetaData> metaData = new ArrayList<ResourceMetaData>();
metaData.add(reader.getMetaData());
for (AnalysisEngine engine : engines) {
metaData.add(engine.getMetaData());
}
final CAS cas = CasCreationUtils.createCas(metaData);
try {
while (reader.hasNext()) {
reader.getNext(cas);
runPipeline(cas, engines);
cas.reset();
}
} finally {
collectionProcessComplete(engines);
destroy(reader);
}
}
示例14: testGenerateBratJsonGetDocument
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
/**
* generate brat JSON data for the document
*/
@Test
public void testGenerateBratJsonGetDocument() throws Exception
{
MappingJackson2HttpMessageConverter jsonConverter =
new MappingJackson2HttpMessageConverter();
String jsonFilePath = "target/test-output/output_cas_to_json_document.json";
String file = "src/test/resources/tcf04-karin-wl.xml";
CAS cas = JCasFactory.createJCas().getCas();
CollectionReader reader = CollectionReaderFactory.createReader(TcfReader.class,
TcfReader.PARAM_SOURCE_LOCATION, file);
reader.getNext(cas);
JCas jCas = cas.getJCas();
AnnotatorState state = new AnnotatorStateImpl(Mode.ANNOTATION);
state.getPreferences().setWindowSize(10);
state.setFirstVisibleUnit(WebAnnoCasUtil.getFirstSentence(jCas));
state.setProject(project);
VDocument vdoc = new VDocument();
preRenderer.render(vdoc, state, jCas, annotationSchemaService.listAnnotationLayer(project));
GetDocumentResponse response = new GetDocumentResponse();
BratRenderer.render(response, state, vdoc, jCas, annotationSchemaService);
JSONUtil.generatePrettyJson(jsonConverter, response, new File(jsonFilePath));
String reference = FileUtils.readFileToString(new File(
"src/test/resources/output_cas_to_json_document_expected.json"), "UTF-8");
String actual = FileUtils.readFileToString(new File(jsonFilePath), "UTF-8");
assertTrue(IOUtils.contentEqualsIgnoreEOL(new StringReader(reference),
new StringReader(actual)));
}
示例15: testSimpleSymbolicRules
import org.apache.uima.collection.CollectionReader; //导入方法依赖的package包/类
@Test
public void testSimpleSymbolicRules()
throws Exception
{
ConstraintsGrammar parser = new ConstraintsGrammar(new FileInputStream(
"src/test/resources/rules/symbolic1.rules"));
Parse p = parser.Parse();
ParsedConstraints constraints = p.accept(new ParserVisitor());
JCas jcas = JCasFactory.createJCas();
CollectionReader reader = createReader(Conll2006Reader.class,
Conll2006Reader.PARAM_SOURCE_LOCATION, "src/test/resources/text/1.conll");
reader.getNext(jcas.getCas());
POS pos = new POS(jcas, 8, 9);
pos.setPosValue("pronoun");
pos.addToIndexes();
Evaluator constraintsEvaluator = new ValuesGenerator();
Lemma lemma = select(jcas, Lemma.class).iterator().next();
List<PossibleValue> possibleValues = constraintsEvaluator.generatePossibleValues(lemma,
"value", constraints);
List<PossibleValue> expectedOutput = new ArrayList<>();
expectedOutput.add(new PossibleValue("good", true));
assertEquals(expectedOutput, possibleValues);
}