本文整理汇总了Java中org.apache.uima.fit.factory.ExternalResourceFactory.createExternalResourceDescription方法的典型用法代码示例。如果您正苦于以下问题:Java ExternalResourceFactory.createExternalResourceDescription方法的具体用法?Java ExternalResourceFactory.createExternalResourceDescription怎么用?Java ExternalResourceFactory.createExternalResourceDescription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.fit.factory.ExternalResourceFactory
的用法示例。
在下文中一共展示了ExternalResourceFactory.createExternalResourceDescription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: beforeTest
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@Override
public void beforeTest() throws UIMAException {
super.beforeTest();
final ExternalResourceDescription tokensDesc = ExternalResourceFactory.createExternalResourceDescription(
"lexica",
ClearNlpLexica.class);
final AnalysisEngineDescription tokeniserDesc = AnalysisEngineFactory.createEngineDescription(
ClearNlpTokeniser.class,
"lexica",
tokensDesc);
tokeniserAe = AnalysisEngineFactory.createEngine(tokeniserDesc);
final AnalysisEngineDescription parserDesc = AnalysisEngineFactory.createEngineDescription(ClearNlpParser.class,
"lexica",
tokensDesc);
ae = AnalysisEngineFactory.createEngine(parserDesc);
}
示例2: createAnalysisEngines
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@Override
protected AnalysisEngine[] createAnalysisEngines() throws ResourceInitializationException {
// Use OpenNlp to generate the POS etc for us
final ExternalResourceDescription tokensDesc = ExternalResourceFactory.createExternalResourceDescription(
"tokens",
SharedOpenNLPModel.class);
final ExternalResourceDescription sentencesDesc = ExternalResourceFactory
.createExternalResourceDescription("sentences", SharedOpenNLPModel.class);
final ExternalResourceDescription posDesc = ExternalResourceFactory.createExternalResourceDescription("posTags",
SharedOpenNLPModel.class);
final ExternalResourceDescription chunksDesc = ExternalResourceFactory
.createExternalResourceDescription("phraseChunks", SharedOpenNLPModel.class);
return asArray(
createAnalysisEngine(OpenNLP.class, "tokens", tokensDesc, "sentences", sentencesDesc, "posTags",
posDesc, "phraseChunks", chunksDesc),
createAnalysisEngine(MaltParser.class));
}
示例3: setUp
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@Before
public void setUp() throws ResourceInitializationException, ResourceAccessException {
// Create a description of an external resource - a fongo instance, in the same way we would
// have created a shared mongo resource
final ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription(
SharedFongoResource.class, "fongo.collection", "test", "fongo.data", "[]");
// Create the analysis engine
final AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription(MongoPatternSaver.class,
MongoPatternSaver.KEY_MONGO, erd,
"collection", "test");
ae = AnalysisEngineFactory.createEngine(aed);
ae.initialize(new CustomResourceSpecifier_impl(), Collections.emptyMap());
sfr = (SharedFongoResource) ae.getUimaContext()
.getResourceObject(MongoPatternSaver.KEY_MONGO);
}
示例4: setupClass
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@BeforeClass
public static void setupClass() throws UIMAException, JMSException {
//Configuration values
Object[] configArr = new String[] {
SharedActiveMQResource.PARAM_PROTOCOL, PROTOCOL_VALUE,
SharedActiveMQResource.PARAM_HOST, HOST_VALUE,
SharedActiveMQResource.PARAM_BROKERARGS, BROKERARGS_VALUE
};
//Create descriptors
ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription(ACTIVEMQ, SharedActiveMQResource.class, configArr);
AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription(ActiveMQ.class, TypeSystemSingleton.getTypeSystemDescriptionInstance(), ACTIVEMQ, erd, ActiveMQ.PARAM_ENDPOINT, ENDPOINT);
//Create annotator
ae = AnalysisEngineFactory.createEngine(aed);
//Get resource so that we can use it to test output
resource = (SharedActiveMQResource) ae.getUimaContext().getResourceObject(ACTIVEMQ);
//Subscribe to what will be the output topic
Session session = resource.getSession();
topicConsumer = session.createConsumer(session.createTopic(ENDPOINT));
}
示例5: makeAE
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
private AnalysisEngine makeAE(boolean removeWordAnnotationFromCas, boolean removeTermOccAnnotationFromCas) throws Exception {
AnalysisEngineDescription aeDesc = AnalysisEngineFactory.createEngineDescription(
FixedExpressionSpotter.class,
FixedExpressionSpotter.FIXED_EXPRESSION_MAX_SIZE, 5,
FixedExpressionSpotter.REMOVE_WORD_ANNOTATIONS_FROM_CAS, removeWordAnnotationFromCas,
FixedExpressionSpotter.REMOVE_TERM_OCC_ANNOTATIONS_FROM_CAS, removeTermOccAnnotationFromCas
);
/*
* The term index resource
*/
ExternalResourceDescription fixedExpressionDesc = ExternalResourceFactory.createExternalResourceDescription(
FixedExpressionResource.FIXED_EXPRESSION_RESOURCE,
FixedExpressionResource.class,
"file:fr/univnantes/termsuite/test/resources/french-fixed-expressions.txt"
);
ExternalResourceFactory.bindResource(aeDesc, fixedExpressionDesc);
AnalysisEngine ae = AnalysisEngineFactory.createEngine(aeDesc);
return ae;
}
示例6: testCustomStoplist
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@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);
assertEquals(1, JCasUtil.select(jCas, Metadata.class).size());
Metadata md = JCasUtil.selectByIndex(jCas, Metadata.class, 0);
assertEquals("keywords", md.getKey());
List<String> keywords = Arrays.asList(md.getValue().split(";"));
assertEquals(1, keywords.size());
assertTrue(keywords.contains("london town"));
ae.destroy();
}
示例7: testLongDocument
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@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);
assertEquals(1, JCasUtil.select(jCas, Metadata.class).size());
Metadata md = JCasUtil.selectByIndex(jCas, Metadata.class, 0);
assertEquals("keywords", md.getKey());
assertNotNull(md.getValue());
ae.destroy();
}
示例8: createWordTokenizerAEDesc
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
public static AnalysisEngineDescription createWordTokenizerAEDesc(ResourceConfig resourceConfig, Lang lang) {
AnalysisEngineDescription ae;
try {
ae = AnalysisEngineFactory.createEngineDescription(
Lexer.class,
Lexer.PARAM_TYPE, "fr.univnantes.termsuite.types.WordAnnotation"
);
ExternalResourceDescription segmentBank = ExternalResourceFactory.createExternalResourceDescription(
SegmentBankResource.class,
getResourceURL(resourceConfig, ResourceType.SEGMENT_BANK, lang)
);
ExternalResourceFactory.bindResource(
ae,
SegmentBank.KEY_SEGMENT_BANK,
segmentBank);
return ae;
} catch (Exception e) {
throw new TermSuiteException(e);
}
}
示例9: testmultipleHitsWithText
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@Test
public void testmultipleHitsWithText() throws Exception{
ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription(FILE_GAZETTEER, SharedFileResource.class);
AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription(File.class, FILE_GAZETTEER, erd, FILE_NAME, getClass().getResource(GAZETTEER_TXT).getPath(), TYPE, LOCATION);
AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed);
// the same search term appears multiple times in text...
jCas.setDocumentText("Hello world, and hello world again.");
// but then subset using a Text annotation
new Text(jCas, 10, jCas.getDocumentText().length()).addToIndexes();
ae.process(jCas);
assertEquals(1, JCasUtil.select(jCas, Location.class).size());
Location l = JCasUtil.selectByIndex(jCas, Location.class, 0);
assertEquals(WORLD, l.getValue());
assertEquals(WORLD, l.getCoveredText());
assertTrue(l.getBegin() > 10);
ae.destroy();
}
示例10: createNormalizerAEDesc
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
public static AnalysisEngineDescription createNormalizerAEDesc(ResourceConfig resourceConfig, Lang lang, Tagger tagger) {
AnalysisEngineDescription ae;
try {
ae = AnalysisEngineFactory.createEngineDescription(
Lexer.class,
Lexer.PARAM_TYPE, "fr.univnantes.termsuite.types.WordAnnotation"
);
ExternalResourceDescription segmentBank = ExternalResourceFactory.createExternalResourceDescription(
SegmentBankResource.class,
getResourceURL(resourceConfig, ResourceType.SEGMENT_BANK, lang)
);
ExternalResourceFactory.bindResource(
ae,
SegmentBank.KEY_SEGMENT_BANK,
segmentBank);
return ae;
} catch (Exception e) {
throw new TermSuiteException(e);
}
}
示例11: testReference
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@Test
public void testReference() throws Exception{
//This test demonstrates the case where whitespace is preserved in gazetteer matching.
ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription(FILE_GAZETTEER, SharedFileResource.class);
AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription(File.class, FILE_GAZETTEER, erd, FILE_NAME, getClass().getResource(GAZETTEER_TXT).getPath(), TYPE, LOCATION, "exactWhitespace", false);
AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed);
// words in term to search for separated by multiple spaces, tabs or newline...
jCas.setDocumentText("This text mentions New York (also known as NY and the Big Apple).");
ae.process(jCas);
// 3 mentions of "New York" and nicknames...
assertEquals(3, JCasUtil.select(jCas, Location.class).size());
// ...but they're all the same entity, so only one ReferenceTarget
assertEquals(1, JCasUtil.select(jCas, ReferenceTarget .class).size());
Location l = JCasUtil.selectByIndex(jCas, Location.class, 0);
assertEquals(NEW_YORK, l.getValue());
ae.destroy();
}
示例12: beforeTest
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@Override
public void beforeTest() throws UIMAException {
super.beforeTest();
final ExternalResourceDescription tokensDesc = ExternalResourceFactory.createExternalResourceDescription(
"lexica",
ClearNlpLexica.class);
final AnalysisEngineDescription desc = AnalysisEngineFactory.createEngineDescription(ClearNlpTokeniser.class,
"lexica",
tokensDesc);
ae = AnalysisEngineFactory.createEngine(desc);
}
示例13: createAnalysisEngines
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
@Override
protected AnalysisEngine[] createAnalysisEngines() throws ResourceInitializationException {
final ExternalResourceDescription parserChunkingDesc = ExternalResourceFactory
.createExternalResourceDescription("parserChunking", SharedOpenNLPModel.class);
// Add in the OpenNLP implementation too, as its a prerequisite
// (in theory we should test OpenNLPParser in isolation, but in practise
// it as this as a
// dependency
// so better test they work together)
final ExternalResourceDescription tokensDesc = ExternalResourceFactory.createExternalResourceDescription(
"tokens",
SharedOpenNLPModel.class);
final ExternalResourceDescription sentencesDesc = ExternalResourceFactory
.createExternalResourceDescription("sentences", SharedOpenNLPModel.class);
final ExternalResourceDescription posDesc = ExternalResourceFactory.createExternalResourceDescription("posTags",
SharedOpenNLPModel.class);
final ExternalResourceDescription chunksDesc = ExternalResourceFactory
.createExternalResourceDescription("phraseChunks", SharedOpenNLPModel.class);
AnalysisEngineFactory.createEngineDescription();
return asArray(
createAnalysisEngine(OpenNLP.class, "tokens", tokensDesc, "sentences", sentencesDesc, "posTags",
posDesc, "phraseChunks", chunksDesc),
createAnalysisEngine(OpenNLPParser.class, "parserChunking", parserChunkingDesc));
}
示例14: runFeatureExtractor
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
private File runFeatureExtractor(File luceneFolder)
throws Exception
{
File outputPath = folder.newFolder();
Object[] parameters = new Object[] {
TokenContext.PARAM_TARGET_INDEX, "1",
TokenContext.PARAM_UNIQUE_EXTRACTOR_NAME,
EXTRACTOR_NAME, TokenContext.PARAM_SOURCE_LOCATION, luceneFolder.toString(),
LuceneUniGramMetaCollector.PARAM_TARGET_LOCATION, luceneFolder.toString()
};
ExternalResourceDescription featureExtractor = ExternalResourceFactory
.createExternalResourceDescription(TokenContext.class, parameters);
List<ExternalResourceDescription> fes = new ArrayList<>();
fes.add(featureExtractor);
CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(
TestReaderSingleLabel.class, TestReaderSingleLabel.PARAM_LANGUAGE, "en",
TestReaderSingleLabel.PARAM_SOURCE_LOCATION, "src/test/resources/text/input.txt",
TestReaderSingleLabel.PARAM_SUPPRESS_DOCUMENT_ANNOTATION, true);
AnalysisEngineDescription segmenter = AnalysisEngineFactory
.createEngineDescription(BreakIteratorSegmenter.class);
AnalysisEngineDescription unitAnno = AnalysisEngineFactory
.createEngineDescription(EachTokenAsUnitAnnotator.class);
AnalysisEngineDescription featExtractorConnector = TaskUtils.getFeatureExtractorConnector(
outputPath.getAbsolutePath(), JsonDataWriter.class.getName(),
Constants.LM_SINGLE_LABEL, Constants.FM_UNIT, DenseFeatureStore.class.getName(),
false, false, false, new ArrayList<>(), false, fes);
SimplePipeline.runPipeline(reader, segmenter, unitAnno, featExtractorConnector);
return outputPath;
}
示例15: getReader
import org.apache.uima.fit.factory.ExternalResourceFactory; //导入方法依赖的package包/类
public CollectionReaderDescription getReader(String type) throws ResourceInitializationException {
CollectionReaderDescription reader = null;
if (type.equals("csv")) {
reader = CollectionReaderFactory.createReaderDescription(
NewsleakCsvStreamReader.class, this.typeSystem,
NewsleakCsvStreamReader.PARAM_DOCUMENT_FILE, this.documentFile,
NewsleakCsvStreamReader.PARAM_METADATA_FILE, this.metadataFile,
NewsleakCsvStreamReader.PARAM_INPUTDIR, this.dataDirectory,
NewsleakCsvStreamReader.PARAM_DEFAULT_LANG, this.defaultLanguage,
NewsleakCsvStreamReader.PARAM_DEBUG_MAX_DOCS, this.debugMaxDocuments
);
} else if (type.equals("hoover")) {
this.metadataFile = this.hooverTmpMetadata;
ExternalResourceDescription hooverResource = ExternalResourceFactory.createExternalResourceDescription(
HooverResource.class,
HooverResource.PARAM_METADATA_FILE, this.dataDirectory + File.separator + this.metadataFile,
HooverResource.PARAM_HOST, this.hooverHost,
HooverResource.PARAM_CLUSTERNAME, this.hooverClustername,
HooverResource.PARAM_INDEX, this.hooverIndex,
HooverResource.PARAM_PORT, this.hooverPort
);
reader = CollectionReaderFactory.createReaderDescription(
HooverElasticsearchReader.class, this.typeSystem,
HooverElasticsearchReader.RESOURCE_HOOVER, hooverResource,
HooverElasticsearchReader.PARAM_DEFAULT_LANG, this.defaultLanguage,
HooverElasticsearchReader.PARAM_DEBUG_MAX_DOCS, this.debugMaxDocuments
);
} else {
this.logger.log(Level.SEVERE, "Unknown reader type: " + type);
System.exit(1);
}
return reader;
}