Java ExternalResourceFactory类代码示例

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的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);
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的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));
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的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);

}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Before
public void setUp() throws Exception {
    daoDesc = ExternalResourceFactory.createExternalResourceDescription(
            XmiFileTreeCorpusDAOResource.class, corpusPathString);
    tsd = CasCreationUtils
            .mergeTypeSystems(Sets.newHashSet(
                    XmiFileTreeCorpusDAO.getTypeSystem(corpusPathString),
                    TypeSystemDescriptionFactory
                            .createTypeSystemDescription(),
                    TokenizerAPI.getTypeSystemDescription(),
                    SentenceSplitterAPI.getTypeSystemDescription()));
    readerDesc = CollectionReaderFactory.createReaderDescription(
            CorpusDAOCollectionReader.class, tsd,
            CorpusDAOCollectionReader.CORPUS_DAO_KEY, daoDesc);
    CAS aCAS = CasCreationUtils.createCas(tsd, null, null, null);
    tokenizerSentenceSplitterDesc = AnalysisEngineFactory
            .createEngineDescription(Unitizer.createTokenizerSentenceSplitterAED());
    unitAnnotatorDesc = AnalysisEngineFactory.createEngineDescription(
            UnitAnnotator.class, UnitAnnotator.PARAM_UNIT_TYPE_NAMES,
            unitTypes);
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Before
public void setUp() throws Exception {
    daoDesc = ExternalResourceFactory.createExternalResourceDescription(
            XmiFileTreeCorpusDAOResource.class, corpusPathString);
    tsd = CasCreationUtils
            .mergeTypeSystems(Sets.newHashSet(
                    XmiFileTreeCorpusDAO.getTypeSystem(corpusPathString),
                    TypeSystemDescriptionFactory
                            .createTypeSystemDescription(),
                    TokenizerAPI.getTypeSystemDescription(),
                    SentenceSplitterAPI.getTypeSystemDescription()));
    reader = CollectionReaderFactory.createReaderDescription(
            CorpusDAOCollectionReader.class, tsd,
            CorpusDAOCollectionReader.CORPUS_DAO_KEY, daoDesc);
    CAS aCAS = CasCreationUtils.createCas(tsd, null, null, null);
    tokenizerSentenceSplitter = Unitizer.createTokenizerSentenceSplitterAED();
    unitAnnotator = AnalysisEngineFactory.createEngineDescription(
            UnitAnnotator.class, UnitAnnotator.PARAM_UNIT_TYPE_NAMES,
            unitTypes);
    unitClassifier = AnalysisEngineFactory.createEngineDescription(
            UnitClassifier.class, UnitClassifier.PARAM_CLASS_TYPE_NAMES,
            classTypes);
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void testChunks() throws Exception{
	ExternalResourceDescription tokensDesc = ExternalResourceFactory.createExternalResourceDescription("tokens", SharedOpenNLPModel.class);
	ExternalResourceDescription sentencesDesc = ExternalResourceFactory.createExternalResourceDescription("sentences", SharedOpenNLPModel.class);
	ExternalResourceDescription posDesc = ExternalResourceFactory.createExternalResourceDescription("posTags", SharedOpenNLPModel.class);
	ExternalResourceDescription chunksDesc = ExternalResourceFactory.createExternalResourceDescription("phraseChunks", SharedOpenNLPModel.class);

	AnalysisEngineDescription descNLP = AnalysisEngineFactory.createEngineDescription(OpenNLP.class, "tokens", tokensDesc, "sentences", sentencesDesc, "posTags", posDesc, "phraseChunks", chunksDesc);
	AnalysisEngine aeNLP = AnalysisEngineFactory.createEngine(descNLP);
	
	AnalysisEngine ae = AnalysisEngineFactory.createEngine(TestAnnotator.class);
	
	jCas.setDocumentText("PERSON JOHN SMITH WAS SEEN ENTERING THE WAREHOUSE");
	aeNLP.process(jCas);
	ae.process(jCas);
	
	assertEquals(1, JCasUtil.select(jCas, Person.class).size());
	assertEquals("JOHN SMITH", JCasUtil.selectByIndex(jCas, Person.class, 0).getValue());
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void testProperty() throws Exception{
	ExternalResourceDescription erd = ExternalResourceFactory.createExternalResourceDescription(MONGO, SharedFongoResource.class, FONGO_COLLECTION, MONGO_COLL, FONGO_DATA, JSON.serialize(GAZ_DATA));
	AnalysisEngineDescription aed = AnalysisEngineFactory.createEngineDescription(MongoRegex.class, MONGO, erd, COLLECTION, MONGO_COLL, TYPE, LOCATION, REGEX, LONDON_REGEX);
	
	AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed);
	
	jCas.setDocumentText(TEXT);
	
	ae.process(jCas);
	
	assertEquals(1, JCasUtil.select(jCas, Location.class).size());
	Location l = JCasUtil.selectByIndex(jCas, Location.class, 0);
	assertEquals("London", l.getValue());
	assertEquals("London", l.getCoveredText());
	assertEquals("Property_Test", l.getGeoJson());
	
	ae.destroy();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void test() 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);

	jCas.setDocumentText("Hello world, this is a test");

	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());

	ae.destroy();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void testmultipleHits() 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.");

	ae.process(jCas);

	assertEquals(2, JCasUtil.select(jCas, Location.class).size());
	Location l = JCasUtil.selectByIndex(jCas, Location.class, 0);
	assertEquals(WORLD, l.getValue());
	assertEquals(WORLD, l.getCoveredText());

	ae.destroy();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void testCaseSensitive() 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, "caseSensitive", true);

	AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed);

	jCas.setDocumentText("This text mentions New York and Paris in upper case and new york in lower case");

	ae.process(jCas);

	// should match "new york" and "Paris", but not "New York"
	assertEquals(2, JCasUtil.select(jCas, Location.class).size());
	Location l1 = JCasUtil.selectByIndex(jCas, Location.class, 0);
	Location l2 = JCasUtil.selectByIndex(jCas, Location.class, 1);
	assertEquals("Paris", l1.getValue());
	assertEquals("new york", l2.getValue());

	ae.destroy();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void testPlurals() throws Exception{
	//This test demonstrates pluralisation in the gazetteer

	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, "plural", true);

	AnalysisEngine ae = AnalysisEngineFactory.createEngine(aed);

	jCas.setDocumentText("There may be many New Yorks and many Parises, but there's only one London.");

	ae.process(jCas);

	assertEquals(3, JCasUtil.select(jCas, Location.class).size());
	Location l1 = JCasUtil.selectByIndex(jCas, Location.class, 0);
	Location l2 = JCasUtil.selectByIndex(jCas, Location.class, 1);
	Location l3 = JCasUtil.selectByIndex(jCas, Location.class, 2);
	assertEquals("New Yorks", l1.getValue());
	assertEquals("Parises", l2.getValue());
	assertEquals("London", l3.getValue());

	ae.destroy();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void testWhitespaceExact() 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);

	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, and New    York again, and New	York again, and New \nYork yet again");

	ae.process(jCas);

	// only one mention of "New York" has the two words separated by a single space (as in the gazetteer)
	assertEquals(1, JCasUtil.select(jCas, Location.class).size());
	Location l = JCasUtil.selectByIndex(jCas, Location.class, 0);
	assertEquals(NEW_YORK, l.getValue());

	ae.destroy();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的package包/类
@Test
public void testWhitespaceNormalized() 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, and New    York again, and New	York again, and New \nYork yet again");

	ae.process(jCas);

	// Three mentions of "New York" if we reduce any whitespace to a single space (exactWhitespace parameter, which ignores new lines)
	assertEquals(3, JCasUtil.select(jCas, Location.class).size());
	Location l = JCasUtil.selectByIndex(jCas, Location.class, 0);
	assertEquals(NEW_YORK, l.getValue());

	ae.destroy();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的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();
}
 

import org.apache.uima.fit.factory.ExternalResourceFactory; //导入依赖的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();
}