Java CollectionReaderFactory类代码示例

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void main(String[] args) throws ResourceInitializationException, UIMAException, IOException {
	SimplePipeline.runPipeline(
			CollectionReaderFactory.createReaderDescription(TextgridTEIUrlReader.class,
					TextgridTEIUrlReader.PARAM_INPUT, "http://www.textgridrep.org/textgrid:tx4z.0",
					TextgridTEIUrlReader.PARAM_CLEANUP, true),
			AnalysisEngineFactory.createEngineDescription(XmiWriter.class, XmiWriter.PARAM_USE_DOCUMENT_ID, true,
					XmiWriter.PARAM_TARGET_LOCATION, "src/test/resources/SpeakerAssignmentRules/"));

	SimplePipeline.runPipeline(
			CollectionReaderFactory.createReaderDescription(TextgridTEIUrlReader.class,
					TextgridTEIUrlReader.PARAM_INPUT, "http://www.textgridrep.org/textgrid:w3zd.0",
					TextgridTEIUrlReader.PARAM_CLEANUP, true),
			AnalysisEngineFactory.createEngineDescription(XmiWriter.class, XmiWriter.PARAM_USE_DOCUMENT_ID, true,
					XmiWriter.PARAM_TARGET_LOCATION, "src/test/resources/SpeakerAssignmentRules/"));

	new File("src/test/resources/SpeakerAssignmentRules/typesystem.xml").delete();
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void exportToHTML(File inputFile, File outputFile)
        throws Exception
{
    File intermediateXMIsFile = File.createTempFile("temp", ".xmi.tar.gz");

    SingleXMLToXMIExporter.exportToXMIs(inputFile, intermediateXMIsFile);

    SimplePipeline.runPipeline(
            CollectionReaderFactory.createReaderDescription(
                    CompressedXmiReader.class,
                    CompressedXmiReader.PARAM_SOURCE_LOCATION, intermediateXMIsFile
            ),
            AnalysisEngineFactory.createEngineDescription(ArgumentsToHTMLExporter.class,
                    ArgumentsToHTMLExporter.PARAM_OUTPUT_FILE, outputFile),
            AnalysisEngineFactory.createEngineDescription(
                    ArgumentDumpWriter.class
            )
    );

    Files.delete(intermediateXMIsFile.toPath());
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void main(String[] args)
        throws Exception
{
    String in = "/tmp/temp-in";
    String out = "/tmp/out2.tar.gz";
    // test it
    SimplePipeline.runPipeline(CollectionReaderFactory.createReaderDescription(
            XmiReader.class,
            XmiReader.PARAM_SOURCE_LOCATION, in,
            XmiReader.PARAM_PATTERNS, XmiReader.INCLUDE_PREFIX + "*.xmi"
            ),
            AnalysisEngineFactory.createEngineDescription(
                    NoOpAnnotator.class
            ),
            AnalysisEngineFactory.createEngineDescription(
                    CompressedXmiWriter.class,
                    CompressedXmiWriter.PARAM_OUTPUT_FILE, out
            )
    );

}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void main(String[] args) throws UIMAException, IOException {

		Logger.getRootLogger().setLevel(Level.INFO);

		if (args.length > 0)
			textFolder = args[0];

		// read preprocessed documents
		CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(BinaryCasReader.class,
				BinaryCasReader.PARAM_SOURCE_LOCATION, textFolder, BinaryCasReader.PARAM_PATTERNS, textPattern,
				BinaryCasReader.PARAM_LANGUAGE, "en");

		// find Open IE tuples
		AnalysisEngineDescription openIE = AnalysisEngineFactory.createEngineDescription(OpenIEAnnotator.class);

		// write annotated data to file
		AnalysisEngineDescription writer = AnalysisEngineFactory.createEngineDescription(BinaryCasWriter.class,
				BinaryCasWriter.PARAM_TARGET_LOCATION, textFolder, BinaryCasWriter.PARAM_STRIP_EXTENSION, true,
				BinaryCasWriter.PARAM_FILENAME_EXTENSION, ".oie.bin6", BinaryCasWriter.PARAM_OVERWRITE, true);

		// run pipeline
		SimplePipeline.runPipeline(reader, openIE, writer);
	}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public void run()
    throws Exception
{
    String language = "en";
    String trainCorpora = DemoConstants.TRAIN_FOLDER_CROSS_VALIDATION;
    String trainFileSuffix = "*.txt";

    CollectionReaderDescription crd = CollectionReaderFactory.createReaderDescription(
            LineTokenTagReader.class, LineTokenTagReader.PARAM_LANGUAGE, language,
            LineTokenTagReader.PARAM_SOURCE_LOCATION, trainCorpora,
            LineTokenTagReader.PARAM_PATTERNS, trainFileSuffix);

    FlexTagCrossValidation flex = new FlexTagCrossValidation(crd, 2);

    if (System.getProperty("DKPRO_HOME") == null) {
        flex.setDKProHomeFolder("target/home");
    }
    flex.setExperimentName("WekaCrossValidationDemo");

    flex.setFeatures(TcFeatureFactory.create(LuceneCharacterNGram.class));
    
    List<Object> configuration = asList(new Object[] { J48.class.getName() });
    flex.setClassifier(Classifier.WEKA, configuration);
    flex.addReport(CvWekafAvgKnownUnknownAccuracyReport.class);
    flex.execute();
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
private static void trainModel(String folder)
    throws Exception
{
    String language = "en";
    String corpora = DemoConstants.TRAIN_FOLDER;
    String fileSuffix = "*.txt";

    CollectionReaderDescription trainReader = CollectionReaderFactory.createReaderDescription(
            LineTokenTagReader.class, LineTokenTagReader.PARAM_LANGUAGE, language,
            LineTokenTagReader.PARAM_SOURCE_LOCATION, corpora,
            LineTokenTagReader.PARAM_PATTERNS, fileSuffix);

    FlexTagTrainSaveModel flex = new FlexTagTrainSaveModel(trainReader, new File(folder));

    flex.setFeatures(TcFeatureFactory.create(BrownCluster.class,
            BrownCluster.PARAM_RESOURCE_LOCATION, DemoConstants.BROWN_CLUSTER));

    if (System.getProperty("DKPRO_HOME") == null) {
        flex.setDKProHomeFolder("target/home");
    }
    flex.setExperimentName("ExampleUseModelDemo");
    flex.execute();
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public void run()
    throws Exception
{
    String modelFolder = "target/theModel";
    // train the model we will use later
    trainModel(modelFolder);

    CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(
            TextReader.class, TextReader.PARAM_SOURCE_LOCATION,
            "src/main/resources/raw/rawText.txt", TextReader.PARAM_LANGUAGE, "en");

    AnalysisEngineDescription seg = AnalysisEngineFactory
            .createEngineDescription(BreakIteratorSegmenter.class);
    AnalysisEngineDescription tagger = AnalysisEngineFactory.createEngineDescription(
            FlexTagUima.class, FlexTagUima.PARAM_LANGUAGE, "en",
            FlexTagUima.PARAM_MODEL_LOCATION, modelFolder);

    // a helper class which simply iterates each token and prints the predicted POS tag
    AnalysisEngineDescription printer = AnalysisEngineFactory
            .createEngineDescription(OutputPrinter.class);

    SimplePipeline.runPipeline(reader, seg, tagger, printer);
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
private static void trainModel(String folder)
    throws Exception
{
    String language = "en";
    String corpora = DemoConstants.TRAIN_FOLDER;
    String fileSuffix = "*.txt";
    
    CollectionReaderDescription trainReader = CollectionReaderFactory.createReaderDescription(
            LineTokenTagReader.class, LineTokenTagReader.PARAM_LANGUAGE, language,
            LineTokenTagReader.PARAM_SOURCE_LOCATION, corpora,
            LineTokenTagReader.PARAM_PATTERNS, fileSuffix);

    FlexTagTrainSaveModel flex = new FlexTagTrainSaveModel(trainReader, new File(folder));

    if (System.getProperty("DKPRO_HOME") == null) {
        flex.setDKProHomeFolder("target/home");
    }
    flex.setFeatures(DefaultFeatures.getDefaultFeatures(Classifier.CRFSUITE));
    flex.setExperimentName("ExampleUseModelDemo");
    flex.execute();
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
private void runMetaCollection(File luceneFolder)
    throws Exception
{

    Object[] parameters = new Object[] { LuceneUniGramMetaCollector.PARAM_UNIQUE_EXTRACTOR_NAME,
            EXTRACTOR_NAME,
            TokenContext.PARAM_SOURCE_LOCATION, luceneFolder.toString(),
            LuceneUniGramMetaCollector.PARAM_TARGET_LOCATION, luceneFolder.toString()
            };

    List<Object> parameterList = new ArrayList<Object>(Arrays.asList(parameters));

    CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(
            TestReaderSingleLabel.class, TestReaderSingleLabel.PARAM_LANGUAGE, "en",
            TestReaderSingleLabel.PARAM_SOURCE_LOCATION, "src/test/resources/text/input.txt");

    AnalysisEngineDescription segmenter = AnalysisEngineFactory
            .createEngineDescription(BreakIteratorSegmenter.class);

    AnalysisEngineDescription metaCollector = AnalysisEngineFactory
            .createEngineDescription(LuceneUniGramMetaCollector.class, parameterList.toArray());

    // run meta collector
    SimplePipeline.runPipeline(reader, segmenter, metaCollector);
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
  if (args.length != 3) {
    System.out.println("arguments: " //
            + "path to XML descriptor for pipeline, " //
            + "folder with text files, " //
            + "folder to output xmi files");
    System.exit(-1);
  }

  // A collection reader that reads text files
  CollectionReader reader = CollectionReaderFactory.createReader(FilesCollectionReader.class,
          null, FilesCollectionReader.PARAM_ROOT_FILE, args[1]);

  AggregateBuilder builder = new AggregateBuilder();
  AnalysisEngineDescription descriptor = (AnalysisEngineDescription) createResourceCreationSpecifier(
          new XMLInputSource(RunPipelineXmi.class.getClassLoader().getResourceAsStream(args[0]),
                  new File(".")), new Object[0]);
  builder.add(descriptor);
  builder.add(XmiWriter.getDescription(new File(args[2])));
  
  SimplePipeline.runPipeline(reader, builder.createAggregateDescription());
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
  if (args.length != 3) {
    System.out.println("arguments: " //
            + "path to XML descriptor for pipeline, " //
            + "folder with text files, " //
            + "path to output tsv file");
    System.exit(-1);
  }

  // A collection reader that reads text files
  CollectionReader reader = CollectionReaderFactory.createReader(FilesCollectionReader.class,
          null, FilesCollectionReader.PARAM_ROOT_FILE, args[1]);

  AggregateBuilder builder = new AggregateBuilder();
  AnalysisEngineDescription descriptor = (AnalysisEngineDescription) createResourceCreationSpecifier(
          new XMLInputSource(RunPipelineTsv.class.getClassLoader().getResourceAsStream(args[0]),
                  new File(".")), new Object[0]);
  builder.add(descriptor);
  builder.add(TsvWriter.getDescription(new File(args[2])));

  SimplePipeline.runPipeline(reader, builder.createAggregateDescription());
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
	// A collection reader that reads XMIs
	CollectionReader reader = CollectionReaderFactory.createReader(XReader.class, null, XReader.PARAM_ROOT_FILE,
			args[0]);

	// The pipeline of annotators
	AggregateBuilder builder = new AggregateBuilder();

	// other annotators, if needed
	builder.add(UIMAFramework.getXMLParser().parseAnalysisEngineDescription(
			new XMLInputSource("src/main/resources/org/ie4opendata/octroy/SimpleFrenchTokenAndSentenceAnnotator.xml")));

	// Use this to get the parameters for the descriptor
	//System.out.println(ReasonAnnotator.getClassifierDescription("org/ie4opendata/octroy/reason/model.jar"));
	//System.exit(0);
	// The reason classifier annotator, configured to write training data
	builder.add(ReasonAnnotator.getWriterDescription("src/main/resources/org/ie4opendata/octroy/reason"));

	// Run the pipeline of annotators on each of the CASes produced by the reader
	SimplePipeline.runPipeline(reader, builder.createAggregateDescription());

	// Train a classifier on the training data, and package it into a .jar file
	Train.main("src/main/resources/org/ie4opendata/octroy/reason");
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
	CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(XmiReader.class,
			XmiReader.PARAM_SOURCE_LOCATION, "src/main/resources/gender/*/*.xmi", XmiReader.PARAM_LENIENT, true);

	String tmpView = "DP";

	AggregateBuilder b = new AggregateBuilder();

	b.add(AnalysisEngineFactory.createEngineDescription(PrepareClearTk.class, PrepareClearTk.PARAM_VIEW_NAME,
			tmpView, PrepareClearTk.PARAM_ANNOTATION_TYPE, DramatisPersonae.class,
			PrepareClearTk.PARAM_SUBANNOTATIONS, Arrays.asList(Figure.class)));
	b.add(AnalysisEngineFactory.createEngineDescription(BreakIteratorSegmenter.class), CAS.NAME_DEFAULT_SOFA,
			tmpView);
	b.add(AnalysisEngineFactory.createEngineDescription(ClearTkGenderAnnotator.class,
			DefaultDataWriterFactory.PARAM_DATA_WRITER_CLASS_NAME, LibSvmStringOutcomeDataWriter.class,
			DirectoryDataWriterFactory.PARAM_OUTPUT_DIRECTORY, "target/models"), CAS.NAME_DEFAULT_SOFA, tmpView);
	b.add(AnalysisEngineFactory.createEngineDescription(XmiWriter.class, XmiWriter.PARAM_TARGET_LOCATION,
			"target/xmi"));
	SimplePipeline.runPipeline(reader, b.createAggregateDescription());

	Train.main(new File("target/models"), new String[] { "-t", "0" });
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
@Test
public void testRules1() throws Exception {
	org.apache.uima.fit.pipeline.JCasIterator iter = SimplePipeline.iteratePipeline(
			CollectionReaderFactory.createReaderDescription(XmiReader.class, XmiReader.PARAM_SOURCE_LOCATION,
					"src/test/resources/SpeakerAssignmentRules/tx4z.0.xmi", XmiReader.PARAM_LENIENT, true),
			AnalysisEngineFactory.createEngineDescription(FigureReferenceAnnotator.class),
			AnalysisEngineFactory.createEngineDescription(SpeakerAssignmentRules.class,
					SpeakerAssignmentRules.PARAM_RULE_FILE_URL,
					new File("src/test/resources/SpeakerAssignmentRules/speaker-assignment-mapping.tsv").toURI()
							.toURL()))
			.iterator();
	if (iter.hasNext()) {
		JCas jcas = iter.next();
		for (Speaker speaker : JCasUtil.select(jcas, Speaker.class)) {
			if (speaker.getCoveredText().equalsIgnoreCase("carlos"))
				assertNotNull(speaker.getCoveredText(), speaker.getFigure());
		}
	}
}
 

import org.apache.uima.fit.factory.CollectionReaderFactory; //导入依赖的package包/类
@Test
public void testRules2() throws Exception {
	org.apache.uima.fit.pipeline.JCasIterator iter = SimplePipeline.iteratePipeline(
			CollectionReaderFactory.createReaderDescription(XmiReader.class, XmiReader.PARAM_SOURCE_LOCATION,
					"src/test/resources/SpeakerAssignmentRules/w3zd.0.xmi", XmiReader.PARAM_LENIENT, true),
			AnalysisEngineFactory.createEngineDescription(FigureReferenceAnnotator.class),
			AnalysisEngineFactory.createEngineDescription(SpeakerAssignmentRules.class,
					SpeakerAssignmentRules.PARAM_RULE_FILE_URL,
					new File("src/test/resources/SpeakerAssignmentRules/speaker-assignment-mapping.tsv").toURI()
							.toURL()))
			.iterator();
	assertTrue(iter.hasNext());
	JCas jcas = iter.next();
	assertNotNull(jcas);
	for (Speaker speaker : JCasUtil.select(jcas, Speaker.class)) {
		if (speaker.getCoveredText().equalsIgnoreCase("der capitain"))
			assertNotNull(speaker.getCoveredText(), speaker.getFigure());
	}
}