List of usage examples for org.apache.commons.io FileUtils openOutputStream
public static FileOutputStream openOutputStream(File file) throws IOException
From source file:com.textocat.textokit.morph.lemmatizer.util.GenerateNormalizedTextWriterDescriptor.java
public static void main(String[] args) throws ResourceInitializationException, IOException, SAXException { AnalysisEngineDescription anDesc = createEngineDescription(NormalizedTextWriter.class); try (FileOutputStream out = FileUtils.openOutputStream(new File( "src/main/resources/" + NormalizedTextWriter.class.getName().replace('.', '/') + ".xml"))) { anDesc.toXML(new BufferedOutputStream(out)); }/* w w w . j a va 2 s .c o m*/ }
From source file:com.textocat.textokit.segmentation.GenerateOSPLSplitterDescriptor.java
public static void main(String[] args) throws UIMAException, IOException, SAXException { String outputPath = "src/main/resources/" + OneSentencePerLineSplitter.class.getName().replace('.', '/') + ".xml"; AnalysisEngineDescription desc = OneSentencePerLineSplitter.createDescription(); FileOutputStream out = FileUtils.openOutputStream(new File(outputPath)); try {/* ww w.j a v a2s . c om*/ desc.toXML(out); } finally { IOUtils.closeQuietly(out); } }
From source file:com.textocat.textokit.segmentation.GenerateParagraphSplitterDescriptor.java
public static void main(String[] args) throws UIMAException, IOException, SAXException { String outputPath = "src/main/resources/" + ParagraphSplitter.class.getName().replace('.', '/') + ".xml"; TypeSystemDescription tsDesc = SentenceSplitterAPI.getTypeSystemDescription(); AnalysisEngineDescription desc = createEngineDescription(ParagraphSplitter.class, tsDesc); FileOutputStream out = FileUtils.openOutputStream(new File(outputPath)); try {//w ww .j av a 2 s.co m desc.toXML(out); } finally { IOUtils.closeQuietly(out); } }
From source file:com.textocat.textokit.segmentation.GenerateSentenceSplitterDescriptor.java
public static void main(String[] args) throws UIMAException, IOException, SAXException { String outputPath = "src/main/resources/" + SentenceSplitterAPI.AE_SENTENCE_SPLITTER.replace('.', '/') + ".xml"; TypeSystemDescription tsDesc = SentenceSplitterAPI.getTypeSystemDescription(); AnalysisEngineDescription desc = createEngineDescription(SentenceSplitter.class, tsDesc); FileOutputStream out = FileUtils.openOutputStream(new File(outputPath)); try {/*w w w . j a v a2 s. c o m*/ desc.toXML(out); } finally { IOUtils.closeQuietly(out); } }
From source file:com.textocat.textokit.postagger.opennlp.GeneratePipelineDescriptorForOpenNLPPosTagger.java
public static void main(String[] args) throws UIMAException, IOException, SAXException { if (args.length != 1) { System.err.println("Provide output path!"); System.exit(1);/*from w ww . ja v a2s . co m*/ } File outFile = new File(args[0]); // AnalysisEngineDescription outDesc = getDescription(); OutputStream out = FileUtils.openOutputStream(outFile); try { outDesc.toXML(out); } finally { IOUtils.closeQuietly(out); } }
From source file:com.textocat.textokit.segmentation.GenerateBasicAggregateDescriptor.java
/** * @param args//from w w w . j av a 2s. c o m * @throws ResourceInitializationException */ public static void main(String[] args) throws UIMAException, IOException, SAXException { Map<String, MetaDataObject> aeDescriptions = Maps.newLinkedHashMap(); aeDescriptions.put("tokenizer", TokenizerAPI.getAEImport()); aeDescriptions.put("sentenceSplitter", SentenceSplitterAPI.getAEImport()); String outputPath = "desc/basic-aggregate.xml"; AnalysisEngineDescription desc = PipelineDescriptorUtils.createAggregateDescription(aeDescriptions); FileOutputStream out = FileUtils.openOutputStream(new File(outputPath)); try { desc.toXML(out); } finally { IOUtils.closeQuietly(out); } }
From source file:com.textocat.textokit.dictmatcher.GenerateTypedDictionaryAnnotatorDesc.java
public static void main(String[] args) throws ResourceInitializationException, IOException, SAXException { String relOutPath = (DictionaryAnnotator.class.getName() + "-typed").replace('.', '/') + ".xml"; TypeSystemDescription tsd = TypeSystemDescriptionFactory .createTypeSystemDescription("com.textocat.textokit.dictmatcher.ts-dictmatcher"); AnalysisEngineDescription desc = AnalysisEngineFactory.createEngineDescription(DictionaryAnnotator.class, tsd, PARAM_CHUNK_ADAPTER_CLASS, TypedChunkAnnotationAdapter.class.getName()); ConfigurationParameterFactory.addConfigurationParameters(desc, TypedChunkAnnotationAdapter.class); try (FileOutputStream os = FileUtils.openOutputStream(new File("src/main/resources/" + relOutPath))) { desc.toXML(os);/*from w w w . jav a 2 s.c o m*/ } }
From source file:com.textocat.textokit.dictmatcher.GenerateTaggedDictionaryAnnotatorDesc.java
public static void main(String[] args) throws ResourceInitializationException, IOException, SAXException { String relOutPath = (DictionaryAnnotator.class.getName() + "-tagged").replace('.', '/') + ".xml"; TypeSystemDescription tsd = TypeSystemDescriptionFactory .createTypeSystemDescription("com.textocat.textokit.dictmatcher.ts-dictmatcher"); AnalysisEngineDescription desc = AnalysisEngineFactory.createEngineDescription(DictionaryAnnotator.class, tsd, PARAM_CHUNK_ADAPTER_CLASS, TaggedChunkAnnotationAdapter.class.getName(), PARAM_RESULT_ANNOTATION_TYPE, DictionaryMatch.class.getName(), PARAM_TAG_FEATURE, "tag"); try (FileOutputStream os = FileUtils.openOutputStream(new File("src/main/resources/" + relOutPath))) { desc.toXML(os);//from ww w . j a v a 2 s . c om } }
From source file:com.textocat.textokit.morph.opencorpora.resource.XmlDictionaryParserLauncher.java
public static void main(String[] args) throws Exception { XmlDictionaryParserLauncher cfg = new XmlDictionaryParserLauncher(); new JCommander(cfg, args); MorphDictionaryImpl dict = new MorphDictionaryImpl(); DictionaryExtension ext = cfg.dictExtensionClass.newInstance(); FileInputStream fis = FileUtils.openInputStream(cfg.dictXmlFile); try {/* ww w . j a v a 2 s .c om*/ new XmlDictionaryParser(dict, ext, fis).run(); } finally { IOUtils.closeQuietly(fis); } log.info("Preparing to serialization..."); long timeBefore = currentTimeMillis(); OutputStream fout = new BufferedOutputStream(FileUtils.openOutputStream(cfg.outputFile), 8192 * 8); ObjectOutputStream out = new ObjectOutputStream(fout); try { out.writeObject(dict.getGramModel()); out.writeObject(dict); } finally { out.close(); } log.info("Serialization finished in {} ms.\nOutput size: {} bytes", currentTimeMillis() - timeBefore, cfg.outputFile.length()); }
From source file:com.textocat.textokit.morph.opencorpora.resource.XmlDictionaryPSP.java
public static void main(String[] args) throws Exception { XmlDictionaryPSP cfg = new XmlDictionaryPSP(); new JCommander(cfg, args); MorphDictionaryImpl dict = new MorphDictionaryImpl(); DictionaryExtension ext = cfg.dictExtensionClass.newInstance(); FileInputStream fis = FileUtils.openInputStream(cfg.dictXmlFile); try {// ww w. j a va 2 s. co m new XmlDictionaryParser(dict, ext, fis).run(); } finally { IOUtils.closeQuietly(fis); } System.out.println("Preparing to serialization..."); long timeBefore = currentTimeMillis(); OutputStream fout = new BufferedOutputStream(FileUtils.openOutputStream(cfg.outputJarFile), 8192 * 8); Manifest manifest = new Manifest(); manifest.getMainAttributes().putValue(Attributes.Name.MANIFEST_VERSION.toString(), "1.0"); manifest.getMainAttributes().putValue(OpencorporaMorphDictionaryAPI.ME_OPENCORPORA_DICTIONARY_VERSION, dict.getVersion()); manifest.getMainAttributes().putValue(OpencorporaMorphDictionaryAPI.ME_OPENCORPORA_DICTIONARY_REVISION, dict.getRevision()); manifest.getMainAttributes().putValue(OpencorporaMorphDictionaryAPI.ME_OPENCORPORA_DICTIONARY_VARIANT, cfg.variant); String dictEntryName = String.format( OpencorporaMorphDictionaryAPI.FILENAME_PATTERN_OPENCORPORA_SERIALIZED_DICT, dict.getVersion(), dict.getRevision(), cfg.variant); JarOutputStream jarOut = new JarOutputStream(fout, manifest); jarOut.putNextEntry(new ZipEntry(dictEntryName)); ObjectOutputStream serOut = new ObjectOutputStream(jarOut); try { serOut.writeObject(dict.getGramModel()); serOut.writeObject(dict); } finally { serOut.flush(); jarOut.closeEntry(); serOut.close(); } System.out.println(String.format("Serialization finished in %s ms.\nOutput size: %s bytes", currentTimeMillis() - timeBefore, cfg.outputJarFile.length())); }