List of usage examples for org.apache.commons.io Charsets UTF_8
Charset UTF_8
To view the source code for org.apache.commons.io Charsets UTF_8.
Click Source Link
Eight-bit Unicode Transformation Format.
From source file:org.datacleaner.cli.GrouperIT.java
private void checkOutputFileForInconsistencies(final String filePath) { try {/*from ww w . j a v a 2s.c om*/ final List<String> lines = Files.readLines(new File(filePath), Charsets.UTF_8); for (int i = 1; i < lines.size(); i++) { // skipping header final String[] values = lines.get(i).split(";"); final int grouperCount = Integer.parseInt(StringUtils.strip(values[0], "\"")); final String[] idList = values[1].split(","); final int expectedCount = EXPECTED_GROUP_LENGTHS[i - 1]; if (grouperCount != idList.length || grouperCount != expectedCount) { fail(String.format("Size inconsistency at line: %d (%d != %d || %d != %d)", i, grouperCount, idList.length, grouperCount, expectedCount)); } } } catch (IOException e) { fail(e.getMessage()); } }
From source file:org.dederem.common.service.VersionAnalyseService.java
/** * Read method for "Packages" file.//from w w w . j a v a2 s .c o m * * @param input * InputStream on the text file * @return The object populated with the content of the file. * @throws IOException * I/O error. */ public final DebVersion analyzeFile(final String suite, final InputStream input) throws IOException { final DebVersion result = new DebVersion(); final Map<String, StringBuilder> data = new HashMap<>(); StringBuilder lastData = null; // NOPMD - init final BufferedReader reader = new BufferedReader(new InputStreamReader(input, Charsets.UTF_8)); String line = reader.readLine(); while (line != null) { if (line.isEmpty()) { // manage the end of the bloc final DebPackageDesc pkgDesc = this.readPackageDesc(data); if (pkgDesc != null) { // check if file already present in the repository final DebPackageDesc local = this.repoService.getPackageInLocalRepo(suite, pkgDesc.getDebPackage()); if (local == null) { // add the package to package list. result.getPackages().add(pkgDesc); } else { if (this.repoService.checkPackageEquality(pkgDesc, local)) { // add the package to package list. result.getPackages().add(local); } else { // add the package to package list. result.getPackages().add(pkgDesc); } } } data.clear(); } else { // manage a new entry in the current bloc if (Character.isWhitespace(line.charAt(0))) { if (lastData != null) { lastData.append(line); } } else { final String key = StringUtils.substringBefore(line, ":"); final String value = StringUtils.substringAfter(line, ":"); lastData = new StringBuilder(value); data.put(key, lastData); } } line = reader.readLine(); } result.setSuite(suite); return result; }
From source file:org.dice_research.topicmodeling.io.json.stream.JsonWritingDocumentConsumer.java
public static JsonWritingDocumentConsumer createJsonWritingDocumentConsumer(OutputStream out) { Writer writer = null;//from w w w . java 2 s . c o m try { writer = new OutputStreamWriter(new BufferedOutputStream(out), Charsets.UTF_8); JsonWritingDocumentConsumer consumer = new JsonWritingDocumentConsumer(writer); consumer.writeHead(); return consumer; } catch (Exception e) { LOGGER.error("Error while trying to write corpus to XML file. Returning null.", e); IOUtils.closeQuietly(writer); } return null; }
From source file:org.dice_research.topicmodeling.io.json.stream.StreamBasedJsonDocumentSupplier.java
public static StreamBasedJsonDocumentSupplier createReader(File file, boolean useDocumentIdsFromFile) { Reader reader;/* w w w. jav a2 s . com*/ try { reader = new InputStreamReader(new FileInputStream(file), Charsets.UTF_8); } catch (IOException e) { LOGGER.error("Couldn't create FileReader. Returning null.", e); return null; } return createReader(reader, useDocumentIdsFromFile); }
From source file:org.dice_research.topicmodeling.io.json.stream.StreamBasedJsonDocumentSupplier.java
public static StreamBasedJsonDocumentSupplier createReader(File file, boolean useDocumentIdsFromFile, GsonBuilder builder) {//from ww w. j a v a2s . c o m Reader reader; try { reader = new InputStreamReader(new FileInputStream(file), Charsets.UTF_8); } catch (IOException e) { LOGGER.error("Couldn't create FileReader. Returning null.", e); return null; } return createReader(reader, useDocumentIdsFromFile, builder); }
From source file:org.dice_research.topicmodeling.io.xml.CorpusXmlReader.java
public void readCorpus(InputStream in) { this.corpus = new DocumentListCorpus<List<Document>>(new ArrayList<Document>()); String text;//from w w w . j av a 2s .c o m try { text = IOUtils.toString(in, Charsets.UTF_8); } catch (IOException e) { LOGGER.error("Couldn't read stream.", e); return; } parser.parse(text); }
From source file:org.dice_research.topicmodeling.io.xml.CorpusXmlWriter.java
@Override public void writeCorpus(Corpus corpus, OutputStream out) throws IOException { Writer writer = null;//from ww w .ja va2s . co m try { writer = new OutputStreamWriter(out, Charsets.UTF_8); writer.write(CorpusXmlTagHelper.XML_FILE_HEAD); writer.write("<"); writer.write(CorpusXmlTagHelper.CORPUS_TAG_NAME); writer.write(" "); writer.write(CorpusXmlTagHelper.NAMESPACE_DECLARATION); writer.write(">\n"); for (Document d : corpus) { writeDocument(writer, d); } writer.write("</"); writer.write(CorpusXmlTagHelper.CORPUS_TAG_NAME); writer.write(">"); } finally { IOUtils.closeQuietly(writer); } }
From source file:org.dice_research.topicmodeling.io.xml.XmlWritingDocumentConsumer.java
public static XmlWritingDocumentConsumer createXmlWritingDocumentConsumer(File file) { Writer writer = null;/* www . jav a 2 s.c o m*/ if (!file.getParentFile().exists()) { file.getParentFile().mkdirs(); } try { writer = new OutputStreamWriter(new BufferedOutputStream(new FileOutputStream(file)), Charsets.UTF_8); XmlWritingDocumentConsumer consumer = new XmlWritingDocumentConsumer(writer); consumer.writeHead(); return consumer; } catch (Exception e) { LOGGER.error("Error while trying to write corpus to XML file. Returning null.", e); IOUtils.closeQuietly(writer); } return null; }
From source file:org.dragonet.entity.metadata.type.ByteArrayMeta.java
public ByteArrayMeta(String data) { this(data.getBytes(Charsets.UTF_8)); }
From source file:org.dspace.app.util.GoogleMetadataTest.java
/** * Test to see the priorities work, the PDF should be returned * @throws Exception//from w w w . j a v a 2s. co m */ @Test public void testGetPDFURLDifferentMimeTypes() throws Exception { context.turnOffAuthorisationSystem(); Bundle bundle = ContentServiceFactory.getInstance().getBundleService().create(context, it, "ORIGINAL"); Bitstream b = bitstreamService.create(context, new ByteArrayInputStream("Bitstream 1".getBytes(Charsets.UTF_8))); b.setName(context, "Word"); b.setFormat(context, bitstreamFormatService.create(context)); b.getFormat(context).setMIMEType("application/msword"); bundleService.addBitstream(context, bundle, b); Bitstream b2 = bitstreamService.create(context, new ByteArrayInputStream("Bitstream 2".getBytes(Charsets.UTF_8))); b2.setName(context, "Pdf"); b2.setFormat(context, bitstreamFormatService.create(context)); b2.getFormat(context).setMIMEType("application/pdf"); bundleService.addBitstream(context, bundle, b2); Bitstream b3 = bitstreamService.create(context, new ByteArrayInputStream("Bitstream 3".getBytes(Charsets.UTF_8))); b3.setName(context, "Rtf"); b3.setFormat(context, bitstreamFormatService.create(context)); b3.getFormat(context).setMIMEType("text/richtext"); bundleService.addBitstream(context, bundle, b3); context.restoreAuthSystemState(); context.commit(); GoogleMetadata gm = new GoogleMetadata(this.context, it); String[] urlSplitted = gm.getPDFURL().get(0).split("/"); assertEquals("Pdf", urlSplitted[urlSplitted.length - 1]); }