List of usage examples for org.apache.commons.io ByteOrderMark UTF_16BE
ByteOrderMark UTF_16BE
To view the source code for org.apache.commons.io ByteOrderMark UTF_16BE.
Click Source Link
From source file:org.apache.any23.util.StreamUtils.java
public static Document inputStreamToDocument(InputStream is) throws MalformedByteSequenceException { DocumentBuilderFactory factory = null; DocumentBuilder builder = null; Document doc = null;/* ww w. j a va 2s . c o m*/ try { factory = DocumentBuilderFactory.newInstance(); builder = factory.newDocumentBuilder(); } catch (ParserConfigurationException e) { logger.error("Error converting InputStream to Document: {}", e); } try { BOMInputStream bomIn = new BOMInputStream(is, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_32BE, ByteOrderMark.UTF_32LE); if (bomIn.hasBOM()) { @SuppressWarnings("unused") int firstNonBOMByte = bomIn.read(); // Skips BOM } doc = builder.parse(bomIn); } catch (SAXException | IOException e) { logger.error("Error converting InputStream to Document: {}", e); } return doc; }
From source file:org.hillview.storage.TextFileLoader.java
Reader getFileReader() { try {/*from w w w . j a v a 2 s . com*/ HillviewLogger.instance.info("Reading file", "{0}", this.filename); this.inputStream = new FileInputStream(this.filename); this.bufferedInputStream = new BufferedInputStream(inputStream); // The buffered input stream is needed by the CompressorStream // to detect the compression method at runtime. InputStream fis = this.bufferedInputStream; if (Utilities.isCompressed(this.filename)) { this.compressedStream = new CompressorStreamFactory().createCompressorInputStream(fis); fis = this.compressedStream; } this.bomStream = new BOMInputStream(fis, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE); ByteOrderMark bom = this.bomStream.getBOM(); String charsetName = bom == null ? "UTF-8" : bom.getCharsetName(); return new InputStreamReader(this.bomStream, charsetName); } catch (IOException | CompressorException e) { throw new RuntimeException(e); } }
From source file:org.languagetool.commandline.Main.java
private InputStreamReader getInputStreamReader(String filename, String encoding) throws IOException { String charsetName = encoding != null ? encoding : Charset.defaultCharset().name(); InputStream is = System.in; if (!isStdIn(filename)) { is = new FileInputStream(new File(filename)); BOMInputStream bomIn = new BOMInputStream(is, true, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_32BE, ByteOrderMark.UTF_32LE); if (bomIn.hasBOM() && encoding == null) { charsetName = bomIn.getBOMCharsetName(); }/*w w w . j a v a2s . c o m*/ is = bomIn; } return new InputStreamReader(new BufferedInputStream(is), charsetName); }
From source file:org.languagetool.gui.Main.java
private void loadFile(File file) { try (FileInputStream inputStream = new FileInputStream(file)) { BOMInputStream bomIn = new BOMInputStream(inputStream, false, ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_32BE, ByteOrderMark.UTF_32LE); String charsetName;//from w w w . jav a2 s .c o m if (bomIn.hasBOM()) { bom = bomIn.getBOM(); charsetName = bom.getCharsetName(); } else { // No BOM found bom = null; charsetName = null; } String fileContents = StringTools.readStream(bomIn, charsetName); textArea.setText(fileContents); currentFile = file; updateTitle(); if (recentFiles.contains(file.getAbsolutePath())) { recentFiles.remove(file.getAbsolutePath()); } recentFiles.add(file.getAbsolutePath()); localStorage.saveProperty("recentFiles", recentFiles); updateRecentFilesMenu(); } catch (IOException e) { Tools.showError(e); } }
From source file:org.omegat.util.TMXReaderTest.java
public void testCharset() throws Exception { File xml = new File("build/testdata/test.xml"); xml.getParentFile().mkdirs();/* w ww . jav a 2s . c o m*/ testXml(xml, ByteOrderMark.UTF_8, "<?xml version=\"1.0\"?>", "UTF-8"); testXml(xml, ByteOrderMark.UTF_16LE, "<?xml version=\"1.0\"?>", "UTF-16LE"); testXml(xml, ByteOrderMark.UTF_16BE, "<?xml version=\"1.0\"?>", "UTF-16BE"); testXml(xml, ByteOrderMark.UTF_32LE, "<?xml version=\"1.0\"?>", "UTF-32LE"); testXml(xml, ByteOrderMark.UTF_32BE, "<?xml version=\"1.0\"?>", "UTF-32BE"); testXml(xml, null, "<?xml version=\"1.0\" encoding=\"UTF-8\"?>", "UTF-8"); testXml(xml, null, "<?xml version=\"1.0\" encoding=\"ISO-8859-1\"?>", "ISO-8859-1"); }
From source file:org.sonar.api.batch.fs.internal.DefaultInputFile.java
@Override public InputStream inputStream() throws IOException { return contents != null ? new ByteArrayInputStream(contents.getBytes(charset())) : new BOMInputStream(Files.newInputStream(path()), ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE); }
From source file:org.sonar.batch.report.SourcePublisher.java
@Override public void publish(BatchReportWriter writer) { for (final BatchComponent resource : resourceCache.all()) { if (!resource.isFile()) { continue; }/*from w w w.ja v a 2s. c o m*/ DefaultInputFile inputFile = (DefaultInputFile) resource.inputComponent(); File iofile = writer.getSourceFile(resource.batchId()); int line = 0; try (FileOutputStream output = new FileOutputStream(iofile); BOMInputStream bomIn = new BOMInputStream(new FileInputStream(inputFile.file()), ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE); BufferedReader reader = new BufferedReader(new InputStreamReader(bomIn, inputFile.charset()))) { String lineStr = reader.readLine(); while (lineStr != null) { IOUtils.write(lineStr, output, StandardCharsets.UTF_8); line++; if (line < inputFile.lines()) { IOUtils.write("\n", output, StandardCharsets.UTF_8); } lineStr = reader.readLine(); } } catch (IOException e) { throw new IllegalStateException("Unable to store file source in the report", e); } } }
From source file:org.sonar.scanner.scan.filesystem.ByteCharsetDetectorTest.java
@Test public void detectBOM() throws URISyntaxException, IOException { byte[] b = ByteOrderMark.UTF_16BE.getBytes(); assertThat(charsets.detectBOM(b)).isEqualTo(ByteOrderMark.UTF_16BE); assertThat(charsets.detectBOM(readFile("UTF-8"))).isEqualTo(ByteOrderMark.UTF_8); assertThat(charsets.detectBOM(readFile("UTF-16BE"))).isEqualTo(ByteOrderMark.UTF_16BE); assertThat(charsets.detectBOM(readFile("UTF-16LE"))).isEqualTo(ByteOrderMark.UTF_16LE); assertThat(charsets.detectBOM(readFile("UTF-32BE"))).isEqualTo(ByteOrderMark.UTF_32BE); assertThat(charsets.detectBOM(readFile("UTF-32LE"))).isEqualTo(ByteOrderMark.UTF_32LE); }
From source file:org.sonarsource.sonarlint.core.container.analysis.filesystem.FileMetadata.java
private static InputStream streamFile(File file) { try {//from w w w .jav a 2s. co m return new BOMInputStream(new FileInputStream(file), ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE); } catch (FileNotFoundException e) { throw new IllegalStateException("File not found: " + file.getAbsolutePath(), e); } }
From source file:org.w3.i18n.Utils.java
public static ByteOrderMark findByteOrderMark(byte[] bytes) { if (bytes == null) { throw new NullPointerException("bytes: " + bytes); }/*from ww w . j a v a 2 s. c om*/ ByteOrderMark byteOrderMark; try { byteOrderMark = new BOMInputStream(new ByteArrayInputStream(bytes), ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_32BE, ByteOrderMark.UTF_32LE) .getBOM(); } catch (IOException ex) { throw new RuntimeException(ex); } return byteOrderMark; }