Java Code Examples for org.apache.commons.io.ByteOrderMark#UTF_8

String[] readFieldNamesFromFile( String fileName, CsvInputMeta csvInputMeta ) throws HopException {
  String delimiter = environmentSubstitute( csvInputMeta.getDelimiter() );
  String enclosure = environmentSubstitute( csvInputMeta.getEnclosure() );
  String realEncoding = environmentSubstitute( csvInputMeta.getEncoding() );

  try ( FileObject fileObject = HopVfs.getFileObject( fileName );
        BOMInputStream inputStream =
          new BOMInputStream( HopVfs.getInputStream( fileObject ), ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE,
            ByteOrderMark.UTF_16BE ) ) {
    InputStreamReader reader = null;
    if ( Utils.isEmpty( realEncoding ) ) {
      reader = new InputStreamReader( inputStream );
    } else {
      reader = new InputStreamReader( inputStream, realEncoding );
    }
    EncodingType encodingType = EncodingType.guessEncodingType( reader.getEncoding() );
    String line =
      TextFileInput.getLine( log, reader, encodingType, TextFileInputMeta.FILE_FORMAT_UNIX, new StringBuilder(
        1000 ) );
    String[] fieldNames = TextFileLineUtil.guessStringsFromLine( log, line, delimiter, enclosure, csvInputMeta.getEscapeCharacter() );
    if ( !Utils.isEmpty( csvInputMeta.getEnclosure() ) ) {
      removeEnclosure( fieldNames, csvInputMeta.getEnclosure() );
    }
    trimFieldNames( fieldNames );
    return fieldNames;
  } catch ( IOException e ) {
    throw new HopFileException( BaseMessages.getString( PKG, "CsvInput.Exception.CreateFieldMappingError" ), e );
  }
}
 

public static XMLEventReader createEventReader(InputStream stream) throws XMLStreamException {
    Charset charset = UTF8Charset.get();

    BOMInputStream bomStream = new BOMInputStream(stream, false,
            ByteOrderMark.UTF_8, ByteOrderMark.UTF_16BE, ByteOrderMark.UTF_16LE);
    try {
        if (bomStream.hasBOM())
            charset = Charset.forName(bomStream.getBOMCharsetName());
    } catch (IOException e) {
        throw new XMLStreamException(e);
    }

    XMLInputFactory factory = XMLInputFactory.newInstance();
    return factory.createXMLEventReader(new XMLFixInputStreamReader(bomStream, charset));
}
 

private void digestEncodedStreamToUtf8(@Nonnull InputStream inStream, @Nonnull Charset charset,
                                       boolean isRequireLineEndingConvert, @Nullable ClientLineEnding clientLineEnding)
		throws IOException {

	try (BOMInputStream unicodeInputStream = new BOMInputStream(inStream, false,
			ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE,
			ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE);

	     InputStreamReader encodedStreamReader = new InputStreamReader(unicodeInputStream,
			     charset)) {
		CharsetEncoder utf8CharsetEncoder = CharsetDefs.UTF8.newEncoder()
				.onMalformedInput(CodingErrorAction.REPORT)
				.onUnmappableCharacter(CodingErrorAction.REPORT);

		char[] buffer = new char[bufferSize];
		int read;
		while ((read = encodedStreamReader.read(buffer)) > 0) {
			// Convert encoded stream to UTF8 since server digest is UTF8
			ByteBuffer utf8ByteBuffer = utf8CharsetEncoder
					.encode(CharBuffer.wrap(buffer, 0, read));

			if (isRequireLineEndingConvert) {
				ByteBuffer convert = findAndReplaceEncodedClientLineEndingIfRequireLineEndingCovert(
						encodedStreamReader, utf8CharsetEncoder, utf8ByteBuffer,
						clientLineEnding);

				update(convert.array(), convert.arrayOffset(), convert.limit());
			} else {
				update(utf8ByteBuffer.array(), utf8ByteBuffer.arrayOffset(),
						utf8ByteBuffer.limit());
			}
		}
	}
}
 

private void digestEncodedStreamToUtf8(@Nonnull InputStream inStream, @Nonnull Charset charset,
                                       boolean isRequireLineEndingConvert, @Nullable ClientLineEnding clientLineEnding)
		throws IOException {

	try (BOMInputStream unicodeInputStream = new BOMInputStream(inStream, false,
			ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE,
			ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE);

	     InputStreamReader encodedStreamReader = new InputStreamReader(unicodeInputStream,
			     charset)) {
		CharsetEncoder utf8CharsetEncoder = CharsetDefs.UTF8.newEncoder()
				.onMalformedInput(CodingErrorAction.REPORT)
				.onUnmappableCharacter(CodingErrorAction.REPORT);

		char[] buffer = new char[bufferSize];
		int read;
		while ((read = encodedStreamReader.read(buffer)) > 0) {
			// Convert encoded stream to UTF8 since server digest is UTF8
			ByteBuffer utf8ByteBuffer = utf8CharsetEncoder
					.encode(CharBuffer.wrap(buffer, 0, read));

			if (isRequireLineEndingConvert) {
				ByteBuffer convert = findAndReplaceEncodedClientLineEndingIfRequireLineEndingCovert(
						encodedStreamReader, utf8CharsetEncoder, utf8ByteBuffer,
						clientLineEnding);

				update(convert.array(), convert.arrayOffset(), convert.limit());
			} else {
				update(utf8ByteBuffer.array(), utf8ByteBuffer.arrayOffset(),
						utf8ByteBuffer.limit());
			}
		}
	}
}
 

private void digestEncodedStreamToUtf8(@Nonnull InputStream inStream, @Nonnull Charset charset,
                                       boolean isRequireLineEndingConvert, @Nullable ClientLineEnding clientLineEnding)
		throws IOException {

	try (BOMInputStream unicodeInputStream = new BOMInputStream(inStream, false,
			ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE,
			ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE);

	     InputStreamReader encodedStreamReader = new InputStreamReader(unicodeInputStream,
			     charset)) {
		CharsetEncoder utf8CharsetEncoder = CharsetDefs.UTF8.newEncoder()
				.onMalformedInput(CodingErrorAction.REPORT)
				.onUnmappableCharacter(CodingErrorAction.REPORT);

		char[] buffer = new char[bufferSize];
		int read;
		while ((read = encodedStreamReader.read(buffer)) > 0) {
			// Convert encoded stream to UTF8 since server digest is UTF8
			ByteBuffer utf8ByteBuffer = utf8CharsetEncoder
					.encode(CharBuffer.wrap(buffer, 0, read));

			if (isRequireLineEndingConvert) {
				ByteBuffer convert = findAndReplaceEncodedClientLineEndingIfRequireLineEndingCovert(
						encodedStreamReader, utf8CharsetEncoder, utf8ByteBuffer,
						clientLineEnding);

				update(convert.array(), convert.arrayOffset(), convert.limit());
			} else {
				update(utf8ByteBuffer.array(), utf8ByteBuffer.arrayOffset(),
						utf8ByteBuffer.limit());
			}
		}
	}
}
 

private void digestEncodedStreamToUtf8(@Nonnull InputStream inStream, @Nonnull Charset charset,
                                       boolean isRequireLineEndingConvert, @Nullable ClientLineEnding clientLineEnding)
		throws IOException {

	try (BOMInputStream unicodeInputStream = new BOMInputStream(inStream, false,
			ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE,
			ByteOrderMark.UTF_32LE, ByteOrderMark.UTF_32BE);

	     InputStreamReader encodedStreamReader = new InputStreamReader(unicodeInputStream,
			     charset)) {
		CharsetEncoder utf8CharsetEncoder = CharsetDefs.UTF8.newEncoder()
				.onMalformedInput(CodingErrorAction.REPORT)
				.onUnmappableCharacter(CodingErrorAction.REPORT);

		char[] buffer = new char[bufferSize];
		int read;
		while ((read = encodedStreamReader.read(buffer)) > 0) {
			// Convert encoded stream to UTF8 since server digest is UTF8
			ByteBuffer utf8ByteBuffer = utf8CharsetEncoder
					.encode(CharBuffer.wrap(buffer, 0, read));

			if (isRequireLineEndingConvert) {
				ByteBuffer convert = findAndReplaceEncodedClientLineEndingIfRequireLineEndingCovert(
						encodedStreamReader, utf8CharsetEncoder, utf8ByteBuffer,
						clientLineEnding);

				update(convert.array(), convert.arrayOffset(), convert.limit());
			} else {
				update(utf8ByteBuffer.array(), utf8ByteBuffer.arrayOffset(),
						utf8ByteBuffer.limit());
			}
		}
	}
}
 

private static @Nonnull BOMInputStream bomInputStream(@Nonnull InputStream inputStream) {
  return new BOMInputStream(
      inputStream,
      ByteOrderMark.UTF_8,
      ByteOrderMark.UTF_16BE,
      ByteOrderMark.UTF_16LE,
      ByteOrderMark.UTF_32BE,
      ByteOrderMark.UTF_32LE);
}
 

/**
 * Return a Reader that reads the InputStream in the character set specified by the BOM. If no BOM is found, a default character set is used.
 */
public static Reader getCharsetDetectingInputStreamReader(InputStream inputStream, String defaultCharset) throws IOException {
	BOMInputStream bOMInputStream = new BOMInputStream(inputStream,ByteOrderMark.UTF_8, ByteOrderMark.UTF_16LE, ByteOrderMark.UTF_16BE);
	ByteOrderMark bom = bOMInputStream.getBOM();
	String charsetName = bom == null ? defaultCharset : bom.getCharsetName();
	return new InputStreamReader(new BufferedInputStream(bOMInputStream), charsetName);
}
 

/**
 * Constructs a new BOM InputStream that excludes a {@link ByteOrderMark#UTF_8} BOM.
 * 
 * @param delegate
 *            the InputStream to delegate to
 */
public BOMInputStream(InputStream delegate) {
    this(delegate, false, ByteOrderMark.UTF_8);
}
 

/**
 * Constructs a new BOM InputStream that detects a a {@link ByteOrderMark#UTF_8} and optionally includes it.
 * 
 * @param delegate
 *            the InputStream to delegate to
 * @param include
 *            true to include the UTF-8 BOM or false to exclude it
 */
public BOMInputStream(InputStream delegate, boolean include) {
    this(delegate, include, ByteOrderMark.UTF_8);
}
 

/**
 * Constructs a new BOM InputStream that excludes a {@link ByteOrderMark#UTF_8} BOM.
 * 
 * @param delegate
 *            the InputStream to delegate to
 */
public BOMInputStream(final InputStream delegate) {
    this(delegate, false, ByteOrderMark.UTF_8);
}
 

/**
 * Constructs a new BOM InputStream that detects a a {@link ByteOrderMark#UTF_8} and optionally includes it.
 * 
 * @param delegate
 *            the InputStream to delegate to
 * @param include
 *            true to include the UTF-8 BOM or false to exclude it
 */
public BOMInputStream(final InputStream delegate, final boolean include) {
    this(delegate, include, ByteOrderMark.UTF_8);
}