Example usage for java.nio.charset StandardCharsets UTF

Introduction

In this page you can find the example usage for java.nio.charset StandardCharsets UTF_16BE.

Prototype

Charset UTF_16BE

To view the source code for java.nio.charset StandardCharsets UTF_16BE.

Click Source Link

Document

Sixteen-bit UCS Transformation Format, big-endian byte order.

Usage

From source file:org.apache.nifi.security.util.crypto.HashService.java

/**
 * Returns a {@link List} of supported {@link Charset}s on this platform. This is not a complete
 * list, as only the charsets in {@link StandardCharsets} are returned to be consistent across
 * JVM instances.// ww  w  .  j av a 2  s  .c  o  m
 *
 * @return the list of charsets
 */
public static List<Charset> getSupportedCharsets() {
    return Arrays.asList(StandardCharsets.US_ASCII, StandardCharsets.ISO_8859_1, StandardCharsets.UTF_8,
            StandardCharsets.UTF_16BE, StandardCharsets.UTF_16LE, StandardCharsets.UTF_16);
}

From source file:org.sonar.scanner.scan.filesystem.CharsetValidationTest.java

@Test
public void detectUTF16Ascii() throws CharacterCodingException {
    String text = "some text to test";
    byte[] utf16be = encode(text, StandardCharsets.UTF_16BE);
    byte[] utf16le = encode(text, StandardCharsets.UTF_16LE);
    byte[] utf8 = encode(text, StandardCharsets.UTF_8);
    byte[] iso88591 = encode(text, StandardCharsets.ISO_8859_1);
    byte[] utf32 = encode(text, Charset.forName("UTF-32LE"));

    assertThat(charsets.isUTF16(utf16le, true).charset()).isEqualTo(StandardCharsets.UTF_16LE);
    assertThat(charsets.isUTF16(utf16be, true).charset()).isEqualTo(StandardCharsets.UTF_16BE);
    // not enough nulls -> we don't know
    assertThat(charsets.isUTF16(iso88591, true).valid()).isEqualTo(Validation.MAYBE);
    assertThat(charsets.isUTF16(utf8, true).valid()).isEqualTo(Validation.MAYBE);
    // fail based on double nulls
    assertThat(charsets.isUTF16(utf32, true).valid()).isEqualTo(Validation.NO);
}

From source file:org.apache.nifi.security.util.crypto.HashService.java

/**
 * Returns the raw {@code byte[]} hash of the specified value.
 *
 * @param algorithm the hash algorithm to use
 * @param value     the value to hash (cannot be {@code null} but can be an empty String)
 * @param charset   the charset to use//from w w w . ja  v a 2 s  .com
 * @return the hash value in bytes
 */
public static byte[] hashValueRaw(HashAlgorithm algorithm, String value, Charset charset) {
    if (value == null) {
        throw new IllegalArgumentException("The value cannot be null");
    }
    /** See the note on {@link HashServiceTest#testHashValueShouldHandleUTF16BOMIssue()} */
    if (charset == StandardCharsets.UTF_16) {
        logger.warn(
                "The charset provided was UTF-16, but Java will insert a Big Endian BOM in the decoded message before hashing, so switching to UTF-16BE");
        charset = StandardCharsets.UTF_16BE;
    }
    return hashValueRaw(algorithm, value.getBytes(charset));
}

From source file:com.github.anba.es6draft.chakra.ChakraTest.java

private static Charset charsetFor(BOMInputStream bis, Charset defaultCharset) throws IOException {
    ByteOrderMark bom = bis.getBOM();//  w  w  w .  j  a  v a  2 s.c om
    if (ByteOrderMark.UTF_8.equals(bom)) {
        return StandardCharsets.UTF_8;
    }
    if (ByteOrderMark.UTF_16LE.equals(bom)) {
        return StandardCharsets.UTF_16LE;
    }
    if (ByteOrderMark.UTF_16BE.equals(bom)) {
        return StandardCharsets.UTF_16BE;
    }
    return defaultCharset;
}

From source file:org.polymap.p4.data.importer.prompts.CharsetPrompt.java

private void initCharsets() {
    charsets = new TreeMap<String, Charset>();

    for (Charset charset : Charset.availableCharsets().values()) {
        charsets.put(displayName(charset), charset);
    }//from ww w. j a v a  2  s  . c o  m

    displayNames = new ListOrderedSet<String>();
    // add all defaults on top
    displayNames.add(displayName(StandardCharsets.ISO_8859_1));
    displayNames.add(displayName(StandardCharsets.US_ASCII));
    displayNames.add(displayName(StandardCharsets.UTF_8));
    displayNames.add(displayName(StandardCharsets.UTF_16));
    displayNames.add(displayName(StandardCharsets.UTF_16BE));
    displayNames.add(displayName(StandardCharsets.UTF_16LE));

    // a separator
    charsets.put(SEPARATOR, selection);
    displayNames.add(SEPARATOR);

    // add the rest
    for (String displayName : charsets.keySet()) {
        displayNames.add(displayName);
    }
}

From source file:com.microsoft.azure.management.datalake.store.uploader.StringExtensionsTests.java

@Test
public void StringExtensions_FindNewLine_UTF16BigEndian() {
    for (Triple<String, Integer, Integer> t : TestDataUTF16) {
        byte[] exactBuffer = t.getLeft().getBytes(StandardCharsets.UTF_16BE);
        byte[] largerBuffer = new byte[exactBuffer.length + 100];
        System.arraycopy(exactBuffer, 0, largerBuffer, 0, exactBuffer.length);

        int forwardInExactBuffer = StringExtensions.findNewline(exactBuffer, 0, exactBuffer.length, false,
                StandardCharsets.UTF_16BE, null);
        Assert.assertEquals(t.getMiddle().intValue(), forwardInExactBuffer);

        int forwardInLargeBuffer = StringExtensions.findNewline(largerBuffer, 0, exactBuffer.length, false,
                StandardCharsets.UTF_16BE, null);
        Assert.assertEquals(t.getMiddle().intValue(), forwardInLargeBuffer);

        int reverseInExactBuffer = StringExtensions.findNewline(exactBuffer,
                Math.max(0, exactBuffer.length - 1), exactBuffer.length, true, StandardCharsets.UTF_16BE, null);
        Assert.assertEquals(t.getRight().intValue(), reverseInExactBuffer);

        int reverseInLargeBuffer = StringExtensions.findNewline(largerBuffer,
                Math.max(0, exactBuffer.length - 1), exactBuffer.length, true, StandardCharsets.UTF_16BE, null);
        Assert.assertEquals(t.getRight().intValue(), reverseInLargeBuffer);
    }/*from  w  w  w.  j  a va 2 s  .c  o m*/

    for (Triple<String, Integer, Integer> t : TestDataUTF16CustomDelim) {
        byte[] exactBuffer = t.getLeft().getBytes(StandardCharsets.UTF_16BE);
        byte[] largerBuffer = new byte[exactBuffer.length + 100];
        System.arraycopy(exactBuffer, 0, largerBuffer, 0, exactBuffer.length);

        int forwardInExactBuffer = StringExtensions.findNewline(exactBuffer, 0, exactBuffer.length, false,
                StandardCharsets.UTF_16BE, customDelim);
        Assert.assertEquals(t.getMiddle().intValue(), forwardInExactBuffer);

        int forwardInLargeBuffer = StringExtensions.findNewline(largerBuffer, 0, exactBuffer.length, false,
                StandardCharsets.UTF_16BE, customDelim);
        Assert.assertEquals(t.getMiddle().intValue(), forwardInLargeBuffer);

        int reverseInExactBuffer = StringExtensions.findNewline(exactBuffer,
                Math.max(0, exactBuffer.length - 1), exactBuffer.length, true, StandardCharsets.UTF_16BE,
                customDelim);
        Assert.assertEquals(t.getRight().intValue(), reverseInExactBuffer);

        int reverseInLargeBuffer = StringExtensions.findNewline(largerBuffer,
                Math.max(0, exactBuffer.length - 1), exactBuffer.length, true, StandardCharsets.UTF_16BE,
                customDelim);
        Assert.assertEquals(t.getRight().intValue(), reverseInLargeBuffer);
    }
}

From source file:com.sonymobile.android.media.internal.ISOBMFFParser.java

private String readID3String(int frameSize) {
    String metadataString = null;
    try {// www . java  2  s  .  c o  m
        int encoding = mDataSource.readByte();
        if (frameSize > 1) {
            if (encoding == 0) {
                // ISO 8859-1
                byte[] buffer = new byte[frameSize - 1];
                mDataSource.read(buffer);
                metadataString = new String(buffer, StandardCharsets.ISO_8859_1);
            } else if (encoding == 2) {
                // UTF-16
                int bom = mDataSource.readShort();
                byte[] buffer = new byte[frameSize - 3];
                short little_endian = (short) 0xFFFE;
                mDataSource.read(buffer);
                if (bom == little_endian) {
                    metadataString = new String(buffer, StandardCharsets.UTF_16LE);
                } else {
                    metadataString = new String(buffer, StandardCharsets.UTF_16BE);
                }
            } else if (encoding == 3) {
                // UTF-8
                byte[] buffer = new byte[frameSize - 1];
                mDataSource.read(buffer);
                metadataString = new String(buffer, StandardCharsets.UTF_8);
            } else {
                // UCS-2
                int bom = mDataSource.readShort();
                byte[] buffer = new byte[frameSize - 3];
                mDataSource.read(buffer);
                short little_endian = (short) 0xFFFE;
                if (bom == little_endian) {
                    for (int i = 0; i < buffer.length; i += 2) {
                        byte tempByte = buffer[i];
                        buffer[i] = buffer[i + 1];
                        buffer[i + 1] = tempByte;
                    }
                }
                metadataString = new String(buffer, "UCS-2");
            }
        }
    } catch (IOException e) {
        if (LOGS_ENABLED)
            Log.e(TAG, "IOEception reading ID3 string", e);
    }
    return metadataString;
}

From source file:com.sonymobile.android.media.internal.ISOBMFFParser.java

private boolean parseDataBox(BoxHeader header) {
    try {//from www .jav a2 s . com
        if (mCurrentMetaDataKey != null) {
            String metaDataValue;
            if (mCurrentMetaDataKey == KEY_DISC_NUMBER) {
                mDataSource.skipBytes(4); // skip type
                mDataSource.skipBytes(4); // skip locale
                mDataSource.skipBytes(2); // skip album id type
                                          // and album id len
                int diskNumber = mDataSource.readShort();
                mDataSource.skipBytes(2); // skip total number of disks
                metaDataValue = Integer.toString(diskNumber);
            } else {
                byte[] typefield = new byte[4];
                mDataSource.read(typefield);
                int type = typefield[0];
                int flag = (typefield[1] | typefield[2] | typefield[3]);

                Charset encoding = StandardCharsets.UTF_8;
                if (type == 2) {
                    encoding = StandardCharsets.UTF_16BE;
                }
                mDataSource.skipBytes(4); // skip locale for now
                byte[] data = new byte[(int) header.boxDataSize - 8];
                mDataSource.read(data);
                if (mCurrentMetaDataKey == KEY_TRACK_NUMBER) {
                    int trackNumber = (data[2] << 8) & 0xFF | data[3];
                    int trackTotalNumber = (data[4] << 8) & 0xFF | data[5];
                    metaDataValue = trackNumber + "/" + trackTotalNumber;
                } else if (mCurrentMetaDataKey == KEY_COMPILATION) {
                    metaDataValue = Byte.toString(data[0]);
                } else if (mCurrentMetaDataKey == KEY_GENRE) {
                    if (type == 0 && flag == 1) {
                        metaDataValue = new String(data, encoding);
                    } else {
                        int genre = data[data.length - 1];
                        genre--;
                        if (genre < 0) {
                            genre = 255;
                        }
                        metaDataValue = Integer.toString(genre);
                    }
                } else {
                    metaDataValue = new String(data, encoding);
                }
            }
            mMetaDataValues.put(mCurrentMetaDataKey, metaDataValue);
        }
    } catch (IOException e) {
        if (LOGS_ENABLED)
            Log.e(TAG, "could not read data", e);

        return false;
    }
    return true;
}

Example usage for java.nio.charset StandardCharsets UTF_16BE

Introduction

Prototype

Document

Usage