org.apache.sanselan.util

Class UnicodeUtils

java.lang.Object

org.apache.sanselan.util.UnicodeUtils

All Implemented Interfaces:

BinaryConstants

public abstract class UnicodeUtils
extends Object
implements BinaryConstants

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	UnicodeUtils.UnicodeException

Field Summary

Fields

Modifier and Type	Field and Description
static int	CHAR_ENCODING_CODE_AMBIGUOUS
static int	CHAR_ENCODING_CODE_ISO_8859_1
static int	CHAR_ENCODING_CODE_UTF_16_BIG_ENDIAN_NO_BOM
static int	CHAR_ENCODING_CODE_UTF_16_BIG_ENDIAN_WITH_BOM
static int	CHAR_ENCODING_CODE_UTF_16_LITTLE_ENDIAN_NO_BOM
static int	CHAR_ENCODING_CODE_UTF_16_LITTLE_ENDIAN_WITH_BOM
static int	CHAR_ENCODING_CODE_UTF_8

Fields inherited from interface org.apache.sanselan.common.BinaryConstants

BYTE_ORDER_BIG_ENDIAN, BYTE_ORDER_INTEL, BYTE_ORDER_LEAST_SIGNIFICANT_BYTE, BYTE_ORDER_LITTLE_ENDIAN, BYTE_ORDER_LSB, BYTE_ORDER_MOST_SIGNIFICANT_BYTE, BYTE_ORDER_MOTOROLA, BYTE_ORDER_MSB, BYTE_ORDER_NETWORK

Method Summary

Methods

Modifier and Type	Method and Description
protected abstract int	findEnd(byte[] bytes, int index, boolean includeTerminator)
int	findEndWithoutTerminator(byte[] bytes, int index)
int	findEndWithTerminator(byte[] bytes, int index)
static UnicodeUtils	getInstance(int charEncodingCode)
static boolean	isValidISO_8859_1(String s)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

CHAR_ENCODING_CODE_ISO_8859_1

public static final int CHAR_ENCODING_CODE_ISO_8859_1

See Also:

Constant Field Values

CHAR_ENCODING_CODE_UTF_16_BIG_ENDIAN_WITH_BOM

public static final int CHAR_ENCODING_CODE_UTF_16_BIG_ENDIAN_WITH_BOM

See Also:

Constant Field Values

CHAR_ENCODING_CODE_UTF_16_LITTLE_ENDIAN_WITH_BOM

public static final int CHAR_ENCODING_CODE_UTF_16_LITTLE_ENDIAN_WITH_BOM

See Also:

Constant Field Values

CHAR_ENCODING_CODE_UTF_16_BIG_ENDIAN_NO_BOM

public static final int CHAR_ENCODING_CODE_UTF_16_BIG_ENDIAN_NO_BOM

See Also:

Constant Field Values

CHAR_ENCODING_CODE_UTF_16_LITTLE_ENDIAN_NO_BOM

public static final int CHAR_ENCODING_CODE_UTF_16_LITTLE_ENDIAN_NO_BOM

See Also:

Constant Field Values

CHAR_ENCODING_CODE_UTF_8

public static final int CHAR_ENCODING_CODE_UTF_8

See Also:

Constant Field Values

CHAR_ENCODING_CODE_AMBIGUOUS

public static final int CHAR_ENCODING_CODE_AMBIGUOUS

See Also:

Constant Field Values

Method Detail

isValidISO_8859_1

public static final boolean isValidISO_8859_1(String s)

findEndWithTerminator

public final int findEndWithTerminator(byte[] bytes,
                        int index)
                                throws UnicodeUtils.UnicodeException

Throws:

UnicodeUtils.UnicodeException

findEndWithoutTerminator

public final int findEndWithoutTerminator(byte[] bytes,
                           int index)
                                   throws UnicodeUtils.UnicodeException

Throws:

UnicodeUtils.UnicodeException

findEnd

protected abstract int findEnd(byte[] bytes,
          int index,
          boolean includeTerminator)
                        throws UnicodeUtils.UnicodeException

Throws:

UnicodeUtils.UnicodeException

getInstance

public static UnicodeUtils getInstance(int charEncodingCode)
                                throws UnicodeUtils.UnicodeException

Throws:

UnicodeUtils.UnicodeException