Package org.mozilla.universalchardet.prober

Class CharsetProber

java.lang.Object

org.mozilla.universalchardet.prober.CharsetProber

Direct Known Subclasses:

Big5Prober, EscCharsetProber, EUCJPProber, EUCKRProber, EUCTWProber, GB18030Prober, HebrewProber, Latin1Prober, MBCSGroupProber, SBCSGroupProber, SingleByteCharsetProber, SJISProber, UTF8Prober

public abstract class CharsetProber
extends java.lang.Object

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	CharsetProber.ProbingState

Field Summary

Fields

Modifier and Type	Field	Description
static int	ASCII_A
static int	ASCII_A_CAPITAL
static int	ASCII_GT
static int	ASCII_LT
static int	ASCII_SP
static int	ASCII_Z
static int	ASCII_Z_CAPITAL
static float	SHORTCUT_THRESHOLD

Constructor Summary

Constructors

Constructor	Description
CharsetProber()

Method Summary

Modifier and Type	Method	Description
static java.nio.ByteBuffer	filterWithEnglishLetters(byte[] buf, int offset, int length)
static java.nio.ByteBuffer	filterWithoutEnglishLetters(byte[] buf, int offset, int length)
abstract java.lang.String	getCharSetName()
abstract float	getConfidence()
abstract CharsetProber.ProbingState	getState()
abstract CharsetProber.ProbingState	handleData(byte[] buf, int offset, int length)
private static boolean	isAscii(byte b)
private static boolean	isAsciiSymbol(byte b)
abstract void	reset()
abstract void	setOption()

Methods inherited from class java.lang.Object

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

Field Detail

SHORTCUT_THRESHOLD

public static final float SHORTCUT_THRESHOLD

See Also:

Constant Field Values

ASCII_A

public static final int ASCII_A

See Also:

Constant Field Values

ASCII_Z

public static final int ASCII_Z

See Also:

Constant Field Values

ASCII_A_CAPITAL

public static final int ASCII_A_CAPITAL

See Also:

Constant Field Values

ASCII_Z_CAPITAL

public static final int ASCII_Z_CAPITAL

See Also:

Constant Field Values

ASCII_LT

public static final int ASCII_LT

See Also:

Constant Field Values

ASCII_GT

public static final int ASCII_GT

See Also:

Constant Field Values

ASCII_SP

public static final int ASCII_SP

See Also:

Constant Field Values

Constructor Detail

CharsetProber

public CharsetProber()

Method Detail

getCharSetName

public abstract java.lang.String getCharSetName()

handleData

public abstract CharsetProber.ProbingState handleData(byte[] buf,
                                                      int offset,
                                                      int length)

getState

public abstract CharsetProber.ProbingState getState()

reset

public abstract void reset()

getConfidence

public abstract float getConfidence()

setOption

public abstract void setOption()

filterWithoutEnglishLetters

public static java.nio.ByteBuffer filterWithoutEnglishLetters(byte[] buf,
                                                              int offset,
                                                              int length)

filterWithEnglishLetters

public static java.nio.ByteBuffer filterWithEnglishLetters(byte[] buf,
                                                           int offset,
                                                           int length)

isAscii

private static boolean isAscii(byte b)

isAsciiSymbol

private static boolean isAsciiSymbol(byte b)