sun.text.normalizer
Class NormalizerImpl

java.lang.Object
  sun.text.normalizer.NormalizerImpl

public final class NormalizerImpl
extends Object

Field Summary

static int	BEFORE_PRI_29 Options bit 8, use buggy recomposition described in Unicode Public Review Issue #29 at http://www.unicode.org/review/resolved-pri.html#pri29 Used in IDNA implementation according to strict interpretation of IDNA definition based on Unicode 3.2 which predates PRI #29.
static int	CC_MASK
static int	COMBINES_ANY
static int	HANGUL_BASE
static int	HANGUL_COUNT
static int	INDEX_MIN_NFC_NO_MAYBE
static int	INDEX_MIN_NFD_NO_MAYBE
static int	INDEX_MIN_NFKC_NO_MAYBE
static int	INDEX_MIN_NFKD_NO_MAYBE
static int	JAMO_L_BASE
static int	JAMO_L_COUNT
static int	JAMO_T_BASE
static int	JAMO_T_COUNT
static int	JAMO_V_BASE
static int	JAMO_V_COUNT
static int	MIN_WITH_LEAD_CC FCD check: everything below this code point is known to have a 0 lead combining class
static int	OPTIONS_COMPAT Options bit 12, for compatibility vs. canonical decomposition.
static int	OPTIONS_COMPOSE_CONTIGUOUS Options bit 13, no discontiguous composition (FCC vs.
static int	OPTIONS_SETS_MASK
static int	QC_ANY_MAYBE
static int	QC_ANY_NO
static int	QC_MASK
static int	QC_MAYBE
static int	QC_NFC
static int	QC_NFD
static int	QC_NFKC
static int	QC_NFKD
static int	WITHOUT_CORRIGENDUM4_CORRECTIONS

Method Summary

static UnicodeSet	addPropertyStarts(UnicodeSet set)
static String	canonicalDecomposeWithSingleQuotation(String string)
static int	compose(char[] src, int srcStart, int srcLimit, char[] dest, int destStart, int destLimit, int options, UnicodeSet nx)
static String	convert(String str)
static int	decompose(char[] src, int srcStart, int srcLimit, char[] dest, int destStart, int destLimit, boolean compat, int[] outTrailCC, UnicodeSet nx)
static int	getCombiningClass(int c)
static int	getDecompose(int[] chars, String[] decomps) Get the canonical decomposition sherman for ComposedCharIter
static char	getFCD16(char c)
static int	getFCD16(int c)
static char	getFCD16FromSurrogatePair(char fcd16, char c2)
static int	getFromIndexesArr(int index)
static long	getNorm32(char c)
static long	getNorm32FromSurrogatePair(long norm32, char c2)
static UnicodeSet	getNX(int options)
static VersionInfo	getUnicodeVersion()
static boolean	isCanonSafeStart(int c)
static boolean	isFullCompositionExclusion(int c)
static boolean	isNFDSafe(long norm32, int ccOrQCMask, int decompQCMask)
static boolean	isNFSkippable(int c, NormalizerBase.Mode mode, long mask)
static boolean	isTrueStarter(long norm32, int ccOrQCMask, int decompQCMask)
static NormalizerBase.QuickCheckResult	quickCheck(char[] src, int srcStart, int srcLimit, int minNoMaybe, int qcMask, int options, boolean allowMaybe, UnicodeSet nx)
static int	quickCheck(int c, int modeValue) Internal API, used in UCharacter.getIntPropertyValue().

Methods inherited from class java.lang.Object

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

Field Detail

QC_NFC

public static final int QC_NFC

See Also:

Constant Field Values

QC_NFKC

public static final int QC_NFKC

See Also:

Constant Field Values

QC_NFD

public static final int QC_NFD

See Also:

Constant Field Values

QC_NFKD

public static final int QC_NFKD

See Also:

Constant Field Values

QC_ANY_NO

public static final int QC_ANY_NO

See Also:

Constant Field Values

QC_MAYBE

public static final int QC_MAYBE

See Also:

Constant Field Values

QC_ANY_MAYBE

public static final int QC_ANY_MAYBE

See Also:

Constant Field Values

QC_MASK

public static final int QC_MASK

See Also:

Constant Field Values

COMBINES_ANY

public static final int COMBINES_ANY

See Also:

Constant Field Values

CC_MASK

public static final int CC_MASK

See Also:

Constant Field Values

INDEX_MIN_NFC_NO_MAYBE

public static final int INDEX_MIN_NFC_NO_MAYBE

See Also:

Constant Field Values

INDEX_MIN_NFKC_NO_MAYBE

public static final int INDEX_MIN_NFKC_NO_MAYBE

See Also:

Constant Field Values

INDEX_MIN_NFD_NO_MAYBE

public static final int INDEX_MIN_NFD_NO_MAYBE

See Also:

Constant Field Values

INDEX_MIN_NFKD_NO_MAYBE

public static final int INDEX_MIN_NFKD_NO_MAYBE

See Also:

Constant Field Values

MIN_WITH_LEAD_CC

public static final int MIN_WITH_LEAD_CC

FCD check: everything below this code point is known to have a 0 lead combining class

See Also:

Constant Field Values

JAMO_L_BASE

public static final int JAMO_L_BASE

See Also:

Constant Field Values

JAMO_V_BASE

public static final int JAMO_V_BASE

See Also:

Constant Field Values

JAMO_T_BASE

public static final int JAMO_T_BASE

See Also:

Constant Field Values

HANGUL_BASE

public static final int HANGUL_BASE

See Also:

Constant Field Values

JAMO_L_COUNT

public static final int JAMO_L_COUNT

See Also:

Constant Field Values

JAMO_V_COUNT

public static final int JAMO_V_COUNT

See Also:

Constant Field Values

JAMO_T_COUNT

public static final int JAMO_T_COUNT

See Also:

Constant Field Values

HANGUL_COUNT

public static final int HANGUL_COUNT

See Also:

Constant Field Values

OPTIONS_SETS_MASK

public static final int OPTIONS_SETS_MASK

See Also:

Constant Field Values

BEFORE_PRI_29

public static final int BEFORE_PRI_29

Options bit 8, use buggy recomposition described in Unicode Public Review Issue #29 at http://www.unicode.org/review/resolved-pri.html#pri29 Used in IDNA implementation according to strict interpretation of IDNA definition based on Unicode 3.2 which predates PRI #29. See ICU4C unormimp.h

See Also:

Constant Field Values

OPTIONS_COMPAT

public static final int OPTIONS_COMPAT

Options bit 12, for compatibility vs. canonical decomposition.

See Also:

Constant Field Values

OPTIONS_COMPOSE_CONTIGUOUS

public static final int OPTIONS_COMPOSE_CONTIGUOUS

Options bit 13, no discontiguous composition (FCC vs. NFC).

See Also:

Constant Field Values

WITHOUT_CORRIGENDUM4_CORRECTIONS

public static final int WITHOUT_CORRIGENDUM4_CORRECTIONS

See Also:

Constant Field Values

Method Detail

getFromIndexesArr

public static int getFromIndexesArr(int index)

getNorm32

public static long getNorm32(char c)

getNorm32FromSurrogatePair

public static long getNorm32FromSurrogatePair(long norm32,
                                              char c2)

getUnicodeVersion

public static VersionInfo getUnicodeVersion()

getFCD16

public static char getFCD16(char c)

getFCD16FromSurrogatePair

public static char getFCD16FromSurrogatePair(char fcd16,
                                             char c2)

getFCD16

public static int getFCD16(int c)

isNFDSafe

public static boolean isNFDSafe(long norm32,
                                int ccOrQCMask,
                                int decompQCMask)

isTrueStarter

public static boolean isTrueStarter(long norm32,
                                    int ccOrQCMask,
                                    int decompQCMask)

quickCheck

public static NormalizerBase.QuickCheckResult quickCheck(char[] src,
                                                         int srcStart,
                                                         int srcLimit,
                                                         int minNoMaybe,
                                                         int qcMask,
                                                         int options,
                                                         boolean allowMaybe,
                                                         UnicodeSet nx)

decompose

public static int decompose(char[] src,
                            int srcStart,
                            int srcLimit,
                            char[] dest,
                            int destStart,
                            int destLimit,
                            boolean compat,
                            int[] outTrailCC,
                            UnicodeSet nx)

compose

public static int compose(char[] src,
                          int srcStart,
                          int srcLimit,
                          char[] dest,
                          int destStart,
                          int destLimit,
                          int options,
                          UnicodeSet nx)

getCombiningClass

public static int getCombiningClass(int c)

isFullCompositionExclusion

public static boolean isFullCompositionExclusion(int c)

isCanonSafeStart

public static boolean isCanonSafeStart(int c)

isNFSkippable

public static boolean isNFSkippable(int c,
                                    NormalizerBase.Mode mode,
                                    long mask)

addPropertyStarts

public static UnicodeSet addPropertyStarts(UnicodeSet set)

quickCheck

public static final int quickCheck(int c,
                                   int modeValue)

Internal API, used in UCharacter.getIntPropertyValue().

Parameters:

c - code point

modeValue - numeric value compatible with Mode

Returns:

numeric value compatible with QuickCheck

getNX

public static final UnicodeSet getNX(int options)

getDecompose

public static int getDecompose(int[] chars,
                               String[] decomps)

Get the canonical decomposition sherman for ComposedCharIter

canonicalDecomposeWithSingleQuotation

public static String canonicalDecomposeWithSingleQuotation(String string)

convert

public static String convert(String str)