com.ibm.icu.dev.tool.normalizer
Class UInfo

java.lang.Object
  |
  +--com.ibm.icu.dev.tool.normalizer.UInfo

public final class UInfo
extends java.lang.Object


Field Summary
static byte COMBINING_SPACING_MARK
           
static byte CONNECTOR_PUNCTUATION
           
static byte CONTROL
           
static byte CURRENCY_SYMBOL
           
static byte DASH_PUNCTUATION
           
static byte DECIMAL_DIGIT_NUMBER
           
static byte ENCLOSING_MARK
           
static byte END_PUNCTUATION
           
static byte FORMAT
           
static byte LETTER_NUMBER
           
static byte LINE_SEPARATOR
           
static byte LOWERCASE_LETTER
           
static byte MATH_SYMBOL
           
static byte MODIFIER_LETTER
           
static byte MODIFIER_SYMBOL
           
static byte NON_SPACING_MARK
           
static byte OTHER_LETTER
           
static byte OTHER_NUMBER
           
static byte OTHER_PUNCTUATION
           
static byte OTHER_SYMBOL
           
static byte PARAGRAPH_SEPARATOR
           
static byte PRIVATE_USE
           
static byte SPACE_SEPARATOR
           
static byte START_PUNCTUATION
           
static byte SURROGATE
           
static byte TITLECASE_LETTER
           
static byte UNASSIGNED
           
static byte UPPERCASE_LETTER
           
 
Constructor Summary
UInfo()
           
UInfo(java.lang.String fileName, java.lang.String composeExcludeFileName)
           
 
Method Summary
 java.lang.String fixCanonical(java.lang.String source)
           
 java.lang.StringBuffer fixCanonical(java.lang.StringBuffer target)
          Given a decomposed string of characters, put it in canonical order by finding and processing all exchangeable pairs.
 byte getBidiClass(char ch)
           
 short getCanonicalClass(char ch)
           
 byte getCategory(char ch)
           
 java.lang.String getComment(char ch)
           
 short getDecimal(char ch)
           
 java.lang.String getDecomposition(char ch)
           
 java.lang.String getDecompositionChars(char ch)
           
 short getDigit(char ch)
           
 java.lang.String getFullDecomposition(char ch, boolean canonical)
           
 java.lang.StringBuffer getFullDecomposition(char ch, boolean canonical, java.lang.StringBuffer output)
           
 java.lang.String getFullDecomposition(java.lang.String s, boolean canonical)
           
 char getLowercase(char ch)
           
 boolean getMirrored(char ch)
           
 java.lang.String getName(char ch)
           
 java.lang.String getName(char ch, boolean shortVersion)
           
 java.lang.String getName(java.lang.String s)
           
 java.lang.String getName(java.lang.String s, boolean shortVersion)
           
 java.lang.String getName10(char ch)
           
 float getNumeric(char ch)
           
 char getTitlecase(char ch)
           
 char getUppercase(char ch)
           
 boolean hasCanonicalDecomposition(char ch)
           
 boolean hasCompatibilityDecomposition(char ch)
           
 boolean isCBS(java.lang.String s)
           
 boolean isCCS(java.lang.String s)
           
 boolean isDisparaged(char ch)
           
 boolean isEquivalent(java.lang.String a, java.lang.String b, boolean canonical)
           
 boolean isExcludedComposition(char ch)
          Is this character excluded from the composition algorithm by virtue of being listed in the composition exclusion table in Tech Report #15?
 boolean isFormat(char ch)
           
 boolean isLetter(char ch)
           
 boolean isMark(char ch)
           
 boolean isNumber(char ch)
           
 boolean isPunctuation(char ch)
           
 boolean isSeparator(char ch)
           
 boolean isSymbol(char ch)
           
 java.lang.String replace(java.lang.String source, java.lang.String replacee, java.lang.String replacer)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

UNASSIGNED

public static final byte UNASSIGNED

UPPERCASE_LETTER

public static final byte UPPERCASE_LETTER

LOWERCASE_LETTER

public static final byte LOWERCASE_LETTER

TITLECASE_LETTER

public static final byte TITLECASE_LETTER

MODIFIER_LETTER

public static final byte MODIFIER_LETTER

OTHER_LETTER

public static final byte OTHER_LETTER

NON_SPACING_MARK

public static final byte NON_SPACING_MARK

ENCLOSING_MARK

public static final byte ENCLOSING_MARK

COMBINING_SPACING_MARK

public static final byte COMBINING_SPACING_MARK

DECIMAL_DIGIT_NUMBER

public static final byte DECIMAL_DIGIT_NUMBER

LETTER_NUMBER

public static final byte LETTER_NUMBER

OTHER_NUMBER

public static final byte OTHER_NUMBER

SPACE_SEPARATOR

public static final byte SPACE_SEPARATOR

LINE_SEPARATOR

public static final byte LINE_SEPARATOR

PARAGRAPH_SEPARATOR

public static final byte PARAGRAPH_SEPARATOR

CONTROL

public static final byte CONTROL

FORMAT

public static final byte FORMAT

PRIVATE_USE

public static final byte PRIVATE_USE

SURROGATE

public static final byte SURROGATE

DASH_PUNCTUATION

public static final byte DASH_PUNCTUATION

START_PUNCTUATION

public static final byte START_PUNCTUATION

END_PUNCTUATION

public static final byte END_PUNCTUATION

CONNECTOR_PUNCTUATION

public static final byte CONNECTOR_PUNCTUATION

OTHER_PUNCTUATION

public static final byte OTHER_PUNCTUATION

MATH_SYMBOL

public static final byte MATH_SYMBOL

CURRENCY_SYMBOL

public static final byte CURRENCY_SYMBOL

MODIFIER_SYMBOL

public static final byte MODIFIER_SYMBOL

OTHER_SYMBOL

public static final byte OTHER_SYMBOL
Constructor Detail

UInfo

public UInfo(java.lang.String fileName,
             java.lang.String composeExcludeFileName)

UInfo

public UInfo()
Method Detail

getName

public java.lang.String getName(char ch)

getDecomposition

public java.lang.String getDecomposition(char ch)

getName10

public java.lang.String getName10(char ch)

getComment

public java.lang.String getComment(char ch)

getNumeric

public float getNumeric(char ch)

getCanonicalClass

public short getCanonicalClass(char ch)

getDecimal

public short getDecimal(char ch)

getDigit

public short getDigit(char ch)

getUppercase

public char getUppercase(char ch)

getLowercase

public char getLowercase(char ch)

getTitlecase

public char getTitlecase(char ch)

getCategory

public byte getCategory(char ch)

getBidiClass

public byte getBidiClass(char ch)

getMirrored

public boolean getMirrored(char ch)

isDisparaged

public boolean isDisparaged(char ch)

isLetter

public boolean isLetter(char ch)

isMark

public boolean isMark(char ch)

isNumber

public boolean isNumber(char ch)

isSeparator

public boolean isSeparator(char ch)

isFormat

public boolean isFormat(char ch)

isPunctuation

public boolean isPunctuation(char ch)

isSymbol

public boolean isSymbol(char ch)

isExcludedComposition

public boolean isExcludedComposition(char ch)
Is this character excluded from the composition algorithm by virtue of being listed in the composition exclusion table in Tech Report #15?

getName

public java.lang.String getName(java.lang.String s)

getName

public java.lang.String getName(java.lang.String s,
                                boolean shortVersion)

getName

public java.lang.String getName(char ch,
                                boolean shortVersion)

replace

public java.lang.String replace(java.lang.String source,
                                java.lang.String replacee,
                                java.lang.String replacer)

isCCS

public boolean isCCS(java.lang.String s)

isCBS

public boolean isCBS(java.lang.String s)

hasCanonicalDecomposition

public boolean hasCanonicalDecomposition(char ch)

hasCompatibilityDecomposition

public boolean hasCompatibilityDecomposition(char ch)

isEquivalent

public boolean isEquivalent(java.lang.String a,
                            java.lang.String b,
                            boolean canonical)

getFullDecomposition

public java.lang.String getFullDecomposition(java.lang.String s,
                                             boolean canonical)

getFullDecomposition

public java.lang.StringBuffer getFullDecomposition(char ch,
                                                   boolean canonical,
                                                   java.lang.StringBuffer output)

getFullDecomposition

public java.lang.String getFullDecomposition(char ch,
                                             boolean canonical)

fixCanonical

public java.lang.StringBuffer fixCanonical(java.lang.StringBuffer target)
Given a decomposed string of characters, put it in canonical order by finding and processing all exchangeable pairs.

fixCanonical

public java.lang.String fixCanonical(java.lang.String source)

getDecompositionChars

public java.lang.String getDecompositionChars(char ch)


Copyright (c) 2001 IBM Corporation and others.