深入学习java源码之Subset与UnicodeBlock
Character.Subset表示Unicode字符集的特定子集
Modifier and Type | Method and Description |
---|---|
boolean |
equals(Object obj) 比较两个 |
int |
hashCode() 返回由 |
String |
toString() 返回此子集的名称。 |
java源码
public final
class Character implements java.io.Serializable, Comparable<Character> {
public static final int MIN_RADIX = 2;
public static final int MAX_RADIX = 36;
public static final char MIN_VALUE = '\u0000';
public static final char MAX_VALUE = '\uFFFF';
@SuppressWarnings("unchecked")
public static final Class<Character> TYPE = (Class<Character>) Class.getPrimitiveClass("char");
public static final byte UNASSIGNED = 0;
public static final byte UPPERCASE_LETTER = 1;
static final int ERROR = 0xFFFFFFFF;
public static final byte DIRECTIONALITY_UNDEFINED = -1;
public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
public static final char MIN_HIGH_SURROGATE = '\uD800';
public static final char MAX_HIGH_SURROGATE = '\uDBFF';
public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
public static final int MAX_CODE_POINT = 0X10FFFF;
public static class Subset {
private String name;
protected Subset(String name) {
if (name == null) {
throw new NullPointerException("name");
}
this.name = name;
}
public final boolean equals(Object obj) {
return (this == obj);
}
public final int hashCode() {
return super.hashCode();
}
public final String toString() {
return name;
}
}
}
Character.UnicodeBlock 一系列字符子集,表示Unicode规范中的字符块。
字符块通常定义用于特定脚本或目的的字符。 一个字符最多包含一个Unicode块。
字段
static Character.UnicodeBlock |
ANCIENT_GREEK_NUMBERS 常数为“古希腊数字”Unicode字符块。 |
static Character.UnicodeBlock |
ANCIENT_SYMBOLS “古代符号”Unicode字符块的常数。 |
static Character.UnicodeBlock |
ARABIC “阿拉伯语”Unicode字符块的常量。 |
static Character.UnicodeBlock |
ARABIC_EXTENDED_A “阿拉伯语扩展A”Unicode字符块的常量。 |
static Character.UnicodeBlock |
ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS 常数为“阿拉伯数学字母符号”Unicode字符块。 |
方法
Modifier and Type | Method and Description |
---|---|
static Character.UnicodeBlock |
forName(String blockName) 返回具有给定名称的UnicodeBlock。 |
static Character.UnicodeBlock |
of(char c) 返回表示包含给定字符,或Unicode的块中的对象 |
static Character.UnicodeBlock |
of(int codePoint) 返回表示包含给定字符(Unicode代码点)Unicode的块中的对象,或 |
public final class Locale implements Cloneable, Serializable {
static private final Cache LOCALECACHE = new Cache();
/** Useful constant for country.
*/
static public final Locale US = createConstant("en", "US");
/**
* This method must be called only for creating the Locale.*
* constants due to making shortcuts.
*/
private static Locale createConstant(String lang, String country) {
BaseLocale base = BaseLocale.createInstance(lang, country);
return getInstance(base, null);
}
}
public static final class UnicodeBlock extends Subset {
private static Map<String, UnicodeBlock> map = new HashMap<>(256);
private UnicodeBlock(String idName) {
super(idName);
map.put(idName, this);
}
private UnicodeBlock(String idName, String alias) {
this(idName);
map.put(alias, this);
}
private UnicodeBlock(String idName, String... aliases) {
this(idName);
for (String alias : aliases)
map.put(alias, this);
}
public static final UnicodeBlock BASIC_LATIN =
new UnicodeBlock("BASIC_LATIN",
"BASIC LATIN",
"BASICLATIN");
public static final UnicodeBlock LATIN_1_SUPPLEMENT =
new UnicodeBlock("LATIN_1_SUPPLEMENT",
"LATIN-1 SUPPLEMENT",
"LATIN-1SUPPLEMENT");
public static final UnicodeBlock LATIN_EXTENDED_A =
new UnicodeBlock("LATIN_EXTENDED_A",
"LATIN EXTENDED-A",
"LATINEXTENDED-A");
public static final UnicodeBlock CYRILLIC =
new UnicodeBlock("CYRILLIC");
public static final UnicodeBlock ARMENIAN =
new UnicodeBlock("ARMENIAN");
public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS =
new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS",
"COMBINING DIACRITICAL MARKS FOR SYMBOLS",
"COMBININGDIACRITICALMARKSFORSYMBOLS",
"COMBINING MARKS FOR SYMBOLS",
"COMBININGMARKSFORSYMBOLS");
public static final UnicodeBlock ARROWS =
new UnicodeBlock("ARROWS");
public static final UnicodeBlock SPECIALS =
new UnicodeBlock("SPECIALS");
public static final UnicodeBlock PHAGS_PA =
new UnicodeBlock("PHAGS_PA",
"PHAGS-PA");
public static final UnicodeBlock ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS =
new UnicodeBlock("ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS",
"ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
"ARABICMATHEMATICALALPHABETICSYMBOLS");
private static final int blockStarts[] = {
0x0000, // 0000..007F; Basic Latin
0x0080, // 0080..00FF; Latin-1 Supplement
0x0100, // 0100..017F; Latin Extended-A
0x0180, // 0180..024F; Latin Extended-B
0x0400, // 0400..04FF; Cyrillic
0x0500, // 0500..052F; Cyrillic Supplement
0x0530, // 0530..058F; Armenian
0x0590, // 0590..05FF; Hebrew
0x0600, // 0600..06FF; Arabic
0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A
0x100000 // 100000..10FFFF; Supplementary Private Use Area-B
};
private static final UnicodeBlock[] blocks = {
BASIC_LATIN,
LATIN_1_SUPPLEMENT,
LATIN_EXTENDED_A,
LATIN_EXTENDED_B,
IPA_EXTENSIONS,
SPACING_MODIFIER_LETTERS,
COMBINING_DIACRITICAL_MARKS,
GREEK,
CYRILLIC,
CYRILLIC_SUPPLEMENTARY,
ARMENIAN,
THAI,
LAO,
TIBETAN,
MYANMAR,
null,
TAGS,
null,
VARIATION_SELECTORS_SUPPLEMENT,
null,
SUPPLEMENTARY_PRIVATE_USE_AREA_A,
SUPPLEMENTARY_PRIVATE_USE_AREA_B
};
public static UnicodeBlock of(char c) {
return of((int)c);
}
public static UnicodeBlock of(int codePoint) {
if (!isValidCodePoint(codePoint)) {
throw new IllegalArgumentException();
}
int top, bottom, current;
bottom = 0;
top = blockStarts.length;
current = top/2;
// invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
while (top - bottom > 1) {
if (codePoint >= blockStarts[current]) {
bottom = current;
} else {
top = current;
}
current = (top + bottom) / 2;
}
return blocks[current];
}
public static final UnicodeBlock forName(String blockName) {
UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US));
if (block == null) {
throw new IllegalArgumentException();
}
return block;
}
}
public static boolean isValidCodePoint(int codePoint) {
// Optimized form of:
// codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT
int plane = codePoint >>> 16;
return plane < ((MAX_CODE_POINT + 1) >>> 16);
}
static class Character.UnicodeScript 一个家庭代表在定义的字符脚本字符子集的 Unicode Standard Annex #24: Script Names
每个Unicode字符都分配给一个Unicode脚本,一个特定的脚本,如Latin ,或以下三个特殊值之一 , Inherited,Common或Unknown 。
Modifier and Type | Method and Description |
---|---|
static Character.UnicodeScript |
forName(String scriptName) 使用给定的Unicode脚本名称或脚本名称别名返回UnicodeScript常量。 |
static Character.UnicodeScript |
of(int codePoint) 返回表示给定字符(Unicode代码点)分配给的Unicode脚本的枚举常量。 |
static Character.UnicodeScript |
valueOf(String name) 以指定的名称返回此类型的枚举常量。 |
static Character.UnicodeScript[] |
values() 按照它们声明的顺序返回一个包含此枚举类型常量的数组。 |
public static enum UnicodeScript {
/**
* Unicode script "Common".
*/
COMMON,
/**
* Unicode script "Latin".
*/
LATIN,
/**
* Unicode script "Greek".
*/
GREEK,
/**
* Unicode script "Cyrillic".
*/
CYRILLIC,
/**
* Unicode script "Armenian".
*/
ARMENIAN,
/**
* Unicode script "Hebrew".
*/
HEBREW,
/**
* Unicode script "Arabic".
*/
ARABIC,
/**
* Unicode script "Takri".
*/
TAKRI,
/**
* Unicode script "Miao".
*/
MIAO,
/**
* Unicode script "Unknown".
*/
UNKNOWN;
private static final int[] scriptStarts = {
0x0000, // 0000..0040; COMMON
0x0041, // 0041..005A; LATIN
0x005B, // 005B..0060; COMMON
0x0061, // 0061..007A; LATIN
0x007B, // 007B..00A9; COMMON
0x0370, // 0370..0373; GREEK
0x0374, // 0374..0374; COMMON
0x0375, // 0375..037D; GREEK
0x037E, // 037E..0383; COMMON
0x0384, // 0384..0384; GREEK
0x0385, // 0385..0385; COMMON
0x0386, // 0386..0386; GREEK
0x0387, // 0387..0387; COMMON
0x0388, // 0388..03E1; GREEK
0x03E2, // 03E2..03EF; COPTIC
0x03F0, // 03F0..03FF; GREEK
0x1D200, // 1D200..1D2FF; GREEK
0x1D300, // 1D300..1EDFF; COMMON
0x1EE00, // 1EE00..1EFFF; ARABIC
0x1F000, // 1F000..1F1FF; COMMON
0x1F200, // 1F200..1F200; HIRAGANA
0x1F201, // 1F210..1FFFF; COMMON
0x20000, // 20000..E0000; HAN
0xE0001, // E0001..E00FF; COMMON
0xE0100, // E0100..E01EF; INHERITED
0xE01F0 // E01F0..10FFFF; UNKNOWN
};
private static final UnicodeScript[] scripts = {
COMMON,
LATIN,
COMMON,
LATIN,
COMMON,
LATIN,
COMMON,
LATIN,
COMMON,
LATIN,
COMMON,
LATIN,
COMMON,
LATIN,
COMMON,
LATIN,
GREEK,
COMMON,
GREEK,
COMMON,
GREEK,
COMMON,
GREEK,
COMMON,
GREEK,
COPTIC,
GREEK,
COMMON,
HAN,
COMMON,
INHERITED,
UNKNOWN
};
private static HashMap<String, Character.UnicodeScript> aliases;
static {
aliases = new HashMap<>(128);
aliases.put("ARAB", ARABIC);
aliases.put("ARMI", IMPERIAL_ARAMAIC);
aliases.put("ARMN", ARMENIAN);
aliases.put("AVST", AVESTAN);
aliases.put("BALI", BALINESE);
aliases.put("BAMU", BAMUM);
aliases.put("BATK", BATAK);
aliases.put("BENG", BENGALI);
aliases.put("BOPO", BOPOMOFO);
aliases.put("BRAI", BRAILLE);
aliases.put("BRAH", BRAHMI);
aliases.put("BUGI", BUGINESE);
aliases.put("BUHD", BUHID);
aliases.put("CAKM", CHAKMA);
aliases.put("CANS", CANADIAN_ABORIGINAL);
aliases.put("CARI", CARIAN);
aliases.put("CHAM", CHAM);
aliases.put("CHER", CHEROKEE);
aliases.put("COPT", COPTIC);
aliases.put("CPRT", CYPRIOT);
aliases.put("CYRL", CYRILLIC);
aliases.put("DEVA", DEVANAGARI);
aliases.put("TGLG", TAGALOG);
aliases.put("THAA", THAANA);
aliases.put("THAI", THAI);
aliases.put("TIBT", TIBETAN);
aliases.put("UGAR", UGARITIC);
aliases.put("VAII", VAI);
aliases.put("XPEO", OLD_PERSIAN);
aliases.put("XSUX", CUNEIFORM);
aliases.put("YIII", YI);
aliases.put("ZINH", INHERITED);
aliases.put("ZYYY", COMMON);
aliases.put("ZZZZ", UNKNOWN);
}
public static UnicodeScript of(int codePoint) {
if (!isValidCodePoint(codePoint))
throw new IllegalArgumentException();
int type = getType(codePoint);
// leave SURROGATE and PRIVATE_USE for table lookup
if (type == UNASSIGNED)
return UNKNOWN;
int index = Arrays.binarySearch(scriptStarts, codePoint);
if (index < 0)
index = -index - 2;
return scripts[index];
}
public static final UnicodeScript forName(String scriptName) {
scriptName = scriptName.toUpperCase(Locale.ENGLISH);
//.replace(' ', '_'));
UnicodeScript sc = aliases.get(scriptName);
if (sc != null)
return sc;
return valueOf(scriptName);
}
}
public static int getType(char ch) {
return getType((int)ch);
}
public static int getType(int codePoint) {
return CharacterData.of(codePoint).getType(codePoint);
}
abstract class CharacterData {
abstract int getProperties(int ch);
abstract int getType(int ch);
abstract boolean isWhitespace(int ch);
abstract boolean isMirrored(int ch);
abstract boolean isJavaIdentifierStart(int ch);
abstract boolean isJavaIdentifierPart(int ch);
abstract boolean isUnicodeIdentifierStart(int ch);
abstract boolean isUnicodeIdentifierPart(int ch);
abstract boolean isIdentifierIgnorable(int ch);
abstract int toLowerCase(int ch);
abstract int toUpperCase(int ch);
abstract int toTitleCase(int ch);
abstract int digit(int ch, int radix);
abstract int getNumericValue(int ch);
abstract byte getDirectionality(int ch);
//need to implement for JSR204
int toUpperCaseEx(int ch) {
return toUpperCase(ch);
}
char[] toUpperCaseCharArray(int ch) {
return null;
}
boolean isOtherLowercase(int ch) {
return false;
}
boolean isOtherUppercase(int ch) {
return false;
}
boolean isOtherAlphabetic(int ch) {
return false;
}
boolean isIdeographic(int ch) {
return false;
}
// Character <= 0xff (basic latin) is handled by internal fast-path
// to avoid initializing large tables.
// Note: performance of this "fast-path" code may be sub-optimal
// in negative cases for some accessors due to complicated ranges.
// Should revisit after optimization of table initialization.
static final CharacterData of(int ch) {
if (ch >>> 8 == 0) { // fast-path
return CharacterDataLatin1.instance;
} else {
switch(ch >>> 16) { //plane 00-16
case(0):
return CharacterData00.instance;
case(1):
return CharacterData01.instance;
case(2):
return CharacterData02.instance;
case(14):
return CharacterData0E.instance;
case(15): // Private Use
case(16): // Private Use
return CharacterDataPrivateUse.instance;
default:
return CharacterDataUndefined.instance;
}
}
}
}
package java.lang;
/** The CharacterData class encapsulates the large tables found in
Java.lang.Character. */
class CharacterDataLatin1 extends CharacterData {
int getProperties(int ch) {
char offset = (char)ch;
int props = A[offset];
return props;
}
int getPropertiesEx(int ch) {
char offset = (char)ch;
int props = B[offset];
return props;
}
boolean isOtherLowercase(int ch) {
int props = getPropertiesEx(ch);
return (props & 0x0001) != 0;
}
boolean isOtherUppercase(int ch) {
int props = getPropertiesEx(ch);
return (props & 0x0002) != 0;
}
boolean isOtherAlphabetic(int ch) {
int props = getPropertiesEx(ch);
return (props & 0x0004) != 0;
}
boolean isIdeographic(int ch) {
int props = getPropertiesEx(ch);
return (props & 0x0010) != 0;
}
int getType(int ch) {
int props = getProperties(ch);
return (props & 0x1F);
}
boolean isJavaIdentifierStart(int ch) {
int props = getProperties(ch);
return ((props & 0x00007000) >= 0x00005000);
}
boolean isJavaIdentifierPart(int ch) {
int props = getProperties(ch);
return ((props & 0x00003000) != 0);
}
boolean isUnicodeIdentifierStart(int ch) {
int props = getProperties(ch);
return ((props & 0x00007000) == 0x00007000);
}
boolean isUnicodeIdentifierPart(int ch) {
int props = getProperties(ch);
return ((props & 0x00001000) != 0);
}
boolean isIdentifierIgnorable(int ch) {
int props = getProperties(ch);
return ((props & 0x00007000) == 0x00001000);
}
int toLowerCase(int ch) {
int mapChar = ch;
int val = getProperties(ch);
if (((val & 0x00020000) != 0) &&
((val & 0x07FC0000) != 0x07FC0000)) {
int offset = val << 5 >> (5+18);
mapChar = ch + offset;
}
return mapChar;
}
int toUpperCase(int ch) {
int mapChar = ch;
int val = getProperties(ch);
if ((val & 0x00010000) != 0) {
if ((val & 0x07FC0000) != 0x07FC0000) {
int offset = val << 5 >> (5+18);
mapChar = ch - offset;
} else if (ch == 0x00B5) {
mapChar = 0x039C;
}
}
return mapChar;
}
int toTitleCase(int ch) {
return toUpperCase(ch);
}
int digit(int ch, int radix) {
int value = -1;
if (radix >= Character.MIN_RADIX && radix <= Character.MAX_RADIX) {
int val = getProperties(ch);
int kind = val & 0x1F;
if (kind == Character.DECIMAL_DIGIT_NUMBER) {
value = ch + ((val & 0x3E0) >> 5) & 0x1F;
}
else if ((val & 0xC00) == 0x00000C00) {
// Java supradecimal digit
value = (ch + ((val & 0x3E0) >> 5) & 0x1F) + 10;
}
}
return (value < radix) ? value : -1;
}
int getNumericValue(int ch) {
int val = getProperties(ch);
int retval = -1;
switch (val & 0xC00) {
default: // cannot occur
case (0x00000000): // not numeric
retval = -1;
break;
case (0x00000400): // simple numeric
retval = ch + ((val & 0x3E0) >> 5) & 0x1F;
break;
case (0x00000800) : // "strange" numeric
retval = -2;
break;
case (0x00000C00): // Java supradecimal
retval = (ch + ((val & 0x3E0) >> 5) & 0x1F) + 10;
break;
}
return retval;
}
boolean isWhitespace(int ch) {
int props = getProperties(ch);
return ((props & 0x00007000) == 0x00004000);
}
byte getDirectionality(int ch) {
int val = getProperties(ch);
byte directionality = (byte)((val & 0x78000000) >> 27);
if (directionality == 0xF ) {
directionality = -1;
}
return directionality;
}
boolean isMirrored(int ch) {
int props = getProperties(ch);
return ((props & 0x80000000) != 0);
}
int toUpperCaseEx(int ch) {
int mapChar = ch;
int val = getProperties(ch);
if ((val & 0x00010000) != 0) {
if ((val & 0x07FC0000) != 0x07FC0000) {
int offset = val << 5 >> (5+18);
mapChar = ch - offset;
}
else {
switch(ch) {
// map overflow characters
case 0x00B5 : mapChar = 0x039C; break;
default : mapChar = Character.ERROR; break;
}
}
}
return mapChar;
}
static char[] sharpsMap = new char[] {'S', 'S'};
char[] toUpperCaseCharArray(int ch) {
char[] upperMap = {(char)ch};
if (ch == 0x00DF) {
upperMap = sharpsMap;
}
return upperMap;
}
static final CharacterDataLatin1 instance = new CharacterDataLatin1();
private CharacterDataLatin1() {};
// The following tables and code generated using:
// java GenerateCharacter -template c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u181/11358/jdk/make/data/characterdata/CharacterDataLatin1.java.template -spec c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u181/11358/jdk/make/data/unicodedata/UnicodeData.txt -specialcasing c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u181/11358/jdk/make/data/unicodedata/SpecialCasing.txt -proplist c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u181/11358/jdk/make/data/unicodedata/PropList.txt -o c:/re/workspace/8-2-build-windows-amd64-cygwin/jdk8u181/11358/build/windows-amd64/jdk/gensrc/java/lang/CharacterDataLatin1.java -string -usecharforbyte -latin1 8
// The A table has 256 entries for a total of 1024 bytes.
static final int A[] = new int[256];
static final String A_DATA =
"\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
"\u100F\u4800\u100F\u4800\u100F\u5800\u400F\u5000\u400F\u5800\u400F\u6000\u400F"+
"\u5000\u400F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F"+
"\u4800\u100F\u4800\u100F\u5000\u400F\u5000\u400F\u5000\u400F\u5800\u400F\u6000"+
"\u400C\u6800\030\u6800\030\u2800\030\u2800\u601A\u2800\030\u6800\030\u6800"+
"\030\uE800\025\uE800\026\u6800\030\u2000\031\u3800\030\u2000\024\u3800\030"+
"\u3800\030\u1800\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u1800"+
"\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u1800\u3609\u3800\030\u6800\030"+
"\uE800\031\u6800\031\uE800\031\u6800\030\u6800\030\202\u7FE1\202\u7FE1\202"+
"\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1"+
"\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202"+
"\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1\202\u7FE1"+
"\202\u7FE1\uE800\025\u6800\030\uE800\026\u6800\033\u6800\u5017\u6800\033\201"+
"\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2"+
"\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201"+
"\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2\201\u7FE2"+
"\201\u7FE2\201\u7FE2\201\u7FE2\uE800\025\u6800\031\uE800\026\u6800\031\u4800"+
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u5000\u100F"+
"\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F"+
"\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800"+
"\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F\u4800\u100F"+
"\u3800\014\u6800\030\u2800\u601A\u2800\u601A\u2800\u601A\u2800\u601A\u6800"+
"\034\u6800\030\u6800\033\u6800\034\000\u7005\uE800\035\u6800\031\u4800\u1010"+
"\u6800\034\u6800\033\u2800\034\u2800\031\u1800\u060B\u1800\u060B\u6800\033"+
"\u07FD\u7002\u6800\030\u6800\030\u6800\033\u1800\u050B\000\u7005\uE800\036"+
"\u6800\u080B\u6800\u080B\u6800\u080B\u6800\030\202\u7001\202\u7001\202\u7001"+
"\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202"+
"\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001"+
"\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\u6800\031\202\u7001\202"+
"\u7001\202\u7001\202\u7001\202\u7001\202\u7001\202\u7001\u07FD\u7002\201\u7002"+
"\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201"+
"\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002"+
"\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\u6800"+
"\031\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002\201\u7002"+
"\u061D\u7002";
// The B table has 256 entries for a total of 512 bytes.
static final char B[] = (
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\001"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\001\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000"+
"\000\000\000\000\000\000\000\000\000").toCharArray();
// In all, the character property tables require 1024 bytes.
static {
{ // THIS CODE WAS AUTOMATICALLY CREATED BY GenerateCharacter:
char[] data = A_DATA.toCharArray();
assert (data.length == (256 * 2));
int i = 0, j = 0;
while (i < (256 * 2)) {
int entry = data[i++] << 16;
A[j++] = entry | data[i++];
}
}
}
}