AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-4334 Unicode 4.1 update

Browse Source 
X-SVN-Rev: 17104
This commit is contained in:
Markus Scherer 2005-01-10 18:02:54 +00:00
parent 723f11566a
commit 7f8d06b42b
40 changed files with 10356 additions and 2524 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
icu4c/source/common/uchar.c
View File

@ -958,12 +958,8 @@ uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
return;
}
/* add the start code point of each same-value range of each trie */
/* add the start code point of each same-value range of the main trie */
utrie_enum(&propsTrie, NULL, _enumPropertyStartsRange, sa);
if(propsVectorsColumns>0) {
/* if propsVectorsColumns==0 then the properties vectors trie may not be there at all */
utrie_enum(&propsVectorsTrie, NULL, _enumPropertyStartsRange, sa);
}
/* add code points with hardcoded properties, plus the ones following them */
@ -992,6 +988,16 @@ uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
sa->add(sa->set, U_z+1);
sa->add(sa->set, U_A);
sa->add(sa->set, U_Z+1);
sa->add(sa->set, U_FW_a);
sa->add(sa->set, U_FW_z+1);
sa->add(sa->set, U_FW_A);
sa->add(sa->set, U_FW_Z+1);
/* add for u_isxdigit() */
sa->add(sa->set, U_f+1);
sa->add(sa->set, U_F+1);
sa->add(sa->set, U_FW_f+1);
sa->add(sa->set, U_FW_F+1);
/* add for UCHAR_DEFAULT_IGNORABLE_CODE_POINT what was not added above */
sa->add(sa->set, WJ); /* range WJ..NOMDIG */
@ -1003,3 +1009,21 @@ uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
/* add for UCHAR_GRAPHEME_BASE and others */
USET_ADD_CP_AND_NEXT(sa, CGJ);
}
U_CAPI void U_EXPORT2
upropsvec_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
if(U_FAILURE(*pErrorCode)) {
return;
}
if(!HAVE_DATA) {
*pErrorCode=dataErrorCode;
return;
}
/* add the start code point of each same-value range of the properties vectors trie */
if(propsVectorsColumns>0) {
/* if propsVectorsColumns==0 then the properties vectors trie may not be there at all */
utrie_enum(&propsVectorsTrie, NULL, _enumPropertyStartsRange, sa);
}
}

136
icu4c/source/common/unicode/uchar.h
View File

@ -1,6 +1,6 @@
/*
**********************************************************************
* Copyright (C) 1997-2004, International Business Machines
* Copyright (C) 1997-2005, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
@ -39,7 +39,7 @@ U_CDECL_BEGIN
* @see u_getUnicodeVersion
* @stable ICU 2.0
*/
#define U_UNICODE_VERSION "4.0.1"
#define U_UNICODE_VERSION "4.1"
/**
* \file
@ -358,6 +358,16 @@ typedef enum UProperty {
processing collation tailoring rules.
@draft ICU 3.0 */
UCHAR_SEGMENT_STARTER,
/** Binary property Pattern_Syntax (new in Unicode 4.1).
See UAX #31 Identifier and Pattern Syntax
(http://www.unicode.org/reports/tr31/)
@draft ICU 3.4 */
UCHAR_PATTERN_SYNTAX,
/** Binary property Pattern_White_Space (new in Unicode 4.1).
See UAX #31 Identifier and Pattern Syntax
(http://www.unicode.org/reports/tr31/)
@draft ICU 3.4 */
UCHAR_PATTERN_WHITE_SPACE,
/** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */
UCHAR_BINARY_LIMIT,
@ -426,6 +436,21 @@ typedef enum UProperty {
see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */
UCHAR_TRAIL_CANONICAL_COMBINING_CLASS,
/** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
Used in UAX #29: Text Boundaries
(http://www.unicode.org/reports/tr29/)
Returns UGraphemeClusterBreak values. @draft ICU 3.4 */
UCHAR_GRAPHEME_CLUSTER_BREAK,
/** Enumerated property Sentence_Break (new in Unicode 4.1).
Used in UAX #29: Text Boundaries
(http://www.unicode.org/reports/tr29/)
Returns USentenceBreak values. @draft ICU 3.4 */
UCHAR_SENTENCE_BREAK,
/** Enumerated property Word_Break (new in Unicode 4.1).
Used in UAX #29: Text Boundaries
(http://www.unicode.org/reports/tr29/)
Returns UWordBreakValues values. @draft ICU 3.4 */
UCHAR_WORD_BREAK,
/** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
UCHAR_INT_LIMIT,
@ -1119,6 +1144,49 @@ enum UBlockCode {
/** @stable ICU 2.6 */
UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/
/* New blocks in Unicode 4.1 */
/** @draft ICU 3.4 */
UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
/** @draft ICU 3.4 */
UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
/** @draft ICU 3.4 */
UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
/** @draft ICU 3.4 */
UBLOCK_BUGINESE = 129, /*[1A00]*/
/** @draft ICU 3.4 */
UBLOCK_CJK_BASIC_STROKES = 130, /*[31C0]*/
/** @draft ICU 3.4 */
UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
/** @draft ICU 3.4 */
UBLOCK_COPTIC = 132, /*[2C80]*/
/** @draft ICU 3.4 */
UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
/** @draft ICU 3.4 */
UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
/** @draft ICU 3.4 */
UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
/** @draft ICU 3.4 */
UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
/** @draft ICU 3.4 */
UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
/** @draft ICU 3.4 */
UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
/** @draft ICU 3.4 */
UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
/** @draft ICU 3.4 */
UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
/** @draft ICU 3.4 */
UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
/** @draft ICU 3.4 */
UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
/** @draft ICU 3.4 */
UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
/** @draft ICU 3.4 */
UBLOCK_Tifinagh = 144, /*[2D30]*/
/** @draft ICU 3.4 */
UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
/** @stable ICU 2.0 */
UBLOCK_COUNT,
@ -1295,6 +1363,65 @@ typedef enum UJoiningGroup {
U_JG_COUNT
} UJoiningGroup;
/**
* Grapheme Cluster Break constants.
*
* @see UCHAR_GRAPHEME_CLUSTER_BREAK
* @draft ICU 3.4
*/
typedef enum UGraphemeClusterBreak {
U_GCB_OTHER, /*[Other]*/ /*See note !!*/
U_GCB_CONTROL, /*[Control]*/
U_GCB_CR, /*[CR]*/
U_GCB_EXTEND, /*[Extend]*/
U_GCB_L, /*[L]*/
U_GCB_LF, /*[LF]*/
U_GCB_LV, /*[LV]*/
U_GCB_LVT, /*[LVT]*/
U_GCB_T, /*[T]*/
U_GCB_V, /*[V]*/
U_GCB_COUNT
} UGraphemeClusterBreak;
/**
* Word Break constants.
* (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
*
* @see UCHAR_WORD_BREAK
* @draft ICU 3.4
*/
typedef enum UWordBreakValues {
U_WB_OTHER, /*[Other]*/ /*See note !!*/
U_WB_ALETTER, /*[ALetter]*/
U_WB_FORMAT, /*[Format]*/
U_WB_KATAKANA, /*[Katakana]*/
U_WB_MIDLETTER, /*[MidLetter]*/
U_WB_MIDNUM, /*[MidNum]*/
U_WB_NUMERIC, /*[Numeric]*/
U_WB_COUNT
} UWordBreakValues;
/**
* Sentence Break constants.
*
* @see UCHAR_SENTENCE_BREAK
* @draft ICU 3.4
*/
typedef enum USentenceBreak {
U_SB_OTHER, /*[Other]*/ /*See note !!*/
U_SB_ATERM, /*[ATerm]*/
U_SB_CLOSE, /*[Close]*/
U_SB_FORMAT, /*[Format]*/
U_SB_LOWER, /*[Lower]*/
U_SB_NUMERIC, /*[Numeric]*/
U_SB_OLETTER, /*[OLetter]*/
U_SB_SEP, /*[Sep]*/
U_SB_SP, /*[Sp]*/
U_SB_STERM, /*[STerm]*/
U_SB_UPPER, /*[Upper]*/
U_SB_COUNT
} USentenceBreak;
/**
* Line Break constants.
*
@ -1335,6 +1462,11 @@ typedef enum ULineBreak {
U_LB_ZWSPACE, /*[ZW]*/
U_LB_NEXT_LINE, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
U_LB_WORD_JOINER, /*[WJ]*/
U_LB_H2, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
U_LB_H3, /*[H3]*/
U_LB_JL, /*[JL]*/
U_LB_JT, /*[JT]*/
U_LB_JV, /*[JV]*/
U_LB_COUNT
} ULineBreak;

11
icu4c/source/common/unicode/uscript.h
View File

@ -1,6 +1,6 @@
/*
**********************************************************************
* Copyright (C) 1997-2004, International Business Machines
* Copyright (C) 1997-2005, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
@ -86,6 +86,15 @@ typedef enum UScriptCode {
/** New script code in Unicode 4.0.1 @draft ICU 3.0 */
USCRIPT_KATAKANA_OR_HIRAGANA,/*Hrkt */
/* New scripts in Unicode 4.1 @draft ICU 3.4 */
USCRIPT_BUGINESE, /* Bugi */
USCRIPT_GLAGOLITIC, /* Glag */
USCRIPT_KHAROSHTHI, /* Khar */
USCRIPT_SYLOTI_NAGRI, /* Sylo */
USCRIPT_NEW_TAI_LUE, /* Talu */
USCRIPT_TIFINAGH, /* Tfng */
USCRIPT_OLD_PERSIAN, /* Xpeo */
USCRIPT_CODE_LIMIT
} UScriptCode;

34
icu4c/source/common/uniset_props.cpp
View File

@ -1,7 +1,7 @@
/*
*******************************************************************************
*
* Copyright (C) 1999-2004, International Business Machines
* Copyright (C) 1999-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -89,24 +89,25 @@ U_CDECL_END
static const struct C99_Map {
const char* name;
C99_Property_Function func;
UPropertySource src;
} C99_DISPATCH[] = {
// These three entries omitted; they clash with PropertyAliases
// names for Unicode properties, so UnicodeSet already maps them
// to those properties.
//{ "alpha", u_isalpha },
//{ "lower", u_islower },
//{ "upper", u_isupper },
//{ "alpha", u_isalpha, UPROPS_SRC_PROPSVEC },
//{ "lower", u_islower, UPROPS_SRC_CASE },
//{ "upper", u_isupper, UPROPS_SRC_CASE },
// MUST be in SORTED order
{ "blank", u_isblank },
{ "cntrl", u_iscntrl },
{ "digit", u_isdigit },
{ "graph", u_isgraph },
{ "print", u_isprint },
{ "punct", u_ispunct },
{ "space", u_isspace },
{ "title", u_istitle },
{ "xdigit", u_isxdigit }
{ "blank", u_isblank, UPROPS_SRC_PROPSVEC },
{ "cntrl", u_iscntrl, UPROPS_SRC_CHAR },
{ "digit", u_isdigit, UPROPS_SRC_CHAR },
{ "graph", u_isgraph, UPROPS_SRC_CHAR },
{ "print", u_isprint, UPROPS_SRC_CHAR },
{ "punct", u_ispunct, UPROPS_SRC_CHAR },
{ "space", u_isspace, UPROPS_SRC_CHAR },
{ "title", u_istitle, UPROPS_SRC_CHAR },
{ "xdigit", u_isxdigit, UPROPS_SRC_CHAR }
};
#define C99_COUNT (9)
@ -1048,7 +1049,7 @@ UnicodeSet::applyPropertyAlias(const UnicodeString& prop,
if (!mungeCharName(buf, vname, sizeof(buf))) FAIL(ec);
UVersionInfo version;
u_versionFromString(version, buf);
applyFilter(versionFilter, &version, UPROPS_SRC_CHAR, ec);
applyFilter(versionFilter, &version, UPROPS_SRC_PROPSVEC, ec);
return *this;
}
break;
@ -1086,7 +1087,7 @@ UnicodeSet::applyPropertyAlias(const UnicodeString& prop,
for (int32_t i=0; i<C99_COUNT; ++i) {
int32_t c = uprv_comparePropertyNames(pname, C99_DISPATCH[i].name);
if (c == 0) {
applyFilter(c99Filter, (void*) &C99_DISPATCH[i], UPROPS_SRC_CHAR, ec);
applyFilter(c99Filter, (void*) &C99_DISPATCH[i], C99_DISPATCH[i].src, ec);
return *this;
} else if (c < 0) {
// Further entries will not match; bail out
@ -1336,6 +1337,9 @@ const UnicodeSet* UnicodeSet::getInclusions(int32_t src, UErrorCode &status) {
case UPROPS_SRC_CHAR:
uchar_addPropertyStarts(&sa, &status);
break;
case UPROPS_SRC_PROPSVEC:
upropsvec_addPropertyStarts(&sa, &status);
break;
case UPROPS_SRC_HST:
uhst_addPropertyStarts(&sa, &status);
break;

77
icu4c/source/common/uprops.c
View File

@ -86,7 +86,9 @@ static const struct {
{ UPROPS_SRC_NORM, 0 }, /* UCHAR_NFKD_INERT */
{ UPROPS_SRC_NORM, 0 }, /* UCHAR_NFC_INERT */
{ UPROPS_SRC_NORM, 0 }, /* UCHAR_NFKC_INERT */
{ UPROPS_SRC_NORM, 0 } /* UCHAR_SEGMENT_STARTER */
{ UPROPS_SRC_NORM, 0 }, /* UCHAR_SEGMENT_STARTER */
{ 2, U_MASK(UPROPS_V2_PATTERN_SYNTAX) },
{ 2, U_MASK(UPROPS_V2_PATTERN_WHITE_SPACE) }
};
U_CAPI UBool U_EXPORT2
@ -231,6 +233,12 @@ u_getIntPropertyValue(UChar32 c, UProperty which) {
case UCHAR_TRAIL_CANONICAL_COMBINING_CLASS:
return unorm_getFCD16FromCodePoint(c)&0xff;
#endif
case UCHAR_GRAPHEME_CLUSTER_BREAK:
return (int32_t)(u_getUnicodeProperties(c, 2)&UPROPS_GCB_MASK)>>UPROPS_GCB_SHIFT;
case UCHAR_SENTENCE_BREAK:
return (int32_t)(u_getUnicodeProperties(c, 2)&UPROPS_SB_MASK)>>UPROPS_SB_SHIFT;
case UCHAR_WORD_BREAK:
return (int32_t)(u_getUnicodeProperties(c, 2)&UPROPS_WB_MASK)>>UPROPS_WB_SHIFT;
default:
return 0; /* undefined */
}
@ -249,7 +257,6 @@ u_getIntPropertyMinValue(UProperty which) {
U_CAPI int32_t U_EXPORT2
u_getIntPropertyMaxValue(UProperty which) {
UErrorCode errorCode;
int32_t max;
if(which<UCHAR_BINARY_START) {
return -1; /* undefined */
@ -265,28 +272,23 @@ u_getIntPropertyMaxValue(UProperty which) {
errorCode=U_ZERO_ERROR;
return ubidi_getMaxValue(ubidi_getSingleton(&errorCode), which);
case UCHAR_BLOCK:
max=(uprv_getMaxValues(0)&UPROPS_BLOCK_MASK)>>UPROPS_BLOCK_SHIFT;
return max!=0 ? max : (int32_t)UBLOCK_COUNT-1;
return (uprv_getMaxValues(0)&UPROPS_BLOCK_MASK)>>UPROPS_BLOCK_SHIFT;
case UCHAR_CANONICAL_COMBINING_CLASS:
case UCHAR_LEAD_CANONICAL_COMBINING_CLASS:
case UCHAR_TRAIL_CANONICAL_COMBINING_CLASS:
return 0xff; /* TODO do we need to be more precise, getting the actual maximum? */
case UCHAR_DECOMPOSITION_TYPE:
max=uprv_getMaxValues(2)&UPROPS_DT_MASK;
return max!=0 ? max : (int32_t)U_DT_COUNT-1;
return uprv_getMaxValues(2)&UPROPS_DT_MASK;
case UCHAR_EAST_ASIAN_WIDTH:
max=(uprv_getMaxValues(0)&UPROPS_EA_MASK)>>UPROPS_EA_SHIFT;
return max!=0 ? max : (int32_t)U_EA_COUNT-1;
return (uprv_getMaxValues(0)&UPROPS_EA_MASK)>>UPROPS_EA_SHIFT;
case UCHAR_GENERAL_CATEGORY:
return (int32_t)U_CHAR_CATEGORY_COUNT-1;
case UCHAR_LINE_BREAK:
max=(uprv_getMaxValues(0)&UPROPS_LB_MASK)>>UPROPS_LB_SHIFT;
return max!=0 ? max : (int32_t)U_LB_COUNT-1;
return (uprv_getMaxValues(0)&UPROPS_LB_MASK)>>UPROPS_LB_SHIFT;
case UCHAR_NUMERIC_TYPE:
return (int32_t)U_NT_COUNT-1;
case UCHAR_SCRIPT:
max=uprv_getMaxValues(0)&UPROPS_SCRIPT_MASK;
return max!=0 ? max : (int32_t)USCRIPT_CODE_LIMIT-1;
return uprv_getMaxValues(0)&UPROPS_SCRIPT_MASK;
case UCHAR_HANGUL_SYLLABLE_TYPE:
return (int32_t)U_HST_COUNT-1;
#if !UCONFIG_NO_NORMALIZATION
@ -297,6 +299,12 @@ u_getIntPropertyMaxValue(UProperty which) {
case UCHAR_NFKC_QUICK_CHECK:
return (int32_t)UNORM_MAYBE;
#endif
case UCHAR_GRAPHEME_CLUSTER_BREAK:
return (uprv_getMaxValues(2)&UPROPS_GCB_MASK)>>UPROPS_GCB_SHIFT;
case UCHAR_SENTENCE_BREAK:
return (uprv_getMaxValues(2)&UPROPS_SB_MASK)>>UPROPS_SB_SHIFT;
case UCHAR_WORD_BREAK:
return (uprv_getMaxValues(2)&UPROPS_WB_MASK)>>UPROPS_WB_SHIFT;
default:
return -1; /* undefined */
}
@ -311,7 +319,7 @@ uprops_getSource(UProperty which) {
return UPROPS_SRC_NONE; /* undefined */
} else if(which<UCHAR_BINARY_LIMIT) {
if(binProps[which].mask!=0) {
return UPROPS_SRC_CHAR;
return UPROPS_SRC_PROPSVEC;
} else {
return (UPropertySource)binProps[which].column;
}
@ -319,6 +327,10 @@ uprops_getSource(UProperty which) {
return UPROPS_SRC_NONE; /* undefined */
} else if(which<UCHAR_INT_LIMIT) {
switch(which) {
case UCHAR_GENERAL_CATEGORY:
case UCHAR_NUMERIC_TYPE:
return UPROPS_SRC_CHAR;
case UCHAR_HANGUL_SYLLABLE_TYPE:
return UPROPS_SRC_HST;
@ -337,10 +349,43 @@ uprops_getSource(UProperty which) {
return UPROPS_SRC_BIDI;
default:
return UPROPS_SRC_CHAR;
return UPROPS_SRC_PROPSVEC;
}
} else if(which<UCHAR_STRING_START) {
switch(which) {
case UCHAR_GENERAL_CATEGORY_MASK:
case UCHAR_NUMERIC_VALUE:
return UPROPS_SRC_CHAR;
default:
return UPROPS_SRC_NONE;
}
} else if(which<UCHAR_STRING_LIMIT) {
switch(which) {
case UCHAR_AGE:
return UPROPS_SRC_PROPSVEC;
case UCHAR_BIDI_MIRRORING_GLYPH:
return UPROPS_SRC_BIDI;
case UCHAR_CASE_FOLDING:
case UCHAR_LOWERCASE_MAPPING:
case UCHAR_SIMPLE_CASE_FOLDING:
case UCHAR_SIMPLE_LOWERCASE_MAPPING:
case UCHAR_SIMPLE_TITLECASE_MAPPING:
case UCHAR_SIMPLE_UPPERCASE_MAPPING:
case UCHAR_TITLECASE_MAPPING:
case UCHAR_UPPERCASE_MAPPING:
return UPROPS_SRC_CASE;
case UCHAR_ISO_COMMENT:
case UCHAR_NAME:
case UCHAR_UNICODE_1_NAME:
return UPROPS_SRC_NAMES;
default:
return UPROPS_SRC_NONE;
}
} else if(which==UCHAR_GENERAL_CATEGORY_MASK) {
return UPROPS_SRC_CHAR;
} else {
return UPROPS_SRC_NONE; /* undefined */
}

48
icu4c/source/common/uprops.h
View File

@ -95,8 +95,7 @@ enum {
* Properties in vector word 0
* Bits
* 31..24 DerivedAge version major/minor one nibble each
* 23 reserved
* 22..18 Line Break
* 23..18 Line Break
* 17..15 East Asian Width
* 14.. 7 UBlockCode
* 6.. 0 UScriptCode
@ -106,7 +105,7 @@ enum {
#define UPROPS_AGE_MASK 0xff000000
#define UPROPS_AGE_SHIFT 24
#define UPROPS_LB_MASK 0x007C0000
#define UPROPS_LB_MASK 0x00FC0000
#define UPROPS_LB_SHIFT 18
#define UPROPS_EA_MASK 0x00038000
@ -168,21 +167,28 @@ enum {
* Properties in vector word 2
* Bits
* 31..24 More binary properties
* 13..11 reserved, was Joining Type in format version 3
* 10.. 5 reserved, was Joining Group in format version 3
* 23..19 reserved
* 18..14 Sentence Break
* 13..10 Word Break
* 9.. 5 Grapheme Cluster Break
* 4.. 0 Decomposition Type
*/
#define UPROPS_WAS_JT_MASK 0x00003800
#define UPROPS_WAS_JT_SHIFT 11
#define UPROPS_SB_MASK 0x0007c000
#define UPROPS_SB_SHIFT 14
#define UPROPS_WAS_JG_MASK 0x000007e0
#define UPROPS_WAS_JG_SHIFT 5
#define UPROPS_WB_MASK 0x00003c00
#define UPROPS_WB_SHIFT 10
#define UPROPS_GCB_MASK 0x000003e0
#define UPROPS_GCB_SHIFT 5
#define UPROPS_DT_MASK 0x0000001f
enum {
UPROPS_V2_S_TERM=24, /* new in ICU 3.0 and Unicode 4.0.1 */
UPROPS_V2_VARIATION_SELECTOR,
UPROPS_V2_PATTERN_SYNTAX, /* new in ICU 3.4 and Unicode 4.1 */
UPROPS_V2_PATTERN_WHITE_SPACE,
UPROPS_V2_TOP /* must be <=32 */
};
@ -260,8 +266,10 @@ enum {
FF =0x000c,
CR =0x000d,
U_A =0x0041,
U_F =0x0046,
U_Z =0x005a,
U_a =0x0061,
U_f =0x0066,
U_z =0x007a,
DEL =0x007f,
NL =0x0085,
@ -276,6 +284,12 @@ enum {
WJ =0x2060,
INHSWAP =0x206a,
NOMDIG =0x206f,
U_FW_A =0xff21,
U_FW_F =0xff26,
U_FW_Z =0xff3a,
U_FW_a =0xff41,
U_FW_f =0xff46,
U_FW_z =0xff5a,
ZWNBSP =0xfeff
};
@ -331,8 +345,10 @@ uprv_getISOCommentCharacters(const USetAdder *sa);
enum UPropertySource {
/** No source, not a supported property. */
UPROPS_SRC_NONE,
/** From uchar.c/uprops.icu */
/** From uchar.c/uprops.icu main trie */
UPROPS_SRC_CHAR,
/** From uchar.c/uprops.icu properties vectors trie */
UPROPS_SRC_PROPSVEC,
/** Hangul_Syllable_Type, from uchar.c/uprops.icu */
UPROPS_SRC_HST,
/** From unames.c/unames.icu */
@ -343,7 +359,7 @@ enum UPropertySource {
UPROPS_SRC_CASE,
/** From ubidi_props.c/ubidi.icu */
UPROPS_SRC_BIDI,
/** One more than the highes UPropertySource (UPROPS_SRC_) constant. */
/** One more than the highest UPropertySource (UPROPS_SRC_) constant. */
UPROPS_SRC_COUNT
};
typedef enum UPropertySource UPropertySource;
@ -356,13 +372,21 @@ U_CAPI UPropertySource U_EXPORT2
uprops_getSource(UProperty which);
/**
* Enumerate each core properties data trie and add the
* Enumerate uprops.icu's main data trie and add the
* start of each range of same properties to the set.
* @internal
*/
U_CAPI void U_EXPORT2
uchar_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode);
/**
* Enumerate uprops.icu's properties vectors trie and add the
* start of each range of same properties to the set.
* @internal
*/
U_CAPI void U_EXPORT2
upropsvec_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode);
/**
* Same as uchar_addPropertyStarts() but only for Hangul_Syllable_Type.
* @internal

2
icu4c/source/configure vendored
View File

@ -585,7 +585,7 @@ LIB_VERSION_MAJOR=`echo $LIB_VERSION | sed 's/\..*//'`
echo "$ac_t""release $VERSION, library $LIB_VERSION" 1>&6
UNICODE_VERSION="4.0.1"
UNICODE_VERSION="4.1"

4
icu4c/source/configure.in
View File

@ -1,6 +1,6 @@
dnl -*-m4-*-
dnl configure.in for ICU
dnl Copyright (c) 1999-2004, International Business Machines Corporation and
dnl Copyright (c) 1999-2005, International Business Machines Corporation and
dnl others. All Rights Reserved.
dnl Stephen F. Booth, heavily modified by Yves and others
@ -34,7 +34,7 @@ AC_SUBST(LIB_VERSION)
AC_SUBST(LIB_VERSION_MAJOR)
AC_MSG_RESULT([release $VERSION, library $LIB_VERSION])
UNICODE_VERSION="4.0.1"
UNICODE_VERSION="4.1"
AC_SUBST(UNICODE_VERSION)
AC_SUBST(CPPFLAGS)

4
icu4c/source/data/makedata.mak
View File

@ -1,5 +1,5 @@
#**********************************************************************
#* Copyright (C) 1999-2004, International Business Machines Corporation
#* Copyright (C) 1999-2005, International Business Machines Corporation
#* and others. All Rights Reserved.
#**********************************************************************
# nmake file for creating data files on win32
@ -13,7 +13,7 @@
U_ICUDATA_NAME=icudt33
##############################################################################
U_ICUDATA_ENDIAN_SUFFIX=l
UNICODE_VERSION=4.0.1
UNICODE_VERSION=4.1
# ICUMAKE
# Must be provided by whoever runs this makefile.

35
icu4c/source/data/unidata/BidiMirroring.txt
View File

@ -1,10 +1,14 @@
# BidiMirroring-4.0.0.txt
# BidiMirroring-4.1.0.txt
#
# Bidi_Mirroring_Glyph Property
#
# This file is an informative supplement to the UnicodeData file. It
# lists characters that have the mirrored property
# This file is an informative contributory data file in the
# Unicode Character Database.
#
# This data file lists characters that have the mirrored property
# where there is another Unicode character that typically has a glyph
# that is the mirror image of the original character's glyph.
# The repertoire covered by the file is Unicode 4.0.0.
# The repertoire covered by the file is Unicode 4.1.0.
#
# The file contains a list of lines with mappings from one code point
# to another one for character-based mirroring.
@ -24,7 +28,7 @@
# at http://www.unicode.org/unicode/reports/tr9/
#
# This file was originally created by Markus Scherer.
# Extended for Unicode 3.2 and 4.0 by Ken Whistler.
# Extended for Unicode 3.2, 4.0, and 4.1 by Ken Whistler.
#
# ############################################################
@ -180,6 +184,10 @@
2773; 2772 # LIGHT RIGHT TORTOISE SHELL BRACKET
2774; 2775 # MEDIUM LEFT CURLY BRACKET ORNAMENT
2775; 2774 # MEDIUM RIGHT CURLY BRACKET ORNAMENT
27C3; 27C4 # OPEN SUBSET
27C4; 27C3 # OPEN SUPERSET
27C5; 27C6 # LEFT S-SHAPED BAG DELIMITER
27C6; 27C5 # RIGHT S-SHAPED BAG DELIMITER
27D5; 27D6 # LEFT OUTER JOIN
27D6; 27D5 # RIGHT OUTER JOIN
27DD; 27DE # LONG RIGHT TACK
@ -238,7 +246,7 @@
29FD; 29FC # RIGHT-POINTING CURVED ANGLE BRACKET
2A2B; 2A2C # MINUS SIGN WITH FALLING DOTS
2A2C; 2A2B # MINUS SIGN WITH RISING DOTS
2A2D; 2A2C # PLUS SIGN IN LEFT HALF CIRCLE
2A2D; 2A2E # PLUS SIGN IN LEFT HALF CIRCLE
2A2E; 2A2D # PLUS SIGN IN RIGHT HALF CIRCLE
2A34; 2A35 # MULTIPLICATION SIGN IN LEFT HALF CIRCLE
2A35; 2A34 # MULTIPLICATION SIGN IN RIGHT HALF CIRCLE
@ -316,6 +324,16 @@
2AF8; 2AF7 # TRIPLE NESTED GREATER-THAN
2AF9; 2AFA # DOUBLE-LINE SLANTED LESS-THAN OR EQUAL TO
2AFA; 2AF9 # DOUBLE-LINE SLANTED GREATER-THAN OR EQUAL TO
2E02; 2E03 # LEFT SUBSTITUTION BRACKET
2E03; 2E02 # RIGHT SUBSTITUTION BRACKET
2E04; 2E05 # LEFT DOTTED SUBSTITUTION BRACKET
2E05; 2E04 # RIGHT DOTTED SUBSTITUTION BRACKET
2E09; 2E0A # LEFT TRANSPOSITION BRACKET
2E0A; 2E09 # RIGHT TRANSPOSITION BRACKET
2E0C; 2E0D # LEFT RAISED OMISSION BRACKET
2E0D; 2E0C # RIGHT RAISED OMISSION BRACKET
2E1C; 2E1D # LEFT LOW PARAPHRASE BRACKET
2E1D; 2E1C # RIGHT LOW PARAPHRASE BRACKET
3008; 3009 # LEFT ANGLE BRACKET
3009; 3008 # RIGHT ANGLE BRACKET
300A; 300B # LEFT DOUBLE ANGLE BRACKET
@ -347,7 +365,9 @@ FF60; FF5F # FULLWIDTH RIGHT WHITE PARENTHESIS
FF62; FF63 # [BEST FIT] HALFWIDTH LEFT CORNER BRACKET
FF63; FF62 # [BEST FIT] HALFWIDTH RIGHT CORNER BRACKET
# The following characters have no appropriate mirroring character
# The following characters have no appropriate mirroring character.
# For these characters it is up to the rendering system
# to provide mirrored glyphs.
# 2140; DOUBLE-STRUCK N-ARY SUMMATION
# 2201; COMPLEMENT
@ -410,6 +430,7 @@ FF63; FF62 # [BEST FIT] HALFWIDTH RIGHT CORNER BRACKET
# 22FF; Z NOTATION BAG MEMBERSHIP
# 2320; TOP HALF INTEGRAL
# 2321; BOTTOM HALF INTEGRAL
# 27C0; THREE DIMENSIONAL ANGLE
# 27D3; LOWER RIGHT CORNER WITH DOT
# 27D4; UPPER LEFT CORNER WITH DOT
# 27DC; LEFT MULTIMAP

41
icu4c/source/data/unidata/Blocks.txt
View File

@ -1,22 +1,27 @@
# Blocks-4.0.1.txt
# Date: 2004-03-01, 15:52 [KW]
# Blocks-4.1.0.txt
# Date: 2004-12-03, 15:20 [KW]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
#
# Note: The casing of block names is not normative.
# For example, "Basic Latin" and "BASIC LATIN" are equivalent.
#
# Format:
# Start Code..End Code; Block Name
# ================================================
# Note: When comparing block names, casing, whitespace, hyphens,
# and underbars are ignored.
# For example, "Latin Extended-A" and "latin extended a" are equivalent.
# For more information on the comparison of property values,
# see UCD.html.
#
# Code points not explicitly listed in this file are given the value No_Block.
# Format:
# Start Code..End Code; Block Name
# ================================================
# All code points not explicitly listed for Block
# have the value No_Block.
# Property: Block
@ -34,6 +39,7 @@
0590..05FF; Hebrew
0600..06FF; Arabic
0700..074F; Syriac
0750..077F; Arabic Supplement
0780..07BF; Thaana
0900..097F; Devanagari
0980..09FF; Bengali
@ -52,6 +58,7 @@
10A0..10FF; Georgian
1100..11FF; Hangul Jamo
1200..137F; Ethiopic
1380..139F; Ethiopic Supplement
13A0..13FF; Cherokee
1400..167F; Unified Canadian Aboriginal Syllabics
1680..169F; Ogham
@ -64,8 +71,12 @@
1800..18AF; Mongolian
1900..194F; Limbu
1950..197F; Tai Le
1980..19DF; New Tai Lue
19E0..19FF; Khmer Symbols
1A00..1A1F; Buginese
1D00..1D7F; Phonetic Extensions
1D80..1DBF; Phonetic Extensions Supplement
1DC0..1DFF; Combining Diacritical Marks Supplement
1E00..1EFF; Latin Extended Additional
1F00..1FFF; Greek Extended
2000..206F; General Punctuation
@ -92,6 +103,12 @@
2980..29FF; Miscellaneous Mathematical Symbols-B
2A00..2AFF; Supplemental Mathematical Operators
2B00..2BFF; Miscellaneous Symbols and Arrows
2C00..2C5F; Glagolitic
2C80..2C8F; Coptic
2D00..2D2F; Georgian Supplement
2D30..2D7F; Tifinagh
2D80..2DDF; Ethiopic Extended
2E00..2E7F; Supplemental Punctuation
2E80..2EFF; CJK Radicals Supplement
2F00..2FDF; Kangxi Radicals
2FF0..2FFF; Ideographic Description Characters
@ -102,6 +119,7 @@
3130..318F; Hangul Compatibility Jamo
3190..319F; Kanbun
31A0..31BF; Bopomofo Extended
31C0..31EF; CJK Basic Strokes
31F0..31FF; Katakana Phonetic Extensions
3200..32FF; Enclosed CJK Letters and Months
3300..33FF; CJK Compatibility
@ -110,6 +128,8 @@
4E00..9FFF; CJK Unified Ideographs
A000..A48F; Yi Syllables
A490..A4CF; Yi Radicals
A700..A71F; Modifier Tone Letters
A800..A82F; Syloti Nagri
AC00..D7AF; Hangul Syllables
D800..DB7F; High Surrogates
DB80..DBFF; High Private Use Surrogates
@ -119,6 +139,7 @@ F900..FAFF; CJK Compatibility Ideographs
FB00..FB4F; Alphabetic Presentation Forms
FB50..FDFF; Arabic Presentation Forms-A
FE00..FE0F; Variation Selectors
FE10..FE1F; Vertical Forms
FE20..FE2F; Combining Half Marks
FE30..FE4F; CJK Compatibility Forms
FE50..FE6F; Small Form Variants
@ -128,15 +149,19 @@ FFF0..FFFF; Specials
10000..1007F; Linear B Syllabary
10080..100FF; Linear B Ideograms
10100..1013F; Aegean Numbers
10140..1018F; Ancient Greek Numbers
10300..1032F; Old Italic
10330..1034F; Gothic
10380..1039F; Ugaritic
103A0..103DF; Old Persian
10400..1044F; Deseret
10450..1047F; Shavian
10480..104AF; Osmanya
10800..1083F; Cypriot Syllabary
10A00..10A5F; Kharoshthi
1D000..1D0FF; Byzantine Musical Symbols
1D100..1D1FF; Musical Symbols
1D200..1D24F; Ancient Greek Musical Notation
1D300..1D35F; Tai Xuan Jing Symbols
1D400..1D7FF; Mathematical Alphanumeric Symbols
20000..2A6DF; CJK Unified Ideographs Extension B

145
icu4c/source/data/unidata/CaseFolding.txt
View File

@ -1,8 +1,8 @@
# CaseFolding-4.0.1.txt
# Date: 2004-03-02, 02:41:24 GMT [MD]
# CaseFolding-4.1.0.txt
# Date: 2004-12-11, 05:35:45 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
# Case Folding Properties
@ -271,6 +271,9 @@
022E; C; 022F; # LATIN CAPITAL LETTER O WITH DOT ABOVE
0230; C; 0231; # LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON
0232; C; 0233; # LATIN CAPITAL LETTER Y WITH MACRON
023B; C; 023C; # LATIN CAPITAL LETTER C WITH STROKE
023D; C; 019A; # LATIN CAPITAL LETTER L WITH BAR
0241; C; 0294; # LATIN CAPITAL LETTER GLOTTAL STOP
0345; C; 03B9; # COMBINING GREEK YPOGEGRAMMENI
0386; C; 03AC; # GREEK CAPITAL LETTER ALPHA WITH TONOS
0388; C; 03AD; # GREEK CAPITAL LETTER EPSILON WITH TONOS
@ -449,6 +452,7 @@
04F0; C; 04F1; # CYRILLIC CAPITAL LETTER U WITH DIAERESIS
04F2; C; 04F3; # CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE
04F4; C; 04F5; # CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS
04F6; C; 04F7; # CYRILLIC CAPITAL LETTER GHE WITH DESCENDER
04F8; C; 04F9; # CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS
0500; C; 0501; # CYRILLIC CAPITAL LETTER KOMI DE
0502; C; 0503; # CYRILLIC CAPITAL LETTER KOMI DJE
@ -497,6 +501,44 @@
0555; C; 0585; # ARMENIAN CAPITAL LETTER OH
0556; C; 0586; # ARMENIAN CAPITAL LETTER FEH
0587; F; 0565 0582; # ARMENIAN SMALL LIGATURE ECH YIWN
10A0; C; 2D00; # GEORGIAN CAPITAL LETTER AN
10A1; C; 2D01; # GEORGIAN CAPITAL LETTER BAN
10A2; C; 2D02; # GEORGIAN CAPITAL LETTER GAN
10A3; C; 2D03; # GEORGIAN CAPITAL LETTER DON
10A4; C; 2D04; # GEORGIAN CAPITAL LETTER EN
10A5; C; 2D05; # GEORGIAN CAPITAL LETTER VIN
10A6; C; 2D06; # GEORGIAN CAPITAL LETTER ZEN
10A7; C; 2D07; # GEORGIAN CAPITAL LETTER TAN
10A8; C; 2D08; # GEORGIAN CAPITAL LETTER IN
10A9; C; 2D09; # GEORGIAN CAPITAL LETTER KAN
10AA; C; 2D0A; # GEORGIAN CAPITAL LETTER LAS
10AB; C; 2D0B; # GEORGIAN CAPITAL LETTER MAN
10AC; C; 2D0C; # GEORGIAN CAPITAL LETTER NAR
10AD; C; 2D0D; # GEORGIAN CAPITAL LETTER ON
10AE; C; 2D0E; # GEORGIAN CAPITAL LETTER PAR
10AF; C; 2D0F; # GEORGIAN CAPITAL LETTER ZHAR
10B0; C; 2D10; # GEORGIAN CAPITAL LETTER RAE
10B1; C; 2D11; # GEORGIAN CAPITAL LETTER SAN
10B2; C; 2D12; # GEORGIAN CAPITAL LETTER TAR
10B3; C; 2D13; # GEORGIAN CAPITAL LETTER UN
10B4; C; 2D14; # GEORGIAN CAPITAL LETTER PHAR
10B5; C; 2D15; # GEORGIAN CAPITAL LETTER KHAR
10B6; C; 2D16; # GEORGIAN CAPITAL LETTER GHAN
10B7; C; 2D17; # GEORGIAN CAPITAL LETTER QAR
10B8; C; 2D18; # GEORGIAN CAPITAL LETTER SHIN
10B9; C; 2D19; # GEORGIAN CAPITAL LETTER CHIN
10BA; C; 2D1A; # GEORGIAN CAPITAL LETTER CAN
10BB; C; 2D1B; # GEORGIAN CAPITAL LETTER JIL
10BC; C; 2D1C; # GEORGIAN CAPITAL LETTER CIL
10BD; C; 2D1D; # GEORGIAN CAPITAL LETTER CHAR
10BE; C; 2D1E; # GEORGIAN CAPITAL LETTER XAN
10BF; C; 2D1F; # GEORGIAN CAPITAL LETTER JHAN
10C0; C; 2D20; # GEORGIAN CAPITAL LETTER HAE
10C1; C; 2D21; # GEORGIAN CAPITAL LETTER HE
10C2; C; 2D22; # GEORGIAN CAPITAL LETTER HIE
10C3; C; 2D23; # GEORGIAN CAPITAL LETTER WE
10C4; C; 2D24; # GEORGIAN CAPITAL LETTER HAR
10C5; C; 2D25; # GEORGIAN CAPITAL LETTER HOE
1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW
1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE
1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW
@ -844,6 +886,103 @@
24CD; C; 24E7; # CIRCLED LATIN CAPITAL LETTER X
24CE; C; 24E8; # CIRCLED LATIN CAPITAL LETTER Y
24CF; C; 24E9; # CIRCLED LATIN CAPITAL LETTER Z
2C00; C; 2C30; # GLAGOLITIC CAPITAL LETTER AZU
2C01; C; 2C31; # GLAGOLITIC CAPITAL LETTER BUKY
2C02; C; 2C32; # GLAGOLITIC CAPITAL LETTER VEDE
2C03; C; 2C33; # GLAGOLITIC CAPITAL LETTER GLAGOLI
2C04; C; 2C34; # GLAGOLITIC CAPITAL LETTER DOBRO
2C05; C; 2C35; # GLAGOLITIC CAPITAL LETTER YESTU
2C06; C; 2C36; # GLAGOLITIC CAPITAL LETTER ZHIVETE
2C07; C; 2C37; # GLAGOLITIC CAPITAL LETTER DZELO
2C08; C; 2C38; # GLAGOLITIC CAPITAL LETTER ZEMLJA
2C09; C; 2C39; # GLAGOLITIC CAPITAL LETTER IZHE
2C0A; C; 2C3A; # GLAGOLITIC CAPITAL LETTER INITIAL IZHE
2C0B; C; 2C3B; # GLAGOLITIC CAPITAL LETTER I
2C0C; C; 2C3C; # GLAGOLITIC CAPITAL LETTER DJERVI
2C0D; C; 2C3D; # GLAGOLITIC CAPITAL LETTER KAKO
2C0E; C; 2C3E; # GLAGOLITIC CAPITAL LETTER LJUDIJE
2C0F; C; 2C3F; # GLAGOLITIC CAPITAL LETTER MYSLITE
2C10; C; 2C40; # GLAGOLITIC CAPITAL LETTER NASHI
2C11; C; 2C41; # GLAGOLITIC CAPITAL LETTER ONU
2C12; C; 2C42; # GLAGOLITIC CAPITAL LETTER POKOJI
2C13; C; 2C43; # GLAGOLITIC CAPITAL LETTER RITSI
2C14; C; 2C44; # GLAGOLITIC CAPITAL LETTER SLOVO
2C15; C; 2C45; # GLAGOLITIC CAPITAL LETTER TVRIDO
2C16; C; 2C46; # GLAGOLITIC CAPITAL LETTER UKU
2C17; C; 2C47; # GLAGOLITIC CAPITAL LETTER FRITU
2C18; C; 2C48; # GLAGOLITIC CAPITAL LETTER HERU
2C19; C; 2C49; # GLAGOLITIC CAPITAL LETTER OTU
2C1A; C; 2C4A; # GLAGOLITIC CAPITAL LETTER PE
2C1B; C; 2C4B; # GLAGOLITIC CAPITAL LETTER SHTA
2C1C; C; 2C4C; # GLAGOLITIC CAPITAL LETTER TSI
2C1D; C; 2C4D; # GLAGOLITIC CAPITAL LETTER CHRIVI
2C1E; C; 2C4E; # GLAGOLITIC CAPITAL LETTER SHA
2C1F; C; 2C4F; # GLAGOLITIC CAPITAL LETTER YERU
2C20; C; 2C50; # GLAGOLITIC CAPITAL LETTER YERI
2C21; C; 2C51; # GLAGOLITIC CAPITAL LETTER YATI
2C22; C; 2C52; # GLAGOLITIC CAPITAL LETTER SPIDERY HA
2C23; C; 2C53; # GLAGOLITIC CAPITAL LETTER YU
2C24; C; 2C54; # GLAGOLITIC CAPITAL LETTER SMALL YUS
2C25; C; 2C55; # GLAGOLITIC CAPITAL LETTER SMALL YUS WITH TAIL
2C26; C; 2C56; # GLAGOLITIC CAPITAL LETTER YO
2C27; C; 2C57; # GLAGOLITIC CAPITAL LETTER IOTATED SMALL YUS
2C28; C; 2C58; # GLAGOLITIC CAPITAL LETTER BIG YUS
2C29; C; 2C59; # GLAGOLITIC CAPITAL LETTER IOTATED BIG YUS
2C2A; C; 2C5A; # GLAGOLITIC CAPITAL LETTER FITA
2C2B; C; 2C5B; # GLAGOLITIC CAPITAL LETTER IZHITSA
2C2C; C; 2C5C; # GLAGOLITIC CAPITAL LETTER SHTAPIC
2C2D; C; 2C5D; # GLAGOLITIC CAPITAL LETTER TROKUTASTI A
2C2E; C; 2C5E; # GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C80; C; 2C81; # COPTIC CAPITAL LETTER ALFA
2C82; C; 2C83; # COPTIC CAPITAL LETTER VIDA
2C84; C; 2C85; # COPTIC CAPITAL LETTER GAMMA
2C86; C; 2C87; # COPTIC CAPITAL LETTER DALDA
2C88; C; 2C89; # COPTIC CAPITAL LETTER EIE
2C8A; C; 2C8B; # COPTIC CAPITAL LETTER SOU
2C8C; C; 2C8D; # COPTIC CAPITAL LETTER ZATA
2C8E; C; 2C8F; # COPTIC CAPITAL LETTER HATE
2C90; C; 2C91; # COPTIC CAPITAL LETTER THETHE
2C92; C; 2C93; # COPTIC CAPITAL LETTER IAUDA
2C94; C; 2C95; # COPTIC CAPITAL LETTER KAPA
2C96; C; 2C97; # COPTIC CAPITAL LETTER LAULA
2C98; C; 2C99; # COPTIC CAPITAL LETTER MI
2C9A; C; 2C9B; # COPTIC CAPITAL LETTER NI
2C9C; C; 2C9D; # COPTIC CAPITAL LETTER KSI
2C9E; C; 2C9F; # COPTIC CAPITAL LETTER O
2CA0; C; 2CA1; # COPTIC CAPITAL LETTER PI
2CA2; C; 2CA3; # COPTIC CAPITAL LETTER RO
2CA4; C; 2CA5; # COPTIC CAPITAL LETTER SIMA
2CA6; C; 2CA7; # COPTIC CAPITAL LETTER TAU
2CA8; C; 2CA9; # COPTIC CAPITAL LETTER UA
2CAA; C; 2CAB; # COPTIC CAPITAL LETTER FI
2CAC; C; 2CAD; # COPTIC CAPITAL LETTER KHI
2CAE; C; 2CAF; # COPTIC CAPITAL LETTER PSI
2CB0; C; 2CB1; # COPTIC CAPITAL LETTER OOU
2CB2; C; 2CB3; # COPTIC CAPITAL LETTER DIALECT-P ALEF
2CB4; C; 2CB5; # COPTIC CAPITAL LETTER OLD COPTIC AIN
2CB6; C; 2CB7; # COPTIC CAPITAL LETTER CRYPTOGRAMMIC EIE
2CB8; C; 2CB9; # COPTIC CAPITAL LETTER DIALECT-P KAPA
2CBA; C; 2CBB; # COPTIC CAPITAL LETTER DIALECT-P NI
2CBC; C; 2CBD; # COPTIC CAPITAL LETTER CRYPTOGRAMMIC NI
2CBE; C; 2CBF; # COPTIC CAPITAL LETTER OLD COPTIC OOU
2CC0; C; 2CC1; # COPTIC CAPITAL LETTER SAMPI
2CC2; C; 2CC3; # COPTIC CAPITAL LETTER CROSSED SHEI
2CC4; C; 2CC5; # COPTIC CAPITAL LETTER OLD COPTIC SHEI
2CC6; C; 2CC7; # COPTIC CAPITAL LETTER OLD COPTIC ESH
2CC8; C; 2CC9; # COPTIC CAPITAL LETTER AKHMIMIC KHEI
2CCA; C; 2CCB; # COPTIC CAPITAL LETTER DIALECT-P HORI
2CCC; C; 2CCD; # COPTIC CAPITAL LETTER OLD COPTIC HORI
2CCE; C; 2CCF; # COPTIC CAPITAL LETTER OLD COPTIC HA
2CD0; C; 2CD1; # COPTIC CAPITAL LETTER L-SHAPED HA
2CD2; C; 2CD3; # COPTIC CAPITAL LETTER OLD COPTIC HEI
2CD4; C; 2CD5; # COPTIC CAPITAL LETTER OLD COPTIC HAT
2CD6; C; 2CD7; # COPTIC CAPITAL LETTER OLD COPTIC GANGIA
2CD8; C; 2CD9; # COPTIC CAPITAL LETTER OLD COPTIC DJA
2CDA; C; 2CDB; # COPTIC CAPITAL LETTER OLD COPTIC SHIMA
2CDC; C; 2CDD; # COPTIC CAPITAL LETTER OLD NUBIAN SHIMA
2CDE; C; 2CDF; # COPTIC CAPITAL LETTER OLD NUBIAN NGI
2CE0; C; 2CE1; # COPTIC CAPITAL LETTER OLD NUBIAN NYI
2CE2; C; 2CE3; # COPTIC CAPITAL LETTER OLD NUBIAN WAU
FB00; F; 0066 0066; # LATIN SMALL LIGATURE FF
FB01; F; 0066 0069; # LATIN SMALL LIGATURE FI
FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL

100
icu4c/source/data/unidata/DerivedAge.txt
View File

@ -1,8 +1,8 @@
# DerivedAge-4.0.1.txt
# Date: 2004-03-02, 02:41:24 GMT [MD]
# DerivedAge-4.1.0.txt
# Date: 2004-12-11, 05:35:45 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
#
@ -726,3 +726,97 @@ FE47..FE48 ; 4.0 # [2] PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET..
E0100..E01EF ; 4.0 # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 1226
# ================================================
# Newly assigned in Unicode 4.1.0 (XXX, 2005)
0237..0241 ; 4.1 # [11] LATIN SMALL LETTER DOTLESS J..LATIN CAPITAL LETTER GLOTTAL STOP
0358..035C ; 4.1 # [5] COMBINING DOT ABOVE RIGHT..COMBINING DOUBLE BREVE BELOW
03FC..03FF ; 4.1 # [4] GREEK RHO WITH STROKE SYMBOL..GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
04F6..04F7 ; 4.1 # [2] CYRILLIC CAPITAL LETTER GHE WITH DESCENDER..CYRILLIC SMALL LETTER GHE WITH DESCENDER
05A2 ; 4.1 # HEBREW ACCENT ATNAH HAFUKH
05BA ; 4.1 # HEBREW POINT QAMATS QATAN
05C5..05C6 ; 4.1 # [2] HEBREW MARK LOWER DOT..HEBREW PUNCTUATION NUN HAFUKHA
060B ; 4.1 # AFGHANI SIGN
061E ; 4.1 # ARABIC TRIPLE DOT PUNCTUATION MARK
0659..065E ; 4.1 # [6] ARABIC ZWARAKAY..ARABIC FATHA WITH TWO DOTS
0750..076D ; 4.1 # [30] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE
097D ; 4.1 # DEVANAGARI LETTER GLOTTAL STOP
09CE ; 4.1 # BENGALI LETTER KHANDA TA
0BB6 ; 4.1 # TAMIL LETTER SHA
0BE6 ; 4.1 # TAMIL DIGIT ZERO
0FD0..0FD1 ; 4.1 # [2] TIBETAN MARK BSKA- SHOG GI MGO RGYAN..TIBETAN MARK MNYAM YIG GI MGO RGYAN
10F9..10FA ; 4.1 # [2] GEORGIAN LETTER TURNED GAN..GEORGIAN LETTER AIN
10FC ; 4.1 # MODIFIER LETTER GEORGIAN NAR
1207 ; 4.1 # ETHIOPIC SYLLABLE HOA
1247 ; 4.1 # ETHIOPIC SYLLABLE QOA
1287 ; 4.1 # ETHIOPIC SYLLABLE XOA
12AF ; 4.1 # ETHIOPIC SYLLABLE KOA
12CF ; 4.1 # ETHIOPIC SYLLABLE WOA
12EF ; 4.1 # ETHIOPIC SYLLABLE YOA
130F ; 4.1 # ETHIOPIC SYLLABLE GOA
131F ; 4.1 # ETHIOPIC SYLLABLE GGWAA
1347 ; 4.1 # ETHIOPIC SYLLABLE TZOA
135F..1360 ; 4.1 # [2] ETHIOPIC COMBINING GEMINATION MARK..ETHIOPIC SECTION MARK
1380..1399 ; 4.1 # [26] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC TONAL MARK KURT
1980..19A9 ; 4.1 # [42] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW XVA
19B0..19C9 ; 4.1 # [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
19D0..19D9 ; 4.1 # [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
19DE..19DF ; 4.1 # [2] NEW TAI LUE SIGN LE..NEW TAI LUE SIGN LEW
1A00..1A1B ; 4.1 # [28] BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE
1A1E..1A1F ; 4.1 # [2] BUGINESE PALLAWA..BUGINESE END OF SECTION
1D6C..1DC3 ; 4.1 # [88] LATIN SMALL LETTER B WITH MIDDLE TILDE..COMBINING SUSPENSION MARK
2055..2056 ; 4.1 # [2] FLOWER PUNCTUATION MARK..THREE DOT PUNCTUATION
2058..205E ; 4.1 # [7] FOUR DOT PUNCTUATION..VERTICAL FOUR DOTS
2090..2094 ; 4.1 # [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
20B2..20B5 ; 4.1 # [4] GUARANI SIGN..CEDI SIGN
20EB ; 4.1 # COMBINING LONG DOUBLE SOLIDUS OVERLAY
213C ; 4.1 # DOUBLE-STRUCK SMALL PI
214C ; 4.1 # PER SIGN
23D1..23DB ; 4.1 # [11] METRICAL BREVE..FUSE
2618 ; 4.1 # SHAMROCK
267E..267F ; 4.1 # [2] PERMANENT PAPER SIGN..WHEELCHAIR SYMBOL
2692..269C ; 4.1 # [11] HAMMER AND PICK..FLEUR-DE-LIS
26A2..26B1 ; 4.1 # [16] DOUBLED FEMALE SIGN..FUNERAL URN
27C0..27C6 ; 4.1 # [7] THREE DIMENSIONAL ANGLE..RIGHT S-SHAPED BAG DELIMITER
2B0E..2B13 ; 4.1 # [6] RIGHTWARDS ARROW WITH TIP DOWNWARDS..SQUARE WITH BOTTOM HALF BLACK
2C00..2C2E ; 4.1 # [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E ; 4.1 # [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
2C80..2CEA ; 4.1 # [107] COPTIC CAPITAL LETTER ALFA..COPTIC SYMBOL SHIMA SIMA
2CF9..2D25 ; 4.1 # [45] COPTIC OLD NUBIAN FULL STOP..GEORGIAN SMALL LETTER HOE
2D30..2D65 ; 4.1 # [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ
2D6F ; 4.1 # TIFINAGH MODIFIER LETTER LABIALIZATION
2D80..2D96 ; 4.1 # [23] ETHIOPIC SYLLABLE LOA..ETHIOPIC SYLLABLE GGWE
2DA0..2DA6 ; 4.1 # [7] ETHIOPIC SYLLABLE SSA..ETHIOPIC SYLLABLE SSO
2DA8..2DAE ; 4.1 # [7] ETHIOPIC SYLLABLE CCA..ETHIOPIC SYLLABLE CCO
2DB0..2DB6 ; 4.1 # [7] ETHIOPIC SYLLABLE ZZA..ETHIOPIC SYLLABLE ZZO
2DB8..2DBE ; 4.1 # [7] ETHIOPIC SYLLABLE CCHA..ETHIOPIC SYLLABLE CCHO
2DC0..2DC6 ; 4.1 # [7] ETHIOPIC SYLLABLE QYA..ETHIOPIC SYLLABLE QYO
2DC8..2DCE ; 4.1 # [7] ETHIOPIC SYLLABLE KYA..ETHIOPIC SYLLABLE KYO
2DD0..2DD6 ; 4.1 # [7] ETHIOPIC SYLLABLE XYA..ETHIOPIC SYLLABLE XYO
2DD8..2DDE ; 4.1 # [7] ETHIOPIC SYLLABLE GYA..ETHIOPIC SYLLABLE GYO
2E00..2E17 ; 4.1 # [24] RIGHT ANGLE SUBSTITUTION MARKER..DOUBLE OBLIQUE HYPHEN
2E1C..2E1D ; 4.1 # [2] LEFT LOW PARAPHRASE BRACKET..RIGHT LOW PARAPHRASE BRACKET
31C0..31CF ; 4.1 # [16] CJK BASIC STROKE T..CJK BASIC STROKE N
327E ; 4.1 # CIRCLED HANGUL IEUNG U
9FA6..9FBB ; 4.1 # [22] CJK UNIFIED IDEOGRAPH-9FA6..CJK UNIFIED IDEOGRAPH-9FBB
A700..A716 ; 4.1 # [23] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR
A800..A82B ; 4.1 # [44] SYLOTI NAGRI LETTER A..SYLOTI NAGRI POETRY MARK-4
FA70..FAD9 ; 4.1 # [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
FE10..FE19 ; 4.1 # [10] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
10140..1018A ; 4.1 # [75] GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ZERO SIGN
103A0..103C3 ; 4.1 # [36] OLD PERSIAN SIGN A..OLD PERSIAN SIGN HA
103C8..103D5 ; 4.1 # [14] OLD PERSIAN SIGN AURAMAZDAA..OLD PERSIAN NUMBER HUNDRED
10A00..10A03 ; 4.1 # [4] KHAROSHTHI LETTER A..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; 4.1 # [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A13 ; 4.1 # [8] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI LETTER GHA
10A15..10A17 ; 4.1 # [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
10A19..10A33 ; 4.1 # [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA
10A38..10A3A ; 4.1 # [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
10A3F..10A47 ; 4.1 # [9] KHAROSHTHI VIRAMA..KHAROSHTHI NUMBER ONE THOUSAND
10A50..10A58 ; 4.1 # [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES
1D200..1D245 ; 4.1 # [70] GREEK VOCAL NOTATION SYMBOL-1..GREEK MUSICAL LEIMMA
1D6A4..1D6A5 ; 4.1 # [2] MATHEMATICAL ITALIC SMALL DOTLESS I..MATHEMATICAL ITALIC SMALL DOTLESS J
# Total code points: 1273

252
icu4c/source/data/unidata/DerivedBidiClass.txt
View File

@ -1,8 +1,8 @@
# DerivedBidiClass-4.0.1.txt
# Date: 2004-03-11, 18:33:24 GMT [MD]
# DerivedBidiClass-4.1.0.txt
# Date: 2004-12-11, 05:36:16 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
@ -28,7 +28,7 @@
01BB ; L # Lo LATIN LETTER TWO WITH STROKE
01BC..01BF ; L # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN
01C0..01C3 ; L # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK
01C4..0236 ; L # L& [115] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER T WITH CURL
01C4..0241 ; L # L& [126] LATIN CAPITAL LETTER DZ WITH CARON..LATIN CAPITAL LETTER GLOTTAL STOP
0250..02AF ; L # L& [96] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
02B0..02B8 ; L # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
02BB..02C1 ; L # Lm [7] MODIFIER LETTER TURNED COMMA..MODIFIER LETTER REVERSED GLOTTAL STOP
@ -43,11 +43,10 @@
03A3..03CE ; L # L& [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS
03D0..03F5 ; L # L& [38] GREEK BETA SYMBOL..GREEK LUNATE EPSILON SYMBOL
03F7..03FB ; L # L& [5] GREEK CAPITAL LETTER SHO..GREEK SMALL LETTER SAN
0400..0481 ; L # L& [130] CYRILLIC CAPITAL LETTER IE WITH GRAVE..CYRILLIC SMALL LETTER KOPPA
03FD..0481 ; L # L& [133] GREEK CAPITAL REVERSED LUNATE SIGMA SYMBOL..CYRILLIC SMALL LETTER KOPPA
0482 ; L # So CYRILLIC THOUSANDS SIGN
048A..04CE ; L # L& [69] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EM WITH TAIL
04D0..04F5 ; L # L& [38] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER CHE WITH DIAERESIS
04F8..04F9 ; L # L& [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS
04D0..04F9 ; L # L& [42] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER YERU WITH DIAERESIS
0500..050F ; L # L& [16] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER KOMI TJE
0531..0556 ; L # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH
0559 ; L # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
@ -64,6 +63,7 @@
0964..0965 ; L # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
0966..096F ; L # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
0970 ; L # Po DEVANAGARI ABBREVIATION SIGN
097D ; L # Lo DEVANAGARI LETTER GLOTTAL STOP
0982..0983 ; L # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
0985..098C ; L # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L
098F..0990 ; L # Lo [2] BENGALI LETTER E..BENGALI LETTER AI
@ -75,6 +75,7 @@
09BE..09C0 ; L # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II
09C7..09C8 ; L # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
09CB..09CC ; L # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU
09CE ; L # Lo BENGALI LETTER KHANDA TA
09D7 ; L # Mc BENGALI AU LENGTH MARK
09DC..09DD ; L # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E1 ; L # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
@ -136,14 +137,13 @@
0B9E..0B9F ; L # Lo [2] TAMIL LETTER NYA..TAMIL LETTER TTA
0BA3..0BA4 ; L # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA
0BA8..0BAA ; L # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA
0BAE..0BB5 ; L # Lo [8] TAMIL LETTER MA..TAMIL LETTER VA
0BB7..0BB9 ; L # Lo [3] TAMIL LETTER SSA..TAMIL LETTER HA
0BAE..0BB9 ; L # Lo [12] TAMIL LETTER MA..TAMIL LETTER HA
0BBE..0BBF ; L # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I
0BC1..0BC2 ; L # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU
0BC6..0BC8 ; L # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI
0BCA..0BCC ; L # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU
0BD7 ; L # Mc TAMIL AU LENGTH MARK
0BE7..0BEF ; L # Nd [9] TAMIL DIGIT ONE..TAMIL DIGIT NINE
0BE6..0BEF ; L # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE
0BF0..0BF2 ; L # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND
0C01..0C03 ; L # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
0C05..0C0C ; L # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L
@ -236,6 +236,7 @@
0FBE..0FC5 ; L # So [8] TIBETAN KU RU KHA..TIBETAN SYMBOL RDO RJE
0FC7..0FCC ; L # So [6] TIBETAN SYMBOL RDO RJE RGYA GRAM..TIBETAN SYMBOL NOR BU BZHI -KHYIL
0FCF ; L # So TIBETAN SIGN RDEL NAG GSUM
0FD0..0FD1 ; L # Po [2] TIBETAN MARK BSKA- SHOG GI MGO RGYAN..TIBETAN MARK MNYAM YIG GI MGO RGYAN
1000..1021 ; L # Lo [34] MYANMAR LETTER KA..MYANMAR LETTER A
1023..1027 ; L # Lo [5] MYANMAR LETTER I..MYANMAR LETTER E
1029..102A ; L # Lo [2] MYANMAR LETTER O..MYANMAR LETTER AU
@ -247,39 +248,31 @@
1050..1055 ; L # Lo [6] MYANMAR LETTER SHA..MYANMAR LETTER VOCALIC LL
1056..1057 ; L # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
10A0..10C5 ; L # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10D0..10F8 ; L # Lo [41] GEORGIAN LETTER AN..GEORGIAN LETTER ELIFI
10D0..10FA ; L # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
10FB ; L # Po GEORGIAN PARAGRAPH SEPARATOR
10FC ; L # Lm MODIFIER LETTER GEORGIAN NAR
1100..1159 ; L # Lo [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH
115F..11A2 ; L # Lo [68] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA
11A8..11F9 ; L # Lo [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH
1200..1206 ; L # Lo [7] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE HO
1208..1246 ; L # Lo [63] ETHIOPIC SYLLABLE LA..ETHIOPIC SYLLABLE QO
1248 ; L # Lo ETHIOPIC SYLLABLE QWA
1200..1248 ; L # Lo [73] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE QWA
124A..124D ; L # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE
1250..1256 ; L # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO
1258 ; L # Lo ETHIOPIC SYLLABLE QHWA
125A..125D ; L # Lo [4] ETHIOPIC SYLLABLE QHWI..ETHIOPIC SYLLABLE QHWE
1260..1286 ; L # Lo [39] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XO
1288 ; L # Lo ETHIOPIC SYLLABLE XWA
1260..1288 ; L # Lo [41] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XWA
128A..128D ; L # Lo [4] ETHIOPIC SYLLABLE XWI..ETHIOPIC SYLLABLE XWE
1290..12AE ; L # Lo [31] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KO
12B0 ; L # Lo ETHIOPIC SYLLABLE KWA
1290..12B0 ; L # Lo [33] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KWA
12B2..12B5 ; L # Lo [4] ETHIOPIC SYLLABLE KWI..ETHIOPIC SYLLABLE KWE
12B8..12BE ; L # Lo [7] ETHIOPIC SYLLABLE KXA..ETHIOPIC SYLLABLE KXO
12C0 ; L # Lo ETHIOPIC SYLLABLE KXWA
12C2..12C5 ; L # Lo [4] ETHIOPIC SYLLABLE KXWI..ETHIOPIC SYLLABLE KXWE
12C8..12CE ; L # Lo [7] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE WO
12D0..12D6 ; L # Lo [7] ETHIOPIC SYLLABLE PHARYNGEAL A..ETHIOPIC SYLLABLE PHARYNGEAL O
12D8..12EE ; L # Lo [23] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE YO
12F0..130E ; L # Lo [31] ETHIOPIC SYLLABLE DA..ETHIOPIC SYLLABLE GO
1310 ; L # Lo ETHIOPIC SYLLABLE GWA
12C8..12D6 ; L # Lo [15] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE PHARYNGEAL O
12D8..1310 ; L # Lo [57] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE GWA
1312..1315 ; L # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
1318..131E ; L # Lo [7] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE GGO
1320..1346 ; L # Lo [39] ETHIOPIC SYLLABLE THA..ETHIOPIC SYLLABLE TZO
1348..135A ; L # Lo [19] ETHIOPIC SYLLABLE FA..ETHIOPIC SYLLABLE FYA
1361..1368 ; L # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
1369..1371 ; L # Nd [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE
1372..137C ; L # No [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND
1318..135A ; L # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
1360..1368 ; L # Po [9] ETHIOPIC SECTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
1369..137C ; L # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
1380..138F ; L # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
13A0..13F4 ; L # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
1401..166C ; L # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
166D..166E ; L # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
@ -317,9 +310,20 @@
1946..194F ; L # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE
1950..196D ; L # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI
1970..1974 ; L # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
1980..19A9 ; L # Lo [42] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW XVA
19B0..19C0 ; L # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
19C1..19C7 ; L # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
19C8..19C9 ; L # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
19D0..19D9 ; L # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
1A00..1A16 ; L # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA
1A19..1A1B ; L # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
1A1E..1A1F ; L # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION
1D00..1D2B ; L # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D61 ; L # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
1D62..1D6B ; L # L& [10] LATIN SUBSCRIPT SMALL LETTER I..LATIN SMALL LETTER UE
1D62..1D77 ; L # L& [22] LATIN SUBSCRIPT SMALL LETTER I..LATIN SMALL LETTER TURNED G
1D78 ; L # Lm MODIFIER LETTER CYRILLIC EN
1D79..1D9A ; L # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF ; L # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
1E00..1E9B ; L # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE
1EA0..1EF9 ; L # L& [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE
1F00..1F15 ; L # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
@ -344,6 +348,7 @@
200E ; L # Cf LEFT-TO-RIGHT MARK
2071 ; L # L& SUPERSCRIPT LATIN SMALL LETTER I
207F ; L # L& SUPERSCRIPT LATIN SMALL LETTER N
2090..2094 ; L # Lm [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
2102 ; L # L& DOUBLE-STRUCK CAPITAL C
2107 ; L # L& EULER CONSTANT
210A..2113 ; L # L& [10] SCRIPT SMALL G..SCRIPT SMALL L
@ -357,13 +362,29 @@
2133..2134 ; L # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O
2135..2138 ; L # Lo [4] ALEF SYMBOL..DALET SYMBOL
2139 ; L # L& INFORMATION SOURCE
213D..213F ; L # L& [3] DOUBLE-STRUCK SMALL GAMMA..DOUBLE-STRUCK CAPITAL PI
213C..213F ; L # L& [4] DOUBLE-STRUCK SMALL PI..DOUBLE-STRUCK CAPITAL PI
2145..2149 ; L # L& [5] DOUBLE-STRUCK ITALIC CAPITAL D..DOUBLE-STRUCK ITALIC SMALL J
2160..2183 ; L # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED
2336..237A ; L # So [69] APL FUNCTIONAL SYMBOL I-BEAM..APL FUNCTIONAL SYMBOL ALPHA
2395 ; L # So APL FUNCTIONAL SYMBOL QUAD
249C..24E9 ; L # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
26AC ; L # So MEDIUM SMALL WHITE CIRCLE
2800..28FF ; L # So [256] BRAILLE PATTERN BLANK..BRAILLE PATTERN DOTS-12345678
2C00..2C2E ; L # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E ; L # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
2C80..2CE4 ; L # L& [101] COPTIC CAPITAL LETTER ALFA..COPTIC SYMBOL KAI
2D00..2D25 ; L # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE
2D30..2D65 ; L # Lo [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ
2D6F ; L # Lm TIFINAGH MODIFIER LETTER LABIALIZATION
2D80..2D96 ; L # Lo [23] ETHIOPIC SYLLABLE LOA..ETHIOPIC SYLLABLE GGWE
2DA0..2DA6 ; L # Lo [7] ETHIOPIC SYLLABLE SSA..ETHIOPIC SYLLABLE SSO
2DA8..2DAE ; L # Lo [7] ETHIOPIC SYLLABLE CCA..ETHIOPIC SYLLABLE CCO
2DB0..2DB6 ; L # Lo [7] ETHIOPIC SYLLABLE ZZA..ETHIOPIC SYLLABLE ZZO
2DB8..2DBE ; L # Lo [7] ETHIOPIC SYLLABLE CCHA..ETHIOPIC SYLLABLE CCHO
2DC0..2DC6 ; L # Lo [7] ETHIOPIC SYLLABLE QYA..ETHIOPIC SYLLABLE QYO
2DC8..2DCE ; L # Lo [7] ETHIOPIC SYLLABLE KYA..ETHIOPIC SYLLABLE KYO
2DD0..2DD6 ; L # Lo [7] ETHIOPIC SYLLABLE XYA..ETHIOPIC SYLLABLE XYO
2DD8..2DDE ; L # Lo [7] ETHIOPIC SYLLABLE GYA..ETHIOPIC SYLLABLE GYO
3005 ; L # Lm IDEOGRAPHIC ITERATION MARK
3006 ; L # Lo IDEOGRAPHIC CLOSING MARK
3007 ; L # Nl IDEOGRAPHIC NUMBER ZERO
@ -398,12 +419,21 @@
337B..33DD ; L # So [99] SQUARE ERA NAME HEISEI..SQUARE WB
33E0..33FE ; L # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE
3400..4DB5 ; L # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FA5 ; L # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
A000..A48C ; L # Lo [1165] YI SYLLABLE IT..YI SYLLABLE YYR
4E00..9FBB ; L # Lo [20924] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FBB
A000..A014 ; L # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; L # Lm YI SYLLABLE WU
A016..A48C ; L # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
A800..A801 ; L # Lo [2] SYLOTI NAGRI LETTER A..SYLOTI NAGRI LETTER I
A803..A805 ; L # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O
A807..A80A ; L # Lo [4] SYLOTI NAGRI LETTER KO..SYLOTI NAGRI LETTER GHO
A80C..A822 ; L # Lo [23] SYLOTI NAGRI LETTER CO..SYLOTI NAGRI LETTER HO
A823..A824 ; L # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
A827 ; L # Mc SYLOTI NAGRI VOWEL SIGN OO
AC00..D7A3 ; L # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
E000..F8FF ; L # Co [6400] <private-use-E000>..<private-use-F8FF>
F900..FA2D ; L # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA30..FA6A ; L # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A
FA70..FAD9 ; L # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
FB00..FB06 ; L # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
FB13..FB17 ; L # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
FF21..FF3A ; L # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
@ -434,6 +464,9 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
1034A ; L # Nl GOTHIC LETTER NINE HUNDRED
10380..1039D ; L # Lo [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU
1039F ; L # Po UGARITIC WORD DIVIDER
103A0..103C3 ; L # Lo [36] OLD PERSIAN SIGN A..OLD PERSIAN SIGN HA
103C8..103CF ; L # Lo [8] OLD PERSIAN SIGN AURAMAZDAA..OLD PERSIAN SIGN BUUMISH
103D0 ; L # So OLD PERSIAN WORD DIVIDER
10400..1044F ; L # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW
10450..1049D ; L # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO
104A0..104A9 ; L # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
@ -464,7 +497,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
1D540..1D544 ; L # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M
1D546 ; L # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O
1D54A..1D550 ; L # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y
1D552..1D6A3 ; L # L& [338] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL MONOSPACE SMALL Z
1D552..1D6A5 ; L # L& [340] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL ITALIC SMALL DOTLESS J
1D6A8..1D6C0 ; L # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA
1D6C1 ; L # Sm MATHEMATICAL BOLD NABLA
1D6C2..1D6DA ; L # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA
@ -491,20 +524,19 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD>
100000..10FFFD; L # Co [65534] <private-use-100000>..<private-use-10FFFD>
# The above property value applies to 873851 code points not listed here.
# Total code points: 1102638
# The above property value applies to 872685 code points not listed here.
# Total code points: 1102297
# ================================================
# Bidi_Class=Right_To_Left
0590 ; R # Cn <reserved-0590>
05A2 ; R # Cn <reserved-05A2>
05BA ; R # Cn <reserved-05BA>
05BE ; R # Po HEBREW PUNCTUATION MAQAF
05C0 ; R # Po HEBREW PUNCTUATION PASEQ
05C3 ; R # Po HEBREW PUNCTUATION SOF PASUQ
05C5..05CF ; R # Cn [11] <reserved-05C5>..<reserved-05CF>
05C6 ; R # Po HEBREW PUNCTUATION NUN HAFUKHA
05C7..05CF ; R # Cn [9] <reserved-05C7>..<reserved-05CF>
05D0..05EA ; R # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
05EB..05EF ; R # Cn [5] <reserved-05EB>..<reserved-05EF>
05F0..05F2 ; R # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD
@ -536,9 +568,24 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL
1083C ; R # Lo CYPRIOT SYLLABLE ZA
1083D..1083E ; R # Cn [2] <reserved-1083D>..<reserved-1083E>
1083F ; R # Lo CYPRIOT SYLLABLE ZO
10840..10FFF ; R # Cn [1984] <reserved-10840>..<reserved-10FFF>
10840..109FF ; R # Cn [448] <reserved-10840>..<reserved-109FF>
10A00 ; R # Lo KHAROSHTHI LETTER A
10A04 ; R # Cn <reserved-10A04>
10A07..10A0B ; R # Cn [5] <reserved-10A07>..<reserved-10A0B>
10A10..10A13 ; R # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA
10A14 ; R # Cn <reserved-10A14>
10A15..10A17 ; R # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
10A18 ; R # Cn <reserved-10A18>
10A19..10A33 ; R # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA
10A34..10A37 ; R # Cn [4] <reserved-10A34>..<reserved-10A37>
10A3B..10A3E ; R # Cn [4] <reserved-10A3B>..<reserved-10A3E>
10A40..10A43 ; R # Nd [4] KHAROSHTHI DIGIT ONE..KHAROSHTHI DIGIT FOUR
10A44..10A47 ; R # No [4] KHAROSHTHI NUMBER TEN..KHAROSHTHI NUMBER ONE THOUSAND
10A48..10A4F ; R # Cn [8] <reserved-10A48>..<reserved-10A4F>
10A50..10A58 ; R # Po [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES
10A59..10FFF ; R # Cn [1447] <reserved-10A59>..<reserved-10FFF>
# Total code points: 2483
# Total code points: 2467
# ================================================
@ -563,9 +610,8 @@ FF10..FF19 ; EN # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
002B ; ES # Sm PLUS SIGN
002D ; ES # Pd HYPHEN-MINUS
FF0F ; ES # Po FULLWIDTH SOLIDUS
# Total code points: 3
# Total code points: 2
# ================================================
@ -586,7 +632,7 @@ FF0F ; ES # Po FULLWIDTH SOLIDUS
2030..2034 ; ET # Po [5] PER MILLE SIGN..TRIPLE PRIME
207A..207B ; ET # Sm [2] SUPERSCRIPT PLUS SIGN..SUPERSCRIPT MINUS
208A..208B ; ET # Sm [2] SUBSCRIPT PLUS SIGN..SUBSCRIPT MINUS
20A0..20B1 ; ET # Sc [18] EURO-CURRENCY SIGN..PESO SIGN
20A0..20B5 ; ET # Sc [22] EURO-CURRENCY SIGN..CEDI SIGN
212E ; ET # So ESTIMATED SYMBOL
2212..2213 ; ET # Sm [2] MINUS SIGN..MINUS-OR-PLUS SIGN
FB29 ; ET # Sm HEBREW LETTER ALTERNATIVE PLUS SIGN
@ -603,7 +649,7 @@ FF0D ; ET # Pd FULLWIDTH HYPHEN-MINUS
FFE0..FFE1 ; ET # Sc [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN
FFE5..FFE6 ; ET # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN
# Total code points: 61
# Total code points: 65
# ================================================
@ -623,15 +669,16 @@ FFE5..FFE6 ; ET # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN
003A ; CS # Po COLON
00A0 ; CS # Zs NO-BREAK SPACE
060C ; CS # Po ARABIC COMMA
202F ; CS # Zs NARROW NO-BREAK SPACE
2044 ; CS # Sm FRACTION SLASH
FE50 ; CS # Po SMALL COMMA
FE52 ; CS # Po SMALL FULL STOP
FE55 ; CS # Po SMALL COLON
FF0C ; CS # Po FULLWIDTH COMMA
FF0E ; CS # Po FULLWIDTH FULL STOP
FF0E..FF0F ; CS # Po [2] FULLWIDTH FULL STOP..FULLWIDTH SOLIDUS
FF1A ; CS # Po FULLWIDTH COLON
# Total code points: 13
# Total code points: 15
# ================================================
@ -665,11 +712,10 @@ FF1A ; CS # Po FULLWIDTH COLON
180E ; WS # Zs MONGOLIAN VOWEL SEPARATOR
2000..200A ; WS # Zs [11] EN QUAD..HAIR SPACE
2028 ; WS # Zl LINE SEPARATOR
202F ; WS # Zs NARROW NO-BREAK SPACE
205F ; WS # Zs MEDIUM MATHEMATICAL SPACE
3000 ; WS # Zs IDEOGRAPHIC SPACE
# Total code points: 19
# Total code points: 18
# ================================================
@ -721,6 +767,7 @@ FF1A ; CS # Po FULLWIDTH COLON
0384..0385 ; ON # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS
0387 ; ON # Po GREEK ANO TELEIA
03F6 ; ON # Sm GREEK REVERSED LUNATE EPSILON SYMBOL
03FC ; ON # L& GREEK RHO WITH STROKE SYMBOL
058A ; ON # Pd ARMENIAN HYPHEN
060E..060F ; ON # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA
06E9 ; ON # So ARABIC PLACE OF SAJDAH
@ -730,6 +777,7 @@ FF1A ; CS # Po FULLWIDTH COLON
0F3B ; ON # Pe TIBETAN MARK GUG RTAGS GYAS
0F3C ; ON # Ps TIBETAN MARK ANG KHANG GYON
0F3D ; ON # Pe TIBETAN MARK ANG KHANG GYAS
1390..1399 ; ON # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
169B ; ON # Ps OGHAM FEATHER MARK
169C ; ON # Pe OGHAM REVERSED FEATHER MARK
17F0..17F9 ; ON # No [10] KHMER SYMBOL LEK ATTAK SON..KHMER SYMBOL LEK ATTAK PRAM-BUON
@ -738,7 +786,7 @@ FF1A ; CS # Po FULLWIDTH COLON
1807..180A ; ON # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU
1940 ; ON # So LIMBU SIGN LOO
1944..1945 ; ON # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
19E0..19FF ; ON # So [32] KHMER SYMBOL PATHAMASAT..KHMER SYMBOL DAP-PRAM ROC
19DE..19FF ; ON # So [34] NEW TAI LUE SIGN LE..KHMER SYMBOL DAP-PRAM ROC
1FBD ; ON # Sk GREEK KORONIS
1FBF..1FC1 ; ON # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI
1FCD..1FCF ; ON # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI
@ -767,7 +815,7 @@ FF1A ; CS # Po FULLWIDTH COLON
2052 ; ON # Sm COMMERCIAL MINUS SIGN
2053 ; ON # Po SWUNG DASH
2054 ; ON # Pc INVERTED UNDERTIE
2057 ; ON # Po QUADRUPLE PRIME
2055..205E ; ON # Po [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS
207C ; ON # Sm SUPERSCRIPT EQUALS SIGN
207D ; ON # Ps SUPERSCRIPT LEFT PARENTHESIS
207E ; ON # Pe SUPERSCRIPT RIGHT PARENTHESIS
@ -788,6 +836,7 @@ FF1A ; CS # Po FULLWIDTH COLON
2140..2144 ; ON # Sm [5] DOUBLE-STRUCK N-ARY SUMMATION..TURNED SANS-SERIF CAPITAL Y
214A ; ON # So PROPERTY LINE
214B ; ON # Sm TURNED AMPERSAND
214C ; ON # So PER SIGN
2153..215F ; ON # No [13] VULGAR FRACTION ONE THIRD..FRACTION NUMERATOR ONE
2190..2194 ; ON # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
2195..2199 ; ON # So [5] UP DOWN ARROW..SOUTH WEST ARROW
@ -825,7 +874,7 @@ FF1A ; CS # Po FULLWIDTH COLON
23B4 ; ON # Ps TOP SQUARE BRACKET
23B5 ; ON # Pe BOTTOM SQUARE BRACKET
23B6 ; ON # Po BOTTOM SQUARE BRACKET OVER TOP SQUARE BRACKET
23B7..23D0 ; ON # So [26] RADICAL SYMBOL BOTTOM..VERTICAL LINE EXTENSION
23B7..23DB ; ON # So [37] RADICAL SYMBOL BOTTOM..FUSE
2400..2426 ; ON # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
2440..244A ; ON # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..2487 ; ON # No [40] CIRCLED DIGIT ONE..PARENTHESIZED NUMBER TWENTY
@ -836,12 +885,11 @@ FF1A ; CS # Po FULLWIDTH COLON
25C1 ; ON # Sm WHITE LEFT-POINTING TRIANGLE
25C2..25F7 ; ON # So [54] BLACK LEFT-POINTING SMALL TRIANGLE..WHITE CIRCLE WITH UPPER RIGHT QUADRANT
25F8..25FF ; ON # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE
2600..2617 ; ON # So [24] BLACK SUN WITH RAYS..BLACK SHOGI PIECE
2619..266E ; ON # So [86] REVERSED ROTATED FLORAL HEART BULLET..MUSIC NATURAL SIGN
2600..266E ; ON # So [111] BLACK SUN WITH RAYS..MUSIC NATURAL SIGN
266F ; ON # Sm MUSIC SHARP SIGN
2670..267D ; ON # So [14] WEST SYRIAC CROSS..PARTIALLY-RECYCLED PAPER SYMBOL
2680..2691 ; ON # So [18] DIE FACE-1..BLACK FLAG
26A0..26A1 ; ON # So [2] WARNING SIGN..HIGH VOLTAGE SIGN
2670..269C ; ON # So [45] WEST SYRIAC CROSS..FLEUR-DE-LIS
26A0..26AB ; ON # So [12] WARNING SIGN..MEDIUM BLACK CIRCLE
26AD..26B1 ; ON # So [5] MARRIAGE SYMBOL..FUNERAL URN
2701..2704 ; ON # So [4] UPPER BLADE SCISSORS..WHITE SCISSORS
2706..2709 ; ON # So [4] TELEPHONE LOCATION SIGN..ENVELOPE
270C..2727 ; ON # So [28] VICTORY HAND..WHITE FOUR POINTED STAR
@ -869,6 +917,9 @@ FF1A ; CS # Po FULLWIDTH COLON
2794 ; ON # So HEAVY WIDE-HEADED RIGHTWARDS ARROW
2798..27AF ; ON # So [24] HEAVY SOUTH EAST ARROW..NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
27B1..27BE ; ON # So [14] NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW..OPEN-OUTLINED RIGHTWARDS ARROW
27C0..27C4 ; ON # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; ON # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; ON # Pe RIGHT S-SHAPED BAG DELIMITER
27D0..27E5 ; ON # Sm [22] WHITE DIAMOND WITH CENTRED DOT..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; ON # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; ON # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
@ -909,7 +960,26 @@ FF1A ; CS # Po FULLWIDTH COLON
29FC ; ON # Ps LEFT-POINTING CURVED ANGLE BRACKET
29FD ; ON # Pe RIGHT-POINTING CURVED ANGLE BRACKET
29FE..2AFF ; ON # Sm [258] TINY..N-ARY WHITE VERTICAL BAR
2B00..2B0D ; ON # So [14] NORTH EAST WHITE ARROW..UP DOWN BLACK ARROW
2B00..2B13 ; ON # So [20] NORTH EAST WHITE ARROW..SQUARE WITH BOTTOM HALF BLACK
2CE5..2CEA ; ON # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
2CF9..2CFC ; ON # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER
2CFD ; ON # No COPTIC FRACTION ONE HALF
2CFE..2CFF ; ON # Po [2] COPTIC FULL STOP..COPTIC MORPHOLOGICAL DIVIDER
2E00..2E01 ; ON # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; ON # Ps LEFT SUBSTITUTION BRACKET
2E03 ; ON # Pe RIGHT SUBSTITUTION BRACKET
2E04 ; ON # Ps LEFT DOTTED SUBSTITUTION BRACKET
2E05 ; ON # Pe RIGHT DOTTED SUBSTITUTION BRACKET
2E06..2E08 ; ON # Po [3] RAISED INTERPOLATION MARKER..DOTTED TRANSPOSITION MARKER
2E09 ; ON # Ps LEFT TRANSPOSITION BRACKET
2E0A ; ON # Pe RIGHT TRANSPOSITION BRACKET
2E0B ; ON # Po RAISED SQUARE
2E0C ; ON # Pi LEFT RAISED OMISSION BRACKET
2E0D ; ON # Pf RIGHT RAISED OMISSION BRACKET
2E0E..2E16 ; ON # Po [9] EDITORIAL CORONIS..DOTTED RIGHT-POINTING ANGLE
2E17 ; ON # Pd DOUBLE OBLIQUE HYPHEN
2E1C ; ON # Ps LEFT LOW PARAPHRASE BRACKET
2E1D ; ON # Pe RIGHT LOW PARAPHRASE BRACKET
2E80..2E99 ; ON # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3 ; ON # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5 ; ON # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
@ -945,11 +1015,12 @@ FF1A ; CS # Po FULLWIDTH COLON
303E..303F ; ON # So [2] IDEOGRAPHIC VARIATION INDICATOR..IDEOGRAPHIC HALF FILL SPACE
309B..309C ; ON # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
30A0 ; ON # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
30FB ; ON # Pc KATAKANA MIDDLE DOT
30FB ; ON # Po KATAKANA MIDDLE DOT
31C0..31CF ; ON # So [16] CJK BASIC STROKE T..CJK BASIC STROKE N
321D..321E ; ON # So [2] PARENTHESIZED KOREAN CHARACTER OJEON..PARENTHESIZED KOREAN CHARACTER O HU
3250 ; ON # So PARTNERSHIP SIGN
3251..325F ; ON # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE
327C..327D ; ON # So [2] CIRCLED KOREAN CHARACTER CHAMKO..CIRCLED KOREAN CHARACTER JUEUI
327C..327E ; ON # So [3] CIRCLED KOREAN CHARACTER CHAMKO..CIRCLED HANGUL IEUNG U
32B1..32BF ; ON # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY
32CC..32CF ; ON # So [4] SQUARE HG..LIMITED LIABILITY SIGN
3377..337A ; ON # So [4] SQUARE DM..SQUARE IU
@ -957,9 +1028,15 @@ FF1A ; CS # Po FULLWIDTH COLON
33FF ; ON # So SQUARE GAL
4DC0..4DFF ; ON # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
A490..A4C6 ; ON # So [55] YI RADICAL QOT..YI RADICAL KE
A700..A716 ; ON # Sk [23] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR
A828..A82B ; ON # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK-4
FD3E ; ON # Ps ORNATE LEFT PARENTHESIS
FD3F ; ON # Pe ORNATE RIGHT PARENTHESIS
FDFD ; ON # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
FE10..FE16 ; ON # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK
FE17 ; ON # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET
FE18 ; ON # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET
FE19 ; ON # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
FE30 ; ON # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
FE31..FE32 ; ON # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
FE33..FE34 ; ON # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE
@ -1021,8 +1098,7 @@ FF60 ; ON # Pe FULLWIDTH RIGHT WHITE PARENTHESIS
FF61 ; ON # Po HALFWIDTH IDEOGRAPHIC FULL STOP
FF62 ; ON # Ps HALFWIDTH LEFT CORNER BRACKET
FF63 ; ON # Pe HALFWIDTH RIGHT CORNER BRACKET
FF64 ; ON # Po HALFWIDTH IDEOGRAPHIC COMMA
FF65 ; ON # Pc HALFWIDTH KATAKANA MIDDLE DOT
FF64..FF65 ; ON # Po [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDLE DOT
FFE2 ; ON # Sm FULLWIDTH NOT SIGN
FFE3 ; ON # Sk FULLWIDTH MACRON
FFE4 ; ON # So FULLWIDTH BROKEN BAR
@ -1032,9 +1108,16 @@ FFED..FFEE ; ON # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE
FFF9..FFFB ; ON # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
10101 ; ON # Po AEGEAN WORD SEPARATOR DOT
10140..10174 ; ON # Nl [53] GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ACROPHONIC STRATIAN FIFTY MNAS
10175..10178 ; ON # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN
10179..10189 ; ON # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN
1018A ; ON # No GREEK ZERO SIGN
103D1..103D5 ; ON # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED
1D200..1D241 ; ON # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D245 ; ON # So GREEK MUSICAL LEIMMA
1D300..1D356 ; ON # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
# Total code points: 2793
# Total code points: 3109
# ================================================
@ -1083,18 +1166,15 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
# Bidi_Class=Nonspacing_Mark
0300..0357 ; NSM # Mn [88] COMBINING GRAVE ACCENT..COMBINING RIGHT HALF RING ABOVE
035D..036F ; NSM # Mn [19] COMBINING DOUBLE BREVE..COMBINING LATIN SMALL LETTER X
0300..036F ; NSM # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
0483..0486 ; NSM # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA
0488..0489 ; NSM # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
0591..05A1 ; NSM # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
05A3..05B9 ; NSM # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM
05BB..05BD ; NSM # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
0591..05BD ; NSM # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG
05BF ; NSM # Mn HEBREW POINT RAFE
05C1..05C2 ; NSM # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
05C4 ; NSM # Mn HEBREW MARK UPPER DOT
05C4..05C5 ; NSM # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
0610..0615 ; NSM # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH
064B..0658 ; NSM # Mn [14] ARABIC FATHATAN..ARABIC MARK NOON GHUNNA
064B..065E ; NSM # Mn [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS
0670 ; NSM # Mn ARABIC LETTER SUPERSCRIPT ALEF
06D6..06DC ; NSM # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
06DE ; NSM # Me ARABIC START OF RUB EL HIZB
@ -1169,6 +1249,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
1036..1037 ; NSM # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW
1039 ; NSM # Mn MYANMAR SIGN VIRAMA
1058..1059 ; NSM # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
135F ; NSM # Mn ETHIOPIC COMBINING GEMINATION MARK
1712..1714 ; NSM # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA
1732..1734 ; NSM # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD
1752..1753 ; NSM # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
@ -1184,41 +1265,54 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
1929..192B ; NSM # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
1932 ; NSM # Mn LIMBU SMALL LETTER ANUSVARA
1939..193B ; NSM # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
1A17..1A18 ; NSM # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
1DC0..1DC3 ; NSM # Mn [4] COMBINING DOTTED GRAVE ACCENT..COMBINING SUSPENSION MARK
20D0..20DC ; NSM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; NSM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1 ; NSM # Mn COMBINING LEFT RIGHT ARROW ABOVE
20E2..20E4 ; NSM # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE
20E5..20EA ; NSM # Mn [6] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LEFTWARDS ARROW OVERLAY
20E5..20EB ; NSM # Mn [7] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LONG DOUBLE SOLIDUS OVERLAY
302A..302F ; NSM # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; NSM # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
A802 ; NSM # Mc SYLOTI NAGRI SIGN DVISVARA
A806 ; NSM # Mn SYLOTI NAGRI SIGN HASANTA
A80B ; NSM # Mn SYLOTI NAGRI SIGN ANUSVARA
A825..A826 ; NSM # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
FB1E ; NSM # Mn HEBREW POINT JUDEO-SPANISH VARIKA
FE00..FE0F ; NSM # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
FE20..FE23 ; NSM # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
10A01..10A03 ; NSM # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; NSM # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; NSM # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10A38..10A3A ; NSM # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
10A3F ; NSM # Mn KHAROSHTHI VIRAMA
1D167..1D169 ; NSM # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
1D17B..1D182 ; NSM # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
1D185..1D18B ; NSM # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
1D1AA..1D1AD ; NSM # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
1D242..1D244 ; NSM # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 803
# Total code points: 846
# ================================================
# Bidi_Class=Arabic_Letter
0600..0603 ; AL # Cf [4] ARABIC NUMBER SIGN..ARABIC SIGN SAFHA
0604..060B ; AL # Cn [8] <reserved-0604>..<reserved-060B>
0604..060A ; AL # Cn [7] <reserved-0604>..<reserved-060A>
060B ; AL # Sc AFGHANI SIGN
060D ; AL # Po ARABIC DATE SEPARATOR
0616..061A ; AL # Cn [5] <reserved-0616>..<reserved-061A>
061B ; AL # Po ARABIC SEMICOLON
061C..061E ; AL # Cn [3] <reserved-061C>..<reserved-061E>
061F ; AL # Po ARABIC QUESTION MARK
061C..061D ; AL # Cn [2] <reserved-061C>..<reserved-061D>
061E..061F ; AL # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK
0620 ; AL # Cn <reserved-0620>
0621..063A ; AL # Lo [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN
063B..063F ; AL # Cn [5] <reserved-063B>..<reserved-063F>
0640 ; AL # Lm ARABIC TATWEEL
0641..064A ; AL # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
0659..065F ; AL # Cn [7] <reserved-0659>..<reserved-065F>
065F ; AL # Cn <reserved-065F>
066D ; AL # Po ARABIC FIVE POINTED STAR
066E..066F ; AL # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
0671..06D3 ; AL # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
@ -1235,8 +1329,8 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
0710 ; AL # Lo SYRIAC LETTER ALAPH
0712..072F ; AL # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
074B..074C ; AL # Cn [2] <reserved-074B>..<reserved-074C>
074D..074F ; AL # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE
0750..077F ; AL # Cn [48] <reserved-0750>..<reserved-077F>
074D..076D ; AL # Lo [33] SYRIAC LETTER SOGDIAN ZHAIN..ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE
076E..077F ; AL # Cn [18] <reserved-076E>..<reserved-077F>
0780..07A5 ; AL # Lo [38] THAANA LETTER HAA..THAANA LETTER WAAVU
07B1 ; AL # Lo THAANA LETTER NAA
07B2..07BF ; AL # Cn [14] <reserved-07B2>..<reserved-07BF>
@ -1256,7 +1350,7 @@ FE75 ; AL # Cn <reserved-FE75>
FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
FEFD..FEFE ; AL # Cn [2] <reserved-FEFD>..<reserved-FEFE>
# Total code points: 1136
# Total code points: 1130
# ================================================

889
icu4c/source/data/unidata/DerivedCoreProperties.txt
View File

File diff suppressed because it is too large Load Diff

49
icu4c/source/data/unidata/DerivedJoiningGroup.txt
View File

@ -1,8 +1,8 @@
# DerivedJoiningGroup-4.0.1.txt
# Date: 2004-03-02, 02:42:04 GMT [MD]
# DerivedJoiningGroup-4.1.0.txt
# Date: 2004-12-15, 02:14:58 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
@ -18,8 +18,9 @@
0639..063A ; Ain # Lo [2] ARABIC LETTER AIN..ARABIC LETTER GHAIN
06A0 ; Ain # Lo ARABIC LETTER AIN WITH THREE DOTS ABOVE
06FC ; Ain # Lo ARABIC LETTER GHAIN WITH DOT BELOW
075D..075F ; Ain # Lo [3] ARABIC LETTER AIN WITH TWO DOTS ABOVE..ARABIC LETTER AIN WITH TWO DOTS VERTICALLY ABOVE
# Total code points: 4
# Total code points: 7
# ================================================
@ -43,8 +44,9 @@
062A..062B ; Beh # Lo [2] ARABIC LETTER TEH..ARABIC LETTER THEH
066E ; Beh # Lo ARABIC LETTER DOTLESS BEH
0679..0680 ; Beh # Lo [8] ARABIC LETTER TTEH..ARABIC LETTER BEHEH
0750..0756 ; Beh # Lo [7] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER BEH WITH SMALL V
# Total code points: 12
# Total code points: 19
# ================================================
@ -58,8 +60,9 @@
062F..0630 ; Dal # Lo [2] ARABIC LETTER DAL..ARABIC LETTER THAL
0688..0690 ; Dal # Lo [9] ARABIC LETTER DDAL..ARABIC LETTER DAL WITH FOUR DOTS ABOVE
06EE ; Dal # Lo ARABIC LETTER DAL WITH INVERTED V
0759..075A ; Dal # Lo [2] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER DAL WITH INVERTED SMALL V BELOW
# Total code points: 12
# Total code points: 14
# ================================================
@ -79,8 +82,9 @@
0641 ; Feh # Lo ARABIC LETTER FEH
06A1..06A6 ; Feh # Lo [6] ARABIC LETTER DOTLESS FEH..ARABIC LETTER PEHEH
0760..0761 ; Feh # Lo [2] ARABIC LETTER FEH WITH TWO DOTS BELOW..ARABIC LETTER FEH WITH THREE DOTS POINTING UPWARDS BELOW
# Total code points: 7
# Total code points: 9
# ================================================
@ -93,8 +97,9 @@
06A9 ; Gaf # Lo ARABIC LETTER KEHEH
06AB ; Gaf # Lo ARABIC LETTER KAF WITH RING
06AF..06B4 ; Gaf # Lo [6] ARABIC LETTER GAF..ARABIC LETTER GAF WITH THREE DOTS ABOVE
0762..0764 ; Gaf # Lo [3] ARABIC LETTER KEHEH WITH DOT ABOVE..ARABIC LETTER KEHEH WITH THREE DOTS POINTING UPWARDS BELOW
# Total code points: 8
# Total code points: 11
# ================================================
@ -108,14 +113,15 @@
062C..062E ; Hah # Lo [3] ARABIC LETTER JEEM..ARABIC LETTER KHAH
0681..0687 ; Hah # Lo [7] ARABIC LETTER HAH WITH HAMZA ABOVE..ARABIC LETTER TCHEHEH
06BF ; Hah # Lo ARABIC LETTER TCHEH WITH DOT ABOVE
0757..0758 ; Hah # Lo [2] ARABIC LETTER HAH WITH TWO DOTS ABOVE..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW
# Total code points: 11
# Total code points: 13
# ================================================
06C2..06C3 ; Hamza_On_Heh_Goal # Lo [2] ARABIC LETTER HEH GOAL WITH HAMZA ABOVE..ARABIC LETTER TEH MARBUTA GOAL
06C3 ; Hamza_On_Heh_Goal # Lo ARABIC LETTER TEH MARBUTA GOAL
# Total code points: 2
# Total code points: 1
# ================================================
@ -131,9 +137,9 @@
# ================================================
06C1 ; Heh_Goal # Lo ARABIC LETTER HEH GOAL
06C1..06C2 ; Heh_Goal # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
# Total code points: 1
# Total code points: 2
# ================================================
@ -165,8 +171,9 @@
0644 ; Lam # Lo ARABIC LETTER LAM
06B5..06B8 ; Lam # Lo [4] ARABIC LETTER LAM WITH SMALL V..ARABIC LETTER LAM WITH THREE DOTS BELOW
076A ; Lam # Lo ARABIC LETTER LAM WITH BAR
# Total code points: 5
# Total code points: 6
# ================================================
@ -177,8 +184,9 @@
# ================================================
0645 ; Meem # Lo ARABIC LETTER MEEM
0765..0766 ; Meem # Lo [2] ARABIC LETTER MEEM WITH DOT ABOVE..ARABIC LETTER MEEM WITH DOT BELOW
# Total code points: 1
# Total code points: 3
# ================================================
@ -190,8 +198,9 @@
0646 ; Noon # Lo ARABIC LETTER NOON
06B9..06BD ; Noon # Lo [5] ARABIC LETTER NOON WITH DOT BELOW..ARABIC LETTER NOON WITH THREE DOTS ABOVE
0767..0769 ; Noon # Lo [3] ARABIC LETTER NOON WITH TWO DOTS BELOW..ARABIC LETTER NOON WITH SMALL V
# Total code points: 6
# Total code points: 9
# ================================================
@ -224,8 +233,10 @@
0631..0632 ; Reh # Lo [2] ARABIC LETTER REH..ARABIC LETTER ZAIN
0691..0699 ; Reh # Lo [9] ARABIC LETTER RREH..ARABIC LETTER REH WITH FOUR DOTS ABOVE
06EF ; Reh # Lo ARABIC LETTER REH WITH INVERTED V
075B ; Reh # Lo ARABIC LETTER REH WITH STROKE
076B..076C ; Reh # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE
# Total code points: 12
# Total code points: 15
# ================================================
@ -252,8 +263,10 @@
0633..0634 ; Seen # Lo [2] ARABIC LETTER SEEN..ARABIC LETTER SHEEN
069A..069C ; Seen # Lo [3] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER SEEN WITH THREE DOTS BELOW AND THREE DOTS ABOVE
06FA ; Seen # Lo ARABIC LETTER SHEEN WITH DOT BELOW
075C ; Seen # Lo ARABIC LETTER SEEN WITH FOUR DOTS ABOVE
076D ; Seen # Lo ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE
# Total code points: 6
# Total code points: 8
# ================================================

51
icu4c/source/data/unidata/DerivedJoiningType.txt
View File

@ -1,8 +1,8 @@
# DerivedJoiningType-4.0.1.txt
# Date: 2004-03-02, 02:42:08 GMT [MD]
# DerivedJoiningType-4.1.0.txt
# Date: 2004-12-15, 02:15:30 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
@ -35,7 +35,7 @@
066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH
069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE
06C1 ; D # Lo ARABIC LETTER HEH GOAL
06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
06CC ; D # Lo ARABIC LETTER FARSI YEH
06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V
06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW
@ -47,9 +47,11 @@
0729 ; D # Lo SYRIAC LETTER QAPH
072B ; D # Lo SYRIAC LETTER SHIN
072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL
074E..074F ; D # Lo [2] SYRIAC LETTER SOGDIAN KHAPH..SYRIAC LETTER SOGDIAN FE
074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW
075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR
076D ; D # Lo ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE
# Total code points: 111
# Total code points: 137
# ================================================
@ -64,7 +66,7 @@
0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE
0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE
06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE
06C2..06CB ; R # Lo [10] ARABIC LETTER HEH GOAL WITH HAMZA ABOVE..ARABIC LETTER VE
06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE
06CD ; R # Lo ARABIC LETTER YEH WITH TAIL
06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE
06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
@ -78,27 +80,28 @@
072C ; R # Lo SYRIAC LETTER TAW
072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH
074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN
0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE
076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE
# Total code points: 65
# Total code points: 69
# ================================================
# Joining_Type=Transparent
00AD ; T # Cf SOFT HYPHEN
0300..0357 ; T # Mn [88] COMBINING GRAVE ACCENT..COMBINING RIGHT HALF RING ABOVE
035D..036F ; T # Mn [19] COMBINING DOUBLE BREVE..COMBINING LATIN SMALL LETTER X
0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
0483..0486 ; T # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA
0591..05A1 ; T # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
05A3..05B9 ; T # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM
05BB..05BD ; T # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG
05BF ; T # Mn HEBREW POINT RAFE
05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
05C4 ; T # Mn HEBREW MARK UPPER DOT
05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
0610..0615 ; T # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH
064B..0658 ; T # Mn [14] ARABIC FATHATAN..ARABIC MARK NOON GHUNNA
064B..065E ; T # Mn [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS
0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF
06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
06DE ; T # Me ARABIC START OF RUB EL HIZB
06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA
06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM
@ -173,6 +176,7 @@
1036..1037 ; T # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW
1039 ; T # Mn MYANMAR SIGN VIRAMA
1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
135F ; T # Mn ETHIOPIC COMBINING GEMINATION MARK
1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA
1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD
1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
@ -188,28 +192,41 @@
1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA
1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
1DC0..1DC3 ; T # Mn [4] COMBINING DOTTED GRAVE ACCENT..COMBINING SUSPENSION MARK
200B ; T # Cf ZERO WIDTH SPACE
200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
2060..2063 ; T # Cf [4] WORD JOINER..INVISIBLE SEPARATOR
206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE
20E5..20EA ; T # Mn [6] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LEFTWARDS ARROW OVERLAY
20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE
20E5..20EB ; T # Mn [7] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LONG DOUBLE SOLIDUS OVERLAY
302A..302F ; T # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA
A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA
A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA
FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
FE20..FE23 ; T # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE
FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
10A3F ; T # Mn KHAROSHTHI VIRAMA
1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
E0001 ; T # Cf LANGUAGE TAG
E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 923
# Total code points: 975

68
icu4c/source/data/unidata/DerivedNormalizationProps.txt
View File

@ -1,8 +1,8 @@
# DerivedNormalizationProps-4.0.1.txt
# Date: 2004-03-02, 02:42:17 GMT [MD]
# DerivedNormalizationProps-4.1.0.txt
# Date: 2004-12-11, 05:42:12 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
@ -41,6 +41,7 @@
1D40 ; FC_NFKC; 0074
1D41 ; FC_NFKC; 0075
1D42 ; FC_NFKC; 0077
1D78 ; FC_NFKC; 043D
20A8 ; FC_NFKC; 0072 0073
2102 ; FC_NFKC; 0063
2103 ; FC_NFKC; 00B0 0063
@ -579,7 +580,7 @@
1D7A8 ; FC_NFKC; 03C9
1D7BB ; FC_NFKC; 03C3
# Total code points: 564
# Total code points: 565
# ================================================
@ -649,6 +650,7 @@ FA22 ; Full_Composition_Exclusion
FA25..FA26 ; Full_Composition_Exclusion
FA2A..FA2D ; Full_Composition_Exclusion
FA30..FA6A ; Full_Composition_Exclusion
FA70..FAD9 ; Full_Composition_Exclusion
FB1D ; Full_Composition_Exclusion
FB1F ; Full_Composition_Exclusion
FB2A..FB36 ; Full_Composition_Exclusion
@ -661,7 +663,7 @@ FB46..FB4E ; Full_Composition_Exclusion
1D1BB..1D1C0 ; Full_Composition_Exclusion
2F800..2FA1D ; Full_Composition_Exclusion
# Total code points: 1009
# Total code points: 1115
# ================================================
@ -887,6 +889,7 @@ FA22 ; NFD_QC; N
FA25..FA26 ; NFD_QC; N
FA2A..FA2D ; NFD_QC; N
FA30..FA6A ; NFD_QC; N
FA70..FAD9 ; NFD_QC; N
FB1D ; NFD_QC; N
FB1F ; NFD_QC; N
FB2A..FB36 ; NFD_QC; N
@ -899,7 +902,7 @@ FB46..FB4E ; NFD_QC; N
1D1BB..1D1C0 ; NFD_QC; N
2F800..2FA1D ; NFD_QC; N
# Total code points: 13098
# Total code points: 13204
# ================================================
@ -975,6 +978,7 @@ FA22 ; NFC_QC; N
FA25..FA26 ; NFC_QC; N
FA2A..FA2D ; NFC_QC; N
FA30..FA6A ; NFC_QC; N
FA70..FAD9 ; NFC_QC; N
FB1D ; NFC_QC; N
FB1F ; NFC_QC; N
FB2A..FB36 ; NFC_QC; N
@ -987,7 +991,7 @@ FB46..FB4E ; NFC_QC; N
1D1BB..1D1C0 ; NFC_QC; N
2F800..2FA1D ; NFC_QC; N
# Total code points: 1009
# Total code points: 1115
# ================================================
@ -1163,11 +1167,14 @@ FB46..FB4E ; NFC_QC; N
0FAC ; NFKD_QC; N
0FB9 ; NFKD_QC; N
1026 ; NFKD_QC; N
10FC ; NFKD_QC; N
1D2C..1D2E ; NFKD_QC; N
1D30..1D3A ; NFKD_QC; N
1D3C..1D4D ; NFKD_QC; N
1D4F..1D61 ; NFKD_QC; N
1D62..1D6A ; NFKD_QC; N
1D78 ; NFKD_QC; N
1D9B..1DBF ; NFKD_QC; N
1E00..1E9B ; NFKD_QC; N
1EA0..1EF9 ; NFKD_QC; N
1F00..1F15 ; NFKD_QC; N
@ -1218,6 +1225,7 @@ FB46..FB4E ; NFC_QC; N
208A..208C ; NFKD_QC; N
208D ; NFKD_QC; N
208E ; NFKD_QC; N
2090..2094 ; NFKD_QC; N
20A8 ; NFKD_QC; N
2100..2101 ; NFKD_QC; N
2102 ; NFKD_QC; N
@ -1239,7 +1247,7 @@ FB46..FB4E ; NFC_QC; N
2135..2138 ; NFKD_QC; N
2139 ; NFKD_QC; N
213B ; NFKD_QC; N
213D..213F ; NFKD_QC; N
213C..213F ; NFKD_QC; N
2140 ; NFKD_QC; N
2145..2149 ; NFKD_QC; N
2153..215F ; NFKD_QC; N
@ -1278,6 +1286,7 @@ FB46..FB4E ; NFC_QC; N
2A0C ; NFKD_QC; N
2A74..2A76 ; NFKD_QC; N
2ADC ; NFKD_QC; N
2D6F ; NFKD_QC; N
2E9F ; NFKD_QC; N
2EF3 ; NFKD_QC; N
2F00..2FD5 ; NFKD_QC; N
@ -1340,7 +1349,7 @@ FB46..FB4E ; NFC_QC; N
322A..3243 ; NFKD_QC; N
3250 ; NFKD_QC; N
3251..325F ; NFKD_QC; N
3260..327D ; NFKD_QC; N
3260..327E ; NFKD_QC; N
3280..3289 ; NFKD_QC; N
328A..32B0 ; NFKD_QC; N
32B1..32BF ; NFKD_QC; N
@ -1356,6 +1365,7 @@ FA22 ; NFKD_QC; N
FA25..FA26 ; NFKD_QC; N
FA2A..FA2D ; NFKD_QC; N
FA30..FA6A ; NFKD_QC; N
FA70..FAD9 ; NFKD_QC; N
FB00..FB06 ; NFKD_QC; N
FB13..FB17 ; NFKD_QC; N
FB1D ; NFKD_QC; N
@ -1372,6 +1382,10 @@ FD50..FD8F ; NFKD_QC; N
FD92..FDC7 ; NFKD_QC; N
FDF0..FDFB ; NFKD_QC; N
FDFC ; NFKD_QC; N
FE10..FE16 ; NFKD_QC; N
FE17 ; NFKD_QC; N
FE18 ; NFKD_QC; N
FE19 ; NFKD_QC; N
FE30 ; NFKD_QC; N
FE31..FE32 ; NFKD_QC; N
FE33..FE34 ; NFKD_QC; N
@ -1445,8 +1459,7 @@ FF60 ; NFKD_QC; N
FF61 ; NFKD_QC; N
FF62 ; NFKD_QC; N
FF63 ; NFKD_QC; N
FF64 ; NFKD_QC; N
FF65 ; NFKD_QC; N
FF64..FF65 ; NFKD_QC; N
FF66..FF6F ; NFKD_QC; N
FF70 ; NFKD_QC; N
FF71..FF9D ; NFKD_QC; N
@ -1484,7 +1497,7 @@ FFED..FFEE ; NFKD_QC; N
1D540..1D544 ; NFKD_QC; N
1D546 ; NFKD_QC; N
1D54A..1D550 ; NFKD_QC; N
1D552..1D6A3 ; NFKD_QC; N
1D552..1D6A5 ; NFKD_QC; N
1D6A8..1D6C0 ; NFKD_QC; N
1D6C1 ; NFKD_QC; N
1D6C2..1D6DA ; NFKD_QC; N
@ -1509,7 +1522,7 @@ FFED..FFEE ; NFKD_QC; N
1D7CE..1D7FF ; NFKD_QC; N
2F800..2FA1D ; NFKD_QC; N
# Total code points: 16396
# Total code points: 16561
# ================================================
@ -1582,11 +1595,14 @@ FFED..FFEE ; NFKD_QC; N
0FA7 ; NFKC_QC; N
0FAC ; NFKC_QC; N
0FB9 ; NFKC_QC; N
10FC ; NFKC_QC; N
1D2C..1D2E ; NFKC_QC; N
1D30..1D3A ; NFKC_QC; N
1D3C..1D4D ; NFKC_QC; N
1D4F..1D61 ; NFKC_QC; N
1D62..1D6A ; NFKC_QC; N
1D78 ; NFKC_QC; N
1D9B..1DBF ; NFKC_QC; N
1E9A..1E9B ; NFKC_QC; N
1F71 ; NFKC_QC; N
1F73 ; NFKC_QC; N
@ -1634,6 +1650,7 @@ FFED..FFEE ; NFKD_QC; N
208A..208C ; NFKC_QC; N
208D ; NFKC_QC; N
208E ; NFKC_QC; N
2090..2094 ; NFKC_QC; N
20A8 ; NFKC_QC; N
2100..2101 ; NFKC_QC; N
2102 ; NFKC_QC; N
@ -1655,7 +1672,7 @@ FFED..FFEE ; NFKD_QC; N
2135..2138 ; NFKC_QC; N
2139 ; NFKC_QC; N
213B ; NFKC_QC; N
213D..213F ; NFKC_QC; N
213C..213F ; NFKC_QC; N
2140 ; NFKC_QC; N
2145..2149 ; NFKC_QC; N
2153..215F ; NFKC_QC; N
@ -1670,6 +1687,7 @@ FFED..FFEE ; NFKD_QC; N
2A0C ; NFKC_QC; N
2A74..2A76 ; NFKC_QC; N
2ADC ; NFKC_QC; N
2D6F ; NFKC_QC; N
2E9F ; NFKC_QC; N
2EF3 ; NFKC_QC; N
2F00..2FD5 ; NFKC_QC; N
@ -1687,7 +1705,7 @@ FFED..FFEE ; NFKD_QC; N
322A..3243 ; NFKC_QC; N
3250 ; NFKC_QC; N
3251..325F ; NFKC_QC; N
3260..327D ; NFKC_QC; N
3260..327E ; NFKC_QC; N
3280..3289 ; NFKC_QC; N
328A..32B0 ; NFKC_QC; N
32B1..32BF ; NFKC_QC; N
@ -1702,6 +1720,7 @@ FA22 ; NFKC_QC; N
FA25..FA26 ; NFKC_QC; N
FA2A..FA2D ; NFKC_QC; N
FA30..FA6A ; NFKC_QC; N
FA70..FAD9 ; NFKC_QC; N
FB00..FB06 ; NFKC_QC; N
FB13..FB17 ; NFKC_QC; N
FB1D ; NFKC_QC; N
@ -1718,6 +1737,10 @@ FD50..FD8F ; NFKC_QC; N
FD92..FDC7 ; NFKC_QC; N
FDF0..FDFB ; NFKC_QC; N
FDFC ; NFKC_QC; N
FE10..FE16 ; NFKC_QC; N
FE17 ; NFKC_QC; N
FE18 ; NFKC_QC; N
FE19 ; NFKC_QC; N
FE30 ; NFKC_QC; N
FE31..FE32 ; NFKC_QC; N
FE33..FE34 ; NFKC_QC; N
@ -1791,8 +1814,7 @@ FF60 ; NFKC_QC; N
FF61 ; NFKC_QC; N
FF62 ; NFKC_QC; N
FF63 ; NFKC_QC; N
FF64 ; NFKC_QC; N
FF65 ; NFKC_QC; N
FF64..FF65 ; NFKC_QC; N
FF66..FF6F ; NFKC_QC; N
FF70 ; NFKC_QC; N
FF71..FF9D ; NFKC_QC; N
@ -1830,7 +1852,7 @@ FFED..FFEE ; NFKC_QC; N
1D540..1D544 ; NFKC_QC; N
1D546 ; NFKC_QC; N
1D54A..1D550 ; NFKC_QC; N
1D552..1D6A3 ; NFKC_QC; N
1D552..1D6A5 ; NFKC_QC; N
1D6A8..1D6C0 ; NFKC_QC; N
1D6C1 ; NFKC_QC; N
1D6C2..1D6DA ; NFKC_QC; N
@ -1855,7 +1877,7 @@ FFED..FFEE ; NFKC_QC; N
1D7CE..1D7FF ; NFKC_QC; N
2F800..2FA1D ; NFKC_QC; N
# Total code points: 4319
# Total code points: 4484
# ================================================
@ -2408,7 +2430,7 @@ FB46..FB4E ; Expands_On_NFC
322A..3243 ; Expands_On_NFKD
3250 ; Expands_On_NFKD
3251..325F ; Expands_On_NFKD
326E..327D ; Expands_On_NFKD
326E..327E ; Expands_On_NFKD
32B1..32BF ; Expands_On_NFKD
32C0..32CF ; Expands_On_NFKD
3300..33FF ; Expands_On_NFKD
@ -2432,6 +2454,7 @@ FD50..FD8F ; Expands_On_NFKD
FD92..FDC7 ; Expands_On_NFKD
FDF0..FDFB ; Expands_On_NFKD
FDFC ; Expands_On_NFKD
FE19 ; Expands_On_NFKD
FE30 ; Expands_On_NFKD
FE49..FE4C ; Expands_On_NFKD
FE70..FE72 ; Expands_On_NFKD
@ -2443,7 +2466,7 @@ FFE3 ; Expands_On_NFKD
1D15E..1D164 ; Expands_On_NFKD
1D1BB..1D1C0 ; Expands_On_NFKD
# Total code points: 13297
# Total code points: 13299
# ================================================
@ -2561,6 +2584,7 @@ FD50..FD8F ; Expands_On_NFKC
FD92..FDC7 ; Expands_On_NFKC
FDF0..FDFB ; Expands_On_NFKC
FDFC ; Expands_On_NFKC
FE19 ; Expands_On_NFKC
FE30 ; Expands_On_NFKC
FE49..FE4C ; Expands_On_NFKC
FE70..FE72 ; Expands_On_NFKC
@ -2571,4 +2595,4 @@ FFE3 ; Expands_On_NFKC
1D15E..1D164 ; Expands_On_NFKC
1D1BB..1D1C0 ; Expands_On_NFKC
# Total code points: 1170
# Total code points: 1171

140
icu4c/source/data/unidata/DerivedNumericValues.txt
View File

@ -1,8 +1,8 @@
# DerivedNumericValues-4.0.1.txt
# Date: 2004-03-11, 18:44:27 GMT [MD]
# DerivedNumericValues-4.1.0.txt
# Date: 2004-12-11, 05:44:37 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
@ -30,6 +30,7 @@
0A66 ; 0.0 # Nd GURMUKHI DIGIT ZERO
0AE6 ; 0.0 # Nd GUJARATI DIGIT ZERO
0B66 ; 0.0 # Nd ORIYA DIGIT ZERO
0BE6 ; 0.0 # Nd TAMIL DIGIT ZERO
0C66 ; 0.0 # Nd TELUGU DIGIT ZERO
0CE6 ; 0.0 # Nd KANNADA DIGIT ZERO
0D66 ; 0.0 # Nd MALAYALAM DIGIT ZERO
@ -41,6 +42,7 @@
17F0 ; 0.0 # No KHMER SYMBOL LEK ATTAK SON
1810 ; 0.0 # Nd MONGOLIAN DIGIT ZERO
1946 ; 0.0 # Nd LIMBU DIGIT ZERO
19D0 ; 0.0 # Nd NEW TAI LUE DIGIT ZERO
2070 ; 0.0 # No SUPERSCRIPT ZERO
2080 ; 0.0 # No SUBSCRIPT ZERO
24EA ; 0.0 # No CIRCLED DIGIT ZERO
@ -48,6 +50,7 @@
3007 ; 0.0 # Nl IDEOGRAPHIC NUMBER ZERO
96F6 ; 0.0 # Lo CJK UNIFIED IDEOGRAPH-96F6
FF10 ; 0.0 # Nd FULLWIDTH DIGIT ZERO
1018A ; 0.0 # No GREEK ZERO SIGN
104A0 ; 0.0 # Nd OSMANYA DIGIT ZERO
1D7CE ; 0.0 # Nd MATHEMATICAL BOLD DIGIT ZERO
1D7D8 ; 0.0 # Nd MATHEMATICAL DOUBLE-STRUCK DIGIT ZERO
@ -55,7 +58,7 @@ FF10 ; 0.0 # Nd FULLWIDTH DIGIT ZERO
1D7EC ; 0.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT ZERO
1D7F6 ; 0.0 # Nd MATHEMATICAL MONOSPACE DIGIT ZERO
# Total code points: 32
# Total code points: 35
# ================================================
@ -78,8 +81,9 @@ FF10 ; 0.0 # Nd FULLWIDTH DIGIT ZERO
# ================================================
00BC ; 0.25 # No VULGAR FRACTION ONE QUARTER
10140 ; 0.25 # Nl GREEK ACROPHONIC ATTIC ONE QUARTER
# Total code points: 1
# Total code points: 2
# ================================================
@ -103,8 +107,11 @@ FF10 ; 0.0 # Nd FULLWIDTH DIGIT ZERO
00BD ; 0.5 # No VULGAR FRACTION ONE HALF
0F2A ; 0.5 # No TIBETAN DIGIT HALF ONE
2CFD ; 0.5 # No COPTIC FRACTION ONE HALF
10141 ; 0.5 # Nl GREEK ACROPHONIC ATTIC ONE HALF
10175..10176 ; 0.5 # No [2] GREEK ONE HALF SIGN..GREEK ONE HALF SIGN ALTERNATE FORM
# Total code points: 2
# Total code points: 6
# ================================================
@ -121,14 +128,16 @@ FF10 ; 0.0 # Nd FULLWIDTH DIGIT ZERO
# ================================================
2154 ; 0.66666667 # No VULGAR FRACTION TWO THIRDS
10177 ; 0.66666667 # No GREEK TWO THIRDS SIGN
# Total code points: 1
# Total code points: 2
# ================================================
00BE ; 0.75 # No VULGAR FRACTION THREE QUARTERS
10178 ; 0.75 # No GREEK THREE QUARTERS SIGN
# Total code points: 1
# Total code points: 2
# ================================================
@ -168,11 +177,12 @@ FF10 ; 0.0 # Nd FULLWIDTH DIGIT ZERO
0ED1 ; 1.0 # Nd LAO DIGIT ONE
0F21 ; 1.0 # Nd TIBETAN DIGIT ONE
1041 ; 1.0 # Nd MYANMAR DIGIT ONE
1369 ; 1.0 # Nd ETHIOPIC DIGIT ONE
1369 ; 1.0 # No ETHIOPIC DIGIT ONE
17E1 ; 1.0 # Nd KHMER DIGIT ONE
17F1 ; 1.0 # No KHMER SYMBOL LEK ATTAK MUOY
1811 ; 1.0 # Nd MONGOLIAN DIGIT ONE
1947 ; 1.0 # Nd LIMBU DIGIT ONE
19D1 ; 1.0 # Nd NEW TAI LUE DIGIT ONE
2081 ; 1.0 # No SUBSCRIPT ONE
215F ; 1.0 # No FRACTION NUMERATOR ONE
2160 ; 1.0 # Nl ROMAN NUMERAL ONE
@ -194,15 +204,19 @@ FF10 ; 0.0 # Nd FULLWIDTH DIGIT ZERO
5F0C ; 1.0 # Lo CJK UNIFIED IDEOGRAPH-5F0C
FF11 ; 1.0 # Nd FULLWIDTH DIGIT ONE
10107 ; 1.0 # No AEGEAN NUMBER ONE
10142 ; 1.0 # Nl GREEK ACROPHONIC ATTIC ONE DRACHMA
10158..1015A ; 1.0 # Nl [3] GREEK ACROPHONIC HERAEUM ONE PLETHRON..GREEK ACROPHONIC HERMIONE ONE
10320 ; 1.0 # No OLD ITALIC NUMERAL ONE
103D1 ; 1.0 # Nl OLD PERSIAN NUMBER ONE
104A1 ; 1.0 # Nd OSMANYA DIGIT ONE
10A40 ; 1.0 # Nd KHAROSHTHI DIGIT ONE
1D7CF ; 1.0 # Nd MATHEMATICAL BOLD DIGIT ONE
1D7D9 ; 1.0 # Nd MATHEMATICAL DOUBLE-STRUCK DIGIT ONE
1D7E3 ; 1.0 # Nd MATHEMATICAL SANS-SERIF DIGIT ONE
1D7ED ; 1.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT ONE
1D7F7 ; 1.0 # Nd MATHEMATICAL MONOSPACE DIGIT ONE
# Total code points: 51
# Total code points: 58
# ================================================
@ -230,11 +244,12 @@ FF11 ; 1.0 # Nd FULLWIDTH DIGIT ONE
0ED2 ; 2.0 # Nd LAO DIGIT TWO
0F22 ; 2.0 # Nd TIBETAN DIGIT TWO
1042 ; 2.0 # Nd MYANMAR DIGIT TWO
136A ; 2.0 # Nd ETHIOPIC DIGIT TWO
136A ; 2.0 # No ETHIOPIC DIGIT TWO
17E2 ; 2.0 # Nd KHMER DIGIT TWO
17F2 ; 2.0 # No KHMER SYMBOL LEK ATTAK PII
1812 ; 2.0 # Nd MONGOLIAN DIGIT TWO
1948 ; 2.0 # Nd LIMBU DIGIT TWO
19D2 ; 2.0 # Nd NEW TAI LUE DIGIT TWO
2082 ; 2.0 # No SUBSCRIPT TWO
2161 ; 2.0 # Nl ROMAN NUMERAL TWO
2171 ; 2.0 # Nl SMALL ROMAN NUMERAL TWO
@ -257,14 +272,17 @@ FF11 ; 1.0 # Nd FULLWIDTH DIGIT ONE
8D30 ; 2.0 # Lo CJK UNIFIED IDEOGRAPH-8D30
FF12 ; 2.0 # Nd FULLWIDTH DIGIT TWO
10108 ; 2.0 # No AEGEAN NUMBER TWO
1015B..1015E ; 2.0 # Nl [4] GREEK ACROPHONIC EPIDAUREAN TWO..GREEK ACROPHONIC EPIDAUREAN TWO DRACHMAS
103D2 ; 2.0 # Nl OLD PERSIAN NUMBER TWO
104A2 ; 2.0 # Nd OSMANYA DIGIT TWO
10A41 ; 2.0 # Nd KHAROSHTHI DIGIT TWO
1D7D0 ; 2.0 # Nd MATHEMATICAL BOLD DIGIT TWO
1D7DA ; 2.0 # Nd MATHEMATICAL DOUBLE-STRUCK DIGIT TWO
1D7E4 ; 2.0 # Nd MATHEMATICAL SANS-SERIF DIGIT TWO
1D7EE ; 2.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT TWO
1D7F8 ; 2.0 # Nd MATHEMATICAL MONOSPACE DIGIT TWO
# Total code points: 51
# Total code points: 58
# ================================================
@ -292,11 +310,12 @@ FF12 ; 2.0 # Nd FULLWIDTH DIGIT TWO
0ED3 ; 3.0 # Nd LAO DIGIT THREE
0F23 ; 3.0 # Nd TIBETAN DIGIT THREE
1043 ; 3.0 # Nd MYANMAR DIGIT THREE
136B ; 3.0 # Nd ETHIOPIC DIGIT THREE
136B ; 3.0 # No ETHIOPIC DIGIT THREE
17E3 ; 3.0 # Nd KHMER DIGIT THREE
17F3 ; 3.0 # No KHMER SYMBOL LEK ATTAK BEI
1813 ; 3.0 # Nd MONGOLIAN DIGIT THREE
1949 ; 3.0 # Nd LIMBU DIGIT THREE
19D3 ; 3.0 # Nd NEW TAI LUE DIGIT THREE
2083 ; 3.0 # No SUBSCRIPT THREE
2162 ; 3.0 # Nl ROMAN NUMERAL THREE
2172 ; 3.0 # Nl SMALL ROMAN NUMERAL THREE
@ -317,13 +336,14 @@ FF12 ; 2.0 # Nd FULLWIDTH DIGIT TWO
FF13 ; 3.0 # Nd FULLWIDTH DIGIT THREE
10109 ; 3.0 # No AEGEAN NUMBER THREE
104A3 ; 3.0 # Nd OSMANYA DIGIT THREE
10A42 ; 3.0 # Nd KHAROSHTHI DIGIT THREE
1D7D1 ; 3.0 # Nd MATHEMATICAL BOLD DIGIT THREE
1D7DB ; 3.0 # Nd MATHEMATICAL DOUBLE-STRUCK DIGIT THREE
1D7E5 ; 3.0 # Nd MATHEMATICAL SANS-SERIF DIGIT THREE
1D7EF ; 3.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT THREE
1D7F9 ; 3.0 # Nd MATHEMATICAL MONOSPACE DIGIT THREE
# Total code points: 50
# Total code points: 52
# ================================================
@ -350,11 +370,12 @@ FF13 ; 3.0 # Nd FULLWIDTH DIGIT THREE
0ED4 ; 4.0 # Nd LAO DIGIT FOUR
0F24 ; 4.0 # Nd TIBETAN DIGIT FOUR
1044 ; 4.0 # Nd MYANMAR DIGIT FOUR
136C ; 4.0 # Nd ETHIOPIC DIGIT FOUR
136C ; 4.0 # No ETHIOPIC DIGIT FOUR
17E4 ; 4.0 # Nd KHMER DIGIT FOUR
17F4 ; 4.0 # No KHMER SYMBOL LEK ATTAK BUON
1814 ; 4.0 # Nd MONGOLIAN DIGIT FOUR
194A ; 4.0 # Nd LIMBU DIGIT FOUR
19D4 ; 4.0 # Nd NEW TAI LUE DIGIT FOUR
2074 ; 4.0 # No SUPERSCRIPT FOUR
2084 ; 4.0 # No SUBSCRIPT FOUR
2163 ; 4.0 # Nl ROMAN NUMERAL FOUR
@ -375,13 +396,14 @@ FF13 ; 3.0 # Nd FULLWIDTH DIGIT THREE
FF14 ; 4.0 # Nd FULLWIDTH DIGIT FOUR
1010A ; 4.0 # No AEGEAN NUMBER FOUR
104A4 ; 4.0 # Nd OSMANYA DIGIT FOUR
10A43 ; 4.0 # Nd KHAROSHTHI DIGIT FOUR
1D7D2 ; 4.0 # Nd MATHEMATICAL BOLD DIGIT FOUR
1D7DC ; 4.0 # Nd MATHEMATICAL DOUBLE-STRUCK DIGIT FOUR
1D7E6 ; 4.0 # Nd MATHEMATICAL SANS-SERIF DIGIT FOUR
1D7F0 ; 4.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT FOUR
1D7FA ; 4.0 # Nd MATHEMATICAL MONOSPACE DIGIT FOUR
# Total code points: 47
# Total code points: 49
# ================================================
@ -407,11 +429,12 @@ FF14 ; 4.0 # Nd FULLWIDTH DIGIT FOUR
0ED5 ; 5.0 # Nd LAO DIGIT FIVE
0F25 ; 5.0 # Nd TIBETAN DIGIT FIVE
1045 ; 5.0 # Nd MYANMAR DIGIT FIVE
136D ; 5.0 # Nd ETHIOPIC DIGIT FIVE
136D ; 5.0 # No ETHIOPIC DIGIT FIVE
17E5 ; 5.0 # Nd KHMER DIGIT FIVE
17F5 ; 5.0 # No KHMER SYMBOL LEK ATTAK PRAM
1815 ; 5.0 # Nd MONGOLIAN DIGIT FIVE
194B ; 5.0 # Nd LIMBU DIGIT FIVE
19D5 ; 5.0 # Nd NEW TAI LUE DIGIT FIVE
2075 ; 5.0 # No SUPERSCRIPT FIVE
2085 ; 5.0 # No SUBSCRIPT FIVE
2164 ; 5.0 # Nl ROMAN NUMERAL FIVE
@ -430,6 +453,11 @@ FF14 ; 4.0 # Nd FULLWIDTH DIGIT FOUR
4F0D ; 5.0 # Lo CJK UNIFIED IDEOGRAPH-4F0D
FF15 ; 5.0 # Nd FULLWIDTH DIGIT FIVE
1010B ; 5.0 # No AEGEAN NUMBER FIVE
10143 ; 5.0 # Nl GREEK ACROPHONIC ATTIC FIVE
10148 ; 5.0 # Nl GREEK ACROPHONIC ATTIC FIVE TALENTS
1014F ; 5.0 # Nl GREEK ACROPHONIC ATTIC FIVE STATERS
1015F ; 5.0 # Nl GREEK ACROPHONIC TROEZENIAN FIVE
10173 ; 5.0 # Nl GREEK ACROPHONIC DELPHIC FIVE MNAS
10321 ; 5.0 # No OLD ITALIC NUMERAL FIVE
104A5 ; 5.0 # Nd OSMANYA DIGIT FIVE
1D7D3 ; 5.0 # Nd MATHEMATICAL BOLD DIGIT FIVE
@ -438,7 +466,7 @@ FF15 ; 5.0 # Nd FULLWIDTH DIGIT FIVE
1D7F1 ; 5.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT FIVE
1D7FB ; 5.0 # Nd MATHEMATICAL MONOSPACE DIGIT FIVE
# Total code points: 46
# Total code points: 52
# ================================================
@ -464,11 +492,12 @@ FF15 ; 5.0 # Nd FULLWIDTH DIGIT FIVE
0ED6 ; 6.0 # Nd LAO DIGIT SIX
0F26 ; 6.0 # Nd TIBETAN DIGIT SIX
1046 ; 6.0 # Nd MYANMAR DIGIT SIX
136E ; 6.0 # Nd ETHIOPIC DIGIT SIX
136E ; 6.0 # No ETHIOPIC DIGIT SIX
17E6 ; 6.0 # Nd KHMER DIGIT SIX
17F6 ; 6.0 # No KHMER SYMBOL LEK ATTAK PRAM-MUOY
1816 ; 6.0 # Nd MONGOLIAN DIGIT SIX
194C ; 6.0 # Nd LIMBU DIGIT SIX
19D6 ; 6.0 # Nd NEW TAI LUE DIGIT SIX
2076 ; 6.0 # No SUPERSCRIPT SIX
2086 ; 6.0 # No SUBSCRIPT SIX
2165 ; 6.0 # Nl ROMAN NUMERAL SIX
@ -495,7 +524,7 @@ FF16 ; 6.0 # Nd FULLWIDTH DIGIT SIX
1D7F2 ; 6.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT SIX
1D7FC ; 6.0 # Nd MATHEMATICAL MONOSPACE DIGIT SIX
# Total code points: 46
# Total code points: 47
# ================================================
@ -521,11 +550,12 @@ FF16 ; 6.0 # Nd FULLWIDTH DIGIT SIX
0ED7 ; 7.0 # Nd LAO DIGIT SEVEN
0F27 ; 7.0 # Nd TIBETAN DIGIT SEVEN
1047 ; 7.0 # Nd MYANMAR DIGIT SEVEN
136F ; 7.0 # Nd ETHIOPIC DIGIT SEVEN
136F ; 7.0 # No ETHIOPIC DIGIT SEVEN
17E7 ; 7.0 # Nd KHMER DIGIT SEVEN
17F7 ; 7.0 # No KHMER SYMBOL LEK ATTAK PRAM-PII
1817 ; 7.0 # Nd MONGOLIAN DIGIT SEVEN
194D ; 7.0 # Nd LIMBU DIGIT SEVEN
19D7 ; 7.0 # Nd NEW TAI LUE DIGIT SEVEN
2077 ; 7.0 # No SUPERSCRIPT SEVEN
2087 ; 7.0 # No SUBSCRIPT SEVEN
2166 ; 7.0 # Nl ROMAN NUMERAL SEVEN
@ -551,7 +581,7 @@ FF17 ; 7.0 # Nd FULLWIDTH DIGIT SEVEN
1D7F3 ; 7.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT SEVEN
1D7FD ; 7.0 # Nd MATHEMATICAL MONOSPACE DIGIT SEVEN
# Total code points: 45
# Total code points: 46
# ================================================
@ -577,11 +607,12 @@ FF17 ; 7.0 # Nd FULLWIDTH DIGIT SEVEN
0ED8 ; 8.0 # Nd LAO DIGIT EIGHT
0F28 ; 8.0 # Nd TIBETAN DIGIT EIGHT
1048 ; 8.0 # Nd MYANMAR DIGIT EIGHT
1370 ; 8.0 # Nd ETHIOPIC DIGIT EIGHT
1370 ; 8.0 # No ETHIOPIC DIGIT EIGHT
17E8 ; 8.0 # Nd KHMER DIGIT EIGHT
17F8 ; 8.0 # No KHMER SYMBOL LEK ATTAK PRAM-BEI
1818 ; 8.0 # Nd MONGOLIAN DIGIT EIGHT
194E ; 8.0 # Nd LIMBU DIGIT EIGHT
19D8 ; 8.0 # Nd NEW TAI LUE DIGIT EIGHT
2078 ; 8.0 # No SUPERSCRIPT EIGHT
2088 ; 8.0 # No SUBSCRIPT EIGHT
2167 ; 8.0 # Nl ROMAN NUMERAL EIGHT
@ -607,7 +638,7 @@ FF18 ; 8.0 # Nd FULLWIDTH DIGIT EIGHT
1D7F4 ; 8.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT EIGHT
1D7FE ; 8.0 # Nd MATHEMATICAL MONOSPACE DIGIT EIGHT
# Total code points: 45
# Total code points: 46
# ================================================
@ -633,11 +664,12 @@ FF18 ; 8.0 # Nd FULLWIDTH DIGIT EIGHT
0ED9 ; 9.0 # Nd LAO DIGIT NINE
0F29 ; 9.0 # Nd TIBETAN DIGIT NINE
1049 ; 9.0 # Nd MYANMAR DIGIT NINE
1371 ; 9.0 # Nd ETHIOPIC DIGIT NINE
1371 ; 9.0 # No ETHIOPIC DIGIT NINE
17E9 ; 9.0 # Nd KHMER DIGIT NINE
17F9 ; 9.0 # No KHMER SYMBOL LEK ATTAK PRAM-BUON
1819 ; 9.0 # Nd MONGOLIAN DIGIT NINE
194F ; 9.0 # Nd LIMBU DIGIT NINE
19D9 ; 9.0 # Nd NEW TAI LUE DIGIT NINE
2079 ; 9.0 # No SUPERSCRIPT NINE
2089 ; 9.0 # No SUBSCRIPT NINE
2168 ; 9.0 # Nl ROMAN NUMERAL NINE
@ -663,7 +695,7 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
1D7F5 ; 9.0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT NINE
1D7FF ; 9.0 # Nd MATHEMATICAL MONOSPACE DIGIT NINE
# Total code points: 45
# Total code points: 46
# ================================================
@ -684,9 +716,15 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
5341 ; 10.0 # Lo CJK UNIFIED IDEOGRAPH-5341
62FE ; 10.0 # Lo CJK UNIFIED IDEOGRAPH-62FE
10110 ; 10.0 # No AEGEAN NUMBER TEN
10149 ; 10.0 # Nl GREEK ACROPHONIC ATTIC TEN TALENTS
10150 ; 10.0 # Nl GREEK ACROPHONIC ATTIC TEN STATERS
10157 ; 10.0 # Nl GREEK ACROPHONIC ATTIC TEN MNAS
10160..10164 ; 10.0 # Nl [5] GREEK ACROPHONIC TROEZENIAN TEN..GREEK ACROPHONIC THESPIAN TEN
10322 ; 10.0 # No OLD ITALIC NUMERAL TEN
103D3 ; 10.0 # Nl OLD PERSIAN NUMBER TEN
10A44 ; 10.0 # No KHAROSHTHI NUMBER TEN
# Total code points: 18
# Total code points: 28
# ================================================
@ -787,8 +825,10 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
3039 ; 20.0 # Nl HANGZHOU NUMERAL TWENTY
5EFF ; 20.0 # Lo CJK UNIFIED IDEOGRAPH-5EFF
10111 ; 20.0 # No AEGEAN NUMBER TWENTY
103D4 ; 20.0 # Nl OLD PERSIAN NUMBER TWENTY
10A45 ; 20.0 # No KHAROSHTHI NUMBER TWENTY
# Total code points: 8
# Total code points: 10
# ================================================
@ -851,8 +891,9 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
325A ; 30.0 # No CIRCLED NUMBER THIRTY
5345 ; 30.0 # Lo CJK UNIFIED IDEOGRAPH-5345
10112 ; 30.0 # No AEGEAN NUMBER THIRTY
10165 ; 30.0 # Nl GREEK ACROPHONIC THESPIAN THIRTY
# Total code points: 5
# Total code points: 6
# ================================================
@ -977,9 +1018,14 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
217C ; 50.0 # Nl SMALL ROMAN NUMERAL FIFTY
32BF ; 50.0 # No CIRCLED NUMBER FIFTY
10114 ; 50.0 # No AEGEAN NUMBER FIFTY
10144 ; 50.0 # Nl GREEK ACROPHONIC ATTIC FIFTY
1014A ; 50.0 # Nl GREEK ACROPHONIC ATTIC FIFTY TALENTS
10151 ; 50.0 # Nl GREEK ACROPHONIC ATTIC FIFTY STATERS
10166..10169 ; 50.0 # Nl [4] GREEK ACROPHONIC TROEZENIAN FIFTY..GREEK ACROPHONIC THESPIAN FIFTY
10174 ; 50.0 # Nl GREEK ACROPHONIC STRATIAN FIFTY MNAS
10323 ; 50.0 # No OLD ITALIC NUMERAL FIFTY
# Total code points: 6
# Total code points: 14
# ================================================
@ -1019,8 +1065,13 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
767E ; 100.0 # Lo CJK UNIFIED IDEOGRAPH-767E
964C ; 100.0 # Lo CJK UNIFIED IDEOGRAPH-964C
10119 ; 100.0 # No AEGEAN NUMBER ONE HUNDRED
1014B ; 100.0 # Nl GREEK ACROPHONIC ATTIC ONE HUNDRED TALENTS
10152 ; 100.0 # Nl GREEK ACROPHONIC ATTIC ONE HUNDRED STATERS
1016A ; 100.0 # Nl GREEK ACROPHONIC THESPIAN ONE HUNDRED
103D5 ; 100.0 # Nl OLD PERSIAN NUMBER HUNDRED
10A46 ; 100.0 # No KHAROSHTHI NUMBER ONE HUNDRED
# Total code points: 8
# Total code points: 13
# ================================================
@ -1031,8 +1082,9 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
# ================================================
1011B ; 300.0 # No AEGEAN NUMBER THREE HUNDRED
1016B ; 300.0 # Nl GREEK ACROPHONIC THESPIAN THREE HUNDRED
# Total code points: 1
# Total code points: 2
# ================================================
@ -1045,8 +1097,12 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
216E ; 500.0 # Nl ROMAN NUMERAL FIVE HUNDRED
217E ; 500.0 # Nl SMALL ROMAN NUMERAL FIVE HUNDRED
1011D ; 500.0 # No AEGEAN NUMBER FIVE HUNDRED
10145 ; 500.0 # Nl GREEK ACROPHONIC ATTIC FIVE HUNDRED
1014C ; 500.0 # Nl GREEK ACROPHONIC ATTIC FIVE HUNDRED TALENTS
10153 ; 500.0 # Nl GREEK ACROPHONIC ATTIC FIVE HUNDRED STATERS
1016C..10170 ; 500.0 # Nl [5] GREEK ACROPHONIC EPIDAUREAN FIVE HUNDRED..GREEK ACROPHONIC NAXIAN FIVE HUNDRED
# Total code points: 3
# Total code points: 11
# ================================================
@ -1080,8 +1136,12 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
4EDF ; 1000.0 # Lo CJK UNIFIED IDEOGRAPH-4EDF
5343 ; 1000.0 # Lo CJK UNIFIED IDEOGRAPH-5343
10122 ; 1000.0 # No AEGEAN NUMBER ONE THOUSAND
1014D ; 1000.0 # Nl GREEK ACROPHONIC ATTIC ONE THOUSAND TALENTS
10154 ; 1000.0 # Nl GREEK ACROPHONIC ATTIC ONE THOUSAND STATERS
10171 ; 1000.0 # Nl GREEK ACROPHONIC THESPIAN ONE THOUSAND
10A47 ; 1000.0 # No KHAROSHTHI NUMBER ONE THOUSAND
# Total code points: 7
# Total code points: 11
# ================================================
@ -1105,8 +1165,11 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
2181 ; 5000.0 # Nl ROMAN NUMERAL FIVE THOUSAND
10126 ; 5000.0 # No AEGEAN NUMBER FIVE THOUSAND
10146 ; 5000.0 # Nl GREEK ACROPHONIC ATTIC FIVE THOUSAND
1014E ; 5000.0 # Nl GREEK ACROPHONIC ATTIC FIVE THOUSAND TALENTS
10172 ; 5000.0 # Nl GREEK ACROPHONIC THESPIAN FIVE THOUSAND
# Total code points: 2
# Total code points: 5
# ================================================
@ -1139,8 +1202,9 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
4E07 ; 10000.0 # Lo CJK UNIFIED IDEOGRAPH-4E07
842C ; 10000.0 # Lo CJK UNIFIED IDEOGRAPH-842C
1012B ; 10000.0 # No AEGEAN NUMBER TEN THOUSAND
10155 ; 10000.0 # Nl GREEK ACROPHONIC ATTIC TEN THOUSAND STATERS
# Total code points: 5
# Total code points: 6
# ================================================
@ -1163,8 +1227,10 @@ FF19 ; 9.0 # Nd FULLWIDTH DIGIT NINE
# ================================================
1012F ; 50000.0 # No AEGEAN NUMBER FIFTY THOUSAND
10147 ; 50000.0 # Nl GREEK ACROPHONIC ATTIC FIFTY THOUSAND
10156 ; 50000.0 # Nl GREEK ACROPHONIC ATTIC FIFTY THOUSAND STATERS
# Total code points: 1
# Total code points: 3
# ================================================

144
icu4c/source/data/unidata/EastAsianWidth.txt
View File

@ -1,12 +1,12 @@
# EastAsianWidth-4.0.0.txt
# EastAsianWidth-4.1.0.txt
#
# East Asian Width Properties
#
# This file is a supplement to the UnicodeData.txt file.
# It contains informative data only.
# The format is two fields separated by a semicolon.
# Field 1: Unicode value
# Field 2: East Asian Width property, consisting of one of the following values:
# Field 0: Unicode value
# Field 1: East Asian Width property, consisting of one of the following values:
# "N", "A", "H", "W", "F", "Na"
# - All code points, assigned or unassigned, that are not listed
# explicitly are given the value "N".
@ -16,7 +16,7 @@
# The Unicode name of each character is provided in a comment for help
# in identifying the characters.
#
# See UTR #11: East Asian Character Width, for more information
# See UAX #11: East Asian Character Width, for more information.
0000..001F;N
0020..007E;Na
007F..00A0;N
@ -106,7 +106,7 @@
01DA;A
01DB;N
01DC;A
01DD..0236;N
01DD..0241;N
0250;N
0251;A
0252..0260;N
@ -128,8 +128,7 @@
02DE;N
02DF;A
02E0..02FF;N
0300..0357;A
035D..036F;A
0300..036F;A
0374..0375;N
037A;N
037E;N
@ -143,8 +142,7 @@
03C2;N
03C3..03C9;A
03CA..03CE;N
03D0..03FB;N
0400;N
03D0..0400;N
0401;A
0402..040F;N
0410..044F;A
@ -152,32 +150,30 @@
0451;A
0452..0486;N
0488..04CE;N
04D0..04F5;N
04F8..04F9;N
04D0..04F9;N
0500..050F;N
0531..0556;N
0559..055F;N
0561..0587;N
0589..058A;N
0591..05A1;N
05A3..05B9;N
05BB..05C4;N
0591..05C6;N
05D0..05EA;N
05F0..05F4;N
0600..0603;N
060C..0615;N
060B..0615;N
061B;N
061F;N
061E..061F;N
0621..063A;N
0640..0658;N
0640..065E;N
0660..070D;N
070F..074A;N
074D..074F;N
074D..076D;N
0780..07B1;N
0901..0939;N
093C..094D;N
0950..0954;N
0958..0970;N
097D;N
0981..0983;N
0985..098C;N
098F..0990;N
@ -187,7 +183,7 @@
09B6..09B9;N
09BC..09C4;N
09C7..09C8;N
09CB..09CD;N
09CB..09CE;N
09D7;N
09DC..09DD;N
09DF..09E3;N
@ -244,13 +240,12 @@
0B9E..0B9F;N
0BA3..0BA4;N
0BA8..0BAA;N
0BAE..0BB5;N
0BB7..0BB9;N
0BAE..0BB9;N
0BBE..0BC2;N
0BC6..0BC8;N
0BCA..0BCD;N
0BD7;N
0BE7..0BFA;N
0BE6..0BFA;N
0C01..0C03;N
0C05..0C0C;N
0C0E..0C10;N
@ -324,7 +319,7 @@
0F90..0F97;N
0F99..0FBC;N
0FBE..0FCC;N
0FCF;N
0FCF..0FD1;N
1000..1021;N
1023..1027;N
1029..102A;N
@ -332,38 +327,29 @@
1036..1039;N
1040..1059;N
10A0..10C5;N
10D0..10F8;N
10FB;N
10D0..10FC;N
1100..1159;W
115F;W
1160..11A2;N
11A8..11F9;N
1200..1206;N
1208..1246;N
1248;N
1200..1248;N
124A..124D;N
1250..1256;N
1258;N
125A..125D;N
1260..1286;N
1288;N
1260..1288;N
128A..128D;N
1290..12AE;N
12B0;N
1290..12B0;N
12B2..12B5;N
12B8..12BE;N
12C0;N
12C2..12C5;N
12C8..12CE;N
12D0..12D6;N
12D8..12EE;N
12F0..130E;N
1310;N
12C8..12D6;N
12D8..1310;N
1312..1315;N
1318..131E;N
1320..1346;N
1348..135A;N
1361..137C;N
1318..135A;N
135F..137C;N
1380..1399;N
13A0..13F4;N
1401..1676;N
1680..169C;N
@ -388,8 +374,12 @@
1940;N
1944..196D;N
1970..1974;N
19E0..19FF;N
1D00..1D6B;N
1980..19A9;N
19B0..19C9;N
19D0..19D9;N
19DE..1A1B;N
1A1E..1A1F;N
1D00..1DC3;N
1E00..1E9B;N
1EA0..1EF9;N
1F00..1F15;N
@ -430,9 +420,7 @@
203B;A
203C..203D;N
203E;A
203F..2054;N
2057;N
205F..2063;N
203F..2063;N
206A..2071;N
2074;A
2075..207E;N
@ -440,12 +428,13 @@
2080;N
2081..2084;A
2085..208E;N
2090..2094;N
20A0..20A8;N
20A9;H
20AA..20AB;N
20AC;A
20AD..20B1;N
20D0..20EA;N
20AD..20B5;N
20D0..20EB;N
2100..2102;N
2103;A
2104;N
@ -462,8 +451,7 @@
2126;A
2127..212A;N
212B;A
212C..213B;N
213D..214B;N
212C..214C;N
2153..2154;A
2155..215A;N
215B..215E;A
@ -541,7 +529,7 @@
2312;A
2313..2328;N
2329..232A;W
232B..23D0;N
232B..23DB;N
2400..2426;N
2440..244A;N
2460..24E9;A
@ -583,8 +571,7 @@
260E..260F;A
2610..2613;N
2614..2615;A
2616..2617;N
2619..261B;N
2616..261B;N
261C;A
261D;N
261E;A
@ -602,9 +589,8 @@
266C..266D;A
266E;N
266F;A
2670..267D;N
2680..2691;N
26A0..26A1;N
2670..269C;N
26A0..26B1;N
2701..2704;N
2706..2709;N
270C..2727;N
@ -620,11 +606,29 @@
2780..2794;N
2798..27AF;N
27B1..27BE;N
27C0..27C6;N
27D0..27E5;N
27E6..27EB;Na
27F0..2984;N
2985..2986;Na
2987..2B0D;N
2987..2B13;N
2C00..2C2E;N
2C30..2C5E;N
2C80..2CEA;N
2CF9..2D25;N
2D30..2D65;N
2D6F;N
2D80..2D96;N
2DA0..2DA6;N
2DA8..2DAE;N
2DB0..2DB6;N
2DB8..2DBE;N
2DC0..2DC6;N
2DC8..2DCE;N
2DD0..2DD6;N
2DD8..2DDE;N
2E00..2E17;N
2E1C..2E1D;N
2E80..2E99;W
2E9B..2EF3;W
2F00..2FD5;W
@ -637,16 +641,18 @@
3105..312C;W
3131..318E;W
3190..31B7;W
31C0..31CF;W
31F0..321E;W
3220..3243;W
3250..327D;W
327F..32FE;W
3250..32FE;W
3300..33FF;W
3400..4DB5;W
4DC0..4DFF;N
4E00..9FA5;W
4E00..9FBB;W
A000..A48C;W
A490..A4C6;W
A700..A716;N
A800..A82B;N
AC00..D7A3;W
D800..DB7F;N
DB80..DBFF;N
@ -654,6 +660,7 @@ DC00..DFFF;N
E000..F8FF;A
F900..FA2D;W
FA30..FA6A;W
FA70..FAD9;W
FB00..FB06;N
FB13..FB17;N
FB1D..FB36;N
@ -667,6 +674,7 @@ FD50..FD8F;N
FD92..FDC7;N
FDF0..FDFD;N
FE00..FE0F;A
FE10..FE19;W
FE20..FE23;N
FE30..FE52;W
FE54..FE66;W
@ -693,12 +701,13 @@ FFFD;A
10080..100FA;N
10100..10102;N
10107..10133;N
10137..1013F;N
10137..1018A;N
10300..1031E;N
10320..10323;N
10330..1034A;N
10380..1039D;N
1039F;N
1039F..103C3;N
103C8..103D5;N
10400..1049D;N
104A0..104A9;N
10800..10805;N
@ -707,9 +716,18 @@ FFFD;A
10837..10838;N
1083C;N
1083F;N
10A00..10A03;N
10A05..10A06;N
10A0C..10A13;N
10A15..10A17;N
10A19..10A33;N
10A38..10A3A;N
10A3F..10A47;N
10A50..10A58;N
1D000..1D0F5;N
1D100..1D126;N
1D12A..1D1DD;N
1D200..1D245;N
1D300..1D356;N
1D400..1D454;N
1D456..1D49C;N
@ -729,7 +747,7 @@ FFFD;A
1D540..1D544;N
1D546;N
1D54A..1D550;N
1D552..1D6A3;N
1D552..1D6A5;N
1D6A8..1D7C9;N
1D7CE..1D7FF;N
20000..2A6D6;W

1025
icu4c/source/data/unidata/GraphemeBreakProperty.txt Normal file
View File

File diff suppressed because it is too large Load Diff

1000
icu4c/source/data/unidata/LineBreak.txt
View File

File diff suppressed because it is too large Load Diff

427
icu4c/source/data/unidata/NormalizationTest.txt
View File

@ -1,5 +1,5 @@
# NormalizationTest-4.0.0.txt
# Date: 2003-02-25,23:12:31 GMT [MD]
# NormalizationTest-4.1.0.txt
# Date: 2004-12-14, 02:28:42 GMT [MD]
#
# Normalization Test Suite
# Format:
@ -540,6 +540,7 @@
0FAC;0FAB 0FB7;0FAB 0FB7;0FAB 0FB7;0FAB 0FB7;
0FB9;0F90 0FB5;0F90 0FB5;0F90 0FB5;0F90 0FB5;
1026;1026;1025 102E;1026;1025 102E;
10FC;10FC;10FC;10DC;10DC;
1D2C;1D2C;1D2C;0041;0041;
1D2D;1D2D;1D2D;00C6;00C6;
1D2E;1D2E;1D2E;0042;0042;
@ -600,6 +601,44 @@
1D68;1D68;1D68;03C1;03C1;
1D69;1D69;1D69;03C6;03C6;
1D6A;1D6A;1D6A;03C7;03C7;
1D78;1D78;1D78;043D;043D;
1D9B;1D9B;1D9B;0252;0252;
1D9C;1D9C;1D9C;0063;0063;
1D9D;1D9D;1D9D;0255;0255;
1D9E;1D9E;1D9E;00F0;00F0;
1D9F;1D9F;1D9F;025C;025C;
1DA0;1DA0;1DA0;0066;0066;
1DA1;1DA1;1DA1;025F;025F;
1DA2;1DA2;1DA2;0261;0261;
1DA3;1DA3;1DA3;0265;0265;
1DA4;1DA4;1DA4;0268;0268;
1DA5;1DA5;1DA5;0269;0269;
1DA6;1DA6;1DA6;026A;026A;
1DA7;1DA7;1DA7;1D7B;1D7B;
1DA8;1DA8;1DA8;029D;029D;
1DA9;1DA9;1DA9;026D;026D;
1DAA;1DAA;1DAA;1D85;1D85;
1DAB;1DAB;1DAB;029F;029F;
1DAC;1DAC;1DAC;0271;0271;
1DAD;1DAD;1DAD;0270;0270;
1DAE;1DAE;1DAE;0272;0272;
1DAF;1DAF;1DAF;0273;0273;
1DB0;1DB0;1DB0;0274;0274;
1DB1;1DB1;1DB1;0275;0275;
1DB2;1DB2;1DB2;0278;0278;
1DB3;1DB3;1DB3;0282;0282;
1DB4;1DB4;1DB4;0283;0283;
1DB5;1DB5;1DB5;01AB;01AB;
1DB6;1DB6;1DB6;0289;0289;
1DB7;1DB7;1DB7;028A;028A;
1DB8;1DB8;1DB8;1D1C;1D1C;
1DB9;1DB9;1DB9;028B;028B;
1DBA;1DBA;1DBA;028C;028C;
1DBB;1DBB;1DBB;007A;007A;
1DBC;1DBC;1DBC;0290;0290;
1DBD;1DBD;1DBD;0291;0291;
1DBE;1DBE;1DBE;0292;0292;
1DBF;1DBF;1DBF;03B8;03B8;
1E00;1E00;0041 0325;1E00;0041 0325;
1E01;1E01;0061 0325;1E01;0061 0325;
1E02;1E02;0042 0307;1E02;0042 0307;
@ -1136,6 +1175,11 @@
208C;208C;208C;003D;003D;
208D;208D;208D;0028;0028;
208E;208E;208E;0029;0029;
2090;2090;2090;0061;0061;
2091;2091;2091;0065;0065;
2092;2092;2092;006F;006F;
2093;2093;2093;0078;0078;
2094;2094;2094;0259;0259;
20A8;20A8;20A8;0052 0073;0052 0073;
2100;2100;2100;0061 002F 0063;0061 002F 0063;
2101;2101;2101;0061 002F 0073;0061 002F 0073;
@ -1183,6 +1227,7 @@
2138;2138;2138;05D3;05D3;
2139;2139;2139;0069;0069;
213B;213B;213B;0046 0041 0058;0046 0041 0058;
213C;213C;213C;03C0;03C0;
213D;213D;213D;03B3;03B3;
213E;213E;213E;0393;0393;
213F;213F;213F;03A0;03A0;
@ -1431,6 +1476,7 @@
2A75;2A75;2A75;003D 003D;003D 003D;
2A76;2A76;2A76;003D 003D 003D;003D 003D 003D;
2ADC;2ADD 0338;2ADD 0338;2ADD 0338;2ADD 0338;
2D6F;2D6F;2D6F;2D61;2D61;
2E9F;2E9F;2E9F;6BCD;6BCD;
2EF3;2EF3;2EF3;9F9F;9F9F;
2F00;2F00;2F00;4E00;4E00;
@ -1935,6 +1981,7 @@
327B;327B;327B;D558;1112 1161;
327C;327C;327C;CC38 ACE0;110E 1161 11B7 1100 1169;
327D;327D;327D;C8FC C758;110C 116E 110B 1174;
327E;327E;327E;C6B0;110B 116E;
3280;3280;3280;4E00;4E00;
3281;3281;3281;4E8C;4E8C;
3282;3282;3282;4E09;4E09;
@ -13839,6 +13886,112 @@ FA67;9038;9038;9038;9038;
FA68;96E3;96E3;96E3;96E3;
FA69;97FF;97FF;97FF;97FF;
FA6A;983B;983B;983B;983B;
FA70;4E26;4E26;4E26;4E26;
FA71;51B5;51B5;51B5;51B5;
FA72;5168;5168;5168;5168;
FA73;4F80;4F80;4F80;4F80;
FA74;5145;5145;5145;5145;
FA75;5180;5180;5180;5180;
FA76;52C7;52C7;52C7;52C7;
FA77;52FA;52FA;52FA;52FA;
FA78;559D;559D;559D;559D;
FA79;5555;5555;5555;5555;
FA7A;5599;5599;5599;5599;
FA7B;55E2;55E2;55E2;55E2;
FA7C;585A;585A;585A;585A;
FA7D;58B3;58B3;58B3;58B3;
FA7E;5944;5944;5944;5944;
FA7F;5954;5954;5954;5954;
FA80;5A62;5A62;5A62;5A62;
FA81;5B28;5B28;5B28;5B28;
FA82;5ED2;5ED2;5ED2;5ED2;
FA83;5ED9;5ED9;5ED9;5ED9;
FA84;5F69;5F69;5F69;5F69;
FA85;5FAD;5FAD;5FAD;5FAD;
FA86;60D8;60D8;60D8;60D8;
FA87;614E;614E;614E;614E;
FA88;6108;6108;6108;6108;
FA89;618E;618E;618E;618E;
FA8A;6160;6160;6160;6160;
FA8B;61F2;61F2;61F2;61F2;
FA8C;6234;6234;6234;6234;
FA8D;63C4;63C4;63C4;63C4;
FA8E;641C;641C;641C;641C;
FA8F;6452;6452;6452;6452;
FA90;6556;6556;6556;6556;
FA91;6674;6674;6674;6674;
FA92;6717;6717;6717;6717;
FA93;671B;671B;671B;671B;
FA94;6756;6756;6756;6756;
FA95;6B79;6B79;6B79;6B79;
FA96;6BBA;6BBA;6BBA;6BBA;
FA97;6D41;6D41;6D41;6D41;
FA98;6EDB;6EDB;6EDB;6EDB;
FA99;6ECB;6ECB;6ECB;6ECB;
FA9A;6F22;6F22;6F22;6F22;
FA9B;701E;701E;701E;701E;
FA9C;716E;716E;716E;716E;
FA9D;77A7;77A7;77A7;77A7;
FA9E;7235;7235;7235;7235;
FA9F;72AF;72AF;72AF;72AF;
FAA0;732A;732A;732A;732A;
FAA1;7471;7471;7471;7471;
FAA2;7506;7506;7506;7506;
FAA3;753B;753B;753B;753B;
FAA4;761D;761D;761D;761D;
FAA5;761F;761F;761F;761F;
FAA6;76CA;76CA;76CA;76CA;
FAA7;76DB;76DB;76DB;76DB;
FAA8;76F4;76F4;76F4;76F4;
FAA9;774A;774A;774A;774A;
FAAA;7740;7740;7740;7740;
FAAB;78CC;78CC;78CC;78CC;
FAAC;7AB1;7AB1;7AB1;7AB1;
FAAD;7BC0;7BC0;7BC0;7BC0;
FAAE;7C7B;7C7B;7C7B;7C7B;
FAAF;7D5B;7D5B;7D5B;7D5B;
FAB0;7DF4;7DF4;7DF4;7DF4;
FAB1;7F3E;7F3E;7F3E;7F3E;
FAB2;8005;8005;8005;8005;
FAB3;8352;8352;8352;8352;
FAB4;83EF;83EF;83EF;83EF;
FAB5;8779;8779;8779;8779;
FAB6;8941;8941;8941;8941;
FAB7;8986;8986;8986;8986;
FAB8;8996;8996;8996;8996;
FAB9;8ABF;8ABF;8ABF;8ABF;
FABA;8AF8;8AF8;8AF8;8AF8;
FABB;8ACB;8ACB;8ACB;8ACB;
FABC;8B01;8B01;8B01;8B01;
FABD;8AFE;8AFE;8AFE;8AFE;
FABE;8AED;8AED;8AED;8AED;
FABF;8BE9;8BE9;8BE9;8BE9;
FAC0;8B8A;8B8A;8B8A;8B8A;
FAC1;8D08;8D08;8D08;8D08;
FAC2;8F38;8F38;8F38;8F38;
FAC3;9072;9072;9072;9072;
FAC4;9199;9199;9199;9199;
FAC5;9276;9276;9276;9276;
FAC6;967C;967C;967C;967C;
FAC7;96E3;96E3;96E3;96E3;
FAC8;9756;9756;9756;9756;
FAC9;97DB;97DB;97DB;97DB;
FACA;97FF;97FF;97FF;97FF;
FACB;980B;980B;980B;980B;
FACC;983B;983B;983B;983B;
FACD;9B12;9B12;9B12;9B12;
FACE;9F9C;9F9C;9F9C;9F9C;
FACF;2284A;2284A;2284A;2284A;
FAD0;22844;22844;22844;22844;
FAD1;233D5;233D5;233D5;233D5;
FAD2;3B9D;3B9D;3B9D;3B9D;
FAD3;4018;4018;4018;4018;
FAD4;4039;4039;4039;4039;
FAD5;25249;25249;25249;25249;
FAD6;25CD0;25CD0;25CD0;25CD0;
FAD7;27ED3;27ED3;27ED3;27ED3;
FAD8;9F43;9F43;9F43;9F43;
FAD9;9F8E;9F8E;9F8E;9F8E;
FB00;FB00;FB00;0066 0066;0066 0066;
FB01;FB01;FB01;0066 0069;0066 0069;
FB02;FB02;FB02;0066 006C;0066 006C;
@ -14488,6 +14641,16 @@ FDF9;FDF9;FDF9;0635 0644 0649;0635 0644 0649;
FDFA;FDFA;FDFA;0635 0644 0649 0020 0627 0644 0644 0647 0020 0639 0644 064A 0647 0020 0648 0633 0644 0645;0635 0644 0649 0020 0627 0644 0644 0647 0020 0639 0644 064A 0647 0020 0648 0633 0644 0645;
FDFB;FDFB;FDFB;062C 0644 0020 062C 0644 0627 0644 0647;062C 0644 0020 062C 0644 0627 0644 0647;
FDFC;FDFC;FDFC;0631 06CC 0627 0644;0631 06CC 0627 0644;
FE10;FE10;FE10;002C;002C;
FE11;FE11;FE11;3001;3001;
FE12;FE12;FE12;3002;3002;
FE13;FE13;FE13;003A;003A;
FE14;FE14;FE14;003B;003B;
FE15;FE15;FE15;0021;0021;
FE16;FE16;FE16;003F;003F;
FE17;FE17;FE17;3016;3016;
FE18;FE18;FE18;3017;3017;
FE19;FE19;FE19;002E 002E 002E;002E 002E 002E;
FE30;FE30;FE30;002E 002E;002E 002E;
FE31;FE31;FE31;2014;2014;
FE32;FE32;FE32;2013;2013;
@ -15573,6 +15736,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
1D6A1;1D6A1;1D6A1;0078;0078;
1D6A2;1D6A2;1D6A2;0079;0079;
1D6A3;1D6A3;1D6A3;007A;007A;
1D6A4;1D6A4;1D6A4;0131;0131;
1D6A5;1D6A5;1D6A5;0237;0237;
1D6A8;1D6A8;1D6A8;0391;0391;
1D6A9;1D6A9;1D6A9;0392;0392;
1D6AA;1D6AA;1D6AA;0393;0393;
@ -16500,8 +16665,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 0313 0315 0300 05AE 0062;0061 05AE 0313 0300 0315 0062;0061 05AE 0313 0300 0315 0062;0061 05AE 0313 0300 0315 0062;0061 05AE 0313 0300 0315 0062;
0061 0315 0300 05AE 0314 0062;00E0 05AE 0314 0315 0062;0061 05AE 0300 0314 0315 0062;00E0 05AE 0314 0315 0062;0061 05AE 0300 0314 0315 0062;
0061 0314 0315 0300 05AE 0062;0061 05AE 0314 0300 0315 0062;0061 05AE 0314 0300 0315 0062;0061 05AE 0314 0300 0315 0062;0061 05AE 0314 0300 0315 0062;
0061 035F 0315 0300 0315 0062;00E0 0315 0315 035F 0062;0061 0300 0315 0315 035F 0062;00E0 0315 0315 035F 0062;0061 0300 0315 0315 035F 0062;
0061 0315 035F 0315 0300 0062;00E0 0315 0315 035F 0062;0061 0300 0315 0315 035F 0062;00E0 0315 0315 035F 0062;0061 0300 0315 0315 035F 0062;
0061 035C 0315 0300 0315 0062;00E0 0315 0315 035C 0062;0061 0300 0315 0315 035C 0062;00E0 0315 0315 035C 0062;0061 0300 0315 0315 035C 0062;
0061 0315 035C 0315 0300 0062;00E0 0315 0315 035C 0062;0061 0300 0315 0315 035C 0062;00E0 0315 0315 035C 0062;0061 0300 0315 0315 035C 0062;
0061 059A 0316 302A 0316 0062;0061 302A 0316 0316 059A 0062;0061 302A 0316 0316 059A 0062;0061 302A 0316 0316 059A 0062;0061 302A 0316 0316 059A 0062;
0061 0316 059A 0316 302A 0062;0061 302A 0316 0316 059A 0062;0061 302A 0316 0316 059A 0062;0061 302A 0316 0316 059A 0062;0061 302A 0316 0316 059A 0062;
0061 059A 0316 302A 0317 0062;0061 302A 0316 0317 059A 0062;0061 302A 0316 0317 059A 0062;0061 302A 0316 0317 059A 0062;0061 302A 0316 0317 059A 0062;
@ -16510,8 +16675,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 0318 059A 0316 302A 0062;0061 302A 0318 0316 059A 0062;0061 302A 0318 0316 059A 0062;0061 302A 0318 0316 059A 0062;0061 302A 0318 0316 059A 0062;
0061 059A 0316 302A 0319 0062;0061 302A 0316 0319 059A 0062;0061 302A 0316 0319 059A 0062;0061 302A 0316 0319 059A 0062;0061 302A 0316 0319 059A 0062;
0061 0319 059A 0316 302A 0062;0061 302A 0319 0316 059A 0062;0061 302A 0319 0316 059A 0062;0061 302A 0319 0316 059A 0062;0061 302A 0319 0316 059A 0062;
0061 035F 0315 0300 031A 0062;00E0 0315 031A 035F 0062;0061 0300 0315 031A 035F 0062;00E0 0315 031A 035F 0062;0061 0300 0315 031A 035F 0062;
0061 031A 035F 0315 0300 0062;00E0 031A 0315 035F 0062;0061 0300 031A 0315 035F 0062;00E0 031A 0315 035F 0062;0061 0300 031A 0315 035F 0062;
0061 035C 0315 0300 031A 0062;00E0 0315 031A 035C 0062;0061 0300 0315 031A 035C 0062;00E0 0315 031A 035C 0062;0061 0300 0315 031A 035C 0062;
0061 031A 035C 0315 0300 0062;00E0 031A 0315 035C 0062;0061 0300 031A 0315 035C 0062;00E0 031A 0315 035C 0062;0061 0300 031A 0315 035C 0062;
0061 302A 031B 0321 031B 0062;0061 0321 031B 031B 302A 0062;0061 0321 031B 031B 302A 0062;0061 0321 031B 031B 302A 0062;0061 0321 031B 031B 302A 0062;
0061 031B 302A 031B 0321 0062;0061 0321 031B 031B 302A 0062;0061 0321 031B 031B 302A 0062;0061 0321 031B 031B 302A 0062;0061 0321 031B 031B 302A 0062;
0061 059A 0316 302A 031C 0062;0061 302A 0316 031C 059A 0062;0061 302A 0316 031C 059A 0062;0061 302A 0316 031C 059A 0062;0061 302A 0316 031C 059A 0062;
@ -16632,18 +16797,28 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 0356 059A 0316 302A 0062;0061 302A 0356 0316 059A 0062;0061 302A 0356 0316 059A 0062;0061 302A 0356 0316 059A 0062;0061 302A 0356 0316 059A 0062;
0061 0315 0300 05AE 0357 0062;00E0 05AE 0357 0315 0062;0061 05AE 0300 0357 0315 0062;00E0 05AE 0357 0315 0062;0061 05AE 0300 0357 0315 0062;
0061 0357 0315 0300 05AE 0062;0061 05AE 0357 0300 0315 0062;0061 05AE 0357 0300 0315 0062;0061 05AE 0357 0300 0315 0062;0061 05AE 0357 0300 0315 0062;
0061 0345 035D 035F 035D 0062;0061 035F 035D 035D 0345 0062;0061 035F 035D 035D 0345 0062;0061 035F 035D 035D 0345 0062;0061 035F 035D 035D 0345 0062;
0061 035D 0345 035D 035F 0062;0061 035F 035D 035D 0345 0062;0061 035F 035D 035D 0345 0062;0061 035F 035D 035D 0345 0062;0061 035F 035D 035D 0345 0062;
0061 0345 035D 035F 035E 0062;0061 035F 035D 035E 0345 0062;0061 035F 035D 035E 0345 0062;0061 035F 035D 035E 0345 0062;0061 035F 035D 035E 0345 0062;
0061 035E 0345 035D 035F 0062;0061 035F 035E 035D 0345 0062;0061 035F 035E 035D 0345 0062;0061 035F 035E 035D 0345 0062;0061 035F 035E 035D 0345 0062;
0061 035D 035F 0315 035F 0062;0061 0315 035F 035F 035D 0062;0061 0315 035F 035F 035D 0062;0061 0315 035F 035F 035D 0062;0061 0315 035F 035F 035D 0062;
0061 035F 035D 035F 0315 0062;0061 0315 035F 035F 035D 0062;0061 0315 035F 035F 035D 0062;0061 0315 035F 035F 035D 0062;0061 0315 035F 035F 035D 0062;
0061 0345 035D 035F 0360 0062;0061 035F 035D 0360 0345 0062;0061 035F 035D 0360 0345 0062;0061 035F 035D 0360 0345 0062;0061 035F 035D 0360 0345 0062;
0061 0360 0345 035D 035F 0062;0061 035F 0360 035D 0345 0062;0061 035F 0360 035D 0345 0062;0061 035F 0360 035D 0345 0062;0061 035F 0360 035D 0345 0062;
0061 0345 035D 035F 0361 0062;0061 035F 035D 0361 0345 0062;0061 035F 035D 0361 0345 0062;0061 035F 035D 0361 0345 0062;0061 035F 035D 0361 0345 0062;
0061 0361 0345 035D 035F 0062;0061 035F 0361 035D 0345 0062;0061 035F 0361 035D 0345 0062;0061 035F 0361 035D 0345 0062;0061 035F 0361 035D 0345 0062;
0061 035D 035F 0315 0362 0062;0061 0315 035F 0362 035D 0062;0061 0315 035F 0362 035D 0062;0061 0315 035F 0362 035D 0062;0061 0315 035F 0362 035D 0062;
0061 0362 035D 035F 0315 0062;0061 0315 0362 035F 035D 0062;0061 0315 0362 035F 035D 0062;0061 0315 0362 035F 035D 0062;0061 0315 0362 035F 035D 0062;
0061 035C 0315 0300 0358 0062;00E0 0315 0358 035C 0062;0061 0300 0315 0358 035C 0062;00E0 0315 0358 035C 0062;0061 0300 0315 0358 035C 0062;
0061 0358 035C 0315 0300 0062;00E0 0358 0315 035C 0062;0061 0300 0358 0315 035C 0062;00E0 0358 0315 035C 0062;0061 0300 0358 0315 035C 0062;
0061 059A 0316 302A 0359 0062;0061 302A 0316 0359 059A 0062;0061 302A 0316 0359 059A 0062;0061 302A 0316 0359 059A 0062;0061 302A 0316 0359 059A 0062;
0061 0359 059A 0316 302A 0062;0061 302A 0359 0316 059A 0062;0061 302A 0359 0316 059A 0062;0061 302A 0359 0316 059A 0062;0061 302A 0359 0316 059A 0062;
0061 059A 0316 302A 035A 0062;0061 302A 0316 035A 059A 0062;0061 302A 0316 035A 059A 0062;0061 302A 0316 035A 059A 0062;0061 302A 0316 035A 059A 0062;
0061 035A 059A 0316 302A 0062;0061 302A 035A 0316 059A 0062;0061 302A 035A 0316 059A 0062;0061 302A 035A 0316 059A 0062;0061 302A 035A 0316 059A 0062;
0061 0315 0300 05AE 035B 0062;00E0 05AE 035B 0315 0062;0061 05AE 0300 035B 0315 0062;00E0 05AE 035B 0315 0062;0061 05AE 0300 035B 0315 0062;
0061 035B 0315 0300 05AE 0062;0061 05AE 035B 0300 0315 0062;0061 05AE 035B 0300 0315 0062;0061 05AE 035B 0300 0315 0062;0061 05AE 035B 0300 0315 0062;
0061 035D 035C 0315 035C 0062;0061 0315 035C 035C 035D 0062;0061 0315 035C 035C 035D 0062;0061 0315 035C 035C 035D 0062;0061 0315 035C 035C 035D 0062;
0061 035C 035D 035C 0315 0062;0061 0315 035C 035C 035D 0062;0061 0315 035C 035C 035D 0062;0061 0315 035C 035C 035D 0062;0061 0315 035C 035C 035D 0062;
0061 0345 035D 035C 035D 0062;0061 035C 035D 035D 0345 0062;0061 035C 035D 035D 0345 0062;0061 035C 035D 035D 0345 0062;0061 035C 035D 035D 0345 0062;
0061 035D 0345 035D 035C 0062;0061 035C 035D 035D 0345 0062;0061 035C 035D 035D 0345 0062;0061 035C 035D 035D 0345 0062;0061 035C 035D 035D 0345 0062;
0061 0345 035D 035C 035E 0062;0061 035C 035D 035E 0345 0062;0061 035C 035D 035E 0345 0062;0061 035C 035D 035E 0345 0062;0061 035C 035D 035E 0345 0062;
0061 035E 0345 035D 035C 0062;0061 035C 035E 035D 0345 0062;0061 035C 035E 035D 0345 0062;0061 035C 035E 035D 0345 0062;0061 035C 035E 035D 0345 0062;
0061 035D 035C 0315 035F 0062;0061 0315 035C 035F 035D 0062;0061 0315 035C 035F 035D 0062;0061 0315 035C 035F 035D 0062;0061 0315 035C 035F 035D 0062;
0061 035F 035D 035C 0315 0062;0061 0315 035F 035C 035D 0062;0061 0315 035F 035C 035D 0062;0061 0315 035F 035C 035D 0062;0061 0315 035F 035C 035D 0062;
0061 0345 035D 035C 0360 0062;0061 035C 035D 0360 0345 0062;0061 035C 035D 0360 0345 0062;0061 035C 035D 0360 0345 0062;0061 035C 035D 0360 0345 0062;
0061 0360 0345 035D 035C 0062;0061 035C 0360 035D 0345 0062;0061 035C 0360 035D 0345 0062;0061 035C 0360 035D 0345 0062;0061 035C 0360 035D 0345 0062;
0061 0345 035D 035C 0361 0062;0061 035C 035D 0361 0345 0062;0061 035C 035D 0361 0345 0062;0061 035C 035D 0361 0345 0062;0061 035C 035D 0361 0345 0062;
0061 0361 0345 035D 035C 0062;0061 035C 0361 035D 0345 0062;0061 035C 0361 035D 0345 0062;0061 035C 0361 035D 0345 0062;0061 035C 0361 035D 0345 0062;
0061 035D 035C 0315 0362 0062;0061 0315 035C 0362 035D 0062;0061 0315 035C 0362 035D 0062;0061 0315 035C 0362 035D 0062;0061 0315 035C 0362 035D 0062;
0061 0362 035D 035C 0315 0062;0061 0315 0362 035C 035D 0062;0061 0315 0362 035C 035D 0062;0061 0315 0362 035C 035D 0062;0061 0315 0362 035C 035D 0062;
0061 0315 0300 05AE 0363 0062;00E0 05AE 0363 0315 0062;0061 05AE 0300 0363 0315 0062;00E0 05AE 0363 0315 0062;0061 05AE 0300 0363 0315 0062;
0061 0363 0315 0300 05AE 0062;0061 05AE 0363 0300 0315 0062;0061 05AE 0363 0300 0315 0062;0061 05AE 0363 0300 0315 0062;0061 05AE 0363 0300 0315 0062;
0061 0315 0300 05AE 0364 0062;00E0 05AE 0364 0315 0062;0061 05AE 0300 0364 0315 0062;00E0 05AE 0364 0315 0062;0061 05AE 0300 0364 0315 0062;
@ -16712,6 +16887,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 05A0 0315 0300 05AE 0062;0061 05AE 05A0 0300 0315 0062;0061 05AE 05A0 0300 0315 0062;0061 05AE 05A0 0300 0315 0062;0061 05AE 05A0 0300 0315 0062;
0061 0315 0300 05AE 05A1 0062;00E0 05AE 05A1 0315 0062;0061 05AE 0300 05A1 0315 0062;00E0 05AE 05A1 0315 0062;0061 05AE 0300 05A1 0315 0062;
0061 05A1 0315 0300 05AE 0062;0061 05AE 05A1 0300 0315 0062;0061 05AE 05A1 0300 0315 0062;0061 05AE 05A1 0300 0315 0062;0061 05AE 05A1 0300 0315 0062;
0061 059A 0316 302A 05A2 0062;0061 302A 0316 05A2 059A 0062;0061 302A 0316 05A2 059A 0062;0061 302A 0316 05A2 059A 0062;0061 302A 0316 05A2 059A 0062;
0061 05A2 059A 0316 302A 0062;0061 302A 05A2 0316 059A 0062;0061 302A 05A2 0316 059A 0062;0061 302A 05A2 0316 059A 0062;0061 302A 05A2 0316 059A 0062;
0061 059A 0316 302A 05A3 0062;0061 302A 0316 05A3 059A 0062;0061 302A 0316 05A3 059A 0062;0061 302A 0316 05A3 059A 0062;0061 302A 0316 05A3 059A 0062;
0061 05A3 059A 0316 302A 0062;0061 302A 05A3 0316 059A 0062;0061 302A 05A3 0316 059A 0062;0061 302A 05A3 0316 059A 0062;0061 302A 05A3 0316 059A 0062;
0061 059A 0316 302A 05A4 0062;0061 302A 0316 05A4 059A 0062;0061 302A 0316 05A4 059A 0062;0061 302A 0316 05A4 059A 0062;0061 302A 0316 05A4 059A 0062;
@ -16758,6 +16935,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 05B8 05B9 05B8 05B7 0062;0061 05B7 05B8 05B8 05B9 0062;0061 05B7 05B8 05B8 05B9 0062;0061 05B7 05B8 05B8 05B9 0062;0061 05B7 05B8 05B8 05B9 0062;
0061 05BB 05B9 05B8 05B9 0062;0061 05B8 05B9 05B9 05BB 0062;0061 05B8 05B9 05B9 05BB 0062;0061 05B8 05B9 05B9 05BB 0062;0061 05B8 05B9 05B9 05BB 0062;
0061 05B9 05BB 05B9 05B8 0062;0061 05B8 05B9 05B9 05BB 0062;0061 05B8 05B9 05B9 05BB 0062;0061 05B8 05B9 05B9 05BB 0062;0061 05B8 05B9 05B9 05BB 0062;
0061 05B9 05B8 05B7 05BA 0062;0061 05B7 05B8 05BA 05B9 0062;0061 05B7 05B8 05BA 05B9 0062;0061 05B7 05B8 05BA 05B9 0062;0061 05B7 05B8 05BA 05B9 0062;
0061 05BA 05B9 05B8 05B7 0062;0061 05B7 05BA 05B8 05B9 0062;0061 05B7 05BA 05B8 05B9 0062;0061 05B7 05BA 05B8 05B9 0062;0061 05B7 05BA 05B8 05B9 0062;
0061 05BC 05BB 05B9 05BB 0062;0061 05B9 05BB 05BB 05BC 0062;0061 05B9 05BB 05BB 05BC 0062;0061 05B9 05BB 05BB 05BC 0062;0061 05B9 05BB 05BB 05BC 0062;
0061 05BB 05BC 05BB 05B9 0062;0061 05B9 05BB 05BB 05BC 0062;0061 05B9 05BB 05BB 05BC 0062;0061 05B9 05BB 05BB 05BC 0062;0061 05B9 05BB 05BB 05BC 0062;
0061 05BD 05BC 05BB 05BC 0062;0061 05BB 05BC 05BC 05BD 0062;0061 05BB 05BC 05BC 05BD 0062;0061 05BB 05BC 05BC 05BD 0062;0061 05BB 05BC 05BC 05BD 0062;
@ -16772,6 +16951,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 05C2 FB1E 05C2 05C1 0062;0061 05C1 05C2 05C2 FB1E 0062;0061 05C1 05C2 05C2 FB1E 0062;0061 05C1 05C2 05C2 FB1E 0062;0061 05C1 05C2 05C2 FB1E 0062;
0061 0315 0300 05AE 05C4 0062;00E0 05AE 05C4 0315 0062;0061 05AE 0300 05C4 0315 0062;00E0 05AE 05C4 0315 0062;0061 05AE 0300 05C4 0315 0062;
0061 05C4 0315 0300 05AE 0062;0061 05AE 05C4 0300 0315 0062;0061 05AE 05C4 0300 0315 0062;0061 05AE 05C4 0300 0315 0062;0061 05AE 05C4 0300 0315 0062;
0061 059A 0316 302A 05C5 0062;0061 302A 0316 05C5 059A 0062;0061 302A 0316 05C5 059A 0062;0061 302A 0316 05C5 059A 0062;0061 302A 0316 05C5 059A 0062;
0061 05C5 059A 0316 302A 0062;0061 302A 05C5 0316 059A 0062;0061 302A 05C5 0316 059A 0062;0061 302A 05C5 0316 059A 0062;0061 302A 05C5 0316 059A 0062;
0061 0315 0300 05AE 0610 0062;00E0 05AE 0610 0315 0062;0061 05AE 0300 0610 0315 0062;00E0 05AE 0610 0315 0062;0061 05AE 0300 0610 0315 0062;
0061 0610 0315 0300 05AE 0062;0061 05AE 0610 0300 0315 0062;0061 05AE 0610 0300 0315 0062;0061 05AE 0610 0300 0315 0062;0061 05AE 0610 0300 0315 0062;
0061 0315 0300 05AE 0611 0062;00E0 05AE 0611 0315 0062;0061 05AE 0300 0611 0315 0062;00E0 05AE 0611 0315 0062;0061 05AE 0300 0611 0315 0062;
@ -16812,6 +16993,18 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 0657 0315 0300 05AE 0062;0061 05AE 0657 0300 0315 0062;0061 05AE 0657 0300 0315 0062;0061 05AE 0657 0300 0315 0062;0061 05AE 0657 0300 0315 0062;
0061 0315 0300 05AE 0658 0062;00E0 05AE 0658 0315 0062;0061 05AE 0300 0658 0315 0062;00E0 05AE 0658 0315 0062;0061 05AE 0300 0658 0315 0062;
0061 0658 0315 0300 05AE 0062;0061 05AE 0658 0300 0315 0062;0061 05AE 0658 0300 0315 0062;0061 05AE 0658 0300 0315 0062;0061 05AE 0658 0300 0315 0062;
0061 0315 0300 05AE 0659 0062;00E0 05AE 0659 0315 0062;0061 05AE 0300 0659 0315 0062;00E0 05AE 0659 0315 0062;0061 05AE 0300 0659 0315 0062;
0061 0659 0315 0300 05AE 0062;0061 05AE 0659 0300 0315 0062;0061 05AE 0659 0300 0315 0062;0061 05AE 0659 0300 0315 0062;0061 05AE 0659 0300 0315 0062;
0061 0315 0300 05AE 065A 0062;00E0 05AE 065A 0315 0062;0061 05AE 0300 065A 0315 0062;00E0 05AE 065A 0315 0062;0061 05AE 0300 065A 0315 0062;
0061 065A 0315 0300 05AE 0062;0061 05AE 065A 0300 0315 0062;0061 05AE 065A 0300 0315 0062;0061 05AE 065A 0300 0315 0062;0061 05AE 065A 0300 0315 0062;
0061 0315 0300 05AE 065B 0062;00E0 05AE 065B 0315 0062;0061 05AE 0300 065B 0315 0062;00E0 05AE 065B 0315 0062;0061 05AE 0300 065B 0315 0062;
0061 065B 0315 0300 05AE 0062;0061 05AE 065B 0300 0315 0062;0061 05AE 065B 0300 0315 0062;0061 05AE 065B 0300 0315 0062;0061 05AE 065B 0300 0315 0062;
0061 059A 0316 302A 065C 0062;0061 302A 0316 065C 059A 0062;0061 302A 0316 065C 059A 0062;0061 302A 0316 065C 059A 0062;0061 302A 0316 065C 059A 0062;
0061 065C 059A 0316 302A 0062;0061 302A 065C 0316 059A 0062;0061 302A 065C 0316 059A 0062;0061 302A 065C 0316 059A 0062;0061 302A 065C 0316 059A 0062;
0061 0650 064F 064E 065D 0062;0061 064E 064F 065D 0650 0062;0061 064E 064F 065D 0650 0062;0061 064E 064F 065D 0650 0062;0061 064E 064F 065D 0650 0062;
0061 065D 0650 064F 064E 0062;0061 064E 065D 064F 0650 0062;0061 064E 065D 064F 0650 0062;0061 064E 065D 064F 0650 0062;0061 064E 065D 064F 0650 0062;
0061 064F 064E 064D 065E 0062;0061 064D 064E 065E 064F 0062;0061 064D 064E 065E 064F 0062;0061 064D 064E 065E 064F 0062;0061 064D 064E 065E 064F 0062;
0061 065E 064F 064E 064D 0062;0061 064D 065E 064E 064F 0062;0061 064D 065E 064E 064F 0062;0061 064D 065E 064E 064F 0062;0061 064D 065E 064E 064F 0062;
0061 0711 0670 0652 0670 0062;0061 0652 0670 0670 0711 0062;0061 0652 0670 0670 0711 0062;0061 0652 0670 0670 0711 0062;0061 0652 0670 0670 0711 0062;
0061 0670 0711 0670 0652 0062;0061 0652 0670 0670 0711 0062;0061 0652 0670 0670 0711 0062;0061 0652 0670 0670 0711 0062;0061 0652 0670 0670 0711 0062;
0061 0315 0300 05AE 06D6 0062;00E0 05AE 06D6 0315 0062;0061 05AE 0300 06D6 0315 0062;00E0 05AE 06D6 0315 0062;0061 05AE 0300 06D6 0315 0062;
@ -17020,6 +17213,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 1037 3099 093C 0334 0062;0061 0334 1037 093C 3099 0062;0061 0334 1037 093C 3099 0062;0061 0334 1037 093C 3099 0062;0061 0334 1037 093C 3099 0062;
0061 05B0 094D 3099 1039 0062;0061 3099 094D 1039 05B0 0062;0061 3099 094D 1039 05B0 0062;0061 3099 094D 1039 05B0 0062;0061 3099 094D 1039 05B0 0062;
0061 1039 05B0 094D 3099 0062;0061 3099 1039 094D 05B0 0062;0061 3099 1039 094D 05B0 0062;0061 3099 1039 094D 05B0 0062;0061 3099 1039 094D 05B0 0062;
0061 0315 0300 05AE 135F 0062;00E0 05AE 135F 0315 0062;0061 05AE 0300 135F 0315 0062;00E0 05AE 135F 0315 0062;0061 05AE 0300 135F 0315 0062;
0061 135F 0315 0300 05AE 0062;0061 05AE 135F 0300 0315 0062;0061 05AE 135F 0300 0315 0062;0061 05AE 135F 0300 0315 0062;0061 05AE 135F 0300 0315 0062;
0061 05B0 094D 3099 1714 0062;0061 3099 094D 1714 05B0 0062;0061 3099 094D 1714 05B0 0062;0061 3099 094D 1714 05B0 0062;0061 3099 094D 1714 05B0 0062;
0061 1714 05B0 094D 3099 0062;0061 3099 1714 094D 05B0 0062;0061 3099 1714 094D 05B0 0062;0061 3099 1714 094D 05B0 0062;0061 3099 1714 094D 05B0 0062;
0061 05B0 094D 3099 1734 0062;0061 3099 094D 1734 05B0 0062;0061 3099 094D 1734 05B0 0062;0061 3099 094D 1734 05B0 0062;0061 3099 094D 1734 05B0 0062;
@ -17036,6 +17231,18 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 193A 0315 0300 05AE 0062;0061 05AE 193A 0300 0315 0062;0061 05AE 193A 0300 0315 0062;0061 05AE 193A 0300 0315 0062;0061 05AE 193A 0300 0315 0062;
0061 059A 0316 302A 193B 0062;0061 302A 0316 193B 059A 0062;0061 302A 0316 193B 059A 0062;0061 302A 0316 193B 059A 0062;0061 302A 0316 193B 059A 0062;
0061 193B 059A 0316 302A 0062;0061 302A 193B 0316 059A 0062;0061 302A 193B 0316 059A 0062;0061 302A 193B 0316 059A 0062;0061 302A 193B 0316 059A 0062;
0061 0315 0300 05AE 1A17 0062;00E0 05AE 1A17 0315 0062;0061 05AE 0300 1A17 0315 0062;00E0 05AE 1A17 0315 0062;0061 05AE 0300 1A17 0315 0062;
0061 1A17 0315 0300 05AE 0062;0061 05AE 1A17 0300 0315 0062;0061 05AE 1A17 0300 0315 0062;0061 05AE 1A17 0300 0315 0062;0061 05AE 1A17 0300 0315 0062;
0061 059A 0316 302A 1A18 0062;0061 302A 0316 1A18 059A 0062;0061 302A 0316 1A18 059A 0062;0061 302A 0316 1A18 059A 0062;0061 302A 0316 1A18 059A 0062;
0061 1A18 059A 0316 302A 0062;0061 302A 1A18 0316 059A 0062;0061 302A 1A18 0316 059A 0062;0061 302A 1A18 0316 059A 0062;0061 302A 1A18 0316 059A 0062;
0061 0315 0300 05AE 1DC0 0062;00E0 05AE 1DC0 0315 0062;0061 05AE 0300 1DC0 0315 0062;00E0 05AE 1DC0 0315 0062;0061 05AE 0300 1DC0 0315 0062;
0061 1DC0 0315 0300 05AE 0062;0061 05AE 1DC0 0300 0315 0062;0061 05AE 1DC0 0300 0315 0062;0061 05AE 1DC0 0300 0315 0062;0061 05AE 1DC0 0300 0315 0062;
0061 0315 0300 05AE 1DC1 0062;00E0 05AE 1DC1 0315 0062;0061 05AE 0300 1DC1 0315 0062;00E0 05AE 1DC1 0315 0062;0061 05AE 0300 1DC1 0315 0062;
0061 1DC1 0315 0300 05AE 0062;0061 05AE 1DC1 0300 0315 0062;0061 05AE 1DC1 0300 0315 0062;0061 05AE 1DC1 0300 0315 0062;0061 05AE 1DC1 0300 0315 0062;
0061 059A 0316 302A 1DC2 0062;0061 302A 0316 1DC2 059A 0062;0061 302A 0316 1DC2 059A 0062;0061 302A 0316 1DC2 059A 0062;0061 302A 0316 1DC2 059A 0062;
0061 1DC2 059A 0316 302A 0062;0061 302A 1DC2 0316 059A 0062;0061 302A 1DC2 0316 059A 0062;0061 302A 1DC2 0316 059A 0062;0061 302A 1DC2 0316 059A 0062;
0061 0315 0300 05AE 1DC3 0062;00E0 05AE 1DC3 0315 0062;0061 05AE 0300 1DC3 0315 0062;00E0 05AE 1DC3 0315 0062;0061 05AE 0300 1DC3 0315 0062;
0061 1DC3 0315 0300 05AE 0062;0061 05AE 1DC3 0300 0315 0062;0061 05AE 1DC3 0300 0315 0062;0061 05AE 1DC3 0300 0315 0062;0061 05AE 1DC3 0300 0315 0062;
0061 0315 0300 05AE 20D0 0062;00E0 05AE 20D0 0315 0062;0061 05AE 0300 20D0 0315 0062;00E0 05AE 20D0 0315 0062;0061 05AE 0300 20D0 0315 0062;
0061 20D0 0315 0300 05AE 0062;0061 05AE 20D0 0300 0315 0062;0061 05AE 20D0 0300 0315 0062;0061 05AE 20D0 0300 0315 0062;0061 05AE 20D0 0300 0315 0062;
0061 0315 0300 05AE 20D1 0062;00E0 05AE 20D1 0315 0062;0061 05AE 0300 20D1 0315 0062;00E0 05AE 20D1 0315 0062;0061 05AE 0300 20D1 0315 0062;
@ -17076,12 +17283,14 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 20E9 0315 0300 05AE 0062;0061 05AE 20E9 0300 0315 0062;0061 05AE 20E9 0300 0315 0062;0061 05AE 20E9 0300 0315 0062;0061 05AE 20E9 0300 0315 0062;
0061 093C 0334 20EA 0062;0061 0334 20EA 093C 0062;0061 0334 20EA 093C 0062;0061 0334 20EA 093C 0062;0061 0334 20EA 093C 0062;
0061 20EA 093C 0334 0062;0061 20EA 0334 093C 0062;0061 20EA 0334 093C 0062;0061 20EA 0334 093C 0062;0061 20EA 0334 093C 0062;
0061 093C 0334 20EB 0062;0061 0334 20EB 093C 0062;0061 0334 20EB 093C 0062;0061 0334 20EB 093C 0062;0061 0334 20EB 093C 0062;
0061 20EB 093C 0334 0062;0061 20EB 0334 093C 0062;0061 20EB 0334 093C 0062;0061 20EB 0334 093C 0062;0061 20EB 0334 093C 0062;
0061 0316 302A 031B 302A 0062;0061 031B 302A 302A 0316 0062;0061 031B 302A 302A 0316 0062;0061 031B 302A 302A 0316 0062;0061 031B 302A 302A 0316 0062;
0061 302A 0316 302A 031B 0062;0061 031B 302A 302A 0316 0062;0061 031B 302A 302A 0316 0062;0061 031B 302A 302A 0316 0062;0061 031B 302A 302A 0316 0062;
0061 0300 05AE 1D16D 302B 0062;00E0 1D16D 05AE 302B 0062;0061 1D16D 05AE 302B 0300 0062;00E0 1D16D 05AE 302B 0062;0061 1D16D 05AE 302B 0300 0062;
0061 302B 0300 05AE 1D16D 0062;00E0 1D16D 302B 05AE 0062;0061 1D16D 302B 05AE 0300 0062;00E0 1D16D 302B 05AE 0062;0061 1D16D 302B 05AE 0300 0062;
0061 035F 0315 0300 302C 0062;00E0 0315 302C 035F 0062;0061 0300 0315 302C 035F 0062;00E0 0315 302C 035F 0062;0061 0300 0315 302C 035F 0062;
0061 302C 035F 0315 0300 0062;00E0 302C 0315 035F 0062;0061 0300 302C 0315 035F 0062;00E0 302C 0315 035F 0062;0061 0300 302C 0315 035F 0062;
0061 035C 0315 0300 302C 0062;00E0 0315 302C 035C 0062;0061 0300 0315 302C 035C 0062;00E0 0315 302C 035C 0062;0061 0300 0315 302C 035C 0062;
0061 302C 035C 0315 0300 0062;00E0 302C 0315 035C 0062;0061 0300 302C 0315 035C 0062;00E0 302C 0315 035C 0062;0061 0300 302C 0315 035C 0062;
0061 302E 059A 0316 302D 0062;0061 0316 059A 302D 302E 0062;0061 0316 059A 302D 302E 0062;0061 0316 059A 302D 302E 0062;0061 0316 059A 302D 302E 0062;
0061 302D 302E 059A 0316 0062;0061 0316 302D 059A 302E 0062;0061 0316 302D 059A 302E 0062;0061 0316 302D 059A 302E 0062;0061 0316 302D 059A 302E 0062;
0061 1D16D 302E 059A 302E 0062;0061 059A 302E 302E 1D16D 0062;0061 059A 302E 302E 1D16D 0062;0061 059A 302E 302E 1D16D 0062;0061 059A 302E 302E 1D16D 0062;
@ -17092,6 +17301,8 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 3099 094D 3099 093C 0062;0061 093C 3099 3099 094D 0062;0061 093C 3099 3099 094D 0062;0061 093C 3099 3099 094D 0062;0061 093C 3099 3099 094D 0062;
0061 094D 3099 093C 309A 0062;0061 093C 3099 309A 094D 0062;0061 093C 3099 309A 094D 0062;0061 093C 3099 309A 094D 0062;0061 093C 3099 309A 094D 0062;
0061 309A 094D 3099 093C 0062;0061 093C 309A 3099 094D 0062;0061 093C 309A 3099 094D 0062;0061 093C 309A 3099 094D 0062;0061 093C 309A 3099 094D 0062;
0061 05B0 094D 3099 A806 0062;0061 3099 094D A806 05B0 0062;0061 3099 094D A806 05B0 0062;0061 3099 094D A806 05B0 0062;0061 3099 094D A806 05B0 0062;
0061 A806 05B0 094D 3099 0062;0061 3099 A806 094D 05B0 0062;0061 3099 A806 094D 05B0 0062;0061 3099 A806 094D 05B0 0062;0061 3099 A806 094D 05B0 0062;
0061 064B FB1E 05C2 FB1E 0062;0061 05C2 FB1E FB1E 064B 0062;0061 05C2 FB1E FB1E 064B 0062;0061 05C2 FB1E FB1E 064B 0062;0061 05C2 FB1E FB1E 064B 0062;
0061 FB1E 064B FB1E 05C2 0062;0061 05C2 FB1E FB1E 064B 0062;0061 05C2 FB1E FB1E 064B 0062;0061 05C2 FB1E FB1E 064B 0062;0061 05C2 FB1E FB1E 064B 0062;
0061 0315 0300 05AE FE20 0062;00E0 05AE FE20 0315 0062;0061 05AE 0300 FE20 0315 0062;00E0 05AE FE20 0315 0062;0061 05AE 0300 FE20 0315 0062;
@ -17102,6 +17313,18 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 FE22 0315 0300 05AE 0062;0061 05AE FE22 0300 0315 0062;0061 05AE FE22 0300 0315 0062;0061 05AE FE22 0300 0315 0062;0061 05AE FE22 0300 0315 0062;
0061 0315 0300 05AE FE23 0062;00E0 05AE FE23 0315 0062;0061 05AE 0300 FE23 0315 0062;00E0 05AE FE23 0315 0062;0061 05AE 0300 FE23 0315 0062;
0061 FE23 0315 0300 05AE 0062;0061 05AE FE23 0300 0315 0062;0061 05AE FE23 0300 0315 0062;0061 05AE FE23 0300 0315 0062;0061 05AE FE23 0300 0315 0062;
0061 059A 0316 302A 10A0D 0062;0061 302A 0316 10A0D 059A 0062;0061 302A 0316 10A0D 059A 0062;0061 302A 0316 10A0D 059A 0062;0061 302A 0316 10A0D 059A 0062;
0061 10A0D 059A 0316 302A 0062;0061 302A 10A0D 0316 059A 0062;0061 302A 10A0D 0316 059A 0062;0061 302A 10A0D 0316 059A 0062;0061 302A 10A0D 0316 059A 0062;
0061 0315 0300 05AE 10A0F 0062;00E0 05AE 10A0F 0315 0062;0061 05AE 0300 10A0F 0315 0062;00E0 05AE 10A0F 0315 0062;0061 05AE 0300 10A0F 0315 0062;
0061 10A0F 0315 0300 05AE 0062;0061 05AE 10A0F 0300 0315 0062;0061 05AE 10A0F 0300 0315 0062;0061 05AE 10A0F 0300 0315 0062;0061 05AE 10A0F 0300 0315 0062;
0061 0315 0300 05AE 10A38 0062;00E0 05AE 10A38 0315 0062;0061 05AE 0300 10A38 0315 0062;00E0 05AE 10A38 0315 0062;0061 05AE 0300 10A38 0315 0062;
0061 10A38 0315 0300 05AE 0062;0061 05AE 10A38 0300 0315 0062;0061 05AE 10A38 0300 0315 0062;0061 05AE 10A38 0300 0315 0062;0061 05AE 10A38 0300 0315 0062;
0061 093C 0334 10A39 0062;0061 0334 10A39 093C 0062;0061 0334 10A39 093C 0062;0061 0334 10A39 093C 0062;0061 0334 10A39 093C 0062;
0061 10A39 093C 0334 0062;0061 10A39 0334 093C 0062;0061 10A39 0334 093C 0062;0061 10A39 0334 093C 0062;0061 10A39 0334 093C 0062;
0061 059A 0316 302A 10A3A 0062;0061 302A 0316 10A3A 059A 0062;0061 302A 0316 10A3A 059A 0062;0061 302A 0316 10A3A 059A 0062;0061 302A 0316 10A3A 059A 0062;
0061 10A3A 059A 0316 302A 0062;0061 302A 10A3A 0316 059A 0062;0061 302A 10A3A 0316 059A 0062;0061 302A 10A3A 0316 059A 0062;0061 302A 10A3A 0316 059A 0062;
0061 05B0 094D 3099 10A3F 0062;0061 3099 094D 10A3F 05B0 0062;0061 3099 094D 10A3F 05B0 0062;0061 3099 094D 10A3F 05B0 0062;0061 3099 094D 10A3F 05B0 0062;
0061 10A3F 05B0 094D 3099 0062;0061 3099 10A3F 094D 05B0 0062;0061 3099 10A3F 094D 05B0 0062;0061 3099 10A3F 094D 05B0 0062;0061 3099 10A3F 094D 05B0 0062;
0061 302A 031B 0321 1D165 0062;0061 0321 031B 1D165 302A 0062;0061 0321 031B 1D165 302A 0062;0061 0321 031B 1D165 302A 0062;0061 0321 031B 1D165 302A 0062;
0061 1D165 302A 031B 0321 0062;0061 0321 1D165 031B 302A 0062;0061 0321 1D165 031B 302A 0062;0061 0321 1D165 031B 302A 0062;0061 0321 1D165 031B 302A 0062;
0061 302A 031B 0321 1D166 0062;0061 0321 031B 1D166 302A 0062;0061 0321 031B 1D166 302A 0062;0061 0321 031B 1D166 302A 0062;0061 0321 031B 1D166 302A 0062;
@ -17162,5 +17385,169 @@ FFEE;FFEE;FFEE;25CB;25CB;
0061 1D1AC 0315 0300 05AE 0062;0061 05AE 1D1AC 0300 0315 0062;0061 05AE 1D1AC 0300 0315 0062;0061 05AE 1D1AC 0300 0315 0062;0061 05AE 1D1AC 0300 0315 0062;
0061 0315 0300 05AE 1D1AD 0062;00E0 05AE 1D1AD 0315 0062;0061 05AE 0300 1D1AD 0315 0062;00E0 05AE 1D1AD 0315 0062;0061 05AE 0300 1D1AD 0315 0062;
0061 1D1AD 0315 0300 05AE 0062;0061 05AE 1D1AD 0300 0315 0062;0061 05AE 1D1AD 0300 0315 0062;0061 05AE 1D1AD 0300 0315 0062;0061 05AE 1D1AD 0300 0315 0062;
0061 0315 0300 05AE 1D242 0062;00E0 05AE 1D242 0315 0062;0061 05AE 0300 1D242 0315 0062;00E0 05AE 1D242 0315 0062;0061 05AE 0300 1D242 0315 0062;
0061 1D242 0315 0300 05AE 0062;0061 05AE 1D242 0300 0315 0062;0061 05AE 1D242 0300 0315 0062;0061 05AE 1D242 0300 0315 0062;0061 05AE 1D242 0300 0315 0062;
0061 0315 0300 05AE 1D243 0062;00E0 05AE 1D243 0315 0062;0061 05AE 0300 1D243 0315 0062;00E0 05AE 1D243 0315 0062;0061 05AE 0300 1D243 0315 0062;
0061 1D243 0315 0300 05AE 0062;0061 05AE 1D243 0300 0315 0062;0061 05AE 1D243 0300 0315 0062;0061 05AE 1D243 0300 0315 0062;0061 05AE 1D243 0300 0315 0062;
0061 0315 0300 05AE 1D244 0062;00E0 05AE 1D244 0315 0062;0061 05AE 0300 1D244 0315 0062;00E0 05AE 1D244 0315 0062;0061 05AE 0300 1D244 0315 0062;
0061 1D244 0315 0300 05AE 0062;0061 05AE 1D244 0300 0315 0062;0061 05AE 1D244 0300 0315 0062;0061 05AE 1D244 0300 0315 0062;0061 05AE 1D244 0300 0315 0062;
#
@Part3 # PRI #29 Test
#
09C7 0334 09BE;09C7 0334 09BE;09C7 0334 09BE;09C7 0334 09BE;09C7 0334 09BE;
09C7 0334 09D7;09C7 0334 09D7;09C7 0334 09D7;09C7 0334 09D7;09C7 0334 09D7;
0B47 0334 0B3E;0B47 0334 0B3E;0B47 0334 0B3E;0B47 0334 0B3E;0B47 0334 0B3E;
0B47 0334 0B56;0B47 0334 0B56;0B47 0334 0B56;0B47 0334 0B56;0B47 0334 0B56;
0B47 0334 0B57;0B47 0334 0B57;0B47 0334 0B57;0B47 0334 0B57;0B47 0334 0B57;
0B92 0334 0BD7;0B92 0334 0BD7;0B92 0334 0BD7;0B92 0334 0BD7;0B92 0334 0BD7;
0BC6 0334 0BBE;0BC6 0334 0BBE;0BC6 0334 0BBE;0BC6 0334 0BBE;0BC6 0334 0BBE;
0BC6 0334 0BD7;0BC6 0334 0BD7;0BC6 0334 0BD7;0BC6 0334 0BD7;0BC6 0334 0BD7;
0BC7 0334 0BBE;0BC7 0334 0BBE;0BC7 0334 0BBE;0BC7 0334 0BBE;0BC7 0334 0BBE;
0CBF 0334 0CD5;0CBF 0334 0CD5;0CBF 0334 0CD5;0CBF 0334 0CD5;0CBF 0334 0CD5;
0CC6 0334 0CC2;0CC6 0334 0CC2;0CC6 0334 0CC2;0CC6 0334 0CC2;0CC6 0334 0CC2;
0CC6 0334 0CD5;0CC6 0334 0CD5;0CC6 0334 0CD5;0CC6 0334 0CD5;0CC6 0334 0CD5;
0CC6 0334 0CD6;0CC6 0334 0CD6;0CC6 0334 0CD6;0CC6 0334 0CD6;0CC6 0334 0CD6;
0CCA 0334 0CD5;0CCA 0334 0CD5;0CC6 0CC2 0334 0CD5;0CCA 0334 0CD5;0CC6 0CC2 0334 0CD5;
0D46 0334 0D3E;0D46 0334 0D3E;0D46 0334 0D3E;0D46 0334 0D3E;0D46 0334 0D3E;
0D46 0334 0D57;0D46 0334 0D57;0D46 0334 0D57;0D46 0334 0D57;0D46 0334 0D57;
0D47 0334 0D3E;0D47 0334 0D3E;0D47 0334 0D3E;0D47 0334 0D3E;0D47 0334 0D3E;
0DD9 0334 0DCF;0DD9 0334 0DCF;0DD9 0334 0DCF;0DD9 0334 0DCF;0DD9 0334 0DCF;
0DD9 0334 0DDF;0DD9 0334 0DDF;0DD9 0334 0DDF;0DD9 0334 0DDF;0DD9 0334 0DDF;
0F40 0334 0FB5;0F40 0334 0FB5;0F40 0334 0FB5;0F40 0334 0FB5;0F40 0334 0FB5;
0F42 0334 0FB7;0F42 0334 0FB7;0F42 0334 0FB7;0F42 0334 0FB7;0F42 0334 0FB7;
0F4C 0334 0FB7;0F4C 0334 0FB7;0F4C 0334 0FB7;0F4C 0334 0FB7;0F4C 0334 0FB7;
0F51 0334 0FB7;0F51 0334 0FB7;0F51 0334 0FB7;0F51 0334 0FB7;0F51 0334 0FB7;
0F56 0334 0FB7;0F56 0334 0FB7;0F56 0334 0FB7;0F56 0334 0FB7;0F56 0334 0FB7;
0F5B 0334 0FB7;0F5B 0334 0FB7;0F5B 0334 0FB7;0F5B 0334 0FB7;0F5B 0334 0FB7;
0F90 0334 0FB5;0F90 0334 0FB5;0F90 0334 0FB5;0F90 0334 0FB5;0F90 0334 0FB5;
0F92 0334 0FB7;0F92 0334 0FB7;0F92 0334 0FB7;0F92 0334 0FB7;0F92 0334 0FB7;
0F9C 0334 0FB7;0F9C 0334 0FB7;0F9C 0334 0FB7;0F9C 0334 0FB7;0F9C 0334 0FB7;
0FA1 0334 0FB7;0FA1 0334 0FB7;0FA1 0334 0FB7;0FA1 0334 0FB7;0FA1 0334 0FB7;
0FA6 0334 0FB7;0FA6 0334 0FB7;0FA6 0334 0FB7;0FA6 0334 0FB7;0FA6 0334 0FB7;
0FAB 0334 0FB7;0FAB 0334 0FB7;0FAB 0334 0FB7;0FAB 0334 0FB7;0FAB 0334 0FB7;
1025 0334 102E;1025 0334 102E;1025 0334 102E;1025 0334 102E;1025 0334 102E;
1100 0334 1161;1100 0334 1161;1100 0334 1161;1100 0334 1161;1100 0334 1161;
1100 0334 116E;1100 0334 116E;1100 0334 116E;1100 0334 116E;1100 0334 116E;
1101 0334 1166;1101 0334 1166;1101 0334 1166;1101 0334 1166;1101 0334 1166;
1101 0334 1173;1101 0334 1173;1101 0334 1173;1101 0334 1173;1101 0334 1173;
1102 0334 116B;1102 0334 116B;1102 0334 116B;1102 0334 116B;1102 0334 116B;
1103 0334 1163;1103 0334 1163;1103 0334 1163;1103 0334 1163;1103 0334 1163;
1103 0334 1170;1103 0334 1170;1103 0334 1170;1103 0334 1170;1103 0334 1170;
1104 0334 1168;1104 0334 1168;1104 0334 1168;1104 0334 1168;1104 0334 1168;
1104 0334 1175;1104 0334 1175;1104 0334 1175;1104 0334 1175;1104 0334 1175;
1105 0334 116D;1105 0334 116D;1105 0334 116D;1105 0334 116D;1105 0334 116D;
1106 0334 1165;1106 0334 1165;1106 0334 1165;1106 0334 1165;1106 0334 1165;
1106 0334 1172;1106 0334 1172;1106 0334 1172;1106 0334 1172;1106 0334 1172;
1107 0334 116A;1107 0334 116A;1107 0334 116A;1107 0334 116A;1107 0334 116A;
1108 0334 1162;1108 0334 1162;1108 0334 1162;1108 0334 1162;1108 0334 1162;
1108 0334 116F;1108 0334 116F;1108 0334 116F;1108 0334 116F;1108 0334 116F;
1109 0334 1167;1109 0334 1167;1109 0334 1167;1109 0334 1167;1109 0334 1167;
1109 0334 1174;1109 0334 1174;1109 0334 1174;1109 0334 1174;1109 0334 1174;
110A 0334 116C;110A 0334 116C;110A 0334 116C;110A 0334 116C;110A 0334 116C;
110B 0334 1164;110B 0334 1164;110B 0334 1164;110B 0334 1164;110B 0334 1164;
110B 0334 1171;110B 0334 1171;110B 0334 1171;110B 0334 1171;110B 0334 1171;
110C 0334 1169;110C 0334 1169;110C 0334 1169;110C 0334 1169;110C 0334 1169;
110D 0334 1161;110D 0334 1161;110D 0334 1161;110D 0334 1161;110D 0334 1161;
110D 0334 116E;110D 0334 116E;110D 0334 116E;110D 0334 116E;110D 0334 116E;
110E 0334 1166;110E 0334 1166;110E 0334 1166;110E 0334 1166;110E 0334 1166;
110E 0334 1173;110E 0334 1173;110E 0334 1173;110E 0334 1173;110E 0334 1173;
110F 0334 116B;110F 0334 116B;110F 0334 116B;110F 0334 116B;110F 0334 116B;
1110 0334 1163;1110 0334 1163;1110 0334 1163;1110 0334 1163;1110 0334 1163;
1110 0334 1170;1110 0334 1170;1110 0334 1170;1110 0334 1170;1110 0334 1170;
1111 0334 1168;1111 0334 1168;1111 0334 1168;1111 0334 1168;1111 0334 1168;
1111 0334 1175;1111 0334 1175;1111 0334 1175;1111 0334 1175;1111 0334 1175;
1112 0334 116D;1112 0334 116D;1112 0334 116D;1112 0334 116D;1112 0334 116D;
AC54 0334 11AE;AC54 0334 11AE;1100 1164 0334 11AE;AC54 0334 11AE;1100 1164 0334 11AE;
ACA8 0334 11B5;ACA8 0334 11B5;1100 1167 0334 11B5;ACA8 0334 11B5;1100 1167 0334 11B5;
ACFC 0334 11BC;ACFC 0334 11BC;1100 116A 0334 11BC;ACFC 0334 11BC;1100 116A 0334 11BC;
ADC0 0334 11AE;ADC0 0334 11AE;1100 1171 0334 11AE;ADC0 0334 11AE;1100 1171 0334 11AE;
AE14 0334 11B5;AE14 0334 11B5;1100 1174 0334 11B5;AE14 0334 11B5;1100 1174 0334 11B5;
AE68 0334 11BC;AE68 0334 11BC;1101 1162 0334 11BC;AE68 0334 11BC;1101 1162 0334 11BC;
AF2C 0334 11AE;AF2C 0334 11AE;1101 1169 0334 11AE;AF2C 0334 11AE;1101 1169 0334 11AE;
AF80 0334 11B5;AF80 0334 11B5;1101 116C 0334 11B5;AF80 0334 11B5;1101 116C 0334 11B5;
AFD4 0334 11BC;AFD4 0334 11BC;1101 116F 0334 11BC;AFD4 0334 11BC;1101 116F 0334 11BC;
B098 0334 11AE;B098 0334 11AE;1102 1161 0334 11AE;B098 0334 11AE;1102 1161 0334 11AE;
B0EC 0334 11B5;B0EC 0334 11B5;1102 1164 0334 11B5;B0EC 0334 11B5;1102 1164 0334 11B5;
B140 0334 11BC;B140 0334 11BC;1102 1167 0334 11BC;B140 0334 11BC;1102 1167 0334 11BC;
B204 0334 11AE;B204 0334 11AE;1102 116E 0334 11AE;B204 0334 11AE;1102 116E 0334 11AE;
B258 0334 11B5;B258 0334 11B5;1102 1171 0334 11B5;B258 0334 11B5;1102 1171 0334 11B5;
B2AC 0334 11BC;B2AC 0334 11BC;1102 1174 0334 11BC;B2AC 0334 11BC;1102 1174 0334 11BC;
B370 0334 11AE;B370 0334 11AE;1103 1166 0334 11AE;B370 0334 11AE;1103 1166 0334 11AE;
B3C4 0334 11B5;B3C4 0334 11B5;1103 1169 0334 11B5;B3C4 0334 11B5;1103 1169 0334 11B5;
B418 0334 11BC;B418 0334 11BC;1103 116C 0334 11BC;B418 0334 11BC;1103 116C 0334 11BC;
B4DC 0334 11AE;B4DC 0334 11AE;1103 1173 0334 11AE;B4DC 0334 11AE;1103 1173 0334 11AE;
B530 0334 11B5;B530 0334 11B5;1104 1161 0334 11B5;B530 0334 11B5;1104 1161 0334 11B5;
B584 0334 11BC;B584 0334 11BC;1104 1164 0334 11BC;B584 0334 11BC;1104 1164 0334 11BC;
B648 0334 11AE;B648 0334 11AE;1104 116B 0334 11AE;B648 0334 11AE;1104 116B 0334 11AE;
B69C 0334 11B5;B69C 0334 11B5;1104 116E 0334 11B5;B69C 0334 11B5;1104 116E 0334 11B5;
B6F0 0334 11BC;B6F0 0334 11BC;1104 1171 0334 11BC;B6F0 0334 11BC;1104 1171 0334 11BC;
B7B4 0334 11AE;B7B4 0334 11AE;1105 1163 0334 11AE;B7B4 0334 11AE;1105 1163 0334 11AE;
B808 0334 11B5;B808 0334 11B5;1105 1166 0334 11B5;B808 0334 11B5;1105 1166 0334 11B5;
B85C 0334 11BC;B85C 0334 11BC;1105 1169 0334 11BC;B85C 0334 11BC;1105 1169 0334 11BC;
B920 0334 11AE;B920 0334 11AE;1105 1170 0334 11AE;B920 0334 11AE;1105 1170 0334 11AE;
B974 0334 11B5;B974 0334 11B5;1105 1173 0334 11B5;B974 0334 11B5;1105 1173 0334 11B5;
B9C8 0334 11BC;B9C8 0334 11BC;1106 1161 0334 11BC;B9C8 0334 11BC;1106 1161 0334 11BC;
BA8C 0334 11AE;BA8C 0334 11AE;1106 1168 0334 11AE;BA8C 0334 11AE;1106 1168 0334 11AE;
BAE0 0334 11B5;BAE0 0334 11B5;1106 116B 0334 11B5;BAE0 0334 11B5;1106 116B 0334 11B5;
BB34 0334 11BC;BB34 0334 11BC;1106 116E 0334 11BC;BB34 0334 11BC;1106 116E 0334 11BC;
BBF8 0334 11AE;BBF8 0334 11AE;1106 1175 0334 11AE;BBF8 0334 11AE;1106 1175 0334 11AE;
BC4C 0334 11B5;BC4C 0334 11B5;1107 1163 0334 11B5;BC4C 0334 11B5;1107 1163 0334 11B5;
BCA0 0334 11BC;BCA0 0334 11BC;1107 1166 0334 11BC;BCA0 0334 11BC;1107 1166 0334 11BC;
BD64 0334 11AE;BD64 0334 11AE;1107 116D 0334 11AE;BD64 0334 11AE;1107 116D 0334 11AE;
BDB8 0334 11B5;BDB8 0334 11B5;1107 1170 0334 11B5;BDB8 0334 11B5;1107 1170 0334 11B5;
BE0C 0334 11BC;BE0C 0334 11BC;1107 1173 0334 11BC;BE0C 0334 11BC;1107 1173 0334 11BC;
BED0 0334 11AE;BED0 0334 11AE;1108 1165 0334 11AE;BED0 0334 11AE;1108 1165 0334 11AE;
BF24 0334 11B5;BF24 0334 11B5;1108 1168 0334 11B5;BF24 0334 11B5;1108 1168 0334 11B5;
BF78 0334 11BC;BF78 0334 11BC;1108 116B 0334 11BC;BF78 0334 11BC;1108 116B 0334 11BC;
C03C 0334 11AE;C03C 0334 11AE;1108 1172 0334 11AE;C03C 0334 11AE;1108 1172 0334 11AE;
C090 0334 11B5;C090 0334 11B5;1108 1175 0334 11B5;C090 0334 11B5;1108 1175 0334 11B5;
C0E4 0334 11BC;C0E4 0334 11BC;1109 1163 0334 11BC;C0E4 0334 11BC;1109 1163 0334 11BC;
C1A8 0334 11AE;C1A8 0334 11AE;1109 116A 0334 11AE;C1A8 0334 11AE;1109 116A 0334 11AE;
C1FC 0334 11B5;C1FC 0334 11B5;1109 116D 0334 11B5;C1FC 0334 11B5;1109 116D 0334 11B5;
C250 0334 11BC;C250 0334 11BC;1109 1170 0334 11BC;C250 0334 11BC;1109 1170 0334 11BC;
C314 0334 11AE;C314 0334 11AE;110A 1162 0334 11AE;C314 0334 11AE;110A 1162 0334 11AE;
C368 0334 11B5;C368 0334 11B5;110A 1165 0334 11B5;C368 0334 11B5;110A 1165 0334 11B5;
C3BC 0334 11BC;C3BC 0334 11BC;110A 1168 0334 11BC;C3BC 0334 11BC;110A 1168 0334 11BC;
C480 0334 11AE;C480 0334 11AE;110A 116F 0334 11AE;C480 0334 11AE;110A 116F 0334 11AE;
C4D4 0334 11B5;C4D4 0334 11B5;110A 1172 0334 11B5;C4D4 0334 11B5;110A 1172 0334 11B5;
C528 0334 11BC;C528 0334 11BC;110A 1175 0334 11BC;C528 0334 11BC;110A 1175 0334 11BC;
C5EC 0334 11AE;C5EC 0334 11AE;110B 1167 0334 11AE;C5EC 0334 11AE;110B 1167 0334 11AE;
C640 0334 11B5;C640 0334 11B5;110B 116A 0334 11B5;C640 0334 11B5;110B 116A 0334 11B5;
C694 0334 11BC;C694 0334 11BC;110B 116D 0334 11BC;C694 0334 11BC;110B 116D 0334 11BC;
C758 0334 11AE;C758 0334 11AE;110B 1174 0334 11AE;C758 0334 11AE;110B 1174 0334 11AE;
C7AC 0334 11B5;C7AC 0334 11B5;110C 1162 0334 11B5;C7AC 0334 11B5;110C 1162 0334 11B5;
C800 0334 11BC;C800 0334 11BC;110C 1165 0334 11BC;C800 0334 11BC;110C 1165 0334 11BC;
C8C4 0334 11AE;C8C4 0334 11AE;110C 116C 0334 11AE;C8C4 0334 11AE;110C 116C 0334 11AE;
C918 0334 11B5;C918 0334 11B5;110C 116F 0334 11B5;C918 0334 11B5;110C 116F 0334 11B5;
C96C 0334 11BC;C96C 0334 11BC;110C 1172 0334 11BC;C96C 0334 11BC;110C 1172 0334 11BC;
CA30 0334 11AE;CA30 0334 11AE;110D 1164 0334 11AE;CA30 0334 11AE;110D 1164 0334 11AE;
CA84 0334 11B5;CA84 0334 11B5;110D 1167 0334 11B5;CA84 0334 11B5;110D 1167 0334 11B5;
CAD8 0334 11BC;CAD8 0334 11BC;110D 116A 0334 11BC;CAD8 0334 11BC;110D 116A 0334 11BC;
CB9C 0334 11AE;CB9C 0334 11AE;110D 1171 0334 11AE;CB9C 0334 11AE;110D 1171 0334 11AE;
CBF0 0334 11B5;CBF0 0334 11B5;110D 1174 0334 11B5;CBF0 0334 11B5;110D 1174 0334 11B5;
CC44 0334 11BC;CC44 0334 11BC;110E 1162 0334 11BC;CC44 0334 11BC;110E 1162 0334 11BC;
CD08 0334 11AE;CD08 0334 11AE;110E 1169 0334 11AE;CD08 0334 11AE;110E 1169 0334 11AE;
CD5C 0334 11B5;CD5C 0334 11B5;110E 116C 0334 11B5;CD5C 0334 11B5;110E 116C 0334 11B5;
CDB0 0334 11BC;CDB0 0334 11BC;110E 116F 0334 11BC;CDB0 0334 11BC;110E 116F 0334 11BC;
CE74 0334 11AE;CE74 0334 11AE;110F 1161 0334 11AE;CE74 0334 11AE;110F 1161 0334 11AE;
CEC8 0334 11B5;CEC8 0334 11B5;110F 1164 0334 11B5;CEC8 0334 11B5;110F 1164 0334 11B5;
CF1C 0334 11BC;CF1C 0334 11BC;110F 1167 0334 11BC;CF1C 0334 11BC;110F 1167 0334 11BC;
CFE0 0334 11AE;CFE0 0334 11AE;110F 116E 0334 11AE;CFE0 0334 11AE;110F 116E 0334 11AE;
D034 0334 11B5;D034 0334 11B5;110F 1171 0334 11B5;D034 0334 11B5;110F 1171 0334 11B5;
D088 0334 11BC;D088 0334 11BC;110F 1174 0334 11BC;D088 0334 11BC;110F 1174 0334 11BC;
D14C 0334 11AE;D14C 0334 11AE;1110 1166 0334 11AE;D14C 0334 11AE;1110 1166 0334 11AE;
D1A0 0334 11B5;D1A0 0334 11B5;1110 1169 0334 11B5;D1A0 0334 11B5;1110 1169 0334 11B5;
D1F4 0334 11BC;D1F4 0334 11BC;1110 116C 0334 11BC;D1F4 0334 11BC;1110 116C 0334 11BC;
D2B8 0334 11AE;D2B8 0334 11AE;1110 1173 0334 11AE;D2B8 0334 11AE;1110 1173 0334 11AE;
D30C 0334 11B5;D30C 0334 11B5;1111 1161 0334 11B5;D30C 0334 11B5;1111 1161 0334 11B5;
D360 0334 11BC;D360 0334 11BC;1111 1164 0334 11BC;D360 0334 11BC;1111 1164 0334 11BC;
D424 0334 11AE;D424 0334 11AE;1111 116B 0334 11AE;D424 0334 11AE;1111 116B 0334 11AE;
D478 0334 11B5;D478 0334 11B5;1111 116E 0334 11B5;D478 0334 11B5;1111 116E 0334 11B5;
D4CC 0334 11BC;D4CC 0334 11BC;1111 1171 0334 11BC;D4CC 0334 11BC;1111 1171 0334 11BC;
D590 0334 11AE;D590 0334 11AE;1112 1163 0334 11AE;D590 0334 11AE;1112 1163 0334 11AE;
D5E4 0334 11B5;D5E4 0334 11B5;1112 1166 0334 11B5;D5E4 0334 11B5;1112 1166 0334 11B5;
D638 0334 11BC;D638 0334 11BC;1112 1169 0334 11BC;D638 0334 11BC;1112 1169 0334 11BC;
D6FC 0334 11AE;D6FC 0334 11AE;1112 1170 0334 11AE;D6FC 0334 11AE;1112 1170 0334 11AE;
D750 0334 11B5;D750 0334 11B5;1112 1173 0334 11B5;D750 0334 11B5;1112 1173 0334 11B5;
#
# END OF FILE

348
icu4c/source/data/unidata/PropList.txt
View File

@ -1,8 +1,8 @@
# PropList-4.0.1.txt
# Date: 2004-03-02, 02:42:40 GMT [MD]
# PropList-4.1.0.txt
# Date: 2004-12-14, 01:07:52 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
@ -46,14 +46,16 @@
207B ; Dash # Sm SUPERSCRIPT MINUS
208B ; Dash # Sm SUBSCRIPT MINUS
2212 ; Dash # Sm MINUS SIGN
2E17 ; Dash # Pd DOUBLE OBLIQUE HYPHEN
301C ; Dash # Pd WAVE DASH
3030 ; Dash # Pd WAVY DASH
30A0 ; Dash # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
FE31..FE32 ; Dash # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
FE58 ; Dash # Pd SMALL EM DASH
FE63 ; Dash # Pd SMALL HYPHEN-MINUS
FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
# Total code points: 20
# Total code points: 22
# ================================================
@ -62,12 +64,13 @@ FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
058A ; Hyphen # Pd ARMENIAN HYPHEN
1806 ; Hyphen # Pd MONGOLIAN TODO SOFT HYPHEN
2010..2011 ; Hyphen # Pd [2] HYPHEN..NON-BREAKING HYPHEN
30FB ; Hyphen # Pc KATAKANA MIDDLE DOT
2E17 ; Hyphen # Pd DOUBLE OBLIQUE HYPHEN
30FB ; Hyphen # Po KATAKANA MIDDLE DOT
FE63 ; Hyphen # Pd SMALL HYPHEN-MINUS
FF0D ; Hyphen # Pd FULLWIDTH HYPHEN-MINUS
FF65 ; Hyphen # Pc HALFWIDTH KATAKANA MIDDLE DOT
FF65 ; Hyphen # Po HALFWIDTH KATAKANA MIDDLE DOT
# Total code points: 10
# Total code points: 11
# ================================================
@ -175,10 +178,12 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
212F..2131 ; Other_Math # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F
2133..2134 ; Other_Math # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O
2135..2138 ; Other_Math # Lo [4] ALEF SYMBOL..DALET SYMBOL
213D..213F ; Other_Math # L& [3] DOUBLE-STRUCK SMALL GAMMA..DOUBLE-STRUCK CAPITAL PI
213C..213F ; Other_Math # L& [4] DOUBLE-STRUCK SMALL PI..DOUBLE-STRUCK CAPITAL PI
2145..2149 ; Other_Math # L& [5] DOUBLE-STRUCK ITALIC CAPITAL D..DOUBLE-STRUCK ITALIC SMALL J
23B7 ; Other_Math # So RADICAL SYMBOL BOTTOM
23D0 ; Other_Math # So VERTICAL LINE EXTENSION
27C5 ; Other_Math # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Other_Math # Pe RIGHT S-SHAPED BAG DELIMITER
27E6 ; Other_Math # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Other_Math # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Other_Math # Ps MATHEMATICAL LEFT ANGLE BRACKET
@ -250,7 +255,7 @@ FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT
1D7C4..1D7C9 ; Other_Math # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL
1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
# Total code points: 1099
# Total code points: 1102
# ================================================
@ -274,13 +279,13 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
# ================================================
0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI
05B0..05B9 ; Other_Alphabetic # Mn [10] HEBREW POINT SHEVA..HEBREW POINT HOLAM
05BB..05BD ; Other_Alphabetic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
05B0..05BD ; Other_Alphabetic # Mn [14] HEBREW POINT SHEVA..HEBREW POINT METEG
05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE
05C1..05C2 ; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
05C4 ; Other_Alphabetic # Mn HEBREW MARK UPPER DOT
05C4..05C5 ; Other_Alphabetic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
0610..0615 ; Other_Alphabetic # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH
064B..0657 ; Other_Alphabetic # Mn [13] ARABIC FATHATAN..ARABIC INVERTED DAMMA
0659..065E ; Other_Alphabetic # Mn [6] ARABIC ZWARAKAY..ARABIC FATHA WITH TWO DOTS
0670 ; Other_Alphabetic # Mn ARABIC LETTER SUPERSCRIPT ALEF
06D6..06DC ; Other_Alphabetic # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
06E1..06E4 ; Other_Alphabetic # Mn [4] ARABIC SMALL HIGH DOTLESS HEAD OF KHAH..ARABIC SMALL HIGH MADDA
@ -382,7 +387,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
1038 ; Other_Alphabetic # Mc MYANMAR SIGN VISARGA
1056..1057 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
1058..1059 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
16EE..16F0 ; Other_Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL
135F ; Other_Alphabetic # Mn ETHIOPIC COMBINING GEMINATION MARK
1712..1713 ; Other_Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U
1732..1733 ; Other_Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U
1752..1753 ; Other_Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
@ -400,11 +405,20 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
1930..1931 ; Other_Alphabetic # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
1932 ; Other_Alphabetic # Mn LIMBU SMALL LETTER ANUSVARA
1933..1938 ; Other_Alphabetic # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
2160..2183 ; Other_Alphabetic # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED
19B0..19C0 ; Other_Alphabetic # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
19C8..19C9 ; Other_Alphabetic # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
1A17..1A18 ; Other_Alphabetic # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
1A19..1A1B ; Other_Alphabetic # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
24B6..24E9 ; Other_Alphabetic # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z
A823..A824 ; Other_Alphabetic # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
A825..A826 ; Other_Alphabetic # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
A827 ; Other_Alphabetic # Mc SYLOTI NAGRI VOWEL SIGN OO
FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
1034A ; Other_Alphabetic # Nl GOTHIC LETTER NINE HUNDRED
10A01..10A03 ; Other_Alphabetic # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; Other_Alphabetic # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; Other_Alphabetic # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
# Total code points: 429
# Total code points: 488
# ================================================
@ -413,12 +427,13 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FA5 ; Ideographic # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
4E00..9FBB ; Ideographic # Lo [20924] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FBB
F900..FA2D ; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 71053
# Total code points: 71181
# ================================================
@ -530,9 +545,10 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON
3031..3035 ; Extender # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
309D..309E ; Extender # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
30FC..30FE ; Extender # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
A015 ; Extender # Lm YI SYLLABLE WU
FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
# Total code points: 19
# Total code points: 20
# ================================================
@ -542,10 +558,13 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI
037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI
1D2C..1D61 ; Other_Lowercase # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
1D78 ; Other_Lowercase # Lm MODIFIER LETTER CYRILLIC EN
1D9B..1DBF ; Other_Lowercase # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
2090..2094 ; Other_Lowercase # Lm [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND
24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
# Total code points: 114
# Total code points: 157
# ================================================
@ -593,9 +612,9 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncha
0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
200C..200D ; Other_Grapheme_Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM
1D16E..1D16F ; Other_Grapheme_Extend # Mc [2] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-2
1D16E..1D172 ; Other_Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
# Total code points: 18
# Total code points: 21
# ================================================
@ -613,8 +632,10 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncha
0E3A ; Grapheme_Link # Mn THAI CHARACTER PHINTHU
1039 ; Grapheme_Link # Mn MYANMAR SIGN VIRAMA
17D2 ; Grapheme_Link # Mn KHMER SIGN COENG
A806 ; Grapheme_Link # Mn SYLOTI NAGRI SIGN HASANTA
10A3F ; Grapheme_Link # Mn KHAROSHTHI VIRAMA
# Total code points: 14
# Total code points: 16
# ================================================
@ -640,7 +661,7 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncha
# ================================================
3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FA5 ; Unified_Ideograph # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
4E00..9FBB ; Unified_Ideograph # Lo [20924] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FBB
FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
@ -650,13 +671,12 @@ FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..C
FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
20000..2A6D6 ; Unified_Ideograph # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
# Total code points: 70207
# Total code points: 70229
# ================================================
034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
200B ; Other_Default_Ignorable_Code_Point # Cf ZERO WIDTH SPACE
2064..2069 ; Other_Default_Ignorable_Code_Point # Cn [6] <reserved-2064>..<reserved-2069>
3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER
FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER
@ -666,7 +686,7 @@ E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30] <reserved-E0002>..
E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reserved-E00FF>
E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
# Total code points: 3780
# Total code points: 3779
# ================================================
@ -688,6 +708,9 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>.
0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE
1D62 ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER I
1D96 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH RETROFLEX HOOK
1DA4 ; Soft_Dotted # Lm MODIFIER LETTER SMALL I WITH STROKE
1DA8 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH CROSSED-TAIL
1E2D ; Soft_Dotted # L& LATIN SMALL LETTER I WITH TILDE BELOW
1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
2071 ; Soft_Dotted # L& SUPERSCRIPT LATIN SMALL LETTER I
@ -706,7 +729,7 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>.
1D65E..1D65F ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J
1D692..1D693 ; Soft_Dotted # L& [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J
# Total code points: 41
# Total code points: 44
# ================================================
@ -725,6 +748,12 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>.
# ================================================
1369..1371 ; Other_ID_Continue # No [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE
# Total code points: 9
# ================================================
0021 ; STerm # Po EXCLAMATION MARK
002E ; STerm # Po FULL STOP
003F ; STerm # Po QUESTION MARK
@ -761,3 +790,266 @@ FE00..FE0F ; Variation_Selector # Mn [16] VARIATION SELECTOR-1..VARIATION SE
E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 259
# ================================================
0009..000D ; Pattern_White_Space # Cc [5] <control-0009>..<control-000D>
0020 ; Pattern_White_Space # Zs SPACE
0085 ; Pattern_White_Space # Cc <control-0085>
200E..200F ; Pattern_White_Space # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
2028 ; Pattern_White_Space # Zl LINE SEPARATOR
2029 ; Pattern_White_Space # Zp PARAGRAPH SEPARATOR
# Total code points: 11
# ================================================
0021..0023 ; Pattern_Syntax # Po [3] EXCLAMATION MARK..NUMBER SIGN
0024 ; Pattern_Syntax # Sc DOLLAR SIGN
0025..0027 ; Pattern_Syntax # Po [3] PERCENT SIGN..APOSTROPHE
0028 ; Pattern_Syntax # Ps LEFT PARENTHESIS
0029 ; Pattern_Syntax # Pe RIGHT PARENTHESIS
002A ; Pattern_Syntax # Po ASTERISK
002B ; Pattern_Syntax # Sm PLUS SIGN
002C ; Pattern_Syntax # Po COMMA
002D ; Pattern_Syntax # Pd HYPHEN-MINUS
002E..002F ; Pattern_Syntax # Po [2] FULL STOP..SOLIDUS
003A..003B ; Pattern_Syntax # Po [2] COLON..SEMICOLON
003C..003E ; Pattern_Syntax # Sm [3] LESS-THAN SIGN..GREATER-THAN SIGN
003F..0040 ; Pattern_Syntax # Po [2] QUESTION MARK..COMMERCIAL AT
005B ; Pattern_Syntax # Ps LEFT SQUARE BRACKET
005C ; Pattern_Syntax # Po REVERSE SOLIDUS
005D ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET
005E ; Pattern_Syntax # Sk CIRCUMFLEX ACCENT
005F ; Pattern_Syntax # Pc LOW LINE
0060 ; Pattern_Syntax # Sk GRAVE ACCENT
007B ; Pattern_Syntax # Ps LEFT CURLY BRACKET
007C ; Pattern_Syntax # Sm VERTICAL LINE
007D ; Pattern_Syntax # Pe RIGHT CURLY BRACKET
007E ; Pattern_Syntax # Sm TILDE
00A1 ; Pattern_Syntax # Po INVERTED EXCLAMATION MARK
00A2..00A5 ; Pattern_Syntax # Sc [4] CENT SIGN..YEN SIGN
00A6..00A7 ; Pattern_Syntax # So [2] BROKEN BAR..SECTION SIGN
00A9 ; Pattern_Syntax # So COPYRIGHT SIGN
00AB ; Pattern_Syntax # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
00AC ; Pattern_Syntax # Sm NOT SIGN
00AE ; Pattern_Syntax # So REGISTERED SIGN
00B0 ; Pattern_Syntax # So DEGREE SIGN
00B1 ; Pattern_Syntax # Sm PLUS-MINUS SIGN
00B6 ; Pattern_Syntax # So PILCROW SIGN
00B7 ; Pattern_Syntax # Po MIDDLE DOT
00BB ; Pattern_Syntax # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
00BF ; Pattern_Syntax # Po INVERTED QUESTION MARK
00D7 ; Pattern_Syntax # Sm MULTIPLICATION SIGN
00F7 ; Pattern_Syntax # Sm DIVISION SIGN
2010..2015 ; Pattern_Syntax # Pd [6] HYPHEN..HORIZONTAL BAR
2016..2017 ; Pattern_Syntax # Po [2] DOUBLE VERTICAL LINE..DOUBLE LOW LINE
2018 ; Pattern_Syntax # Pi LEFT SINGLE QUOTATION MARK
2019 ; Pattern_Syntax # Pf RIGHT SINGLE QUOTATION MARK
201A ; Pattern_Syntax # Ps SINGLE LOW-9 QUOTATION MARK
201B..201C ; Pattern_Syntax # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK
201D ; Pattern_Syntax # Pf RIGHT DOUBLE QUOTATION MARK
201E ; Pattern_Syntax # Ps DOUBLE LOW-9 QUOTATION MARK
201F ; Pattern_Syntax # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK
2020..2027 ; Pattern_Syntax # Po [8] DAGGER..HYPHENATION POINT
2030..2038 ; Pattern_Syntax # Po [9] PER MILLE SIGN..CARET
2039 ; Pattern_Syntax # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK
203A ; Pattern_Syntax # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
203B..203E ; Pattern_Syntax # Po [4] REFERENCE MARK..OVERLINE
203F..2040 ; Pattern_Syntax # Pc [2] UNDERTIE..CHARACTER TIE
2041..2043 ; Pattern_Syntax # Po [3] CARET INSERTION POINT..HYPHEN BULLET
2044 ; Pattern_Syntax # Sm FRACTION SLASH
2045 ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH QUILL
2046 ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH QUILL
2047..2051 ; Pattern_Syntax # Po [11] DOUBLE QUESTION MARK..TWO ASTERISKS ALIGNED VERTICALLY
2052 ; Pattern_Syntax # Sm COMMERCIAL MINUS SIGN
2053 ; Pattern_Syntax # Po SWUNG DASH
2054 ; Pattern_Syntax # Pc INVERTED UNDERTIE
2055..205E ; Pattern_Syntax # Po [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS
2190..2194 ; Pattern_Syntax # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
2195..2199 ; Pattern_Syntax # So [5] UP DOWN ARROW..SOUTH WEST ARROW
219A..219B ; Pattern_Syntax # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE
219C..219F ; Pattern_Syntax # So [4] LEFTWARDS WAVE ARROW..UPWARDS TWO HEADED ARROW
21A0 ; Pattern_Syntax # Sm RIGHTWARDS TWO HEADED ARROW
21A1..21A2 ; Pattern_Syntax # So [2] DOWNWARDS TWO HEADED ARROW..LEFTWARDS ARROW WITH TAIL
21A3 ; Pattern_Syntax # Sm RIGHTWARDS ARROW WITH TAIL
21A4..21A5 ; Pattern_Syntax # So [2] LEFTWARDS ARROW FROM BAR..UPWARDS ARROW FROM BAR
21A6 ; Pattern_Syntax # Sm RIGHTWARDS ARROW FROM BAR
21A7..21AD ; Pattern_Syntax # So [7] DOWNWARDS ARROW FROM BAR..LEFT RIGHT WAVE ARROW
21AE ; Pattern_Syntax # Sm LEFT RIGHT ARROW WITH STROKE
21AF..21CD ; Pattern_Syntax # So [31] DOWNWARDS ZIGZAG ARROW..LEFTWARDS DOUBLE ARROW WITH STROKE
21CE..21CF ; Pattern_Syntax # Sm [2] LEFT RIGHT DOUBLE ARROW WITH STROKE..RIGHTWARDS DOUBLE ARROW WITH STROKE
21D0..21D1 ; Pattern_Syntax # So [2] LEFTWARDS DOUBLE ARROW..UPWARDS DOUBLE ARROW
21D2 ; Pattern_Syntax # Sm RIGHTWARDS DOUBLE ARROW
21D3 ; Pattern_Syntax # So DOWNWARDS DOUBLE ARROW
21D4 ; Pattern_Syntax # Sm LEFT RIGHT DOUBLE ARROW
21D5..21F3 ; Pattern_Syntax # So [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW
21F4..22FF ; Pattern_Syntax # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP
2300..2307 ; Pattern_Syntax # So [8] DIAMETER SIGN..WAVY LINE
2308..230B ; Pattern_Syntax # Sm [4] LEFT CEILING..RIGHT FLOOR
230C..231F ; Pattern_Syntax # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER
2320..2321 ; Pattern_Syntax # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL
2322..2328 ; Pattern_Syntax # So [7] FROWN..KEYBOARD
2329 ; Pattern_Syntax # Ps LEFT-POINTING ANGLE BRACKET
232A ; Pattern_Syntax # Pe RIGHT-POINTING ANGLE BRACKET
232B..237B ; Pattern_Syntax # So [81] ERASE TO THE LEFT..NOT CHECK MARK
237C ; Pattern_Syntax # Sm RIGHT ANGLE WITH DOWNWARDS ZIGZAG ARROW
237D..239A ; Pattern_Syntax # So [30] SHOULDERED OPEN BOX..CLEAR SCREEN SYMBOL
239B..23B3 ; Pattern_Syntax # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM
23B4 ; Pattern_Syntax # Ps TOP SQUARE BRACKET
23B5 ; Pattern_Syntax # Pe BOTTOM SQUARE BRACKET
23B6 ; Pattern_Syntax # Po BOTTOM SQUARE BRACKET OVER TOP SQUARE BRACKET
23B7..23DB ; Pattern_Syntax # So [37] RADICAL SYMBOL BOTTOM..FUSE
23DC..23FF ; Pattern_Syntax # Cn [36] <reserved-23DC>..<reserved-23FF>
2400..2426 ; Pattern_Syntax # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
2427..243F ; Pattern_Syntax # Cn [25] <reserved-2427>..<reserved-243F>
2440..244A ; Pattern_Syntax # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
244B..245F ; Pattern_Syntax # Cn [21] <reserved-244B>..<reserved-245F>
2460..249B ; Pattern_Syntax # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP
249C..24E9 ; Pattern_Syntax # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
24EA..24FF ; Pattern_Syntax # No [22] CIRCLED DIGIT ZERO..NEGATIVE CIRCLED DIGIT ZERO
2500..25B6 ; Pattern_Syntax # So [183] BOX DRAWINGS LIGHT HORIZONTAL..BLACK RIGHT-POINTING TRIANGLE
25B7 ; Pattern_Syntax # Sm WHITE RIGHT-POINTING TRIANGLE
25B8..25C0 ; Pattern_Syntax # So [9] BLACK RIGHT-POINTING SMALL TRIANGLE..BLACK LEFT-POINTING TRIANGLE
25C1 ; Pattern_Syntax # Sm WHITE LEFT-POINTING TRIANGLE
25C2..25F7 ; Pattern_Syntax # So [54] BLACK LEFT-POINTING SMALL TRIANGLE..WHITE CIRCLE WITH UPPER RIGHT QUADRANT
25F8..25FF ; Pattern_Syntax # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE
2600..266E ; Pattern_Syntax # So [111] BLACK SUN WITH RAYS..MUSIC NATURAL SIGN
266F ; Pattern_Syntax # Sm MUSIC SHARP SIGN
2670..269C ; Pattern_Syntax # So [45] WEST SYRIAC CROSS..FLEUR-DE-LIS
269D..269F ; Pattern_Syntax # Cn [3] <reserved-269D>..<reserved-269F>
26A0..26B1 ; Pattern_Syntax # So [18] WARNING SIGN..FUNERAL URN
26B2..2700 ; Pattern_Syntax # Cn [79] <reserved-26B2>..<reserved-2700>
2701..2704 ; Pattern_Syntax # So [4] UPPER BLADE SCISSORS..WHITE SCISSORS
2705 ; Pattern_Syntax # Cn <reserved-2705>
2706..2709 ; Pattern_Syntax # So [4] TELEPHONE LOCATION SIGN..ENVELOPE
270A..270B ; Pattern_Syntax # Cn [2] <reserved-270A>..<reserved-270B>
270C..2727 ; Pattern_Syntax # So [28] VICTORY HAND..WHITE FOUR POINTED STAR
2728 ; Pattern_Syntax # Cn <reserved-2728>
2729..274B ; Pattern_Syntax # So [35] STRESS OUTLINED WHITE STAR..HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK
274C ; Pattern_Syntax # Cn <reserved-274C>
274D ; Pattern_Syntax # So SHADOWED WHITE CIRCLE
274E ; Pattern_Syntax # Cn <reserved-274E>
274F..2752 ; Pattern_Syntax # So [4] LOWER RIGHT DROP-SHADOWED WHITE SQUARE..UPPER RIGHT SHADOWED WHITE SQUARE
2753..2755 ; Pattern_Syntax # Cn [3] <reserved-2753>..<reserved-2755>
2756 ; Pattern_Syntax # So BLACK DIAMOND MINUS WHITE X
2757 ; Pattern_Syntax # Cn <reserved-2757>
2758..275E ; Pattern_Syntax # So [7] LIGHT VERTICAL BAR..HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT
275F..2760 ; Pattern_Syntax # Cn [2] <reserved-275F>..<reserved-2760>
2761..2767 ; Pattern_Syntax # So [7] CURVED STEM PARAGRAPH SIGN ORNAMENT..ROTATED FLORAL HEART BULLET
2768 ; Pattern_Syntax # Ps MEDIUM LEFT PARENTHESIS ORNAMENT
2769 ; Pattern_Syntax # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT
276A ; Pattern_Syntax # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT
276B ; Pattern_Syntax # Pe MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT
276C ; Pattern_Syntax # Ps MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT
276D ; Pattern_Syntax # Pe MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT
276E ; Pattern_Syntax # Ps HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT
276F ; Pattern_Syntax # Pe HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
2770 ; Pattern_Syntax # Ps HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT
2771 ; Pattern_Syntax # Pe HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT
2772 ; Pattern_Syntax # Ps LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT
2773 ; Pattern_Syntax # Pe LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT
2774 ; Pattern_Syntax # Ps MEDIUM LEFT CURLY BRACKET ORNAMENT
2775 ; Pattern_Syntax # Pe MEDIUM RIGHT CURLY BRACKET ORNAMENT
2776..2793 ; Pattern_Syntax # No [30] DINGBAT NEGATIVE CIRCLED DIGIT ONE..DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN
2794 ; Pattern_Syntax # So HEAVY WIDE-HEADED RIGHTWARDS ARROW
2795..2797 ; Pattern_Syntax # Cn [3] <reserved-2795>..<reserved-2797>
2798..27AF ; Pattern_Syntax # So [24] HEAVY SOUTH EAST ARROW..NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
27B0 ; Pattern_Syntax # Cn <reserved-27B0>
27B1..27BE ; Pattern_Syntax # So [14] NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW..OPEN-OUTLINED RIGHTWARDS ARROW
27BF ; Pattern_Syntax # Cn <reserved-27BF>
27C0..27C4 ; Pattern_Syntax # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Pattern_Syntax # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Pattern_Syntax # Pe RIGHT S-SHAPED BAG DELIMITER
27C7..27CF ; Pattern_Syntax # Cn [9] <reserved-27C7>..<reserved-27CF>
27D0..27E5 ; Pattern_Syntax # Sm [22] WHITE DIAMOND WITH CENTRED DOT..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Pattern_Syntax # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Pattern_Syntax # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8 ; Pattern_Syntax # Ps MATHEMATICAL LEFT ANGLE BRACKET
27E9 ; Pattern_Syntax # Pe MATHEMATICAL RIGHT ANGLE BRACKET
27EA ; Pattern_Syntax # Ps MATHEMATICAL LEFT DOUBLE ANGLE BRACKET
27EB ; Pattern_Syntax # Pe MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET
27EC..27EF ; Pattern_Syntax # Cn [4] <reserved-27EC>..<reserved-27EF>
27F0..27FF ; Pattern_Syntax # Sm [16] UPWARDS QUADRUPLE ARROW..LONG RIGHTWARDS SQUIGGLE ARROW
2800..28FF ; Pattern_Syntax # So [256] BRAILLE PATTERN BLANK..BRAILLE PATTERN DOTS-12345678
2900..2982 ; Pattern_Syntax # Sm [131] RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE..Z NOTATION TYPE COLON
2983 ; Pattern_Syntax # Ps LEFT WHITE CURLY BRACKET
2984 ; Pattern_Syntax # Pe RIGHT WHITE CURLY BRACKET
2985 ; Pattern_Syntax # Ps LEFT WHITE PARENTHESIS
2986 ; Pattern_Syntax # Pe RIGHT WHITE PARENTHESIS
2987 ; Pattern_Syntax # Ps Z NOTATION LEFT IMAGE BRACKET
2988 ; Pattern_Syntax # Pe Z NOTATION RIGHT IMAGE BRACKET
2989 ; Pattern_Syntax # Ps Z NOTATION LEFT BINDING BRACKET
298A ; Pattern_Syntax # Pe Z NOTATION RIGHT BINDING BRACKET
298B ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH UNDERBAR
298C ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH UNDERBAR
298D ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH TICK IN TOP CORNER
298E ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
298F ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
2990 ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER
2991 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET WITH DOT
2992 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET WITH DOT
2993 ; Pattern_Syntax # Ps LEFT ARC LESS-THAN BRACKET
2994 ; Pattern_Syntax # Pe RIGHT ARC GREATER-THAN BRACKET
2995 ; Pattern_Syntax # Ps DOUBLE LEFT ARC GREATER-THAN BRACKET
2996 ; Pattern_Syntax # Pe DOUBLE RIGHT ARC LESS-THAN BRACKET
2997 ; Pattern_Syntax # Ps LEFT BLACK TORTOISE SHELL BRACKET
2998 ; Pattern_Syntax # Pe RIGHT BLACK TORTOISE SHELL BRACKET
2999..29D7 ; Pattern_Syntax # Sm [63] DOTTED FENCE..BLACK HOURGLASS
29D8 ; Pattern_Syntax # Ps LEFT WIGGLY FENCE
29D9 ; Pattern_Syntax # Pe RIGHT WIGGLY FENCE
29DA ; Pattern_Syntax # Ps LEFT DOUBLE WIGGLY FENCE
29DB ; Pattern_Syntax # Pe RIGHT DOUBLE WIGGLY FENCE
29DC..29FB ; Pattern_Syntax # Sm [32] INCOMPLETE INFINITY..TRIPLE PLUS
29FC ; Pattern_Syntax # Ps LEFT-POINTING CURVED ANGLE BRACKET
29FD ; Pattern_Syntax # Pe RIGHT-POINTING CURVED ANGLE BRACKET
29FE..2AFF ; Pattern_Syntax # Sm [258] TINY..N-ARY WHITE VERTICAL BAR
2B00..2B13 ; Pattern_Syntax # So [20] NORTH EAST WHITE ARROW..SQUARE WITH BOTTOM HALF BLACK
2B14..2BFF ; Pattern_Syntax # Cn [236] <reserved-2B14>..<reserved-2BFF>
2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Pattern_Syntax # Ps LEFT SUBSTITUTION BRACKET
2E03 ; Pattern_Syntax # Pe RIGHT SUBSTITUTION BRACKET
2E04 ; Pattern_Syntax # Ps LEFT DOTTED SUBSTITUTION BRACKET
2E05 ; Pattern_Syntax # Pe RIGHT DOTTED SUBSTITUTION BRACKET
2E06..2E08 ; Pattern_Syntax # Po [3] RAISED INTERPOLATION MARKER..DOTTED TRANSPOSITION MARKER
2E09 ; Pattern_Syntax # Ps LEFT TRANSPOSITION BRACKET
2E0A ; Pattern_Syntax # Pe RIGHT TRANSPOSITION BRACKET
2E0B ; Pattern_Syntax # Po RAISED SQUARE
2E0C ; Pattern_Syntax # Pi LEFT RAISED OMISSION BRACKET
2E0D ; Pattern_Syntax # Pf RIGHT RAISED OMISSION BRACKET
2E0E..2E16 ; Pattern_Syntax # Po [9] EDITORIAL CORONIS..DOTTED RIGHT-POINTING ANGLE
2E17 ; Pattern_Syntax # Pd DOUBLE OBLIQUE HYPHEN
2E18..2E1B ; Pattern_Syntax # Cn [4] <reserved-2E18>..<reserved-2E1B>
2E1C ; Pattern_Syntax # Ps LEFT LOW PARAPHRASE BRACKET
2E1D ; Pattern_Syntax # Pe RIGHT LOW PARAPHRASE BRACKET
2E1E..2E7F ; Pattern_Syntax # Cn [98] <reserved-2E1E>..<reserved-2E7F>
3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET
3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET
300A ; Pattern_Syntax # Ps LEFT DOUBLE ANGLE BRACKET
300B ; Pattern_Syntax # Pe RIGHT DOUBLE ANGLE BRACKET
300C ; Pattern_Syntax # Ps LEFT CORNER BRACKET
300D ; Pattern_Syntax # Pe RIGHT CORNER BRACKET
300E ; Pattern_Syntax # Ps LEFT WHITE CORNER BRACKET
300F ; Pattern_Syntax # Pe RIGHT WHITE CORNER BRACKET
3010 ; Pattern_Syntax # Ps LEFT BLACK LENTICULAR BRACKET
3011 ; Pattern_Syntax # Pe RIGHT BLACK LENTICULAR BRACKET
3012..3013 ; Pattern_Syntax # So [2] POSTAL MARK..GETA MARK
3014 ; Pattern_Syntax # Ps LEFT TORTOISE SHELL BRACKET
3015 ; Pattern_Syntax # Pe RIGHT TORTOISE SHELL BRACKET
3016 ; Pattern_Syntax # Ps LEFT WHITE LENTICULAR BRACKET
3017 ; Pattern_Syntax # Pe RIGHT WHITE LENTICULAR BRACKET
3018 ; Pattern_Syntax # Ps LEFT WHITE TORTOISE SHELL BRACKET
3019 ; Pattern_Syntax # Pe RIGHT WHITE TORTOISE SHELL BRACKET
301A ; Pattern_Syntax # Ps LEFT WHITE SQUARE BRACKET
301B ; Pattern_Syntax # Pe RIGHT WHITE SQUARE BRACKET
301C ; Pattern_Syntax # Pd WAVE DASH
301D ; Pattern_Syntax # Ps REVERSED DOUBLE PRIME QUOTATION MARK
301E..301F ; Pattern_Syntax # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK
3020 ; Pattern_Syntax # So POSTAL MARK FACE
3030 ; Pattern_Syntax # Pd WAVY DASH
FD3E ; Pattern_Syntax # Ps ORNATE LEFT PARENTHESIS
FD3F ; Pattern_Syntax # Pe ORNATE RIGHT PARENTHESIS
FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT
# Total code points: 2955

14
icu4c/source/data/unidata/PropertyAliases.txt
View File

@ -1,8 +1,8 @@
# PropertyAliases-4.0.1.txt
# Date: 2004-03-02, 19:47:55 GMT [MD]
# PropertyAliases-4.1.0.txt
# Date: 2004-12-11, 05:46:23 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
# This file contains aliases for properties used in the UCD.
@ -90,6 +90,7 @@ ccc ; Canonical_Combining_Class
dt ; Decomposition_Type
ea ; East_Asian_Width
gc ; General_Category
GCB ; Grapheme_Cluster_Break
hst ; Hangul_Syllable_Type
jg ; Joining_Group
jt ; Joining_Type
@ -99,6 +100,8 @@ NFD_QC ; NFD_Quick_Check
NFKC_QC ; NFKC_Quick_Check
NFKD_QC ; NFKD_Quick_Check
nt ; Numeric_Type
SB ; Sentence_Break
WB ; Word_Break
# ================================================
# Binary Properties
@ -132,10 +135,13 @@ NChar ; Noncharacter_Code_Point
OAlpha ; Other_Alphabetic
ODI ; Other_Default_Ignorable_Code_Point
OGr_Ext ; Other_Grapheme_Extend
OIDC ; Other_ID_Continue
OIDS ; Other_ID_Start
OLower ; Other_Lowercase
OMath ; Other_Math
OUpper ; Other_Uppercase
Pat_Syn ; Pattern_Syntax
Pat_WS ; Pattern_White_Space
QMark ; Quotation_Mark
Radical ; Radical
SD ; Soft_Dotted
@ -153,5 +159,5 @@ XO_NFKC ; Expands_On_NFKC
XO_NFKD ; Expands_On_NFKD
# ================================================
# Total: 82
# Total: 88

77
icu4c/source/data/unidata/PropertyValueAliases.txt
View File

@ -1,8 +1,8 @@
# PropertyValueAliases-4.0.1.txt
# Date: 2004-03-02, 19:46:47 GMT [MD]
# PropertyValueAliases-4.1.0.txt
# Date: 2004-12-11, 05:46:23 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
# This file contains aliases for property values used in the UCD.
@ -63,6 +63,7 @@ age; n/a ; 3.0
age; n/a ; 3.1
age; n/a ; 3.2
age; n/a ; 4.0
age; n/a ; 4.1
age; n/a ; unassigned
# Bidi_Class (bc)
@ -91,9 +92,12 @@ bc ; WS ; White_Space
blk; n/a ; Aegean_Numbers
blk; n/a ; Alphabetic_Presentation_Forms
blk; n/a ; Ancient_Greek_Musical_Notation
blk; n/a ; Ancient_Greek_Numbers
blk; n/a ; Arabic
blk; n/a ; Arabic_Presentation_Forms-A
blk; n/a ; Arabic_Presentation_Forms-B
blk; n/a ; Arabic_Supplement
blk; n/a ; Armenian
blk; n/a ; Arrows
blk; n/a ; Basic_Latin
@ -103,9 +107,11 @@ blk; n/a ; Bopomofo
blk; n/a ; Bopomofo_Extended
blk; n/a ; Box_Drawing
blk; n/a ; Braille_Patterns
blk; n/a ; Buginese
blk; n/a ; Buhid
blk; n/a ; Byzantine_Musical_Symbols
blk; n/a ; Cherokee
blk; n/a ; CJK_Basic_Strokes
blk; n/a ; CJK_Compatibility
blk; n/a ; CJK_Compatibility_Forms
blk; n/a ; CJK_Compatibility_Ideographs
@ -117,8 +123,10 @@ blk; n/a ; CJK_Unified_Ideographs_Extension_A
blk; n/a ; CJK_Unified_Ideographs_Extension_B
blk; n/a ; Combining_Diacritical_Marks
blk; n/a ; Combining_Diacritical_Marks_for_Symbols
blk; n/a ; Combining_Diacritical_Marks_Supplement
blk; n/a ; Combining_Half_Marks
blk; n/a ; Control_Pictures
blk; n/a ; Coptic
blk; n/a ; Currency_Symbols
blk; n/a ; Cypriot_Syllabary
blk; n/a ; Cyrillic
@ -129,9 +137,13 @@ blk; n/a ; Dingbats
blk; n/a ; Enclosed_Alphanumerics
blk; n/a ; Enclosed_CJK_Letters_and_Months
blk; n/a ; Ethiopic
blk; n/a ; Ethiopic_Extended
blk; n/a ; Ethiopic_Supplement
blk; n/a ; General_Punctuation
blk; n/a ; Geometric_Shapes
blk; n/a ; Georgian
blk; n/a ; Georgian_Supplement
blk; n/a ; Glagolitic
blk; n/a ; Gothic
blk; n/a ; Greek_and_Coptic
blk; n/a ; Greek_Extended
@ -153,6 +165,7 @@ blk; n/a ; Kangxi_Radicals
blk; n/a ; Kannada
blk; n/a ; Katakana
blk; n/a ; Katakana_Phonetic_Extensions
blk; n/a ; Kharoshthi
blk; n/a ; Khmer
blk; n/a ; Khmer_Symbols
blk; n/a ; Lao
@ -173,17 +186,21 @@ blk; n/a ; Miscellaneous_Mathematical_Symbols-B
blk; n/a ; Miscellaneous_Symbols
blk; n/a ; Miscellaneous_Symbols_and_Arrows
blk; n/a ; Miscellaneous_Technical
blk; n/a ; Modifier_Tone_Letters
blk; n/a ; Mongolian
blk; n/a ; Musical_Symbols
blk; n/a ; Myanmar
blk; n/a ; New_Tai_Lue
blk; n/a ; No_Block
blk; n/a ; Number_Forms
blk; n/a ; Ogham
blk; n/a ; Old_Italic
blk; n/a ; Old_Persian
blk; n/a ; Optical_Character_Recognition
blk; n/a ; Oriya
blk; n/a ; Osmanya
blk; n/a ; Phonetic_Extensions
blk; n/a ; Phonetic_Extensions_Supplement
blk; n/a ; Private_Use_Area
blk; n/a ; Runic
blk; n/a ; Shavian
@ -195,8 +212,10 @@ blk; n/a ; Superscripts_and_Subscripts
blk; n/a ; Supplemental_Arrows-A
blk; n/a ; Supplemental_Arrows-B
blk; n/a ; Supplemental_Mathematical_Operators
blk; n/a ; Supplemental_Punctuation
blk; n/a ; Supplementary_Private_Use_Area-A
blk; n/a ; Supplementary_Private_Use_Area-B
blk; n/a ; Syloti_Nagri
blk; n/a ; Syriac
blk; n/a ; Tagalog
blk; n/a ; Tagbanwa
@ -208,10 +227,12 @@ blk; n/a ; Telugu
blk; n/a ; Thaana
blk; n/a ; Thai
blk; n/a ; Tibetan
blk; n/a ; Tifinagh
blk; n/a ; Ugaritic
blk; n/a ; Unified_Canadian_Aboriginal_Syllabics
blk; n/a ; Variation_Selectors
blk; n/a ; Variation_Selectors_Supplement
blk; n/a ; Vertical_Forms
blk; n/a ; Yi_Radicals
blk; n/a ; Yi_Syllables
blk; n/a ; Yijing_Hexagram_Symbols
@ -309,6 +330,19 @@ gc ; Zl ; Line_Separator
gc ; Zp ; Paragraph_Separator
gc ; Zs ; Space_Separator
# Grapheme_Cluster_Break (GCB)
GCB; Control ; Control
GCB; CR ; CR
GCB; Extend ; Extend
GCB; L ; L
GCB; LF ; LF
GCB; LV ; LV
GCB; LVT ; LVT
GCB; Other ; Other
GCB; T ; T
GCB; V ; V
# Hangul_Syllable_Type (hst)
hst; L ; Leading_Jamo
@ -398,10 +432,15 @@ lb ; CM ; Combining_Mark
lb ; CR ; Carriage_Return
lb ; EX ; Exclamation
lb ; GL ; Glue
lb ; H2 ; H2
lb ; H3 ; H3
lb ; HY ; Hyphen
lb ; ID ; Ideographic
lb ; IN ; Inseparable ; Inseperable
lb ; IS ; Infix_Numeric
lb ; JL ; JL
lb ; JT ; JT
lb ; JV ; JV
lb ; LF ; Line_Feed
lb ; NL ; Next_Line
lb ; NS ; Nonstarter
@ -454,15 +493,18 @@ sc ; Armn ; Armenian
sc ; Beng ; Bengali
sc ; Bopo ; Bopomofo
sc ; Brai ; Braille
sc ; Bugi ; Buginese
sc ; Buhd ; Buhid
sc ; Cans ; Canadian_Aboriginal
sc ; Cher ; Cherokee
sc ; Copt ; Coptic
sc ; Cprt ; Cypriot
sc ; Cyrl ; Cyrillic
sc ; Deva ; Devanagari
sc ; Dsrt ; Deseret
sc ; Ethi ; Ethiopic
sc ; Geor ; Georgian
sc ; Glag ; Glagolitic
sc ; Goth ; Gothic
sc ; Grek ; Greek
sc ; Gujr ; Gujarati
@ -475,6 +517,7 @@ sc ; Hira ; Hiragana
sc ; Hrkt ; Katakana_Or_Hiragana
sc ; Ital ; Old_Italic
sc ; Kana ; Katakana
sc ; Khar ; Kharoshthi
sc ; Khmr ; Khmer
sc ; Knda ; Kannada
sc ; Laoo ; Lao
@ -491,15 +534,43 @@ sc ; Qaai ; Inherited
sc ; Runr ; Runic
sc ; Shaw ; Shavian
sc ; Sinh ; Sinhala
sc ; Sylo ; Syloti_Nagri
sc ; Syrc ; Syriac
sc ; Tagb ; Tagbanwa
sc ; Tale ; Tai_Le
sc ; Talu ; New_Tai_Lue
sc ; Taml ; Tamil
sc ; Telu ; Telugu
sc ; Tfng ; Tifinagh
sc ; Tglg ; Tagalog
sc ; Thaa ; Thaana
sc ; Thai ; Thai
sc ; Tibt ; Tibetan
sc ; Ugar ; Ugaritic
sc ; Xpeo ; Old_Persian
sc ; Yiii ; Yi
sc ; Zyyy ; Common
# Sentence_Break (SB)
SB ; ATerm ; ATerm
SB ; Close ; Close
SB ; Format ; Format
SB ; Lower ; Lower
SB ; Numeric ; Numeric
SB ; OLetter ; OLetter
SB ; Other ; Other
SB ; Sep ; Sep
SB ; Sp ; Sp
SB ; STerm ; STerm
SB ; Upper ; Upper
# Word_Break (WB)
WB ; ALetter ; ALetter
WB ; Format ; Format
WB ; Katakana ; Katakana
WB ; MidLetter ; MidLetter
WB ; MidNum ; MidNum
WB ; Numeric ; Numeric
WB ; Other ; Other

278
icu4c/source/data/unidata/Scripts.txt
View File

@ -1,8 +1,8 @@
# Scripts-4.0.1.txt
# Date: 2004-03-11, 18:47:37 GMT [MD]
# Scripts-4.1.0.txt
# Date: 2004-12-11, 05:46:26 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2004 Unicode, Inc.
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
@ -120,7 +120,7 @@
2052 ; Common # Sm COMMERCIAL MINUS SIGN
2053 ; Common # Po SWUNG DASH
2054 ; Common # Pc INVERTED UNDERTIE
2057 ; Common # Po QUADRUPLE PRIME
2055..205E ; Common # Po [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS
205F ; Common # Zs MEDIUM MATHEMATICAL SPACE
2060..2063 ; Common # Cf [4] WORD JOINER..INVISIBLE SEPARATOR
206A..206F ; Common # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
@ -133,7 +133,7 @@
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
20A0..20B1 ; Common # Sc [18] EURO-CURRENCY SIGN..PESO SIGN
20A0..20B5 ; Common # Sc [22] EURO-CURRENCY SIGN..CEDI SIGN
2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
2102 ; Common # L& DOUBLE-STRUCK CAPITAL C
2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA
@ -158,11 +158,12 @@
2135..2138 ; Common # Lo [4] ALEF SYMBOL..DALET SYMBOL
2139 ; Common # L& INFORMATION SOURCE
213A..213B ; Common # So [2] ROTATED CAPITAL Q..FACSIMILE SIGN
213D..213F ; Common # L& [3] DOUBLE-STRUCK SMALL GAMMA..DOUBLE-STRUCK CAPITAL PI
213C..213F ; Common # L& [4] DOUBLE-STRUCK SMALL PI..DOUBLE-STRUCK CAPITAL PI
2140..2144 ; Common # Sm [5] DOUBLE-STRUCK N-ARY SUMMATION..TURNED SANS-SERIF CAPITAL Y
2145..2149 ; Common # L& [5] DOUBLE-STRUCK ITALIC CAPITAL D..DOUBLE-STRUCK ITALIC SMALL J
214A ; Common # So PROPERTY LINE
214B ; Common # Sm TURNED AMPERSAND
214C ; Common # So PER SIGN
2153..215F ; Common # No [13] VULGAR FRACTION ONE THIRD..FRACTION NUMERATOR ONE
2160..2183 ; Common # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED
2190..2194 ; Common # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
@ -198,7 +199,7 @@
23B4 ; Common # Ps TOP SQUARE BRACKET
23B5 ; Common # Pe BOTTOM SQUARE BRACKET
23B6 ; Common # Po BOTTOM SQUARE BRACKET OVER TOP SQUARE BRACKET
23B7..23D0 ; Common # So [26] RADICAL SYMBOL BOTTOM..VERTICAL LINE EXTENSION
23B7..23DB ; Common # So [37] RADICAL SYMBOL BOTTOM..FUSE
2400..2426 ; Common # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
2440..244A ; Common # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..249B ; Common # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP
@ -210,12 +211,10 @@
25C1 ; Common # Sm WHITE LEFT-POINTING TRIANGLE
25C2..25F7 ; Common # So [54] BLACK LEFT-POINTING SMALL TRIANGLE..WHITE CIRCLE WITH UPPER RIGHT QUADRANT
25F8..25FF ; Common # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE
2600..2617 ; Common # So [24] BLACK SUN WITH RAYS..BLACK SHOGI PIECE
2619..266E ; Common # So [86] REVERSED ROTATED FLORAL HEART BULLET..MUSIC NATURAL SIGN
2600..266E ; Common # So [111] BLACK SUN WITH RAYS..MUSIC NATURAL SIGN
266F ; Common # Sm MUSIC SHARP SIGN
2670..267D ; Common # So [14] WEST SYRIAC CROSS..PARTIALLY-RECYCLED PAPER SYMBOL
2680..2691 ; Common # So [18] DIE FACE-1..BLACK FLAG
26A0..26A1 ; Common # So [2] WARNING SIGN..HIGH VOLTAGE SIGN
2670..269C ; Common # So [45] WEST SYRIAC CROSS..FLEUR-DE-LIS
26A0..26B1 ; Common # So [18] WARNING SIGN..FUNERAL URN
2701..2704 ; Common # So [4] UPPER BLADE SCISSORS..WHITE SCISSORS
2706..2709 ; Common # So [4] TELEPHONE LOCATION SIGN..ENVELOPE
270C..2727 ; Common # So [28] VICTORY HAND..WHITE FOUR POINTED STAR
@ -243,6 +242,9 @@
2794 ; Common # So HEAVY WIDE-HEADED RIGHTWARDS ARROW
2798..27AF ; Common # So [24] HEAVY SOUTH EAST ARROW..NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
27B1..27BE ; Common # So [14] NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW..OPEN-OUTLINED RIGHTWARDS ARROW
27C0..27C4 ; Common # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
27C5 ; Common # Ps LEFT S-SHAPED BAG DELIMITER
27C6 ; Common # Pe RIGHT S-SHAPED BAG DELIMITER
27D0..27E5 ; Common # Sm [22] WHITE DIAMOND WITH CENTRED DOT..WHITE SQUARE WITH RIGHTWARDS TICK
27E6 ; Common # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7 ; Common # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
@ -283,7 +285,22 @@
29FC ; Common # Ps LEFT-POINTING CURVED ANGLE BRACKET
29FD ; Common # Pe RIGHT-POINTING CURVED ANGLE BRACKET
29FE..2AFF ; Common # Sm [258] TINY..N-ARY WHITE VERTICAL BAR
2B00..2B0D ; Common # So [14] NORTH EAST WHITE ARROW..UP DOWN BLACK ARROW
2B00..2B13 ; Common # So [20] NORTH EAST WHITE ARROW..SQUARE WITH BOTTOM HALF BLACK
2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Common # Ps LEFT SUBSTITUTION BRACKET
2E03 ; Common # Pe RIGHT SUBSTITUTION BRACKET
2E04 ; Common # Ps LEFT DOTTED SUBSTITUTION BRACKET
2E05 ; Common # Pe RIGHT DOTTED SUBSTITUTION BRACKET
2E06..2E08 ; Common # Po [3] RAISED INTERPOLATION MARKER..DOTTED TRANSPOSITION MARKER
2E09 ; Common # Ps LEFT TRANSPOSITION BRACKET
2E0A ; Common # Pe RIGHT TRANSPOSITION BRACKET
2E0B ; Common # Po RAISED SQUARE
2E0C ; Common # Pi LEFT RAISED OMISSION BRACKET
2E0D ; Common # Pf RIGHT RAISED OMISSION BRACKET
2E0E..2E16 ; Common # Po [9] EDITORIAL CORONIS..DOTTED RIGHT-POINTING ANGLE
2E17 ; Common # Pd DOUBLE OBLIQUE HYPHEN
2E1C ; Common # Ps LEFT LOW PARAPHRASE BRACKET
2E1D ; Common # Pe RIGHT LOW PARAPHRASE BRACKET
2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
3000 ; Common # Zs IDEOGRAPHIC SPACE
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
@ -313,31 +330,39 @@
301E..301F ; Common # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK
3020 ; Common # So POSTAL MARK FACE
3030 ; Common # Pd WAVY DASH
3031..3035 ; Common # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
3036..3037 ; Common # So [2] CIRCLED POSTAL MARK..IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL
303C ; Common # Lo MASU MARK
303D ; Common # Po PART ALTERNATION MARK
303E..303F ; Common # So [2] IDEOGRAPHIC VARIATION INDICATOR..IDEOGRAPHIC HALF FILL SPACE
309B..309C ; Common # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
30A0 ; Common # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
30FB ; Common # Pc KATAKANA MIDDLE DOT
30FB ; Common # Po KATAKANA MIDDLE DOT
30FC ; Common # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
3190..3191 ; Common # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK
3192..3195 ; Common # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK
31C0..31CF ; Common # So [16] CJK BASIC STROKE T..CJK BASIC STROKE N
3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN
322A..3243 ; Common # So [26] PARENTHESIZED IDEOGRAPH MOON..PARENTHESIZED IDEOGRAPH REACH
3250 ; Common # So PARTNERSHIP SIGN
3251..325F ; Common # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE
327F ; Common # So KOREAN STANDARD SYMBOL
327E..327F ; Common # So [2] CIRCLED HANGUL IEUNG U..KOREAN STANDARD SYMBOL
3280..3289 ; Common # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN
328A..32B0 ; Common # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT
32B1..32BF ; Common # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY
32C0..32FE ; Common # So [63] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..CIRCLED KATAKANA WO
3300..33FF ; Common # So [256] SQUARE APAATO..SQUARE GAL
4DC0..4DFF ; Common # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
A700..A716 ; Common # Sk [23] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR
E000..F8FF ; Common # Co [6400] <private-use-E000>..<private-use-F8FF>
FD3E ; Common # Ps ORNATE LEFT PARENTHESIS
FD3F ; Common # Pe ORNATE RIGHT PARENTHESIS
FDFD ; Common # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
FE10..FE16 ; Common # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK
FE17 ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET
FE18 ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET
FE19 ; Common # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
FE30 ; Common # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
FE31..FE32 ; Common # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
FE33..FE34 ; Common # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE
@ -408,8 +433,9 @@ FF60 ; Common # Pe FULLWIDTH RIGHT WHITE PARENTHESIS
FF61 ; Common # Po HALFWIDTH IDEOGRAPHIC FULL STOP
FF62 ; Common # Ps HALFWIDTH LEFT CORNER BRACKET
FF63 ; Common # Pe HALFWIDTH RIGHT CORNER BRACKET
FF64 ; Common # Po HALFWIDTH IDEOGRAPHIC COMMA
FF65 ; Common # Pc HALFWIDTH KATAKANA MIDDLE DOT
FF64..FF65 ; Common # Po [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDLE DOT
FF70 ; Common # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
FF9E..FF9F ; Common # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
FFE0..FFE1 ; Common # Sc [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN
FFE2 ; Common # Sm FULLWIDTH NOT SIGN
FFE3 ; Common # Sk FULLWIDTH MACRON
@ -453,7 +479,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1D540..1D544 ; Common # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M
1D546 ; Common # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O
1D54A..1D550 ; Common # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y
1D552..1D6A3 ; Common # L& [338] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL MONOSPACE SMALL Z
1D552..1D6A5 ; Common # L& [340] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL ITALIC SMALL DOTLESS J
1D6A8..1D6C0 ; Common # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA
1D6C1 ; Common # Sm MATHEMATICAL BOLD NABLA
1D6C2..1D6DA ; Common # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA
@ -481,8 +507,8 @@ E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
F0000..FFFFD ; Common # Co [65534] <private-use-F0000>..<private-use-FFFFD>
100000..10FFFD; Common # Co [65534] <private-use-100000>..<private-use-10FFFD>
# The above property value applies to 880197 code points not listed here.
# Total code points: 1022471
# The above property value applies to 878924 code points not listed here.
# Total code points: 1021355
# ================================================
@ -496,24 +522,27 @@ F0000..FFFFD ; Common # Co [65534] <private-use-F0000>..<private-use-FFFFD>
01BB ; Latin # Lo LATIN LETTER TWO WITH STROKE
01BC..01BF ; Latin # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN
01C0..01C3 ; Latin # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK
01C4..0236 ; Latin # L& [115] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER T WITH CURL
01C4..0241 ; Latin # L& [126] LATIN CAPITAL LETTER DZ WITH CARON..LATIN CAPITAL LETTER GLOTTAL STOP
0250..02AF ; Latin # L& [96] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
02B0..02B8 ; Latin # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
02E0..02E4 ; Latin # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
1D00..1D25 ; Latin # L& [38] LATIN LETTER SMALL CAPITAL A..LATIN LETTER AIN
1D2C..1D5C ; Latin # Lm [49] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL AIN
1D62..1D65 ; Latin # L& [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V
1D6B ; Latin # L& LATIN SMALL LETTER UE
1D6B..1D77 ; Latin # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
1D79..1D9A ; Latin # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF ; Latin # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
1E00..1E9B ; Latin # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE
1EA0..1EF9 ; Latin # L& [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE
2071 ; Latin # L& SUPERSCRIPT LATIN SMALL LETTER I
207F ; Latin # L& SUPERSCRIPT LATIN SMALL LETTER N
2090..2094 ; Latin # Lm [5] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER SCHWA
212A..212B ; Latin # L& [2] KELVIN SIGN..ANGSTROM SIGN
FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
# Total code points: 938
# Total code points: 1037
# ================================================
@ -525,9 +554,10 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
038C ; Greek # L& GREEK CAPITAL LETTER OMICRON WITH TONOS
038E..03A1 ; Greek # L& [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO
03A3..03CE ; Greek # L& [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS
03D0..03F5 ; Greek # L& [38] GREEK BETA SYMBOL..GREEK LUNATE EPSILON SYMBOL
03D0..03E1 ; Greek # L& [18] GREEK BETA SYMBOL..GREEK SMALL LETTER SAMPI
03F0..03F5 ; Greek # L& [6] GREEK KAPPA SYMBOL..GREEK LUNATE EPSILON SYMBOL
03F6 ; Greek # Sm GREEK REVERSED LUNATE EPSILON SYMBOL
03F7..03FB ; Greek # L& [5] GREEK CAPITAL LETTER SHO..GREEK SMALL LETTER SAN
03F7..03FF ; Greek # L& [9] GREEK CAPITAL LETTER SHO..GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
1D26..1D2A ; Greek # L& [5] GREEK LETTER SMALL CAPITAL GAMMA..GREEK LETTER SMALL CAPITAL PSI
1D5D..1D61 ; Greek # Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI
1D66..1D6A ; Greek # L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI
@ -557,8 +587,15 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
1FF6..1FFC ; Greek # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
1FFD..1FFE ; Greek # Sk [2] GREEK OXIA..GREEK DASIA
2126 ; Greek # L& OHM SIGN
10140..10174 ; Greek # Nl [53] GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ACROPHONIC STRATIAN FIFTY MNAS
10175..10178 ; Greek # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN
10179..10189 ; Greek # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN
1018A ; Greek # No GREEK ZERO SIGN
1D200..1D241 ; Greek # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D242..1D244 ; Greek # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1D245 ; Greek # So GREEK MUSICAL LEIMMA
# Total code points: 367
# Total code points: 502
# ================================================
@ -567,12 +604,12 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
0483..0486 ; Cyrillic # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA
0488..0489 ; Cyrillic # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
048A..04CE ; Cyrillic # L& [69] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EM WITH TAIL
04D0..04F5 ; Cyrillic # L& [38] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER CHE WITH DIAERESIS
04F8..04F9 ; Cyrillic # L& [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS
04D0..04F9 ; Cyrillic # L& [42] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER YERU WITH DIAERESIS
0500..050F ; Cyrillic # L& [16] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER KOMI TJE
1D2B ; Cyrillic # L& CYRILLIC LETTER SMALL CAPITAL EL
1D78 ; Cyrillic # Lm MODIFIER LETTER CYRILLIC EN
# Total code points: 263
# Total code points: 266
# ================================================
@ -587,15 +624,14 @@ FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SM
# ================================================
0591..05A1 ; Hebrew # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
05A3..05B9 ; Hebrew # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM
05BB..05BD ; Hebrew # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
0591..05BD ; Hebrew # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG
05BE ; Hebrew # Po HEBREW PUNCTUATION MAQAF
05BF ; Hebrew # Mn HEBREW POINT RAFE
05C0 ; Hebrew # Po HEBREW PUNCTUATION PASEQ
05C1..05C2 ; Hebrew # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
05C3 ; Hebrew # Po HEBREW PUNCTUATION SOF PASUQ
05C4 ; Hebrew # Mn HEBREW MARK UPPER DOT
05C4..05C5 ; Hebrew # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
05C6 ; Hebrew # Po HEBREW PUNCTUATION NUN HAFUKHA
05D0..05EA ; Hebrew # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
05F0..05F2 ; Hebrew # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD
05F3..05F4 ; Hebrew # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM
@ -610,16 +646,18 @@ FB40..FB41 ; Hebrew # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER S
FB43..FB44 ; Hebrew # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH
FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED
# Total code points: 128
# Total code points: 132
# ================================================
060B ; Arabic # Sc AFGHANI SIGN
060D ; Arabic # Po ARABIC DATE SEPARATOR
060E..060F ; Arabic # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA
0610..0615 ; Arabic # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH
061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK
0621..063A ; Arabic # Lo [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN
0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH
0656..0658 ; Arabic # Mn [3] ARABIC SUBSCRIPT ALEF..ARABIC MARK NOON GHUNNA
0656..065E ; Arabic # Mn [9] ARABIC SUBSCRIPT ALEF..ARABIC FATHA WITH TWO DOTS
066A..066D ; Arabic # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR
066E..066F ; Arabic # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
0671..06D3 ; Arabic # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
@ -637,6 +675,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
06FA..06FC ; Arabic # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW
06FD..06FE ; Arabic # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN
06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V
0750..076D ; Arabic # Lo [30] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE
FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM
FD50..FD8F ; Arabic # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
@ -646,7 +685,7 @@ FDFC ; Arabic # Sc RIAL SIGN
FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM
FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
# Total code points: 928
# Total code points: 966
# ================================================
@ -684,8 +723,9 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
0958..0961 ; Devanagari # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL
0962..0963 ; Devanagari # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
0966..096F ; Devanagari # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
097D ; Devanagari # Lo DEVANAGARI LETTER GLOTTAL STOP
# Total code points: 102
# Total code points: 103
# ================================================
@ -704,6 +744,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
09C7..09C8 ; Bengali # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
09CB..09CC ; Bengali # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU
09CD ; Bengali # Mn BENGALI SIGN VIRAMA
09CE ; Bengali # Lo BENGALI LETTER KHANDA TA
09D7 ; Bengali # Mc BENGALI AU LENGTH MARK
09DC..09DD ; Bengali # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E1 ; Bengali # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
@ -714,7 +755,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
09F4..09F9 ; Bengali # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN
09FA ; Bengali # So BENGALI ISSHAR
# Total code points: 90
# Total code points: 91
# ================================================
@ -807,8 +848,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
0B9E..0B9F ; Tamil # Lo [2] TAMIL LETTER NYA..TAMIL LETTER TTA
0BA3..0BA4 ; Tamil # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA
0BA8..0BAA ; Tamil # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA
0BAE..0BB5 ; Tamil # Lo [8] TAMIL LETTER MA..TAMIL LETTER VA
0BB7..0BB9 ; Tamil # Lo [3] TAMIL LETTER SSA..TAMIL LETTER HA
0BAE..0BB9 ; Tamil # Lo [12] TAMIL LETTER MA..TAMIL LETTER HA
0BBE..0BBF ; Tamil # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I
0BC0 ; Tamil # Mn TAMIL VOWEL SIGN II
0BC1..0BC2 ; Tamil # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU
@ -816,13 +856,13 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
0BCA..0BCC ; Tamil # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU
0BCD ; Tamil # Mn TAMIL SIGN VIRAMA
0BD7 ; Tamil # Mc TAMIL AU LENGTH MARK
0BE7..0BEF ; Tamil # Nd [9] TAMIL DIGIT ONE..TAMIL DIGIT NINE
0BE6..0BEF ; Tamil # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE
0BF0..0BF2 ; Tamil # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND
0BF3..0BF8 ; Tamil # So [6] TAMIL DAY SIGN..TAMIL AS ABOVE SIGN
0BF9 ; Tamil # Sc TAMIL RUPEE SIGN
0BFA ; Tamil # So TAMIL NUMBER SIGN
# Total code points: 69
# Total code points: 71
# ================================================
@ -979,8 +1019,9 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
0FC6 ; Tibetan # Mn TIBETAN SYMBOL PADMA GDAN
0FC7..0FCC ; Tibetan # So [6] TIBETAN SYMBOL RDO RJE RGYA GRAM..TIBETAN SYMBOL NOR BU BZHI -KHYIL
0FCF ; Tibetan # So TIBETAN SIGN RDEL NAG GSUM
0FD0..0FD1 ; Tibetan # Po [2] TIBETAN MARK BSKA- SHOG GI MGO RGYAN..TIBETAN MARK MNYAM YIG GI MGO RGYAN
# Total code points: 193
# Total code points: 195
# ================================================
@ -1005,9 +1046,11 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
# ================================================
10A0..10C5 ; Georgian # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10D0..10F8 ; Georgian # Lo [41] GEORGIAN LETTER AN..GEORGIAN LETTER ELIFI
10D0..10FA ; Georgian # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
10FC ; Georgian # Lm MODIFIER LETTER GEORGIAN NAR
2D00..2D25 ; Georgian # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE
# Total code points: 79
# Total code points: 120
# ================================================
@ -1028,36 +1071,38 @@ FFDA..FFDC ; Hangul # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL L
# ================================================
1200..1206 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE HO
1208..1246 ; Ethiopic # Lo [63] ETHIOPIC SYLLABLE LA..ETHIOPIC SYLLABLE QO
1248 ; Ethiopic # Lo ETHIOPIC SYLLABLE QWA
1200..1248 ; Ethiopic # Lo [73] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE QWA
124A..124D ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE
1250..1256 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO
1258 ; Ethiopic # Lo ETHIOPIC SYLLABLE QHWA
125A..125D ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE QHWI..ETHIOPIC SYLLABLE QHWE
1260..1286 ; Ethiopic # Lo [39] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XO
1288 ; Ethiopic # Lo ETHIOPIC SYLLABLE XWA
1260..1288 ; Ethiopic # Lo [41] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XWA
128A..128D ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE XWI..ETHIOPIC SYLLABLE XWE
1290..12AE ; Ethiopic # Lo [31] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KO
12B0 ; Ethiopic # Lo ETHIOPIC SYLLABLE KWA
1290..12B0 ; Ethiopic # Lo [33] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KWA
12B2..12B5 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE KWI..ETHIOPIC SYLLABLE KWE
12B8..12BE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE KXA..ETHIOPIC SYLLABLE KXO
12C0 ; Ethiopic # Lo ETHIOPIC SYLLABLE KXWA
12C2..12C5 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE KXWI..ETHIOPIC SYLLABLE KXWE
12C8..12CE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE WO
12D0..12D6 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE PHARYNGEAL A..ETHIOPIC SYLLABLE PHARYNGEAL O
12D8..12EE ; Ethiopic # Lo [23] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE YO
12F0..130E ; Ethiopic # Lo [31] ETHIOPIC SYLLABLE DA..ETHIOPIC SYLLABLE GO
1310 ; Ethiopic # Lo ETHIOPIC SYLLABLE GWA
12C8..12D6 ; Ethiopic # Lo [15] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE PHARYNGEAL O
12D8..1310 ; Ethiopic # Lo [57] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE GWA
1312..1315 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
1318..131E ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE GGO
1320..1346 ; Ethiopic # Lo [39] ETHIOPIC SYLLABLE THA..ETHIOPIC SYLLABLE TZO
1348..135A ; Ethiopic # Lo [19] ETHIOPIC SYLLABLE FA..ETHIOPIC SYLLABLE FYA
1361..1368 ; Ethiopic # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
1369..1371 ; Ethiopic # Nd [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE
1372..137C ; Ethiopic # No [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND
1318..135A ; Ethiopic # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
135F ; Ethiopic # Mn ETHIOPIC COMBINING GEMINATION MARK
1360..1368 ; Ethiopic # Po [9] ETHIOPIC SECTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
1369..137C ; Ethiopic # No [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND
1380..138F ; Ethiopic # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
1390..1399 ; Ethiopic # So [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
2D80..2D96 ; Ethiopic # Lo [23] ETHIOPIC SYLLABLE LOA..ETHIOPIC SYLLABLE GGWE
2DA0..2DA6 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE SSA..ETHIOPIC SYLLABLE SSO
2DA8..2DAE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE CCA..ETHIOPIC SYLLABLE CCO
2DB0..2DB6 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE ZZA..ETHIOPIC SYLLABLE ZZO
2DB8..2DBE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE CCHA..ETHIOPIC SYLLABLE CCHO
2DC0..2DC6 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE QYA..ETHIOPIC SYLLABLE QYO
2DC8..2DCE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE KYA..ETHIOPIC SYLLABLE KYO
2DD0..2DD6 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE XYA..ETHIOPIC SYLLABLE XYO
2DD8..2DDE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE GYA..ETHIOPIC SYLLABLE GYO
# Total code points: 345
# Total code points: 461
# ================================================
@ -1164,17 +1209,20 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FA5 ; Han # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
4E00..9FBB ; Han # Lo [20924] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FBB
F900..FA2D ; Han # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FA30..FA6A ; Han # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A
FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 71442
# Total code points: 71570
# ================================================
A000..A48C ; Yi # Lo [1165] YI SYLLABLE IT..YI SYLLABLE YYR
A000..A014 ; Yi # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; Yi # Lm YI SYLLABLE WU
A016..A48C ; Yi # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
# Total code points: 1220
@ -1201,16 +1249,16 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
# ================================================
0300..0357 ; Inherited # Mn [88] COMBINING GRAVE ACCENT..COMBINING RIGHT HALF RING ABOVE
035D..036F ; Inherited # Mn [19] COMBINING DOUBLE BREVE..COMBINING LATIN SMALL LETTER X
0300..036F ; Inherited # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
064B..0655 ; Inherited # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
0670 ; Inherited # Mn ARABIC LETTER SUPERSCRIPT ALEF
1DC0..1DC3 ; Inherited # Mn [4] COMBINING DOTTED GRAVE ACCENT..COMBINING SUSPENSION MARK
200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
20D0..20DC ; Inherited # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; Inherited # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1 ; Inherited # Mn COMBINING LEFT RIGHT ARROW ABOVE
20E2..20E4 ; Inherited # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE
20E5..20EA ; Inherited # Mn [6] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LEFTWARDS ARROW OVERLAY
20E5..20EB ; Inherited # Mn [7] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LONG DOUBLE SOLIDUS OVERLAY
302A..302F ; Inherited # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
3099..309A ; Inherited # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
FE00..FE0F ; Inherited # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
@ -1221,7 +1269,7 @@ FE20..FE23 ; Inherited # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOU
1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 438
# Total code points: 448
# ================================================
@ -1328,9 +1376,87 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
# ================================================
3031..3035 ; Katakana_Or_Hiragana # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
309B..309C ; Katakana_Or_Hiragana # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
FF70 ; Katakana_Or_Hiragana # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
FF9E..FF9F ; Katakana_Or_Hiragana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
1A00..1A16 ; Buginese # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA
1A17..1A18 ; Buginese # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
1A19..1A1B ; Buginese # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
1A1E..1A1F ; Buginese # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION
# Total code points: 10
# Total code points: 30
# ================================================
03E2..03EF ; Coptic # L& [14] COPTIC CAPITAL LETTER SHEI..COPTIC SMALL LETTER DEI
2C80..2CE4 ; Coptic # L& [101] COPTIC CAPITAL LETTER ALFA..COPTIC SYMBOL KAI
2CE5..2CEA ; Coptic # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
2CF9..2CFC ; Coptic # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER
2CFD ; Coptic # No COPTIC FRACTION ONE HALF
2CFE..2CFF ; Coptic # Po [2] COPTIC FULL STOP..COPTIC MORPHOLOGICAL DIVIDER
# Total code points: 128
# ================================================
1980..19A9 ; New_Tai_Lue # Lo [42] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW XVA
19B0..19C0 ; New_Tai_Lue # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
19C1..19C7 ; New_Tai_Lue # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
19C8..19C9 ; New_Tai_Lue # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
19D0..19D9 ; New_Tai_Lue # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
19DE..19DF ; New_Tai_Lue # So [2] NEW TAI LUE SIGN LE..NEW TAI LUE SIGN LEW
# Total code points: 80
# ================================================
2C00..2C2E ; Glagolitic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E ; Glagolitic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
# Total code points: 94
# ================================================
2D30..2D65 ; Tifinagh # Lo [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ
2D6F ; Tifinagh # Lm TIFINAGH MODIFIER LETTER LABIALIZATION
# Total code points: 55
# ================================================
A800..A801 ; Syloti_Nagri # Lo [2] SYLOTI NAGRI LETTER A..SYLOTI NAGRI LETTER I
A802 ; Syloti_Nagri # Mc SYLOTI NAGRI SIGN DVISVARA
A803..A805 ; Syloti_Nagri # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O
A806 ; Syloti_Nagri # Mn SYLOTI NAGRI SIGN HASANTA
A807..A80A ; Syloti_Nagri # Lo [4] SYLOTI NAGRI LETTER KO..SYLOTI NAGRI LETTER GHO
A80B ; Syloti_Nagri # Mn SYLOTI NAGRI SIGN ANUSVARA
A80C..A822 ; Syloti_Nagri # Lo [23] SYLOTI NAGRI LETTER CO..SYLOTI NAGRI LETTER HO
A823..A824 ; Syloti_Nagri # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
A825..A826 ; Syloti_Nagri # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
A827 ; Syloti_Nagri # Mc SYLOTI NAGRI VOWEL SIGN OO
A828..A82B ; Syloti_Nagri # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK-4
# Total code points: 44
# ================================================
103A0..103C3 ; Old_Persian # Lo [36] OLD PERSIAN SIGN A..OLD PERSIAN SIGN HA
103C8..103CF ; Old_Persian # Lo [8] OLD PERSIAN SIGN AURAMAZDAA..OLD PERSIAN SIGN BUUMISH
103D0 ; Old_Persian # So OLD PERSIAN WORD DIVIDER
103D1..103D5 ; Old_Persian # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED
# Total code points: 50
# ================================================
10A00 ; Kharoshthi # Lo KHAROSHTHI LETTER A
10A01..10A03 ; Kharoshthi # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
10A05..10A06 ; Kharoshthi # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0F ; Kharoshthi # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
10A10..10A13 ; Kharoshthi # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA
10A15..10A17 ; Kharoshthi # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
10A19..10A33 ; Kharoshthi # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA
10A38..10A3A ; Kharoshthi # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
10A3F ; Kharoshthi # Mn KHAROSHTHI VIRAMA
10A40..10A43 ; Kharoshthi # Nd [4] KHAROSHTHI DIGIT ONE..KHAROSHTHI DIGIT FOUR
10A44..10A47 ; Kharoshthi # No [4] KHAROSHTHI NUMBER TEN..KHAROSHTHI NUMBER ONE THOUSAND
10A50..10A58 ; Kharoshthi # Po [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES
# Total code points: 65

1600
icu4c/source/data/unidata/SentenceBreakProperty.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
icu4c/source/data/unidata/SpecialCasing.txt
View File

@ -1,5 +1,5 @@
# SpecialCasing-4.0.1.txt
# Date: 2003-10-06, 17:30:00 PST [KW]
# SpecialCasing-4.1.0.txt
# Date: 2004-12-16, 03:10:45 GMT [MD]
#
# Special Casing Properties
#
@ -18,25 +18,23 @@
#
# <code>; <lower> ; <title> ; <upper> ; (<condition_list> ;)? # <comment>
#
# <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more than
# one character, they are separated by spaces. Other than as used to separate elements,
# spaces are to be ignored.
# <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more
# than one character, they are separated by spaces. Other than as used to separate
# elements, spaces are to be ignored.
#
# The <condition_list> is optional. Where present, it consists of one or more locales or contexts,
# separated by spaces. In these conditions:
# The <condition_list> is optional. Where present, it consists of one or more locale IDs
# or contexts, separated by spaces. In these conditions:
# - A condition list overrides the normal behavior if all of the listed conditions are true.
# - The context is always the context of the characters in the original string,
# NOT in the resulting string.
# - Case distinctions in the condition list are not significant.
# - Conditions preceded by "Not_" represent the negation of the condition.
#
# A locale is defined as:
# <locale> := <ISO_639_code> ( "_" <ISO_3166_code> ( "_" <variant> )? )?
# <ISO_3166_code> := 2-letter ISO country code,
# <ISO_639_code> := 2-letter ISO language code
# A locale ID is defined by taking any language tag as defined by
# RFC 3066 (or its successor), and replacing '-' by '_'.
#
# A context is one of the following, as defined in the Unicode Standard:
# Final_Sigma, After_Soft_Dotted, More_Above, Before_Dot, Not_Before_Dot, After_I
# A context for a character C is defined by Section 3.13 Default Case Operations,
# on p. 89-90 of The Unicode Standard, Version 4.0, as amended by Unicode 4.0.1.
#
# Parsers of this file must be prepared to deal with future additions to this format:
# * Additional contexts

1361
icu4c/source/data/unidata/UnicodeData.txt
View File

File diff suppressed because it is too large Load Diff

510
icu4c/source/data/unidata/WordBreakProperty.txt Normal file
View File

@ -0,0 +1,510 @@
# WordBreakProperty-4.1.0.txt
# Date: 2004-12-11, 05:47:24 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2005 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
# ================================================
# Property: Word_Break
# All code points not explicitly listed for Word_Break
# have the value Other.
# ================================================
00AD ; Format
0600..0603 ; Format
06DD ; Format
070F ; Format
17B4..17B5 ; Format
200B ; Format
200E..200F ; Format
202A..202E ; Format
2060..2063 ; Format
206A..206F ; Format
FEFF ; Format
FFF9..FFFB ; Format
1D173..1D17A ; Format
E0001 ; Format
E0020..E007F ; Format
# Total code points: 136
# ================================================
3031..3035 ; Katakana
309B..309C ; Katakana
30A0 ; Katakana
30A1..30FA ; Katakana
30FC..30FE ; Katakana
30FF ; Katakana
31F0..31FF ; Katakana
FF66..FF6F ; Katakana
FF70 ; Katakana
FF71..FF9D ; Katakana
FF9E..FF9F ; Katakana
# Total code points: 176
# ================================================
0041..005A ; ALetter
0061..007A ; ALetter
00A0 ; ALetter
00AA ; ALetter
00B5 ; ALetter
00BA ; ALetter
00C0..00D6 ; ALetter
00D8..00F6 ; ALetter
00F8..01BA ; ALetter
01BB ; ALetter
01BC..01BF ; ALetter
01C0..01C3 ; ALetter
01C4..0241 ; ALetter
0250..02AF ; ALetter
02B0..02C1 ; ALetter
02C6..02D1 ; ALetter
02E0..02E4 ; ALetter
02EE ; ALetter
037A ; ALetter
0386 ; ALetter
0388..038A ; ALetter
038C ; ALetter
038E..03A1 ; ALetter
03A3..03CE ; ALetter
03D0..03F5 ; ALetter
03F7..0481 ; ALetter
048A..04CE ; ALetter
04D0..04F9 ; ALetter
0500..050F ; ALetter
0531..0556 ; ALetter
0559 ; ALetter
0561..0587 ; ALetter
05D0..05EA ; ALetter
05F0..05F2 ; ALetter
05F3 ; ALetter
0621..063A ; ALetter
0640 ; ALetter
0641..064A ; ALetter
066E..066F ; ALetter
0671..06D3 ; ALetter
06D5 ; ALetter
06E5..06E6 ; ALetter
06EE..06EF ; ALetter
06FA..06FC ; ALetter
06FF ; ALetter
0710 ; ALetter
0712..072F ; ALetter
074D..076D ; ALetter
0780..07A5 ; ALetter
07B1 ; ALetter
0903 ; ALetter
0904..0939 ; ALetter
093D ; ALetter
093E..0940 ; ALetter
0949..094C ; ALetter
0950 ; ALetter
0958..0961 ; ALetter
097D ; ALetter
0982..0983 ; ALetter
0985..098C ; ALetter
098F..0990 ; ALetter
0993..09A8 ; ALetter
09AA..09B0 ; ALetter
09B2 ; ALetter
09B6..09B9 ; ALetter
09BD ; ALetter
09BF..09C0 ; ALetter
09C7..09C8 ; ALetter
09CB..09CC ; ALetter
09CE ; ALetter
09DC..09DD ; ALetter
09DF..09E1 ; ALetter
09F0..09F1 ; ALetter
0A03 ; ALetter
0A05..0A0A ; ALetter
0A0F..0A10 ; ALetter
0A13..0A28 ; ALetter
0A2A..0A30 ; ALetter
0A32..0A33 ; ALetter
0A35..0A36 ; ALetter
0A38..0A39 ; ALetter
0A3E..0A40 ; ALetter
0A59..0A5C ; ALetter
0A5E ; ALetter
0A72..0A74 ; ALetter
0A83 ; ALetter
0A85..0A8D ; ALetter
0A8F..0A91 ; ALetter
0A93..0AA8 ; ALetter
0AAA..0AB0 ; ALetter
0AB2..0AB3 ; ALetter
0AB5..0AB9 ; ALetter
0ABD ; ALetter
0ABE..0AC0 ; ALetter
0AC9 ; ALetter
0ACB..0ACC ; ALetter
0AD0 ; ALetter
0AE0..0AE1 ; ALetter
0B02..0B03 ; ALetter
0B05..0B0C ; ALetter
0B0F..0B10 ; ALetter
0B13..0B28 ; ALetter
0B2A..0B30 ; ALetter
0B32..0B33 ; ALetter
0B35..0B39 ; ALetter
0B3D ; ALetter
0B40 ; ALetter
0B47..0B48 ; ALetter
0B4B..0B4C ; ALetter
0B5C..0B5D ; ALetter
0B5F..0B61 ; ALetter
0B71 ; ALetter
0B83 ; ALetter
0B85..0B8A ; ALetter
0B8E..0B90 ; ALetter
0B92..0B95 ; ALetter
0B99..0B9A ; ALetter
0B9C ; ALetter
0B9E..0B9F ; ALetter
0BA3..0BA4 ; ALetter
0BA8..0BAA ; ALetter
0BAE..0BB9 ; ALetter
0BBF ; ALetter
0BC1..0BC2 ; ALetter
0BC6..0BC8 ; ALetter
0BCA..0BCC ; ALetter
0C01..0C03 ; ALetter
0C05..0C0C ; ALetter
0C0E..0C10 ; ALetter
0C12..0C28 ; ALetter
0C2A..0C33 ; ALetter
0C35..0C39 ; ALetter
0C41..0C44 ; ALetter
0C60..0C61 ; ALetter
0C82..0C83 ; ALetter
0C85..0C8C ; ALetter
0C8E..0C90 ; ALetter
0C92..0CA8 ; ALetter
0CAA..0CB3 ; ALetter
0CB5..0CB9 ; ALetter
0CBD ; ALetter
0CBE ; ALetter
0CC0..0CC1 ; ALetter
0CC3..0CC4 ; ALetter
0CC7..0CC8 ; ALetter
0CCA..0CCB ; ALetter
0CDE ; ALetter
0CE0..0CE1 ; ALetter
0D02..0D03 ; ALetter
0D05..0D0C ; ALetter
0D0E..0D10 ; ALetter
0D12..0D28 ; ALetter
0D2A..0D39 ; ALetter
0D3F..0D40 ; ALetter
0D46..0D48 ; ALetter
0D4A..0D4C ; ALetter
0D60..0D61 ; ALetter
0D82..0D83 ; ALetter
0D85..0D96 ; ALetter
0D9A..0DB1 ; ALetter
0DB3..0DBB ; ALetter
0DBD ; ALetter
0DC0..0DC6 ; ALetter
0DD0..0DD1 ; ALetter
0DD8..0DDE ; ALetter
0DF2..0DF3 ; ALetter
0F00 ; ALetter
0F40..0F47 ; ALetter
0F49..0F6A ; ALetter
0F7F ; ALetter
0F88..0F8B ; ALetter
1000..1021 ; ALetter
1023..1027 ; ALetter
1029..102A ; ALetter
102C ; ALetter
1031 ; ALetter
1038 ; ALetter
1050..1055 ; ALetter
1056..1057 ; ALetter
10A0..10C5 ; ALetter
10D0..10FA ; ALetter
10FC ; ALetter
1100..1159 ; ALetter
115F..11A2 ; ALetter
11A8..11F9 ; ALetter
1200..1248 ; ALetter
124A..124D ; ALetter
1250..1256 ; ALetter
1258 ; ALetter
125A..125D ; ALetter
1260..1288 ; ALetter
128A..128D ; ALetter
1290..12B0 ; ALetter
12B2..12B5 ; ALetter
12B8..12BE ; ALetter
12C0 ; ALetter
12C2..12C5 ; ALetter
12C8..12D6 ; ALetter
12D8..1310 ; ALetter
1312..1315 ; ALetter
1318..135A ; ALetter
1380..138F ; ALetter
13A0..13F4 ; ALetter
1401..166C ; ALetter
166F..1676 ; ALetter
1681..169A ; ALetter
16A0..16EA ; ALetter
16EE..16F0 ; ALetter
1700..170C ; ALetter
170E..1711 ; ALetter
1720..1731 ; ALetter
1740..1751 ; ALetter
1760..176C ; ALetter
176E..1770 ; ALetter
1780..17B3 ; ALetter
17B6 ; ALetter
17BE..17C5 ; ALetter
17C7..17C8 ; ALetter
17D7 ; ALetter
17DC ; ALetter
1820..1842 ; ALetter
1843 ; ALetter
1844..1877 ; ALetter
1880..18A8 ; ALetter
1900..191C ; ALetter
1923..1926 ; ALetter
1929..192B ; ALetter
1930..1931 ; ALetter
1933..1938 ; ALetter
1950..196D ; ALetter
1970..1974 ; ALetter
1980..19A9 ; ALetter
19B0..19C0 ; ALetter
19C1..19C7 ; ALetter
19C8..19C9 ; ALetter
1A00..1A16 ; ALetter
1A19..1A1B ; ALetter
1D00..1D2B ; ALetter
1D2C..1D61 ; ALetter
1D62..1D77 ; ALetter
1D78 ; ALetter
1D79..1D9A ; ALetter
1D9B..1DBF ; ALetter
1E00..1E9B ; ALetter
1EA0..1EF9 ; ALetter
1F00..1F15 ; ALetter
1F18..1F1D ; ALetter
1F20..1F45 ; ALetter
1F48..1F4D ; ALetter
1F50..1F57 ; ALetter
1F59 ; ALetter
1F5B ; ALetter
1F5D ; ALetter
1F5F..1F7D ; ALetter
1F80..1FB4 ; ALetter
1FB6..1FBC ; ALetter
1FBE ; ALetter
1FC2..1FC4 ; ALetter
1FC6..1FCC ; ALetter
1FD0..1FD3 ; ALetter
1FD6..1FDB ; ALetter
1FE0..1FEC ; ALetter
1FF2..1FF4 ; ALetter
1FF6..1FFC ; ALetter
2071 ; ALetter
207F ; ALetter
2090..2094 ; ALetter
2102 ; ALetter
2107 ; ALetter
210A..2113 ; ALetter
2115 ; ALetter
2119..211D ; ALetter
2124 ; ALetter
2126 ; ALetter
2128 ; ALetter
212A..212D ; ALetter
212F..2131 ; ALetter
2133..2134 ; ALetter
2135..2138 ; ALetter
2139 ; ALetter
213C..213F ; ALetter
2145..2149 ; ALetter
2160..2183 ; ALetter
24B6..24E9 ; ALetter
2C00..2C2E ; ALetter
2C30..2C5E ; ALetter
2C80..2CE4 ; ALetter
2D00..2D25 ; ALetter
2D30..2D65 ; ALetter
2D6F ; ALetter
2D80..2D96 ; ALetter
2DA0..2DA6 ; ALetter
2DA8..2DAE ; ALetter
2DB0..2DB6 ; ALetter
2DB8..2DBE ; ALetter
2DC0..2DC6 ; ALetter
2DC8..2DCE ; ALetter
2DD0..2DD6 ; ALetter
2DD8..2DDE ; ALetter
3005 ; ALetter
303B ; ALetter
303C ; ALetter
3105..312C ; ALetter
3131..318E ; ALetter
31A0..31B7 ; ALetter
A000..A014 ; ALetter
A015 ; ALetter
A016..A48C ; ALetter
A800..A801 ; ALetter
A803..A805 ; ALetter
A807..A80A ; ALetter
A80C..A822 ; ALetter
A823..A824 ; ALetter
A827 ; ALetter
AC00..D7A3 ; ALetter
FA30..FA6A ; ALetter
FB00..FB06 ; ALetter
FB13..FB17 ; ALetter
FB1D ; ALetter
FB1F..FB28 ; ALetter
FB2A..FB36 ; ALetter
FB38..FB3C ; ALetter
FB3E ; ALetter
FB40..FB41 ; ALetter
FB43..FB44 ; ALetter
FB46..FBB1 ; ALetter
FBD3..FD3D ; ALetter
FD50..FD8F ; ALetter
FD92..FDC7 ; ALetter
FDF0..FDFB ; ALetter
FE70..FE74 ; ALetter
FE76..FEFC ; ALetter
FF21..FF3A ; ALetter
FF41..FF5A ; ALetter
FFA0..FFBE ; ALetter
FFC2..FFC7 ; ALetter
FFCA..FFCF ; ALetter
FFD2..FFD7 ; ALetter
FFDA..FFDC ; ALetter
10000..1000B ; ALetter
1000D..10026 ; ALetter
10028..1003A ; ALetter
1003C..1003D ; ALetter
1003F..1004D ; ALetter
10050..1005D ; ALetter
10080..100FA ; ALetter
10140..10174 ; ALetter
10300..1031E ; ALetter
10330..10349 ; ALetter
1034A ; ALetter
10380..1039D ; ALetter
103A0..103C3 ; ALetter
103C8..103CF ; ALetter
103D1..103D5 ; ALetter
10400..1044F ; ALetter
10450..1049D ; ALetter
10800..10805 ; ALetter
10808 ; ALetter
1080A..10835 ; ALetter
10837..10838 ; ALetter
1083C ; ALetter
1083F ; ALetter
10A00 ; ALetter
10A10..10A13 ; ALetter
10A15..10A17 ; ALetter
10A19..10A33 ; ALetter
1D400..1D454 ; ALetter
1D456..1D49C ; ALetter
1D49E..1D49F ; ALetter
1D4A2 ; ALetter
1D4A5..1D4A6 ; ALetter
1D4A9..1D4AC ; ALetter
1D4AE..1D4B9 ; ALetter
1D4BB ; ALetter
1D4BD..1D4C3 ; ALetter
1D4C5..1D505 ; ALetter
1D507..1D50A ; ALetter
1D50D..1D514 ; ALetter
1D516..1D51C ; ALetter
1D51E..1D539 ; ALetter
1D53B..1D53E ; ALetter
1D540..1D544 ; ALetter
1D546 ; ALetter
1D54A..1D550 ; ALetter
1D552..1D6A5 ; ALetter
1D6A8..1D6C0 ; ALetter
1D6C2..1D6DA ; ALetter
1D6DC..1D6FA ; ALetter
1D6FC..1D714 ; ALetter
1D716..1D734 ; ALetter
1D736..1D74E ; ALetter
1D750..1D76E ; ALetter
1D770..1D788 ; ALetter
1D78A..1D7A8 ; ALetter
1D7AA..1D7C2 ; ALetter
1D7C4..1D7C9 ; ALetter
# Total code points: 20161
# ================================================
0027 ; MidLetter
003A ; MidLetter
00B7 ; MidLetter
05F4 ; MidLetter
2019 ; MidLetter
2027 ; MidLetter
# Total code points: 6
# ================================================
002C ; MidNum
002E ; MidNum
003B ; MidNum
037E ; MidNum
0589 ; MidNum
060D ; MidNum
2044 ; MidNum
FE10 ; MidNum
FE13..FE14 ; MidNum
# Total code points: 10
# ================================================
0030..0039 ; Numeric
005F ; Numeric
0660..0669 ; Numeric
066B..066C ; Numeric
06F0..06F9 ; Numeric
0966..096F ; Numeric
09E6..09EF ; Numeric
0A66..0A6F ; Numeric
0AE6..0AEF ; Numeric
0B66..0B6F ; Numeric
0BE6..0BEF ; Numeric
0C66..0C6F ; Numeric
0CE6..0CEF ; Numeric
0D66..0D6F ; Numeric
0E50..0E59 ; Numeric
0ED0..0ED9 ; Numeric
0F20..0F29 ; Numeric
1040..1049 ; Numeric
17E0..17E9 ; Numeric
1810..1819 ; Numeric
1946..194F ; Numeric
19D0..19D9 ; Numeric
203F..2040 ; Numeric
2054 ; Numeric
FE33..FE34 ; Numeric
FE4D..FE4F ; Numeric
FF3F ; Numeric
104A0..104A9 ; Numeric
1D7CE..1D7FF ; Numeric
# Total code points: 272

90
icu4c/source/data/unidata/changes.txt
View File

@ -1,3 +1,93 @@
Unicode 4.1 update
*** related Jitterbugs
4332 RFE: Update to Unicode 4.1
4157 RBBI, TR29 4.1 updates
*** data files & enums & parser code
* file preparation
- ucdstrip:
DerivedCoreProperties.txt
DerivedNormalizationProps.txt
NormalizationTest.txt
GraphemeBreakProperty.txt
SentenceBreakProperty.txt
WordBreakProperty.txt
- ucdstrip and ucdmerge:
EastAsianWidth.txt
LineBreak.txt
* add new files to the repository
GraphemeBreakProperty.txt
SentenceBreakProperty.txt
WordBreakProperty.txt
* update FractionalUCA.txt and UCARules.txt with new canonical closure
* genpname
- handle new enumerated properties in sub read_uchar
- run preparse.pl
* uchar.h & uscript.h & uprops.h & uprops.c & genprops
- new binary properties
+ Pattern_Syntax
+ Pattern_White_Space
- new enumerated properties
+ Grapheme_Cluster_Break
+ Sentence_Break
+ Word_Break
- new block & script & line break values
* gencase
- case-ignorable changes
see http://www.unicode.org/versions/Unicode4.1.0/#CaseMods
now: (D47a) Word_Break=MidLetter or Mn, Me, Cf, Lm, Sk
*** Unicode version numbers
- makedata.mak
- uchar.h
- configure.in
*** tests
- verify that u_charMirror() round-trips
- test all new properties and some new values of old properties
*** other code
* hardcoded Unihan range end/limit
- Unihan range end moves from 9FA5 to 9FBB
search for both 9FA5 (end) and 9FA6 (limit) (regex 9FA[56], case-insensitive)
+ do not modify BOCU/BOCSU code because that would change the encoding
and break binary compatibility!
+ similarly, do not change the GB 18030 range data (ucnvmbcs.c),
NamePrepProfile.txt
+ ignore trietest.c: test data is arbitrary
+ ignore tstnorm.cpp: test optimization, not important
+ ignore collation: 9FA[56] only appears in comments; swapCJK() uses the whole block up to 9FFF
+ do change line_th.txt and word_th.txt
by replacing hardcoded ranges with the new property values
+ do change gennames.c
source\data\brkitr\line_th.txt(229): \u33E0-\u33FE \u3400-\u4DB5 \u4E00-\u9FA5 \uA000-\uA48C \uA490-\uA4C6
source\data\brkitr\word_th.txt(23): \u33E0-\u33FE \u3400-\u4DB5 \u4E00-\u9FA5 \uA000-\uA48C \uA490-\uA4C6
source\tools\gennames\gennames.c(971): 0x4e00, 0x9fa5,
* case mappings
- compare new special casing context conditions with previous ones
see http://www.unicode.org/versions/Unicode4.1.0/#CaseMods
* genpname
- consider storing only the short name if it is the same as the long name
*** other reviews
- UAX #29 changes (grapheme/word/sentence breaks)
- UAX #14 changes (line breaks)
- Pattern_Syntax & Pattern_White_Space
---------------------------------------------------------------------------- ***
Unicode 4.0.1 update
*** related Jitterbugs

75
icu4c/source/test/cintltst/cucdtst.c
View File

@ -1,6 +1,6 @@
/********************************************************************
* COPYRIGHT:
* Copyright (c) 1997-2004, International Business Machines Corporation and
* Copyright (c) 1997-2005, International Business Machines Corporation and
* others. All Rights Reserved.
********************************************************************/
/********************************************************************************
@ -1757,6 +1757,16 @@ TestCharNames() {
static void
TestMirroring() {
USet *set;
UErrorCode errorCode;
UChar32 start, end, c2, c3;
int32_t i;
U_STRING_DECL(mirroredPattern, "[:Bidi_Mirrored:]", 17);
U_STRING_INIT(mirroredPattern, "[:Bidi_Mirrored:]", 17);
log_verbose("Testing u_isMirrored()\n");
if(!(u_isMirrored(0x28) && u_isMirrored(0xbb) && u_isMirrored(0x2045) && u_isMirrored(0x232a) &&
!u_isMirrored(0x27) && !u_isMirrored(0x61) && !u_isMirrored(0x284) && !u_isMirrored(0x3400)
@ -1773,6 +1783,21 @@ TestMirroring() {
) {
log_err("u_charMirror() does not work correctly\n");
}
/* verify that Bidi_Mirroring_Glyph roundtrips */
errorCode=U_ZERO_ERROR;
set=uset_openPattern(mirroredPattern, 17, &errorCode);
for(i=0; 0==uset_getItem(set, i, &start, &end, NULL, 0, &errorCode); ++i) {
do {
c2=u_charMirror(start);
c3=u_charMirror(c2);
if(c3!=start) {
log_err("u_charMirror() does not roundtrip: U+%04lx->U+%04lx->U+%04lx\n", (long)start, (long)c2, (long)c3);
}
} while(++start<=end);
}
uset_close(set);
}
@ -2160,7 +2185,7 @@ TestAdditionalProperties() {
{ 0xfa11, UCHAR_UNIFIED_IDEOGRAPH, TRUE },
{ 0xfa12, UCHAR_UNIFIED_IDEOGRAPH, FALSE },
{ -1, 0x401, 0 },
{ -1, 0x401, 0 }, /* version break for Unicode 4.0.1 */
{ 0x002e, UCHAR_S_TERM, TRUE },
{ 0x0061, UCHAR_S_TERM, FALSE },
@ -2175,7 +2200,7 @@ TestAdditionalProperties() {
/* UCHAR_BIDI_CLASS tested for assigned characters in TestUnicodeData() */
/* test default Bidi classes for unassigned code points */
{ 0x0590, UCHAR_BIDI_CLASS, U_RIGHT_TO_LEFT },
{ 0x05a2, UCHAR_BIDI_CLASS, U_RIGHT_TO_LEFT },
{ 0x05c7, UCHAR_BIDI_CLASS, U_RIGHT_TO_LEFT },
{ 0x05ed, UCHAR_BIDI_CLASS, U_RIGHT_TO_LEFT },
{ 0x07f2, UCHAR_BIDI_CLASS, U_RIGHT_TO_LEFT },
{ 0x08ba, UCHAR_BIDI_CLASS, U_RIGHT_TO_LEFT },
@ -2263,7 +2288,6 @@ TestAdditionalProperties() {
{ 0x232A, UCHAR_LINE_BREAK, U_LB_CLOSE_PUNCTUATION },
{ 0x3401, UCHAR_LINE_BREAK, U_LB_IDEOGRAPHIC },
{ 0x4e02, UCHAR_LINE_BREAK, U_LB_IDEOGRAPHIC },
{ 0xac03, UCHAR_LINE_BREAK, U_LB_IDEOGRAPHIC },
{ 0x20004, UCHAR_LINE_BREAK, U_LB_IDEOGRAPHIC },
{ 0xf905, UCHAR_LINE_BREAK, U_LB_IDEOGRAPHIC },
{ 0xdb7e, UCHAR_LINE_BREAK, U_LB_SURROGATE },
@ -2313,6 +2337,49 @@ TestAdditionalProperties() {
{ 0xd7a4, UCHAR_HANGUL_SYLLABLE_TYPE, 0 },
{ -1, 0x410, 0 }, /* version break for Unicode 4.1 */
{ 0x00d7, UCHAR_PATTERN_SYNTAX, TRUE },
{ 0xfe45, UCHAR_PATTERN_SYNTAX, TRUE },
{ 0x0061, UCHAR_PATTERN_SYNTAX, FALSE },
{ 0x0020, UCHAR_PATTERN_WHITE_SPACE, TRUE },
{ 0x0085, UCHAR_PATTERN_WHITE_SPACE, TRUE },
{ 0x200f, UCHAR_PATTERN_WHITE_SPACE, TRUE },
{ 0x00a0, UCHAR_PATTERN_WHITE_SPACE, FALSE },
{ 0x3000, UCHAR_PATTERN_WHITE_SPACE, FALSE },
{ 0x1d200, UCHAR_BLOCK, UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION },
{ 0x2c8e, UCHAR_BLOCK, UBLOCK_COPTIC },
{ 0xfe17, UCHAR_BLOCK, UBLOCK_VERTICAL_FORMS },
{ 0x1a00, UCHAR_SCRIPT, USCRIPT_BUGINESE },
{ 0x2cea, UCHAR_SCRIPT, USCRIPT_COPTIC },
{ 0xa82b, UCHAR_SCRIPT, USCRIPT_SYLOTI_NAGRI },
{ 0x103d0, UCHAR_SCRIPT, USCRIPT_OLD_PERSIAN },
{ 0xcc28, UCHAR_LINE_BREAK, U_LB_H2 },
{ 0xcc29, UCHAR_LINE_BREAK, U_LB_H3 },
{ 0xac03, UCHAR_LINE_BREAK, U_LB_H3 },
{ 0x115f, UCHAR_LINE_BREAK, U_LB_JL },
{ 0x11aa, UCHAR_LINE_BREAK, U_LB_JT },
{ 0x11a1, UCHAR_LINE_BREAK, U_LB_JV },
{ 0xb2c9, UCHAR_GRAPHEME_CLUSTER_BREAK, U_GCB_LVT },
{ 0x036f, UCHAR_GRAPHEME_CLUSTER_BREAK, U_GCB_EXTEND },
{ 0x0000, UCHAR_GRAPHEME_CLUSTER_BREAK, U_GCB_CONTROL },
{ 0x1160, UCHAR_GRAPHEME_CLUSTER_BREAK, U_GCB_V },
{ 0x05f4, UCHAR_WORD_BREAK, U_WB_MIDLETTER },
{ 0x4ef0, UCHAR_WORD_BREAK, U_WB_OTHER },
{ 0x19d9, UCHAR_WORD_BREAK, U_WB_NUMERIC },
{ 0x2044, UCHAR_WORD_BREAK, U_WB_MIDNUM },
{ 0xfffd, UCHAR_SENTENCE_BREAK, U_SB_OTHER },
{ 0x1ffc, UCHAR_SENTENCE_BREAK, U_SB_UPPER },
{ 0xff63, UCHAR_SENTENCE_BREAK, U_SB_CLOSE },
{ 0x2028, UCHAR_SENTENCE_BREAK, U_SB_SEP },
/* undefined UProperty values */
{ 0x61, 0x4a7, 0 },
{ 0x234bc, 0x15ed, 0 }

19
icu4c/source/tools/gencase/gencase.c
View File

@ -1,7 +1,7 @@
/*
*******************************************************************************
*
* Copyright (C) 2004, International Business Machines
* Copyright (C) 2004-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -104,6 +104,17 @@ derCorePropsBinaries={
"DerivedCoreProperties", derCorePropsNames, LENGTHOF(derCorePropsNames)
};
/* treat Word_Break=MidLetter as a binary property (we ignore all other Word_Break values) */
static const Binary
wordBreakNames[]={
{ "MidLetter", 1, U_MASK(UGENCASE_IS_MID_LETTER_SHIFT), U_MASK(UGENCASE_IS_MID_LETTER_SHIFT) }
};
static const Binaries
wordBreakBinaries={
"WordBreakProperty", wordBreakNames, LENGTHOF(wordBreakNames)
};
static void U_CALLCONV
binariesLineFn(void *context,
char *fields[][2], int32_t fieldCount,
@ -272,7 +283,7 @@ main(int argc, char* argv[]) {
}
/* initialize */
pv=upvec_open(1, 10000);
pv=upvec_open(2, 10000);
caseSensitive=uset_open(1, 0); /* empty set (start>end) */
/* process SpecialCasing.txt */
@ -290,6 +301,10 @@ main(int argc, char* argv[]) {
parseBinariesFile(filename, basename, suffix, &derCorePropsBinaries, &errorCode);
if(ucdVersion>=UNI_4_1) {
parseBinariesFile(filename, basename, suffix, &wordBreakBinaries, &errorCode);
}
/* process UnicodeData.txt */
writeUCDFilename(basename, "UnicodeData", suffix);
parseDB(filename, &errorCode);

24
icu4c/source/tools/gencase/gencase.h
View File

@ -1,7 +1,7 @@
/*
*******************************************************************************
*
* Copyright (C) 2004, International Business Machines
* Copyright (C) 2004-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -23,6 +23,23 @@
U_CDECL_BEGIN
/* Unicode versions --------------------------------------------------------- */
enum {
UNI_1_0,
UNI_1_1,
UNI_2_0,
UNI_3_0,
UNI_3_1,
UNI_3_2,
UNI_4_0,
UNI_4_0_1,
UNI_4_1,
UNI_VER_COUNT
};
extern int32_t ucdVersion;
/* gencase ------------------------------------------------------------------ */
#define UGENCASE_EXC_SHIFT 16
@ -43,6 +60,11 @@ enum {
UGENCASE_UNFOLD_MAX_ROWS=250
};
/* Values for additional data stored in pv column 1 */
enum {
UGENCASE_IS_MID_LETTER_SHIFT /* bit 0 */
};
/* special casing data */
typedef struct {
UChar32 code;

64
icu4c/source/tools/gencase/store.c
View File

@ -1,7 +1,7 @@
/*
*******************************************************************************
*
* Copyright (C) 2004, International Business Machines
* Copyright (C) 2004-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -216,15 +216,46 @@ static UChar unfold[UGENCASE_UNFOLD_MAX_ROWS*UGENCASE_UNFOLD_WIDTH]={
static uint16_t unfoldRows=0;
static uint16_t unfoldTop=UGENCASE_UNFOLD_WIDTH;
/* -------------------------------------------------------------------------- */
/* Unicode versions --------------------------------------------------------- */
static const UVersionInfo
unicodeVersions[]={
{ 1, 0, 0, 0 },
{ 1, 1, 0, 0 },
{ 2, 0, 0, 0 },
{ 3, 0, 0, 0 },
{ 3, 1, 0, 0 },
{ 3, 2, 0, 0 },
{ 4, 0, 0, 0 },
{ 4, 0, 1, 0 },
{ 4, 1, 0, 0 }
};
int32_t ucdVersion=UNI_4_1;
static int32_t
findUnicodeVersion(const UVersionInfo version) {
int32_t i;
for(i=0; /* while(version>unicodeVersions[i]) {} */
i<UNI_VER_COUNT && uprv_memcmp(version, unicodeVersions[i], 4)>0;
++i) {}
if(0<i && i<UNI_VER_COUNT && uprv_memcmp(version, unicodeVersions[i], 4)<0) {
--i; /* fix 4.0.2 to land before 4.1, for valid x>=ucdVersion comparisons */
}
return i; /* version>=unicodeVersions[i] && version<unicodeVersions[i+1]; possible: i==UNI_VER_COUNT */
}
extern void
setUnicodeVersion(const char *v) {
UVersionInfo version;
u_versionFromString(version, v);
uprv_memcpy(dataInfo.dataVersion, version, 4);
ucdVersion=findUnicodeVersion(version);
}
/* -------------------------------------------------------------------------- */
static void
addUnfolding(UChar32 c, const UChar *s, int32_t length) {
int32_t i;
@ -255,6 +286,7 @@ setProps(Props *p) {
UErrorCode errorCode;
uint32_t value, oldValue;
int32_t delta;
UBool isCaseIgnorable;
/* get the non-UnicodeData.txt properties */
value=oldValue=upvec_getValue(pv, p->code, 0);
@ -313,12 +345,28 @@ setProps(Props *p) {
}
/* encode case-ignorable as delta==1 on uncased characters */
if(
(value&UCASE_TYPE_MASK)==UCASE_NONE &&
p->code!=0x307 &&
((U_MASK(p->gc)&(U_GC_MN_MASK|U_GC_ME_MASK|U_GC_CF_MASK|U_GC_LM_MASK|U_GC_SK_MASK))!=0 ||
p->code==0x27 || p->code==0xad || p->code==0x2019)
) {
isCaseIgnorable=FALSE;
if((value&UCASE_TYPE_MASK)==UCASE_NONE) {
if(ucdVersion>=UNI_4_1) {
/* Unicode 4.1 and up: (D47a) Word_Break=MidLetter or Mn, Me, Cf, Lm, Sk */
if(
(U_MASK(p->gc)&(U_GC_MN_MASK|U_GC_ME_MASK|U_GC_CF_MASK|U_GC_LM_MASK|U_GC_SK_MASK))!=0 ||
((upvec_getValue(pv, p->code, 1)>>UGENCASE_IS_MID_LETTER_SHIFT)&1)!=0
) {
isCaseIgnorable=TRUE;
}
} else {
/* before Unicode 4.1: Mn, Me, Cf, Lm, Sk or 0027 or 00AD or 2019 */
if(
(U_MASK(p->gc)&(U_GC_MN_MASK|U_GC_ME_MASK|U_GC_CF_MASK|U_GC_LM_MASK|U_GC_SK_MASK))!=0 ||
p->code==0x27 || p->code==0xad || p->code==0x2019
) {
isCaseIgnorable=TRUE;
}
}
}
if(isCaseIgnorable && p->code!=0x307) {
/*
* We use one of the delta/exception bits, which works because we only
* store the case-ignorable flag for uncased characters.

95
icu4c/source/tools/gennames/gennames.c
View File

@ -1,7 +1,7 @@
/*
*******************************************************************************
*
* Copyright (C) 1999-2004, International Business Machines
* Copyright (C) 1999-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
@ -146,9 +146,50 @@
#define VERSION_STRING "unam"
#define NAME_SEPARATOR_CHAR ';'
/* Unicode versions --------------------------------------------------------- */
enum {
UNI_1_0,
UNI_1_1,
UNI_2_0,
UNI_3_0,
UNI_3_1,
UNI_3_2,
UNI_4_0,
UNI_4_0_1,
UNI_4_1,
UNI_VER_COUNT
};
static const UVersionInfo
unicode_3_0={ 3, 0, 0, 0 },
unicode_3_1={ 3, 1, 0, 0 };
unicodeVersions[]={
{ 1, 0, 0, 0 },
{ 1, 1, 0, 0 },
{ 2, 0, 0, 0 },
{ 3, 0, 0, 0 },
{ 3, 1, 0, 0 },
{ 3, 2, 0, 0 },
{ 4, 0, 0, 0 },
{ 4, 0, 1, 0 },
{ 4, 1, 0, 0 }
};
static int32_t ucdVersion=UNI_4_1;
static int32_t
findUnicodeVersion(const UVersionInfo version) {
int32_t i;
for(i=0; /* while(version>unicodeVersions[i]) {} */
i<UNI_VER_COUNT && uprv_memcmp(version, unicodeVersions[i], 4)>0;
++i) {}
if(0<i && i<UNI_VER_COUNT && uprv_memcmp(version, unicodeVersions[i], 4)<0) {
--i; /* fix 4.0.2 to land before 4.1, for valid x>=ucdVersion comparisons */
}
return i; /* version>=unicodeVersions[i] && version<unicodeVersions[i+1]; possible: i==UNI_VER_COUNT */
}
/* generator data ----------------------------------------------------------- */
/* UDataInfo cf. udata.h */
static UDataInfo dataInfo={
@ -301,7 +342,7 @@ main(int argc, char* argv[]) {
/* preset then read command line options */
options[5].value=u_getDataDirectory();
options[6].value="3.2";
options[6].value="4.1";
argc=u_parseArgs(argc, argv, sizeof(options)/sizeof(options[0]), options);
/* error handling, printing usage message */
@ -348,6 +389,7 @@ main(int argc, char* argv[]) {
/* set the Unicode version */
u_versionFromString(version, options[6].value);
uprv_memcpy(dataInfo.dataVersion, version, 4);
ucdVersion=findUnicodeVersion(version);
init();
parseDB(argc>=2 ? argv[1] : "-", store10Names);
@ -861,6 +903,42 @@ generateData(const char *dataDir) {
}
}
/*
* Required padding for data swapping:
* The token table undergoes a permutation during data swapping when the
* input and output charsets are different.
* The token table cannot grow during swapping, so we need to make sure that
* the table is long enough for successful in-place permutation.
*
* We simply round up tokenCount to the next multiple of 256 to account for
* all possible permutations.
*
* An optimization is possible if we only ever swap between ASCII and EBCDIC:
*
* If tokenCount>256, then a semicolon (NAME_SEPARATOR_CHAR) is used
* and will be swapped between ASCII and EBCDIC between
* positions 0x3b (ASCII semicolon) and 0x5e (EBCDIC semicolon).
* This should be the only -1 entry in tokens[256..511] on which the data
* swapper bases its trail byte permutation map (trailMap[]).
*
* It would be sufficient to increase tokenCount so that its lower 8 bits
* are at least 0x5e+1 to make room for swapping between the two semicolons.
* For values higher than 0x5e, the trail byte permutation map (trailMap[])
* should always be an identity map, where we do not need additional room.
*/
i=tokenCount;
tokenCount=(tokenCount+0xff)&~0xff;
if(!beQuiet && i<tokenCount) {
printf("number of tokens[] padding entries for data swapping: %lu\n", (unsigned long)(tokenCount-i));
}
for(; i<tokenCount; ++i) {
if((i&0xff)==NAME_SEPARATOR_CHAR) {
tokens[i]=-1; /* do not use NAME_SEPARATOR_CHAR as a second token byte */
} else {
tokens[i]=0; /* unused token for padding */
}
}
/*
* Calculate the total size in bytes of the data including:
* - the offset to the token strings, uint32_t (4)
@ -1009,11 +1087,16 @@ generateAlgorithmicData(UNewDataMemory *pData) {
size=0;
if(ucdVersion>=UNI_4_1) {
/* Unicode 4.1 and up has a longer CJK Unihan range than before */
cjk.rangeEnd=0x9FBB;
}
/* number of ranges of algorithmic names */
if(uprv_memcmp(dataInfo.dataVersion, unicode_3_1, sizeof(UVersionInfo))>=0) {
if(ucdVersion>=UNI_3_1) {
/* Unicode 3.1 and up has 4 ranges including CJK Extension B */
countAlgRanges=4;
} else if(uprv_memcmp(dataInfo.dataVersion, unicode_3_0, sizeof(UVersionInfo))>=0) {
} else if(ucdVersion>=UNI_3_0) {
/* Unicode 3.0 has 3 ranges including CJK Extension A */
countAlgRanges=3;
} else {

3530
icu4c/source/tools/genpname/data.h
View File

File diff suppressed because it is too large Load Diff

22
icu4c/source/tools/genpname/preparse.pl
View File

@ -1,7 +1,7 @@
#!/bin/perl -w
#*******************************************************************
# COPYRIGHT:
# Copyright (c) 2002-2004, International Business Machines Corporation and
# Copyright (c) 2002-2005, International Business Machines Corporation and
# others. All Rights Reserved.
#*******************************************************************
@ -844,7 +844,7 @@ sub read_PropertyValueAliases {
# Script Qaac (Coptic) is a special case. Handle it here. See UTR#24:
# http://www.unicode.org/unicode/reports/tr24/
$hash->{'sc'}->{'Qaac'} = 'Coptic'
unless (exists $hash->{'sc'}->{'Qaac'});
unless (exists $hash->{'sc'}->{'Qaac'} || exists $hash->{'sc'}->{'Copt'});
# Add T|True and F|False -- these are values we recognize for
# binary properties (NOT from PropertyValueAliases.txt). These
@ -1132,6 +1132,24 @@ sub read_uchar {
}
}
elsif ($mode eq 'UGraphemeClusterBreak') {
if (m|^\s*(U_GCB_\w+).+?/\*\[(.+?)\]\*/|) {
addDatum($hash, 'GCB', $1, $2);
}
}
elsif ($mode eq 'UWordBreakValues') {
if (m|^\s*(U_WB_\w+).+?/\*\[(.+?)\]\*/|) {
addDatum($hash, 'WB', $1, $2);
}
}
elsif ($mode eq 'USentenceBreak') {
if (m|^\s*(U_SB_\w+).+?/\*\[(.+?)\]\*/|) {
addDatum($hash, 'SB', $1, $2);
}
}
elsif ($mode eq 'ULineBreak') {
if (m|^\s*(U_LB_\w+).+?/\*\[(.+?)\]\*/|) {
addDatum($hash, 'lb', $1, $2);

33
icu4c/source/tools/genprops/props2.c
View File

@ -129,6 +129,24 @@ static const SingleEnum blockSingleEnum={
0, UPROPS_BLOCK_SHIFT, UPROPS_BLOCK_MASK
};
static const SingleEnum graphemeClusterBreakSingleEnum={
"GraphemeBreakProperty", "Grapheme_Cluster_Break",
UCHAR_GRAPHEME_CLUSTER_BREAK,
2, UPROPS_GCB_SHIFT, UPROPS_GCB_MASK
};
static const SingleEnum wordBreakSingleEnum={
"WordBreakProperty", "Word_Break",
UCHAR_WORD_BREAK,
2, UPROPS_WB_SHIFT, UPROPS_WB_MASK
};
static const SingleEnum sentenceBreakSingleEnum={
"SentenceBreakProperty", "Sentence_Break",
UCHAR_SENTENCE_BREAK,
2, UPROPS_SB_SHIFT, UPROPS_SB_MASK
};
static const SingleEnum lineBreakSingleEnum={
"LineBreak", "line break",
UCHAR_LINE_BREAK,
@ -249,7 +267,11 @@ propListNames[]={
/* new properties in Unicode 4.0.1 */
{ "STerm", 2, UPROPS_V2_S_TERM },
{ "Variation_Selector", 2, UPROPS_V2_VARIATION_SELECTOR }
{ "Variation_Selector", 2, UPROPS_V2_VARIATION_SELECTOR },
/* new properties in Unicode 4.1 */
{ "Pattern_Syntax", 2, UPROPS_V2_PATTERN_SYNTAX },
{ "Pattern_White_Space", 2, UPROPS_V2_PATTERN_WHITE_SPACE }
};
static const Binaries
@ -417,6 +439,12 @@ generateAdditionalProperties(char *filename, const char *suffix, UErrorCode *pEr
parseBinariesFile(filename, basename, suffix, &derCorePropsBinaries, pErrorCode);
parseSingleEnumFile(filename, basename, suffix, &graphemeClusterBreakSingleEnum, pErrorCode);
parseSingleEnumFile(filename, basename, suffix, &wordBreakSingleEnum, pErrorCode);
parseSingleEnumFile(filename, basename, suffix, &sentenceBreakSingleEnum, pErrorCode);
/*
* LineBreak-4.0.0.txt:
* - All code points, assigned and unassigned, that are not listed
@ -664,6 +692,9 @@ writeAdditionalData(uint8_t *p, int32_t capacity, int32_t indexes[UPROPS_INDEX_C
(((int32_t)UBLOCK_COUNT-1)<<UPROPS_BLOCK_SHIFT)|
((int32_t)USCRIPT_CODE_LIMIT-1);
indexes[UPROPS_MAX_VALUES_2_INDEX]=
(((int32_t)U_SB_COUNT-1)<<UPROPS_SB_SHIFT)|
(((int32_t)U_WB_COUNT-1)<<UPROPS_WB_SHIFT)|
(((int32_t)U_GCB_COUNT-1)<<UPROPS_GCB_SHIFT)|
((int32_t)U_DT_COUNT-1);
}