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

ICU-184 .res files go to mem map files - build issue

Browse Source 
X-SVN-Rev: 1372
This commit is contained in:
Vladimir Weinstein 2000-05-15 19:09:37 +00:00
parent 0530632bea
commit ec927f3702
17 changed files with 5367 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
icu4c/data/expcon.txt Normal file
View File

@ -0,0 +1 @@
// This file is obsolete

270
icu4c/data/fullhalf.txt Normal file
View File

@ -0,0 +1,270 @@
//--------------------------------------------------------------------
// Copyright (c) 2000, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 01/13/2000 aliu Creation.
//--------------------------------------------------------------------
fullhalf {
Rule {
// Mechanically generated from Unicode Character Database
// multicharacter
"\u30AC<>\uFF76\uFF9E;" // to KATAKANA LETTER GA
"\u30AE<>\uFF77\uFF9E;" // to KATAKANA LETTER GI
"\u30B0<>\uFF78\uFF9E;" // to KATAKANA LETTER GU
"\u30B2<>\uFF79\uFF9E;" // to KATAKANA LETTER GE
"\u30B4<>\uFF7A\uFF9E;" // to KATAKANA LETTER GO
"\u30B6<>\uFF7B\uFF9E;" // to KATAKANA LETTER ZA
"\u30B8<>\uFF7C\uFF9E;" // to KATAKANA LETTER ZI
"\u30BA<>\uFF7D\uFF9E;" // to KATAKANA LETTER ZU
"\u30BC<>\uFF7E\uFF9E;" // to KATAKANA LETTER ZE
"\u30BE<>\uFF7F\uFF9E;" // to KATAKANA LETTER ZO
"\u30C0<>\uFF80\uFF9E;" // to KATAKANA LETTER DA
"\u30C2<>\uFF81\uFF9E;" // to KATAKANA LETTER DI
"\u30C5<>\uFF82\uFF9E;" // to KATAKANA LETTER DU
"\u30C7<>\uFF83\uFF9E;" // to KATAKANA LETTER DE
"\u30C9<>\uFF84\uFF9E;" // to KATAKANA LETTER DO
"\u30D0<>\uFF8A\uFF9E;" // to KATAKANA LETTER BA
"\u30D1<>\uFF8A\uFF9F;" // to KATAKANA LETTER PA
"\u30D3<>\uFF8B\uFF9E;" // to KATAKANA LETTER BI
"\u30D4<>\uFF8B\uFF9F;" // to KATAKANA LETTER PI
"\u30D6<>\uFF8C\uFF9E;" // to KATAKANA LETTER BU
"\u30D7<>\uFF8C\uFF9F;" // to KATAKANA LETTER PU
"\u30D9<>\uFF8D\uFF9E;" // to KATAKANA LETTER BE
"\u30DA<>\uFF8D\uFF9F;" // to KATAKANA LETTER PE
"\u30DC<>\uFF8E\uFF9E;" // to KATAKANA LETTER BO
"\u30DD<>\uFF8E\uFF9F;" // to KATAKANA LETTER PO
"\u30F4<>\uFF73\uFF9E;" // to KATAKANA LETTER VU
"\u30F7<>\uFF9C\uFF9E;" // to KATAKANA LETTER VA
"\u30FA<>\uFF66\uFF9E;" // to KATAKANA LETTER VO
// single character
"\uFF01<>'!';" // from FULLWIDTH EXCLAMATION MARK
"\uFF02<>'\"';" // from FULLWIDTH QUOTATION MARK
"\uFF03<>'#';" // from FULLWIDTH NUMBER SIGN
"\uFF04<>'$';" // from FULLWIDTH DOLLAR SIGN
"\uFF05<>'%';" // from FULLWIDTH PERCENT SIGN
"\uFF06<>'&';" // from FULLWIDTH AMPERSAND
"\uFF07<>'';" // from FULLWIDTH APOSTROPHE
"\uFF08<>'(';" // from FULLWIDTH LEFT PARENTHESIS
"\uFF09<>')';" // from FULLWIDTH RIGHT PARENTHESIS
"\uFF0A<>'*';" // from FULLWIDTH ASTERISK
"\uFF0B<>'+';" // from FULLWIDTH PLUS SIGN
"\uFF0C<>',';" // from FULLWIDTH COMMA
"\uFF0D<>'-';" // from FULLWIDTH HYPHEN-MINUS
"\uFF0E<>'.';" // from FULLWIDTH FULL STOP
"\uFF0F<>'/';" // from FULLWIDTH SOLIDUS
"\uFF10<>'0';" // from FULLWIDTH DIGIT ZERO
"\uFF11<>'1';" // from FULLWIDTH DIGIT ONE
"\uFF12<>'2';" // from FULLWIDTH DIGIT TWO
"\uFF13<>'3';" // from FULLWIDTH DIGIT THREE
"\uFF14<>'4';" // from FULLWIDTH DIGIT FOUR
"\uFF15<>'5';" // from FULLWIDTH DIGIT FIVE
"\uFF16<>'6';" // from FULLWIDTH DIGIT SIX
"\uFF17<>'7';" // from FULLWIDTH DIGIT SEVEN
"\uFF18<>'8';" // from FULLWIDTH DIGIT EIGHT
"\uFF19<>'9';" // from FULLWIDTH DIGIT NINE
"\uFF1A<>':';" // from FULLWIDTH COLON
"\uFF1B<>';';" // from FULLWIDTH SEMICOLON
"\uFF1C<>'<';" // from FULLWIDTH LESS-THAN SIGN
"\uFF1D<>'=';" // from FULLWIDTH EQUALS SIGN
"\uFF1E<>'>';" // from FULLWIDTH GREATER-THAN SIGN
"\uFF1F<>'?';" // from FULLWIDTH QUESTION MARK
"\uFF20<>'@';" // from FULLWIDTH COMMERCIAL AT
"\uFF21<>A;" // from FULLWIDTH LATIN CAPITAL LETTER A
"\uFF22<>B;" // from FULLWIDTH LATIN CAPITAL LETTER B
"\uFF23<>C;" // from FULLWIDTH LATIN CAPITAL LETTER C
"\uFF24<>D;" // from FULLWIDTH LATIN CAPITAL LETTER D
"\uFF25<>E;" // from FULLWIDTH LATIN CAPITAL LETTER E
"\uFF26<>F;" // from FULLWIDTH LATIN CAPITAL LETTER F
"\uFF27<>G;" // from FULLWIDTH LATIN CAPITAL LETTER G
"\uFF28<>H;" // from FULLWIDTH LATIN CAPITAL LETTER H
"\uFF29<>I;" // from FULLWIDTH LATIN CAPITAL LETTER I
"\uFF2A<>J;" // from FULLWIDTH LATIN CAPITAL LETTER J
"\uFF2B<>K;" // from FULLWIDTH LATIN CAPITAL LETTER K
"\uFF2C<>L;" // from FULLWIDTH LATIN CAPITAL LETTER L
"\uFF2D<>M;" // from FULLWIDTH LATIN CAPITAL LETTER M
"\uFF2E<>N;" // from FULLWIDTH LATIN CAPITAL LETTER N
"\uFF2F<>O;" // from FULLWIDTH LATIN CAPITAL LETTER O
"\uFF30<>P;" // from FULLWIDTH LATIN CAPITAL LETTER P
"\uFF31<>Q;" // from FULLWIDTH LATIN CAPITAL LETTER Q
"\uFF32<>R;" // from FULLWIDTH LATIN CAPITAL LETTER R
"\uFF33<>S;" // from FULLWIDTH LATIN CAPITAL LETTER S
"\uFF34<>T;" // from FULLWIDTH LATIN CAPITAL LETTER T
"\uFF35<>U;" // from FULLWIDTH LATIN CAPITAL LETTER U
"\uFF36<>V;" // from FULLWIDTH LATIN CAPITAL LETTER V
"\uFF37<>W;" // from FULLWIDTH LATIN CAPITAL LETTER W
"\uFF38<>X;" // from FULLWIDTH LATIN CAPITAL LETTER X
"\uFF39<>Y;" // from FULLWIDTH LATIN CAPITAL LETTER Y
"\uFF3A<>Z;" // from FULLWIDTH LATIN CAPITAL LETTER Z
"\uFF3B<>'[';" // from FULLWIDTH LEFT SQUARE BRACKET
"\uFF3C<>'\\';" // from FULLWIDTH REVERSE SOLIDUS {double escape - aliu}
"\uFF3D<>']';" // from FULLWIDTH RIGHT SQUARE BRACKET
"\uFF3E<>'^';" // from FULLWIDTH CIRCUMFLEX ACCENT
"\uFF3F<>'_';" // from FULLWIDTH LOW LINE
"\uFF40<>'`';" // from FULLWIDTH GRAVE ACCENT
"\uFF41<>a;" // from FULLWIDTH LATIN SMALL LETTER A
"\uFF42<>b;" // from FULLWIDTH LATIN SMALL LETTER B
"\uFF43<>c;" // from FULLWIDTH LATIN SMALL LETTER C
"\uFF44<>d;" // from FULLWIDTH LATIN SMALL LETTER D
"\uFF45<>e;" // from FULLWIDTH LATIN SMALL LETTER E
"\uFF46<>f;" // from FULLWIDTH LATIN SMALL LETTER F
"\uFF47<>g;" // from FULLWIDTH LATIN SMALL LETTER G
"\uFF48<>h;" // from FULLWIDTH LATIN SMALL LETTER H
"\uFF49<>i;" // from FULLWIDTH LATIN SMALL LETTER I
"\uFF4A<>j;" // from FULLWIDTH LATIN SMALL LETTER J
"\uFF4B<>k;" // from FULLWIDTH LATIN SMALL LETTER K
"\uFF4C<>l;" // from FULLWIDTH LATIN SMALL LETTER L
"\uFF4D<>m;" // from FULLWIDTH LATIN SMALL LETTER M
"\uFF4E<>n;" // from FULLWIDTH LATIN SMALL LETTER N
"\uFF4F<>o;" // from FULLWIDTH LATIN SMALL LETTER O
"\uFF50<>p;" // from FULLWIDTH LATIN SMALL LETTER P
"\uFF51<>q;" // from FULLWIDTH LATIN SMALL LETTER Q
"\uFF52<>r;" // from FULLWIDTH LATIN SMALL LETTER R
"\uFF53<>s;" // from FULLWIDTH LATIN SMALL LETTER S
"\uFF54<>t;" // from FULLWIDTH LATIN SMALL LETTER T
"\uFF55<>u;" // from FULLWIDTH LATIN SMALL LETTER U
"\uFF56<>v;" // from FULLWIDTH LATIN SMALL LETTER V
"\uFF57<>w;" // from FULLWIDTH LATIN SMALL LETTER W
"\uFF58<>x;" // from FULLWIDTH LATIN SMALL LETTER X
"\uFF59<>y;" // from FULLWIDTH LATIN SMALL LETTER Y
"\uFF5A<>z;" // from FULLWIDTH LATIN SMALL LETTER Z
"\uFF5B<>'{';" // from FULLWIDTH LEFT CURLY BRACKET
"\uFF5C<>'|';" // from FULLWIDTH VERTICAL LINE
"\uFF5D<>'}';" // from FULLWIDTH RIGHT CURLY BRACKET
"\uFF5E<>'~';" // from FULLWIDTH TILDE
"\u3002<>\uFF61;" // to HALFWIDTH IDEOGRAPHIC FULL STOP
"\u300C<>\uFF62;" // to HALFWIDTH LEFT CORNER BRACKET
"\u300D<>\uFF63;" // to HALFWIDTH RIGHT CORNER BRACKET
"\u3001<>\uFF64;" // to HALFWIDTH IDEOGRAPHIC COMMA
"\u30FB<>\uFF65;" // to HALFWIDTH KATAKANA MIDDLE DOT
"\u30F2<>\uFF66;" // to HALFWIDTH KATAKANA LETTER WO
"\u30A1<>\uFF67;" // to HALFWIDTH KATAKANA LETTER SMALL A
"\u30A3<>\uFF68;" // to HALFWIDTH KATAKANA LETTER SMALL I
"\u30A5<>\uFF69;" // to HALFWIDTH KATAKANA LETTER SMALL U
"\u30A7<>\uFF6A;" // to HALFWIDTH KATAKANA LETTER SMALL E
"\u30A9<>\uFF6B;" // to HALFWIDTH KATAKANA LETTER SMALL O
"\u30E3<>\uFF6C;" // to HALFWIDTH KATAKANA LETTER SMALL YA
"\u30E5<>\uFF6D;" // to HALFWIDTH KATAKANA LETTER SMALL YU
"\u30E7<>\uFF6E;" // to HALFWIDTH KATAKANA LETTER SMALL YO
"\u30C3<>\uFF6F;" // to HALFWIDTH KATAKANA LETTER SMALL TU
"\u30FC<>\uFF70;" // to HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
"\u30A2<>\uFF71;" // to HALFWIDTH KATAKANA LETTER A
"\u30A4<>\uFF72;" // to HALFWIDTH KATAKANA LETTER I
"\u30A6<>\uFF73;" // to HALFWIDTH KATAKANA LETTER U
"\u30A8<>\uFF74;" // to HALFWIDTH KATAKANA LETTER E
"\u30AA<>\uFF75;" // to HALFWIDTH KATAKANA LETTER O
"\u30AB<>\uFF76;" // to HALFWIDTH KATAKANA LETTER KA
"\u30AD<>\uFF77;" // to HALFWIDTH KATAKANA LETTER KI
"\u30AF<>\uFF78;" // to HALFWIDTH KATAKANA LETTER KU
"\u30B1<>\uFF79;" // to HALFWIDTH KATAKANA LETTER KE
"\u30B3<>\uFF7A;" // to HALFWIDTH KATAKANA LETTER KO
"\u30B5<>\uFF7B;" // to HALFWIDTH KATAKANA LETTER SA
"\u30B7<>\uFF7C;" // to HALFWIDTH KATAKANA LETTER SI
"\u30B9<>\uFF7D;" // to HALFWIDTH KATAKANA LETTER SU
"\u30BB<>\uFF7E;" // to HALFWIDTH KATAKANA LETTER SE
"\u30BD<>\uFF7F;" // to HALFWIDTH KATAKANA LETTER SO
"\u30BF<>\uFF80;" // to HALFWIDTH KATAKANA LETTER TA
"\u30C1<>\uFF81;" // to HALFWIDTH KATAKANA LETTER TI
"\u30C4<>\uFF82;" // to HALFWIDTH KATAKANA LETTER TU
"\u30C6<>\uFF83;" // to HALFWIDTH KATAKANA LETTER TE
"\u30C8<>\uFF84;" // to HALFWIDTH KATAKANA LETTER TO
"\u30CA<>\uFF85;" // to HALFWIDTH KATAKANA LETTER NA
"\u30CB<>\uFF86;" // to HALFWIDTH KATAKANA LETTER NI
"\u30CC<>\uFF87;" // to HALFWIDTH KATAKANA LETTER NU
"\u30CD<>\uFF88;" // to HALFWIDTH KATAKANA LETTER NE
"\u30CE<>\uFF89;" // to HALFWIDTH KATAKANA LETTER NO
"\u30CF<>\uFF8A;" // to HALFWIDTH KATAKANA LETTER HA
"\u30D2<>\uFF8B;" // to HALFWIDTH KATAKANA LETTER HI
"\u30D5<>\uFF8C;" // to HALFWIDTH KATAKANA LETTER HU
"\u30D8<>\uFF8D;" // to HALFWIDTH KATAKANA LETTER HE
"\u30DB<>\uFF8E;" // to HALFWIDTH KATAKANA LETTER HO
"\u30DE<>\uFF8F;" // to HALFWIDTH KATAKANA LETTER MA
"\u30DF<>\uFF90;" // to HALFWIDTH KATAKANA LETTER MI
"\u30E0<>\uFF91;" // to HALFWIDTH KATAKANA LETTER MU
"\u30E1<>\uFF92;" // to HALFWIDTH KATAKANA LETTER ME
"\u30E2<>\uFF93;" // to HALFWIDTH KATAKANA LETTER MO
"\u30E4<>\uFF94;" // to HALFWIDTH KATAKANA LETTER YA
"\u30E6<>\uFF95;" // to HALFWIDTH KATAKANA LETTER YU
"\u30E8<>\uFF96;" // to HALFWIDTH KATAKANA LETTER YO
"\u30E9<>\uFF97;" // to HALFWIDTH KATAKANA LETTER RA
"\u30EA<>\uFF98;" // to HALFWIDTH KATAKANA LETTER RI
"\u30EB<>\uFF99;" // to HALFWIDTH KATAKANA LETTER RU
"\u30EC<>\uFF9A;" // to HALFWIDTH KATAKANA LETTER RE
"\u30ED<>\uFF9B;" // to HALFWIDTH KATAKANA LETTER RO
"\u30EF<>\uFF9C;" // to HALFWIDTH KATAKANA LETTER WA
"\u30F3<>\uFF9D;" // to HALFWIDTH KATAKANA LETTER N
"\u3099<>\uFF9E;" // to HALFWIDTH KATAKANA VOICED SOUND MARK
"\u309A<>\uFF9F;" // to HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
"\u1160<>\uFFA0;" // to HALFWIDTH HANGUL FILLER
"\u1100<>\uFFA1;" // to HALFWIDTH HANGUL LETTER KIYEOK
"\u1101<>\uFFA2;" // to HALFWIDTH HANGUL LETTER SSANGKIYEOK
"\u11AA<>\uFFA3;" // to HALFWIDTH HANGUL LETTER KIYEOK-SIOS
"\u1102<>\uFFA4;" // to HALFWIDTH HANGUL LETTER NIEUN
"\u11AC<>\uFFA5;" // to HALFWIDTH HANGUL LETTER NIEUN-CIEUC
"\u11AD<>\uFFA6;" // to HALFWIDTH HANGUL LETTER NIEUN-HIEUH
"\u1103<>\uFFA7;" // to HALFWIDTH HANGUL LETTER TIKEUT
"\u1104<>\uFFA8;" // to HALFWIDTH HANGUL LETTER SSANGTIKEUT
"\u1105<>\uFFA9;" // to HALFWIDTH HANGUL LETTER RIEUL
"\u11B0<>\uFFAA;" // to HALFWIDTH HANGUL LETTER RIEUL-KIYEOK
"\u11B1<>\uFFAB;" // to HALFWIDTH HANGUL LETTER RIEUL-MIEUM
"\u11B2<>\uFFAC;" // to HALFWIDTH HANGUL LETTER RIEUL-PIEUP
"\u11B3<>\uFFAD;" // to HALFWIDTH HANGUL LETTER RIEUL-SIOS
"\u11B4<>\uFFAE;" // to HALFWIDTH HANGUL LETTER RIEUL-THIEUTH
"\u11B5<>\uFFAF;" // to HALFWIDTH HANGUL LETTER RIEUL-PHIEUPH
"\u111A<>\uFFB0;" // to HALFWIDTH HANGUL LETTER RIEUL-HIEUH
"\u1106<>\uFFB1;" // to HALFWIDTH HANGUL LETTER MIEUM
"\u1107<>\uFFB2;" // to HALFWIDTH HANGUL LETTER PIEUP
"\u1108<>\uFFB3;" // to HALFWIDTH HANGUL LETTER SSANGPIEUP
"\u1121<>\uFFB4;" // to HALFWIDTH HANGUL LETTER PIEUP-SIOS
"\u1109<>\uFFB5;" // to HALFWIDTH HANGUL LETTER SIOS
"\u110A<>\uFFB6;" // to HALFWIDTH HANGUL LETTER SSANGSIOS
"\u110B<>\uFFB7;" // to HALFWIDTH HANGUL LETTER IEUNG
"\u110C<>\uFFB8;" // to HALFWIDTH HANGUL LETTER CIEUC
"\u110D<>\uFFB9;" // to HALFWIDTH HANGUL LETTER SSANGCIEUC
"\u110E<>\uFFBA;" // to HALFWIDTH HANGUL LETTER CHIEUCH
"\u110F<>\uFFBB;" // to HALFWIDTH HANGUL LETTER KHIEUKH
"\u1110<>\uFFBC;" // to HALFWIDTH HANGUL LETTER THIEUTH
"\u1111<>\uFFBD;" // to HALFWIDTH HANGUL LETTER PHIEUPH
"\u1112<>\uFFBE;" // to HALFWIDTH HANGUL LETTER HIEUH
"\u1161<>\uFFC2;" // to HALFWIDTH HANGUL LETTER A
"\u1162<>\uFFC3;" // to HALFWIDTH HANGUL LETTER AE
"\u1163<>\uFFC4;" // to HALFWIDTH HANGUL LETTER YA
"\u1164<>\uFFC5;" // to HALFWIDTH HANGUL LETTER YAE
"\u1165<>\uFFC6;" // to HALFWIDTH HANGUL LETTER EO
"\u1166<>\uFFC7;" // to HALFWIDTH HANGUL LETTER E
"\u1167<>\uFFCA;" // to HALFWIDTH HANGUL LETTER YEO
"\u1168<>\uFFCB;" // to HALFWIDTH HANGUL LETTER YE
"\u1169<>\uFFCC;" // to HALFWIDTH HANGUL LETTER O
"\u116A<>\uFFCD;" // to HALFWIDTH HANGUL LETTER WA
"\u116B<>\uFFCE;" // to HALFWIDTH HANGUL LETTER WAE
"\u116C<>\uFFCF;" // to HALFWIDTH HANGUL LETTER OE
"\u116D<>\uFFD2;" // to HALFWIDTH HANGUL LETTER YO
"\u116E<>\uFFD3;" // to HALFWIDTH HANGUL LETTER U
"\u116F<>\uFFD4;" // to HALFWIDTH HANGUL LETTER WEO
"\u1170<>\uFFD5;" // to HALFWIDTH HANGUL LETTER WE
"\u1171<>\uFFD6;" // to HALFWIDTH HANGUL LETTER WI
"\u1172<>\uFFD7;" // to HALFWIDTH HANGUL LETTER YU
"\u1173<>\uFFDA;" // to HALFWIDTH HANGUL LETTER EU
"\u1174<>\uFFDB;" // to HALFWIDTH HANGUL LETTER YI
"\u1175<>\uFFDC;" // to HALFWIDTH HANGUL LETTER I
"\uFFE0<>'\u00a2';" // from FULLWIDTH CENT SIGN
"\uFFE1<>'\u00a3';" // from FULLWIDTH POUND SIGN
"\uFFE2<>'\u00ac';" // from FULLWIDTH NOT SIGN
"\uFFE3<>' '\u0304;" // from FULLWIDTH MACRON
"\uFFE4<>'\u00a6';" // from FULLWIDTH BROKEN BAR
"\uFFE5<>'\u00a5';" // from FULLWIDTH YEN SIGN
"\uFFE6<>\u20A9;" // from FULLWIDTH WON SIGN
"\u2502<>\uFFE8;" // to HALFWIDTH FORMS LIGHT VERTICAL
"\u2190<>\uFFE9;" // to HALFWIDTH LEFTWARDS ARROW
"\u2191<>\uFFEA;" // to HALFWIDTH UPWARDS ARROW
"\u2192<>\uFFEB;" // to HALFWIDTH RIGHTWARDS ARROW
"\u2193<>\uFFEC;" // to HALFWIDTH DOWNWARDS ARROW
"\u25A0<>\uFFED;" // to HALFWIDTH BLACK SQUARE
"\u25CB<>\uFFEE;" // to HALFWIDTH WHITE CIRCLE
}
}

128
icu4c/data/kbdescl1.txt Normal file
View File

@ -0,0 +1,128 @@
//--------------------------------------------------------------------
// Copyright (C) 1999, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 11/17/99 aliu Creation.
//--------------------------------------------------------------------
// KeyboardEscape-Latin1
kbdescl1 {
Rule {
"esc='';"
"grave=`;"
"acute='';"
"hat=^;"
"tilde=~;"
"umlaut=:;"
"ring=.;"
"cedilla=,;"
"slash=/;"
"super=^;"
// Make keyboard entry of {esc} possible
// and of backslash
"'\\'{esc}>{esc};"
"'\\\\'>'\\';"
// Long keys
"cur{esc}>\u00A4;"
"sec{esc}>\u00A7;"
"not{esc}>\u00AC;"
"mul{esc}>\u00D7;"
"div{esc}>\u00F7;"
"\\ {esc}>\u00A0;" // non-breaking space
"!{esc}>\u00A1;" // inverted exclamation
"c/{esc}>\u00A2;" // cent sign
"lb{esc}>\u00A3;" // pound sign
"'|'{esc}>\u00A6;" // broken vertical bar
":{esc}>\u00A8;" // umlaut
"{super}a{esc}>\u00AA;" // feminine ordinal
"'<<'{esc}>\u00AB;"
"r{esc}>\u00AE;"
"--{esc}>\u00AF;"
"-{esc}>\u00AD;"
"+-{esc}>\u00B1;"
"{super}2{esc}>\u00B2;"
"{super}3{esc}>\u00B3;"
"{acute}{esc}>\u00B4;"
"m{esc}>\u00B5;"
"para{esc}>\u00B6;"
"dot{esc}>\u00B7;"
"{cedilla}{esc}>\u00B8;"
"{super}1{esc}>\u00B9;"
"{super}o{esc}>\u00BA;" // masculine ordinal
"'>>'{esc}>\u00BB;"
"1/4{esc}>\u00BC;"
"1/2{esc}>\u00BD;"
"3/4{esc}>\u00BE;"
"?{esc}>\u00BF;"
"A{grave}{esc}>\u00C0;"
"A{acute}{esc}>\u00C1;"
"A{hat}{esc}>\u00C2;"
"A{tilde}{esc}>\u00C3;"
"A{umlaut}{esc}>\u00C4;"
"A{ring}{esc}>\u00C5;"
"AE{esc}>\u00C6;"
"C{cedilla}{esc}>\u00C7;"
"E{grave}{esc}>\u00C8;"
"E{acute}{esc}>\u00C9;"
"E{hat}{esc}>\u00CA;"
"E{umlaut}{esc}>\u00CB;"
"I{grave}{esc}>\u00CC;"
"I{acute}{esc}>\u00CD;"
"I{hat}{esc}>\u00CE;"
"I{umlaut}{esc}>\u00CF;"
"D-{esc}>\u00D0;"
"N{tilde}{esc}>\u00D1;"
"O{grave}{esc}>\u00D2;"
"O{acute}{esc}>\u00D3;"
"O{hat}{esc}>\u00D4;"
"O{tilde}{esc}>\u00D5;"
"O{umlaut}{esc}>\u00D6;"
"O{slash}{esc}>\u00D8;"
"U{grave}{esc}>\u00D9;"
"U{acute}{esc}>\u00DA;"
"U{hat}{esc}>\u00DB;"
"U{umlaut}{esc}>\u00DC;"
"Y{acute}{esc}>\u00DD;"
"TH{esc}>\u00DE;"
"ss{esc}>\u00DF;"
"a{grave}{esc}>\u00E0;"
"a{acute}{esc}>\u00E1;"
"a{hat}{esc}>\u00E2;"
"a{tilde}{esc}>\u00E3;"
"a{umlaut}{esc}>\u00E4;"
"a{ring}{esc}>\u00E5;"
"ae{esc}>\u00E6;"
"c{cedilla}{esc}>\u00E7;"
"c{esc}>\u00A9;" // copyright - after c{cedilla}
"e{grave}{esc}>\u00E8;"
"e{acute}{esc}>\u00E9;"
"e{hat}{esc}>\u00EA;"
"e{umlaut}{esc}>\u00EB;"
"i{grave}{esc}>\u00EC;"
"i{acute}{esc}>\u00ED;"
"i{hat}{esc}>\u00EE;"
"i{umlaut}{esc}>\u00EF;"
"d-{esc}>\u00F0;"
"n{tilde}{esc}>\u00F1;"
"o{grave}{esc}>\u00F2;"
"o{acute}{esc}>\u00F3;"
"o{hat}{esc}>\u00F4;"
"o{tilde}{esc}>\u00F5;"
"o{umlaut}{esc}>\u00F6;"
"o{slash}{esc}>\u00F8;"
"o{esc}>\u00B0;"
"u{grave}{esc}>\u00F9;"
"u{acute}{esc}>\u00FA;"
"u{hat}{esc}>\u00FB;"
"u{umlaut}{esc}>\u00FC;"
"y{acute}{esc}>\u00FD;"
"y{esc}>\u00A5;" // yen sign
"th{esc}>\u00FE;"
//masked: "ss{esc}>\u00FF;"
}
}

240
icu4c/data/larabic.txt Normal file
View File

@ -0,0 +1,240 @@
//--------------------------------------------------------------------
// Copyright (C) 1999, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 11/17/99 aliu Creation.
//--------------------------------------------------------------------
// Latin-Arabic
larabic {
Rule {
// To Do: finish adding shadda, add sokoon
"alefmadda=\u0622;"
"alefuhamza=\u0623;"
"wauuhamza=\u0624;"
"alefhamza=\u0625;"
"yehuhamza=\u0626;"
"alef=\u0627;"
"beh=\u0628;"
"tehmarbuta=\u0629;"
"teh=\u062A;"
"theh=\u062B;"
"geem=\u062C;"
"hah=\u062D;"
"kha=\u062E;"
"dal=\u062F;"
"dhal=\u0630;"
"reh=\u0631;"
"zain=\u0632;"
"seen=\u0633;"
"sheen=\u0634;"
"sad=\u0635;"
"dad=\u0636;"
"tah=\u0637;"
"zah=\u0638;"
"ein=\u0639;"
"ghein=\u063A;"
"feh=\u0641;"
"qaaf=\u0642;"
"kaf=\u0643;"
"lam=\u0644;"
"meem=\u0645;"
"noon=\u0646;"
"heh=\u0647;"
"wau=\u0648;"
"yehmaqsura=\u0649;"
"yeh=\u064A;"
"peh=\u06A4;"
"hamza=\u0621;"
"fathatein=\u064B;"
"dammatein=\u064C;"
"kasratein=\u064D;"
"fatha=\u064E;"
"damma=\u064F;"
"kasra=\u0650;"
"shadda=\u0651;"
"sokoon=\u0652;"
// convert English to Arabic
"Arabic>"
"\u062a\u062a\u0645\u062a\u0639' '"
"\u0627\u0644\u0644\u063a\u0629' '"
"\u0627\u0644\u0639\u0631\u0628\u0628\u064a\u0629' '"
"\u0628\u0628\u0646\u0638\u0645' '"
"\u0643\u062a\u0627\u0628\u0628\u064a\u0629' '"
"\u062c\u0645\u064a\u0644\u0629;"
"ai>{alefmadda};"
"ae>{alefuhamza};"
"ao>{alefhamza};"
"aa>{alef};"
"an>{fathatein};"
"a>{fatha};"
"b>{beh};"
"c>{kaf};"
"{dhal})dh>{shadda};"
"dh>{dhal};"
"{dad})dd>{shadda};"
"dd>{dad};"
"{dal})d>{shadda};"
"d>{dal};"
"e>{ein};"
"f>{feh};"
"gh>{ghein};"
"g>{geem};"
"hh>{hah};"
"h>{heh};"
"ii>{kasratein};"
"i>{kasra};"
"j>{geem};"
"kh>{kha};"
"k>{kaf};"
"l>{lam};"
"m>{meem};"
"n>{noon};"
"o>{hamza};"
"p>{peh};"
"q>{qaaf};"
"r>{reh};"
"sh>{sheen};"
"ss>{sad};"
"s>{seen};"
"th>{theh};"
"tm>{tehmarbuta};"
"tt>{tah};"
"t>{teh};"
"uu>{dammatein};"
"u>{damma};"
"v>{beh};"
"we>{wauuhamza};"
"w>{wau};"
"x>{kaf}{shadda}{seen};"
"ye>{yehuhamza};"
"ym>{yehmaqsura};"
"y>{yeh};"
"zz>{zah};"
"z>{zain};"
"0>\u0660;"+ // Arabic digit 0
"1>\u0661;"+ // Arabic digit 1
"2>\u0662;"+ // Arabic digit 2
"3>\u0663;"+ // Arabic digit 3
"4>\u0664;"+ // Arabic digit 4
"5>\u0665;"+ // Arabic digit 5
"6>\u0666;"+ // Arabic digit 6
"7>\u0667;"+ // Arabic digit 7
"8>\u0668;"+ // Arabic digit 8
"9>\u0669;"+ // Arabic digit 9
"%>\u066A;"+ // Arabic %
".>\u066B;"+ // Arabic decimal separator
",>\u066C;"+ // Arabic thousands separator
"*>\u066D;"+ // Arabic five-pointed star
"`0>0;"+ // Escaped forms of the above
"`1>1;"
"`2>2;"
"`3>3;"
"`4>4;"
"`5>5;"
"`6>6;"
"`7>7;"
"`8>8;"
"`9>9;"
"`%>%;"
"`.>.;"
"`,>,;"
"`*>*;"
"``>`;"
"''>;"
// now Arabic to English
"''ai<a){alefmadda};"
"ai<{alefmadda};"
"''ae<a){alefuhamza};"
"ae<{alefuhamza};"
"''ao<a){alefhamza};"
"ao<{alefhamza};"
"''aa<a){alef};"
"aa<{alef};"
"''an<a){fathatein};"
"an<{fathatein};"
"''a<a){fatha};"
"a<{fatha};"
"b<{beh};"
"''dh<d){dhal};"
"dh<{dhal};"
"''dd<d){dad};"
"dd<{dad};"
"''d<d){dal};"
"d<{dal};"
"''e<a){ein};"
"''e<w){ein};"
"''e<y){ein};"
"e<{ein};"
"f<{feh};"
"gh<{ghein};"
"''hh<d){hah};"
"''hh<t){hah};"
"''hh<k){hah};"
"''hh<s){hah};"
"hh<{hah};"
"''h<d){heh};"
"''h<t){heh};"
"''h<k){heh};"
"''h<s){heh};"
"h<{heh};"
"''ii<i){kasratein};"
"ii<{kasratein};"
"''i<i){kasra};"
"i<{kasra};"
"j<{geem};"
"kh<{kha};"
"x<{kaf}{shadda}{seen};"
"k<{kaf};"
"l<{lam};"
"''m<y){meem};"
"''m<t){meem};"
"m<{meem};"
"n<{noon};"
"''o<a){hamza};"
"o<{hamza};"
"p<{peh};"
"q<{qaaf};"
"r<{reh};"
"sh<{sheen};"
"''ss<s){sad};"
"ss<{sad};"
"''s<s){seen};"
"s<{seen};"
"th<{theh};"
"tm<{tehmarbuta};"
"''tt<t){tah};"
"tt<{tah};"
"''t<t){teh};"
"t<{teh};"
"''uu<u){dammatein};"
"uu<{dammatein};"
"''u<u){damma};"
"u<{damma};"
"we<{wauuhamza};"
"w<{wau};"
"ye<{yehuhamza};"
"ym<{yehmaqsura};"
"''y<y){yeh};"
"y<{yeh};"
"''zz<z){zah};"
"zz<{zah};"
"''z<z){zain};"
"z<{zain};"
"dh<dh){shadda};"
"dd<dd){shadda};"
"''d<d){shadda};"
}
}

307
icu4c/data/lcyril.txt Normal file
View File

@ -0,0 +1,307 @@
//--------------------------------------------------------------------
// Copyright (C) 1999, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 11/17/99 aliu Creation.
// 12/10/99 aliu Fix case handling.
//--------------------------------------------------------------------
lcyril {
Rule {
//* /* This class is designed to be a general Latin-Cyrillic
//* transliteration. The standard Russian transliterations
//* are generally used for the letters from Russian,
//* with additional Cyrillic characters given consistent
//* mappings.
//* */
"S-hacek=\u0160;"
"s-hacek=\u0161;"
"YO=\u0401;"
"J=\u0408;"
"A=\u0410;"
"B=\u0411;"
"V=\u0412;"
"G=\u0413;"
"D=\u0414;"
"YE=\u0415;"
"ZH=\u0416;"
"Z=\u0417;"
"YI=\u0418;"
"Y=\u0419;"
"K=\u041A;"
"L=\u041B;"
"M=\u041C;"
"N=\u041D;"
"O=\u041E;"
"P=\u041F;"
"R=\u0420;"
"S=\u0421;"
"T=\u0422;"
"U=\u0423;"
"F=\u0424;"
"KH=\u0425;"
"TS=\u0426;"
"CH=\u0427;"
"SH=\u0428;"
"SHCH=\u0429;"
"HARD=\u042A;"
"I=\u042B;"
"SOFT=\u042C;"
"E=\u042D;"
"YU=\u042E;"
"YA=\u042F;"
// Lowercase
"a=\u0430;"
"b=\u0431;"
"v=\u0432;"
"g=\u0433;"
"d=\u0434;"
"ye=\u0435;"
"zh=\u0436;"
"z=\u0437;"
"yi=\u0438;"
"y=\u0439;"
"k=\u043a;"
"l=\u043b;"
"m=\u043c;"
"n=\u043d;"
"o=\u043e;"
"p=\u043f;"
"r=\u0440;"
"s=\u0441;"
"t=\u0442;"
"u=\u0443;"
"f=\u0444;"
"kh=\u0445;"
"ts=\u0446;"
"ch=\u0447;"
"sh=\u0448;"
"shch=\u0449;"
"hard=\u044a;"
"i=\u044b;"
"soft=\u044c;"
"e=\u044d;"
"yu=\u044e;"
"ya=\u044f;"
"yo=\u0451;"
"j=\u0458;"
// variables
// some are duplicated so lowercasing works
"csoft=[eiyEIY];"
"CSOFT=[eiyEIY];"
"BECOMES_H=[{HARD}{hard}];"
"becomes_h=[{HARD}{hard}];"
"BECOMES_S=[{S}{s}];"
"becomes_s=[{S}{s}];"
"BECOMES_C=[{CH}{ch}];"
"becomes_c=[{CH}{ch}];"
"BECOMES_VOWEL=[{A}{E}{I}{O}{U}{a}{e}{i}{o}{u}];"
"becomes_vowel=[{A}{E}{I}{O}{U}{a}{e}{i}{o}{u}];"
"letter=[[:Lu:][:Ll:]];"
"lower=[[:Ll:]];"
//* /*
//* Modified to combine display transliterator and typing transliterator.
//* The display mapping uses accents for the "soft" vowels.
//* It does not, although it could, use characters like \u0161 instead of digraphs
//* like sh.
//* */
// #############################################
// Special titlecase forms, not duplicated
// #############################################
"Ch>{CH};" "Ch<{CH}({lower};"
"Kh>{KH};" "Kh<{KH}({lower};"
"Shch>{SHCH};" "Shch<{SHCH}({lower};"
"Sh>{SH};" "Sh<{SH}({lower};"
"Ts>{TS};" "Ts<{TS}({lower};"
"Zh>{ZH};" "Zh<{ZH}({lower};"
"Yi>{YI};" //+ "Yi<{YI}({lower};"
"Ye>{YE};" //+ "Ye<{YE}({lower};"
"Yo>{YO};" //+ "Yo<{YO}({lower};"
"Yu>{YU};" //+ "Yu<{YU}({lower};"
"Ya>{YA};" //+ "Ya<{YA}({lower};"
// #############################################
// Rules to Duplicate
// To get the lowercase versions, copy these and lowercase
// #############################################
// variant spellings in English
"SHTCH>{SHCH};"
"TCH>{CH};"
"TH>{Z};"
"Q>{K};"
"WH>{V};"
"W>{V};"
"X>{K}{S};" //+ "X<{K}{S};"
// Separate letters that would otherwise join
"SH''<{SH}({BECOMES_C};"
"T''<{T}({BECOMES_S};"
"K''<{K}({BECOMES_H};"
"S''<{S}({BECOMES_H};"
"T''<{T}({BECOMES_H};"
"Z''<{Z}({BECOMES_H};"
"Y''<{Y}({BECOMES_VOWEL};"
// Main letters
"A<>{A};"
"B<>{B};"
"CH<>{CH};"
"D<>{D};"
"E<>{E};"
"F<>{F};"
"G<>{G};"
"\u00cc<>{YI};"
"I<>{I};"
"KH<>{KH};"
"K<>{K};"
"L<>{L};"
"M<>{M};"
"N<>{N};"
"O<>{O};"
"P<>{P};"
"R<>{R};"
"SHCH<>{SHCH};"
"SH>{SH};" //+ "SH<{SH};"
"{S-hacek}<>{SH};"
"S<>{S};"
"TS<>{TS};"
"T<>{T};"
"U<>{U};"
"V<>{V};"
//\u00cc\u00c0\u00c8\u00d2\u00d9
"YE>{YE};" //+ "YE<{YE};"
"\u00c8<>{YE};"
"YO>{YO};" //+ "YO<{YO};"
"\u00d2<>{YO};"
"YU>{YU};" //+ "YU<{YU};"
"\u00d9<>{YU};"
"YA>{YA};" //+ "YA<{YA};"
"\u00c0<>{YA};"
"Y<>{Y};"
"ZH<>{ZH};"
"Z<>{Z};"
"H<>{HARD};"
"\u0178<>{SOFT};"
// Non-russian
"J<>{J};"
// variant spellings in English
"C({csoft}>{S};"
"C>{K};"
// #############################################
// Duplicated Rules
// Copy and lowercase the above rules
// #############################################
// variant spellings in english
"shtch>{shch};"
"tch>{ch};"
"th>{z};"
"q>{k};"
"wh>{v};"
"w>{v};"
"x>{k}{s};" //+ "x<{k}{s};"
// separate letters that would otherwise join
"sh''<{sh}({becomes_c};"
"t''<{t}({becomes_s};"
"k''<{k}({becomes_h};"
"s''<{s}({becomes_h};"
"t''<{t}({becomes_h};"
"z''<{z}({becomes_h};"
"y''<{y}({becomes_vowel};"
// main letters
"a<>{a};"
"b<>{b};"
"ch<>{ch};"
"d<>{d};"
"e<>{e};"
"f<>{f};"
"g<>{g};"
"\u00ec<>{yi};"
"i<>{i};"
"kh<>{kh};"
"k<>{k};"
"l<>{l};"
"m<>{m};"
"n<>{n};"
"o<>{o};"
"p<>{p};"
"r<>{r};"
"shch<>{shch};"
"sh>{sh};" //+ "sh<{sh};"
"{s-hacek}<>{sh};"
"s<>{s};"
"ts<>{ts};"
"t<>{t};"
"u<>{u};"
"v<>{v};"
//\u00ec\u00e0\u00e8\u00f2\u00f9
"ye>{ye};" //+ "ye<{ye};"
"\u00e8<>{ye};"
"yo>{yo};" //+ "yo<{yo};"
"\u00f2<>{yo};"
"yu>{yu};" //+ "yu<{yu};"
"\u00f9<>{yu};"
"ya>{ya};" //+ "ya<{ya};"
"\u00e0<>{ya};"
"y<>{y};"
"zh<>{zh};"
"z<>{z};"
"h<>{hard};"
"\u00ff<>{soft};"
// non-russian
"j<>{j};"
// variant spellings in english
"c({csoft}>{s};"
"c>{k};"
// #############################################
// End of Duplicated Rules
// #############################################
//generally the last rule
"''>;"
//the end
}
}

411
icu4c/data/ldevan.txt Normal file
View File

@ -0,0 +1,411 @@
//--------------------------------------------------------------------
// Copyright (C) 1999, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 11/17/99 aliu Creation.
//--------------------------------------------------------------------
// Latin-Devanagari
ldevan {
Rule {
//#####################################################################
// Keyboard Transliteration Table
//#####################################################################
// Conversions should be:
// 1. complete
// * convert every sequence of Latin letters (a to z plus apostrophe)
// to a sequence of Native letters
// * convert every sequence of Native letters to Latin letters
// 2. reversable
// * any string of Native converted to Latin and back should be the same
// * this is not true for English converted to Native & back, e.g.:
// k -> {kaf} -> k
// c -> {kaf} -> k
//#####################################################################
// Sequences of Latin letters may convert to a single Native letter.
// When this is the case, an apostrophe can be used to indicate separate
// letters.$
// E.g. sh -> {shin}
// s'h -> {sin}{heh}
// ss -> {sad}
// s's -> {sin}{shadda}
//#####################################################################
// To Do:
// finish adding shadda, add sokoon, fix uppercase
// make two transliteration tables: one with vowels, one without
//#####################################################################
// Modifications
// Devanagari Transliterator: broken up with consonsants/vowels
//#####################################################################
// Unicode character name definitions
//#####################################################################
//consonants
"candrabindu=\u0901;"
"bindu=\u0902;"
"visarga=\u0903;"
// w<vowel> represents the stand-alone form
"wa=\u0905;"
"waa=\u0906;"
"wi=\u0907;"
"wii=\u0908;"
"wu=\u0909;"
"wuu=\u090A;"
"wr=\u090B;"
"wl=\u090C;"
"we=\u090F;"
"wai=\u0910;"
"wo=\u0913;"
"wau=\u0914;"
"ka=\u0915;"
"kha=\u0916;"
"ga=\u0917;"
"gha=\u0918;"
"nga=\u0919;"
"ca=\u091A;"
"cha=\u091B;"
"ja=\u091C;"
"jha=\u091D;"
"nya=\u091E;"
"tta=\u091F;"
"ttha=\u0920;"
"dda=\u0921;"
"ddha=\u0922;"
"nna=\u0923;"
"ta=\u0924;"
"tha=\u0925;"
"da=\u0926;"
"dha=\u0927;"
"na=\u0928;"
"pa=\u092A;"
"pha=\u092B;"
"ba=\u092C;"
"bha=\u092D;"
"ma=\u092E;"
"ya=\u092F;"
"ra=\u0930;"
"rra=\u0931;"
"la=\u0933;"
"va=\u0935;"
"sha=\u0936;"
"ssa=\u0937;"
"sa=\u0938;"
"ha=\u0939;"
// <vowel> represents the dependent form
"aa=\u093E;"
"i=\u093F;"
"ii=\u0940;"
"u=\u0941;"
"uu=\u0942;"
"rh=\u0943;"
"lh=\u0944;"
"e=\u0947;"
"ai=\u0948;"
"o=\u094B;"
"au=\u094C;"
"virama=\u094D;"
"wrr=\u0960;"
"rrh=\u0962;"
"danda=\u0964;"
"doubleDanda=\u0965;"
"depVowelAbove=[\u093E-\u0940\u0945-\u094C];"
"depVowelBelow=[\u0941-\u0944];"
// Ech: Double escape U+0000, so UnicodeString doesn't consider it
// to be the end of the string. This is only necessary for U+0000
// right now. [liu]
"endThing=[{danda}{doubleDanda}\\u0000-\u08FF\u0980-\uFFFF];"
"&=[{virama}{aa}{ai}{au}{ii}{i}{uu}{u}{rrh}{rh}{lh}{e}{o}];"
"%=[bcdfghjklmnpqrstvwxyz];"
//#####################################################################
// convert from Latin letters to Native letters
//#####################################################################
//Hindi>\u092d\u093e\u0930\u0924--\u0020\u0926\u0947\u0936\u0020\u092c\u0928\u094d\u0927\u0941\u002e
// special forms with no good conversion
"mm>{bindu};"
"x>{visarga};"
// convert to independent forms at start of word or syllable:
// e.g. keai -> {ka}{e}{wai}; k'ai -> {ka}{wai}; (ai) -> ({wai})
// Moved up [LIU]
"aa>{waa};"
"ai>{wai};"
"au>{wau};"
"ii>{wii};"
"i>{wi};"
"uu>{wuu};"
"u>{wu};"
"rrh>{wrr};"
"rh>{wr};"
"lh>{wl};"
"e>{we};"
"o>{wo};"
"a>{wa};"
// normal consonants
"kh>{kha}|{virama};"
"k>{ka}|{virama};"
"q>{ka}|{virama};"
"gh>{gha}|{virama};"
"g>{ga}|{virama};"
"ng>{nga}|{virama};"
"ch>{cha}|{virama};"
"c>{ca}|{virama};"
"jh>{jha}|{virama};"
"j>{ja}|{virama};"
"ny>{nya}|{virama};"
"tth>{ttha}|{virama};"
"tt>{tta}|{virama};"
"ddh>{ddha}|{virama};"
"dd>{dda}|{virama};"
"nn>{nna}|{virama};"
"th>{tha}|{virama};"
"t>{ta}|{virama};"
"dh>{dha}|{virama};"
"d>{da}|{virama};"
"n>{na}|{virama};"
"ph>{pha}|{virama};"
"p>{pa}|{virama};"
"bh>{bha}|{virama};"
"b>{ba}|{virama};"
"m>{ma}|{virama};"
"y>{ya}|{virama};"
"r>{ra}|{virama};"
"l>{la}|{virama};"
"v>{va}|{virama};"
"f>{va}|{virama};"
"w>{va}|{virama};"
"sh>{sha}|{virama};"
"ss>{ssa}|{virama};"
"s>{sa}|{virama};"
"z>{sa}|{virama};"
"h>{ha}|{virama};"
".>{danda};"
"{danda}.>{doubleDanda};"
"{depVowelAbove})~>{bindu};"
"{depVowelBelow})~>{candrabindu};"
// convert to dependent forms after consonant with no vowel:
// e.g. kai -> {ka}{virama}ai -> {ka}{ai}
"{virama}aa>{aa};"
"{virama}ai>{ai};"
"{virama}au>{au};"
"{virama}ii>{ii};"
"{virama}i>{i};"
"{virama}uu>{uu};"
"{virama}u>{u};"
"{virama}rrh>{rrh};"
"{virama}rh>{rh};"
"{virama}lh>{lh};"
"{virama}e>{e};"
"{virama}o>{o};"
"{virama}a>;"
// otherwise convert independent forms when separated by ': k'ai -> {ka}{virama}{wai}
"{virama}''aa>{waa};"
"{virama}''ai>{wai};"
"{virama}''au>{wau};"
"{virama}''ii>{wii};"
"{virama}''i>{wi};"
"{virama}''uu>{wuu};"
"{virama}''u>{wu};"
"{virama}''rrh>{wrr};"
"{virama}''rh>{wr};"
"{virama}''lh>{wl};"
"{virama}''e>{we};"
"{virama}''o>{wo};"
"{virama}''a>{wa};"
"{virama}({endThing}>;"
// convert any left-over apostrophes used for separation
"''>;"
//#####################################################################
// convert from Native letters to Latin letters
//#####################################################################
// special forms with no good conversion
"mm<{bindu};"
"x<{visarga};"
// normal consonants
"kh<{kha}(&;"
"kha<{kha};"
"k''<{ka}{virama}({ha};"
"k<{ka}(&;"
"ka<{ka};"
"gh<{gha}(&;"
"gha<{gha};"
"g''<{ga}{virama}({ha};"
"g<{ga}(&;"
"ga<{ga};"
"ng<{nga}(&;"
"nga<{nga};"
"ch<{cha}(&;"
"cha<{cha};"
"c''<{ca}{virama}({ha};"
"c<{ca}(&;"
"ca<{ca};"
"jh<{jha}(&;"
"jha<{jha};"
"j''<{ja}{virama}({ha};"
"j<{ja}(&;"
"ja<{ja};"
"ny<{nya}(&;"
"nya<{nya};"
"tth<{ttha}(&;"
"ttha<{ttha};"
"tt''<{tta}{virama}({ha};"
"tt<{tta}(&;"
"tta<{tta};"
"ddh<{ddha}(&;"
"ddha<{ddha};"
"dd''<{dda}(&{ha};"
"dd<{dda}(&;"
"dda<{dda};"
"dh<{dha}(&;"
"dha<{dha};"
"d''<{da}{virama}({ha};"
"d''<{da}{virama}({ddha};"
"d''<{da}{virama}({dda};"
"d''<{da}{virama}({dha};"
"d''<{da}{virama}({da};"
"d<{da}(&;"
"da<{da};"
"th<{tha}(&;"
"tha<{tha};"
"t''<{ta}{virama}({ha};"
"t''<{ta}{virama}({ttha};"
"t''<{ta}{virama}({tta};"
"t''<{ta}{virama}({tha};"
"t''<{ta}{virama}({ta};"
"t<{ta}(&;"
"ta<{ta};"
"n''<{na}{virama}({ga};"
"n''<{na}{virama}({ya};"
"n<{na}(&;"
"na<{na};"
"ph<{pha}(&;"
"pha<{pha};"
"p''<{pa}{virama}({ha};"
"p<{pa}(&;"
"pa<{pa};"
"bh<{bha}(&;"
"bha<{bha};"
"b''<{ba}{virama}({ha};"
"b<{ba}(&;"
"ba<{ba};"
"m''<{ma}{virama}({ma};"
"m''<{ma}{virama}({bindu};"
"m<{ma}(&;"
"ma<{ma};"
"y<{ya}(&;"
"ya<{ya};"
"r''<{ra}{virama}({ha};"
"r<{ra}(&;"
"ra<{ra};"
"l''<{la}{virama}({ha};"
"l<{la}(&;"
"la<{la};"
"v<{va}(&;"
"va<{va};"
"sh<{sha}(&;"
"sha<{sha};"
"ss<{ssa}(&;"
"ssa<{ssa};"
"s''<{sa}{virama}({ha};"
"s''<{sa}{virama}({sha};"
"s''<{sa}{virama}({ssa};"
"s''<{sa}{virama}({sa};"
"s<{sa}(&;"
"sa<{sa};"
"h<{ha}(&;"
"ha<{ha};"
// dependent vowels (should never occur except following consonants)
"aa<{aa};"
"ai<{ai};"
"au<{au};"
"ii<{ii};"
"i<{i};"
"uu<{uu};"
"u<{u};"
"rrh<{rrh};"
"rh<{rh};"
"lh<{lh};"
"e<{e};"
"o<{o};"
// independent vowels (when following consonants)
"''aa<a){waa};"
"''aa<%){waa};"
"''ai<a){wai};"
"''ai<%){wai};"
"''au<a){wau};"
"''au<%){wau};"
"''ii<a){wii};"
"''ii<%){wii};"
"''i<a){wi};"
"''i<%){wi};"
"''uu<a){wuu};"
"''uu<%){wuu};"
"''u<a){wu};"
"''u<%){wu};"
"''rrh<%){wrr};"
"''rh<%){wr};"
"''lh<%){wl};"
"''e<%){we};"
"''o<%){wo};"
"''a<a){wa};"
"''a<%){wa};"
// independent vowels (otherwise)
"aa<{waa};"
"ai<{wai};"
"au<{wau};"
"ii<{wii};"
"i<{wi};"
"uu<{wuu};"
"u<{wu};"
"rrh<{wrr};"
"rh<{wr};"
"lh<{wl};"
"e<{we};"
"o<{wo};"
"a<{wa};"
// blow away any remaining viramas
"<{virama};"
}
}

376
icu4c/data/lgreek.txt Normal file
View File

@ -0,0 +1,376 @@
//--------------------------------------------------------------------
// Copyright (C) 1999, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 11/17/99 aliu Creation.
//--------------------------------------------------------------------
// Latin-Greek
lgreek {
Rule {
// ==============================================
// Modern Greek Transliteration Rules
//
// This transliterates modern Greek characters, but using rules
// that are traditional for Ancient Greek, and
// thus more resemble Greek words that have become part
// of English. It differs from the official Greek
// transliteration, which is more phonetic (since
// most modern Greek vowels, for example, have
// degenerated simply to sound like "ee").
//
// There are only a few tricky parts.
// 1. eta and omega don't map directly to Latin vowels,
// so we use a macron on e and o, and some
// other combinations if they are accented.
// 2. The accented, diaeresis i and y are substituted too.
// 3. Some letters use digraphs, like "ph". While typical,
// they need some special handling.
// 4. A gamma before a gamma or a few other letters is
// transliterated as an "n", as in "Anglo"
// 5. An ypsilon after a vowel is a "u", as in
// "Mouseio". Otherwise it is a "y" as in "Physikon"
// 6. The construction of the rules is made simpler by making sure
// that most rules for lowercase letters exactly correspond to the
// rules for uppercase letters, *except* for the case of the letters
// in the rule itself. That way, after modifying the uppercase rules,
// you can just copy, paste, and "set to lowercase" to get
// the rules for lowercase letters!
// ==============================================
// ==============================================
// Variables, used to make the rules more comprehensible
// and for conditionals.
// ==============================================
// Latin Letters
"E-MACRON=\u0112;"
"e-macron=\u0113;"
"O-MACRON=\u014C;"
"o-macron=\u014D;"
"Y-UMLAUT=\u0178;"
"y-umlaut=\u00FF;"
//! // with real accents.
//! + "E-MACRON-ACUTE=\u0112\u0301;"
//! + "e-macron-acute=\u0113\u0301;"
//! + "O-MACRON-ACUTE=\u014C\u0301;"
//! + "o-macron-acute=\u014D\u0301;"
//! + "y-umlaut-acute=\u00FF\u0301;"
//! + "\u00ef-acute=\u00ef\u0301;"
//! + "\u00fc-acute=\u00fc\u0301;"
//! //
// single letter equivalents
"E-MACRON-ACUTE=\u00CA;"
"e-macron-acute=\u00EA;"
"O-MACRON-ACUTE=\u00D4;"
"o-macron-acute=\u00F4;"
"y-umlaut-acute=\u0177;"
"\u00ef-acute=\u00EE;"
"\u00fc-acute=\u00FB;"
// Greek Letters
"ALPHA=\u0391;"
"BETA=\u0392;"
"GAMMA=\u0393;"
"DELTA=\u0394;"
"EPSILON=\u0395;"
"ZETA=\u0396;"
"ETA=\u0397;"
"THETA=\u0398;"
"IOTA=\u0399;"
"KAPPA=\u039A;"
"LAMBDA=\u039B;"
"MU=\u039C;"
"NU=\u039D;"
"XI=\u039E;"
"OMICRON=\u039F;"
"PI=\u03A0;"
"RHO=\u03A1;"
"SIGMA=\u03A3;"
"TAU=\u03A4;"
"YPSILON=\u03A5;"
"PHI=\u03A6;"
"CHI=\u03A7;"
"PSI=\u03A8;"
"OMEGA=\u03A9;"
"ALPHA+=\u0386;"
"EPSILON+=\u0388;"
"ETA+=\u0389;"
"IOTA+=\u038A;"
"OMICRON+=\u038C;"
"YPSILON+=\u038E;"
"OMEGA+=\u038F;"
"IOTA_DIAERESIS=\u03AA;"
"YPSILON_DIAERESIS=\u03AB;"
"alpha=\u03B1;"
"beta=\u03B2;"
"gamma=\u03B3;"
"delta=\u03B4;"
"epsilon=\u03B5;"
"zeta=\u03B6;"
"eta=\u03B7;"
"theta=\u03B8;"
"iota=\u03B9;"
"kappa=\u03BA;"
"lambda=\u03BB;"
"mu=\u03BC;"
"nu=\u03BD;"
"xi=\u03BE;"
"omicron=\u03BF;"
"pi=\u03C0;"
"rho=\u03C1;"
"sigma=\u03C3;"
"tau=\u03C4;"
"ypsilon=\u03C5;"
"phi=\u03C6;"
"chi=\u03C7;"
"psi=\u03C8;"
"omega=\u03C9;"
//forms
"alpha+=\u03AC;"
"epsilon+=\u03AD;"
"eta+=\u03AE;"
"iota+=\u03AF;"
"omicron+=\u03CC;"
"ypsilon+=\u03CD;"
"omega+=\u03CE;"
"iota_diaeresis=\u03CA;"
"ypsilon_diaeresis=\u03CB;"
"iota_diaeresis+=\u0390;"
"ypsilon_diaeresis+=\u03B0;"
"sigma+=\u03C2;"
// Variables for conditional mappings
// Use lowercase for all variable names, to allow cut/paste below.
"letter=[~[:Lu:][:Ll:]];"
"lower=[[:Ll:]];"
"softener=[eiyEIY];"
"vowel=[aeiouAEIOU"
"{ALPHA}{EPSILON}{ETA}{IOTA}{OMICRON}{YPSILON}{OMEGA}"
"{ALPHA+}{EPSILON+}{ETA+}{IOTA+}{OMICRON+}{YPSILON+}{OMEGA+}"
"{IOTA_DIAERESIS}{YPSILON_DIAERESIS}"
"{alpha}{epsilon}{eta}{iota}{omicron}{ypsilon}{omega}"
"{alpha+}{epsilon+}{eta+}{iota+}{omicron+}{ypsilon+}{omega+}"
"{iota_diaeresis}{ypsilon_diaeresis}"
"{iota_diaeresis+}{ypsilon_diaeresis+}"
"];"
"n-gamma=[GKXCgkxc];"
"gamma-n=[{GAMMA}{KAPPA}{CHI}{XI}{gamma}{kappa}{chi}{xi}];"
"pp=[Pp];"
// ==============================================
// Rules
// ==============================================
// The following are special titlecases, and should
// not be copied when duplicating the lowercase
// ==============================================
"Th <> {THETA}({lower};"
"Ph <> {PHI}({lower};"
"Ch <> {CHI}({lower};"
//masked: + "Ps<{PHI}({lower};"
// Because there is no uppercase forms for final sigma,
// we had to move all the sigma rules up here.
// Remember to insert ' to preserve round trip, for double letters
// don't need to do this for the digraphs with h,
// since it is not created when mapping back from greek
// use special form for s
"''S <> ({pp}) {SIGMA} ;" // handle PS
"S <> {SIGMA};"
// The following are a bit tricky. 's' takes two forms in greek
// final or non final.
// We use ~s to represent the abnormal form: final before letter
// or non-final before non-letter.
// We use 's to separate p and s (otherwise ps is one letter)
// so, we break out the following forms:
"''s < ({pp}) {sigma} ({letter});"
"s < {sigma} ({letter});"
"~s < {sigma} ;"
"~s < {sigma+} ({letter});"
"''s < ({pp}) {sigma+} ;"
"s < {sigma+} ;"
"~s ({letter}) > {sigma+};"
"~s > {sigma};"
"''s ({letter}) > {sigma};"
"''s > {sigma+};"
"s ({letter}) > {sigma};"
"s > {sigma+};"
// because there are no uppercase forms, had to move these up too.
"i\"`>{iota_diaeresis+};"
"y\"`>{ypsilon_diaeresis+};"
"{\u00ef-acute} <> {iota_diaeresis+};"
"{\u00fc-acute} <> {vowel}){ypsilon_diaeresis+};"
"{y-umlaut-acute} <> {ypsilon_diaeresis+};"
// ==============================================
// Uppercase Forms.
// To make lowercase forms, just copy and lowercase below
// ==============================================
// Typing variants, in case the keyboard doesn't have accents
"A`>{ALPHA+};"
"E`>{EPSILON+};"
"EE`>{ETA+};"
"EE>{ETA};"
"I`>{IOTA+};"
"O`>{OMICRON+};"
"OO`>{OMEGA+};"
"OO>{OMEGA};"
"I\">{IOTA_DIAERESIS};"
"Y\">{YPSILON_DIAERESIS};"
// Basic Letters
"A<>{ALPHA};"
"\u00c1<>{ALPHA+};"
"B<>{BETA};"
"N ({n-gamma}) <> {GAMMA} ({gamma-n});"
"G<>{GAMMA};"
"D<>{DELTA};"
"''E <> ([Ee]){EPSILON};" // handle EE
"E<>{EPSILON};"
"\u00c9<>{EPSILON+};"
"Z<>{ZETA};"
"{E-MACRON-ACUTE}<>{ETA+};"
"{E-MACRON}<>{ETA};"
"TH<>{THETA};"
"I<>{IOTA};"
"\u00cd<>{IOTA+};"
"\u00cf<>{IOTA_DIAERESIS};"
"K<>{KAPPA};"
"L<>{LAMBDA};"
"M<>{MU};"
"N'' <> {NU} ({gamma-n});"
"N<>{NU};"
"X<>{XI};"
"''O <> ([Oo]) {OMICRON};" // handle OO
"O<>{OMICRON};"
"\u00d3<>{OMICRON+};"
"PH<>{PHI};" // needs ordering before P
"PS<>{PSI};" // needs ordering before P
"P<>{PI};"
"R<>{RHO};"
"T<>{TAU};"
"U <> ({vowel}) {YPSILON};"
"\u00da <> ({vowel}) {YPSILON+};"
"\u00dc <> ({vowel}) {YPSILON_DIAERESIS};"
"Y<>{YPSILON};"
"\u00dd<>{YPSILON+};"
"{Y-UMLAUT}<>{YPSILON_DIAERESIS};"
"CH<>{CHI};"
"{O-MACRON-ACUTE}<>{OMEGA+};"
"{O-MACRON}<>{OMEGA};"
// Extra English Letters. Mapped for completeness
"C({softener})>|S;"
"C>|K;"
"F>|PH;"
"H>|CH;"
"J>|I;"
"Q>|K;"
"V>|U;"
"W>|U;"
// ==============================================
// Lowercase Forms. Just copy above and lowercase
// ==============================================
// typing variants, in case the keyboard doesn't have accents
"a`>{alpha+};"
"e`>{epsilon+};"
"ee`>{eta+};"
"ee>{eta};"
"i`>{iota+};"
"o`>{omicron+};"
"oo`>{omega+};"
"oo>{omega};"
"i\">{iota_diaeresis};"
"y\">{ypsilon_diaeresis};"
// basic letters
"a<>{alpha};"
"\u00e1<>{alpha+};"
"b<>{beta};"
"n ({n-gamma}) <> {gamma} ({gamma-n});"
"g<>{gamma};"
"d<>{delta};"
"''e <> ([Ee]){epsilon};" // handle EE
"e<>{epsilon};"
"\u00e9<>{epsilon+};"
"z<>{zeta};"
"{e-macron-acute}<>{eta+};"
"{e-macron}<>{eta};"
"th<>{theta};"
"i<>{iota};"
"\u00ed<>{iota+};"
"\u00ef<>{iota_diaeresis};"
"k<>{kappa};"
"l<>{lambda};"
"m<>{mu};"
"n'' <> {nu} ({gamma-n});"
"n<>{nu};"
"x<>{xi};"
"''o <> ([Oo]) {omicron};" // handle OO
"o<>{omicron};"
"\u00f3<>{omicron+};"
"ph<>{phi};" // needs ordering before p
"ps<>{psi};" // needs ordering before p
"p<>{pi};"
"r<>{rho};"
"t<>{tau};"
"u <> ({vowel}){ypsilon};"
"\u00fa <> ({vowel}){ypsilon+};"
"\u00fc <> ({vowel}){ypsilon_diaeresis};"
"y<>{ypsilon};"
"\u00fd<>{ypsilon+};"
"{y-umlaut}<>{ypsilon_diaeresis};"
"ch<>{chi};"
"{o-macron-acute}<>{omega+};"
"{o-macron}<>{omega};"
// extra english letters. mapped for completeness
"c({softener})>|s;"
"c>|k;"
"f>|ph;"
"h>|ch;"
"j>|i;"
"q>|k;"
"v>|u;"
"w>|u;"
// ====================================
// Normal final rule: remove '
// ====================================
//+ "''>;"
}
}

2
icu4c/data/lhalfwid.txt Normal file
View File

@ -0,0 +1,2 @@
// This file is obsolete
// See fullhalf

278
icu4c/data/lhebrew.txt Normal file
View File

@ -0,0 +1,278 @@
//--------------------------------------------------------------------
// Copyright (C) 1999, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 11/17/99 aliu Creation.
//--------------------------------------------------------------------
// Latin-Hebrew
lhebrew {
Rule {
//variable names, derived from the Unicode names.
"POINT_SHEVA=\u05B0;"
"POINT_HATAF_SEGOL=\u05B1;"
"POINT_HATAF_PATAH=\u05B2;"
"POINT_HATAF_QAMATS=\u05B3;"
"POINT_HIRIQ=\u05B4;"
"POINT_TSERE=\u05B5;"
"POINT_SEGOL=\u05B6;"
"POINT_PATAH=\u05B7;"
"POINT_QAMATS=\u05B8;"
"POINT_HOLAM=\u05B9;"
"POINT_QUBUTS=\u05BB;"
"POINT_DAGESH_OR_MAPIQ=\u05BC;"
"POINT_METEG=\u05BD;"
"PUNCTUATION_MAQAF=\u05BE;"
"POINT_RAFE=\u05BF;"
"PUNCTUATION_PASEQ=\u05C0;"
"POINT_SHIN_DOT=\u05C1;"
"POINT_SIN_DOT=\u05C2;"
"PUNCTUATION_SOF_PASUQ=\u05C3;"
"ALEF=\u05D0;"
"BET=\u05D1;"
"GIMEL=\u05D2;"
"DALET=\u05D3;"
"HE=\u05D4;"
"VAV=\u05D5;"
"ZAYIN=\u05D6;"
"HET=\u05D7;"
"TET=\u05D8;"
"YOD=\u05D9;"
"FINAL_KAF=\u05DA;"
"KAF=\u05DB;"
"LAMED=\u05DC;"
"FINAL_MEM=\u05DD;"
"MEM=\u05DE;"
"FINAL_NUN=\u05DF;"
"NUN=\u05E0;"
"SAMEKH=\u05E1;"
"AYIN=\u05E2;"
"FINAL_PE=\u05E3;"
"PE=\u05E4;"
"FINAL_TSADI=\u05E5;"
"TSADI=\u05E6;"
"QOF=\u05E7;"
"RESH=\u05E8;"
"SHIN=\u05E9;"
"TAV=\u05EA;"
"YIDDISH_DOUBLE_VAV=\u05F0;"
"YIDDISH_VAV_YOD=\u05F1;"
"YIDDISH_DOUBLE_YOD=\u05F2;"
"PUNCTUATION_GERESH=\u05F3;"
"PUNCTUATION_GERSHAYIM=\u05F4;"
//wildcards
//The values can be anything we don't use in this file: start at E000.
"letter=[abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ];"
"softvowel=[eiyEIY];"
"vowellike=[{ALEF}{AYIN}{YOD}{VAV}];"
//?>{POINT_SHEVA}
//?>{POINT_HATAF_SEGOL}
//?>{POINT_HATAF_PATAH}
//?>{POINT_HATAF_QAMATS}
//?>{POINT_HIRIQ}
//?>{POINT_TSERE}
//?>{POINT_SEGOL}
//?>{POINT_PATAH}
//?>{POINT_QAMATS}
//?>{POINT_HOLAM}
//?>{POINT_QUBUTS}
//?>{POINT_DAGESH_OR_MAPIQ}
//?>{POINT_METEG}
//?>{PUNCTUATION_MAQAF}
//?>{POINT_RAFE}
//?>{PUNCTUATION_PASEQ}
//?>{POINT_SHIN_DOT}
//?>{POINT_SIN_DOT}
//?>{PUNCTUATION_SOF_PASUQ}
"a>{ALEF};"
"A>{ALEF};"
"b>{BET};"
"B>{BET};"
"c({softvowel}>{SAMEKH};"
"C({softvowel}>{SAMEKH};"
"c({letter}>{KAF};"
"C({letter}>{KAF};"
"c>{FINAL_KAF};"
"C>{FINAL_KAF};"
"d>{DALET};"
"D>{DALET};"
"e>{AYIN};"
"E>{AYIN};"
"f({letter}>{PE};"
"f>{FINAL_PE};"
"F({letter}>{PE};"
"F>{FINAL_PE};"
"g>{GIMEL};"
"G>{GIMEL};"
"h>{HE};"
"H>{HE};"
"i>{YOD};"
"I>{YOD};"
"j>{DALET}{SHIN};"
"J>{DALET}{SHIN};"
"kH>{HET};"
"kh>{HET};"
"KH>{HET};"
"Kh>{HET};"
"k({letter}>{KAF};"
"K({letter}>{KAF};"
"k>{FINAL_KAF};"
"K>{FINAL_KAF};"
"l>{LAMED};"
"L>{LAMED};"
"m({letter}>{MEM};"
"m>{FINAL_MEM};"
"M({letter}>{MEM};"
"M>{FINAL_MEM};"
"n({letter}>{NUN};"
"n>{FINAL_NUN};"
"N({letter}>{NUN};"
"N>{FINAL_NUN};"
"o>{VAV};"
"O>{VAV};"
"p({letter}>{PE};"
"p>{FINAL_PE};"
"P({letter}>{PE};"
"P>{FINAL_PE};"
"q>{QOF};"
"Q>{QOF};"
"r>{RESH};"
"R>{RESH};"
"sH>{SHIN};"
"sh>{SHIN};"
"SH>{SHIN};"
"Sh>{SHIN};"
"s>{SAMEKH};"
"S>{SAMEKH};"
"th>{TAV};"
"tH>{TAV};"
"TH>{TAV};"
"Th>{TAV};"
"tS({letter}>{TSADI};"
"ts({letter}>{TSADI};"
"Ts({letter}>{TSADI};"
"TS({letter}>{TSADI};"
"tS>{FINAL_TSADI};"
"ts>{FINAL_TSADI};"
"Ts>{FINAL_TSADI};"
"TS>{FINAL_TSADI};"
"t>{TET};"
"T>{TET};"
"u>{VAV};"
"U>{VAV};"
"v>{VAV};"
"V>{VAV};"
"w>{VAV};"
"W>{VAV};"
"x>{KAF}{SAMEKH};"
"X>{KAF}{SAMEKH};"
"y>{YOD};"
"Y>{YOD};"
"z>{ZAYIN};"
"Z>{ZAYIN};"
//#?>{YIDDISH_DOUBLE_VAV}
//?>{YIDDISH_VAV_YOD}
//?>{YIDDISH_DOUBLE_YOD}
//?>{PUNCTUATION_GERESH}
//?>{PUNCTUATION_GERSHAYIM}
"''>;"
//{POINT_SHEVA}>@
//{POINT_HATAF_SEGOL}>@
//{POINT_HATAF_PATAH}>@
//{POINT_HATAF_QAMATS}>@
//{POINT_HIRIQ}>@
//{POINT_TSERE}>@
//{POINT_SEGOL}>@
//{POINT_PATAH}>@
//{POINT_QAMATS}>@
//{POINT_HOLAM}>@
//{POINT_QUBUTS}>@
//{POINT_DAGESH_OR_MAPIQ}>@
//{POINT_METEG}>@
//{PUNCTUATION_MAQAF}>@
//{POINT_RAFE}>@
//{PUNCTUATION_PASEQ}>@
//{POINT_SHIN_DOT}>@
//{POINT_SIN_DOT}>@
//{PUNCTUATION_SOF_PASUQ}>@
"a<{ALEF};"
"e<{AYIN};"
"b<{BET};"
"d<{DALET};"
"k<{FINAL_KAF};"
"m<{FINAL_MEM};"
"n<{FINAL_NUN};"
"p<{FINAL_PE};"
"ts<{FINAL_TSADI};"
"g<{GIMEL};"
"kh<{HET};"
"h<{HE};"
"k''<{KAF}({HE};"
"k<{KAF};"
"l<{LAMED};"
"m<{MEM};"
"n<{NUN};"
"p<{PE};"
"q<{QOF};"
"r<{RESH};"
"s''<{SAMEKH}({HE};"
"s<{SAMEKH};"
"sh<{SHIN};"
"th<{TAV};"
"t''<{TET}({HE};"
"t''<{TET}({SAMEKH};"
"t''<{TET}({SHIN};"
"t<{TET};"
"ts<{TSADI};"
"v<{VAV}({vowellike};"
"u<{VAV};"
"y<{YOD};"
"z<{ZAYIN};"
//{YIDDISH_DOUBLE_VAV}>@
//{YIDDISH_VAV_YOD}>@
//{YIDDISH_DOUBLE_YOD}>@
//{PUNCTUATION_GERESH}>@
//{PUNCTUATION_GERSHAYIM}>@
"<'';"
}
}

322
icu4c/data/ljamo.txt Normal file
View File

@ -0,0 +1,322 @@
//--------------------------------------------------------------------
// Copyright (c) 2000, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 01/13/2000 aliu Creation.
//--------------------------------------------------------------------
ljamo {
Rule {
// VARIABLES
"initial=[\u1100-\u115F];"
"medial=[\u1160-\u11A7];"
"final=[\u11A8-\u11F9];" // added - aliu
"vowel=[aeiouwyAEIOUWY\u1160-\u11A7];"
"consonant=[bcdfghjklmnpqrstvxzBCDFGHJKLMNPQRSTVXZ{medial}{final}];"
"ye=[yeYE];"
"ywe=[yweYWE];"
"yw=[ywYW];"
"nl=[nlNL];"
"gnl=[gnlGNL];"
"lsgb=[lsgbLSGB];"
"ywao=[ywaoYWAO];"
"bl=[blBL];"
// RULES
// Hangul structure is IMF or IM
// So you can have, because of adjacent sequences
// IM, but not II or IF
// MF or MI, but not MM
// FI, but not FF or FM
// For English, we just have C or V.
// To generate valid Hangul:
// Vowels:
// We insert IEUNG between VV, and otherwise map V to M
// We also insert IEUNG if there is no
// Consonants:
// We don't break doubles
// Cases like lmgg, we have to break at lm
// So to guess whether a consonant is I or F
// we map all C's to F, except when followed by a vowel, e.g.
// X[{vowel}>CHOSEONG (initial)
// X>JONGSEONG (final)
// special insertion for funny sequences of vowels, and for empty consonant
"'' < ({consonant}) \u110B;" // insert a break between any consonant and the empty consonant.
"({medial}) ({vowel}) <> \u110B;" // HANGUL CHOSEONG IEUNG
// Below, insert an empty consonant in front of a vowel, if there is no Initial in front.
// Fix casing.
// Because Korean is caseless, we just want to treat everything as
// lowercase.
// we could do this by always preceeding this transliterator with
// an upper-lowercase transformation, but that wouldn't invert nicely.
// We use the "revisit" syntax to just convert latin to latin
// so that we can avoid
// having to restate all the Latin=>Jamo rules, with the I/F handling.
// We don't have to add titlecase, since that will be picked up
// since the first letter is converted, then revisited. E.g.
// |Gg => |gg => {sang kiyeok}
// We do have to have all caps, since otherwise we could get:
// |GG => |gG => {kiyeok}|G => {kiyeok}|g => {kiyeok}{kiyeok}
"Z > |z;"
"YU > |yu;"
"YO > |yo;"
"YI > |yi;"
"YEO > |yeo;"
"YE > |ye;"
"YAE > |yae;"
"YA > |ya;"
"Y > |y;"
"WI > |wi;"
"WEO > |weo;"
"WE > |we;"
"WAE > |wae;"
"WA > |wa;"
"W > |w;"
"U > |u;"
"T > |t;"
"SS > |ss;"
"S > |s;"
"P > |p;"
"OE > |oe;"
"O > |o;"
"NJ > |nj;"
"NH > |nh;"
"NG > |ng;"
"N > |n;"
"M > |m;"
"LT > |lt;"
"LS > |ls;"
"LP > |lp;"
"LM > |lm;"
"LH > |lh;"
"LG > |lg;"
"LB > |lb;"
"L > |l;"
"K > |k;"
"JJ > |jj;"
"J > |j;"
"I > |i;"
"H > |h;"
"GS > |gs;"
"GG > |gg;"
"G > |g;"
"EU > |eu;"
"EO > |eo;"
"E > |e;"
"DD > |dd;"
"D > |d;"
"BS > |bs;"
"BB > |bb;"
"B > |b;"
"AE > |ae;"
"A > |a;"
// APOSTROPHE
// As always, an apostrophe is used to separate digraphs into
// singles. That is, if you really wanted [KAN][GGAN], instead
// of [KANG][GAN] you would write "kan'ggan".
// Rules for inserting ' when mapping separated digraphs back
// from Hangul to Latin. Catch every letter that can be the
// LAST of a digraph (or multigraph) AND first of an initial
"'' < (l) (\u11c0;" // hangul jongseong thieuth
"'' < ({lsgb}) (\u11ba;" // hangul jongseong sios
"'' < (l) (\u11c1;" // hangul jongseong phieuph
"'' < (l) (\u11b7;" // hangul jongseong mieum
"'' < (n) (\u11bd;" // hangul jongseong cieuc
"'' < ({nl}) (\u11c2;" // hangul jongseong hieuh
"'' < ({gnl}) (\u11a9;" // hangul jongseong ssangkiyeok
"'' < ({bl}) (\u11b8;" // hangul jongseong pieup
"'' < (d) (\u11ae;" // hangul jongseong tikeut
"'' < ({ye}) (\u116e;" // hangul jungseong u
"'' < ({ywe}) (\u1169;" // hangul jungseong o
"'' < ({yw}) (\u1175;" // hangul jungseong i
"'' < ({ywao}) (\u1166;" // hangul jungseong e
"'' < ({yw}) (\u1161;" // hangul jungseong a
"'' < (l) (\u1110;" // hangul choseong thieuth
"'' < ({lsgb}) (\u110a;" // hangul choseong ssangsios
"'' < ({lsgb}) (\u1109;" // hangul choseong sios
"'' < (l) (\u1111;" // hangul choseong phieuph
"'' < (l) (\u1106;" // hangul choseong mieum
"'' < (n) (\u110c;" // hangul choseong cieuc
"'' < (n) (\u110d;"
"'' < ({nl}) (\u1112;" // hangul choseong hieuh
"'' < ({gnl}) (\u1101;" // hangul choseong ssangkiyeok
"'' < ({gnl}) (\u1100;" // hangul choseong kiyeok
"'' < (d) (\u1103;" // hangul choseong tikeut
"'' < (d) (\u1104;"
"'' < ({bl}) (\u1107;" // hangul choseong pieup
"'' < ({bl}) (\u1108;"
// INITIALS
"t ({vowel}) <> \u1110;" // hangul choseong thieuth
"ss ({vowel}) <> \u110a;" // hangul choseong ssangsios
"s ({vowel}) <> \u1109;" // hangul choseong sios
"p ({vowel}) <> \u1111;" // hangul choseong phieuph
"n ({vowel}) <> \u1102;" // hangul choseong nieun
"m ({vowel}) <> \u1106;" // hangul choseong mieum
"l ({vowel}) <> \u1105;" // hangul choseong rieul
"k ({vowel}) <> \u110f;" // hangul choseong khieukh
"j ({vowel}) <> \u110c;" // hangul choseong cieuc
"h ({vowel}) <> \u1112;" // hangul choseong hieuh
"gg ({vowel}) <> \u1101;" // hangul choseong ssangkiyeok
"g ({vowel}) <> \u1100;" // hangul choseong kiyeok
"d ({vowel}) <> \u1103;" // hangul choseong tikeut
"c ({vowel}) <> \u110e;" // hangul choseong chieuch
"b ({vowel}) <> \u1107;" // hangul choseong pieup
"bb ({vowel}) <> \u1108;"
"jj ({vowel}) <> \u110d;"
"dd ({vowel}) <> \u1104;"
// If we have gotten through to these rules, and we start with
// a consonant, then the remaining mappings would be to F,
// because must have CC (or C<non-letter>), not CV.
// If we have F before us, then
// we would end up with FF, which is wrong. The simplest fix is
// to still make it an initial, but also insert an "u",
// so we end up with F, I, u, and then continue with the C
// special, only initial
"bb > \u1108\u116e;" // hangul choseong ssangpieup
"jj > \u1108\u110d;" // hangul choseong ssangcieuc
"dd > \u1108\u1104;" // hangul choseong ssangtikeut
"({final}) t > \u1110\u116e;" // hangul choseong thieuth
"({final}) ss > \u110a\u116e;" // hangul choseong ssangsios
"({final}) s > \u1109\u116e;" // hangul choseong sios
"({final}) p > \u1111\u116e;" // hangul choseong phieuph
"({final}) n > \u1102\u116e;" // hangul choseong nieun
"({final}) m > \u1106\u116e;" // hangul choseong mieum
"({final}) l > \u1105\u116e;" // hangul choseong rieul
"({final}) k > \u110f\u116e;" // hangul choseong khieukh
"({final}) j > \u110c\u116e;" // hangul choseong cieuc
"({final}) h > \u1112\u116e;" // hangul choseong hieuh
"({final}) gg > \u1101\u116e;" // hangul choseong ssangkiyeok
"({final}) g > \u1100\u116e;" // hangul choseong kiyeok
"({final}) d > \u1103\u116e;" // hangul choseong tikeut
"({final}) c > \u110e\u116e;" // hangul choseong chieuch
"({final}) b > \u1107\u116e;" // hangul choseong pieup
// MEDIALS after INITIALS
"({initial}) yu <> \u1172;" // hangul jungseong yu
"({initial}) yo <> \u116d;" // hangul jungseong yo
"({initial}) yi <> \u1174;" // hangul jungseong yi
"({initial}) yeo <> \u1167;" // hangul jungseong yeo
"({initial}) ye <> \u1168;" // hangul jungseong ye
"({initial}) yae <> \u1164;" // hangul jungseong yae
"({initial}) ya <> \u1163;" // hangul jungseong ya
"({initial}) wi <> \u1171;" // hangul jungseong wi
"({initial}) weo <> \u116f;" // hangul jungseong weo
"({initial}) we <> \u1170;" // hangul jungseong we
"({initial}) wae <> \u116b;" // hangul jungseong wae
"({initial}) wa <> \u116a;" // hangul jungseong wa
"({initial}) u <> \u116e;" // hangul jungseong u
"({initial}) oe <> \u116c;" // hangul jungseong oe
"({initial}) o <> \u1169;" // hangul jungseong o
"({initial}) i <> \u1175;" // hangul jungseong i
"({initial}) eu <> \u1173;" // hangul jungseong eu
"({initial}) eo <> \u1165;" // hangul jungseong eo
"({initial}) e <> \u1166;" // hangul jungseong e
"({initial}) ae <> \u1162;" // hangul jungseong ae
"({initial}) a <> \u1161;" // hangul jungseong a
// MEDIALS (vowels) not after INITIALs
"yu > \u110B\u1172;" // hangul jungseong yu
"yo > \u110B\u116d;" // hangul jungseong yo
"yi > \u110B\u1174;" // hangul jungseong yi
"yeo > \u110B\u1167;" // hangul jungseong yeo
"ye > \u110B\u1168;" // hangul jungseong ye
"yae > \u110B\u1164;" // hangul jungseong yae
"ya > \u110B\u1163;" // hangul jungseong ya
"wi > \u110B\u1171;" // hangul jungseong wi
"weo > \u110B\u116f;" // hangul jungseong weo
"we > \u110B\u1170;" // hangul jungseong we
"wae > \u110B\u116b;" // hangul jungseong wae
"wa > \u110B\u116a;" // hangul jungseong wa
"u > \u110B\u116e;" // hangul jungseong u
"oe > \u110B\u116c;" // hangul jungseong oe
"o > \u110B\u1169;" // hangul jungseong o
"i > \u110B\u1175;" // hangul jungseong i
"eu > \u110B\u1173;" // hangul jungseong eu
"eo > \u110B\u1165;" // hangul jungseong eo
"e > \u110B\u1166;" // hangul jungseong e
"ae > \u110B\u1162;" // hangul jungseong ae
"a > \u110B\u1161;" // hangul jungseong a
// FINALS
"t <> \u11c0;" // hangul jongseong thieuth
"ss <> \u11bb;" // hangul jongseong ssangsios
"s <> \u11ba;" // hangul jongseong sios
"p <> \u11c1;" // hangul jongseong phieuph
"nj <> \u11ac;" // hangul jongseong nieun-cieuc
"nh <> \u11ad;" // hangul jongseong nieun-hieuh
"ng <> \u11bc;" // hangul jongseong ieung
"n <> \u11ab;" // hangul jongseong nieun
"m <> \u11b7;" // hangul jongseong mieum
"lt <> \u11b4;" // hangul jongseong rieul-thieuth
"ls <> \u11b3;" // hangul jongseong rieul-sios
"lp <> \u11b5;" // hangul jongseong rieul-phieuph
"lm <> \u11b1;" // hangul jongseong rieul-mieum
"lh <> \u11b6;" // hangul jongseong rieul-hieuh
"lg <> \u11b0;" // hangul jongseong rieul-kiyeok
"lb <> \u11b2;" // hangul jongseong rieul-pieup
"l <> \u11af;" // hangul jongseong rieul
"k <> \u11bf;" // hangul jongseong khieukh
"j <> \u11bd;" // hangul jongseong cieuc
"h <> \u11c2;" // hangul jongseong hieuh
"gs <> \u11aa;" // hangul jongseong kiyeok-sios
"gg <> \u11a9;" // hangul jongseong ssangkiyeok
"g <> \u11a8;" // hangul jongseong kiyeok
"d <> \u11ae;" // hangul jongseong tikeut
"c <> \u11be;" // hangul jongseong chieuch
"bs <> \u11b9;" // hangul jongseong pieup-sios
"b <> \u11b8;" // hangul jongseong pieup
// extra English letters
// {moved to bottom - aliu}
"z > |s;"
//{ + "Z > |s;" } masked
"x > |ks;"
"X > |ks;"
"v > |b;"
"V > |b;"
"r > |l;"
"R > |l;"
"q > |k;"
"Q > |k;"
"f > |p;"
"F > |p;"
//{ + "c > |k;" } masked
"C > |k;"
"y > \u1172;" // hangul jungseong yu
"w > \u1171;" // hangul jungseong wi
// ====================================
// Normal final rule: remove '
// ====================================
"''>;"
}
}

1329
icu4c/data/lkana.txt Normal file
View File

File diff suppressed because it is too large Load Diff

2
icu4c/data/lrussian.txt Normal file
View File

@ -0,0 +1,2 @@
// This file is obsolete
// See lcyril

83
icu4c/data/quotes.txt Normal file
View File

@ -0,0 +1,83 @@
//--------------------------------------------------------------------
// Copyright (C) 1999, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 11/17/99 aliu Creation.
//--------------------------------------------------------------------
// StraightQuotes-CurlyQuotes
quotes {
Rule {
// Rewritten using character codes [LIU]
"white=[[:Zs:][:Zl:][:Zp:]];"
"black=[^{white}];"
"open=[:Ps:];"
"dquote=\";"
"lAng=\u3008;"
"ldAng=\u300A;"
"lBrk='[';"
"lBrc='{';"
"lquote=\u2018;"
"rquote=\u2019;"
"ldquote=\u201C;"
"rdquote=\u201D;"
"ldguill=\u00AB;"
"rdguill=\u00BB;"
"lguill=\u2039;"
"rguill=\u203A;"
"mdash=\u2014;"
//#######################################
// Conversions from input
//#######################################
// join single quotes
"{lquote}''>{ldquote};"
"{lquote}{lquote}>{ldquote};"
"{rquote}''>{rdquote};"
"{rquote}{rquote}>{rdquote};"
//smart single quotes
"{white})''>{lquote};"
"{open})''>{lquote};"
"{black})''>{rquote};"
"''>{lquote};"
//smart doubles
"{white}){dquote}>{ldquote};"
"{open}){dquote}>{ldquote};"
"{black}){dquote}>{rdquote};"
"{dquote}>{ldquote};"
// join single guillemets
"{rguill}{rguill}>{rdguill};"
"'>>'>{rdguill};"
"{lguill}{lguill}>{ldguill};"
"'<<'>{ldguill};"
// prevent double spaces
"\\ )\\ >;"
// join hyphens into dash
"-->{mdash};"
//#######################################
// Conversions back to input
//#######################################
//smart quotes
"''<{lquote};"
"''<{rquote};"
"{dquote}<{ldquote};"
"{dquote}<{rdquote};"
//hyphens
"--<{mdash};"
}
}

46
icu4c/data/translit_index.txt Normal file
View File

@ -0,0 +1,46 @@
//--------------------------------------------------------------------
// Copyright (c) 2000, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 01/13/2000 aliu Creation.
//--------------------------------------------------------------------
translit_index {
// Map transliterator names to resource file names. This
// mapping is required because transliterator names typically
// exceed the limits of 8.3 file names.
RuleBasedTransliteratorIDs {
// This is an n x 3 array of strings that serves as an index
// to the system rule-based transliterator resource bundle
// data files. If RBT files are installed or removed from the
// system this table must be updated. For each of the n rows,
// the first item is the ID of the forward transliterator for
// the rule. The second item is the ID of the reverse
// transliterator for the rule. Some rule files only contain
// forward direction rules; for those, the second item is a
// zero-length string. The third item is the name of the
// resource bundle file, a string of 8 or fewer lowercase
// letters or digits. This file will be sought in the data
// directory within the subdirectory "translit". IDs must
// have the form "From-To" or "SingleName" to work properly
// with the Transliterator code.
// Basic language rules
{ "Fullwidth-Halfwidth", "Halfwidth-Fullwidth", "fullhalf" }
{ "Latin-Arabic", "Arabic-Latin", "larabic" }
{ "Latin-Cyrillic", "Cyrillic-Latin", "lcyril" }
{ "Latin-Devanagari", "Devanagari-Latin", "ldevan" }
{ "Latin-Greek", "Greek-Latin", "lgreek" }
{ "Latin-Hebrew", "Hebrew-Latin", "lhebrew" }
{ "Latin-Jamo", "Jamo-Latin", "ljamo" }
{ "Latin-Kana", "Kana-Latin", "lkana" }
// Other miscellaneous rules
{ "StraightQuotes-CurlyQuotes", "CurlyQuotes-StraightQuotes",
"quotes" }
{ "KeyboardEscape-Latin1", "", "kbdescl1" }
{ "UnicodeName-UnicodeChar", "", "ucname" }
}
}

1525
icu4c/data/ucname.txt Normal file
View File

File diff suppressed because it is too large Load Diff

1
icu4c/source/data/locales/expcon.txt Normal file
View File

@ -0,0 +1 @@
// This file is obsolete

46
icu4c/source/data/translit/translit_index.txt Normal file
View File

@ -0,0 +1,46 @@
//--------------------------------------------------------------------
// Copyright (c) 2000, International Business Machines
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// Date Name Description
// 01/13/2000 aliu Creation.
//--------------------------------------------------------------------
translit_index {
// Map transliterator names to resource file names. This
// mapping is required because transliterator names typically
// exceed the limits of 8.3 file names.
RuleBasedTransliteratorIDs {
// This is an n x 3 array of strings that serves as an index
// to the system rule-based transliterator resource bundle
// data files. If RBT files are installed or removed from the
// system this table must be updated. For each of the n rows,
// the first item is the ID of the forward transliterator for
// the rule. The second item is the ID of the reverse
// transliterator for the rule. Some rule files only contain
// forward direction rules; for those, the second item is a
// zero-length string. The third item is the name of the
// resource bundle file, a string of 8 or fewer lowercase
// letters or digits. This file will be sought in the data
// directory within the subdirectory "translit". IDs must
// have the form "From-To" or "SingleName" to work properly
// with the Transliterator code.
// Basic language rules
{ "Fullwidth-Halfwidth", "Halfwidth-Fullwidth", "fullhalf" }
{ "Latin-Arabic", "Arabic-Latin", "larabic" }
{ "Latin-Cyrillic", "Cyrillic-Latin", "lcyril" }
{ "Latin-Devanagari", "Devanagari-Latin", "ldevan" }
{ "Latin-Greek", "Greek-Latin", "lgreek" }
{ "Latin-Hebrew", "Hebrew-Latin", "lhebrew" }
{ "Latin-Jamo", "Jamo-Latin", "ljamo" }
{ "Latin-Kana", "Kana-Latin", "lkana" }
// Other miscellaneous rules
{ "StraightQuotes-CurlyQuotes", "CurlyQuotes-StraightQuotes",
"quotes" }
{ "KeyboardEscape-Latin1", "", "kbdescl1" }
{ "UnicodeName-UnicodeChar", "", "ucname" }
}
}