From 032a18718e842a29c9c43718b909483acf24f44d Mon Sep 17 00:00:00 2001 From: Vladimir Weinstein Date: Thu, 18 May 2000 20:26:32 +0000 Subject: [PATCH] ICU-184 .res files go to mem map files - build issue X-SVN-Rev: 1407 --- icu4c/data/translit/expcon.txt | 1 - icu4c/data/translit/fullhalf.txt | 270 ------ icu4c/data/translit/index.txt | 46 - icu4c/data/translit/kbdescl1.txt | 128 --- icu4c/data/translit/larabic.txt | 240 ----- icu4c/data/translit/lcyril.txt | 307 ------ icu4c/data/translit/ldevan.txt | 411 -------- icu4c/data/translit/lgreek.txt | 376 -------- icu4c/data/translit/lhalfwid.txt | 2 - icu4c/data/translit/lhebrew.txt | 278 ------ icu4c/data/translit/ljamo.txt | 322 ------- icu4c/data/translit/lkana.txt | 1329 -------------------------- icu4c/data/translit/lrussian.txt | 2 - icu4c/data/translit/quotes.txt | 83 -- icu4c/data/translit/ucname.txt | 1525 ------------------------------ 15 files changed, 5320 deletions(-) delete mode 100644 icu4c/data/translit/expcon.txt delete mode 100644 icu4c/data/translit/fullhalf.txt delete mode 100644 icu4c/data/translit/index.txt delete mode 100644 icu4c/data/translit/kbdescl1.txt delete mode 100644 icu4c/data/translit/larabic.txt delete mode 100644 icu4c/data/translit/lcyril.txt delete mode 100644 icu4c/data/translit/ldevan.txt delete mode 100644 icu4c/data/translit/lgreek.txt delete mode 100644 icu4c/data/translit/lhalfwid.txt delete mode 100644 icu4c/data/translit/lhebrew.txt delete mode 100644 icu4c/data/translit/ljamo.txt delete mode 100644 icu4c/data/translit/lkana.txt delete mode 100644 icu4c/data/translit/lrussian.txt delete mode 100644 icu4c/data/translit/quotes.txt delete mode 100644 icu4c/data/translit/ucname.txt diff --git a/icu4c/data/translit/expcon.txt b/icu4c/data/translit/expcon.txt deleted file mode 100644 index e65f32f8b07..00000000000 --- a/icu4c/data/translit/expcon.txt +++ /dev/null @@ -1 +0,0 @@ -// This file is obsolete diff --git a/icu4c/data/translit/fullhalf.txt b/icu4c/data/translit/fullhalf.txt deleted file mode 100644 index f9f8c239ffc..00000000000 --- a/icu4c/data/translit/fullhalf.txt +++ /dev/null @@ -1,270 +0,0 @@ -//-------------------------------------------------------------------- -// 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 - } -} diff --git a/icu4c/data/translit/index.txt b/icu4c/data/translit/index.txt deleted file mode 100644 index 993d1bf7793..00000000000 --- a/icu4c/data/translit/index.txt +++ /dev/null @@ -1,46 +0,0 @@ -//-------------------------------------------------------------------- -// Copyright (c) 2000, International Business Machines -// Corporation and others. All Rights Reserved. -//-------------------------------------------------------------------- -// Date Name Description -// 01/13/2000 aliu Creation. -//-------------------------------------------------------------------- - -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" } - } -} diff --git a/icu4c/data/translit/kbdescl1.txt b/icu4c/data/translit/kbdescl1.txt deleted file mode 100644 index 43259cfffc5..00000000000 --- a/icu4c/data/translit/kbdescl1.txt +++ /dev/null @@ -1,128 +0,0 @@ -//-------------------------------------------------------------------- -// 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;" - } -} diff --git a/icu4c/data/translit/larabic.txt b/icu4c/data/translit/larabic.txt deleted file mode 100644 index b1c468fe9c0..00000000000 --- a/icu4c/data/translit/larabic.txt +++ /dev/null @@ -1,240 +0,0 @@ -//-------------------------------------------------------------------- -// 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{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 - } -} diff --git a/icu4c/data/translit/ldevan.txt b/icu4c/data/translit/ldevan.txt deleted file mode 100644 index f805ce2f825..00000000000 --- a/icu4c/data/translit/ldevan.txt +++ /dev/null @@ -1,411 +0,0 @@ -//-------------------------------------------------------------------- -// 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 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;" - - // 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 {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 ' - // ==================================== - - //+ "''>;" - } -} diff --git a/icu4c/data/translit/lhalfwid.txt b/icu4c/data/translit/lhalfwid.txt deleted file mode 100644 index bb2d2112dcb..00000000000 --- a/icu4c/data/translit/lhalfwid.txt +++ /dev/null @@ -1,2 +0,0 @@ -// This file is obsolete -// See fullhalf diff --git a/icu4c/data/translit/lhebrew.txt b/icu4c/data/translit/lhebrew.txt deleted file mode 100644 index 68805dee732..00000000000 --- a/icu4c/data/translit/lhebrew.txt +++ /dev/null @@ -1,278 +0,0 @@ -//-------------------------------------------------------------------- -// 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}>@ - - "<'';" - } -} diff --git a/icu4c/data/translit/ljamo.txt b/icu4c/data/translit/ljamo.txt deleted file mode 100644 index 8b14c75fdd2..00000000000 --- a/icu4c/data/translit/ljamo.txt +++ /dev/null @@ -1,322 +0,0 @@ -//-------------------------------------------------------------------- -// 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), 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 ' - // ==================================== - - "''>;" - } -} diff --git a/icu4c/data/translit/lkana.txt b/icu4c/data/translit/lkana.txt deleted file mode 100644 index 8fb2b6ba2d1..00000000000 --- a/icu4c/data/translit/lkana.txt +++ /dev/null @@ -1,1329 +0,0 @@ -//-------------------------------------------------------------------- -// Copyright (C) 1999, International Business Machines -// Corporation and others. All Rights Reserved. -//-------------------------------------------------------------------- -// Date Name Description -// 11/17/99 aliu Creation. -//-------------------------------------------------------------------- - -// Latin-Kana - -// Rewritten April 1999 to implement Hepburn (kebon shiki) -// transliteration. Reference: CJKV Information Processing, Lunde, -// 1999, pp. 30-35. -// @author Alan Liu - -lkana { - Rule { - //# $Revision: 1.2 $ - // Transliteration rules for Japanese Hiragana and Katakana to - // romaji - // lower case roman generates hiragana. - // upper case roman generates katakana. - // Uses modified Hepburn. Small changes to make unambiguous. - // Kunrei-shiki: Hepburn/MHepburn -//* /* -//* si: shi -//* si ~ya: sha -//* si ~yu: shu -//* si ~yo: sho -//* zi: ji -//* zi ~ya: ja -//* zi ~yu: ju -//* zi ~yo: jo -//* ti: chi -//* ti ~ya: cha -//* ti ~yu: chu -//* ti ~yu: cho -//* tu: tsu -//* di: ji/dji -//* du: zu/dzu -//* hu: fu -//* // for foreign words -//* se ~i si -//* si ~e she - -//* ze ~i zi -//* zi ~e je - -//* te ~i ti -//* ti ~e che -//* te ~u tu - -//* de ~i di -//* de ~u du -//* de ~i di - -//* he ~u: hu -//* hu ~a fa -//* hu ~i fi -//* hu ~e he -//* hu ~o ho -//* // Most small forms are generated, but if necessary -//* // explicit small forms are given with ~a, ~ya, etc. -//* */ - //####################################### - // Definitions of variables to be substituted - //####################################### - - "vowel=[aeiou];" - "quote='';" - - // now the kana - "long=\u30FC;" - - "~a=\u3041;" - "^a=\u3042;" - "~i=\u3043;" - "^i=\u3044;" - "~u=\u3045;" - "^u=\u3046;" - "~e=\u3047;" - "^e=\u3048;" - "~o=\u3049;" - "^o=\u304A;" - - "ka=\u304B;" - "ga=\u304C;" - "ki=\u304D;" - "gi=\u304E;" - "ku=\u304F;" - "gu=\u3050;" - "ke=\u3051;" - "ge=\u3052;" - "ko=\u3053;" - "go=\u3054;" - - //these are small katakana - "~ka=\u30F5;" - "~ke=\u30F6;" - - "sa=\u3055;" - "za=\u3056;" - "si=\u3057;" - "zi=\u3058;" - "su=\u3059;" - "zu=\u305A;" - "se=\u305B;" - "ze=\u305C;" - "so=\u305D;" - "zo=\u305E;" - - "ta=\u305F;" - "da=\u3060;" - "ti=\u3061;" - "di=\u3062;" - "~tu=\u3063;" - "tu=\u3064;" - "du=\u3065;" - "te=\u3066;" - "de=\u3067;" - "to=\u3068;" - "do=\u3069;" - - "na=\u306A;" - "ni=\u306B;" - "nu=\u306C;" - "ne=\u306D;" - "no=\u306E;" - - "ha=\u306F;" - "ba=\u3070;" - "pa=\u3071;" - "hi=\u3072;" - "bi=\u3073;" - "pi=\u3074;" - "hu=\u3075;" - "bu=\u3076;" - "pu=\u3077;" - "he=\u3078;" - "be=\u3079;" - "pe=\u307A;" - "ho=\u307B;" - "bo=\u307C;" - "po=\u307D;" - - "ma=\u307E;" - "mi=\u307F;" - "mu=\u3080;" - "me=\u3081;" - "mo=\u3082;" - - "~ya=\u3083;" - "ya=\u3084;" - "~yu=\u3085;" - "yu=\u3086;" - "~yo=\u3087;" - "yo=\u3088;" - - "ra=\u3089;" - "ri=\u308A;" - "ru=\u308B;" - "re=\u308C;" - "ro=\u308D;" - - "~wa=\u308E;" - "wa=\u308F;" - "wi=\u3090;" - "we=\u3091;" - "wo=\u3092;" - - "^n=\u3093;" - "vu=\u3094;" - - // alternates, just to make the rules easier - "~yi=\u3043;" - "yi=\u3044;" - "~ye=\u3047;" - "ye=\u3048;" - "wu={^u};" - // end alternates - - // Katakana - - "~A=\u30A1;" - "^A=\u30A2;" - "~I=\u30A3;" - "^I=\u30A4;" - "~U=\u30A5;" - "^U=\u30A6;" - "~E=\u30A7;" - "^E=\u30A8;" - "~O=\u30A9;" - "^O=\u30AA;" - - "KA=\u30AB;" - "GA=\u30AC;" - "KI=\u30AD;" - "GI=\u30AE;" - "KU=\u30AF;" - "GU=\u30B0;" - "KE=\u30B1;" - "GE=\u30B2;" - "KO=\u30B3;" - "GO=\u30B4;" - - //these generate small katakana - "~KA=\u30F5;" - "~KE=\u30F6;" - - "SA=\u30B5;" - "ZA=\u30B6;" - "SI=\u30B7;" - "ZI=\u30B8;" - "SU=\u30B9;" - "ZU=\u30BA;" - "SE=\u30BB;" - "ZE=\u30BC;" - "SO=\u30BD;" - "ZO=\u30BE;" - - "TA=\u30BF;" - "DA=\u30C0;" - "TI=\u30C1;" - "DI=\u30C2;" - "~TU=\u30C3;" - "TU=\u30C4;" - "DU=\u30C5;" - "TE=\u30C6;" - "DE=\u30C7;" - "TO=\u30C8;" - "DO=\u30C9;" - - "NA=\u30CA;" - "NI=\u30CB;" - "NU=\u30CC;" - "NE=\u30CD;" - "NO=\u30CE;" - - "HA=\u30CF;" - "BA=\u30D0;" - "PA=\u30D1;" - "HI=\u30D2;" - "BI=\u30D3;" - "PI=\u30D4;" - "HU=\u30D5;" - "BU=\u30D6;" - "PU=\u30D7;" - "HE=\u30D8;" - "BE=\u30D9;" - "PE=\u30DA;" - "HO=\u30DB;" - "BO=\u30DC;" - "PO=\u30DD;" - - "MA=\u30DE;" - "MI=\u30DF;" - "MU=\u30E0;" - "ME=\u30E1;" - "MO=\u30E2;" - - "~YA=\u30E3;" - "YA=\u30E4;" - "~YU=\u30E5;" - "YU=\u30E6;" - "~YO=\u30E7;" - "YO=\u30E8;" - "~WA=\u30EE;" - - // alternates, just to make the rules easier - "~YI=\u30A3;" - "YI=\u30A4;" - "~YE=\u30A7;" - "YE=\u30A8;" - "WU={^U};" - // end alternates - - "RA=\u30E9;" - "RI=\u30EA;" - "RU=\u30EB;" - "RE=\u30EC;" - "RO=\u30ED;" - - "VA=\u30F7;" - "VI=\u30F8;" - "VU=\u30F4;" - "VE=\u30F9;" - "VO=\u30FA;" - - "WA=\u30EF;" - "WI=\u30F0;" - "WE=\u30F1;" - "WO=\u30F2;" - - "^N=\u30F3;" - "LONG=\u30FC;" - "QUOTE='';" - - // Variables used for double-letters with tsu - - "K-START=[{KA}{KI}{KU}{KE}{KO}{ka}{ki}{ku}{ke}{ko}];" - "G-START=[{GA}{GI}{GU}{GE}{GO}{ga}{gi}{gu}{ge}{go}];" - - "S-START=[{SA}{SI}{SU}{SE}{SO}{sa}{si}{su}{se}{so}];" - "Z-START=[{ZA}{ZU}{ZE}{ZO}{za}{zu}{ze}{zo}];" - "J-START=[{ZI}{zi}];" - - "T-START=[{TA}{TI}{TU}{TE}{TO}{ta}{ti}{tu}{te}{to}];" - "D-START=[{DA}{DI}{DU}{DE}{DO}{da}{di}{du}{de}{do}];" - - "N-START=[{NA}{NI}{NU}{NE}{NO}{na}{ni}{nu}{ne}{no}];" - - "H-START=[{HA}{HI}{HE}{HO}{ha}{hi}{he}{ho}];" - "F-START=[{HU}{hu}];" - "B-START=[{BA}{BI}{BU}{BE}{BO}{ba}{bi}{bu}{be}{bo}];" - "P-START=[{PA}{PI}{PU}{PE}{PO}{pa}{pi}{pu}{pe}{po}];" - - "M-START=[{MA}{MI}{MU}{ME}{MO}{ma}{mi}{mu}{me}{mo}];" - - "Y-START=[{YA}{YU}{YO}{ya}{yu}{yo}];" - - "R-START=[{RA}{RI}{RU}{RE}{RO}{ra}{ri}{ru}{re}{ro}];" - - "W-START=[{WA}{WI}{WE}{WO}{wa}{wi}{we}{wo}];" - - "V-START=[{VA}{VI}{VU}{VE}{VO}{vu}];" - - // lowercase copies for convenience in making hiragana - - "k-start={K-START};" - "g-start={G-START};" - "s-start={S-START};" - "z-start={Z-START};" - "j-start={J-START};" - "t-start={T-START};" - "d-start={D-START};" - "n-start={N-START};" - "h-start={H-START};" - "f-start={F-START};" - "b-start={B-START};" - "p-start={P-START};" - "m-start={M-START};" - "y-start={Y-START};" - "r-start={R-START};" - "w-start={W-START};" - "v-start={V-START};" - - // remember that the order is very significant: - // always put longer before shorter elements - - //####################################### - // KATAKANA - //####################################### - - "VA>{VA};" - "VI>{VI};" - "VE>{VE};" - "VO>{VO};" - - "VA<{VA};" - "VI<{VI};" - "VE<{VE};" - "VO<{VO};" - - //####################################### - // KATAKANA SHARED - // These are also used to produce hiragana, by lowercasing - //####################################### - - "A>{^A};" - - "BA>{BA};" - "BI>{BI};" - "BU>{BU};" - "BE>{BE};" - "BO>{BO};" - "BY>{BI}|~Y;" - - "CHI>{TI};" - "CH>{TI}|~Y;" - - "C(I>|S;" - "C(E>|S;" - - "DA>{DA};" - "DI>{DE}{~I};" - "DU>{DE}{~U};" - "DE>{DE};" - "DO>{DO};" - "DZU>{DU};" - "DJI>{DI};" - "DJ>{DI}|~Y;" - - "E>{^E};" - - "FU>{HU};" - - "GA>{GA};" - "GI>{GI};" - "GU>{GU};" - "GE>{GE};" - "GO>{GO};" - "GY>{GI}|~Y;" - - "HA>{HA};" - "HI>{HI};" - "HU>{HE}{~U};" - "HE>{HE};" - "HO>{HO};" - - "I>{^I};" - - "JI>{ZI};" - - "KA>{KA};" - "KI>{KI};" - "KU>{KU};" - "KE>{KE};" - "KO>{KO};" - "KY>{KI}|~Y;" - - "MA>{MA};" - "MI>{MI};" - "MU>{MU};" - "ME>{ME};" - "MO>{MO};" - "MY>{MI}|~Y;" - - "M(P>{^N};" - "M(B>{^N};" - "M(F>{^N};" - "M(V>{^N};" - - "NA>{NA};" - "NI>{NI};" - "NU>{NU};" - "NE>{NE};" - "NO>{NO};" - "NY>{NI}|~Y;" - - "O>{^O};" - - "PA>{PA};" - "PI>{PI};" - "PU>{PU};" - "PE>{PE};" - "PO>{PO};" - "PY>{PI}|~Y;" - - "RA>{RA};" - "RI>{RI};" - "RU>{RU};" - "RE>{RE};" - "RO>{RO};" - "RY>{RI}|~Y;" - - "SA>{SA};" - "SI>{SE}{~I};" - "SU>{SU};" - "SE>{SE};" - "SO>{SO};" - - "SHI>{SI};" - "SH>{SI}|~Y;" - - "TA>{TA};" - "TI>{TE}{~I};" - "TU>{TE}{~U};" - "TE>{TE};" - "TO>{TO};" - - "TSU>{TU};" - //+ "TS>{TU}|~;" - - "U>{^U};" - - "VU>{VU};" - - "WA>{WA};" - "WI>{WI};" - "WU>{WU};" - "WE>{WE};" - "WO>{WO};" - - "YA>{YA};" - "YI>{YI};" - "YU>{YU};" - "YE>{YE};" - "YO>{YO};" - - "ZA>{ZA};" - "ZI>{ZE}{~I};" - "ZU>{ZU};" - "ZE>{ZE};" - "ZO>{ZO};" - - // SMALL FORMS - - "~A>{~A};" - "~I>{~I};" - "~U>{~U};" - "~E>{~E};" - "~O>{~O};" - "~KA>{~KA};" - "~KE>{~KE};" - "~TSU>{~TU};" - "~WA>{~WA};" - "~YA>{~YA};" - "~YI>{~YI};" - "~YU>{~YU};" - "~YE>{~YE};" - "~YO>{~YO};" - - // DOUBLE CONSONANTS - - "B(B>{~TU};" - "C(K>{~TU};" - "C(C>{~TU};" - "C(Q>{~TU};" - "D(D>{~TU};" - "F(F>{~TU};" - "G(G>{~TU};" - "H(H>{~TU};" - "J(J>{~TU};" - "K(K>{~TU};" - "L(L>{~TU};" - "M(M>{~TU};" - "N(N>{~TU};" - "P(P>{~TU};" - "Q(Q>{~TU};" - "R(R>{~TU};" - "S(SH>{~TU};" - "S(S>{~TU};" - "T(CH>{~TU};" - "T(T>{~TU};" - "V(V>{~TU};" - "W(W>{~TU};" - "X(X>{~TU};" - "Y(Y>{~TU};" - "Z(Z>{~TU};" - - // ######################################## - // CATCH MISSING VOWELS! - // THESE ARE TO INSURE COMPLETENESS, THAT - // ALL ROMAJI MAPS TO KANA - // ######################################## - -//* /* -//* "SH>{SI};" -//* "TS>{TU};" -//* "CH>{TI};" -//* "DJ>{DI};" -//* "DZ>{DU};" -//* */ - - // THE FOLLOWING ARE NOT REALLY NECESSARY, BUT PRODUCE - // SLIGHTLY MORE NATURAL RESULTS. - - //masked: "BY>{BI};" - "CY>{SE}{~I};" - "DY>{DE}{~I};" - //masked: "GY>{GI};" - "HY>{HI};" - //masked: "KY>{KI};" - //masked: "MY>{MI};" - //masked: "PY>{PI};" - //masked: "RY>{RI};" - "SY>{SE}{~I};" - "TY>{TE}{~I};" - "ZY>{ZE}{~I};" - - // SIMPLE SUBSTITUTIONS USING BACKUP - - "C>|K;" - "F>{HU}|~;" - "J>{ZI}|~Y;" - "L>|R;" - "Q>|K;" // BACKUP AND REDO - "V>{VU}|~;" - "W>{^U}|~;" - "X>|KS;" - - // WE HAD TO LIST THE LONGER ONES FIRST, - // SO HERE ARE THE ISOLATED CONSONANTS - - "B>{BU};" - "D>{DE};" - //masked: "F>{HU};" - "G>{GU};" - "H>{HE};" - //masked: "J>{ZI};" - "K>{KU};" - "M>{^N};" - "N>{^N};" - "P>{PU};" - "R>{RU};" - "S>{SU};" - "T>{TE};" - //masked: "V>{BU};" - //masked: "W>{^U};" - //masked: "X>{KU}{SU};" - "Y>{^I};" - "Z>{ZU};" - - // NOW KANA TO ROMAN - - "GYA<{GI}{~YA};" - "GYI<{GI}{~I};" - "GYU<{GI}{~YU};" - "GYE<{GI}{~E};" - "GYO<{GI}{~YO};" - - "GA<{GA};" - "GI<{GI};" - "GU<{GU};" - "GE<{GE};" - "GO<{GO};" - - "KYA<{KI}{~YA};" - "KYI<{KI}{~I};" - "KYU<{KI}{~YU};" - "KYE<{KI}{~E};" - "KYO<{KI}{~YO};" - - "KA<{KA};" - "KI<{KI};" - "KU<{KU};" - "KE<{KE};" - "KO<{KO};" - - "JA<{ZI}{~YA};" - "JI<{ZI}{~I};" - "JU<{ZI}{~YU};" - "JE<{ZI}{~E};" - "JO<{ZI}{~YO};" - "JI<{ZI};" - - "ZA<{ZA};" - "ZI<{ZE}{~I};" - "ZU<{ZU};" - "ZE<{ZE};" - "ZO<{ZO};" - - "SHA<{SI}{~YA};" - "SHI<{SI}{~I};" - "SHU<{SI}{~YU};" - "SHE<{SI}{~E};" - "SHO<{SI}{~YO};" - "SHI<{SI};" - - "SA<{SA};" - "SI<{SE}{~I};" - "SU<{SU};" - "SE<{SE};" - "SO<{SO};" - - "DJA<{DI}{~YA};" - "DJI<{DI}{~I};" - "DJU<{DI}{~YU};" - "DJE<{DI}{~E};" - "DJO<{DI}{~YO};" - "DJI<{DI};" - - "DZU<{DU};" - - "DA<{DA};" - "DI<{DE}{~I};" - "DU<{DE}{~U};" - "DE<{DE};" - "DO<{DO};" - - "CHA<{TI}{~YA};" - "CHI<{TI}{~I};" - "CHU<{TI}{~YU};" - "CHE<{TI}{~E};" - "CHO<{TI}{~YO};" - "CHI<{TI};" - - "TSU<{TU};" - - "TA<{TA};" - "TI<{TE}{~I};" - "TU<{TE}{~U};" - "TE<{TE};" - "TO<{TO};" - - "NYA<{NI}{~YA};" - "NYI<{NI}{~I};" - "NYU<{NI}{~YU};" - "NYE<{NI}{~E};" - "NYO<{NI}{~YO};" - - "NA<{NA};" - "NI<{NI};" - "NU<{NU};" - "NE<{NE};" - "NO<{NO};" - - "BYA<{BI}{~YA};" - "BYI<{BI}{~I};" - "BYU<{BI}{~YU};" - "BYE<{BI}{~E};" - "BYO<{BI}{~YO};" - - "BA<{BA};" - "BI<{BI};" - "BU<{BU};" - "BE<{BE};" - "BO<{BO};" - - "PYA<{PI}{~YA};" - "PYI<{PI}{~I};" - "PYU<{PI}{~YU};" - "PYE<{PI}{~E};" - "PYO<{PI}{~YO};" - - "PA<{PA};" - "PI<{PI};" - "PU<{PU};" - "PE<{PE};" - "PO<{PO};" - - "FA<{HU}{~A};" - "FI<{HU}{~I};" - "FE<{HU}{~E};" - "FO<{HU}{~O};" - "FU<{HU};" - - "HA<{HA};" - "HI<{HI};" - "HU<{HE}{~U};" - "HE<{HE};" - "HO<{HO};" - - "MYA<{MI}{~YA};" - "MYI<{MI}{~I};" - "MYU<{MI}{~YU};" - "MYE<{MI}{~E};" - "MYO<{MI}{~YO};" - - "MA<{MA};" - "MI<{MI};" - "MU<{MU};" - "ME<{ME};" - "MO<{MO};" - - "YA<{YA};" - //+ "YE<{YI};" - "YU<{YU};" - //+ "YE<{YE};" - "YO<{YO};" - - "RYA<{RI}{~YA};" - "RYI<{RI}{~I};" - "RYU<{RI}{~YU};" - "RYE<{RI}{~E};" - "RYO<{RI}{~YO};" - - "RA<{RA};" - "RI<{RI};" - "RU<{RU};" - "RE<{RE};" - "RO<{RO};" - - "WA<{WA};" - "WI<{WI};" - "WE<{WE};" - "WO<{WO};" - //+ "WU<{WU};" - - "VA<{VU}{~A};" - "VI<{VU}{~I};" - "VE<{VU}{~E};" - "VO<{VU}{~O};" - "VU<{VU};" - - // DOUBLED LETTERS - - "N''<{^N}({^A};" - "N''<{^N}({^I};" - "N''<{^N}({^U};" - "N''<{^N}({^E};" - "N''<{^N}({^O};" - "N''<{^N}({NA};" - "N''<{^N}({NI};" - "N''<{^N}({NU};" - "N''<{^N}({NE};" - "N''<{^N}({NO};" - "N''<{^N}({YA};" - "N''<{^N}({YU};" - "N''<{^N}({YO};" - "N''<{^N}({^N};" - "N<{^N};" - - "N<{~TU}({N-START};" - "M<{~TU}({M-START};" - "W<{~TU}({W-START};" - "Y<{~TU}({Y-START};" - "G<{~TU}({G-START};" - "K<{~TU}({K-START};" - "Z<{~TU}({Z-START};" - "J<{~TU}({J-START};" - "S<{~TU}({S-START};" - "D<{~TU}({D-START};" - "T<{~TU}({T-START};" - "B<{~TU}({B-START};" - "P<{~TU}({P-START};" - "H<{~TU}({H-START};" - "F<{~TU}({F-START};" - "R<{~TU}({R-START};" - "V<{~TU}({V-START};" - - "A<{^A};" // MOVED THIS BLOCK DOWN {aliu} - "I<{^I};" - "U<{^U};" - "E<{^E};" - "O<{^O};" - - // SMALL FORMS - - "~A<{~A};" - "~I<{~I};" - "~U<{~U};" - "~E<{~E};" - "~O<{~O};" - "~KA<{~KA};" - "~KE<{~KE};" - "~YA<{~YA};" - "~YU<{~YU};" - "~YO<{~YO};" - "~TSU<{~TU};" - "~WA<{~WA};" - - // LENGTH MARK. LATER, COULD USE CIRCUMFLEX - - "A{^a};" - - "ba>{ba};" - "bi>{bi};" - "bu>{bu};" - "be>{be};" - "bo>{bo};" - "by>{bi}|~y;" - - "chi>{ti};" - "ch>{ti}|~y;" - - "c(i>|s;" - "c(e>|s;" - - "da>{da};" - "di>{de}{~i};" - "du>{de}{~u};" - "de>{de};" - "do>{do};" - "dzu>{du};" - "dji>{di};" - "dj>{di}|~y;" - - "e>{^e};" - - "fu>{hu};" - - "ga>{ga};" - "gi>{gi};" - "gu>{gu};" - "ge>{ge};" - "go>{go};" - "gy>{gi}|~y;" - - "ha>{ha};" - "hi>{hi};" - "hu>{he}{~u};" - "he>{he};" - "ho>{ho};" - - "i>{^i};" - - "ji>{zi};" - - "ka>{ka};" - "ki>{ki};" - "ku>{ku};" - "ke>{ke};" - "ko>{ko};" - "ky>{ki}|~y;" - - "ma>{ma};" - "mi>{mi};" - "mu>{mu};" - "me>{me};" - "mo>{mo};" - "my>{mi}|~y;" - - "m(p>{^n};" - "m(b>{^n};" - "m(f>{^n};" - "m(v>{^n};" - - "na>{na};" - "ni>{ni};" - "nu>{nu};" - "ne>{ne};" - "no>{no};" - "ny>{ni}|~y;" - - "o>{^o};" - - "pa>{pa};" - "pi>{pi};" - "pu>{pu};" - "pe>{pe};" - "po>{po};" - "py>{pi}|~y;" - - "ra>{ra};" - "ri>{ri};" - "ru>{ru};" - "re>{re};" - "ro>{ro};" - "ry>{ri}|~y;" - - "sa>{sa};" - "si>{se}{~i};" - "su>{su};" - "se>{se};" - "so>{so};" - - "shi>{si};" - "sh>{si}|~y;" - - "ta>{ta};" - "ti>{te}{~i};" - "tu>{te}{~u};" - "te>{te};" - "to>{to};" - - "tsu>{tu};" - //+ "ts>{tu}|~;" - - "u>{^u};" - - "vu>{vu};" - - "wa>{wa};" - "wi>{wi};" - "wu>{wu};" - "we>{we};" - "wo>{wo};" - - "ya>{ya};" - "yi>{yi};" - "yu>{yu};" - "ye>{ye};" - "yo>{yo};" - - "za>{za};" - "zi>{ze}{~i};" - "zu>{zu};" - "ze>{ze};" - "zo>{zo};" - - // small forms - - "~a>{~a};" - "~i>{~i};" - "~u>{~u};" - "~e>{~e};" - "~o>{~o};" - "~ka>{~ka};" - "~ke>{~ke};" - "~tsu>{~tu};" - "~wa>{~wa};" - "~ya>{~ya};" - "~yi>{~yi};" - "~yu>{~yu};" - "~ye>{~ye};" - "~yo>{~yo};" - - // Double Consonants - - "b(b>{~tu};" - "c(k>{~tu};" - "c(c>{~tu};" - "c(q>{~tu};" - "d(d>{~tu};" - "f(f>{~tu};" - "g(g>{~tu};" - "h(h>{~tu};" - "j(j>{~tu};" - "k(k>{~tu};" - "l(l>{~tu};" - "m(m>{~tu};" - "n(n>{~tu};" - "p(p>{~tu};" - "q(q>{~tu};" - "r(r>{~tu};" - "s(sh>{~tu};" - "s(s>{~tu};" - "t(ch>{~tu};" - "t(t>{~tu};" - "v(v>{~tu};" - "w(w>{~tu};" - "x(x>{~tu};" - "y(y>{~tu};" - "z(z>{~tu};" - - // ######################################## - // catch missing vowels! - // These are to insure completeness, that - // all romaji maps to kana - // ######################################## - -//* /* -//* "sh>{si};" -//* "ts>{tu};" -//* "ch>{ti};" -//* "dj>{di};" -//* "dz>{du};" -//* */ - - // the following are not really necessary, but produce - // slightly more natural results. - - //masked: "by>{bi};" - "cy>{se}{~i};" - "dy>{de}{~i};" - //masked: "gy>{gi};" - "hy>{hi};" - //masked: "ky>{ki};" - //masked: "my>{mi};" - //masked: "py>{pi};" - //masked: "ry>{ri};" - "sy>{se}{~i};" - "ty>{te}{~i};" - "zy>{ze}{~i};" - - // simple substitutions using backup - - "c>|k;" - "f>{hu}|~;" - "j>{zi}|~y;" - "l>|r;" - "q>|k;" // backup and redo - "v>{vu}|~;" - "w>{^u}|~;" - "x>|ks;" - - // We had to list the longer ones first, - // so here are the isolated consonants - - "b>{bu};" - "d>{de};" - //masked: "f>{hu};" - "g>{gu};" - "h>{he};" - //masked: "j>{zi};" - "k>{ku};" - "m>{^n};" - "n>{^n};" - "p>{pu};" - "r>{ru};" - "s>{su};" - "t>{te};" - //masked: "v>{bu};" - //masked: "w>{^u};" - //masked: "x>{ku}{su};" - "y>{^i};" - "z>{zu};" - - // NOW KANA TO ROMAN - - "gya<{gi}{~ya};" - "gyi<{gi}{~i};" - "gyu<{gi}{~yu};" - "gye<{gi}{~e};" - "gyo<{gi}{~yo};" - - "ga<{ga};" - "gi<{gi};" - "gu<{gu};" - "ge<{ge};" - "go<{go};" - - "kya<{ki}{~ya};" - "kyi<{ki}{~i};" - "kyu<{ki}{~yu};" - "kye<{ki}{~e};" - "kyo<{ki}{~yo};" - - "ka<{ka};" - "ki<{ki};" - "ku<{ku};" - "ke<{ke};" - "ko<{ko};" - - "ja<{zi}{~ya};" - "ji<{zi}{~i};" - "ju<{zi}{~yu};" - "je<{zi}{~e};" - "jo<{zi}{~yo};" - "ji<{zi};" - - "za<{za};" - "zi<{ze}{~i};" - "zu<{zu};" - "ze<{ze};" - "zo<{zo};" - - "sha<{si}{~ya};" - "shi<{si}{~i};" - "shu<{si}{~yu};" - "she<{si}{~e};" - "sho<{si}{~yo};" - "shi<{si};" - - "sa<{sa};" - "si<{se}{~i};" - "su<{su};" - "se<{se};" - "so<{so};" - - "dja<{di}{~ya};" - "dji<{di}{~i};" - "dju<{di}{~yu};" - "dje<{di}{~e};" - "djo<{di}{~yo};" - "dji<{di};" - - "dzu<{du};" - - "da<{da};" - "di<{de}{~i};" - "du<{de}{~u};" - "de<{de};" - "do<{do};" - - "cha<{ti}{~ya};" - "chi<{ti}{~i};" - "chu<{ti}{~yu};" - "che<{ti}{~e};" - "cho<{ti}{~yo};" - "chi<{ti};" - - "tsu<{tu};" - - "ta<{ta};" - "ti<{te}{~i};" - "tu<{te}{~u};" - "te<{te};" - "to<{to};" - - "nya<{ni}{~ya};" - "nyi<{ni}{~i};" - "nyu<{ni}{~yu};" - "nye<{ni}{~e};" - "nyo<{ni}{~yo};" - - "na<{na};" - "ni<{ni};" - "nu<{nu};" - "ne<{ne};" - "no<{no};" - - "bya<{bi}{~ya};" - "byi<{bi}{~i};" - "byu<{bi}{~yu};" - "bye<{bi}{~e};" - "byo<{bi}{~yo};" - - "ba<{ba};" - "bi<{bi};" - "bu<{bu};" - "be<{be};" - "bo<{bo};" - - "pya<{pi}{~ya};" - "pyi<{pi}{~i};" - "pyu<{pi}{~yu};" - "pye<{pi}{~e};" - "pyo<{pi}{~yo};" - - "pa<{pa};" - "pi<{pi};" - "pu<{pu};" - "pe<{pe};" - "po<{po};" - - "fa<{hu}{~a};" - "fi<{hu}{~i};" - "fe<{hu}{~e};" - "fo<{hu}{~o};" - "fu<{hu};" - - "ha<{ha};" - "hi<{hi};" - "hu<{he}{~u};" - "he<{he};" - "ho<{ho};" - - "mya<{mi}{~ya};" - "myi<{mi}{~i};" - "myu<{mi}{~yu};" - "mye<{mi}{~e};" - "myo<{mi}{~yo};" - - "ma<{ma};" - "mi<{mi};" - "mu<{mu};" - "me<{me};" - "mo<{mo};" - - "ya<{ya};" - //+ "ye<{yi};" - "yu<{yu};" - //+ "ye<{ye};" - "yo<{yo};" - - "rya<{ri}{~ya};" - "ryi<{ri}{~i};" - "ryu<{ri}{~yu};" - "rye<{ri}{~e};" - "ryo<{ri}{~yo};" - - "ra<{ra};" - "ri<{ri};" - "ru<{ru};" - "re<{re};" - "ro<{ro};" - - "wa<{wa};" - "wi<{wi};" - "we<{we};" - "wo<{wo};" - //+ "wu<{wu};" - - "va<{vu}{~a};" - "vi<{vu}{~i};" - "ve<{vu}{~e};" - "vo<{vu}{~o};" - "vu<{vu};" - - // Doubled letters - - "n''<{^n}({^a};" - "n''<{^n}({^i};" - "n''<{^n}({^u};" - "n''<{^n}({^e};" - "n''<{^n}({^o};" - "n''<{^n}({na};" - "n''<{^n}({ni};" - "n''<{^n}({nu};" - "n''<{^n}({ne};" - "n''<{^n}({no};" - "n''<{^n}({ya};" - "n''<{^n}({yu};" - "n''<{^n}({yo};" - "n''<{^n}({^n};" - "n<{^n};" - - "n<{~tu}({n-start};" - "m<{~tu}({m-start};" - "w<{~tu}({w-start};" - "y<{~tu}({y-start};" - "g<{~tu}({g-start};" - "k<{~tu}({k-start};" - "z<{~tu}({z-start};" - "j<{~tu}({j-start};" - "s<{~tu}({s-start};" - "d<{~tu}({d-start};" - "t<{~tu}({t-start};" - "b<{~tu}({b-start};" - "p<{~tu}({p-start};" - "h<{~tu}({h-start};" - "f<{~tu}({f-start};" - "r<{~tu}({r-start};" - "v<{~tu}({v-start};" - - "a<{^a};" // Moved this block down {aliu} - "i<{^i};" - "u<{^u};" - "e<{^e};" - "o<{^o};" - - // small forms - - "~a<{~a};" - "~i<{~i};" - "~u<{~u};" - "~e<{~e};" - "~o<{~o};" - //masked: "~ka<{~ka};" ({~ka} is an alias for {~KA}) - //masked: "~ke<{~ke};" ({~ke} is an alias for {~KE}) - "~ya<{~ya};" - "~yu<{~yu};" - "~yo<{~yo};" - "~tsu<{~tu};" - "~wa<{~wa};" - - // length mark. Later, could use circumflex - - "a;" // remove if not used - "{quote}>;" // remove if not used - //+ "<{quote};" - "->{long};" - } -} - - - diff --git a/icu4c/data/translit/lrussian.txt b/icu4c/data/translit/lrussian.txt deleted file mode 100644 index 23cdf4892fe..00000000000 --- a/icu4c/data/translit/lrussian.txt +++ /dev/null @@ -1,2 +0,0 @@ -// This file is obsolete -// See lcyril diff --git a/icu4c/data/translit/quotes.txt b/icu4c/data/translit/quotes.txt deleted file mode 100644 index 7714810bf83..00000000000 --- a/icu4c/data/translit/quotes.txt +++ /dev/null @@ -1,83 +0,0 @@ -//-------------------------------------------------------------------- -// 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};" - } -} diff --git a/icu4c/data/translit/ucname.txt b/icu4c/data/translit/ucname.txt deleted file mode 100644 index 005aed5ba15..00000000000 --- a/icu4c/data/translit/ucname.txt +++ /dev/null @@ -1,1525 +0,0 @@ -//-------------------------------------------------------------------- -// Copyright (C) 1999, International Business Machines -// Corporation and others. All Rights Reserved. -//-------------------------------------------------------------------- -// Date Name Description -// 11/17/99 aliu Creation. -//-------------------------------------------------------------------- - -// UnicodeName-UnicodeChar - -ucname { - Rule { - "account of%>\u2100;" - "addressed to the subject%>\u2101;" - "adi shakti%>\u262c;" - "airplane%>\u2708;" - "all equal to%>\u224c;" - "almost equal or equal to%>\u224a;" - "almost equal to%>\u2248;" - "angle%>\u2220;" - "angstrom unit%>\u212b;" - "ankh%>\u2625;" - "anticlockwise contour integral%>\u2233;" - "anticlockwise open circle arrow%>\u21ba;" - "anticlockwise top semicircle arrow%>\u21b6;" - "apl compose operator%>\u2300;" - "apl out%>\u2301;" - "apple logo%>\uf8ff;" - "approaches the limit%>\u2250;" - "approximately but not actually equal to%>\u2246;" - "approximately equal to or the image of%>\u2252;" - "approximately equal to%>\u2245;" - "aquarius%>\u2652;" - "arc%>\u2312;" - "aries%>\u2648;" - "ascending node%>\u260a;" - "assertion%>\u22a6;" - "asterisk operator%>\u2217;" - "asterism%>\u2042;" - "asymptotically equal to%>\u2243;" - "back-tilted shadowed white right arrow%>\u27ab;" - "balloon-spoked asterisk%>\u2749;" - "ballot box with check%>\u2611;" - "ballot box with x%>\u2612;" - "ballot box%>\u2610;" - "ballot x%>\u2718;" - "barred eighth notes%>\u266b;" - "barred sixteenth notes%>\u266c;" - "because%>\u2235;" - "benzene ring%>\u232c;" - "between%>\u226c;" - "biohazard%>\u2623;" - "black center white star%>\u272c;" - "black chess bishop%>\u265d;" - "black chess king%>\u265a;" - "black chess knight%>\u265e;" - "black chess pawn%>\u265f;" - "black chess queen%>\u265b;" - "black chess rook%>\u265c;" - "black circle%>\u25cf;" - "black club suit%>\u2663;" - "black diamond minus white x%>\u2756;" - "black diamond suit%>\u2666;" - "black diamond%>\u25c6;" - "black down pointing small triangle%>\u25be;" - "black down pointing triangle%>\u25bc;" - "black florette%>\u273f;" - "black four pointed star%>\u2726;" - "black heart suit%>\u2665;" - "black left pointing index%>\u261a;" - "black left pointing pointer%>\u25c4;" - "black left pointing small triangle%>\u25c2;" - "black left pointing triangle%>\u25c0;" - "black lower left triangle%>\u25e3;" - "black lower right triangle%>\u25e2;" - "black nib%>\u2712;" - "black parallelogram%>\u25b0;" - "black rectangle%>\u25ac;" - "black right arrow%>\u27a1;" - "black right arrowhead%>\u27a4;" - "black right pointing index%>\u261b;" - "black right pointing pointer%>\u25ba;" - "black right pointing small triangle%>\u25b8;" - "black right pointing triangle%>\u25b6;" - "black scissors%>\u2702;" - "black small square%>\u25aa;" - "black smiling face%>\u263b;" - "black spade suit%>\u2660;" - "black square%>\u25a0;" - "black star%>\u2605;" - "black sun with rays%>\u2600;" - "black telephone%>\u260e;" - "black up pointing small triangle%>\u25b4;" - "black up pointing triangle%>\u25b2;" - "black upper left triangle%>\u25e4;" - "black upper right triangle%>\u25e5;" - "black vertical rectangle%>\u25ae;" - "black-feathered lower right arrow%>\u27b4;" - "black-feathered right arrow%>\u27b5;" - "black-feathered upper right arrow%>\u27b6;" - "black-letter c%>\u212d;" - "black-letter h%>\u210c;" - "black-letter i%>\u2111;" - "black-letter r%>\u211c;" - "black-letter z%>\u2128;" - "blank%>\u2422;" - "bottom half integral%>\u2321;" - "bottom left corner%>\u231e;" - "bottom left crop%>\u230d;" - "bottom right corner%>\u231f;" - "bottom right crop%>\u230c;" - "bowtie%>\u22c8;" - "bra%>\u2329;" - "broken vertical bar%>\u00a6;" - "bullet operator%>\u2219;" - "bullet%>\u2022;" - "bullseye%>\u25ce;" - "c l symbol%>\u2104;" - "cada una%>\u2106;" - "caduceus%>\u2624;" - "cancer%>\u264b;" - "capricorn%>\u2651;" - "care of%>\u2105;" - "caret insertion point%>\u2041;" - "caret%>\u2038;" - "caution sign%>\u2621;" - "cent sign%>\u00a2;" - "character tie%>\u2040;" - "check mark%>\u2713;" - "chi rho%>\u2627;" - "circle with all but upper left quadrant black%>\u25d5;" - "circle with left half black%>\u25d0;" - "circle with lower half black%>\u25d2;" - "circle with right half black%>\u25d1;" - "circle with upper half black%>\u25d3;" - "circle with upper right quadrant black%>\u25d4;" - "circle with vertical fill%>\u25cd;" - "circled asterisk operator%>\u229b;" - "circled dash%>\u229d;" - "circled digit eight%>\u2467;" - "circled digit five%>\u2464;" - "circled digit four%>\u2463;" - "circled digit nine%>\u2468;" - "circled digit one%>\u2460;" - "circled digit seven%>\u2466;" - "circled digit six%>\u2465;" - "circled digit three%>\u2462;" - "circled digit two%>\u2461;" - "circled digit zero%>\u24ea;" - "circled division slash%>\u2298;" - "circled dot operator%>\u2299;" - "circled equals%>\u229c;" - "circled heavy white right arrow%>\u27b2;" - "circled latin capital letter a%>\u24b6;" - "circled latin capital letter b%>\u24b7;" - "circled latin capital letter c%>\u24b8;" - "circled latin capital letter d%>\u24b9;" - "circled latin capital letter e%>\u24ba;" - "circled latin capital letter f%>\u24bb;" - "circled latin capital letter g%>\u24bc;" - "circled latin capital letter h%>\u24bd;" - "circled latin capital letter i%>\u24be;" - "circled latin capital letter j%>\u24bf;" - "circled latin capital letter k%>\u24c0;" - "circled latin capital letter l%>\u24c1;" - "circled latin capital letter m%>\u24c2;" - "circled latin capital letter n%>\u24c3;" - "circled latin capital letter o%>\u24c4;" - "circled latin capital letter p%>\u24c5;" - "circled latin capital letter q%>\u24c6;" - "circled latin capital letter r%>\u24c7;" - "circled latin capital letter s%>\u24c8;" - "circled latin capital letter t%>\u24c9;" - "circled latin capital letter u%>\u24ca;" - "circled latin capital letter v%>\u24cb;" - "circled latin capital letter w%>\u24cc;" - "circled latin capital letter x%>\u24cd;" - "circled latin capital letter y%>\u24ce;" - "circled latin capital letter z%>\u24cf;" - "circled latin small letter a%>\u24d0;" - "circled latin small letter b%>\u24d1;" - "circled latin small letter c%>\u24d2;" - "circled latin small letter d%>\u24d3;" - "circled latin small letter e%>\u24d4;" - "circled latin small letter f%>\u24d5;" - "circled latin small letter g%>\u24d6;" - "circled latin small letter h%>\u24d7;" - "circled latin small letter i%>\u24d8;" - "circled latin small letter j%>\u24d9;" - "circled latin small letter k%>\u24da;" - "circled latin small letter l%>\u24db;" - "circled latin small letter m%>\u24dc;" - "circled latin small letter n%>\u24dd;" - "circled latin small letter o%>\u24de;" - "circled latin small letter p%>\u24df;" - "circled latin small letter q%>\u24e0;" - "circled latin small letter r%>\u24e1;" - "circled latin small letter s%>\u24e2;" - "circled latin small letter t%>\u24e3;" - "circled latin small letter u%>\u24e4;" - "circled latin small letter v%>\u24e5;" - "circled latin small letter w%>\u24e6;" - "circled latin small letter x%>\u24e7;" - "circled latin small letter y%>\u24e8;" - "circled latin small letter z%>\u24e9;" - "circled minus%>\u2296;" - "circled number eighteen%>\u2471;" - "circled number eleven%>\u246a;" - "circled number fifteen%>\u246e;" - "circled number fourteen%>\u246d;" - "circled number nineteen%>\u2472;" - "circled number seventeen%>\u2470;" - "circled number sixteen%>\u246f;" - "circled number ten%>\u2469;" - "circled number thirteen%>\u246c;" - "circled number twelve%>\u246b;" - "circled number twenty%>\u2473;" - "circled open center eight pointed star%>\u2742;" - "circled plus%>\u2295;" - "circled postal mark%>\u3036;" - "circled ring operator%>\u229a;" - "circled sans serif digit eight%>\u2787;" - "circled sans serif digit five%>\u2784;" - "circled sans serif digit four%>\u2783;" - "circled sans serif digit nine%>\u2788;" - "circled sans serif digit one%>\u2780;" - "circled sans serif digit seven%>\u2786;" - "circled sans serif digit six%>\u2785;" - "circled sans serif digit three%>\u2782;" - "circled sans serif digit two%>\u2781;" - "circled sans serif number ten%>\u2789;" - "circled times%>\u2297;" - "circled white star%>\u272a;" - "clear key%>\u2327;" - "clockwise contour integral%>\u2232;" - "clockwise integral%>\u2231;" - "clockwise open circle arrow%>\u21bb;" - "clockwise top semicircle arrow%>\u21b7;" - "closing angle bracket%>\u3009;" - "closing black lenticular bracket%>\u3011;" - "closing corner bracket%>\u300d;" - "closing double angle bracket%>\u300b;" - "closing tortoise shell bracket%>\u3015;" - "closing white corner bracket%>\u300f;" - "closing white lenticular bracket%>\u3017;" - "closing white square bracket%>\u301b;" - "closing white tortoise shell bracket%>\u3019;" - "cloud%>\u2601;" - "colon equal%>\u2254;" - "colon sign%>\u20a1;" - "comet%>\u2604;" - "command key%>\u2318;" - "complement%>\u2201;" - "conjunction%>\u260c;" - "contains as member%>\u220b;" - "contains as normal subgroup or equal to%>\u22b5;" - "contains as normal subgroup%>\u22b3;" - "contour integral%>\u222e;" - "copyright sign%>\u00a9;" - "corresponds to%>\u2258;" - "cross of jerusalem%>\u2629;" - "cross of lorraine%>\u2628;" - "cruzeiro sign%>\u20a2;" - "cube root%>\u221b;" - "curly logical and%>\u22cf;" - "curly logical or%>\u22ce;" - "currency sign%>\u00a4;" - "curved stem paragraph sign ornament%>\u2761;" - "dagger%>\u2020;" - "dark shade%>\u2593;" - "dashed triangle-headed right arrow%>\u279f;" - "degree sign%>\u00b0;" - "degrees centigrade%>\u2103;" - "degrees fahrenheit%>\u2109;" - "degrees kelvin%>\u212a;" - "delete to the left key%>\u232b;" - "delete to the right key%>\u2326;" - "delta equal to%>\u225c;" - "descending node%>\u260b;" - "diamond operator%>\u22c4;" - "difference between%>\u224f;" - "digit eight period%>\u248f;" - "digit five period%>\u248c;" - "digit four period%>\u248b;" - "digit nine period%>\u2490;" - "digit one period%>\u2488;" - "digit seven period%>\u248e;" - "digit six period%>\u248d;" - "digit three period%>\u248a;" - "digit two period%>\u2489;" - "ditto mark%>\u3003;" - "divides%>\u2223;" - "division sign%>\u00f7;" - "division slash%>\u2215;" - "division times%>\u22c7;" - "does not contain as member%>\u220c;" - "does not contain as normal subgroup or equal%>\u22ed;" - "does not contain as normal subgroup%>\u22eb;" - "does not divide%>\u2224;" - "does not force%>\u22ae;" - "does not precede or equal%>\u22e0;" - "does not precede%>\u2280;" - "does not prove%>\u22ac;" - "does not succeed or equal%>\u22e1;" - "does not succeed%>\u2281;" - "dot minus%>\u2238;" - "dot operator%>\u22c5;" - "dot plus%>\u2214;" - "dotted circle%>\u25cc;" - "double comma quotation mark%>\u201d;" - "double dagger%>\u2021;" - "double exclamation mark%>\u203c;" - "double hyphen%>\u203f;" - "double integral%>\u222c;" - "double intersection%>\u22d2;" - "double prime quotation mark%>\u301e;" - "double prime%>\u2033;" - "double reversed comma quotation mark%>\u201f;" - "double subset%>\u22d0;" - "double superset%>\u22d1;" - "double turned comma quotation mark%>\u201c;" - "double union%>\u22d3;" - "double vertical bar double right turnstile%>\u22ab;" - "double vertical bar%>\u2016;" - "double-struck c%>\u2102;" - "double-struck h%>\u210d;" - "double-struck n%>\u2115;" - "double-struck p%>\u2119;" - "double-struck q%>\u211a;" - "double-struck r%>\u211d;" - "double-struck z%>\u2124;" - "down arrow from bar%>\u21a7;" - "down arrow with corner left%>\u21b5;" - "down arrow with double stroke%>\u21df;" - "down arrow with tip left%>\u21b2;" - "down arrow with tip right%>\u21b3;" - "down arrow%>\u2193;" - "down arrowhead%>\u2304;" - "down dashed arrow%>\u21e3;" - "down double arrow%>\u21d3;" - "down harpoon with barb left%>\u21c3;" - "down harpoon with barb right%>\u21c2;" - "down paired arrows%>\u21ca;" - "down right diagonal ellipsis%>\u22f1;" - "down tack%>\u22a4;" - "down two headed arrow%>\u21a1;" - "down zigzag arrow%>\u21af;" - "drafting point right arrow%>\u279b;" - "earth%>\u2641;" - "eight petalled outlined black florette%>\u2741;" - "eight pointed black star%>\u2734;" - "eight pointed pinwheel star%>\u2735;" - "eight pointed rectilinear black star%>\u2737;" - "eight spoked asterisk%>\u2733;" - "eight teardrop-spoked propeller asterisk%>\u274a;" - "eighth note%>\u266a;" - "element of%>\u2208;" - "small element of%>\u220a;" - "element precedes under relation%>\u22b0;" - "element succeeds under relation%>\u22b1;" - "em dash%>\u2014;" - "em quad%>\u2001;" - "em space%>\u2003;" - "empty set%>\u2205;" - "en dash%>\u2013;" - "en quad%>\u2000;" - "en space%>\u2002;" - "enclosing circle slash%>\u20e0;" - "enclosing circle%>\u20dd;" - "enclosing diamond%>\u20df;" - "enclosing square%>\u20de;" - "end of proof%>\u220e;" - "enter key%>\u2324;" - "envelope%>\u2709;" - "equal and parallel to%>\u22d5;" - "equal colon%>\u2255;" - "equal to by definition%>\u225d;" - "equal to or greater than%>\u22dd;" - "equal to or less than%>\u22dc;" - "equal to or precedes%>\u22de;" - "equal to or succeeds%>\u22df;" - "equiangular to%>\u225a;" - "equivalent to%>\u224d;" - "estimates%>\u2259;" - "eulers%>\u2107;" - "euro-currency sign%>\u20a0;" - "european standard packaging%>\u212e;" - "excess%>\u2239;" - "female sign%>\u2640;" - "feminine ordinal indicator%>\u00aa;" - "figure dash%>\u2012;" - "figure space%>\u2007;" - "first quarter moon%>\u263d;" - "first transfinite cardinal%>\u2135;" - "fisheye%>\u25c9;" - "flat%>\u266d;" - "floral heart%>\u2766;" - "for all%>\u2200;" - "forces%>\u22a9;" - "forms double down and horizontal%>\u2566;" - "forms double down and left%>\u2557;" - "forms double down and right%>\u2554;" - "forms double horizontal%>\u2550;" - "forms double up and horizontal%>\u2569;" - "forms double up and left%>\u255d;" - "forms double up and right%>\u255a;" - "forms double vertical and horizontal%>\u256c;" - "forms double vertical and left%>\u2563;" - "forms double vertical and right%>\u2560;" - "forms double vertical%>\u2551;" - "forms down double and horizontal single%>\u2565;" - "forms down double and left single%>\u2556;" - "forms down double and right single%>\u2553;" - "forms down heavy and horizontal light%>\u2530;" - "forms down heavy and left light%>\u2512;" - "forms down heavy and left up light%>\u2527;" - "forms down heavy and right light%>\u250e;" - "forms down heavy and right up light%>\u251f;" - "forms down heavy and up horizontal light%>\u2541;" - "forms down light and horizontal heavy%>\u252f;" - "forms down light and left heavy%>\u2511;" - "forms down light and left up heavy%>\u2529;" - "forms down light and right heavy%>\u250d;" - "forms down light and right up heavy%>\u2521;" - "forms down light and up horizontal heavy%>\u2547;" - "forms down single and horizontal double%>\u2564;" - "forms down single and left double%>\u2555;" - "forms down single and right double%>\u2552;" - "forms heavy double dash horizontal%>\u254d;" - "forms heavy double dash vertical%>\u254f;" - "forms heavy down and horizontal%>\u2533;" - "forms heavy down and left%>\u2513;" - "forms heavy down and right%>\u250f;" - "forms heavy down%>\u257b;" - "forms heavy horizontal%>\u2501;" - "forms heavy left and light right%>\u257e;" - "forms heavy left%>\u2578;" - "forms heavy quadruple dash horizontal%>\u2509;" - "forms heavy quadruple dash vertical%>\u250b;" - "forms heavy right%>\u257a;" - "forms heavy triple dash horizontal%>\u2505;" - "forms heavy triple dash vertical%>\u2507;" - "forms heavy up and horizontal%>\u253b;" - "forms heavy up and left%>\u251b;" - "forms heavy up and light down%>\u257f;" - "forms heavy up and right%>\u2517;" - "forms heavy up%>\u2579;" - "forms heavy vertical and horizontal%>\u254b;" - "forms heavy vertical and left%>\u252b;" - "forms heavy vertical and right%>\u2523;" - "forms heavy vertical%>\u2503;" - "forms left down heavy and right up light%>\u2545;" - "forms left heavy and right down light%>\u252d;" - "forms left heavy and right up light%>\u2535;" - "forms left heavy and right vertical light%>\u253d;" - "forms left lighand right down heavy%>\u2532;" - "forms left light and right down heavy%>\u2532;" - "forms left light and right up heavy%>\u253a;" - "forms left light and right vertical heavy%>\u254a;" - "forms left up heavy and right down light%>\u2543;" - "forms light arc down and left%>\u256e;" - "forms light arc down and right%>\u256d;" - "forms light arc up and left%>\u256f;" - "forms light arc up and right%>\u2570;" - "forms light diagonal cross%>\u2573;" - "forms light diagonal upper left to lower right%>\u2572;" - "forms light diagonal upper right to lower left%>\u2571;" - "forms light double dash horizontal%>\u254c;" - "forms light double dash vertical%>\u254e;" - "forms light down and horizontal%>\u252c;" - "forms light down and left%>\u2510;" - "forms light down and right%>\u250c;" - "forms light down%>\u2577;" - "forms light horizontal%>\u2500;" - "forms light left and heavy right%>\u257c;" - "forms light left%>\u2574;" - "forms light quadruple dash horizontal%>\u2508;" - "forms light quadruple dash vertical%>\u250a;" - "forms light right%>\u2576;" - "forms light triple dash horizontal%>\u2504;" - "forms light triple dash vertical%>\u2506;" - "forms light up and heavy down%>\u257d;" - "forms light up and horizontal%>\u2534;" - "forms light up and left%>\u2518;" - "forms light up and right%>\u2514;" - "forms light up%>\u2575;" - "forms light vertical and horizontal%>\u253c;" - "forms light vertical and left%>\u2524;" - "forms light vertical and right%>\u251c;" - "forms light vertical%>\u2502;" - "forms right down heavy and left up light%>\u2546;" - "forms right heavy and left down light%>\u252e;" - "forms right heavy and left up light%>\u2536;" - "forms right heavy and left vertical light%>\u253e;" - "forms right light and left down heavy%>\u2531;" - "forms right light and left up heavy%>\u2539;" - "forms right light and left vertical heavy%>\u2549;" - "forms right up heavy and left down light%>\u2544;" - "forms up double and horizontal single%>\u2568;" - "forms up double and left single%>\u255c;" - "forms up double and right single%>\u2559;" - "forms up heavy and down horizontal light%>\u2540;" - "forms up heavy and horizontal light%>\u2538;" - "forms up heavy and left down light%>\u2526;" - "forms up heavy and left light%>\u251a;" - "forms up heavy and right down light%>\u251e;" - "forms up heavy and right light%>\u2516;" - "forms up light and down horizontal heavy%>\u2548;" - "forms up light and horizontal heavy%>\u2537;" - "forms up light and left down heavy%>\u252a;" - "forms up light and left heavy%>\u2519;" - "forms up light and right down heavy%>\u2522;" - "forms up light and right heavy%>\u2515;" - "forms up single and horizontal double%>\u2567;" - "forms up single and left double%>\u255b;" - "forms up single and right double%>\u2558;" - "forms vertical double and horizontal single%>\u256b;" - "forms vertical double and left single%>\u2562;" - "forms vertical double and right single%>\u255f;" - "forms vertical heavy and horizontal light%>\u2542;" - "forms vertical heavy and left light%>\u2528;" - "forms vertical heavy and right light%>\u2520;" - "forms vertical light and horizontal heavy%>\u253f;" - "forms vertical light and left heavy%>\u2525;" - "forms vertical light and right heavy%>\u251d;" - "forms vertical single and horizontal double%>\u256a;" - "forms vertical single and left double%>\u2561;" - "forms vertical single and right double%>\u255e;" - "four balloon-spoked asterisk%>\u2723;" - "four club-spoked asterisk%>\u2725;" - "four teardrop-spoked asterisk%>\u2722;" - "four-per-em space%>\u2005;" - "fourth root%>\u221c;" - "fourth transfinite cardinal%>\u2138;" - "fraction five eighths%>\u215d;" - "fraction five sixths%>\u215a;" - "fraction four fifths%>\u2158;" - "fraction numerator one%>\u215f;" - "fraction one eighth%>\u215b;" - "fraction one fifth%>\u2155;" - "fraction one half%>\u00bd;" - "fraction one quarter%>\u00bc;" - "fraction one sixth%>\u2159;" - "fraction one third%>\u2153;" - "fraction seven eighths%>\u215e;" - "fraction slash%>\u2044;" - "fraction three eighths%>\u215c;" - "fraction three fifths%>\u2157;" - "fraction three quarters%>\u00be;" - "fraction two fifths%>\u2156;" - "fraction two thirds%>\u2154;" - "french franc sign%>\u20a3;" - "front-tilted shadowed white right arrow%>\u27ac;" - "frown%>\u2322;" - "full block%>\u2588;" - "gemini%>\u264a;" - "geometric proportion%>\u223a;" - "geometrically equal to%>\u2251;" - "geometrically equivalent to%>\u224e;" - "geta mark%>\u3013;" - "graphic for acknowledge%>\u2406;" - "graphic for backspace%>\u2408;" - "graphic for bell%>\u2407;" - "graphic for cancel%>\u2418;" - "graphic for carriage return%>\u240d;" - "graphic for data link escape%>\u2410;" - "graphic for delete%>\u2421;" - "graphic for device control four%>\u2414;" - "graphic for device control one%>\u2411;" - "graphic for device control three%>\u2413;" - "graphic for device control two%>\u2412;" - "graphic for end of medium%>\u2419;" - "graphic for end of text%>\u2403;" - "graphic for end of transmission block%>\u2417;" - "graphic for end of transmission%>\u2404;" - "graphic for enquiry%>\u2405;" - "graphic for escape%>\u241b;" - "graphic for file separator%>\u241c;" - "graphic for form feed%>\u240c;" - "graphic for group separator%>\u241d;" - "graphic for horizontal tabulation%>\u2409;" - "graphic for line feed%>\u240a;" - "graphic for negative acknowledge%>\u2415;" - "graphic for newline%>\u2424;" - "graphic for null%>\u2400;" - "graphic for record separator%>\u241e;" - "graphic for shift in%>\u240f;" - "graphic for shift out%>\u240e;" - "graphic for space%>\u2420;" - "graphic for start of heading%>\u2401;" - "graphic for start of text%>\u2402;" - "graphic for substitute%>\u241a;" - "graphic for synchronous idle%>\u2416;" - "graphic for unit separator%>\u241f;" - "graphic for vertical tabulation%>\u240b;" - "greater than but not equal to%>\u2269;" - "greater than but not equivalent to%>\u22e7;" - "greater than equal to or less than%>\u22db;" - "greater than or equal to%>\u2265;" - "greater than or equivalent to%>\u2273;" - "greater than or less than%>\u2277;" - "greater than over equal to%>\u2267;" - "greater than with dot%>\u22d7;" - "hair space%>\u200a;" - "hammer and sickle%>\u262d;" - "hangul double dot tone mark%>\u302f;" - "hangul single dot tone mark%>\u302e;" - "hangzhou numeral eight%>\u3028;" - "hangzhou numeral five%>\u3025;" - "hangzhou numeral four%>\u3024;" - "hangzhou numeral nine%>\u3029;" - "hangzhou numeral one%>\u3021;" - "hangzhou numeral seven%>\u3027;" - "hangzhou numeral six%>\u3026;" - "hangzhou numeral three%>\u3023;" - "hangzhou numeral two%>\u3022;" - "heavy asterisk%>\u2731;" - "heavy black curved down and right arrow%>\u27a5;" - "heavy black curved up and right arrow%>\u27a6;" - "heavy black heart%>\u2764;" - "heavy black-feathered lower right arrow%>\u27b7;" - "heavy black-feathered right arrow%>\u27b8;" - "heavy black-feathered upper right arrow%>\u27b9;" - "heavy check mark%>\u2714;" - "heavy chevron snowflake%>\u2746;" - "heavy concave-pointed black right arrow%>\u27a8;" - "heavy dashed triangle-headed right arrow%>\u27a0;" - "heavy double comma quotation mark ornament%>\u275e;" - "heavy double turned comma quotation mark ornament%>\u275d;" - "heavy eight pointed rectilinear black star%>\u2738;" - "heavy eight teardrop-spoked propeller asterisk%>\u274b;" - "heavy exclamation mark ornament%>\u2762;" - "heavy four balloon-spoked asterisk%>\u2724;" - "heavy greek cross%>\u271a;" - "heavy heart exclamation mark ornament%>\u2763;" - "heavy lower right arrow%>\u2798;" - "heavy lower right-shadowed white right arrow%>\u27ad;" - "heavy multiplication x%>\u2716;" - "heavy open center cross%>\u271c;" - "heavy outlined black star%>\u272e;" - "heavy right arrow%>\u2799;" - "heavy round-tipped right arrow%>\u279c;" - "heavy single comma quotation mark ornament%>\u275c;" - "heavy single turned comma quotation mark ornament%>\u275b;" - "heavy sparkle%>\u2748;" - "heavy teardrop-shanked right arrow%>\u27bb;" - "heavy teardrop-spoked asterisk%>\u273d;" - "heavy teardrop-spoked pinwheel asterisk%>\u2743;" - "heavy triangle-headed right arrow%>\u279e;" - "heavy upper right arrow%>\u279a;" - "heavy upper right-shadowed white right arrow%>\u27ae;" - "heavy vertical bar%>\u275a;" - "heavy wedge-tailed right arrow%>\u27bd;" - "heavy wide-headed right arrow%>\u2794;" - "hermitian conjugate matrix%>\u22b9;" - "homothetic%>\u223b;" - "horizontal ellipsis%>\u2026;" - "hot springs%>\u2668;" - "hourglass%>\u231b;" - "house%>\u2302;" - "hyphen bullet%>\u2043;" - "hyphen%>\u2010;" - "hyphenation point%>\u2027;" - "identical to%>\u2261;" - "ideographic closing mark%>\u3006;" - "ideographic comma%>\u3001;" - "ideographic departing tone mark%>\u302c;" - "ideographic ditto mark%>\u3004;" - "ideographic entering tone mark%>\u302d;" - "ideographic half fill space%>\u303f;" - "ideographic iteration mark%>\u3005;" - "ideographic level tone mark%>\u302a;" - "ideographic number zero%>\u3007;" - "ideographic period%>\u3002;" - "ideographic rising tone mark%>\u302b;" - "ideographic space%>\u3000;" - "image of or approximately equal to%>\u2253;" - "image of%>\u22b7;" - "increment%>\u2206;" - "infinity%>\u221e;" - "integral%>\u222b;" - "intercalate%>\u22ba;" - "interrobang%>\u203d;" - "intersection%>\u2229;" - "inverse bullet%>\u25d8;" - "inverse circled digit eight%>\u277d;" - "inverse circled digit five%>\u277a;" - "inverse circled digit four%>\u2779;" - "inverse circled digit nine%>\u277e;" - "inverse circled digit one%>\u2776;" - "inverse circled digit seven%>\u277c;" - "inverse circled digit six%>\u277b;" - "inverse circled digit three%>\u2778;" - "inverse circled digit two%>\u2777;" - "inverse circled number ten%>\u277f;" - "inverse circled sans serif digit eight%>\u2791;" - "inverse circled sans serif digit five%>\u278e;" - "inverse circled sans serif digit four%>\u278d;" - "inverse circled sans serif digit nine%>\u2792;" - "inverse circled sans serif digit one%>\u278a;" - "inverse circled sans serif digit seven%>\u2790;" - "inverse circled sans serif digit six%>\u278f;" - "inverse circled sans serif digit three%>\u278c;" - "inverse circled sans serif digit two%>\u278b;" - "inverse circled sans serif number ten%>\u2793;" - "inverse white circle%>\u25d9;" - "inverted exclamation mark%>\u00a1;" - "inverted lazy s%>\u223e;" - "inverted question mark%>\u00bf;" - "jupiter%>\u2643;" - "ket%>\u232a;" - "keyboard%>\u2328;" - "l b bar symbol%>\u2114;" - "last quarter moon%>\u263e;" - "latin cross%>\u271d;" - "left arrow from bar%>\u21a4;" - "left arrow over right arrow%>\u21c6;" - "left arrow to bar over right arrow to bar%>\u21b9;" - "left arrow to bar%>\u21e4;" - "left arrow with hook%>\u21a9;" - "left arrow with loop%>\u21ab;" - "left arrow with stroke%>\u219a;" - "left arrow with tail%>\u21a2;" - "left arrow%>\u2190;" - "left ceiling%>\u2308;" - "left dashed arrow%>\u21e0;" - "left double arrow with stroke%>\u21cd;" - "left double arrow%>\u21d0;" - "left five eighths block%>\u258b;" - "left floor%>\u230a;" - "left half black circle%>\u25d6;" - "left half block%>\u258c;" - "left harpoon over right harpoon%>\u21cb;" - "left harpoon with barb down%>\u21bd;" - "left harpoon with barb up%>\u21bc;" - "left normal factor semidirect product%>\u22c9;" - "left one eighth block%>\u258f;" - "left one quarter block%>\u258e;" - "left paired arrows%>\u21c7;" - "left pointing guillemet%>\u00ab;" - "left pointing single guillemet%>\u2039;" - "left right arrow with stroke%>\u21ae;" - "left right arrow%>\u2194;" - "left right double arrow with stroke%>\u21ce;" - "left right double arrow%>\u21d4;" - "left right wave arrow%>\u21ad;" - "left semidirect product%>\u22cb;" - "left seven eighths block%>\u2589;" - "left squiggle arrow%>\u21dc;" - "left tack%>\u22a3;" - "left three eighths block%>\u258d;" - "left three quarter block%>\u258a;" - "left triple arrow%>\u21da;" - "left two headed arrow%>\u219e;" - "left wave arrow%>\u219c;" - "left-shaded white right arrow%>\u27aa;" - "left-to-right embedding%>\u202a;" - "left-to-right mark%>\u200e;" - "left-to-right override%>\u202d;" - "leo%>\u264c;" - "less than but not equal to%>\u2268;" - "less than but not equivalent to%>\u22e6;" - "less than equal to or greater than%>\u22da;" - "less than or equal to%>\u2264;" - "less than or equivalent to%>\u2272;" - "less than or greater than%>\u2276;" - "less than over equal to%>\u2266;" - "less than with dot%>\u22d6;" - "libra%>\u264e;" - "light shade%>\u2591;" - "light vertical bar%>\u2758;" - "lightning%>\u2607;" - "line separator%>\u2028;" - "lira sign%>\u20a4;" - "logical and%>\u2227;" - "logical or%>\u2228;" - "low double comma quotation mark%>\u201e;" - "low double prime quotation mark%>\u301f;" - "low single comma quotation mark%>\u201a;" - "lower blade scissors%>\u2703;" - "lower five eighths block%>\u2585;" - "lower half block%>\u2584;" - "lower half circle%>\u25e1;" - "lower half inverse white circle%>\u25db;" - "lower left arrow%>\u2199;" - "lower left double arrow%>\u21d9;" - "lower left quadrant circular arc%>\u25df;" - "lower one eighth block%>\u2581;" - "lower one quarter block%>\u2582;" - "lower right arrow%>\u2198;" - "lower right double arrow%>\u21d8;" - "lower right drop-shadowed white square%>\u274f;" - "lower right pencil%>\u270e;" - "lower right quadrant circular arc%>\u25de;" - "lower right shadowed white square%>\u2751;" - "lower seven eighths block%>\u2587;" - "lower three eighths block%>\u2583;" - "lower three quarter block%>\u2586;" - "lozenge%>\u25ca;" - "male sign%>\u2642;" - "maltese cross%>\u2720;" - "masculine ordinal indicator%>\u00ba;" - "measured angle%>\u2221;" - "measured by%>\u225e;" - "medium shade%>\u2592;" - "medium vertical bar%>\u2759;" - "mercury%>\u263f;" - "mho%>\u2127;" - "micro sign%>\u00b5;" - "middle dot%>\u00b7;" - "midline horizontal ellipsis%>\u22ef;" - "mill sign%>\u20a5;" - "minus sign%>\u2212;" - "minus tilde%>\u2242;" - "minus-or-plus sign%>\u2213;" - "models%>\u22a7;" - "modifier letter acute%>\u02ca;" - "modifier letter apostrophe%>\u02bc;" - "modifier letter centered left half ring%>\u02d3;" - "modifier letter centered right half ring%>\u02d2;" - "modifier letter circumflex%>\u02c6;" - "modifier letter double prime%>\u02ba;" - "modifier letter down arrowhead%>\u02c5;" - "modifier letter down tack%>\u02d5;" - "modifier letter extra-high tone bar%>\u02e5;" - "modifier letter extra-low tone bar%>\u02e9;" - "modifier letter glottal stop%>\u02c0;" - "modifier letter grave%>\u02cb;" - "modifier letter hacek%>\u02c7;" - "modifier letter half triangular colon%>\u02d1;" - "modifier letter high tone bar%>\u02e6;" - "modifier letter left arrowhead%>\u02c2;" - "modifier letter left half ring%>\u02bf;" - "modifier letter low acute%>\u02cf;" - "modifier letter low grave%>\u02ce;" - "modifier letter low macron%>\u02cd;" - "modifier letter low tone bar%>\u02e8;" - "modifier letter low vertical line%>\u02cc;" - "modifier letter macron%>\u02c9;" - "modifier letter mid tone bar%>\u02e7;" - "modifier letter minus sign%>\u02d7;" - "modifier letter plus sign%>\u02d6;" - "modifier letter prime%>\u02b9;" - "modifier letter reversed comma%>\u02bd;" - "modifier letter reversed glottal stop%>\u02c1;" - "modifier letter rhotic hook%>\u02de;" - "modifier letter right arrowhead%>\u02c3;" - "modifier letter right half ring%>\u02be;" - "modifier letter small capital inverted r%>\u02b6;" - "modifier letter small gamma%>\u02e0;" - "modifier letter small h hook%>\u02b1;" - "modifier letter small h%>\u02b0;" - "modifier letter small j%>\u02b2;" - "modifier letter small l%>\u02e1;" - "modifier letter small r%>\u02b3;" - "modifier letter small reversed glottal stop%>\u02e4;" - "modifier letter small s%>\u02e2;" - "modifier letter small turned r hook%>\u02b5;" - "modifier letter small turned r%>\u02b4;" - "modifier letter small w%>\u02b7;" - "modifier letter small x%>\u02e3;" - "modifier letter small y%>\u02b8;" - "modifier letter triangular colon%>\u02d0;" - "modifier letter turned comma%>\u02bb;" - "modifier letter up arrowhead%>\u02c4;" - "modifier letter up tack%>\u02d4;" - "modifier letter vertical line%>\u02c8;" - "much greater than%>\u226b;" - "much less than%>\u226a;" - "multimap%>\u22b8;" - "multiplication sign%>\u00d7;" - "multiplication x%>\u2715;" - "multiset multiplication%>\u228d;" - "multiset union%>\u228e;" - "multiset%>\u228c;" - "n-ary coproduct%>\u2210;" - "n-ary intersection%>\u22c2;" - "n-ary logical and%>\u22c0;" - "n-ary logical or%>\u22c1;" - "n-ary product%>\u220f;" - "n-ary summation%>\u2211;" - "n-ary union%>\u22c3;" - "nabla%>\u2207;" - "naira sign%>\u20a6;" - "nand%>\u22bc;" - "natural%>\u266e;" - "negated double vertical bar double right turnstile%>\u22af;" - "neither a subset of nor equal to%>\u2288;" - "neither a superset of nor equal to%>\u2289;" - "neither approximately nor actually equal to%>\u2247;" - "neither greater than nor equal to%>\u2271;" - "neither greater than nor equivalent to%>\u2275;" - "neither greater than nor less than%>\u2279;" - "neither less than nor equal to%>\u2270;" - "neither less than nor equivalent to%>\u2274;" - "neither less than nor greater than%>\u2278;" - "neptune%>\u2646;" - "new sheqel sign%>\u20aa;" - "non-breaking hyphen%>\u2011;" - "non-breaking space%>\u00a0;" - "non-spacing acute below%>\u0317;" - "non-spacing acute tone mark%>\u0348;" - "non-spacing acute%>\u0301;" - "non-spacing anticlockwise arrow above%>\u20d4;" - "non-spacing anticlockwise ring overlay%>\u20da;" - "non-spacing breve below%>\u032e;" - "non-spacing breve%>\u0306;" - "non-spacing bridge below%>\u032a;" - "non-spacing candrabindu%>\u0310;" - "non-spacing cedilla%>\u0327;" - "non-spacing centerline overscore%>\u0341;" - "non-spacing centerline underscore%>\u0345;" - "non-spacing circumflex below%>\u032d;" - "non-spacing circumflex%>\u0302;" - "non-spacing clockwise arrow above%>\u20d5;" - "non-spacing clockwise ring overlay%>\u20d9;" - "non-spacing comma above right%>\u0315;" - "non-spacing comma above%>\u0313;" - "non-spacing comma below%>\u0326;" - "non-spacing dashed overscore%>\u0340;" - "non-spacing dashed underscore%>\u0344;" - "non-spacing diaeresis%>\u0308;" - "non-spacing dot above%>\u0307;" - "non-spacing dot below%>\u0323;" - "non-spacing double acute%>\u030b;" - "non-spacing double dot below%>\u0324;" - "non-spacing double grave%>\u030f;" - "non-spacing double overscore%>\u033f;" - "non-spacing double underscore%>\u0333;" - "non-spacing double vertical line above%>\u030e;" - "non-spacing double wavy overscore%>\u0343;" - "non-spacing down tack below%>\u031e;" - "non-spacing four dots above%>\u20dc;" - "non-spacing grave below%>\u0316;" - "non-spacing grave tone mark%>\u0347;" - "non-spacing grave%>\u0300;" - "non-spacing hacek below%>\u032c;" - "non-spacing hacek%>\u030c;" - "non-spacing hook above%>\u0309;" - "non-spacing horn%>\u031b;" - "non-spacing inverted breve below%>\u032f;" - "non-spacing inverted breve%>\u0311;" - "non-spacing inverted bridge below%>\u033a;" - "non-spacing inverted double arch below%>\u032b;" - "non-spacing left angle above%>\u031a;" - "non-spacing left arrow above%>\u20d6;" - "non-spacing left half ring below%>\u031c;" - "non-spacing left harpoon above%>\u20d0;" - "non-spacing left right arrow above%>\u20e1;" - "non-spacing left tack below%>\u0318;" - "non-spacing long bar overlay%>\u0336;" - "non-spacing long slash overlay%>\u0338;" - "non-spacing long vertical bar overlay%>\u20d2;" - "non-spacing macron below%>\u0331;" - "non-spacing macron%>\u0304;" - "non-spacing minus sign below%>\u0320;" - "non-spacing ogonek%>\u0328;" - "non-spacing overscore%>\u0305;" - "non-spacing palatalized hook below%>\u0321;" - "non-spacing plus sign below%>\u031f;" - "non-spacing retroflex hook below%>\u0322;" - "non-spacing reversed comma above%>\u0314;" - "non-spacing right arrow above%>\u20d7;" - "non-spacing right half ring below%>\u0339;" - "non-spacing right harpoon above%>\u20d1;" - "non-spacing right tack below%>\u0319;" - "non-spacing ring above%>\u030a;" - "non-spacing ring below%>\u0325;" - "non-spacing ring overlay%>\u20d8;" - "non-spacing seagull below%>\u033c;" - "non-spacing short bar overlay%>\u0335;" - "non-spacing short slash overlay%>\u0337;" - "non-spacing short vertical bar overlay%>\u20d3;" - "non-spacing square below%>\u033b;" - "non-spacing three dots above%>\u20db;" - "non-spacing tilde below%>\u0330;" - "non-spacing tilde overlay%>\u0334;" - "non-spacing tilde%>\u0303;" - "non-spacing turned comma above%>\u0312;" - "non-spacing underscore%>\u0332;" - "non-spacing up tack below%>\u031d;" - "non-spacing vertical line above%>\u030d;" - "non-spacing vertical line below%>\u0329;" - "non-spacing vertical tilde%>\u033e;" - "non-spacing wavy overscore%>\u0342;" - "non-spacing wavy underscore%>\u0346;" - "non-spacing x above%>\u033d;" - "nor%>\u22bd;" - "normal subgroup of or equal to%>\u22b4;" - "normal subgroup of%>\u22b2;" - "not a subset of%>\u2284;" - "not a superset of%>\u2285;" - "not almost equal to%>\u2249;" - "not an element of%>\u2209;" - "not asymptotically equal to%>\u2244;" - "not equal to%>\u2260;" - "not equivalent to%>\u226d;" - "not greater than%>\u226f;" - "not identical to%>\u2262;" - "not less than%>\u226e;" - "not normal subgroup of or equal to%>\u22ec;" - "not normal subgroup of%>\u22ea;" - "not parallel to%>\u2226;" - "not sign%>\u00ac;" - "not square image of or equal to%>\u22e2;" - "not square original of or equal to%>\u22e3;" - "not tilde%>\u2241;" - "not true%>\u22ad;" - "notched lower right-shadowed white right arrow%>\u27af;" - "notched upper right-shadowed white right arrow%>\u27b1;" - "number eighteen period%>\u2499;" - "number eleven period%>\u2492;" - "number fifteen period%>\u2496;" - "number fourteen period%>\u2495;" - "number nineteen period%>\u249a;" - "number seventeen period%>\u2498;" - "number sixteen period%>\u2497;" - "number ten period%>\u2491;" - "number thirteen period%>\u2494;" - "number twelve period%>\u2493;" - "number twenty period%>\u249b;" - "numero%>\u2116;" - "ocr amount of check%>\u2447;" - "ocr belt buckle%>\u2444;" - "ocr bow tie%>\u2445;" - "ocr branch bank identification%>\u2446;" - "ocr chair%>\u2441;" - "ocr customer account number%>\u2449;" - "ocr dash%>\u2448;" - "ocr double backslash%>\u244a;" - "ocr fork%>\u2442;" - "ocr hook%>\u2440;" - "ocr inverted fork%>\u2443;" - "ohm%>\u2126;" - "one dot leader%>\u2024;" - "open box%>\u2423;" - "open center asterisk%>\u2732;" - "open center black star%>\u272b;" - "open center cross%>\u271b;" - "open center teardrop-spoked asterisk%>\u273c;" - "open-outlined right arrow%>\u27be;" - "opening angle bracket%>\u3008;" - "opening black lenticular bracket%>\u3010;" - "opening corner bracket%>\u300c;" - "opening double angle bracket%>\u300a;" - "opening tortoise shell bracket%>\u3014;" - "opening white corner bracket%>\u300e;" - "opening white lenticular bracket%>\u3016;" - "opening white square bracket%>\u301a;" - "opening white tortoise shell bracket%>\u3018;" - "opposition%>\u260d;" - "option key%>\u2325;" - "original of%>\u22b6;" - "orthodox cross%>\u2626;" - "ounce%>\u2125;" - "outlined black star%>\u272d;" - "outlined greek cross%>\u2719;" - "outlined latin cross%>\u271f;" - "paragraph separator%>\u2029;" - "paragraph sign%>\u00b6;" - "parallel to%>\u2225;" - "parenthesized digit eight%>\u247b;" - "parenthesized digit five%>\u2478;" - "parenthesized digit four%>\u2477;" - "parenthesized digit nine%>\u247c;" - "parenthesized digit one%>\u2474;" - "parenthesized digit seven%>\u247a;" - "parenthesized digit six%>\u2479;" - "parenthesized digit three%>\u2476;" - "parenthesized digit two%>\u2475;" - "parenthesized latin small letter a%>\u249c;" - "parenthesized latin small letter b%>\u249d;" - "parenthesized latin small letter c%>\u249e;" - "parenthesized latin small letter d%>\u249f;" - "parenthesized latin small letter e%>\u24a0;" - "parenthesized latin small letter f%>\u24a1;" - "parenthesized latin small letter g%>\u24a2;" - "parenthesized latin small letter h%>\u24a3;" - "parenthesized latin small letter i%>\u24a4;" - "parenthesized latin small letter j%>\u24a5;" - "parenthesized latin small letter k%>\u24a6;" - "parenthesized latin small letter l%>\u24a7;" - "parenthesized latin small letter m%>\u24a8;" - "parenthesized latin small letter n%>\u24a9;" - "parenthesized latin small letter o%>\u24aa;" - "parenthesized latin small letter p%>\u24ab;" - "parenthesized latin small letter q%>\u24ac;" - "parenthesized latin small letter r%>\u24ad;" - "parenthesized latin small letter s%>\u24ae;" - "parenthesized latin small letter t%>\u24af;" - "parenthesized latin small letter u%>\u24b0;" - "parenthesized latin small letter v%>\u24b1;" - "parenthesized latin small letter w%>\u24b2;" - "parenthesized latin small letter x%>\u24b3;" - "parenthesized latin small letter y%>\u24b4;" - "parenthesized latin small letter z%>\u24b5;" - "parenthesized number eighteen%>\u2485;" - "parenthesized number eleven%>\u247e;" - "parenthesized number fifteen%>\u2482;" - "parenthesized number fourteen%>\u2481;" - "parenthesized number nineteen%>\u2486;" - "parenthesized number seventeen%>\u2484;" - "parenthesized number sixteen%>\u2483;" - "parenthesized number ten%>\u247d;" - "parenthesized number thirteen%>\u2480;" - "parenthesized number twelve%>\u247f;" - "parenthesized number twenty%>\u2487;" - "partial differential%>\u2202;" - "peace symbol%>\u262e;" - "pencil%>\u270f;" - "per mille sign%>\u2030;" - "per ten thousand sign%>\u2031;" - "perspective%>\u2306;" - "peseta sign%>\u20a7;" - "pinwheel star%>\u272f;" - "pisces%>\u2653;" - "pitchfork%>\u22d4;" - "planck constant over 2 pi%>\u210f;" - "planck constant%>\u210e;" - "plus-or-minus sign%>\u00b1;" - "pluto%>\u2647;" - "pop directional embedding%>\u202c;" - "position indicator%>\u2316;" - "postal mark face%>\u3020;" - "postal mark%>\u3012;" - "pound sign%>\u00a3;" - "precedes but not equivalent to%>\u22e8;" - "precedes or equal to%>\u227c;" - "precedes or equivalent to%>\u227e;" - "precedes%>\u227a;" - "prescription take%>\u211e;" - "prime%>\u2032;" - "projective%>\u2305;" - "proportion%>\u2237;" - "proportional to%>\u221d;" - "punctuation space%>\u2008;" - "quarter note%>\u2669;" - "questioned equal to%>\u225f;" - "quotation dash%>\u2015;" - "radioactive%>\u2622;" - "ratio%>\u2236;" - "reference mark%>\u203b;" - "registered trade mark sign%>\u00ae;" - "response%>\u211f;" - "reversed double prime quotation mark%>\u301d;" - "reversed double prime%>\u2036;" - "reversed not sign%>\u2310;" - "reversed prime%>\u2035;" - "reversed tilde equals%>\u22cd;" - "reversed tilde%>\u223d;" - "reversed triple prime%>\u2037;" - "right angle with arc%>\u22be;" - "right angle%>\u221f;" - "right arrow from bar%>\u21a6;" - "right arrow over left arrow%>\u21c4;" - "right arrow to bar%>\u21e5;" - "right arrow with corner down%>\u21b4;" - "right arrow with hook%>\u21aa;" - "right arrow with loop%>\u21ac;" - "right arrow with stroke%>\u219b;" - "right arrow with tail%>\u21a3;" - "right arrow%>\u2192;" - "right ceiling%>\u2309;" - "right dashed arrow%>\u21e2;" - "right double arrow with stroke%>\u21cf;" - "right double arrow%>\u21d2;" - "right floor%>\u230b;" - "right half black circle%>\u25d7;" - "right half block%>\u2590;" - "right harpoon over left harpoon%>\u21cc;" - "right harpoon with barb down%>\u21c1;" - "right harpoon with barb up%>\u21c0;" - "right normal factor semidirect product%>\u22ca;" - "right one eighth block%>\u2595;" - "right paired arrows%>\u21c9;" - "right pointing guillemet%>\u00bb;" - "right pointing single guillemet%>\u203a;" - "right semidirect product%>\u22cc;" - "right squiggle arrow%>\u21dd;" - "right tack%>\u22a2;" - "right triangle%>\u22bf;" - "right triple arrow%>\u21db;" - "right two headed arrow%>\u21a0;" - "right wave arrow%>\u219d;" - "right-shaded white right arrow%>\u27a9;" - "right-to-left embedding%>\u202b;" - "right-to-left mark%>\u200f;" - "right-to-left override%>\u202e;" - "ring equal to%>\u2257;" - "ring in equal to%>\u2256;" - "ring operator%>\u2218;" - "roman numeral eight%>\u2167;" - "roman numeral eleven%>\u216a;" - "roman numeral fifty%>\u216c;" - "roman numeral five hundred%>\u216e;" - "roman numeral five thousand%>\u2181;" - "roman numeral five%>\u2164;" - "roman numeral four%>\u2163;" - "roman numeral nine%>\u2168;" - "roman numeral one hundred%>\u216d;" - "roman numeral one thousand c d%>\u2180;" - "roman numeral one thousand%>\u216f;" - "roman numeral one%>\u2160;" - "roman numeral seven%>\u2166;" - "roman numeral six%>\u2165;" - "roman numeral ten thousand%>\u2182;" - "roman numeral ten%>\u2169;" - "roman numeral three%>\u2162;" - "roman numeral twelve%>\u216b;" - "roman numeral two%>\u2161;" - "rotated floral heart bullet%>\u2767;" - "rotated heavy black heart bullet%>\u2765;" - "rupee sign%>\u20a8;" - "sagittarius%>\u2650;" - "saltire%>\u2613;" - "saturn%>\u2644;" - "scorpius%>\u264f;" - "script b%>\u212c;" - "script e%>\u2130;" - "script f%>\u2131;" - "script h%>\u210b;" - "script i%>\u2110;" - "script l%>\u2112;" - "script m%>\u2133;" - "script p%>\u2118;" - "script r%>\u211b;" - "script small e%>\u212f;" - "script small g%>\u210a;" - "script small l%>\u2113;" - "script small o%>\u2134;" - "scruple%>\u2108;" - "second transfinite cardinal%>\u2136;" - "section sign%>\u00a7;" - "sector%>\u2314;" - "segment%>\u2313;" - "service mark%>\u2120;" - "set minus%>\u2216;" - "shadowed white circle%>\u274d;" - "shadowed white latin cross%>\u271e;" - "shadowed white star%>\u2730;" - "sharp%>\u266f;" - "sine wave%>\u223f;" - "single comma quotation mark%>\u2019;" - "single reversed comma quotation mark%>\u201b;" - "single turned comma quotation mark%>\u2018;" - "six petalled black and white florette%>\u273e;" - "six pointed black star%>\u2736;" - "six-per-em space%>\u2006;" - "sixteen pointed asterisk%>\u273a;" - "skull and crossbones%>\u2620;" - "small contains as member%>\u220d;" - "small roman numeral eight%>\u2177;" - "small roman numeral eleven%>\u217a;" - "small roman numeral fifty%>\u217c;" - "small roman numeral five hundred%>\u217e;" - "small roman numeral five%>\u2174;" - "small roman numeral four%>\u2173;" - "small roman numeral nine%>\u2178;" - "small roman numeral one hundred%>\u217d;" - "small roman numeral one thousand%>\u217f;" - "small roman numeral one%>\u2170;" - "small roman numeral seven%>\u2176;" - "small roman numeral six%>\u2175;" - "small roman numeral ten%>\u2179;" - "small roman numeral three%>\u2172;" - "small roman numeral twelve%>\u217b;" - "small roman numeral two%>\u2171;" - "smile%>\u2323;" - "snowflake%>\u2744;" - "snowman%>\u2603;" - "soft hyphen%>\u00ad;" - "sound recording copyright%>\u2117;" - "spacing acute%>\u00b4;" - "spacing breve%>\u02d8;" - "spacing cedilla%>\u00b8;" - "spacing diaeresis%>\u00a8;" - "spacing dot above%>\u02d9;" - "spacing double acute%>\u02dd;" - "spacing double underscore%>\u2017;" - "spacing macron%>\u00af;" - "spacing ogonek%>\u02db;" - "spacing overscore%>\u203e;" - "spacing ring above%>\u02da;" - "spacing tilde%>\u02dc;" - "sparkle%>\u2747;" - "spherical angle%>\u2222;" - "square cap%>\u2293;" - "square cup%>\u2294;" - "square image of or equal to%>\u2291;" - "square image of or not equal to%>\u22e4;" - "square image of%>\u228f;" - "square lozenge%>\u2311;" - "square original of or equal to%>\u2292;" - "square original of or not equal to%>\u22e5;" - "square original of%>\u2290;" - "square root%>\u221a;" - "square with diagonal crosshatch fill%>\u25a9;" - "square with horizontal fill%>\u25a4;" - "square with left half black%>\u25e7;" - "square with lower right diagonal half black%>\u25ea;" - "square with orthogonal crosshatch fill%>\u25a6;" - "square with right half black%>\u25e8;" - "square with upper left diagonal half black%>\u25e9;" - "square with upper left to lower right fill%>\u25a7;" - "square with upper right to lower left fill%>\u25a8;" - "square with vertical fill%>\u25a5;" - "squared dot operator%>\u22a1;" - "squared minus%>\u229f;" - "squared plus%>\u229e;" - "squared times%>\u22a0;" - "squat black right arrow%>\u27a7;" - "star and crescent%>\u262a;" - "star equals%>\u225b;" - "star of david%>\u2721;" - "star operator%>\u22c6;" - "stop directional override%>\u202f;" - "strictly equivalent to%>\u2263;" - "subscript closing parenthesis%>\u208e;" - "subscript digit eight%>\u2088;" - "subscript digit five%>\u2085;" - "subscript digit four%>\u2084;" - "subscript digit nine%>\u2089;" - "subscript digit one%>\u2081;" - "subscript digit seven%>\u2087;" - "subscript digit six%>\u2086;" - "subscript digit three%>\u2083;" - "subscript digit two%>\u2082;" - "subscript digit zero%>\u2080;" - "subscript equals sign%>\u208c;" - "subscript hyphen-minus%>\u208b;" - "subscript opening parenthesis%>\u208d;" - "subscript plus sign%>\u208a;" - "subset of or equal to%>\u2286;" - "subset of or not equal to%>\u228a;" - "subset of%>\u2282;" - "succeeds but not equivalent to%>\u22e9;" - "succeeds or equal to%>\u227d;" - "succeeds or equivalent to%>\u227f;" - "succeeds%>\u227b;" - "superscript closing parenthesis%>\u207e;" - "superscript digit eight%>\u2078;" - "superscript digit five%>\u2075;" - "superscript digit four%>\u2074;" - "superscript digit nine%>\u2079;" - "superscript digit one%>\u00b9;" - "superscript digit seven%>\u2077;" - "superscript digit six%>\u2076;" - "superscript digit three%>\u00b3;" - "superscript digit two%>\u00b2;" - "superscript digit zero%>\u2070;" - "superscript equals sign%>\u207c;" - "superscript hyphen-minus%>\u207b;" - "superscript latin small letter n%>\u207f;" - "superscript opening parenthesis%>\u207d;" - "superscript plus sign%>\u207a;" - "superset of or equal to%>\u2287;" - "superset of or not equal to%>\u228b;" - "superset of%>\u2283;" - "surface integral%>\u222f;" - "symbol of iran%>\u262b;" - "t e l symbol%>\u2121;" - "tape drive%>\u2707;" - "taurus%>\u2649;" - "teardrop-barbed right arrow%>\u27ba;" - "teardrop-spoked asterisk%>\u273b;" - "telephone location sign%>\u2706;" - "telephone recorder%>\u2315;" - "there does not exist%>\u2204;" - "there exists%>\u2203;" - "therefore%>\u2234;" - "thin space%>\u2009;" - "third transfinite cardinal%>\u2137;" - "three-d bottom-lighted right arrowhead%>\u27a3;" - "three-d top-lighted right arrowhead%>\u27a2;" - "three-per-em space%>\u2004;" - "thunderstorm%>\u2608;" - "tight trifoliate snowflake%>\u2745;" - "tilde operator%>\u223c;" - "top half integral%>\u2320;" - "top left corner%>\u231c;" - "top left crop%>\u230f;" - "top right corner%>\u231d;" - "top right crop%>\u230e;" - "trademark%>\u2122;" - "triangle-headed right arrow%>\u279d;" - "triangular bullet%>\u2023;" - "trigram for earth%>\u2637;" - "trigram for fire%>\u2632;" - "trigram for heaven%>\u2630;" - "trigram for lake%>\u2631;" - "trigram for mountain%>\u2636;" - "trigram for thunder%>\u2633;" - "trigram for water%>\u2635;" - "trigram for wind%>\u2634;" - "triple integral%>\u222d;" - "triple prime%>\u2034;" - "triple tilde%>\u224b;" - "triple vertical bar right turnstile%>\u22aa;" - "true%>\u22a8;" - "turned f%>\u2132;" - "turned greek small letter iota%>\u2129;" - "turned not sign%>\u2319;" - "twelve pointed black star%>\u2739;" - "two dot leader%>\u2025;" - "umbrella%>\u2602;" - "union%>\u222a;" - "up arrow from bar%>\u21a5;" - "up arrow left of down arrow%>\u21c5;" - "up arrow with double stroke%>\u21de;" - "up arrow with tip left%>\u21b0;" - "up arrow with tip right%>\u21b1;" - "up arrow%>\u2191;" - "up arrowhead%>\u2303;" - "up dashed arrow%>\u21e1;" - "up double arrow%>\u21d1;" - "up down arrow with base%>\u21a8;" - "up down arrow%>\u2195;" - "up down double arrow%>\u21d5;" - "up harpoon with barb left%>\u21bf;" - "up harpoon with barb right%>\u21be;" - "up paired arrows%>\u21c8;" - "up pointing triangle with left half black%>\u25ed;" - "up pointing triangle with right half black%>\u25ee;" - "up right diagonal ellipsis%>\u22f0;" - "up tack%>\u22a5;" - "up two headed arrow%>\u219f;" - "upper blade scissors%>\u2701;" - "upper half block%>\u2580;" - "upper half circle%>\u25e0;" - "upper half inverse white circle%>\u25da;" - "upper left arrow to long bar%>\u21b8;" - "upper left arrow%>\u2196;" - "upper left double arrow%>\u21d6;" - "upper left quadrant circular arc%>\u25dc;" - "upper one eighth block%>\u2594;" - "upper right arrow%>\u2197;" - "upper right double arrow%>\u21d7;" - "upper right drop-shadowed white square%>\u2750;" - "upper right pencil%>\u2710;" - "upper right quadrant circular arc%>\u25dd;" - "upper right shadowed white square%>\u2752;" - "uranus%>\u2645;" - "versicle%>\u2123;" - "vertical ellipsis%>\u22ee;" - "vertical kana repeat mark lower half%>\u3035;" - "vertical kana repeat mark upper half%>\u3033;" - "vertical kana repeat mark%>\u3031;" - "vertical kana repeat with voiced sound mark upper half%>\u3034;" - "vertical kana repeat with voiced sound mark%>\u3032;" - "very much greater than%>\u22d9;" - "very much less than%>\u22d8;" - "victory hand%>\u270c;" - "viewdata square%>\u2317;" - "virgo%>\u264d;" - "volume integral%>\u2230;" - "watch%>\u231a;" - "wave dash%>\u301c;" - "wavy dash%>\u3030;" - "wavy line%>\u2307;" - "wedge-tailed right arrow%>\u27bc;" - "wheel of dharma%>\u2638;" - "white bullet%>\u25e6;" - "white chess bishop%>\u2657;" - "white chess king%>\u2654;" - "white chess knight%>\u2658;" - "white chess pawn%>\u2659;" - "white chess queen%>\u2655;" - "white chess rook%>\u2656;" - "white circle%>\u25cb;" - "white club suit%>\u2667;" - "white diamond containing black small diamond%>\u25c8;" - "white diamond suit%>\u2662;" - "white diamond%>\u25c7;" - "white down arrow%>\u21e9;" - "white down pointing index%>\u261f;" - "white down pointing small triangle%>\u25bf;" - "white down pointing triangle%>\u25bd;" - "white florette%>\u2740;" - "white four pointed star%>\u2727;" - "white frowning face%>\u2639;" - "white heart suit%>\u2661;" - "white left arrow%>\u21e6;" - "white left pointing index%>\u261c;" - "white left pointing pointer%>\u25c5;" - "white left pointing small triangle%>\u25c3;" - "white left pointing triangle%>\u25c1;" - "white nib%>\u2711;" - "white parallelogram%>\u25b1;" - "white rectangle%>\u25ad;" - "white right arrow%>\u21e8;" - "white right pointing index%>\u261e;" - "white right pointing pointer%>\u25bb;" - "white right pointing small triangle%>\u25b9;" - "white right pointing triangle%>\u25b7;" - "white scissors%>\u2704;" - "white small square%>\u25ab;" - "white smiling face%>\u263a;" - "white spade suit%>\u2664;" - "white square containing black small square%>\u25a3;" - "white square with rounded corners%>\u25a2;" - "white square with vertical bisecting line%>\u25eb;" - "white square%>\u25a1;" - "white star%>\u2606;" - "white sun with rays%>\u263c;" - "white telephone%>\u260f;" - "white up arrow from bar%>\u21ea;" - "white up arrow%>\u21e7;" - "white up pointing index%>\u261d;" - "white up pointing small triangle%>\u25b5;" - "white up pointing triangle with dot%>\u25ec;" - "white up pointing triangle%>\u25b3;" - "white vertical rectangle%>\u25af;" - "white-feathered right arrow%>\u27b3;" - "won sign%>\u20a9;" - "wreath product%>\u2240;" - "writing hand%>\u270d;" - "x mark3%>\u2717;" - "xor%>\u22bb;" - "yen sign%>\u00a5;" - "yin yang%>\u262f;" - "zero width joiner%>\u200d;" - "zero width non-joiner%>\u200c;" - "zero width space%>\u200b;" - } -}