# SuperScriptFolding.txt # DRAFT 1 - 2004-05-22 Asmus Freytag # Subject to change # # Base version of Unicode: 4.0.0 # # # Datafile for Unicode Techical Report #30 # Copyright (c) 1991-2004 Unicode, Inc. # For terms of use, and documentation see # http://www.unicode.org/reports/tr30/ # ================================= # # Map all characters that are superscripted forms to their equivalent letter # # Format # Field 0 - character code (source) # Field 1 - character code of code sequnece (target) # Comment - utf8 of source -> utf8 of target, followed by # characer name of source -> character name of target # # Notes: # # 1) This is a superset of characters with the compatibility # decomposition # # Stability # The repertoire of modifier letters is not yet complete, therefore # this file would need to change whenever additional modifier # letters are added to the Unicode Standard. # ########################################################################### # characters with compatibility decomposition in UnicodeData.txt 00AA; 0061 # ª → a FEMININE ORDINAL INDICATOR → LATIN SMALL LETTER A 00B2; 0032 # ² → 2 SUPERSCRIPT TWO → DIGIT TWO 00B3; 0033 # ³ → 3 SUPERSCRIPT THREE → DIGIT THREE 00B9; 0031 # ¹ → 1 SUPERSCRIPT ONE → DIGIT ONE 00BA; 006F # º → o MASCULINE ORDINAL INDICATOR → LATIN SMALL LETTER O 02B0; 0068 # ʰ → h MODIFIER LETTER SMALL H → LATIN SMALL LETTER H 02B1; 0266 # ʱ → ɦ MODIFIER LETTER SMALL H WITH HOOK → LATIN SMALL LETTER H WITH HOOK 02B2; 006A # ʲ → j MODIFIER LETTER SMALL J → LATIN SMALL LETTER J 02B3; 0072 # ʳ → r MODIFIER LETTER SMALL R → LATIN SMALL LETTER R 02B4; 0279 # ʴ → ɹ MODIFIER LETTER SMALL TURNED R → LATIN SMALL LETTER TURNED R 02B5; 027B # ʵ → ɻ MODIFIER LETTER SMALL TURNED R WITH HOOK → LATIN SMALL LETTER TURNED R WITH HOOK 02B6; 0281 # ʶ → ʁ MODIFIER LETTER SMALL CAPITAL INVERTED R → LATIN LETTER SMALL CAPITAL INVERTED R 02B7; 0077 # ʷ → w MODIFIER LETTER SMALL W → LATIN SMALL LETTER W 02B8; 0079 # ʸ → y MODIFIER LETTER SMALL Y → LATIN SMALL LETTER Y 02E0; 0263 # ˠ → ɣ MODIFIER LETTER SMALL GAMMA → LATIN SMALL LETTER GAMMA 02E1; 006C # ˡ → l MODIFIER LETTER SMALL L → LATIN SMALL LETTER L 02E2; 0073 # ˢ → s MODIFIER LETTER SMALL S → LATIN SMALL LETTER S 02E3; 0078 # ˣ → x MODIFIER LETTER SMALL X → LATIN SMALL LETTER X 02E4; 0295 # ˤ → ʕ MODIFIER LETTER SMALL REVERSED GLOTTAL STOP → LATIN LETTER PHARYNGEAL VOICED FRICATIVE 1D2C; 0041 # ᴬ → A MODIFIER LETTER CAPITAL A → LATIN CAPITAL LETTER A 1D2D; 00C6 # ᴭ → Æ MODIFIER LETTER CAPITAL AE → LATIN CAPITAL LETTER AE 1D2E; 0042 # ᴮ → B MODIFIER LETTER CAPITAL B → LATIN CAPITAL LETTER B 1D30; 0044 # ᴰ → D MODIFIER LETTER CAPITAL D → LATIN CAPITAL LETTER D 1D31; 0045 # ᴱ → E MODIFIER LETTER CAPITAL E → LATIN CAPITAL LETTER E 1D32; 018E # ᴲ → Ǝ MODIFIER LETTER CAPITAL REVERSED E → LATIN CAPITAL LETTER REVERSED E 1D33; 0047 # ᴳ → G MODIFIER LETTER CAPITAL G → LATIN CAPITAL LETTER G 1D34; 0048 # ᴴ → H MODIFIER LETTER CAPITAL H → LATIN CAPITAL LETTER H 1D35; 0049 # ᴵ → I MODIFIER LETTER CAPITAL I → LATIN CAPITAL LETTER I 1D36; 004A # ᴶ → J MODIFIER LETTER CAPITAL J → LATIN CAPITAL LETTER J 1D37; 004B # ᴷ → K MODIFIER LETTER CAPITAL K → LATIN CAPITAL LETTER K 1D38; 004C # ᴸ → L MODIFIER LETTER CAPITAL L → LATIN CAPITAL LETTER L 1D39; 004D # ᴹ → M MODIFIER LETTER CAPITAL M → LATIN CAPITAL LETTER M 1D3A; 004E # ᴺ → N MODIFIER LETTER CAPITAL N → LATIN CAPITAL LETTER N 1D3C; 004F # ᴼ → O MODIFIER LETTER CAPITAL O → LATIN CAPITAL LETTER O 1D3D; 0222 # ᴽ → Ȣ MODIFIER LETTER CAPITAL OU → LATIN CAPITAL LETTER OU 1D3E; 0050 # ᴾ → P MODIFIER LETTER CAPITAL P → LATIN CAPITAL LETTER P 1D3F; 0052 # ᴿ → R MODIFIER LETTER CAPITAL R → LATIN CAPITAL LETTER R 1D40; 0054 # ᵀ → T MODIFIER LETTER CAPITAL T → LATIN CAPITAL LETTER T 1D41; 0055 # ᵁ → U MODIFIER LETTER CAPITAL U → LATIN CAPITAL LETTER U 1D42; 0057 # ᵂ → W MODIFIER LETTER CAPITAL W → LATIN CAPITAL LETTER W 1D43; 0061 # ᵃ → a MODIFIER LETTER SMALL A → LATIN SMALL LETTER A 1D44; 0250 # ᵄ → ɐ MODIFIER LETTER SMALL TURNED A → LATIN SMALL LETTER TURNED A 1D45; 0251 # ᵅ → ɑ MODIFIER LETTER SMALL ALPHA → LATIN SMALL LETTER ALPHA 1D46; 1D02 # ᵆ → ᴂ MODIFIER LETTER SMALL TURNED AE → LATIN SMALL LETTER TURNED AE 1D47; 0062 # ᵇ → b MODIFIER LETTER SMALL B → LATIN SMALL LETTER B 1D48; 0064 # ᵈ → d MODIFIER LETTER SMALL D → LATIN SMALL LETTER D 1D49; 0065 # ᵉ → e MODIFIER LETTER SMALL E → LATIN SMALL LETTER E 1D4A; 0259 # ᵊ → ə MODIFIER LETTER SMALL SCHWA → LATIN SMALL LETTER SCHWA 1D4B; 025B # ᵋ → ɛ MODIFIER LETTER SMALL OPEN E → LATIN SMALL LETTER OPEN E 1D4C; 025C # ᵌ → ɜ MODIFIER LETTER SMALL TURNED OPEN E → LATIN SMALL LETTER REVERSED OPEN E 1D4D; 0067 # ᵍ → g MODIFIER LETTER SMALL G → LATIN SMALL LETTER G 1D4F; 006B # ᵏ → k MODIFIER LETTER SMALL K → LATIN SMALL LETTER K 1D50; 006D # ᵐ → m MODIFIER LETTER SMALL M → LATIN SMALL LETTER M 1D51; 014B # ᵑ → ŋ MODIFIER LETTER SMALL ENG → LATIN SMALL LETTER ENG 1D52; 006F # ᵒ → o MODIFIER LETTER SMALL O → LATIN SMALL LETTER O 1D53; 0254 # ᵓ → ɔ MODIFIER LETTER SMALL OPEN O → LATIN SMALL LETTER OPEN O 1D54; 1D16 # ᵔ → ᴖ MODIFIER LETTER SMALL TOP HALF O → LATIN SMALL LETTER TOP HALF O 1D55; 1D17 # ᵕ → ᴗ MODIFIER LETTER SMALL BOTTOM HALF O → LATIN SMALL LETTER BOTTOM HALF O 1D56; 0070 # ᵖ → p MODIFIER LETTER SMALL P → LATIN SMALL LETTER P 1D57; 0074 # ᵗ → t MODIFIER LETTER SMALL T → LATIN SMALL LETTER T 1D58; 0075 # ᵘ → u MODIFIER LETTER SMALL U → LATIN SMALL LETTER U 1D59; 1D1D # ᵙ → ᴝ MODIFIER LETTER SMALL SIDEWAYS U → LATIN SMALL LETTER SIDEWAYS U 1D5A; 026F # ᵚ → ɯ MODIFIER LETTER SMALL TURNED M → LATIN SMALL LETTER TURNED M 1D5B; 0076 # ᵛ → v MODIFIER LETTER SMALL V → LATIN SMALL LETTER V 1D5C; 1D25 # ᵜ → ᴥ MODIFIER LETTER SMALL AIN → LATIN LETTER AIN 1D5D; 03B2 # ᵝ → β MODIFIER LETTER SMALL BETA → GREEK SMALL LETTER BETA 1D5E; 03B3 # ᵞ → γ MODIFIER LETTER SMALL GREEK GAMMA → GREEK SMALL LETTER GAMMA 1D5F; 03B4 # ᵟ → δ MODIFIER LETTER SMALL DELTA → GREEK SMALL LETTER DELTA 1D60; 03C6 # ᵠ → φ MODIFIER LETTER SMALL GREEK PHI → GREEK SMALL LETTER PHI 1D61; 03C7 # ᵡ → χ MODIFIER LETTER SMALL CHI → GREEK SMALL LETTER CHI 2070; 0030 # ⁰ → 0 SUPERSCRIPT ZERO → DIGIT ZERO 2071; 0069 # ⁱ → i SUPERSCRIPT LATIN SMALL LETTER I → LATIN SMALL LETTER I 2074; 0034 # ⁴ → 4 SUPERSCRIPT FOUR → DIGIT FOUR 2075; 0035 # ⁵ → 5 SUPERSCRIPT FIVE → DIGIT FIVE 2076; 0036 # ⁶ → 6 SUPERSCRIPT SIX → DIGIT SIX 2077; 0037 # ⁷ → 7 SUPERSCRIPT SEVEN → DIGIT SEVEN 2078; 0038 # ⁸ → 8 SUPERSCRIPT EIGHT → DIGIT EIGHT 2079; 0039 # ⁹ → 9 SUPERSCRIPT NINE → DIGIT NINE 207A; 002B # ⁺ → + SUPERSCRIPT PLUS SIGN → PLUS SIGN 207B; 2212 # ⁻ → − SUPERSCRIPT MINUS → MINUS SIGN 207C; 003D # ⁼ → = SUPERSCRIPT EQUALS SIGN → EQUALS SIGN 207D; 0028 # ⁽ → ( SUPERSCRIPT LEFT PARENTHESIS → LEFT PARENTHESIS 207E; 0029 # ⁾ → ) SUPERSCRIPT RIGHT PARENTHESIS → RIGHT PARENTHESIS 207F; 006E # ⁿ → n SUPERSCRIPT LATIN SMALL LETTER N → LATIN SMALL LETTER N 2120; 0053 004D # ℠ → SM SERVICE MARK → LATIN CAPITAL LETTER S, LATIN CAPITAL LETTER M 2122; 0054 004D # ™ → TM TRADE MARK SIGN → LATIN CAPITAL LETTER T, LATIN CAPITAL LETTER M 3192; 4E00 # ㆒ → 一 IDEOGRAPHIC ANNOTATION ONE MARK → CJK UNIFIED IDEOGRAPH-4E00 3193; 4E8C # ㆓ → 二 IDEOGRAPHIC ANNOTATION TWO MARK → CJK UNIFIED IDEOGRAPH-4E8C 3194; 4E09 # ㆔ → 三 IDEOGRAPHIC ANNOTATION THREE MARK → CJK UNIFIED IDEOGRAPH-4E09 3195; 56DB # ㆕ → 四 IDEOGRAPHIC ANNOTATION FOUR MARK → CJK UNIFIED IDEOGRAPH-56DB 3196; 4E0A # ㆖ → 上 IDEOGRAPHIC ANNOTATION TOP MARK → CJK UNIFIED IDEOGRAPH-4E0A 3197; 4E2D # ㆗ → 中 IDEOGRAPHIC ANNOTATION MIDDLE MARK → CJK UNIFIED IDEOGRAPH-4E2D 3198; 4E0B # ㆘ → 下 IDEOGRAPHIC ANNOTATION BOTTOM MARK → CJK UNIFIED IDEOGRAPH-4E0B 3199; 7532 # ㆙ → 甲 IDEOGRAPHIC ANNOTATION FIRST MARK → CJK UNIFIED IDEOGRAPH-7532 319A; 4E59 # ㆚ → 乙 IDEOGRAPHIC ANNOTATION SECOND MARK → CJK UNIFIED IDEOGRAPH-4E59 319B; 4E19 # ㆛ → 丙 IDEOGRAPHIC ANNOTATION THIRD MARK → CJK UNIFIED IDEOGRAPH-4E19 319C; 4E01 # ㆜ → 丁 IDEOGRAPHIC ANNOTATION FOURTH MARK → CJK UNIFIED IDEOGRAPH-4E01 319D; 5929 # ㆝ → 天 IDEOGRAPHIC ANNOTATION HEAVEN MARK → CJK UNIFIED IDEOGRAPH-5929 319E; 5730 # ㆞ → 地 IDEOGRAPHIC ANNOTATION EARTH MARK → CJK UNIFIED IDEOGRAPH-5730 319F; 4EBA # ㆟ → 人 IDEOGRAPHIC ANNOTATION MAN MARK → CJK UNIFIED IDEOGRAPH-4EBA # other characters that are superscripted forms 02C0; 0294 # ˀ → ʔ MODIFIER LETTER GLOTTAL STOP → LATIN LETTER GLOTTAL STOP 02C1; 0295 # ˁ → ʕ MODIFIER LETTER REVERSED GLOTTAL STOP → LATIN LETTER PHARYNGEAL VOICED FRICATIVE 06E5; 0648 # ۥ → و ARABIC SMALL WAW → ARABIC LETTER WAW 06E6; 064A # ۦ → ي ARABIC SMALL YEH → ARABIC LETTER YEH