Miscellaneous | Linguistic Elements | Collation | search | yi |
# root search rules for Symbols
&'='<'≠'
# root search rules for Arabic, Hebrew, plus two Hebrew-specific additions
&ا # 0627 ARABIC LETTER ALEF
<<<ﺎ<<<ﺍ # FE8E, FE8D: FINAL FORM, ISOLATED FORM
<<آ # 0622 ARABIC LETTER ALEF WITH MADDA ABOVE
<<<ﺂ<<<ﺁ # FE82, FE81: FINAL FORM, ISOLATED FORM
<<أ # 0623 ARABIC LETTER ALEF WITH HAMZA ABOVE
<<<ﺄ<<<ﺃ # FE84, FE83: FINAL FORM, ISOLATED FORM
<<إ # 0625 ARABIC LETTER ALEF WITH HAMZA BELOW
<<<ﺈ<<<ﺇ # FE88, FE87: FINAL FORM, ISOLATED FORM
&و # 0648 ARABIC LETTER WAW
<<<ۥ # 06E5: SMALL WAW
<<<ﻮ<<<ﻭ # FEEE, FEED: FINAL FORM, ISOLATED FORM
<<ؤ # 0624 ARABIC LETTER WAW WITH HAMZA ABOVE
<<<ﺆ<<<ﺅ # FE86, FE85: FINAL FORM, ISOLATED FORM
&ي # 064A ARABIC LETTER YEH
<<<ۦ # 06E6: ARABIC SMALL YEH
<<<ﻳ<<<ﻴ<<<ﻲ<<<ﻱ # FEF3, FEF4, FEF2, FEF1: INITIAL FORM, MEDIAL FORM, FINAL FORM, ISOLATED FORM
<<ئ # 0626 ARABIC LETTER YEH WITH HAMZA ABOVE
<<<ﺋ<<<ﺌ<<<ﺊ<<<ﺉ # FE8B, FE8C, FE8A, FE89: INITIAL FORM, MEDIAL FORM. FINAL FORM, ISOLATED FORM
<<ى # 0649 ARABIC LETTER ALEF MAKSURA
<<<ﯨ<<<ﯩ # FBE8, FBE9: UIGHUR KAZAKH KIRGHIZ ALEF MAKSURA INITIAL FORM, MEDIAL FORM
<<<ﻰ<<<ﻯ # FEF0, FEEF: FINAL FORM, ISOLATED FORM
&ه # 0647 ARABIC LETTER HEH
<<<ﻫ<<<ﻬ<<<ﻪ<<<ﻩ # FEEB, FEEC, FEEA, FEE9: INITIAL FORM, MEDIAL FORM, FINAL FORM;, ISOLATED FORM
<<ة # 0629 ARABIC LETTER TEH MARBUTA
<<<ﺔ<<<ﺓ # FE94, FE93: FINAL FORM, ISOLATED FORM
&[last primary ignorable]<<׳ # 05F3 HEBREW PUNCTUATION GERESH, ignorable
<<'' # APOSTROPHE, Hebrew-specific addition, should match GERESH
<<״ # 05F4 HEBREW PUNCTUATION GERSHAYIM, ignorable
<<'\"' # QUOTATION MARK, Hebrew-specific addition, should match GERSHAYIM
<<ـ # 0640 ARABIC TATWEEL
# Don't need explicit entries for 064B - 0652 ARABIC FATHATAN - ARABIC SUKUN;
# these are already ignorable at level 1, and are not involved in contractions
<<ฺ # 0E3A THAI CHARACTER PHINTHU
# root search rules for modern Korean jamos
# Korean modern complex consonants, decompose: x(L) = CHOSEONG x, x(T) = JONGSEONG x
&ᄀ # 1100 KIYEOK(L) = 11A8 KIYEOK(T)
=ᆨ
&ᄀᄀ # 1100 KIYEOK(L) + 1100 KIYEOK(L) = 1101 SSANGKIYEOK(L) = 11A9 SSANGKIYEOK(T)
=ᄁ=ᆩ
&ᄀᄉ # 1100 KIYEOK(L) + 1109 SIOS(L) = 11AA KIYEOK-SIOS(T)
=ᆪ
&ᄂ # 1102 NIEUN(L) = 11AB NIEUN(T)
=ᆫ
&ᄂᄌ # 1102 NIEUN(L) + 110C CIEUC(L) = 11AC NIEUN-CIEUC(T), also archaic 115C NIEUN-CIEUC(L)
=ᆬ
&ᄂᄒ # 1102 NIEUN(L) + 1112 HIEUH(L) = 11AD NIEUN-HIEUH(T), also archaic 115D NIEUN-HIEUH(L)
=ᆭ
&ᄃ # 1103 TIKEUT(L) = 11AE TIKEUT(T)
=ᆮ
&ᄃᄃ # 1103 TIKEUT(L) + 1103 TIKEUT(L) = 1104 SSANGTIKEUT(L)
=ᄄ
&ᄅ # 1105 RIEUL(L) = 11AF RIEUL(T)
=ᆯ
&ᄅᄀ # 1105 RIEUL(L) + 1100 KIYEOK(L) = 11B0 RIEUL-KIYEOK(T)
=ᆰ
&ᄅᄆ # 1105 RIEUL(L) + 1106 MIEUM(L) = 11B1 RIEUL-MIEUM(T)
=ᆱ
&ᄅᄇ # 1105 RIEUL(L) + 1107 PIEUP(L) = 11B2 RIEUL-PIEUP(T)
=ᆲ
&ᄅᄉ # 1105 RIEUL(L) + 1109 SIOS(L) = 11B3 RIEUL-SIOS(T)
=ᆳ
&ᄅᄐ # 1105 RIEUL(L) + 1110 THIEUTH(L) = 11B4 RIEUL-THIEUTH(T)
=ᆴ
&ᄅᄑ # 1105 RIEUL(L) + 1111 PHIEUPH(L) = 11B5 RIEUL-PHIEUPH(T)
=ᆵ
&ᄅᄒ # 1105 RIEUL(L) + 1112 HIEUH(L) = 11B6 RIEUL-HIEUH(T), also archic 111A RIEUL-HIEUH(L)
=ᆶ
&ᄆ # 1106 MIEUM(L) = 11B7 MIEUM(T)
=ᆷ
&ᄇ # 1107 PIEUP(L) = 11B8 PIEUP(T)
=ᆸ
&ᄇᄇ # 1107 PIEUP(L) + 1107 PIEUP(L) = 1108 SSANGPIEUP(L)
=ᄈ
&ᄇᄉ # 1107 PIEUP(L) + 1109 SIOS(L) = 11B9 PIEUP-SIOS(T), also archaic 1121 PIEUP-SIOS(L)
=ᆹ
&ᄉ # 1109 SIOS(L) = 11BA SIOS(T)
=ᆺ
&ᄉᄉ # 1109 SIOS(L) + 1109 SIOS(L) = 110A SSANGSIOS(L) = 11BB SSANGSIOS(T)
=ᄊ=ᆻ
&ᄋ # 110B IEUNG(L) = 11BC IEUNG(T)
=ᆼ
&ᄌ # 110C CIEUC(L) = 11BD CIEUC(T)
=ᆽ
&ᄌᄌ # 110C CIEUC(L) + 110C CIEUC(L) = 110D SSANGCIEUC(L)
=ᄍ
&ᄎ # 110E CHIEUCH(L) = 11BE CHIEUCH(T)
=ᆾ
&ᄏ # 110F KHIEUKH(L) = 11BF KHIEUKH(T)
=ᆿ
&ᄐ # 1110 THIEUTH(L) = 11C0 THIEUTH(T)
=ᇀ
&ᄑ # 1111 PHIEUPH(L) = 11C1 PHIEUPH(T)
=ᇁ
&ᄒ # 1112 HIEUH(L) = 11C2 HIEUH(T)
=ᇂ
# Korean modern complex vowels, decompose
&ᅡᅵ # 1161 A(V) + 1175 I(V) = 1162 AE(V)
=ᅢ
&ᅣᅵ # 1163 YA(V) + 1175 I(V) = 1164 YAE(V)
=ᅤ
&ᅥᅵ # 1165 EO(V) + 1175 I(V) = 1166 E(V)
=ᅦ
&ᅧᅵ # 1167 YEO(V) + 1175 I(V) = 1168 YE(V)
=ᅨ
&ᅩᅡ # 1169 O(V) + 1161 A(V) = 116A WA(V)
=ᅪ
&ᅩᅡᅵ # 1169 O(V) + 1161 A(V) + 1175 I(V) = 116B WAE(V)
=ᅫ
&ᅩᅵ # 1169 O(V) + 1175 I(V) = 116C OE(V)
=ᅬ
&ᅮᅴ # 116E U(V) + 1174 YI(V) = 116F WEO(V)
=ᅯ
&ᅮᅴᅵ # 116E U(V) + 1174 YI(V) + 1175 I(V) = 1170 WE(V)
=ᅰ
&ᅮᅵ # 116E U(V) + 1175 I(V) = 1171 WI(V)
=ᅱ
|
&׳ # 05F3 HEBREW PUNCTUATION GERESH, ignorable
<<'' # APOSTROPHE, Hebrew-specific addition, should match GERESH
&״ # 05F4 HEBREW PUNCTUATION GERSHAYIM, ignorable
<<'\"' # QUOTATION MARK, Hebrew-specific addition, should match GERSHAYIM
|