diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 6dcbf10c7..c9a431d86 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -298,6 +298,7 @@ FFF0..FFFF; Specials 16A70..16ACF; Tangsa 16AD0..16AFF; Bassa Vah 16B00..16B8F; Pahawh Hmong +16D40..16D7F; Kirat Rai 16E40..16E9F; Medefaidrin 16F00..16F9F; Miao 16FE0..16FFF; Ideographic Symbols and Punctuation diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index a0de787d6..c396d009c 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-16.0.0.txt -# Date: 2023-10-24, 21:03:11 GMT +# Date: 2023-10-25, 12:52:16 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2023,11 +2023,12 @@ A7CB..A7CD ; 16.0 # [3] LATIN CAPITAL LETTER RAMS HORN..LATIN SMALL LETTER 116D0..116E3 ; 16.0 # [20] MYANMAR PAO DIGIT ZERO..MYANMAR EASTERN PWO KAREN DIGIT NINE 11BC0..11BE1 ; 16.0 # [34] SUNUWAR LETTER DEVI..SUNUWAR SIGN PVO 11BF0..11BF9 ; 16.0 # [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE +16D40..16D79 ; 16.0 # [58] KIRAT RAI SIGN ANUSVARA..KIRAT RAI DIGIT NINE 1CEB0..1CEB3 ; 16.0 # [4] HORIZONTAL ZIGZAG LINE..BLACK RIGHT TRIANGLE CARET 1E5D0..1E5FA ; 16.0 # [43] OL ONAL LETTER O..OL ONAL DIGIT NINE 1E5FF ; 16.0 # OL ONAL ABBREVIATION SIGN 1F8B2 ; 16.0 # RIGHTWARDS ARROW WITH LOWER HOOK -# Total code points: 246 +# Total code points: 304 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 5d2157ef5..2e73593f4 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-16.0.0.txt -# Date: 2023-10-24, 21:03:37 GMT +# Date: 2023-10-25, 12:52:46 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1286,6 +1286,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16B40..16B43 ; Alphabetic # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; Alphabetic # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; Alphabetic # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; Alphabetic # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; Alphabetic # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; Alphabetic # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16E40..16E7F ; Alphabetic # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; Alphabetic # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; Alphabetic # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -1417,7 +1420,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 138567 +# Total code points: 138612 # ================================================ @@ -3420,6 +3423,8 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 16AF0..16AF4 ; Case_Ignorable # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Case_Ignorable # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM +16D40..16D42 ; Case_Ignorable # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D6B..16D6C ; Case_Ignorable # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16F4F ; Case_Ignorable # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Case_Ignorable # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Case_Ignorable # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -3467,7 +3472,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2718 +# Total code points: 2723 # ================================================ @@ -6791,6 +6796,9 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16B40..16B43 ; ID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; ID_Start # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; ID_Start # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; ID_Start # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; ID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; ID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16E40..16E7F ; ID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION @@ -6907,7 +6915,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 137144 +# Total code points: 137189 # ================================================ @@ -8125,6 +8133,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16B50..16B59 ; ID_Continue # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16B63..16B77 ; ID_Continue # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; ID_Continue # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; ID_Continue # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; ID_Continue # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; ID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D70..16D79 ; ID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; ID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; ID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -8283,7 +8295,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140344 +# Total code points: 140399 # ================================================ @@ -8933,6 +8945,9 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16B40..16B43 ; XID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; XID_Start # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; XID_Start # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; XID_Start # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; XID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; XID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16E40..16E7F ; XID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; XID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION @@ -9049,7 +9064,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 137121 +# Total code points: 137166 # ================================================ @@ -10268,6 +10283,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16B50..16B59 ; XID_Continue # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16B63..16B77 ; XID_Continue # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; XID_Continue # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; XID_Continue # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; XID_Continue # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; XID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D70..16D79 ; XID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; XID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; XID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; XID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -10426,7 +10445,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140325 +# Total code points: 140380 # ================================================ @@ -12422,6 +12441,11 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 16B5B..16B61 ; Grapheme_Base # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; Grapheme_Base # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; Grapheme_Base # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; Grapheme_Base # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; Grapheme_Base # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; Grapheme_Base # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D..16D6F ; Grapheme_Base # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; Grapheme_Base # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; Grapheme_Base # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; Grapheme_Base # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; Grapheme_Base # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -12638,7 +12662,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 147850 +# Total code points: 147908 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 4a18ccf91..876faa2eb 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ # DerivedNormalizationProps-16.0.0.txt -# Date: 2023-10-24, 18:13:45 GMT +# Date: 2023-10-25, 12:52:52 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -992,11 +992,12 @@ FB46..FB4E ; NFD_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 114BE ; NFD_QC; N # Mc TIRHUTA VOWEL SIGN AU 115BA..115BB ; NFD_QC; N # Mc [2] SIDDHAM VOWEL SIGN O..SIDDHAM VOWEL SIGN AU 11938 ; NFD_QC; N # Mc DIVES AKURU VOWEL SIGN O +16D68..16D6A ; NFD_QC; N # Lo [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU 1D15E..1D164 ; NFD_QC; N # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; NFD_QC; N # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 2F800..2FA1D ; NFD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 13235 +# Total code points: 13238 # ================================================ @@ -1135,8 +1136,9 @@ FB46..FB4E ; NFC_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 114BD ; NFC_QC; M # Mc TIRHUTA VOWEL SIGN SHORT O 115AF ; NFC_QC; M # Mc SIDDHAM VOWEL SIGN AA 11930 ; NFC_QC; M # Mc DIVES AKURU VOWEL SIGN AA +16D67 ; NFC_QC; M # Lo KIRAT RAI VOWEL SIGN E -# Total code points: 111 +# Total code points: 112 # ================================================ @@ -1613,6 +1615,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 114BE ; NFKD_QC; N # Mc TIRHUTA VOWEL SIGN AU 115BA..115BB ; NFKD_QC; N # Mc [2] SIDDHAM VOWEL SIGN O..SIDDHAM VOWEL SIGN AU 11938 ; NFKD_QC; N # Mc DIVES AKURU VOWEL SIGN O +16D68..16D6A ; NFKD_QC; N # Lo [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU 1D15E..1D164 ; NFKD_QC; N # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; NFKD_QC; N # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 1D400..1D454 ; NFKD_QC; N # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G @@ -1702,7 +1705,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKD_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 17031 +# Total code points: 17034 # ================================================ @@ -2160,8 +2163,9 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 114BD ; NFKC_QC; M # Mc TIRHUTA VOWEL SIGN SHORT O 115AF ; NFKC_QC; M # Mc SIDDHAM VOWEL SIGN AA 11930 ; NFKC_QC; M # Mc DIVES AKURU VOWEL SIGN AA +16D67 ; NFKC_QC; M # Lo KIRAT RAI VOWEL SIGN E -# Total code points: 111 +# Total code points: 112 # ================================================ @@ -2394,10 +2398,11 @@ FB46..FB4E ; Expands_On_NFD # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBRE 114BE ; Expands_On_NFD # Mc TIRHUTA VOWEL SIGN AU 115BA..115BB ; Expands_On_NFD # Mc [2] SIDDHAM VOWEL SIGN O..SIDDHAM VOWEL SIGN AU 11938 ; Expands_On_NFD # Mc DIVES AKURU VOWEL SIGN O +16D68..16D6A ; Expands_On_NFD # Lo [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU 1D15E..1D164 ; Expands_On_NFD # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; Expands_On_NFD # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK -# Total code points: 12218 +# Total code points: 12221 # ================================================ @@ -2750,6 +2755,7 @@ FFE3 ; Expands_On_NFKD # Sk FULLWIDTH MACRON 114BE ; Expands_On_NFKD # Mc TIRHUTA VOWEL SIGN AU 115BA..115BB ; Expands_On_NFKD # Mc [2] SIDDHAM VOWEL SIGN O..SIDDHAM VOWEL SIGN AU 11938 ; Expands_On_NFKD # Mc DIVES AKURU VOWEL SIGN O +16D68..16D6A ; Expands_On_NFKD # Lo [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU 1D15E..1D164 ; Expands_On_NFKD # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; Expands_On_NFKD # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 1F100..1F10A ; Expands_On_NFKD # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA @@ -2762,7 +2768,7 @@ FFE3 ; Expands_On_NFKD # Sk FULLWIDTH MACRON 1F213 ; Expands_On_NFKD # So SQUARED KATAKANA DE 1F240..1F248 ; Expands_On_NFKD # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 -# Total code points: 13392 +# Total code points: 13395 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index add68d076..96bbaecc1 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2023-10-24, 21:03:43 GMT +# Date: 2023-10-25, 12:52:55 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2307,6 +2307,11 @@ FFFD ; A # So REPLACEMENT CHARACTER 16B5B..16B61 ; N # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; N # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; N # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; N # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; N # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; N # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D..16D6F ; N # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; N # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; N # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; N # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; N # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH diff --git a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt index 9b5aabfa0..d29c2eec9 100644 --- a/unicodetools/data/ucd/dev/IndicPositionalCategory.txt +++ b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt @@ -1,5 +1,5 @@ # IndicPositionalCategory-16.0.0.txt -# Date: 2023-10-02, 22:58:33 GMT +# Date: 2023-10-24, 20:42:05 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -83,7 +83,7 @@ # list of Indic scripts, including those which do not have # positional characters. Currently, those additional # Indic scripts without positional characters are -# Multani, Phags-pa, and Tai Le. +# Kirat Rai, Multani, Phags-pa, and Tai Le. # # Notes: # diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index 5de0d7554..2cc7ff452 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,5 +1,5 @@ # IndicSyllabicCategory-16.0.0.txt -# Date: 2023-10-02, 22:58:33 GMT +# Date: 2023-10-24, 20:42:05 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -38,7 +38,7 @@ # Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, # Chakma, Cham, Devanagari, Dives Akuru, Dogra, Grantha, Gujarati, # Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada, Kawi, -# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Lepcha, Limbu, +# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Kirat Rai, Lao, Lepcha, Limbu, # Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meetei Mayek, # Modi, Multani, Myanmar, Nandinagari, Newa, New Tai Lue, Oriya, # Phags-pa, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Soyombo, @@ -135,6 +135,7 @@ A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 11D40 ; Bindu # Mn MASARAM GONDI SIGN ANUSVARA 11D95 ; Bindu # Mn GUNJALA GONDI SIGN ANUSVARA 11F00..11F01 ; Bindu # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +16D40..16D41 ; Bindu # Lm [2] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN TONPI # ================================================ @@ -182,6 +183,7 @@ AAF5 ; Visarga # Mc MEETEI MAYEK VOWEL SIGN VISARGA 11D41 ; Visarga # Mn MASARAM GONDI SIGN VISARGA 11D96 ; Visarga # Mc GUNJALA GONDI SIGN VISARGA 11F03 ; Visarga # Mc KAWI SIGN VISARGA +16D42 ; Visarga # Lm KIRAT RAI SIGN VISARGA # ================================================ @@ -324,6 +326,7 @@ ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK 11A34 ; Pure_Killer # Mn ZANABAZAR SQUARE SIGN VIRAMA 11D44 ; Pure_Killer # Mn MASARAM GONDI SIGN HALANTA 11F41 ; Pure_Killer # Mc KAWI SIGN KILLER +16D6B..16D6C ; Pure_Killer # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT # ================================================ @@ -712,6 +715,7 @@ ABE9..ABEA ; Vowel_Dependent # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEET 11F36..11F3A ; Vowel_Dependent # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R 11F3E..11F3F ; Vowel_Dependent # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI 11F40 ; Vowel_Dependent # Mn KAWI VOWEL SIGN EU +16D63..16D6A ; Vowel_Dependent # Lo [8] KIRAT RAI VOWEL SIGN AA..KIRAT RAI VOWEL SIGN AU # ================================================ @@ -922,6 +926,7 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE 11D6C..11D89 ; Consonant # Lo [30] GUNJALA GONDI LETTER YA..GUNJALA GONDI LETTER SA 11EE0..11EF1 ; Consonant # Lo [18] MAKASAR LETTER KA..MAKASAR LETTER A 11F12..11F33 ; Consonant # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +16D43..16D62 ; Consonant # Lo [32] KIRAT RAI LETTER A..KIRAT RAI LETTER HA # ================================================ @@ -1326,6 +1331,7 @@ ABF0..ABF9 ; Number # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI 11D50..11D59 ; Number # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; Number # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 11F50..11F59 ; Number # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE +16D70..16D79 ; Number # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE # ================================================ diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index daea5c0ac..dc75435f1 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2023-10-24, 21:03:44 GMT +# Date: 2023-10-25, 12:52:56 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3211,6 +3211,12 @@ FFFD ; AI # So REPLACEMENT CHARACTER 16B5B..16B61 ; AL # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; AL # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; AL # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; AL # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; AL # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; AL # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D ; AL # Po KIRAT RAI SIGN YUPI +16D6E..16D6F ; BA # Po [2] KIRAT RAI DANDA..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; AL # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; AL # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E98 ; BA # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 86f666856..07618575c 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-16.0.0.txt -# Date: 2023-10-24, 21:03:47 GMT +# Date: 2023-10-25, 12:53:00 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -15201,6 +15201,9 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 115BA;115BA;115B8 115AF;115BA;115B8 115AF; # (𑖺; 𑖺; 𑖺; 𑖺; 𑖺; ) SIDDHAM VOWEL SIGN O 115BB;115BB;115B9 115AF;115BB;115B9 115AF; # (𑖻; 𑖻; 𑖻; 𑖻; 𑖻; ) SIDDHAM VOWEL SIGN AU 11938;11938;11935 11930;11938;11935 11930; # (𑤸; 𑤸; 𑤸; 𑤸; 𑤸; ) DIVES AKURU VOWEL SIGN O +16D68;16D68;16D67 16D67;16D68;16D67 16D67; # (𖵨; 𖵨; 𖵨; 𖵨; 𖵨; ) KIRAT RAI VOWEL SIGN AI +16D69;16D69;16D63 16D67;16D69;16D63 16D67; # (𖵩; 𖵩; 𖵩; 𖵩; 𖵩; ) KIRAT RAI VOWEL SIGN O +16D6A;16D6A;16D63 16D67 16D67;16D6A;16D63 16D67 16D67; # (𖵪; 𖵪; 𖵪; 𖵪; 𖵪; ) KIRAT RAI VOWEL SIGN AU 1D15E;1D157 1D165;1D157 1D165;1D157 1D165;1D157 1D165; # (𝅗𝅥; 𝅗𝅥; 𝅗𝅥; 𝅗𝅥; 𝅗𝅥; ) MUSICAL SYMBOL HALF NOTE 1D15F;1D158 1D165;1D158 1D165;1D158 1D165;1D158 1D165; # (𝅘𝅥; 𝅘𝅥; 𝅘𝅥; 𝅘𝅥; 𝅘𝅥; ) MUSICAL SYMBOL QUARTER NOTE 1D160;1D158 1D165 1D16E;1D158 1D165 1D16E;1D158 1D165 1D16E;1D158 1D165 1D16E; # (𝅘𝅥𝅮; 𝅘𝅥𝅮; 𝅘𝅥𝅮; 𝅘𝅥𝅮; 𝅘𝅥𝅮; ) MUSICAL SYMBOL EIGHTH NOTE @@ -19143,5 +19146,8 @@ D750 0334 11B5;D750 0334 11B5;1112 1173 0334 11B5;D750 0334 11B5;1112 1173 0334 115B8 0334 115AF;115B8 0334 115AF;115B8 0334 115AF;115B8 0334 115AF;115B8 0334 115AF; # (𑖸◌̴𑖯; 𑖸◌̴𑖯; 𑖸◌̴𑖯; 𑖸◌̴𑖯; 𑖸◌̴𑖯; ) SIDDHAM VOWEL SIGN E, COMBINING TILDE OVERLAY, SIDDHAM VOWEL SIGN AA 115B9 0334 115AF;115B9 0334 115AF;115B9 0334 115AF;115B9 0334 115AF;115B9 0334 115AF; # (𑖹◌̴𑖯; 𑖹◌̴𑖯; 𑖹◌̴𑖯; 𑖹◌̴𑖯; 𑖹◌̴𑖯; ) SIDDHAM VOWEL SIGN AI, COMBINING TILDE OVERLAY, SIDDHAM VOWEL SIGN AA 11935 0334 11930;11935 0334 11930;11935 0334 11930;11935 0334 11930;11935 0334 11930; # (𑤵◌̴𑤰; 𑤵◌̴𑤰; 𑤵◌̴𑤰; 𑤵◌̴𑤰; 𑤵◌̴𑤰; ) DIVES AKURU VOWEL SIGN E, COMBINING TILDE OVERLAY, DIVES AKURU VOWEL SIGN AA +16D63 0334 16D67;16D63 0334 16D67;16D63 0334 16D67;16D63 0334 16D67;16D63 0334 16D67; # (𖵣◌̴𖵧; 𖵣◌̴𖵧; 𖵣◌̴𖵧; 𖵣◌̴𖵧; 𖵣◌̴𖵧; ) KIRAT RAI VOWEL SIGN AA, COMBINING TILDE OVERLAY, KIRAT RAI VOWEL SIGN E +16D67 0334 16D67;16D67 0334 16D67;16D67 0334 16D67;16D67 0334 16D67;16D67 0334 16D67; # (𖵧◌̴𖵧; 𖵧◌̴𖵧; 𖵧◌̴𖵧; 𖵧◌̴𖵧; 𖵧◌̴𖵧; ) KIRAT RAI VOWEL SIGN E, COMBINING TILDE OVERLAY, KIRAT RAI VOWEL SIGN E +16D69 0334 16D67;16D69 0334 16D67;16D63 16D67 0334 16D67;16D69 0334 16D67;16D63 16D67 0334 16D67; # (𖵩◌̴𖵧; 𖵩◌̴𖵧; 𖵩◌̴𖵧; 𖵩◌̴𖵧; 𖵩◌̴𖵧; ) KIRAT RAI VOWEL SIGN O, COMBINING TILDE OVERLAY, KIRAT RAI VOWEL SIGN E # # EOF diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 0e34fbc04..a07d784e8 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-16.0.0.txt -# Date: 2023-10-24, 21:03:50 GMT +# Date: 2023-10-25, 12:53:04 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -313,6 +313,7 @@ blk; Khmer ; Khmer blk; Khmer_Symbols ; Khmer_Symbols blk; Khojki ; Khojki blk; Khudawadi ; Khudawadi +blk; Kirat_Rai ; Kirat_Rai blk; Lao ; Lao blk; Latin_1_Sup ; Latin_1_Supplement ; Latin_1 blk; Latin_Ext_A ; Latin_Extended_A @@ -1364,6 +1365,7 @@ sc ; Khmr ; Khmer sc ; Khoj ; Khojki sc ; Kits ; Khitan_Small_Script sc ; Knda ; Kannada +sc ; Krai ; Kirat_Rai sc ; Kthi ; Kaithi sc ; Lana ; Tai_Tham sc ; Laoo ; Lao diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 376dac297..800611d20 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-16.0.0.txt -# Date: 2023-10-24, 21:04:04 GMT +# Date: 2023-10-25, 12:53:25 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3050,6 +3050,16 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # ================================================ +16D40..16D42 ; Kirat_Rai # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; Kirat_Rai # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; Kirat_Rai # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D..16D6F ; Kirat_Rai # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; Kirat_Rai # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE + +# Total code points: 58 + +# ================================================ + 1E5D0..1E5ED ; Ol_Onal # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG 1E5EE..1E5EF ; Ol_Onal # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E5F0 ; Ol_Onal # Lo OL ONAL SIGN HODDOND diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 20da9b7d8..9c89d3d50 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -25832,6 +25832,64 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 16B8D;PAHAWH HMONG CLAN SIGN TSWB;Lo;0;L;;;;;N;;;;; 16B8E;PAHAWH HMONG CLAN SIGN KWM;Lo;0;L;;;;;N;;;;; 16B8F;PAHAWH HMONG CLAN SIGN VWJ;Lo;0;L;;;;;N;;;;; +16D40;KIRAT RAI SIGN ANUSVARA;Lm;0;L;;;;;N;;;;; +16D41;KIRAT RAI SIGN TONPI;Lm;0;L;;;;;N;;;;; +16D42;KIRAT RAI SIGN VISARGA;Lm;0;L;;;;;N;;;;; +16D43;KIRAT RAI LETTER A;Lo;0;L;;;;;N;;;;; +16D44;KIRAT RAI LETTER KA;Lo;0;L;;;;;N;;;;; +16D45;KIRAT RAI LETTER KHA;Lo;0;L;;;;;N;;;;; +16D46;KIRAT RAI LETTER GA;Lo;0;L;;;;;N;;;;; +16D47;KIRAT RAI LETTER GHA;Lo;0;L;;;;;N;;;;; +16D48;KIRAT RAI LETTER NGA;Lo;0;L;;;;;N;;;;; +16D49;KIRAT RAI LETTER CA;Lo;0;L;;;;;N;;;;; +16D4A;KIRAT RAI LETTER CHA;Lo;0;L;;;;;N;;;;; +16D4B;KIRAT RAI LETTER JA;Lo;0;L;;;;;N;;;;; +16D4C;KIRAT RAI LETTER JHA;Lo;0;L;;;;;N;;;;; +16D4D;KIRAT RAI LETTER NYA;Lo;0;L;;;;;N;;;;; +16D4E;KIRAT RAI LETTER TTA;Lo;0;L;;;;;N;;;;; +16D4F;KIRAT RAI LETTER TTHA;Lo;0;L;;;;;N;;;;; +16D50;KIRAT RAI LETTER DDA;Lo;0;L;;;;;N;;;;; +16D51;KIRAT RAI LETTER DDHA;Lo;0;L;;;;;N;;;;; +16D52;KIRAT RAI LETTER TA;Lo;0;L;;;;;N;;;;; +16D53;KIRAT RAI LETTER THA;Lo;0;L;;;;;N;;;;; +16D54;KIRAT RAI LETTER DA;Lo;0;L;;;;;N;;;;; +16D55;KIRAT RAI LETTER DHA;Lo;0;L;;;;;N;;;;; +16D56;KIRAT RAI LETTER NA;Lo;0;L;;;;;N;;;;; +16D57;KIRAT RAI LETTER PA;Lo;0;L;;;;;N;;;;; +16D58;KIRAT RAI LETTER PHA;Lo;0;L;;;;;N;;;;; +16D59;KIRAT RAI LETTER BA;Lo;0;L;;;;;N;;;;; +16D5A;KIRAT RAI LETTER BHA;Lo;0;L;;;;;N;;;;; +16D5B;KIRAT RAI LETTER MA;Lo;0;L;;;;;N;;;;; +16D5C;KIRAT RAI LETTER YA;Lo;0;L;;;;;N;;;;; +16D5D;KIRAT RAI LETTER RA;Lo;0;L;;;;;N;;;;; +16D5E;KIRAT RAI LETTER LA;Lo;0;L;;;;;N;;;;; +16D5F;KIRAT RAI LETTER VA;Lo;0;L;;;;;N;;;;; +16D60;KIRAT RAI LETTER SA;Lo;0;L;;;;;N;;;;; +16D61;KIRAT RAI LETTER SHA;Lo;0;L;;;;;N;;;;; +16D62;KIRAT RAI LETTER HA;Lo;0;L;;;;;N;;;;; +16D63;KIRAT RAI VOWEL SIGN AA;Lo;0;L;;;;;N;;;;; +16D64;KIRAT RAI VOWEL SIGN I;Lo;0;L;;;;;N;;;;; +16D65;KIRAT RAI VOWEL SIGN U;Lo;0;L;;;;;N;;;;; +16D66;KIRAT RAI VOWEL SIGN UE;Lo;0;L;;;;;N;;;;; +16D67;KIRAT RAI VOWEL SIGN E;Lo;0;L;;;;;N;;;;; +16D68;KIRAT RAI VOWEL SIGN AI;Lo;0;L;16D67 16D67;;;;N;;;;; +16D69;KIRAT RAI VOWEL SIGN O;Lo;0;L;16D63 16D67;;;;N;;;;; +16D6A;KIRAT RAI VOWEL SIGN AU;Lo;0;L;16D69 16D67;;;;N;;;;; +16D6B;KIRAT RAI SIGN VIRAMA;Lm;0;L;;;;;N;;;;; +16D6C;KIRAT RAI SIGN SAAT;Lm;0;L;;;;;N;;;;; +16D6D;KIRAT RAI SIGN YUPI;Po;0;L;;;;;N;;;;; +16D6E;KIRAT RAI DANDA;Po;0;L;;;;;N;;;;; +16D6F;KIRAT RAI DOUBLE DANDA;Po;0;L;;;;;N;;;;; +16D70;KIRAT RAI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +16D71;KIRAT RAI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +16D72;KIRAT RAI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +16D73;KIRAT RAI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +16D74;KIRAT RAI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +16D75;KIRAT RAI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +16D76;KIRAT RAI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +16D77;KIRAT RAI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +16D78;KIRAT RAI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +16D79;KIRAT RAI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 16E40;MEDEFAIDRIN CAPITAL LETTER M;Lu;0;L;;;;;N;;;;16E60; 16E41;MEDEFAIDRIN CAPITAL LETTER S;Lu;0;L;;;;;N;;;;16E61; 16E42;MEDEFAIDRIN CAPITAL LETTER V;Lu;0;L;;;;;N;;;;16E62; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 08b73924c..4219b2fbf 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-10-24, 21:04:08 GMT +# Date: 2023-10-25, 12:53:29 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2137,6 +2137,11 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 16B5B..16B61 ; R # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; R # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; R # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; R # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; R # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; R # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D..16D6F ; R # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; R # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; R # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; R # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; R # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index 058e3bb76..2d25d9af1 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-16.0.0.txt -# Date: 2023-10-24, 21:03:44 GMT +# Date: 2023-10-25, 12:52:55 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -650,8 +650,10 @@ A960..A97C ; L # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANG 1160..11A7 ; V # Lo [72] HANGUL JUNGSEONG FILLER..HANGUL JUNGSEONG O-YAE D7B0..D7C6 ; V # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAEA-E +16D63 ; V # Lo KIRAT RAI VOWEL SIGN AA +16D67..16D6A ; V # Lo [4] KIRAT RAI VOWEL SIGN E..KIRAT RAI VOWEL SIGN AU -# Total code points: 95 +# Total code points: 100 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index c1fd23e22..17e9ced38 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-16.0.0.txt -# Date: 2023-10-24, 21:04:05 GMT +# Date: 2023-10-25, 12:53:26 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2473,6 +2473,9 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16B40..16B43 ; OLetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; OLetter # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; OLetter # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; OLetter # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; OLetter # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; OLetter # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16F00..16F4A ; OLetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; OLetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -2553,7 +2556,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132786 +# Total code points: 132831 # ================================================ @@ -2625,6 +2628,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +16D70..16D79 ; Numeric # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE @@ -2633,7 +2637,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 744 +# Total code points: 754 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 62f655d99..65682200c 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-16.0.0.txt -# Date: 2023-10-24, 21:04:08 GMT +# Date: 2023-10-25, 12:53:29 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1228,6 +1228,9 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16B40..16B43 ; ALetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; ALetter # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; ALetter # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; ALetter # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; ALetter # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; ALetter # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16E40..16E7F ; ALetter # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F4A ; ALetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; ALetter # Lo MIAO LETTER NASALIZATION @@ -1326,7 +1329,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 29667 +# Total code points: 29712 # ================================================ @@ -1443,6 +1446,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +16D70..16D79 ; Numeric # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE @@ -1451,7 +1455,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 743 +# Total code points: 753 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index b3216b731..2a39d1660 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2023-10-24, 21:03:35 GMT +# Date: 2023-10-25, 12:52:43 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1067,6 +1067,11 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 16B5B..16B61 ; L # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; L # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; L # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; L # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; L # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; L # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D..16D6F ; L # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; L # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; L # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; L # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; L # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -1192,7 +1197,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 820290 code points not listed here. +# The above property value applies to 820232 code points not listed here. # Total code points: 1096260 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index c3ef6239a..475a4338a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-16.0.0.txt -# Date: 2023-10-24, 21:03:36 GMT +# Date: 2023-10-25, 12:52:46 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1794,6 +1794,11 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B5B..16B61 ; 0 # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; 0 # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; 0 # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; 0 # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; 0 # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; 0 # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D..16D6F ; 0 # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; 0 # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; 0 # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; 0 # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; 0 # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -2026,7 +2031,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 826520 code points not listed here. +# The above property value applies to 826462 code points not listed here. # Total code points: 1113182 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt index b1789d11f..c173fc1dd 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt @@ -1,5 +1,5 @@ # DerivedDecompositionType-16.0.0.txt -# Date: 2023-10-16, 14:22:23 GMT +# Date: 2023-10-25, 12:52:48 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -260,11 +260,12 @@ FB46..FB4E ; Canonical # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 114BE ; Canonical # Mc TIRHUTA VOWEL SIGN AU 115BA..115BB ; Canonical # Mc [2] SIDDHAM VOWEL SIGN O..SIDDHAM VOWEL SIGN AU 11938 ; Canonical # Mc DIVES AKURU VOWEL SIGN O +16D68..16D6A ; Canonical # Lo [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU 1D15E..1D164 ; Canonical # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; Canonical # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 2F800..2FA1D ; Canonical # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 13235 +# Total code points: 13238 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index b9c329c1d..b9b084bdd 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-16.0.0.txt -# Date: 2023-10-24, 21:03:39 GMT +# Date: 2023-10-25, 12:52:49 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1829,6 +1829,11 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 16B5B..16B61 ; N # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; N # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; N # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; N # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; N # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; N # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D..16D6F ; N # Po [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; N # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; N # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; N # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; N # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH @@ -2065,7 +2070,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 766038 code points not listed here. +# The above property value applies to 765980 code points not listed here. # Total code points: 792618 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 2a5ac8419..0fcfe447b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-16.0.0.txt -# Date: 2023-10-24, 21:03:39 GMT +# Date: 2023-10-25, 12:52:49 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -559,7 +559,8 @@ FFFE..FFFF ; Cn # [2] .. 16B5A ; Cn # 16B62 ; Cn # 16B78..16B7C ; Cn # [5] .. -16B90..16E3F ; Cn # [688] .. +16B90..16D3F ; Cn # [432] .. +16D7A..16E3F ; Cn # [198] .. 16E9B..16EFF ; Cn # [101] .. 16F4B..16F4E ; Cn # [4] .. 16F88..16F8E ; Cn # [7] .. @@ -734,7 +735,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824472 +# Total code points: 824414 # ================================================ @@ -2144,6 +2145,8 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 10D4E ; Lm # GARAY VOWEL LENGTH MARK 10D6F ; Lm # GARAY REDUPLICATION MARK 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM +16D40..16D42 ; Lm # [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D6B..16D6C ; Lm # [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16F93..16F9F ; Lm # [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; Lm # [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Lm # OLD CHINESE ITERATION MARK @@ -2155,7 +2158,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 399 +# Total code points: 404 # ================================================ @@ -2609,6 +2612,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 16B00..16B2F ; Lo # [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B63..16B77 ; Lo # [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; Lo # [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D43..16D6A ; Lo # [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16F00..16F4A ; Lo # [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; Lo # MIAO LETTER NASALIZATION 17000..187F7 ; Lo # [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 @@ -2680,7 +2684,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132360 +# Total code points: 132400 # ================================================ @@ -3303,6 +3307,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16A60..16A69 ; Nd # [10] MRO DIGIT ZERO..MRO DIGIT NINE 16AC0..16AC9 ; Nd # [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +16D70..16D79 ; Nd # [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Nd # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Nd # [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE @@ -3311,7 +3316,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 730 +# Total code points: 740 # ================================================ @@ -3892,6 +3897,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 16AF5 ; Po # BASSA VAH FULL STOP 16B37..16B3B ; Po # [5] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS FEEM 16B44 ; Po # PAHAWH HMONG SIGN XAUS +16D6D..16D6F ; Po # [3] KIRAT RAI SIGN YUPI..KIRAT RAI DOUBLE DANDA 16E97..16E9A ; Po # [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH 16FE2 ; Po # OLD CHINESE HOOK MARK 1BC9F ; Po # DUPLOYAN PUNCTUATION CHINOOK FULL STOP @@ -3899,7 +3905,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 1E5FF ; Po # OL ONAL ABBREVIATION SIGN 1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 630 +# Total code points: 633 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 0581bb420..0ffc06dbb 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2023-10-24, 21:03:41 GMT +# Date: 2023-10-25, 12:52:51 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -68,8 +68,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762480 code points not listed here. -# Total code points: 899948 +# The above property value applies to 762422 code points not listed here. +# Total code points: 899890 # ================================================ @@ -542,6 +542,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 16A60..16A69 ; NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16AC0..16AC9 ; NU # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; NU # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; NU # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE @@ -550,7 +551,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 674 +# Total code points: 684 # ================================================ @@ -1430,6 +1431,10 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 16B5B..16B61 ; AL # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; AL # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; AL # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; AL # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; AL # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; AL # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D ; AL # Po KIRAT RAI SIGN YUPI 16E40..16E7F ; AL # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; AL # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E99..16E9A ; AL # Po [2] MEDEFAIDRIN SYMBOL AIVA..MEDEFAIDRIN EXCLAMATION OH @@ -1600,7 +1605,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21915 +# Total code points: 21961 # ================================================ @@ -2505,11 +2510,12 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 16AF5 ; BA # Po BASSA VAH FULL STOP 16B37..16B39 ; BA # Po [3] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN CIM CHEEM 16B44 ; BA # Po PAHAWH HMONG SIGN XAUS +16D6E..16D6F ; BA # Po [2] KIRAT RAI DANDA..KIRAT RAI DOUBLE DANDA 16E97..16E98 ; BA # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 267 +# Total code points: 269 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index b9437c06f..d69094d10 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-16.0.0.txt -# Date: 2023-10-24, 21:03:41 GMT +# Date: 2023-10-25, 12:52:52 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -36497,6 +36497,64 @@ FFFD ; REPLACEMENT CHARACTER 16B8D ; PAHAWH HMONG CLAN SIGN TSWB 16B8E ; PAHAWH HMONG CLAN SIGN KWM 16B8F ; PAHAWH HMONG CLAN SIGN VWJ +16D40 ; KIRAT RAI SIGN ANUSVARA +16D41 ; KIRAT RAI SIGN TONPI +16D42 ; KIRAT RAI SIGN VISARGA +16D43 ; KIRAT RAI LETTER A +16D44 ; KIRAT RAI LETTER KA +16D45 ; KIRAT RAI LETTER KHA +16D46 ; KIRAT RAI LETTER GA +16D47 ; KIRAT RAI LETTER GHA +16D48 ; KIRAT RAI LETTER NGA +16D49 ; KIRAT RAI LETTER CA +16D4A ; KIRAT RAI LETTER CHA +16D4B ; KIRAT RAI LETTER JA +16D4C ; KIRAT RAI LETTER JHA +16D4D ; KIRAT RAI LETTER NYA +16D4E ; KIRAT RAI LETTER TTA +16D4F ; KIRAT RAI LETTER TTHA +16D50 ; KIRAT RAI LETTER DDA +16D51 ; KIRAT RAI LETTER DDHA +16D52 ; KIRAT RAI LETTER TA +16D53 ; KIRAT RAI LETTER THA +16D54 ; KIRAT RAI LETTER DA +16D55 ; KIRAT RAI LETTER DHA +16D56 ; KIRAT RAI LETTER NA +16D57 ; KIRAT RAI LETTER PA +16D58 ; KIRAT RAI LETTER PHA +16D59 ; KIRAT RAI LETTER BA +16D5A ; KIRAT RAI LETTER BHA +16D5B ; KIRAT RAI LETTER MA +16D5C ; KIRAT RAI LETTER YA +16D5D ; KIRAT RAI LETTER RA +16D5E ; KIRAT RAI LETTER LA +16D5F ; KIRAT RAI LETTER VA +16D60 ; KIRAT RAI LETTER SA +16D61 ; KIRAT RAI LETTER SHA +16D62 ; KIRAT RAI LETTER HA +16D63 ; KIRAT RAI VOWEL SIGN AA +16D64 ; KIRAT RAI VOWEL SIGN I +16D65 ; KIRAT RAI VOWEL SIGN U +16D66 ; KIRAT RAI VOWEL SIGN UE +16D67 ; KIRAT RAI VOWEL SIGN E +16D68 ; KIRAT RAI VOWEL SIGN AI +16D69 ; KIRAT RAI VOWEL SIGN O +16D6A ; KIRAT RAI VOWEL SIGN AU +16D6B ; KIRAT RAI SIGN VIRAMA +16D6C ; KIRAT RAI SIGN SAAT +16D6D ; KIRAT RAI SIGN YUPI +16D6E ; KIRAT RAI DANDA +16D6F ; KIRAT RAI DOUBLE DANDA +16D70 ; KIRAT RAI DIGIT ZERO +16D71 ; KIRAT RAI DIGIT ONE +16D72 ; KIRAT RAI DIGIT TWO +16D73 ; KIRAT RAI DIGIT THREE +16D74 ; KIRAT RAI DIGIT FOUR +16D75 ; KIRAT RAI DIGIT FIVE +16D76 ; KIRAT RAI DIGIT SIX +16D77 ; KIRAT RAI DIGIT SEVEN +16D78 ; KIRAT RAI DIGIT EIGHT +16D79 ; KIRAT RAI DIGIT NINE 16E40 ; MEDEFAIDRIN CAPITAL LETTER M 16E41 ; MEDEFAIDRIN CAPITAL LETTER S 16E42 ; MEDEFAIDRIN CAPITAL LETTER V @@ -44422,6 +44480,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 150059 +# Total code points: 150117 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt index 808a5bd98..3c347a110 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt @@ -1,5 +1,5 @@ # DerivedNumericType-16.0.0.txt -# Date: 2023-10-24, 21:03:43 GMT +# Date: 2023-10-25, 12:52:54 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -282,6 +282,7 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 16A60..16A69 ; Decimal # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16AC0..16AC9 ; Decimal # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Decimal # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +16D70..16D79 ; Decimal # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 1D7CE..1D7FF ; Decimal # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Decimal # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Decimal # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE @@ -290,6 +291,6 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Decimal # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 730 +# Total code points: 740 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt index 1a3e45761..c02b8a5c0 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt @@ -1,5 +1,5 @@ # DerivedNumericValues-16.0.0.txt -# Date: 2023-10-24, 21:03:43 GMT +# Date: 2023-10-25, 12:52:55 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -114,6 +114,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 16A60 ; 0.0 ; ; 0 # Nd MRO DIGIT ZERO 16AC0 ; 0.0 ; ; 0 # Nd TANGSA DIGIT ZERO 16B50 ; 0.0 ; ; 0 # Nd PAHAWH HMONG DIGIT ZERO +16D70 ; 0.0 ; ; 0 # Nd KIRAT RAI DIGIT ZERO 16E80 ; 0.0 ; ; 0 # No MEDEFAIDRIN DIGIT ZERO 1D2C0 ; 0.0 ; ; 0 # No KAKTOVIK NUMERAL ZERO 1D2E0 ; 0.0 ; ; 0 # No MAYAN NUMERAL ZERO @@ -131,7 +132,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1FBF0 ; 0.0 ; ; 0 # Nd SEGMENTED DIGIT ZERO -# Total code points: 93 +# Total code points: 94 # ================================================ @@ -537,6 +538,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 16A61 ; 1.0 ; ; 1 # Nd MRO DIGIT ONE 16AC1 ; 1.0 ; ; 1 # Nd TANGSA DIGIT ONE 16B51 ; 1.0 ; ; 1 # Nd PAHAWH HMONG DIGIT ONE +16D71 ; 1.0 ; ; 1 # Nd KIRAT RAI DIGIT ONE 16E81 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE 16E94 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE ALTERNATE FORM 1D2C1 ; 1.0 ; ; 1 # No KAKTOVIK NUMERAL ONE @@ -563,7 +565,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1FBF1 ; 1.0 ; ; 1 # Nd SEGMENTED DIGIT ONE 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 149 +# Total code points: 150 # ================================================ @@ -696,6 +698,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 16A62 ; 2.0 ; ; 2 # Nd MRO DIGIT TWO 16AC2 ; 2.0 ; ; 2 # Nd TANGSA DIGIT TWO 16B52 ; 2.0 ; ; 2 # Nd PAHAWH HMONG DIGIT TWO +16D72 ; 2.0 ; ; 2 # Nd KIRAT RAI DIGIT TWO 16E82 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO 16E95 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO ALTERNATE FORM 1D2C2 ; 2.0 ; ; 2 # No KAKTOVIK NUMERAL TWO @@ -722,7 +725,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1FBF2 ; 2.0 ; ; 2 # Nd SEGMENTED DIGIT TWO 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 151 +# Total code points: 152 # ================================================ @@ -847,6 +850,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 16A63 ; 3.0 ; ; 3 # Nd MRO DIGIT THREE 16AC3 ; 3.0 ; ; 3 # Nd TANGSA DIGIT THREE 16B53 ; 3.0 ; ; 3 # Nd PAHAWH HMONG DIGIT THREE +16D73 ; 3.0 ; ; 3 # Nd KIRAT RAI DIGIT THREE 16E83 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE 16E96 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 1D2C3 ; 3.0 ; ; 3 # No KAKTOVIK NUMERAL THREE @@ -875,7 +879,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 149 +# Total code points: 150 # ================================================ @@ -995,6 +999,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 16A64 ; 4.0 ; ; 4 # Nd MRO DIGIT FOUR 16AC4 ; 4.0 ; ; 4 # Nd TANGSA DIGIT FOUR 16B54 ; 4.0 ; ; 4 # Nd PAHAWH HMONG DIGIT FOUR +16D74 ; 4.0 ; ; 4 # Nd KIRAT RAI DIGIT FOUR 16E84 ; 4.0 ; ; 4 # No MEDEFAIDRIN DIGIT FOUR 1D2C4 ; 4.0 ; ; 4 # No KAKTOVIK NUMERAL FOUR 1D2E4 ; 4.0 ; ; 4 # No MAYAN NUMERAL FOUR @@ -1021,7 +1026,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 140 +# Total code points: 141 # ================================================ @@ -1144,6 +1149,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 16A65 ; 5.0 ; ; 5 # Nd MRO DIGIT FIVE 16AC5 ; 5.0 ; ; 5 # Nd TANGSA DIGIT FIVE 16B55 ; 5.0 ; ; 5 # Nd PAHAWH HMONG DIGIT FIVE +16D75 ; 5.0 ; ; 5 # Nd KIRAT RAI DIGIT FIVE 16E85 ; 5.0 ; ; 5 # No MEDEFAIDRIN DIGIT FIVE 1D2C5 ; 5.0 ; ; 5 # No KAKTOVIK NUMERAL FIVE 1D2E5 ; 5.0 ; ; 5 # No MAYAN NUMERAL FIVE @@ -1169,7 +1175,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1FBF5 ; 5.0 ; ; 5 # Nd SEGMENTED DIGIT FIVE 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 138 +# Total code points: 139 # ================================================ @@ -1279,6 +1285,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 16A66 ; 6.0 ; ; 6 # Nd MRO DIGIT SIX 16AC6 ; 6.0 ; ; 6 # Nd TANGSA DIGIT SIX 16B56 ; 6.0 ; ; 6 # Nd PAHAWH HMONG DIGIT SIX +16D76 ; 6.0 ; ; 6 # Nd KIRAT RAI DIGIT SIX 16E86 ; 6.0 ; ; 6 # No MEDEFAIDRIN DIGIT SIX 1D2C6 ; 6.0 ; ; 6 # No KAKTOVIK NUMERAL SIX 1D2E6 ; 6.0 ; ; 6 # No MAYAN NUMERAL SIX @@ -1302,7 +1309,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1FBF6 ; 6.0 ; ; 6 # Nd SEGMENTED DIGIT SIX 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 122 +# Total code points: 123 # ================================================ @@ -1410,6 +1417,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 16A67 ; 7.0 ; ; 7 # Nd MRO DIGIT SEVEN 16AC7 ; 7.0 ; ; 7 # Nd TANGSA DIGIT SEVEN 16B57 ; 7.0 ; ; 7 # Nd PAHAWH HMONG DIGIT SEVEN +16D77 ; 7.0 ; ; 7 # Nd KIRAT RAI DIGIT SEVEN 16E87 ; 7.0 ; ; 7 # No MEDEFAIDRIN DIGIT SEVEN 1D2C7 ; 7.0 ; ; 7 # No KAKTOVIK NUMERAL SEVEN 1D2E7 ; 7.0 ; ; 7 # No MAYAN NUMERAL SEVEN @@ -1433,7 +1441,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1FBF7 ; 7.0 ; ; 7 # Nd SEGMENTED DIGIT SEVEN 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 122 +# Total code points: 123 # ================================================ @@ -1538,6 +1546,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 16A68 ; 8.0 ; ; 8 # Nd MRO DIGIT EIGHT 16AC8 ; 8.0 ; ; 8 # Nd TANGSA DIGIT EIGHT 16B58 ; 8.0 ; ; 8 # Nd PAHAWH HMONG DIGIT EIGHT +16D78 ; 8.0 ; ; 8 # Nd KIRAT RAI DIGIT EIGHT 16E88 ; 8.0 ; ; 8 # No MEDEFAIDRIN DIGIT EIGHT 1D2C8 ; 8.0 ; ; 8 # No KAKTOVIK NUMERAL EIGHT 1D2E8 ; 8.0 ; ; 8 # No MAYAN NUMERAL EIGHT @@ -1560,7 +1569,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA 1FBF8 ; 8.0 ; ; 8 # Nd SEGMENTED DIGIT EIGHT -# Total code points: 117 +# Total code points: 118 # ================================================ @@ -1668,6 +1677,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 16A69 ; 9.0 ; ; 9 # Nd MRO DIGIT NINE 16AC9 ; 9.0 ; ; 9 # Nd TANGSA DIGIT NINE 16B59 ; 9.0 ; ; 9 # Nd PAHAWH HMONG DIGIT NINE +16D79 ; 9.0 ; ; 9 # Nd KIRAT RAI DIGIT NINE 16E89 ; 9.0 ; ; 9 # No MEDEFAIDRIN DIGIT NINE 1D2C9 ; 9.0 ; ; 9 # No KAKTOVIK NUMERAL NINE 1D2E9 ; 9.0 ; ; 9 # No MAYAN NUMERAL NINE @@ -1691,7 +1701,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1FBF9 ; 9.0 ; ; 9 # Nd SEGMENTED DIGIT NINE 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 123 +# Total code points: 124 # ================================================ diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 880612bf6..9712ab6f4 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -338,6 +338,7 @@ public enum Block_Values implements Named { Khmer_Symbols("Khmer_Symbols"), Khojki("Khojki"), Khudawadi("Khudawadi"), + Kirat_Rai("Kirat_Rai"), Lao("Lao"), Latin_1_Supplement("Latin_1_Sup", "Latin_1"), Latin_Extended_A("Latin_Ext_A"), @@ -1773,6 +1774,7 @@ public enum Script_Values implements Named { Khojki("Khoj"), Khitan_Small_Script("Kits"), Kannada("Knda"), + Kirat_Rai("Krai"), Kaithi("Kthi"), Tai_Tham("Lana"), Lao("Laoo"), diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/ToolUnicodePropertySource.java b/unicodetools/src/main/java/org/unicode/text/UCD/ToolUnicodePropertySource.java index 7780b5505..b06b70633 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/ToolUnicodePropertySource.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/ToolUnicodePropertySource.java @@ -33,6 +33,7 @@ import org.unicode.props.UnicodeProperty; import org.unicode.props.UnicodeProperty.AliasAddAction; import org.unicode.props.UnicodeProperty.BaseProperty; +import org.unicode.props.UnicodeProperty.RegexMatcher; import org.unicode.props.UnicodeProperty.SimpleProperty; import org.unicode.props.UnicodeProperty.UnicodeMapProperty; import org.unicode.text.utility.Settings; @@ -1090,8 +1091,16 @@ public int getMaxWidth(boolean isShort) { unicodeMap.putAll(gcbSpacingMarkSet, "SpacingMark"); final UnicodeProperty hangul = getProperty("Hangul_Syllable_Type"); + final UnicodeProperty name = getProperty("Name"); unicodeMap.putAll(hangul.getSet("L"), "L"); - unicodeMap.putAll(hangul.getSet("V"), "V"); + var regexMatcher = new RegexMatcher(); + unicodeMap.putAll( + hangul.getSet("V") + .addAll( + name.getSet( + regexMatcher.set( + "KIRAT RAI VOWEL SIGN (E|AI|AA|O|AU)"))), + "V"); unicodeMap.putAll(hangul.getSet("T"), "T"); unicodeMap.putAll(hangul.getSet("LV"), "LV"); unicodeMap.putAll(hangul.getSet("LVT"), "LVT"); diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt index db8ebd7b8..2854b13ba 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/MakeUnicodeFiles.txt @@ -986,7 +986,7 @@ File: IndicPositionalCategory # list of Indic scripts, including those which do not have # positional characters. Currently, those additional # Indic scripts without positional characters are -# Multani, Phags-pa, and Tai Le. +# Kirat Rai, Multani, Phags-pa, and Tai Le. # # Notes: # @@ -1076,7 +1076,7 @@ File: IndicSyllabicCategory # Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, # Chakma, Cham, Devanagari, Dives Akuru, Dogra, Grantha, Gujarati, # Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada, Kawi, -# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Lepcha, Limbu, +# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Kirat Rai, Lao, Lepcha, Limbu, # Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meetei Mayek, # Modi, Multani, Myanmar, Nandinagari, Newa, New Tai Lue, Oriya, # Phags-pa, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Soyombo, diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index c83570084..50d5befe2 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -160,6 +160,7 @@ Khmer ; Khmer Khmer_Symbols ; Khmer_Symbols Khojki ; Khojki Khudawadi ; Khudawadi +Kirat_Rai ; Kirat_Rai Lao ; Lao Latin_1_Sup ; Latin_1_Supplement Latin_Ext_A ; Latin_Extended_A