X-Git-Url: https://gitweb.factorcode.org/gitweb.cgi?p=factor.git;a=blobdiff_plain;f=basis%2Funicode%2FUCD%2FDerivedNormalizationProps.txt;h=5d5ab6160397b6affc999a58918dd922090b4e73;hp=00a25f0e7e898caa3b80aea24fe33231c3ac5ae0;hb=e3f197c3bbd776e9bb83d7fa8598687a8842d0b6;hpb=3a6db662840cce231481bb760d8bdc6bdf7e70c2 diff --git a/basis/unicode/UCD/DerivedNormalizationProps.txt b/basis/unicode/UCD/DerivedNormalizationProps.txt index 00a25f0e7e..5d5ab61603 100644 --- a/basis/unicode/UCD/DerivedNormalizationProps.txt +++ b/basis/unicode/UCD/DerivedNormalizationProps.txt @@ -1,11 +1,11 @@ -# DerivedNormalizationProps-13.0.0.txt -# Date: 2019-09-08, 23:31:08 GMT -# © 2019 Unicode®, Inc. +# DerivedNormalizationProps-15.0.0.txt +# Date: 2022-04-02, 01:29:03 GMT +# © 2022 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 http://www.unicode.org/terms_of_use.html +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # ================================================ @@ -132,6 +132,9 @@ 33DD ; FC_NFKC; 0077 0062 # So SQUARE WB 33DE ; FC_NFKC; 0076 2215 006D # So SQUARE V OVER M 33DF ; FC_NFKC; 0061 2215 006D # So SQUARE A OVER M +A7F2 ; FC_NFKC; 0063 # Lm MODIFIER LETTER CAPITAL C +A7F3 ; FC_NFKC; 0066 # Lm MODIFIER LETTER CAPITAL F +A7F4 ; FC_NFKC; 0071 # Lm MODIFIER LETTER CAPITAL Q A7F8 ; FC_NFKC; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE 1D400 ; FC_NFKC; 0061 # L& MATHEMATICAL BOLD CAPITAL A 1D401 ; FC_NFKC; 0062 # L& MATHEMATICAL BOLD CAPITAL B @@ -650,7 +653,7 @@ A7F8 ; FC_NFKC; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE 1F16C ; FC_NFKC; 006D 0072 # So RAISED MR SIGN 1F190 ; FC_NFKC; 0064 006A # So SQUARE DJ -# Total code points: 634 +# Total code points: 637 # ================================================ @@ -1469,6 +1472,7 @@ FB46..FB4E ; NFC_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 32C0..33FF ; NFKD_QC; N # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL A69C..A69D ; NFKD_QC; N # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; NFKD_QC; N # Lm MODIFIER LETTER US +A7F2..A7F4 ; NFKD_QC; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; NFKD_QC; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; NFKD_QC; N # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; NFKD_QC; N # Lm MODIFIER LETTER SMALL TURNED W @@ -1593,6 +1597,9 @@ FFE5..FFE6 ; NFKD_QC; N # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN FFE8 ; NFKD_QC; N # So HALFWIDTH FORMS LIGHT VERTICAL FFE9..FFEC ; NFKD_QC; N # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE +10781..10785 ; NFKD_QC; N # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; NFKD_QC; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; NFKD_QC; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1109A ; NFKD_QC; N # Lo KAITHI LETTER DDDHA 1109C ; NFKD_QC; N # Lo KAITHI LETTER RHA 110AB ; NFKD_QC; N # Lo KAITHI LETTER VA @@ -1645,6 +1652,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1D7C3 ; NFKD_QC; N # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1D7C4..1D7CB ; NFKD_QC; N # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1D7CE..1D7FF ; NFKD_QC; N # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E030..1E06D ; NFKD_QC; N # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1EE00..1EE03 ; NFKD_QC; N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; NFKD_QC; N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; NFKD_QC; N # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -1690,7 +1698,7 @@ 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: 16908 +# Total code points: 17029 # ================================================ @@ -1883,6 +1891,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 32C0..33FF ; NFKC_QC; N # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL A69C..A69D ; NFKC_QC; N # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; NFKC_QC; N # Lm MODIFIER LETTER US +A7F2..A7F4 ; NFKC_QC; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; NFKC_QC; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; NFKC_QC; N # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; NFKC_QC; N # Lm MODIFIER LETTER SMALL TURNED W @@ -2006,6 +2015,9 @@ FFE5..FFE6 ; NFKC_QC; N # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN FFE8 ; NFKC_QC; N # So HALFWIDTH FORMS LIGHT VERTICAL FFE9..FFEC ; NFKC_QC; N # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE +10781..10785 ; NFKC_QC; N # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; NFKC_QC; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; NFKC_QC; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1D15E..1D164 ; NFKC_QC; N # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; NFKC_QC; N # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 1D400..1D454 ; NFKC_QC; N # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G @@ -2049,6 +2061,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1D7C3 ; NFKC_QC; N # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1D7C4..1D7CB ; NFKC_QC; N # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1D7CE..1D7FF ; NFKC_QC; N # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E030..1E06D ; NFKC_QC; N # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1EE00..1EE03 ; NFKC_QC; N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; NFKC_QC; N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; NFKC_QC; N # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -2094,7 +2107,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKC_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 4807 +# Total code points: 4928 # ================================================ @@ -2889,7 +2902,7 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON # It is constructed by applying NFKC, CaseFolding, and removal of Default_Ignorable_Code_Points. # The process of applying these transformations is repeated until a stable result is produced. # WARNING: Application to STRINGS must apply NFC after mapping each character, because characters may interact. -# For more information, see [http://www.unicode.org/reports/tr44/] +# For more information, see [https://www.unicode.org/reports/tr44/] # Omitted code points are unchanged by this mapping. # @missing: 0000..10FFFF; NFKC_CF; @@ -3523,6 +3536,7 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON 17B4..17B5 ; NFKC_CF; # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; NFKC_CF; # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; NFKC_CF; # Cf MONGOLIAN VOWEL SEPARATOR +180F ; NFKC_CF; # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1C80 ; NFKC_CF; 0432 # L& CYRILLIC SMALL LETTER ROUNDED VE 1C81 ; NFKC_CF; 0434 # L& CYRILLIC SMALL LETTER LONG-LEGGED DE 1C82 ; NFKC_CF; 043E # L& CYRILLIC SMALL LETTER NARROW O @@ -4318,6 +4332,7 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON 2C2C ; NFKC_CF; 2C5C # L& GLAGOLITIC CAPITAL LETTER SHTAPIC 2C2D ; NFKC_CF; 2C5D # L& GLAGOLITIC CAPITAL LETTER TROKUTASTI A 2C2E ; NFKC_CF; 2C5E # L& GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F ; NFKC_CF; 2C5F # L& GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; NFKC_CF; 2C61 # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62 ; NFKC_CF; 026B # L& LATIN CAPITAL LETTER L WITH MIDDLE TILDE 2C63 ; NFKC_CF; 1D7D # L& LATIN CAPITAL LETTER P WITH STROKE @@ -5339,12 +5354,19 @@ A7B8 ; NFKC_CF; A7B9 # L& LATIN CAPITAL LETTER U WITH S A7BA ; NFKC_CF; A7BB # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; NFKC_CF; A7BD # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; NFKC_CF; A7BF # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; NFKC_CF; A7C1 # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; NFKC_CF; A7C3 # L& LATIN CAPITAL LETTER ANGLICANA W A7C4 ; NFKC_CF; A794 # L& LATIN CAPITAL LETTER C WITH PALATAL HOOK A7C5 ; NFKC_CF; 0282 # L& LATIN CAPITAL LETTER S WITH HOOK A7C6 ; NFKC_CF; 1D8E # L& LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7 ; NFKC_CF; A7C8 # L& LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; NFKC_CF; A7CA # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; NFKC_CF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S +A7F2 ; NFKC_CF; 0063 # Lm MODIFIER LETTER CAPITAL C +A7F3 ; NFKC_CF; 0066 # Lm MODIFIER LETTER CAPITAL F +A7F4 ; NFKC_CF; 0071 # Lm MODIFIER LETTER CAPITAL Q A7F5 ; NFKC_CF; A7F6 # L& LATIN CAPITAL LETTER REVERSED HALF H A7F8 ; NFKC_CF; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE A7F9 ; NFKC_CF; 0153 # Lm MODIFIER LETTER SMALL LIGATURE OE @@ -6845,6 +6867,97 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] ........ -# Total code points: 10329 +# Total code points: 10491 # ================================================ @@ -9164,6 +9339,7 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] ...... 10400..10427 ; Changes_When_NFKC_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_NFKC_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_NFKC_Casefolded # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_NFKC_Casefolded # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_NFKC_Casefolded # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_NFKC_Casefolded # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10781..10785 ; Changes_When_NFKC_Casefolded # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Changes_When_NFKC_Casefolded # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Changes_When_NFKC_Casefolded # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10C80..10CB2 ; Changes_When_NFKC_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_NFKC_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_NFKC_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -9771,6 +9959,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] ...... -# Total code points: 10329 +# Total code points: 10491 # EOF