Merge remote-tracking branch 'la-vache/unihan-17' into UNC-disunifica…

…tion-of-峀
unicode-org · Nov 14, 2024 · b25a3cc · b25a3cc
2 parents 170fd50 + b0c8783
commit b25a3cc
Show file tree

Hide file tree

Showing 52 changed files with 11,489 additions and 213 deletions.
diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt
@@ -367,6 +367,7 @@ FFF0..FFFF; Specials
 2F800..2FA1F; CJK Compatibility Ideographs Supplement
 30000..3134F; CJK Unified Ideographs Extension G
 31350..323AF; CJK Unified Ideographs Extension H
+323B0..3347F; CJK Unified Ideographs Extension J
 E0000..E007F; Tags
 E0100..E01EF; Variation Selectors Supplement
 F0000..FFFFF; Supplementary Private Use Area-A

diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt
@@ -1,5 +1,5 @@
 # DerivedAge-17.0.0.txt
-# Date: 2024-11-13, 12:26:32 GMT
+# Date: 2024-11-14, 15:47:44 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -2066,7 +2066,8 @@ A7DA..A7DC    ; 16.0 #   [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L
 # Newly assigned in Unicode 17.0.0 (September, 2025)
 
 2B73A..2B73E  ; 17.0 #   [5] CJK UNIFIED IDEOGRAPH-2B73A..CJK UNIFIED IDEOGRAPH-2B73E
+323B0..33479  ; 17.0 # [4298] CJK UNIFIED IDEOGRAPH-323B0..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 5
+# Total code points: 4303
 
 # EOF
diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt
@@ -1,5 +1,5 @@
 # DerivedCoreProperties-17.0.0.txt
-# Date: 2024-11-13, 12:26:49 GMT
+# Date: 2024-11-14, 15:48:02 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -1439,9 +1439,9 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 2EBF0..2EE5D  ; Alphabetic # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 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
+31350..33479  ; Alphabetic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 142764
+# Total code points: 147062
 
 # ================================================
 
@@ -6960,9 +6960,9 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 2EBF0..2EE5D  ; ID_Start # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 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
+31350..33479  ; ID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 141274
+# Total code points: 145572
 
 # ================================================
 
@@ -8367,10 +8367,10 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 2EBF0..2EE5D  ; ID_Continue # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
-31350..323AF  ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
+31350..33479  ; ID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 E0100..E01EF  ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 144546
+# Total code points: 148844
 
 # ================================================
 
@@ -9146,9 +9146,9 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 2EBF0..2EE5D  ; XID_Start # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 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
+31350..33479  ; XID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 141251
+# Total code points: 145549
 
 # ================================================
 
@@ -10554,10 +10554,10 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 2EBF0..2EE5D  ; XID_Continue # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
-31350..323AF  ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
+31350..33479  ; XID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 E0100..E01EF  ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 144527
+# Total code points: 148825
 
 # ================================================
 
@@ -12810,9 +12810,9 @@ FFFC..FFFD    ; Grapheme_Base # So   [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
 2EBF0..2EE5D  ; Grapheme_Base # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 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
+31350..33479  ; Grapheme_Base # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 152735
+# Total code points: 157033
 
 # ================================================
 

diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt
@@ -1,5 +1,5 @@
-# DerivedNormalizationProps-16.0.0.txt
-# Date: 2024-04-30, 21:48:18 GMT
+# DerivedNormalizationProps-17.0.0.txt
+# Date: 2024-11-14, 15:48:05 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html

diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt
@@ -1,5 +1,5 @@
 # EastAsianWidth-17.0.0.txt
-# Date: 2024-11-13, 12:26:54 GMT
+# Date: 2024-11-14, 15:48:07 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -2675,8 +2675,8 @@ FFFD           ; A  # So         REPLACEMENT CHARACTER
 2FA20..2FFFD   ; W  # Cn  [1502] <reserved-2FA20>..<reserved-2FFFD>
 30000..3134A   ; W  # Lo  [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 3134B..3134F   ; W  # Cn     [5] <reserved-3134B>..<reserved-3134F>
-31350..323AF   ; W  # Lo  [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
-323B0..3FFFD   ; W  # Cn [56398] <reserved-323B0>..<reserved-3FFFD>
+31350..33479   ; W  # Lo  [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
+3347A..3FFFD   ; W  # Cn [52100] <reserved-3347A>..<reserved-3FFFD>
 E0001          ; N  # Cf         LANGUAGE TAG
 E0020..E007F   ; N  # Cf    [96] TAG SPACE..CANCEL TAG
 E0100..E01EF   ; A  # Mn   [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256

diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt
@@ -1,5 +1,5 @@
 # LineBreak-17.0.0.txt
-# Date: 2024-11-13, 12:26:54 GMT
+# Date: 2024-11-14, 15:48:07 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -3659,8 +3659,8 @@ FFFD           ; AI # So         REPLACEMENT CHARACTER
 2FA20..2FFFD   ; ID # Cn  [1502] <reserved-2FA20>..<reserved-2FFFD>
 30000..3134A   ; ID # Lo  [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 3134B..3134F   ; ID # Cn     [5] <reserved-3134B>..<reserved-3134F>
-31350..323AF   ; ID # Lo  [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
-323B0..3FFFD   ; ID # Cn [56398] <reserved-323B0>..<reserved-3FFFD>
+31350..33479   ; ID # Lo  [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
+3347A..3FFFD   ; ID # Cn [52100] <reserved-3347A>..<reserved-3FFFD>
 E0001          ; CM # Cf         LANGUAGE TAG
 E0020..E007F   ; CM # Cf    [96] TAG SPACE..CANCEL TAG
 E0100..E01EF   ; CM # Mn   [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256

diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt
@@ -1,5 +1,5 @@
 # PropList-17.0.0.txt
-# Date: 2024-11-13, 12:27:01 GMT
+# Date: 2024-11-14, 15:48:14 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -883,9 +883,9 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 2EBF0..2EE5D  ; Ideographic # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
-31350..323AF  ; Ideographic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
+31350..33479  ; Ideographic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 106482
+# Total code points: 110780
 
 # ================================================
 
@@ -1365,9 +1365,9 @@ FA27..FA29    ; Unified_Ideograph # Lo   [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C
 2CEB0..2EBE0  ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2EBF0..2EE5D  ; Unified_Ideograph # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 30000..3134A  ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
-31350..323AF  ; Unified_Ideograph # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
+31350..33479  ; Unified_Ideograph # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 97685
+# Total code points: 101983
 
 # ================================================
 

diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt
@@ -1,5 +1,5 @@
 # PropertyValueAliases-17.0.0.txt
-# Date: 2024-09-11, 23:38:17 GMT
+# Date: 2024-10-16, 13:48:47 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -212,6 +212,7 @@ blk; CJK_Ext_F                        ; CJK_Unified_Ideographs_Extension_F
 blk; CJK_Ext_G                        ; CJK_Unified_Ideographs_Extension_G
 blk; CJK_Ext_H                        ; CJK_Unified_Ideographs_Extension_H
 blk; CJK_Ext_I                        ; CJK_Unified_Ideographs_Extension_I
+blk; CJK_Ext_J                        ; CJK_Unified_Ideographs_Extension_J
 blk; CJK_Radicals_Sup                 ; CJK_Radicals_Supplement
 blk; CJK_Strokes                      ; CJK_Strokes
 blk; CJK_Symbols                      ; CJK_Symbols_And_Punctuation

diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt
@@ -1,5 +1,5 @@
 # Scripts-17.0.0.txt
-# Date: 2024-11-13, 12:27:13 GMT
+# Date: 2024-11-14, 15:48:27 GMT
 # © 2024 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -1602,9 +1602,9 @@ FA70..FAD9    ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILI
 2EBF0..2EE5D  ; Han # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 2F800..2FA1D  ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; Han # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
-31350..323AF  ; Han # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
+31350..33479  ; Han # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 
-# Total code points: 99035
+# Total code points: 103333
 
 # ================================================
 

diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt
@@ -39775,6 +39775,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
 3134A;<CJK Ideograph Extension G, Last>;Lo;0;L;;;;;N;;;;;
 31350;<CJK Ideograph Extension H, First>;Lo;0;L;;;;;N;;;;;
 323AF;<CJK Ideograph Extension H, Last>;Lo;0;L;;;;;N;;;;;
+323B0;<CJK Ideograph Extension J, First>;Lo;0;L;;;;;N;;;;;
+33479;<CJK Ideograph Extension J, Last>;Lo;0;L;;;;;N;;;;;
 E0001;LANGUAGE TAG;Cf;0;BN;;;;;N;;;;;
 E0020;TAG SPACE;Cf;0;BN;;;;;N;;;;;
 E0021;TAG EXCLAMATION MARK;Cf;0;BN;;;;;N;;;;;

diff --git a/unicodetools/data/ucd/dev/Unihan/kGB7.txt b/unicodetools/data/ucd/dev/Unihan/kGB7.txt
diff --git a/unicodetools/data/ucd/dev/Unihan/kHanYu.txt b/unicodetools/data/ucd/dev/Unihan/kHanYu.txt
@@ -108,7 +108,7 @@
 34A5	10238.090
 34A6	10238.100
 34A7	10239.090
-34A8	10239.060
+34A8	10239.050
 34A9	10240.080
 34AB	10266.050
 34AD	10273.120
@@ -27570,7 +27570,7 @@
 20452	10238.150
 20453	80009.150
 20454	80009.160
-20457	10239.050
+20457	10239.060
 20458	10239.020
 20459	10239.110
 2045A	10239.010