Merge remote-tracking branch 'la-vache/main' into 172-C5

unicode-org · Oct 24, 2023 · e49689b · e49689b
2 parents 24b136d + cab2fa7
commit e49689b
Show file tree

Hide file tree

Showing 162 changed files with 1,217 additions and 292 deletions.
diff --git a/UnicodeJsps/Dockerfile b/UnicodeJsps/Dockerfile
@@ -3,7 +3,7 @@ FROM alpine as cbuild
 WORKDIR /build
 RUN apk add --update wget make gcc musl-dev
 ARG CPATH=https://www.unicode.org/Public/PROGRAMS/BidiReferenceC/
-ARG CVERSION=15.0.0
+ARG CVERSION=15.1.0
 RUN wget -np -nv --reject-regex='.*\.(lib|exe)$' --cut-dirs=4 -nH -r ${CPATH}${CVERSION}/
 RUN cd source && gcc -I ../include/ -static -Os -o3 -o bidiref1 bidiref1.c brutils.c brtest.c brtable.c brrule.c
 RUN ls -lh /build/source/bidiref1 && (/build/source/bidiref1 || true)

diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/IdentifierStatus.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/IdentifierStatus.txt
@@ -1,5 +1,5 @@
 # IdentifierStatus.txt
-# Date: 2023-05-16, 22:25:15 GMT
+# Date: 2023-08-11, 17:46:41 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
@@ -582,8 +582,8 @@ FA27..FA29    ; Allowed    # 1.1    [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK CO
 2B740..2B81D  ; Allowed    # 6.0  [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Allowed    # 8.0 [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Allowed    # 10.0 [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
-2EBF0..2EE4A  ; Allowed    # 15.1 [603] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE4A
+2EBF0..2EE5D  ; Allowed    # 15.1 [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 30000..3134A  ; Allowed    # 13.0 [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 31350..323AF  ; Allowed    # 15.0 [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 112759
+# Total code points: 112778
diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/IdentifierType.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/IdentifierType.txt
@@ -1,5 +1,5 @@
 # IdentifierType.txt
-# Date: 2023-05-16, 22:25:14 GMT
+# Date: 2023-08-11, 17:46:40 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
@@ -576,11 +576,11 @@ FA27..FA29    ; Recommended                    # 1.1    [3] CJK COMPATIBILITY ID
 2B740..2B81D  ; Recommended                    # 6.0  [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Recommended                    # 8.0 [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Recommended                    # 10.0 [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
-2EBF0..2EE4A  ; Recommended                    # 15.1 [603] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE4A
+2EBF0..2EE5D  ; Recommended                    # 15.1 [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
 30000..3134A  ; Recommended                    # 13.0 [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 31350..323AF  ; Recommended                    # 15.0 [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 112742
+# Total code points: 112761
 
 #	Identifier_Type:	Inclusion
 

diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/IdnaMappingTable.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/IdnaMappingTable.txt
@@ -1,5 +1,5 @@
 # IdnaMappingTable.txt
-# Date: 2023-05-15, 22:37:02 GMT
+# Date: 2023-08-10, 22:32:27 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
@@ -2036,7 +2036,7 @@
 1E9A          ; mapped                 ; 0061 02BE     # 1.1  LATIN SMALL LETTER A WITH RIGHT HALF RING
 1E9B          ; mapped                 ; 1E61          # 2.0  LATIN SMALL LETTER LONG S WITH DOT ABOVE
 1E9C..1E9D    ; valid                                  # 5.1  LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE..LATIN SMALL LETTER LONG S WITH HIGH STROKE
-1E9E          ; mapped                 ; 0073 0073     # 5.1  LATIN CAPITAL LETTER SHARP S
+1E9E          ; mapped                 ; 00DF          # 5.1  LATIN CAPITAL LETTER SHARP S
 1E9F          ; valid                                  # 5.1  LATIN SMALL LETTER DELTA
 1EA0          ; mapped                 ; 1EA1          # 1.1  LATIN CAPITAL LETTER A WITH DOT BELOW
 1EA1          ; valid                                  # 1.1  LATIN SMALL LETTER A WITH DOT BELOW
@@ -3422,7 +3422,7 @@
 31C0..31CF    ; valid                  ;      ; NV8    # 4.1  CJK STROKE T..CJK STROKE N
 31D0..31E3    ; valid                  ;      ; NV8    # 5.1  CJK STROKE H..CJK STROKE Q
 31E4..31EE    ; disallowed                             # NA   <reserved-31E4>..<reserved-31EE>
-31EF          ; valid                  ;      ; NV8    # 15.1 IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
+31EF          ; disallowed                             # 15.1 IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION
 31F0..31FF    ; valid                                  # 3.2  KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
 3200          ; disallowed_STD3_mapped ; 0028 1100 0029 #1.1  PARENTHESIZED HANGUL KIYEOK
 3201          ; disallowed_STD3_mapped ; 0028 1102 0029 #1.1  PARENTHESIZED HANGUL NIEUN
@@ -8448,8 +8448,8 @@ FFFE..FFFF    ; disallowed                             # 1.1  <noncharacter-FFFE
 2CEA2..2CEAF  ; disallowed                             # NA   <reserved-2CEA2>..<reserved-2CEAF>
 2CEB0..2EBE0  ; valid                                  # 10.0 CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2EBE1..2EBEF  ; disallowed                             # NA   <reserved-2EBE1>..<reserved-2EBEF>
-2EBF0..2EE4A  ; valid                                  # 15.1 CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE4A
-2EE4B..2F7FF  ; disallowed                             # NA   <reserved-2EE4B>..<reserved-2F7FF>
+2EBF0..2EE5D  ; valid                                  # 15.1 CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
+2EE5E..2F7FF  ; disallowed                             # NA   <reserved-2EE5E>..<reserved-2F7FF>
 2F800         ; mapped                 ; 4E3D          # 3.1  CJK COMPATIBILITY IDEOGRAPH-2F800
 2F801         ; mapped                 ; 4E38          # 3.1  CJK COMPATIBILITY IDEOGRAPH-2F801
 2F802         ; mapped                 ; 4E41          # 3.1  CJK COMPATIBILITY IDEOGRAPH-2F802

diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/NamesList.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/NamesList.txt
@@ -1,10 +1,7 @@
 ; charset=UTF-8
 @@@	The Unicode Standard 15.1.0
-@@@+	U15M230512.lst
-	Unicode 15.1.0 names list, seventh delta.
-	Repertoire synched with UnicodeData-15.1.0d2.txt.
-	Tweak use of notices to suppress year expansions.
-	Update annotations for 06F4..06F7.
+@@@+	U15M230728.lst
+	Unicode 15.1.0 final names list.
 	This file is semi-automatically derived from UnicodeData.txt and
 	a set of manually created annotations using a script to select
 	or suppress information from the data file. The rules used
@@ -2429,7 +2426,8 @@
 	= apostrophe
 	* glottal stop, glottalization, ejective
 	* many languages use this as a letter of their alphabets
-	* used as a tone marker in Bodo, Dogri, and Maithili
+	* used as a tone marker in Bodo and Dogri
+	* indicates vowel elongation, or various truncations and ellipsis in Maithili
 	* used as a modifier letter in the Lisu script
 	* 2019 is the preferred character for a punctuation apostrophe
 	x (apostrophe - 0027)
@@ -4456,7 +4454,8 @@
 	* Uyghur, Kazakh
 06CC	ARABIC LETTER FARSI YEH
 	* Arabic, Persian, Urdu, Kashmiri, ...
-	* initial and medial forms of this letter have dots
+	* initial and medial forms of this letter have two horizontal dots below
+	* retains its dots in initial and medial forms when used in combination with 0654
 	x (arabic letter alef maksura - 0649)
 	x (arabic letter yeh - 064A)
 06CD	ARABIC LETTER YEH WITH TAIL
@@ -19522,8 +19521,10 @@
 	* indicates pronunciation on one side of the mouth only
 	x (section sign - 00A7)
 @		Dashes
+@+		These long dashes are shown in the code charts inside dashed square boxes because of their width. In production fonts they would simply display as extra-wide dashes. 
 2E3A	TWO-EM DASH
 	= omission dash
+	* may be used in Chinese for abrupt change of thought, inserting new content, or continuation of tone or sound
 	x (em dash - 2014)
 2E3B	THREE-EM DASH
 @		Alternate forms of punctuation
@@ -26618,7 +26619,7 @@ D7FB	HANGUL JONGSEONG PHIEUPH-THIEUTH
 @@+
 @+		This block, despite its name, contains a number of unified CJK ideographs. Each is also individually identified by an annotation.
 @+		Subheaders identifying sources for subranges do not indicate required usage or preclude mappings to other sources. For example, many pronunciation variants from KS X 1001:1998 are also mapped to a J source.
-@		Pronunciation variants from KS X 1001:1998
+@		Pronunciation variants from KS X 1001:1998
 F900	CJK COMPATIBILITY IDEOGRAPH-F900
 	: 8C48
 F901	CJK COMPATIBILITY IDEOGRAPH-F901
@@ -44024,6 +44025,7 @@ FFFF	<not a character>
 1BC01	DUPLOYAN LETTER X
 	* Salishan
 @		Line consonants
+@+		Small arrows shown in the chart glyphs for some strokes and arcs indicate the handwriting direction of these characters, and are not visibly rendered.
 1BC02	DUPLOYAN LETTER P
 	* Chinook number 1
 1BC03	DUPLOYAN LETTER T
@@ -54200,9 +54202,9 @@ FFFF	<not a character>
 @@	2B740	CJK Unified Ideographs Extension D	2B81D
 @@	2B820	CJK Unified Ideographs Extension E	2CEA1
 @@	2CEB0	CJK Unified Ideographs Extension F	2EBE0
-@@	2EBF0	CJK Unified Ideographs Extension I	2EE4A
+@@	2EBF0	CJK Unified Ideographs Extension I	2EE5D
 @@	2F800	CJK Compatibility Ideographs Supplement	2FA1F
-@		Duplicate characters from CNS 11643-1992
+@		Duplicate characters from CNS 11643-1992
 2F800	CJK COMPATIBILITY IDEOGRAPH-2F800
 	: 4E3D
 2F801	CJK COMPATIBILITY IDEOGRAPH-2F801

diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/confusables.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/confusables.txt
@@ -1,5 +1,5 @@
 # confusables.txt
-# Date: 2023-05-16, 22:25:14 GMT
+# Date: 2023-08-11, 17:46:40 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
@@ -349,8 +349,8 @@ A4FA ;	002E 002E ;	MA	# ( ꓺ → .. ) LISU LETTER TONE MYA CYA → FULL STOP, F
 
 A6F4 ;	A6F3 A6F3 ;	MA	#* ( ꛴ → ꛳꛳ ) BAMUM COLON → BAMUM FULL STOP, BAMUM FULL STOP	# 
 
-30FB ;	00B7 ;	MA	#* ( ・ → · ) KATAKANA MIDDLE DOT → MIDDLE DOT	# →•→
-FF65 ;	00B7 ;	MA	#* ( ･ → · ) HALFWIDTH KATAKANA MIDDLE DOT → MIDDLE DOT	# →•→
+30FB ;	00B7 ;	MA	# ( ・ → · ) KATAKANA MIDDLE DOT → MIDDLE DOT	# →•→
+FF65 ;	00B7 ;	MA	# ( ･ → · ) HALFWIDTH KATAKANA MIDDLE DOT → MIDDLE DOT	# →•→
 16EB ;	00B7 ;	MA	#* ( ᛫ → · ) RUNIC SINGLE PUNCTUATION → MIDDLE DOT	# 
 0387 ;	00B7 ;	MA	# ( · → · ) GREEK ANO TELEIA → MIDDLE DOT	# 
 2E31 ;	00B7 ;	MA	#* ( ⸱ → · ) WORD SEPARATOR MIDDLE DOT → MIDDLE DOT	# 

diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/data/PropertyAliases.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/data/PropertyAliases.txt
@@ -1,5 +1,5 @@
 # PropertyAliases-15.1.0.txt
-# Date: 2023-03-23, 00:36:58 GMT
+# Date: 2023-08-07, 15:21:34 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
@@ -122,6 +122,7 @@ ea                       ; East_Asian_Width
 gc                       ; General_Category
 GCB                      ; Grapheme_Cluster_Break
 hst                      ; Hangul_Syllable_Type
+InCB                     ; Indic_Conjunct_Break
 InPC                     ; Indic_Positional_Category
 InSC                     ; Indic_Syllabic_Category
 jg                       ; Joining_Group
@@ -211,6 +212,6 @@ XO_NFKC                  ; Expands_On_NFKC
 XO_NFKD                  ; Expands_On_NFKD
 
 # ================================================
-# Total:    133
+# Total:    134
 
 # EOF
diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/data/PropertyValueAliases.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/data/PropertyValueAliases.txt
@@ -1,5 +1,5 @@
-# PropertyValueAliases-15.1.0.txt
-# Date: 2023-05-10, 16:59:10 GMT
+# PropertyValueAliases-16.0.0.txt
+# Date: 2023-10-17, 12:29:15 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
@@ -92,6 +92,7 @@ age; 13.0                             ; V13_0
 age; 14.0                             ; V14_0
 age; 15.0                             ; V15_0
 age; 15.1                             ; V15_1
+age; 16.0                             ; V16_0
 age; NA                               ; Unassigned
 
 # Alphabetic (Alpha)
@@ -367,6 +368,7 @@ blk; Music                            ; Musical_Symbols
 blk; Myanmar                          ; Myanmar
 blk; Myanmar_Ext_A                    ; Myanmar_Extended_A
 blk; Myanmar_Ext_B                    ; Myanmar_Extended_B
+blk; Myanmar_Ext_C                    ; Myanmar_Extended_C
 blk; Nabataean                        ; Nabataean
 blk; Nag_Mundari                      ; Nag_Mundari
 blk; Nandinagari                      ; Nandinagari
@@ -425,6 +427,7 @@ blk; Soyombo                          ; Soyombo
 blk; Specials                         ; Specials
 blk; Sundanese                        ; Sundanese
 blk; Sundanese_Sup                    ; Sundanese_Supplement
+blk; Sunuwar                          ; Sunuwar
 blk; Sup_Arrows_A                     ; Supplemental_Arrows_A
 blk; Sup_Arrows_B                     ; Supplemental_Arrows_B
 blk; Sup_Arrows_C                     ; Supplemental_Arrows_C
@@ -460,6 +463,7 @@ blk; Thai                             ; Thai
 blk; Tibetan                          ; Tibetan
 blk; Tifinagh                         ; Tifinagh
 blk; Tirhuta                          ; Tirhuta
+blk; Todhri                           ; Todhri
 blk; Toto                             ; Toto
 blk; Transport_And_Map                ; Transport_And_Map_Symbols
 blk; UCAS                             ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
@@ -853,6 +857,13 @@ IDS; Y                                ; Yes                              ; T
 Ideo; N                               ; No                               ; F                                ; False
 Ideo; Y                               ; Yes                              ; T                                ; True
 
+# Indic_Conjunct_Break (InCB)
+
+InCB; Consonant                       ; Consonant
+InCB; Extend                          ; Extend
+InCB; Linker                          ; Linker
+InCB; None                            ; None
+
 # Indic_Positional_Category (InPC)
 
 InPC; Bottom                          ; Bottom
@@ -1416,6 +1427,7 @@ sc ; Sogo                             ; Old_Sogdian
 sc ; Sora                             ; Sora_Sompeng
 sc ; Soyo                             ; Soyombo
 sc ; Sund                             ; Sundanese
+sc ; Sunu                             ; Sunuwar
 sc ; Sylo                             ; Syloti_Nagri
 sc ; Syrc                             ; Syriac
 sc ; Tagb                             ; Tagbanwa
@@ -1433,6 +1445,7 @@ sc ; Thai                             ; Thai
 sc ; Tibt                             ; Tibetan
 sc ; Tirh                             ; Tirhuta
 sc ; Tnsa                             ; Tangsa
+sc ; Todr                             ; Todhri
 sc ; Toto                             ; Toto
 sc ; Ugar                             ; Ugaritic
 sc ; Vaii                             ; Vai

diff --git a/UnicodeJsps/src/main/resources/org/unicode/jsp/emoji-sequences.txt b/UnicodeJsps/src/main/resources/org/unicode/jsp/emoji-sequences.txt
@@ -1,5 +1,5 @@
 # emoji-sequences.txt
-# Date: 2023-05-05, 23:24:34 GMT
+# Date: 2023-06-05, 21:39:54 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
@@ -784,7 +784,7 @@
 1F1F9 1F1F2   ; RGI_Emoji_Flag_Sequence      ; flag: Turkmenistan                                             # E2.0   [1] (🇹🇲)
 1F1F9 1F1F3   ; RGI_Emoji_Flag_Sequence      ; flag: Tunisia                                                  # E2.0   [1] (🇹🇳)
 1F1F9 1F1F4   ; RGI_Emoji_Flag_Sequence      ; flag: Tonga                                                    # E2.0   [1] (🇹🇴)
-1F1F9 1F1F7   ; RGI_Emoji_Flag_Sequence      ; flag: Turkey                                                   # E2.0   [1] (🇹🇷)
+1F1F9 1F1F7   ; RGI_Emoji_Flag_Sequence      ; flag: Türkiye                                                  # E2.0   [1] (🇹🇷)
 1F1F9 1F1F9   ; RGI_Emoji_Flag_Sequence      ; flag: Trinidad & Tobago                                        # E2.0   [1] (🇹🇹)
 1F1F9 1F1FB   ; RGI_Emoji_Flag_Sequence      ; flag: Tuvalu                                                   # E2.0   [1] (🇹🇻)
 1F1F9 1F1FC   ; RGI_Emoji_Flag_Sequence      ; flag: Taiwan                                                   # E2.0   [1] (🇹🇼)