Unicode 16 regenerated security files

markusicu · Aug 15, 2024 · 7ea598e · 7ea598e
1 parent 5845839
commit 7ea598e
Show file tree

Hide file tree

Showing 6 changed files with 311 additions and 322 deletions.
diff --git a/unicodetools/data/security/dev/IdentifierType.txt b/unicodetools/data/security/dev/IdentifierType.txt
@@ -1,5 +1,5 @@
 # IdentifierType.txt
-# Date: 2024-05-04, 21:31:06 GMT
+# Date: 2024-08-14, 23:39:57 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
@@ -1406,12 +1406,14 @@ A930..A953    ; Exclusion                      # 5.1   [36] REJANG LETTER KA..RE
 0830..083E    ; Exclusion Not_XID              # 5.2   [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU
 1680          ; Exclusion Not_XID              # 3.0        OGHAM SPACE MARK
 169B..169C    ; Exclusion Not_XID              # 3.0    [2] OGHAM FEATHER MARK..OGHAM REVERSED FEATHER MARK
+16EB..16ED    ; Exclusion Not_XID              # 3.0    [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION
 1735..1736    ; Exclusion Not_XID              # 3.2    [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
 1800..180A    ; Exclusion Not_XID              # 3.0   [11] MONGOLIAN BIRGA..MONGOLIAN NIRUGU
 1A1E..1A1F    ; Exclusion Not_XID              # 4.1    [2] BUGINESE PALLAWA..BUGINESE END OF SECTION
 2CE5..2CEA    ; Exclusion Not_XID              # 4.1    [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
 2CF9..2CFF    ; Exclusion Not_XID              # 4.1    [7] COPTIC OLD NUBIAN FULL STOP..COPTIC MORPHOLOGICAL DIVIDER
 2E30          ; Exclusion Not_XID              # 5.1        RING POINT
+2E3C          ; Exclusion Not_XID              # 7.0        STENOGRAPHIC FULL STOP
 A874..A877    ; Exclusion Not_XID              # 5.0    [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHAD
 A95F          ; Exclusion Not_XID              # 5.1        REJANG SECTION MARK
 10100..10102  ; Exclusion Not_XID              # 4.0    [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK
@@ -1509,7 +1511,7 @@ A95F          ; Exclusion Not_XID              # 5.1        REJANG SECTION MARK
 1E5FF         ; Exclusion Not_XID              # 16.0       OL ONAL ABBREVIATION SIGN
 1E8C7..1E8CF  ; Exclusion Not_XID              # 7.0    [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
 
-# Total code points: 1138
+# Total code points: 1142
 
 #	Identifier_Type:	Obsolete
 
@@ -1752,7 +1754,6 @@ A8F8..A8FA    ; Obsolete Not_XID               # 5.2    [3] DEVANAGARI SIGN PUSH
 1361..1368    ; Not_XID                        # 3.0    [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
 1372..137C    ; Not_XID                        # 3.0   [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND
 1390..1399    ; Not_XID                        # 4.1   [10] ETHIOPIC TONAL MARK YIZET..ETHIOPIC TONAL MARK KURT
-16EB..16ED    ; Not_XID                        # 3.0    [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION
 17D4..17D6    ; Not_XID                        # 3.0    [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH
 17D9..17DB    ; Not_XID                        # 3.0    [3] KHMER SIGN PHNAEK MUAN..KHMER CURRENCY SYMBOL RIEL
 17F0..17F9    ; Not_XID                        # 4.0   [10] KHMER SYMBOL LEK ATTAK SON..KHMER SYMBOL LEK ATTAK PRAM-BUON
@@ -1923,7 +1924,7 @@ A8F8..A8FA    ; Obsolete Not_XID               # 5.2    [3] DEVANAGARI SIGN PUSH
 2E33..2E34    ; Not_XID                        # 6.1    [2] RAISED DOT..RAISED COMMA
 2E36..2E38    ; Not_XID                        # 6.1    [3] DAGGER WITH LEFT GUARD..TURNED DAGGER
 2E3A..2E3B    ; Not_XID                        # 6.1    [2] TWO-EM DASH..THREE-EM DASH
-2E3C..2E42    ; Not_XID                        # 7.0    [7] STENOGRAPHIC FULL STOP..DOUBLE LOW-REVERSED-9 QUOTATION MARK
+2E3D..2E42    ; Not_XID                        # 7.0    [6] VERTICAL SIX DOTS..DOUBLE LOW-REVERSED-9 QUOTATION MARK
 2E43..2E44    ; Not_XID                        # 9.0    [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK
 2E45..2E49    ; Not_XID                        # 10.0   [5] INVERTED LOW KAVYKA..DOUBLE STACKED COMMA
 2E4A..2E4E    ; Not_XID                        # 11.0   [5] DOTTED SOLIDUS..PUNCTUS ELEVATUS MARK
@@ -2193,7 +2194,7 @@ FFFD          ; Not_XID                        # 1.1        REPLACEMENT CHARACTE
 1FB94..1FBCA  ; Not_XID                        # 13.0  [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
 1FBCB..1FBEF  ; Not_XID                        # 16.0  [37] WHITE CROSS MARK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE
 
-# Total code points: 6415
+# Total code points: 6411
 
 #	Identifier_Type:	Not_NFKC
 

diff --git a/unicodetools/data/security/dev/confusables.txt b/unicodetools/data/security/dev/confusables.txt
@@ -1,5 +1,5 @@
 # confusables.txt
-# Date: 2024-05-31, 21:12:55 GMT
+# Date: 2024-08-14, 23:39:57 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
@@ -593,7 +593,7 @@ FF40 ;	0027 ;	MA	#* ( ｀ → ' ) FULLWIDTH GRAVE ACCENT → APOSTROPHE	# →‘
 02B9 ;	0027 ;	MA	# ( ʹ → ' ) MODIFIER LETTER PRIME → APOSTROPHE	# 
 0374 ;	0027 ;	MA	# ( ʹ → ' ) GREEK NUMERAL SIGN → APOSTROPHE	# →′→
 02C8 ;	0027 ;	MA	# ( ˈ → ' ) MODIFIER LETTER VERTICAL LINE → APOSTROPHE	# 
-02CA ;	0027 ;	MA	# ( ˊ → ' ) MODIFIER LETTER ACUTE ACCENT → APOSTROPHE	# →΄→→ʹ→
+02CA ;	0027 ;	MA	# ( ˊ → ' ) MODIFIER LETTER ACUTE ACCENT → APOSTROPHE	# →ʹ→→′→
 02CB ;	0027 ;	MA	# ( ˋ → ' ) MODIFIER LETTER GRAVE ACCENT → APOSTROPHE	# →｀→→‘→
 02F4 ;	0027 ;	MA	#* ( ˴ → ' ) MODIFIER LETTER MIDDLE GRAVE ACCENT → APOSTROPHE	# →ˋ→→｀→→‘→
 02BB ;	0027 ;	MA	# ( ʻ → ' ) MODIFIER LETTER TURNED COMMA → APOSTROPHE	# →‘→
@@ -1904,8 +1904,8 @@ ABAF ;	0063 ;	MA	# ( ꮯ → c ) CHEROKEE SMALL LETTER TLI → LATIN SMALL LETTE
 2DED ;	0368 ;	MA	# ( ⷭ → ͨ ) COMBINING CYRILLIC LETTER ES → COMBINING LATIN SMALL LETTER C	# 
 
 1F74C ;	0043 ;	MA	#* ( 🝌 → C ) ALCHEMICAL SYMBOL FOR CALX → LATIN CAPITAL LETTER C	# 
-118F2 ;	0043 ;	MA	#* ( 𑣲 → C ) WARANG CITI NUMBER NINETY → LATIN CAPITAL LETTER C	# 
 118E9 ;	0043 ;	MA	# ( 𑣩 → C ) WARANG CITI DIGIT NINE → LATIN CAPITAL LETTER C	# 
+118F2 ;	0043 ;	MA	#* ( 𑣲 → C ) WARANG CITI NUMBER NINETY → LATIN CAPITAL LETTER C	# 
 FF23 ;	0043 ;	MA	# ( Ｃ → C ) FULLWIDTH LATIN CAPITAL LETTER C → LATIN CAPITAL LETTER C	# →С→
 216D ;	0043 ;	MA	# ( Ⅽ → C ) ROMAN NUMERAL ONE HUNDRED → LATIN CAPITAL LETTER C	# 
 2102 ;	0043 ;	MA	# ( ℂ → C ) DOUBLE-STRUCK CAPITAL C → LATIN CAPITAL LETTER C	# 
@@ -3795,8 +3795,8 @@ A7DC ;	0245 0338 ;	MA	# ( Ƛ → Ʌ̸ ) LATIN CAPITAL LETTER LAMBDA WITH STROKE
 1170F ;	0077 ;	MA	# ( 𑜏 → w ) AHOM LETTER SA → LATIN SMALL LETTER W	# 
 AB83 ;	0077 ;	MA	# ( ꮃ → w ) CHEROKEE SMALL LETTER LA → LATIN SMALL LETTER W	# →ᴡ→
 
-118EF ;	0057 ;	MA	#* ( 𑣯 → W ) WARANG CITI NUMBER SIXTY → LATIN CAPITAL LETTER W	# 
 118E6 ;	0057 ;	MA	# ( 𑣦 → W ) WARANG CITI DIGIT SIX → LATIN CAPITAL LETTER W	# 
+118EF ;	0057 ;	MA	#* ( 𑣯 → W ) WARANG CITI NUMBER SIXTY → LATIN CAPITAL LETTER W	# 
 1CCEC ;	0057 ;	MA	#* ( 𜳬 → W ) OUTLINED LATIN CAPITAL LETTER W → LATIN CAPITAL LETTER W	# 
 1D416 ;	0057 ;	MA	# ( 𝐖 → W ) MATHEMATICAL BOLD CAPITAL W → LATIN CAPITAL LETTER W	# 
 1D44A ;	0057 ;	MA	# ( 𝑊 → W ) MATHEMATICAL ITALIC CAPITAL W → LATIN CAPITAL LETTER W	# 
@@ -4002,8 +4002,8 @@ A76B ;	021D ;	MA	# ( ꝫ → ȝ ) LATIN SMALL LETTER ET → LATIN SMALL LETTER Y
 AB93 ;	007A ;	MA	# ( ꮓ → z ) CHEROKEE SMALL LETTER NO → LATIN SMALL LETTER Z	# →ᴢ→
 118C4 ;	007A ;	MA	# ( 𑣄 → z ) WARANG CITI SMALL LETTER YA → LATIN SMALL LETTER Z	# 
 
-102F5 ;	005A ;	MA	#* ( 𐋵 → Z ) COPTIC EPACT NUMBER THREE HUNDRED → LATIN CAPITAL LETTER Z	# 
 118E5 ;	005A ;	MA	# ( 𑣥 → Z ) WARANG CITI DIGIT FIVE → LATIN CAPITAL LETTER Z	# 
+102F5 ;	005A ;	MA	#* ( 𐋵 → Z ) COPTIC EPACT NUMBER THREE HUNDRED → LATIN CAPITAL LETTER Z	# 
 FF3A ;	005A ;	MA	# ( Ｚ → Z ) FULLWIDTH LATIN CAPITAL LETTER Z → LATIN CAPITAL LETTER Z	# →Ζ→
 2124 ;	005A ;	MA	# ( ℤ → Z ) DOUBLE-STRUCK CAPITAL Z → LATIN CAPITAL LETTER Z	# 
 2128 ;	005A ;	MA	# ( ℨ → Z ) BLACK-LETTER CAPITAL Z → LATIN CAPITAL LETTER Z	# 

diff --git a/unicodetools/data/security/dev/confusablesSummary.txt b/unicodetools/data/security/dev/confusablesSummary.txt
@@ -1,5 +1,5 @@
 # confusablesSummary.txt
-# Date: 2024-05-31, 21:12:55 GMT
+# Date: 2024-08-14, 23:39:56 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
@@ -91,7 +91,7 @@
 ←	(‎ ʽ ‎)	02BD	 MODIFIER LETTER REVERSED COMMA	# →‘→
 ←	(‎ ʾ ‎)	02BE	 MODIFIER LETTER RIGHT HALF RING	# →ʼ→→′→
 ←	(‎ ˈ ‎)	02C8	 MODIFIER LETTER VERTICAL LINE
-←	(‎ ˊ ‎)	02CA	 MODIFIER LETTER ACUTE ACCENT	# →΄→→ʹ→
+←	(‎ ˊ ‎)	02CA	 MODIFIER LETTER ACUTE ACCENT	# →ʹ→→′→
 ←	(‎ ˋ ‎)	02CB	 MODIFIER LETTER GRAVE ACCENT	# →｀→→‘→
 ←	(‎ ߴ ‎)	07F4	 NKO HIGH TONE APOSTROPHE	# →’→
 ←	(‎ ߵ ‎)	07F5	 NKO LOW TONE APOSTROPHE	# →‘→

diff --git a/unicodetools/data/security/dev/data/draft-restrictions.txt b/unicodetools/data/security/dev/data/draft-restrictions.txt
@@ -24194,6 +24194,7 @@ AB63          ;  ; Uncommon_Use #      (ꭣ)  LATIN SMALL LETTER UO
 0038          ; Allowed ; Recommended #      (8)  DIGIT EIGHT
 0039          ; Allowed ; Recommended #      (9)  DIGIT NINE
 0041..005A    ; Allowed ; Recommended # [26] (A..Z)  LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z
+005F          ; Allowed ; Recommended #      (_)  LOW LINE
 0061          ; Allowed ; Recommended #      (a)  LATIN SMALL LETTER A
 0062          ; Allowed ; Recommended #      (b)  LATIN SMALL LETTER B
 0063          ; Allowed ; Recommended #      (c)  LATIN SMALL LETTER C
@@ -54817,11 +54818,7 @@ FA29          ; Allowed ; Recommended #      (﨩)  CJK COMPATIBILITY IDEOGRAPH-
 323AF         ; Allowed ; Recommended #      (𲎯)  CJK UNIFIED IDEOGRAPH-323AF
 E0100..E01EF  ; Allowed ; Recommended # [240] (U+E0100..U+E01EF)  VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 113001
-
-005F          ; ~IDNA #      (_)  LOW LINE
-
-# Total code points: 1
+# Total code points: 113002
 
 0000..002F    ; ~Unicode Identifier # [48] (U+0000../)  <control-0000>..SOLIDUS
 003A..0040    ; ~Unicode Identifier #  [7] (:..@)  COLON..COMMERCIAL AT

diff --git a/unicodetools/data/security/dev/data/idnchars.txt b/unicodetools/data/security/dev/data/idnchars.txt
@@ -1,5 +1,5 @@
 # idnchars.txt
-# Date: 2024-05-03, 03:51:22 GMT
+# Date: 2024-08-14, 23:39:58 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
@@ -11,8 +11,10 @@
 #
 # Allowed as output characters
 
+0027          ; output #      (')  APOSTROPHE
 002D..002E    ; output #  [2] (-...)  HYPHEN-MINUS..FULL STOP
-0030..0039    ; output # [10] (0..9)  DIGIT ZERO..DIGIT NINE
+0030..003A    ; output # [11] (0..:)  DIGIT ZERO..COLON
+005F          ; output #      (_)  LOW LINE
 0061..007A    ; output # [26] (a..z)  LATIN SMALL LETTER A..LATIN SMALL LETTER Z
 00B7          ; output #      (·)  MIDDLE DOT
 00DF..00F6    ; output # [24] (ß..ö)  LATIN SMALL LETTER SHARP S..LATIN SMALL LETTER O WITH DIAERESIS
@@ -663,7 +665,7 @@ FA27..FA29    ; output #  [3] (﨧..﨩)  CJK COMPATIBILITY IDEOGRAPH-FA27..CJK
 30000..3134A  ; output # [4939] (𰀀..𱍊)  CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 31350..323AF  ; output # [4192] (𱍐..𲎯)  CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 112107
+# Total code points: 112110
 
 # Not allowed at start of identifier