about summary refs log tree commit diff
path: root/localedata/unicode-gen/PropList.txt
diff options
context:
space:
mode:
Diffstat (limited to 'localedata/unicode-gen/PropList.txt')
-rw-r--r--localedata/unicode-gen/PropList.txt100
1 files changed, 73 insertions, 27 deletions
diff --git a/localedata/unicode-gen/PropList.txt b/localedata/unicode-gen/PropList.txt
index 7d2f44c56f..0a5a934682 100644
--- a/localedata/unicode-gen/PropList.txt
+++ b/localedata/unicode-gen/PropList.txt
@@ -1,6 +1,6 @@
-# PropList-13.0.0.txt
-# Date: 2019-11-27, 03:13:28 GMT
-# © 2019 Unicode®, Inc.
+# PropList-14.0.0.txt
+# Date: 2021-08-12, 23:13:05 GMT
+# © 2021 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
 #
@@ -54,6 +54,7 @@
 2E1A          ; Dash # Pd       HYPHEN WITH DIAERESIS
 2E3A..2E3B    ; Dash # Pd   [2] TWO-EM DASH..THREE-EM DASH
 2E40          ; Dash # Pd       DOUBLE HYPHEN
+2E5D          ; Dash # Pd       OBLIQUE HYPHEN
 301C          ; Dash # Pd       WAVE DASH
 3030          ; Dash # Pd       WAVY DASH
 30A0          ; Dash # Pd       KATAKANA-HIRAGANA DOUBLE HYPHEN
@@ -63,7 +64,7 @@ FE63          ; Dash # Pd       SMALL HYPHEN-MINUS
 FF0D          ; Dash # Pd       FULLWIDTH HYPHEN-MINUS
 10EAD         ; Dash # Pd       YEZIDI HYPHENATION MARK
 
-# Total code points: 29
+# Total code points: 30
 
 # ================================================
 
@@ -126,7 +127,7 @@ FF63          ; Quotation_Mark # Pe       HALFWIDTH RIGHT CORNER BRACKET
 05C3          ; Terminal_Punctuation # Po       HEBREW PUNCTUATION SOF PASUQ
 060C          ; Terminal_Punctuation # Po       ARABIC COMMA
 061B          ; Terminal_Punctuation # Po       ARABIC SEMICOLON
-061E..061F    ; Terminal_Punctuation # Po   [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK
+061D..061F    ; Terminal_Punctuation # Po   [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK
 06D4          ; Terminal_Punctuation # Po       ARABIC FULL STOP
 0700..070A    ; Terminal_Punctuation # Po  [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION
 070C          ; Terminal_Punctuation # Po       SYRIAC HARKLEAN METOBELUS
@@ -150,6 +151,7 @@ FF63          ; Quotation_Mark # Pe       HALFWIDTH RIGHT CORNER BRACKET
 1AA8..1AAB    ; Terminal_Punctuation # Po   [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU
 1B5A..1B5B    ; Terminal_Punctuation # Po   [2] BALINESE PANTI..BALINESE PAMADA
 1B5D..1B5F    ; Terminal_Punctuation # Po   [3] BALINESE CARIK PAMUNGKAH..BALINESE CARIK PAREREN
+1B7D..1B7E    ; Terminal_Punctuation # Po   [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG
 1C3B..1C3F    ; Terminal_Punctuation # Po   [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK
 1C7E..1C7F    ; Terminal_Punctuation # Po   [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
 203C..203D    ; Terminal_Punctuation # Po   [2] DOUBLE EXCLAMATION MARK..INTERROBANG
@@ -159,6 +161,7 @@ FF63          ; Quotation_Mark # Pe       HALFWIDTH RIGHT CORNER BRACKET
 2E41          ; Terminal_Punctuation # Po       REVERSED COMMA
 2E4C          ; Terminal_Punctuation # Po       MEDIEVAL COMMA
 2E4E..2E4F    ; Terminal_Punctuation # Po   [2] PUNCTUS ELEVATUS MARK..CORNISH VERSE DIVIDER
+2E53..2E54    ; Terminal_Punctuation # Po   [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK
 3001..3002    ; Terminal_Punctuation # Po   [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
 A4FE..A4FF    ; Terminal_Punctuation # Po   [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP
 A60D..A60F    ; Terminal_Punctuation # Po   [3] VAI COMMA..VAI QUESTION MARK
@@ -189,6 +192,7 @@ FF64          ; Terminal_Punctuation # Po       HALFWIDTH IDEOGRAPHIC COMMA
 10B3A..10B3F  ; Terminal_Punctuation # Po   [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
 10B99..10B9C  ; Terminal_Punctuation # Po   [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT
 10F55..10F59  ; Terminal_Punctuation # Po   [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
+10F86..10F89  ; Terminal_Punctuation # Po   [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS
 11047..1104D  ; Terminal_Punctuation # Po   [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS
 110BE..110C1  ; Terminal_Punctuation # Po   [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
 11141..11143  ; Terminal_Punctuation # Po   [3] CHAKMA DANDA..CHAKMA QUESTION MARK
@@ -220,7 +224,7 @@ FF64          ; Terminal_Punctuation # Po       HALFWIDTH IDEOGRAPHIC COMMA
 1BC9F         ; Terminal_Punctuation # Po       DUPLOYAN PUNCTUATION CHINOOK FULL STOP
 1DA87..1DA8A  ; Terminal_Punctuation # Po   [4] SIGNWRITING COMMA..SIGNWRITING COLON
 
-# Total code points: 267
+# Total code points: 276
 
 # ================================================
 
@@ -600,6 +604,7 @@ FF41..FF46    ; Hex_Digit # L&   [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
 1A6D..1A72    ; Other_Alphabetic # Mc   [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI
 1A73..1A74    ; Other_Alphabetic # Mn   [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG
 1ABF..1AC0    ; Other_Alphabetic # Mn   [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW
+1ACC..1ACE    ; Other_Alphabetic # Mn   [3] COMBINING LATIN SMALL LETTER INSULAR G..COMBINING LATIN SMALL LETTER INSULAR T
 1B00..1B03    ; Other_Alphabetic # Mn   [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
 1B04          ; Other_Alphabetic # Mc       BALINESE SIGN BISAH
 1B35          ; Other_Alphabetic # Mc       BALINESE VOWEL SIGN TEDUNG
@@ -686,10 +691,12 @@ FB1E          ; Other_Alphabetic # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
 11001         ; Other_Alphabetic # Mn       BRAHMI SIGN ANUSVARA
 11002         ; Other_Alphabetic # Mc       BRAHMI SIGN VISARGA
 11038..11045  ; Other_Alphabetic # Mn  [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU
+11073..11074  ; Other_Alphabetic # Mn   [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O
 11082         ; Other_Alphabetic # Mc       KAITHI SIGN VISARGA
 110B0..110B2  ; Other_Alphabetic # Mc   [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
 110B3..110B6  ; Other_Alphabetic # Mn   [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
 110B7..110B8  ; Other_Alphabetic # Mc   [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
+110C2         ; Other_Alphabetic # Mn       KAITHI VOWEL SIGN VOCALIC R
 11100..11102  ; Other_Alphabetic # Mn   [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
 11127..1112B  ; Other_Alphabetic # Mn   [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
 1112C         ; Other_Alphabetic # Mc       CHAKMA VOWEL SIGN E
@@ -815,7 +822,7 @@ FB1E          ; Other_Alphabetic # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
 1F150..1F169  ; Other_Alphabetic # So  [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
 1F170..1F189  ; Other_Alphabetic # So  [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
 
-# Total code points: 1398
+# Total code points: 1404
 
 # ================================================
 
@@ -824,7 +831,7 @@ FB1E          ; Other_Alphabetic # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
 3021..3029    ; Ideographic # Nl   [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
 3038..303A    ; Ideographic # Nl   [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
 3400..4DBF    ; Ideographic # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF
-4E00..9FFC    ; Ideographic # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC
+4E00..9FFF    ; Ideographic # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF
 F900..FA6D    ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
 FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
 16FE4         ; Ideographic # Mn       KHITAN SMALL SCRIPT FILLER
@@ -832,15 +839,15 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 18800..18CD5  ; Ideographic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
 18D00..18D08  ; Ideographic # Lo   [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08
 1B170..1B2FB  ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
-20000..2A6DD  ; Ideographic # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD
-2A700..2B734  ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
+20000..2A6DF  ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
+2A700..2B738  ; Ideographic # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
 2B740..2B81D  ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 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
 
-# Total code points: 101652
+# Total code points: 101661
 
 # ================================================
 
@@ -885,6 +892,9 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 07EB..07F3    ; Diacritic # Mn   [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
 07F4..07F5    ; Diacritic # Lm   [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE
 0818..0819    ; Diacritic # Mn   [2] SAMARITAN MARK OCCLUSION..SAMARITAN MARK DAGESH
+0898..089F    ; Diacritic # Mn   [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA
+08C9          ; Diacritic # Lm       ARABIC SMALL FARSI YEH
+08CA..08D2    ; Diacritic # Mn   [9] ARABIC SMALL HIGH FARSI YEH..ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW
 08E3..08FE    ; Diacritic # Mn  [28] ARABIC TURNED DAMMA BELOW..ARABIC DAMMA WITH DOT
 093C          ; Diacritic # Mn       DEVANAGARI SIGN NUKTA
 094D          ; Diacritic # Mn       DEVANAGARI SIGN VIRAMA
@@ -901,6 +911,7 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 0B4D          ; Diacritic # Mn       ORIYA SIGN VIRAMA
 0B55          ; Diacritic # Mn       ORIYA SIGN OVERLINE
 0BCD          ; Diacritic # Mn       TAMIL SIGN VIRAMA
+0C3C          ; Diacritic # Mn       TELUGU SIGN NUKTA
 0C4D          ; Diacritic # Mn       TELUGU SIGN VIRAMA
 0CBC          ; Diacritic # Mn       KANNADA SIGN NUKTA
 0CCD          ; Diacritic # Mn       KANNADA SIGN VIRAMA
@@ -928,12 +939,16 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 108F          ; Diacritic # Mc       MYANMAR SIGN RUMAI PALAUNG TONE-5
 109A..109B    ; Diacritic # Mc   [2] MYANMAR SIGN KHAMTI TONE-1..MYANMAR SIGN KHAMTI TONE-3
 135D..135F    ; Diacritic # Mn   [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK
+1714          ; Diacritic # Mn       TAGALOG SIGN VIRAMA
+1715          ; Diacritic # Mc       TAGALOG SIGN PAMUDPOD
 17C9..17D3    ; Diacritic # Mn  [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
 17DD          ; Diacritic # Mn       KHMER SIGN ATTHACAN
 1939..193B    ; Diacritic # Mn   [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
 1A75..1A7C    ; Diacritic # Mn   [8] TAI THAM SIGN TONE-1..TAI THAM SIGN KHUEN-LUE KARAN
 1A7F          ; Diacritic # Mn       TAI THAM COMBINING CRYPTOGRAMMIC DOT
 1AB0..1ABD    ; Diacritic # Mn  [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW
+1ABE          ; Diacritic # Me       COMBINING PARENTHESES OVERLAY
+1AC1..1ACB    ; Diacritic # Mn  [11] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING TRIPLE ACUTE ACCENT
 1B34          ; Diacritic # Mn       BALINESE SIGN REREKAN
 1B44          ; Diacritic # Mc       BALINESE ADEG ADEG
 1B6B..1B73    ; Diacritic # Mn   [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
@@ -952,8 +967,7 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 1CF8..1CF9    ; Diacritic # Mn   [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
 1D2C..1D6A    ; Diacritic # Lm  [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
 1DC4..1DCF    ; Diacritic # Mn  [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW
-1DF5..1DF9    ; Diacritic # Mn   [5] COMBINING UP TACK ABOVE..COMBINING WIDE INVERTED BRIDGE BELOW
-1DFD..1DFF    ; Diacritic # Mn   [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+1DF5..1DFF    ; Diacritic # Mn  [11] COMBINING UP TACK ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
 1FBD          ; Diacritic # Sk       GREEK KORONIS
 1FBF..1FC1    ; Diacritic # Sk   [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI
 1FCD..1FCF    ; Diacritic # Sk   [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI
@@ -1008,10 +1022,16 @@ FF70          ; Diacritic # Lm       HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
 FF9E..FF9F    ; Diacritic # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
 FFE3          ; Diacritic # Sk       FULLWIDTH MACRON
 102E0         ; Diacritic # Mn       COPTIC EPACT THOUSANDS MARK
+10780..10785  ; Diacritic # Lm   [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK
+10787..107B0  ; Diacritic # Lm  [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK
+107B2..107BA  ; Diacritic # Lm   [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL
 10AE5..10AE6  ; Diacritic # Mn   [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
 10D22..10D23  ; Diacritic # Lo   [2] HANIFI ROHINGYA MARK SAKIN..HANIFI ROHINGYA MARK NA KHONNA
 10D24..10D27  ; Diacritic # Mn   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
 10F46..10F50  ; Diacritic # Mn  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
+10F82..10F85  ; Diacritic # Mn   [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
+11046         ; Diacritic # Mn       BRAHMI VIRAMA
+11070         ; Diacritic # Mn       BRAHMI SIGN OLD TAMIL VIRAMA
 110B9..110BA  ; Diacritic # Mn   [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
 11133..11134  ; Diacritic # Mn   [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
 11173         ; Diacritic # Mn       MAHAJANI SIGN NUKTA
@@ -1049,18 +1069,24 @@ FFE3          ; Diacritic # Sk       FULLWIDTH MACRON
 16F8F..16F92  ; Diacritic # Mn   [4] MIAO TONE RIGHT..MIAO TONE BELOW
 16F93..16F9F  ; Diacritic # Lm  [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
 16FF0..16FF1  ; Diacritic # Mc   [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
+1AFF0..1AFF3  ; Diacritic # Lm   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
+1AFF5..1AFFB  ; Diacritic # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
+1AFFD..1AFFE  ; Diacritic # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
+1CF00..1CF2D  ; Diacritic # Mn  [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT
+1CF30..1CF46  ; Diacritic # Mn  [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG
 1D167..1D169  ; Diacritic # Mn   [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
 1D16D..1D172  ; Diacritic # Mc   [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
 1D17B..1D182  ; Diacritic # Mn   [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
 1D185..1D18B  ; Diacritic # Mn   [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
 1D1AA..1D1AD  ; Diacritic # Mn   [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
 1E130..1E136  ; Diacritic # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
+1E2AE         ; Diacritic # Mn       TOTO SIGN RISING TONE
 1E2EC..1E2EF  ; Diacritic # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
 1E8D0..1E8D6  ; Diacritic # Mn   [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
 1E944..1E946  ; Diacritic # Mn   [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
 1E948..1E94A  ; Diacritic # Mn   [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA
 
-# Total code points: 882
+# Total code points: 1064
 
 # ================================================
 
@@ -1088,6 +1114,7 @@ AA70          ; Extender # Lm       MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION
 AADD          ; Extender # Lm       TAI VIET SYMBOL SAM
 AAF3..AAF4    ; Extender # Lm   [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
 FF70          ; Extender # Lm       HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
+10781..10782  ; Extender # Lm   [2] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON
 1135D         ; Extender # Lo       GRANTHA SIGN PLUTA
 115C6..115C8  ; Extender # Po   [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3
 11A98         ; Extender # Mn       SOYOMBO GEMINATION MARK
@@ -1097,7 +1124,7 @@ FF70          ; Extender # Lm       HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
 1E13C..1E13D  ; Extender # Lm   [2] NYIAKENG PUACHUE HMONG SIGN XW XW..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
 1E944..1E946  ; Extender # Mn   [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
 
-# Total code points: 48
+# Total code points: 50
 
 # ================================================
 
@@ -1121,8 +1148,12 @@ A69C..A69D    ; Other_Lowercase # Lm   [2] MODIFIER LETTER CYRILLIC HARD SIGN..M
 A770          ; Other_Lowercase # Lm       MODIFIER LETTER US
 A7F8..A7F9    ; Other_Lowercase # Lm   [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
 AB5C..AB5F    ; Other_Lowercase # Lm   [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
+10780         ; Other_Lowercase # Lm       MODIFIER LETTER SMALL CAPITAL AA
+10783..10785  ; Other_Lowercase # Lm   [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK
+10787..107B0  ; Other_Lowercase # Lm  [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK
+107B2..107BA  ; Other_Lowercase # Lm   [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL
 
-# Total code points: 189
+# Total code points: 244
 
 # ================================================
 
@@ -1211,7 +1242,7 @@ E0020..E007F  ; Other_Grapheme_Extend # Cf  [96] TAG SPACE..CANCEL TAG
 # ================================================
 
 3400..4DBF    ; Unified_Ideograph # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF
-4E00..9FFC    ; Unified_Ideograph # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC
+4E00..9FFF    ; Unified_Ideograph # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF
 FA0E..FA0F    ; Unified_Ideograph # Lo   [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
 FA11          ; Unified_Ideograph # Lo       CJK COMPATIBILITY IDEOGRAPH-FA11
 FA13..FA14    ; Unified_Ideograph # Lo   [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
@@ -1219,14 +1250,14 @@ FA1F          ; Unified_Ideograph # Lo       CJK COMPATIBILITY IDEOGRAPH-FA1F
 FA21          ; Unified_Ideograph # Lo       CJK COMPATIBILITY IDEOGRAPH-FA21
 FA23..FA24    ; Unified_Ideograph # Lo   [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24
 FA27..FA29    ; Unified_Ideograph # Lo   [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
-20000..2A6DD  ; Unified_Ideograph # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD
-2A700..2B734  ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
+20000..2A6DF  ; Unified_Ideograph # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
+2A700..2B738  ; Unified_Ideograph # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
 2B740..2B81D  ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 30000..3134A  ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 
-# Total code points: 92856
+# Total code points: 92865
 
 # ================================================
 
@@ -1291,8 +1322,9 @@ E0001         ; Deprecated # Cf       LANGUAGE TAG
 1D62A..1D62B  ; Soft_Dotted # L&   [2] MATHEMATICAL SANS-SERIF ITALIC SMALL I..MATHEMATICAL SANS-SERIF ITALIC SMALL J
 1D65E..1D65F  ; Soft_Dotted # L&   [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J
 1D692..1D693  ; Soft_Dotted # L&   [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J
+1DF1A         ; Soft_Dotted # L&       LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK
 
-# Total code points: 46
+# Total code points: 47
 
 # ================================================
 
@@ -1330,7 +1362,7 @@ AABB..AABC    ; Logical_Order_Exception # Lo   [2] TAI VIET VOWEL AUE..TAI VIET
 002E          ; Sentence_Terminal # Po       FULL STOP
 003F          ; Sentence_Terminal # Po       QUESTION MARK
 0589          ; Sentence_Terminal # Po       ARMENIAN FULL STOP
-061E..061F    ; Sentence_Terminal # Po   [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK
+061D..061F    ; Sentence_Terminal # Po   [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK
 06D4          ; Sentence_Terminal # Po       ARABIC FULL STOP
 0700..0702    ; Sentence_Terminal # Po   [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP
 07F9          ; Sentence_Terminal # Po       NKO EXCLAMATION MARK
@@ -1349,12 +1381,14 @@ AABB..AABC    ; Logical_Order_Exception # Lo   [2] TAI VIET VOWEL AUE..TAI VIET
 1AA8..1AAB    ; Sentence_Terminal # Po   [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU
 1B5A..1B5B    ; Sentence_Terminal # Po   [2] BALINESE PANTI..BALINESE PAMADA
 1B5E..1B5F    ; Sentence_Terminal # Po   [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN
+1B7D..1B7E    ; Sentence_Terminal # Po   [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG
 1C3B..1C3C    ; Sentence_Terminal # Po   [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL
 1C7E..1C7F    ; Sentence_Terminal # Po   [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
 203C..203D    ; Sentence_Terminal # Po   [2] DOUBLE EXCLAMATION MARK..INTERROBANG
 2047..2049    ; Sentence_Terminal # Po   [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
 2E2E          ; Sentence_Terminal # Po       REVERSED QUESTION MARK
 2E3C          ; Sentence_Terminal # Po       STENOGRAPHIC FULL STOP
+2E53..2E54    ; Sentence_Terminal # Po   [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK
 3002          ; Sentence_Terminal # Po       IDEOGRAPHIC FULL STOP
 A4FF          ; Sentence_Terminal # Po       LISU PUNCTUATION FULL STOP
 A60E..A60F    ; Sentence_Terminal # Po   [2] VAI FULL STOP..VAI QUESTION MARK
@@ -1375,6 +1409,7 @@ FF1F          ; Sentence_Terminal # Po       FULLWIDTH QUESTION MARK
 FF61          ; Sentence_Terminal # Po       HALFWIDTH IDEOGRAPHIC FULL STOP
 10A56..10A57  ; Sentence_Terminal # Po   [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
 10F55..10F59  ; Sentence_Terminal # Po   [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
+10F86..10F89  ; Sentence_Terminal # Po   [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS
 11047..11048  ; Sentence_Terminal # Po   [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
 110BE..110C1  ; Sentence_Terminal # Po   [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
 11141..11143  ; Sentence_Terminal # Po   [3] CHAKMA DANDA..CHAKMA QUESTION MARK
@@ -1403,15 +1438,16 @@ FF61          ; Sentence_Terminal # Po       HALFWIDTH IDEOGRAPHIC FULL STOP
 1BC9F         ; Sentence_Terminal # Po       DUPLOYAN PUNCTUATION CHINOOK FULL STOP
 1DA88         ; Sentence_Terminal # Po       SIGNWRITING FULL STOP
 
-# Total code points: 143
+# Total code points: 152
 
 # ================================================
 
 180B..180D    ; Variation_Selector # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+180F          ; Variation_Selector # Mn       MONGOLIAN FREE VARIATION SELECTOR FOUR
 FE00..FE0F    ; Variation_Selector # Mn  [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
 E0100..E01EF  ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 259
+# Total code points: 260
 
 # ================================================
 
@@ -1644,8 +1680,17 @@ E0100..E01EF  ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S
 2E42          ; Pattern_Syntax # Ps       DOUBLE LOW-REVERSED-9 QUOTATION MARK
 2E43..2E4F    ; Pattern_Syntax # Po  [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER
 2E50..2E51    ; Pattern_Syntax # So   [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR
-2E52          ; Pattern_Syntax # Po       TIRONIAN SIGN CAPITAL ET
-2E53..2E7F    ; Pattern_Syntax # Cn  [45] <reserved-2E53>..<reserved-2E7F>
+2E52..2E54    ; Pattern_Syntax # Po   [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK
+2E55          ; Pattern_Syntax # Ps       LEFT SQUARE BRACKET WITH STROKE
+2E56          ; Pattern_Syntax # Pe       RIGHT SQUARE BRACKET WITH STROKE
+2E57          ; Pattern_Syntax # Ps       LEFT SQUARE BRACKET WITH DOUBLE STROKE
+2E58          ; Pattern_Syntax # Pe       RIGHT SQUARE BRACKET WITH DOUBLE STROKE
+2E59          ; Pattern_Syntax # Ps       TOP HALF LEFT PARENTHESIS
+2E5A          ; Pattern_Syntax # Pe       TOP HALF RIGHT PARENTHESIS
+2E5B          ; Pattern_Syntax # Ps       BOTTOM HALF LEFT PARENTHESIS
+2E5C          ; Pattern_Syntax # Pe       BOTTOM HALF RIGHT PARENTHESIS
+2E5D          ; Pattern_Syntax # Pd       OBLIQUE HYPHEN
+2E5E..2E7F    ; Pattern_Syntax # Cn  [34] <reserved-2E5E>..<reserved-2E7F>
 3001..3003    ; Pattern_Syntax # Po   [3] IDEOGRAPHIC COMMA..DITTO MARK
 3008          ; Pattern_Syntax # Ps       LEFT ANGLE BRACKET
 3009          ; Pattern_Syntax # Pe       RIGHT ANGLE BRACKET
@@ -1682,11 +1727,12 @@ FE45..FE46    ; Pattern_Syntax # Po   [2] SESAME DOT..WHITE SESAME DOT
 0600..0605    ; Prepended_Concatenation_Mark # Cf   [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
 06DD          ; Prepended_Concatenation_Mark # Cf       ARABIC END OF AYAH
 070F          ; Prepended_Concatenation_Mark # Cf       SYRIAC ABBREVIATION MARK
+0890..0891    ; Prepended_Concatenation_Mark # Cf   [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
 08E2          ; Prepended_Concatenation_Mark # Cf       ARABIC DISPUTED END OF AYAH
 110BD         ; Prepended_Concatenation_Mark # Cf       KAITHI NUMBER SIGN
 110CD         ; Prepended_Concatenation_Mark # Cf       KAITHI NUMBER SIGN ABOVE
 
-# Total code points: 11
+# Total code points: 13
 
 # ================================================