summaryrefslogtreecommitdiffstats
path: root/util
diff options
context:
space:
mode:
authorLars Knoll <lars.knoll@qt.io>2017-12-12 10:14:28 +0100
committerLars Knoll <lars.knoll@qt.io>2018-01-03 07:47:26 +0000
commit41b4e154d617a820cd7f7f732838647425a58227 (patch)
tree27e9300e3fc275bf4e50de8fb2c5e1f8aeb40fab /util
parent8bfabb34dec8a437a08b5a6e0ecac4a9dd3ae18c (diff)
Update Text segmentation and line break data to Unicode 10.0
Also adjusted the text segmentation and line break algorithms so that they can handle the new data, and pass the test suite. Change-Id: Ib727fd80003e34e96458d7a681996de3fa3691e7 Reviewed-by: Eskil Abrahamsen Blomfeldt <eskil.abrahamsen-blomfeldt@qt.io>
Diffstat (limited to 'util')
-rw-r--r--util/unicode/data/GraphemeBreakProperty.txt175
-rw-r--r--util/unicode/data/LineBreak.txt359
-rw-r--r--util/unicode/data/SentenceBreakProperty.txt136
-rw-r--r--util/unicode/data/WordBreakProperty.txt212
-rw-r--r--util/unicode/main.cpp105
5 files changed, 817 insertions, 170 deletions
diff --git a/util/unicode/data/GraphemeBreakProperty.txt b/util/unicode/data/GraphemeBreakProperty.txt
index fba2ee8793..32bb12e47e 100644
--- a/util/unicode/data/GraphemeBreakProperty.txt
+++ b/util/unicode/data/GraphemeBreakProperty.txt
@@ -1,10 +1,11 @@
-# GraphemeBreakProperty-8.0.0.txt
-# Date: 2015-02-13, 13:47:14 GMT [MD]
+# GraphemeBreakProperty-10.0.0.txt
+# Date: 2017-03-12, 07:03:41 GMT
+# © 2017 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
#
# Unicode Character Database
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-# For documentation, see http://www.unicode.org/reports/tr44/
+# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
@@ -17,6 +18,21 @@
# ================================================
+0600..0605 ; Prepend # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
+06DD ; Prepend # Cf ARABIC END OF AYAH
+070F ; Prepend # Cf SYRIAC ABBREVIATION MARK
+08E2 ; Prepend # Cf ARABIC DISPUTED END OF AYAH
+0D4E ; Prepend # Lo MALAYALAM LETTER DOT REPH
+110BD ; Prepend # Cf KAITHI NUMBER SIGN
+111C2..111C3 ; Prepend # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA
+11A3A ; Prepend # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
+11A86..11A89 ; Prepend # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
+11D46 ; Prepend # Lo MASARAM GONDI REPHA
+
+# Total code points: 19
+
+# ================================================
+
000D ; CR # Cc <control-000D>
# Total code points: 1
@@ -34,10 +50,7 @@
000E..001F ; Control # Cc [18] <control-000E>..<control-001F>
007F..009F ; Control # Cc [33] <control-007F>..<control-009F>
00AD ; Control # Cf SOFT HYPHEN
-0600..0605 ; Control # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
061C ; Control # Cf ARABIC LETTER MARK
-06DD ; Control # Cf ARABIC END OF AYAH
-070F ; Control # Cf SYRIAC ABBREVIATION MARK
180E ; Control # Cf MONGOLIAN VOWEL SEPARATOR
200B ; Control # Cf ZERO WIDTH SPACE
200E..200F ; Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
@@ -51,17 +64,15 @@ D800..DFFF ; Control # Cs [2048] <surrogate-D800>..<surrogate-DFFF>
FEFF ; Control # Cf ZERO WIDTH NO-BREAK SPACE
FFF0..FFF8 ; Control # Cn [9] <reserved-FFF0>..<reserved-FFF8>
FFF9..FFFB ; Control # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
-110BD ; Control # Cf KAITHI NUMBER SIGN
1BCA0..1BCA3 ; Control # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Control # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0000 ; Control # Cn <reserved-E0000>
E0001 ; Control # Cf LANGUAGE TAG
E0002..E001F ; Control # Cn [30] <reserved-E0002>..<reserved-E001F>
-E0020..E007F ; Control # Cf [96] TAG SPACE..CANCEL TAG
E0080..E00FF ; Control # Cn [128] <reserved-E0080>..<reserved-E00FF>
E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
-# Total code points: 6030
+# Total code points: 5925
# ================================================
@@ -89,6 +100,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
+08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
093C ; Extend # Mn DEVANAGARI SIGN NUKTA
@@ -117,6 +129,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
0AC7..0AC8 ; Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
0ACD ; Extend # Mn GUJARATI SIGN VIRAMA
0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
+0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU
0B3C ; Extend # Mn ORIYA SIGN NUKTA
0B3E ; Extend # Mc ORIYA VOWEL SIGN AA
@@ -145,7 +158,8 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
-0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU
+0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
+0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3E ; Extend # Mc MALAYALAM VOWEL SIGN AA
0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
0D4D ; Extend # Mn MALAYALAM SIGN VIRAMA
@@ -195,6 +209,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
17DD ; Extend # Mn KHMER SIGN ATTHACAN
180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA
1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
1927..1928 ; Extend # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
@@ -233,9 +248,9 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
1CED ; Extend # Mn VEDIC SIGN TIRYAK
1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE
1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
-1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
-1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
-200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
+1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
+1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+200C ; Extend # Cf ZERO WIDTH NON-JOINER
20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1 ; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE
@@ -256,7 +271,7 @@ A802 ; Extend # Mn SYLOTI NAGRI SIGN DVISVARA
A806 ; Extend # Mn SYLOTI NAGRI SIGN HASANTA
A80B ; Extend # Mn SYLOTI NAGRI SIGN ANUSVARA
A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
-A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA
+A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
@@ -309,6 +324,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
11234 ; Extend # Mn KHOJKI SIGN ANUSVARA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
+1123E ; Extend # Mn KHOJKI SIGN SUKUN
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
@@ -318,6 +334,9 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11357 ; Extend # Mc GRANTHA AU LENGTH MARK
11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
+11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
+11446 ; Extend # Mn NEWA SIGN NUKTA
114B0 ; Extend # Mc TIRHUTA VOWEL SIGN AA
114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
114BA ; Extend # Mn TIRHUTA VOWEL SIGN SHORT E
@@ -339,6 +358,27 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
+11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
+11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
+11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER
+11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
+11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA
+11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
+11D47 ; Extend # Mn MASARAM GONDI RA-KARA
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
@@ -356,10 +396,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK
1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
+1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
+1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
+E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-# Total code points: 1610
+# Total code points: 1901
# ================================================
@@ -444,6 +491,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1C34..1C35 ; SpacingMark # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG
1CE1 ; SpacingMark # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
1CF2..1CF3 ; SpacingMark # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
+1CF7 ; SpacingMark # Mc VEDIC SIGN ATIKRAMA
A823..A824 ; SpacingMark # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
A827 ; SpacingMark # Mc SYLOTI NAGRI VOWEL SIGN OO
A880..A881 ; SpacingMark # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
@@ -482,6 +530,9 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
11347..11348 ; SpacingMark # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
1134B..1134D ; SpacingMark # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
11362..11363 ; SpacingMark # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
+11435..11437 ; SpacingMark # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11440..11441 ; SpacingMark # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11445 ; SpacingMark # Mc NEWA SIGN VISARGA
114B1..114B2 ; SpacingMark # Mc [2] TIRHUTA VOWEL SIGN I..TIRHUTA VOWEL SIGN II
114B9 ; SpacingMark # Mc TIRHUTA VOWEL SIGN E
114BB..114BC ; SpacingMark # Mc [2] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN O
@@ -498,11 +549,20 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
116B6 ; SpacingMark # Mc TAKRI SIGN VIRAMA
11720..11721 ; SpacingMark # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
11726 ; SpacingMark # Mc AHOM VOWEL SIGN E
+11A07..11A08 ; SpacingMark # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
+11A39 ; SpacingMark # Mc ZANABAZAR SQUARE SIGN VISARGA
+11A57..11A58 ; SpacingMark # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A97 ; SpacingMark # Mc SOYOMBO SIGN VISARGA
+11C2F ; SpacingMark # Mc BHAIKSUKI VOWEL SIGN AA
+11C3E ; SpacingMark # Mc BHAIKSUKI SIGN VISARGA
+11CA9 ; SpacingMark # Mc MARCHEN SUBJOINED LETTER YA
+11CB1 ; SpacingMark # Mc MARCHEN VOWEL SIGN I
+11CB4 ; SpacingMark # Mc MARCHEN VOWEL SIGN O
16F51..16F7E ; SpacingMark # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT
-# Total code points: 330
+# Total code points: 348
# ================================================
@@ -1333,4 +1393,83 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH
# Total code points: 10773
+# ================================================
+
+261D ; E_Base # So WHITE UP POINTING INDEX
+26F9 ; E_Base # So PERSON WITH BALL
+270A..270D ; E_Base # So [4] RAISED FIST..WRITING HAND
+1F385 ; E_Base # So FATHER CHRISTMAS
+1F3C2..1F3C4 ; E_Base # So [3] SNOWBOARDER..SURFER
+1F3C7 ; E_Base # So HORSE RACING
+1F3CA..1F3CC ; E_Base # So [3] SWIMMER..GOLFER
+1F442..1F443 ; E_Base # So [2] EAR..NOSE
+1F446..1F450 ; E_Base # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN
+1F46E ; E_Base # So POLICE OFFICER
+1F470..1F478 ; E_Base # So [9] BRIDE WITH VEIL..PRINCESS
+1F47C ; E_Base # So BABY ANGEL
+1F481..1F483 ; E_Base # So [3] INFORMATION DESK PERSON..DANCER
+1F485..1F487 ; E_Base # So [3] NAIL POLISH..HAIRCUT
+1F4AA ; E_Base # So FLEXED BICEPS
+1F574..1F575 ; E_Base # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY
+1F57A ; E_Base # So MAN DANCING
+1F590 ; E_Base # So RAISED HAND WITH FINGERS SPLAYED
+1F595..1F596 ; E_Base # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS
+1F645..1F647 ; E_Base # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY
+1F64B..1F64F ; E_Base # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS
+1F6A3 ; E_Base # So ROWBOAT
+1F6B4..1F6B6 ; E_Base # So [3] BICYCLIST..PEDESTRIAN
+1F6C0 ; E_Base # So BATH
+1F6CC ; E_Base # So SLEEPING ACCOMMODATION
+1F918..1F91C ; E_Base # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST
+1F91E..1F91F ; E_Base # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN
+1F926 ; E_Base # So FACE PALM
+1F930..1F939 ; E_Base # So [10] PREGNANT WOMAN..JUGGLING
+1F93D..1F93E ; E_Base # So [2] WATER POLO..HANDBALL
+1F9D1..1F9DD ; E_Base # So [13] ADULT..ELF
+
+# Total code points: 98
+
+# ================================================
+
+1F3FB..1F3FF ; E_Modifier # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
+
+# Total code points: 5
+
+# ================================================
+
+200D ; ZWJ # Cf ZERO WIDTH JOINER
+
+# Total code points: 1
+
+# ================================================
+
+2640 ; Glue_After_Zwj # So FEMALE SIGN
+2642 ; Glue_After_Zwj # So MALE SIGN
+2695..2696 ; Glue_After_Zwj # So [2] STAFF OF AESCULAPIUS..SCALES
+2708 ; Glue_After_Zwj # So AIRPLANE
+2764 ; Glue_After_Zwj # So HEAVY BLACK HEART
+1F308 ; Glue_After_Zwj # So RAINBOW
+1F33E ; Glue_After_Zwj # So EAR OF RICE
+1F373 ; Glue_After_Zwj # So COOKING
+1F393 ; Glue_After_Zwj # So GRADUATION CAP
+1F3A4 ; Glue_After_Zwj # So MICROPHONE
+1F3A8 ; Glue_After_Zwj # So ARTIST PALETTE
+1F3EB ; Glue_After_Zwj # So SCHOOL
+1F3ED ; Glue_After_Zwj # So FACTORY
+1F48B ; Glue_After_Zwj # So KISS MARK
+1F4BB..1F4BC ; Glue_After_Zwj # So [2] PERSONAL COMPUTER..BRIEFCASE
+1F527 ; Glue_After_Zwj # So WRENCH
+1F52C ; Glue_After_Zwj # So MICROSCOPE
+1F5E8 ; Glue_After_Zwj # So LEFT SPEECH BUBBLE
+1F680 ; Glue_After_Zwj # So ROCKET
+1F692 ; Glue_After_Zwj # So FIRE ENGINE
+
+# Total code points: 22
+
+# ================================================
+
+1F466..1F469 ; E_Base_GAZ # So [4] BOY..WOMAN
+
+# Total code points: 4
+
# EOF
diff --git a/util/unicode/data/LineBreak.txt b/util/unicode/data/LineBreak.txt
index b627f874d0..d80210bde3 100644
--- a/util/unicode/data/LineBreak.txt
+++ b/util/unicode/data/LineBreak.txt
@@ -1,45 +1,45 @@
-# LineBreak-8.0.0.txt
-# Date: 2015-02-13, 09:15:00 GMT [KW, LI]
+# LineBreak-10.0.0.txt
+# Date: 2017-03-08, 02:00:00 GMT [KW, LI]
+# © 2017 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
+#
+# Unicode Character Database
+# For documentation, see http://www.unicode.org/reports/tr44/
#
# Line_Break Property
#
# This file is a normative contributory data file in the
# Unicode Character Database.
-# It contains both normative and informative data.
-#
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# The format is two fields separated by a semicolon.
# Field 0: Unicode code point value or range of code point values
# Field 1: Line_Break property, consisting of one of the following values:
-# Normative:
-# "BK", "CR", "LF", "CM", "SG", "GL", "CB", "SP", "ZW",
-# "NL", "WJ", "JL", "JV", "JT", "H2", "H3"
-# Informative:
-# "XX", "OP", "CL", "CP", "QU", "NS", "EX", "SY",
-# "IS", "PR", "PO", "NU", "AL", "ID", "IN", "HY",
-# "BB", "BA", "SA", "AI", "B2", "HL", "CJ", "RI"
+# Non-tailorable:
+# "BK", "CM", "CR", "GL", "LF", "NL", "SP", "WJ", "ZW", "ZWJ"
+# Tailorable:
+# "AI", "AL", "B2", "BA", "BB", "CB", "CJ", "CL", "CP", "EB",
+# "EM", "EX", "H2", "H3", "HL", "HY", "ID", "IN", "IS", "JL",
+# "JT", "JV", "NS", "NU", "OP", "PO", "PR", "QU", "RI", "SA",
+# "SG", "SY", "XX"
# - All code points, assigned and unassigned, that are not listed
-# explicitly are given the value "XX".
-# The unassigned code points that default to "ID" include ranges in the
-# following blocks:
-# CJK Unified Ideographs Extension A: U+3400..U+4DBF
-# CJK Unified Ideographs: U+4E00..U+9FFF
-# CJK Compatibility Ideographs: U+F900..U+FAFF
-# CJK Unified Ideographs Extension B: U+20000..U+2A6DF
-# CJK Unified Ideographs Extension C: U+2A700..U+2B73F
-# CJK Unified Ideographs Extension D: U+2B740..U+2B81F
-# CJK Unified Ideographs Extension E: U+2B820..U+2CEAF
-# CJK Compatibility Ideographs Supplement: U+2F800..U+2FA1F
-# and any other reserved code points on
-# Planes 2 and 3: U+20000..U+2FFFD
-# U+30000..U+3FFFD
-# The unassigned code points that default to "PR" comprise a range in the
-# following block:
-# Currency Symbols: U+20A0..U+20CF
-# - Character ranges are specified as for other property files in
-# the Unicode Character Database.
+# explicitly are given the value "XX".
+# - The unassigned code points in the following blocks default to "ID":
+# CJK Unified Ideographs Extension A: U+3400..U+4DBF
+# CJK Unified Ideographs: U+4E00..U+9FFF
+# CJK Compatibility Ideographs: U+F900..U+FAFF
+# - All undesignated code points in Planes 2 and 3, whether inside or
+# outside of allocated blocks, default to "ID":
+# Plane 2: U+20000..U+2FFFD
+# Plane 3: U+30000..U+3FFFD
+# - All unassigned code points in the following Plane 1 range, whether
+# inside or outside of allocated blocks, also default to "ID":
+# Plane 1 range: U+1F000..U+1FFFD
+# - The unassigned code points in the following block default to "PR":
+# Currency Symbols: U+20A0..U+20CF
+#
+# Character ranges are specified as for other property files in the
+# Unicode Character Database.
#
# For legacy reasons, there are no spaces before or after the semicolon
# which separates the two fields. The comments following the number sign
@@ -273,7 +273,11 @@
0840..0858;AL # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0859..085B;CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
085E;AL # Po MANDAIC PUNCTUATION
+0860..086A;AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4;AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
+08B6..08BD;AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
+08D4..08E1;CM # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
+08E2;AL # Cf ARABIC DISPUTED END OF AYAH
08E3..08FF;CM # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
0900..0902;CM # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
0903;CM # Mc DEVANAGARI SIGN VISARGA
@@ -324,6 +328,8 @@
09F9;PO # No BENGALI CURRENCY DENOMINATOR SIXTEEN
09FA;AL # So BENGALI ISSHAR
09FB;PR # Sc BENGALI GANDA MARK
+09FC;AL # Lo BENGALI LETTER VEDIC ANUSVARA
+09FD;AL # Po BENGALI ABBREVIATION SIGN
0A01..0A02;CM # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
0A03;CM # Mc GURMUKHI SIGN VISARGA
0A05..0A0A;AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
@@ -368,6 +374,7 @@
0AF0;AL # Po GUJARATI ABBREVIATION SIGN
0AF1;PR # Sc GUJARATI RUPEE SIGN
0AF9;AL # Lo GUJARATI LETTER ZHA
+0AFA..0AFF;CM # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01;CM # Mn ORIYA SIGN CANDRABINDU
0B02..0B03;CM # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B05..0B0C;AL # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
@@ -436,6 +443,7 @@
0C66..0C6F;NU # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
0C78..0C7E;AL # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR
0C7F;AL # So TELUGU SIGN TUUMU
+0C80;AL # Lo KANNADA SIGN SPACING CANDRABINDU
0C81;CM # Mn KANNADA SIGN CANDRABINDU
0C82..0C83;CM # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C85..0C8C;AL # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
@@ -458,11 +466,12 @@
0CE2..0CE3;CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CE6..0CEF;NU # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2;AL # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
-0D01;CM # Mn MALAYALAM SIGN CANDRABINDU
+0D00..0D01;CM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03;CM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C;AL # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10;AL # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D3A;AL # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
+0D3B..0D3C;CM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3D;AL # Lo MALAYALAM SIGN AVAGRAHA
0D3E..0D40;CM # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44;CM # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
@@ -470,11 +479,14 @@
0D4A..0D4C;CM # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
0D4D;CM # Mn MALAYALAM SIGN VIRAMA
0D4E;AL # Lo MALAYALAM LETTER DOT REPH
+0D4F;AL # So MALAYALAM SIGN PARA
+0D54..0D56;AL # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
0D57;CM # Mc MALAYALAM AU LENGTH MARK
+0D58..0D5E;AL # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH
0D5F..0D61;AL # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D62..0D63;CM # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
0D66..0D6F;NU # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
-0D70..0D75;AL # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
+0D70..0D78;AL # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS
0D79;PO # So MALAYALAM DATE MARK
0D7A..0D7F;AL # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
0D82..0D83;CM # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
@@ -700,7 +712,9 @@
1820..1842;AL # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
1843;AL # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877;AL # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
-1880..18A8;AL # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA
+1880..1884;AL # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
+1885..1886;CM # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
+1887..18A8;AL # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA
18A9;CM # Mn MONGOLIAN LETTER ALI GALI DAGALGA
18AA;AL # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
18B0..18F5;AL # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S
@@ -802,6 +816,7 @@
1C5A..1C77;AL # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH
1C78..1C7D;AL # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD
1C7E..1C7F;BA # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
+1C80..1C88;AL # Ll [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
1CC0..1CC7;AL # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA
1CD0..1CD2;CM # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
1CD3;AL # Po VEDIC SIGN NIHSHVASA
@@ -814,6 +829,7 @@
1CF2..1CF3;CM # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF4;CM # Mn VEDIC TONE CANDRA ABOVE
1CF5..1CF6;AL # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
+1CF7;CM # Mc VEDIC SIGN ATIKRAMA
1CF8..1CF9;CM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
1D00..1D2B;AL # Ll [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D6A;AL # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
@@ -822,8 +838,8 @@
1D79..1D7F;AL # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE
1D80..1D9A;AL # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF;AL # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
-1DC0..1DF5;CM # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
-1DFC..1DFF;CM # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+1DC0..1DF9;CM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
+1DFB..1DFF;CM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1E00..1EFF;AL # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP
1F00..1F15;AL # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D;AL # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
@@ -855,7 +871,9 @@
2007;GL # Zs FIGURE SPACE
2008..200A;BA # Zs [3] PUNCTUATION SPACE..HAIR SPACE
200B;ZW # Cf ZERO WIDTH SPACE
-200C..200F;CM # Cf [4] ZERO WIDTH NON-JOINER..RIGHT-TO-LEFT MARK
+200C;CM # Cf ZERO WIDTH NON-JOINER
+200D;ZWJ # Cf ZERO WIDTH JOINER
+200E..200F;CM # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
2010;BA # Pd HYPHEN
2011;GL # Pd NON-BREAKING HYPHEN
2012..2013;BA # Pd [2] FIGURE DASH..EN DASH
@@ -928,7 +946,8 @@
20BB;PO # Sc NORDIC MARK SIGN
20BC..20BD;PR # Sc [2] MANAT SIGN..RUBLE SIGN
20BE;PO # Sc LARI SIGN
-20BF..20CF;PR # Cn [17] <reserved-20BF>..<reserved-20CF>
+20BF;PR # Sc BITCOIN SIGN
+20C0..20CF;PR # Cn [16] <reserved-20C0>..<reserved-20CF>
20D0..20DC;CM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0;CM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1;CM # Mn COMBINING LEFT RIGHT ARROW ABOVE
@@ -1091,7 +1110,7 @@
23DC..23E1;AL # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET
23E2..23EF;AL # So [14] WHITE TRAPEZIUM..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR
23F0..23F3;ID # So [4] ALARM CLOCK..HOURGLASS WITH FLOWING SAND
-23F4..23FA;AL # So [7] BLACK MEDIUM LEFT-POINTING TRIANGLE..BLACK CIRCLE FOR RECORD
+23F4..23FF;AL # So [12] BLACK MEDIUM LEFT-POINTING TRIANGLE..OBSERVER EYE SYMBOL
2400..2426;AL # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
2440..244A;AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..249B;AI # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP
@@ -1143,7 +1162,9 @@
2616..2617;AI # So [2] WHITE SHOGI PIECE..BLACK SHOGI PIECE
2618;ID # So SHAMROCK
2619;AL # So REVERSED ROTATED FLORAL HEART BULLET
-261A..261F;ID # So [6] BLACK LEFT POINTING INDEX..WHITE DOWN POINTING INDEX
+261A..261C;ID # So [3] BLACK LEFT POINTING INDEX..WHITE LEFT POINTING INDEX
+261D;EB # So WHITE UP POINTING INDEX
+261E..261F;ID # So [2] WHITE RIGHT POINTING INDEX..WHITE DOWN POINTING INDEX
2620..2638;AL # So [25] SKULL AND CROSSBONES..WHEEL OF DHARMA
2639..263B;ID # So [3] WHITE FROWNING FACE..BLACK SMILING FACE
263C..263F;AL # So [4] WHITE SUN WITH RAYS..MERCURY
@@ -1188,19 +1209,23 @@
26EB..26F0;AI # So [6] CASTLE..MOUNTAIN
26F1..26F5;ID # So [5] UMBRELLA ON GROUND..SAILBOAT
26F6;AI # So SQUARE FOUR CORNERS
-26F7..26FA;ID # So [4] SKIER..TENT
+26F7..26F8;ID # So [2] SKIER..ICE SKATE
+26F9;EB # So PERSON WITH BALL
+26FA;ID # So TENT
26FB..26FC;AI # So [2] JAPANESE BANK SYMBOL..HEADSTONE GRAVEYARD SYMBOL
26FD..26FF;ID # So [3] FUEL PUMP..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
2700..2704;ID # So [5] BLACK SAFETY SCISSORS..WHITE SCISSORS
2705..2707;AL # So [3] WHITE HEAVY CHECK MARK..TAPE DRIVE
-2708..270D;ID # So [6] AIRPLANE..WRITING HAND
+2708..2709;ID # So [2] AIRPLANE..ENVELOPE
+270A..270D;EB # So [4] RAISED FIST..WRITING HAND
270E..2756;AL # So [73] LOWER RIGHT PENCIL..BLACK DIAMOND MINUS WHITE X
2757;AI # So HEAVY EXCLAMATION MARK SYMBOL
2758..275A;AL # So [3] LIGHT VERTICAL BAR..HEAVY VERTICAL BAR
275B..2760;QU # So [6] HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT..HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT
2761;AL # So CURVED STEM PARAGRAPH SIGN ORNAMENT
2762..2763;EX # So [2] HEAVY EXCLAMATION MARK ORNAMENT..HEAVY HEART EXCLAMATION MARK ORNAMENT
-2764..2767;AL # So [4] HEAVY BLACK HEART..ROTATED FLORAL HEART BULLET
+2764;ID # So HEAVY BLACK HEART
+2765..2767;AL # So [3] ROTATED HEAVY BLACK HEART BULLET..ROTATED FLORAL HEART BULLET
2768;OP # Ps MEDIUM LEFT PARENTHESIS ORNAMENT
2769;CL # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT
276A;OP # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT
@@ -1277,7 +1302,7 @@
2B76..2B95;AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B98..2BB9;AL # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8;AL # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
-2BCA..2BD1;AL # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
+2BCA..2BD2;AL # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BEC..2BEF;AL # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2C00..2C2E;AL # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E;AL # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
@@ -1355,6 +1380,7 @@
2E40;BA # Pd DOUBLE HYPHEN
2E41;BA # Po REVERSED COMMA
2E42;OP # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
+2E43..2E49;BA # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2E80..2E99;ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3;ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5;ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
@@ -1453,7 +1479,7 @@
30FC;CJ # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
30FD..30FE;NS # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK
30FF;ID # Lo KATAKANA DIGRAPH KOTO
-3105..312D;ID # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
+3105..312E;ID # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E;ID # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
3190..3191;ID # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK
3192..3195;ID # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
@@ -1476,8 +1502,8 @@
3400..4DB5;ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4DB6..4DBF;ID # Cn [10] <reserved-4DB6>..<reserved-4DBF>
4DC0..4DFF;AL # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
-4E00..9FD5;ID # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
-9FD6..9FFF;ID # Cn [42] <reserved-9FD6>..<reserved-9FFF>
+4E00..9FEA;ID # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
+9FEB..9FFF;ID # Cn [21] <reserved-9FEB>..<reserved-9FFF>
A000..A014;ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015;NS # Lm YI SYLLABLE WU
A016..A48C;ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -1519,7 +1545,7 @@ A788;AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
A789..A78A;AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
A78B..A78E;AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F;AL # Lo LATIN LETTER SINOLOGICAL DOT
-A790..A7AD;AL # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
+A790..A7AE;AL # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B7;AL # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
A7F7;AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7F8..A7F9;AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
@@ -1546,7 +1572,7 @@ A876..A877;EX # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD
A880..A881;CM # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
A882..A8B3;AL # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
A8B4..A8C3;CM # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
-A8C4;CM # Mn SAURASHTRA SIGN VIRAMA
+A8C4..A8C5;CM # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
A8CE..A8CF;BA # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
A8D0..A8D9;NU # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE
A8E0..A8F1;CM # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
@@ -2574,16 +2600,16 @@ FF62;OP # Ps HALFWIDTH LEFT CORNER BRACKET
FF63;CL # Pe HALFWIDTH RIGHT CORNER BRACKET
FF64;CL # Po HALFWIDTH IDEOGRAPHIC COMMA
FF65;NS # Po HALFWIDTH KATAKANA MIDDLE DOT
-FF66;AL # Lo HALFWIDTH KATAKANA LETTER WO
+FF66;ID # Lo HALFWIDTH KATAKANA LETTER WO
FF67..FF6F;CJ # Lo [9] HALFWIDTH KATAKANA LETTER SMALL A..HALFWIDTH KATAKANA LETTER SMALL TU
FF70;CJ # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
-FF71..FF9D;AL # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N
+FF71..FF9D;ID # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N
FF9E..FF9F;NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
-FFA0..FFBE;AL # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH
-FFC2..FFC7;AL # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E
-FFCA..FFCF;AL # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE
-FFD2..FFD7;AL # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU
-FFDA..FFDC;AL # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
+FFA0..FFBE;ID # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH
+FFC2..FFC7;ID # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E
+FFCA..FFCF;ID # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE
+FFD2..FFD7;ID # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU
+FFDA..FFDC;ID # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
FFE0;PO # Sc FULLWIDTH CENT SIGN
FFE1;PR # Sc FULLWIDTH POUND SIGN
FFE2;ID # Sm FULLWIDTH NOT SIGN
@@ -2610,7 +2636,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
10175..10178;AL # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN
10179..10189;AL # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN
1018A..1018B;AL # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN
-1018C;AL # So GREEK SINUSOID SIGN
+1018C..1018E;AL # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN
10190..1019B;AL # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN
101A0;AL # So GREEK SYMBOL TAU RHO
101D0..101FC;AL # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND
@@ -2621,6 +2647,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
102E1..102FB;AL # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED
10300..1031F;AL # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10320..10323;AL # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY
+1032D..1032F;AL # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE
10330..10340;AL # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
10341;AL # Nl GOTHIC LETTER NINETY
10342..10349;AL # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
@@ -2637,6 +2664,8 @@ FFFD;AI # So REPLACEMENT CHARACTER
10450..1047F;AL # Lo [48] SHAVIAN LETTER PEEP..SHAVIAN LETTER YEW
10480..1049D;AL # Lo [30] OSMANYA LETTER ALEF..OSMANYA LETTER OO
104A0..104A9;NU # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
+104B0..104D3;AL # Lu [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA
+104D8..104FB;AL # Ll [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA
10500..10527;AL # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE
10530..10563;AL # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW
1056F;AL # Po CAUCASIAN ALBANIAN CITATION MARK
@@ -2774,6 +2803,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
1123A;AL # Po KHOJKI WORD SEPARATOR
1123B..1123C;BA # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
1123D;AL # Po KHOJKI ABBREVIATION SIGN
+1123E;CM # Mn KHOJKI SIGN SUKUN
11280..11286;AL # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
11288;AL # Lo MULTANI LETTER GHA
1128A..1128D;AL # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -2806,6 +2836,19 @@ FFFD;AI # So REPLACEMENT CHARACTER
11362..11363;CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
11366..1136C;CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
11370..11374;CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
+11400..11434;AL # Lo [53] NEWA LETTER A..NEWA LETTER HA
+11435..11437;CM # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11438..1143F;CM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11440..11441;CM # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11442..11444;CM # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
+11445;CM # Mc NEWA SIGN VISARGA
+11446;CM # Mn NEWA SIGN NUKTA
+11447..1144A;AL # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI
+1144B..1144E;BA # Po [4] NEWA DANDA..NEWA GAP FILLER
+1144F;AL # Po NEWA ABBREVIATION SIGN
+11450..11459;NU # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
+1145B;BA # Po NEWA PLACEHOLDER MARK
+1145D;AL # Po NEWA INSERTION SIGN
11480..114AF;AL # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA
114B0..114B2;CM # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II
114B3..114B8;CM # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
@@ -2844,6 +2887,7 @@ FFFD;AI # So REPLACEMENT CHARACTER
11643;AL # Po MODI ABBREVIATION SIGN
11644;AL # Lo MODI SIGN HUVA
11650..11659;NU # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE
+11660..1166C;BB # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
11680..116AA;AL # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
116AB;CM # Mn TAKRI SIGN ANUSVARA
116AC;CM # Mc TAKRI SIGN VISARGA
@@ -2867,7 +2911,65 @@ FFFD;AI # So REPLACEMENT CHARACTER
118E0..118E9;NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
118EA..118F2;AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
118FF;AL # Lo WARANG CITI OM
+11A00;AL # Lo ZANABAZAR SQUARE LETTER A
+11A01..11A06;CM # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
+11A07..11A08;CM # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
+11A09..11A0A;CM # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A0B..11A32;AL # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
+11A33..11A38;CM # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
+11A39;CM # Mc ZANABAZAR SQUARE SIGN VISARGA
+11A3A;AL # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
+11A3B..11A3E;CM # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A3F;BB # Po ZANABAZAR SQUARE INITIAL HEAD MARK
+11A40;AL # Po ZANABAZAR SQUARE CLOSING HEAD MARK
+11A41..11A44;BA # Po [4] ZANABAZAR SQUARE MARK TSHEG..ZANABAZAR SQUARE MARK LONG TSHEG
+11A45;BB # Po ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK
+11A46;AL # Po ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK
+11A47;CM # Mn ZANABAZAR SQUARE SUBJOINER
+11A50;AL # Lo SOYOMBO LETTER A
+11A51..11A56;CM # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A57..11A58;CM # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A59..11A5B;CM # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A5C..11A83;AL # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
+11A86..11A89;AL # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
+11A8A..11A96;CM # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A97;CM # Mc SOYOMBO SIGN VISARGA
+11A98..11A99;CM # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
+11A9A..11A9C;BA # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
+11A9E..11AA0;BB # Po [3] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO HEAD MARK WITH MOON AND SUN
+11AA1..11AA2;BA # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2
11AC0..11AF8;AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
+11C00..11C08;AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
+11C0A..11C2E;AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
+11C2F;CM # Mc BHAIKSUKI VOWEL SIGN AA
+11C30..11C36;CM # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D;CM # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3E;CM # Mc BHAIKSUKI SIGN VISARGA
+11C3F;CM # Mn BHAIKSUKI SIGN VIRAMA
+11C40;AL # Lo BHAIKSUKI SIGN AVAGRAHA
+11C41..11C45;BA # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2
+11C50..11C59;NU # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
+11C5A..11C6C;AL # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK
+11C70;BB # Po MARCHEN HEAD MARK
+11C71;EX # Po MARCHEN MARK SHAD
+11C72..11C8F;AL # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A
+11C92..11CA7;CM # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CA9;CM # Mc MARCHEN SUBJOINED LETTER YA
+11CAA..11CB0;CM # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB1;CM # Mc MARCHEN VOWEL SIGN I
+11CB2..11CB3;CM # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB4;CM # Mc MARCHEN VOWEL SIGN O
+11CB5..11CB6;CM # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+11D00..11D06;AL # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
+11D08..11D09;AL # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
+11D0B..11D30;AL # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
+11D31..11D36;CM # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A;CM # Mn MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D;CM # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D45;CM # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
+11D46;AL # Lo MASARAM GONDI REPHA
+11D47;CM # Mn MASARAM GONDI RA-KARA
+11D50..11D59;NU # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
12000..12399;AL # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E;AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12470..12474;BA # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
@@ -2914,7 +3016,12 @@ FFFD;AI # So REPLACEMENT CHARACTER
16F51..16F7E;CM # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
16F8F..16F92;CM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
16F93..16F9F;AL # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
-1B000..1B001;ID # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
+16FE0..16FE1;NS # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
+17000..187EC;ID # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
+18800..18AF2;ID # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
+1B000..1B0FF;ID # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2
+1B100..1B11E;ID # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2
+1B170..1B2FB;ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A;AL # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C;AL # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88;AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -2996,9 +3103,18 @@ FFFD;AI # So REPLACEMENT CHARACTER
1DA8B;AL # Po SIGNWRITING PARENTHESIS
1DA9B..1DA9F;CM # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA1..1DAAF;CM # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
+1E000..1E006;CM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018;CM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021;CM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024;CM # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A;CM # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E800..1E8C4;AL # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON
1E8C7..1E8CF;AL # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
1E8D0..1E8D6;CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
+1E900..1E943;AL # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA
+1E944..1E94A;CM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
+1E950..1E959;NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
+1E95E..1E95F;OP # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
1EE00..1EE03;AL # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F;AL # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22;AL # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
@@ -3034,37 +3150,79 @@ FFFD;AI # So REPLACEMENT CHARACTER
1EEAB..1EEBB;AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
1EEF0..1EEF1;AL # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
1F000..1F02B;ID # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK
+1F02C..1F02F;ID # Cn [4] <reserved-1F02C>..<reserved-1F02F>
1F030..1F093;ID # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06
+1F094..1F09F;ID # Cn [12] <reserved-1F094>..<reserved-1F09F>
1F0A0..1F0AE;ID # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES
+1F0AF..1F0B0;ID # Cn [2] <reserved-1F0AF>..<reserved-1F0B0>
1F0B1..1F0BF;ID # So [15] PLAYING CARD ACE OF HEARTS..PLAYING CARD RED JOKER
+1F0C0;ID # Cn <reserved-1F0C0>
1F0C1..1F0CF;ID # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER
+1F0D0;ID # Cn <reserved-1F0D0>
1F0D1..1F0F5;ID # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21
+1F0F6..1F0FF;ID # Cn [10] <reserved-1F0F6>..<reserved-1F0FF>
1F100..1F10C;AI # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
+1F10D..1F10F;ID # Cn [3] <reserved-1F10D>..<reserved-1F10F>
1F110..1F12D;AI # So [30] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED CD
1F12E;AL # So CIRCLED WZ
+1F12F;ID # Cn <reserved-1F12F>
1F130..1F169;AI # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F16A..1F16B;AL # So [2] RAISED MC SIGN..RAISED MD SIGN
-1F170..1F19A;AI # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS
+1F16C..1F16F;ID # Cn [4] <reserved-1F16C>..<reserved-1F16F>
+1F170..1F1AC;AI # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
+1F1AD..1F1E5;ID # Cn [57] <reserved-1F1AD>..<reserved-1F1E5>
1F1E6..1F1FF;RI # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F200..1F202;ID # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA
-1F210..1F23A;ID # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
+1F203..1F20F;ID # Cn [13] <reserved-1F203>..<reserved-1F20F>
+1F210..1F23B;ID # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
+1F23C..1F23F;ID # Cn [4] <reserved-1F23C>..<reserved-1F23F>
1F240..1F248;ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
+1F249..1F24F;ID # Cn [7] <reserved-1F249>..<reserved-1F24F>
1F250..1F251;ID # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
-1F300..1F39B;ID # So [156] CYCLONE..CONTROL KNOBS
+1F252..1F25F;ID # Cn [14] <reserved-1F252>..<reserved-1F25F>
+1F260..1F265;ID # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
+1F266..1F2FF;ID # Cn [154] <reserved-1F266>..<reserved-1F2FF>
+1F300..1F384;ID # So [133] CYCLONE..CHRISTMAS TREE
+1F385;EB # So FATHER CHRISTMAS
+1F386..1F39B;ID # So [22] FIREWORKS..CONTROL KNOBS
1F39C..1F39D;AL # So [2] BEAMED ASCENDING MUSICAL NOTES..BEAMED DESCENDING MUSICAL NOTES
1F39E..1F3B4;ID # So [23] FILM FRAMES..FLOWER PLAYING CARDS
1F3B5..1F3B6;AL # So [2] MUSICAL NOTE..MULTIPLE MUSICAL NOTES
1F3B7..1F3BB;ID # So [5] SAXOPHONE..VIOLIN
1F3BC;AL # So MUSICAL SCORE
-1F3BD..1F3FA;ID # So [62] RUNNING SHIRT WITH SASH..AMPHORA
-1F3FB..1F3FF;AL # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
-1F400..1F49F;ID # So [160] RAT..HEART DECORATION
+1F3BD..1F3C1;ID # So [5] RUNNING SHIRT WITH SASH..CHEQUERED FLAG
+1F3C2..1F3C4;EB # So [3] SNOWBOARDER..SURFER
+1F3C5..1F3C6;ID # So [2] SPORTS MEDAL..TROPHY
+1F3C7;EB # So HORSE RACING
+1F3C8..1F3C9;ID # So [2] AMERICAN FOOTBALL..RUGBY FOOTBALL
+1F3CA..1F3CC;EB # So [3] SWIMMER..GOLFER
+1F3CD..1F3FA;ID # So [46] RACING MOTORCYCLE..AMPHORA
+1F3FB..1F3FF;EM # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
+1F400..1F441;ID # So [66] RAT..EYE
+1F442..1F443;EB # So [2] EAR..NOSE
+1F444..1F445;ID # So [2] MOUTH..TONGUE
+1F446..1F450;EB # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN
+1F451..1F465;ID # So [21] CROWN..BUSTS IN SILHOUETTE
+1F466..1F469;EB # So [4] BOY..WOMAN
+1F46A..1F46D;ID # So [4] FAMILY..TWO WOMEN HOLDING HANDS
+1F46E;EB # So POLICE OFFICER
+1F46F;ID # So WOMAN WITH BUNNY EARS
+1F470..1F478;EB # So [9] BRIDE WITH VEIL..PRINCESS
+1F479..1F47B;ID # So [3] JAPANESE OGRE..GHOST
+1F47C;EB # So BABY ANGEL
+1F47D..1F480;ID # So [4] EXTRATERRESTRIAL ALIEN..SKULL
+1F481..1F483;EB # So [3] INFORMATION DESK PERSON..DANCER
+1F484;ID # So LIPSTICK
+1F485..1F487;EB # So [3] NAIL POLISH..HAIRCUT
+1F488..1F49F;ID # So [24] BARBER POLE..HEART DECORATION
1F4A0;AL # So DIAMOND SHAPE WITH A DOT INSIDE
1F4A1;ID # So ELECTRIC LIGHT BULB
1F4A2;AL # So ANGER SYMBOL
1F4A3;ID # So BOMB
1F4A4;AL # So SLEEPING SYMBOL
-1F4A5..1F4AE;ID # So [10] COLLISION SYMBOL..WHITE FLOWER
+1F4A5..1F4A9;ID # So [5] COLLISION SYMBOL..PILE OF POO
+1F4AA;EB # So FLEXED BICEPS
+1F4AB..1F4AE;ID # So [4] DIZZY SYMBOL..WHITE FLOWER
1F4AF;AL # So HUNDRED POINTS SYMBOL
1F4B0;ID # So MONEY BAG
1F4B1..1F4B2;AL # So [2] CURRENCY EXCHANGE..HEAVY DOLLAR SIGN
@@ -3074,31 +3232,80 @@ FFFD;AI # So REPLACEMENT CHARACTER
1F517..1F524;AL # So [14] LINK SYMBOL..INPUT SYMBOL FOR LATIN LETTERS
1F525..1F531;ID # So [13] FIRE..TRIDENT EMBLEM
1F532..1F549;AL # So [24] BLACK SQUARE BUTTON..OM SYMBOL
-1F54A..1F579;ID # So [48] DOVE OF PEACE..JOYSTICK
-1F57B..1F5A3;ID # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
-1F5A5..1F5D3;ID # So [47] DESKTOP COMPUTER..SPIRAL CALENDAR PAD
+1F54A..1F573;ID # So [42] DOVE OF PEACE..HOLE
+1F574..1F575;EB # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY
+1F576..1F579;ID # So [4] DARK SUNGLASSES..JOYSTICK
+1F57A;EB # So MAN DANCING
+1F57B..1F58F;ID # So [21] LEFT HAND TELEPHONE RECEIVER..TURNED OK HAND SIGN
+1F590;EB # So RAISED HAND WITH FINGERS SPLAYED
+1F591..1F594;ID # So [4] REVERSED RAISED HAND WITH FINGERS SPLAYED..REVERSED VICTORY HAND
+1F595..1F596;EB # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS
+1F597..1F5D3;ID # So [61] WHITE DOWN POINTING LEFT HAND INDEX..SPIRAL CALENDAR PAD
1F5D4..1F5DB;AL # So [8] DESKTOP WINDOW..DECREASE FONT SIZE SYMBOL
1F5DC..1F5F3;ID # So [24] COMPRESSION..BALLOT BOX WITH BALLOT
1F5F4..1F5F9;AL # So [6] BALLOT SCRIPT X..BALLOT BOX WITH BOLD CHECK
1F5FA..1F5FF;ID # So [6] WORLD MAP..MOYAI
-1F600..1F64F;ID # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS
+1F600..1F644;ID # So [69] GRINNING FACE..FACE WITH ROLLING EYES
+1F645..1F647;EB # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY
+1F648..1F64A;ID # So [3] SEE-NO-EVIL MONKEY..SPEAK-NO-EVIL MONKEY
+1F64B..1F64F;EB # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS
1F650..1F675;AL # So [38] NORTH WEST POINTING LEAF..SWASH AMPERSAND ORNAMENT
1F676..1F678;QU # So [3] SANS-SERIF HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT..SANS-SERIF HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT
1F679..1F67B;NS # So [3] HEAVY INTERROBANG ORNAMENT..HEAVY SANS-SERIF INTERROBANG ORNAMENT
1F67C..1F67F;AL # So [4] VERY HEAVY SOLIDUS..REVERSE CHECKER BOARD
-1F680..1F6D0;ID # So [81] ROCKET..PLACE OF WORSHIP
+1F680..1F6A2;ID # So [35] ROCKET..SHIP
+1F6A3;EB # So ROWBOAT
+1F6A4..1F6B3;ID # So [16] SPEEDBOAT..NO BICYCLES
+1F6B4..1F6B6;EB # So [3] BICYCLIST..PEDESTRIAN
+1F6B7..1F6BF;ID # So [9] NO PEDESTRIANS..SHOWER
+1F6C0;EB # So BATH
+1F6C1..1F6CB;ID # So [11] BATHTUB..COUCH AND LAMP
+1F6CC;EB # So SLEEPING ACCOMMODATION
+1F6CD..1F6D4;ID # So [8] SHOPPING BAGS..PAGODA
+1F6D5..1F6DF;ID # Cn [11] <reserved-1F6D5>..<reserved-1F6DF>
1F6E0..1F6EC;ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
-1F6F0..1F6F3;ID # So [4] SATELLITE..PASSENGER SHIP
+1F6ED..1F6EF;ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF>
+1F6F0..1F6F8;ID # So [9] SATELLITE..FLYING SAUCER
+1F6F9..1F6FF;ID # Cn [7] <reserved-1F6F9>..<reserved-1F6FF>
1F700..1F773;AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
+1F774..1F77F;ID # Cn [12] <reserved-1F774>..<reserved-1F77F>
1F780..1F7D4;AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
+1F7D5..1F7FF;ID # Cn [43] <reserved-1F7D5>..<reserved-1F7FF>
1F800..1F80B;AL # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
+1F80C..1F80F;ID # Cn [4] <reserved-1F80C>..<reserved-1F80F>
1F810..1F847;AL # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW
+1F848..1F84F;ID # Cn [8] <reserved-1F848>..<reserved-1F84F>
1F850..1F859;AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
+1F85A..1F85F;ID # Cn [6] <reserved-1F85A>..<reserved-1F85F>
1F860..1F887;AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
+1F888..1F88F;ID # Cn [8] <reserved-1F888>..<reserved-1F88F>
1F890..1F8AD;AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
-1F910..1F918;ID # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
-1F980..1F984;ID # So [5] CRAB..UNICORN FACE
+1F8AE..1F8FF;ID # Cn [82] <reserved-1F8AE>..<reserved-1F8FF>
+1F900..1F90B;AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
+1F90C..1F90F;ID # Cn [4] <reserved-1F90C>..<reserved-1F90F>
+1F910..1F917;ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE
+1F918..1F91C;EB # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST
+1F91D;ID # So HANDSHAKE
+1F91E..1F91F;EB # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN
+1F920..1F925;ID # So [6] FACE WITH COWBOY HAT..LYING FACE
+1F926;EB # So FACE PALM
+1F927..1F92F;ID # So [9] SNEEZING FACE..SHOCKED FACE WITH EXPLODING HEAD
+1F930..1F939;EB # So [10] PREGNANT WOMAN..JUGGLING
+1F93A..1F93C;ID # So [3] FENCER..WRESTLERS
+1F93D..1F93E;EB # So [2] WATER POLO..HANDBALL
+1F93F;ID # Cn <reserved-1F93F>
+1F940..1F94C;ID # So [13] WILTED FLOWER..CURLING STONE
+1F94D..1F94F;ID # Cn [3] <reserved-1F94D>..<reserved-1F94F>
+1F950..1F96B;ID # So [28] CROISSANT..CANNED FOOD
+1F96C..1F97F;ID # Cn [20] <reserved-1F96C>..<reserved-1F97F>
+1F980..1F997;ID # So [24] CRAB..CRICKET
+1F998..1F9BF;ID # Cn [40] <reserved-1F998>..<reserved-1F9BF>
1F9C0;ID # So CHEESE WEDGE
+1F9C1..1F9CF;ID # Cn [15] <reserved-1F9C1>..<reserved-1F9CF>
+1F9D0;ID # So FACE WITH MONOCLE
+1F9D1..1F9DD;EB # So [13] ADULT..ELF
+1F9DE..1F9E6;ID # So [9] GENIE..SOCKS
+1F9E7..1FFFD;ID # Cn [1559] <reserved-1F9E7>..<reserved-1FFFD>
20000..2A6D6;ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A6D7..2A6FF;ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF>
2A700..2B734;ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
@@ -3106,7 +3313,9 @@ FFFD;AI # So REPLACEMENT CHARACTER
2B740..2B81D;ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B81E..2B81F;ID # Cn [2] <reserved-2B81E>..<reserved-2B81F>
2B820..2CEA1;ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
-2CEA2..2F7FF;ID # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF>
+2CEA2..2CEAF;ID # Cn [14] <reserved-2CEA2>..<reserved-2CEAF>
+2CEB0..2EBE0;ID # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
+2EBE1..2F7FF;ID # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF>
2F800..2FA1D;ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
2FA1E..2FFFD;ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD>
30000..3FFFD;ID # Cn [65534] <reserved-30000>..<reserved-3FFFD>
diff --git a/util/unicode/data/SentenceBreakProperty.txt b/util/unicode/data/SentenceBreakProperty.txt
index 8dd1abff0f..cd698150f4 100644
--- a/util/unicode/data/SentenceBreakProperty.txt
+++ b/util/unicode/data/SentenceBreakProperty.txt
@@ -1,10 +1,11 @@
-# SentenceBreakProperty-8.0.0.txt
-# Date: 2015-03-11, 22:29:43 GMT [MD]
+# SentenceBreakProperty-10.0.0.txt
+# Date: 2017-03-08, 08:42:08 GMT
+# © 2017 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
#
# Unicode Character Database
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-# For documentation, see http://www.unicode.org/reports/tr44/
+# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
@@ -53,6 +54,7 @@
0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
+08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
0903 ; Extend # Mc DEVANAGARI SIGN VISARGA
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
@@ -95,6 +97,7 @@
0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
0ACD ; Extend # Mn GUJARATI SIGN VIRAMA
0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
+0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU
0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B3C ; Extend # Mn ORIYA SIGN NUKTA
@@ -136,8 +139,9 @@
0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
-0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU
+0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
+0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
@@ -207,6 +211,7 @@
17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
17DD ; Extend # Mn KHMER SIGN ATTHACAN
180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA
1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
1923..1926 ; Extend # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU
@@ -271,9 +276,10 @@
1CED ; Extend # Mn VEDIC SIGN TIRYAK
1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE
+1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA
1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
-1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
-1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
+1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
@@ -299,7 +305,7 @@ A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL
A827 ; Extend # Mc SYLOTI NAGRI VOWEL SIGN OO
A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
-A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA
+A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
@@ -381,6 +387,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11234 ; Extend # Mn KHOJKI SIGN ANUSVARA
11235 ; Extend # Mc KHOJKI SIGN VIRAMA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
+1123E ; Extend # Mn KHOJKI SIGN SUKUN
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
@@ -396,6 +403,12 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
+11435..11437 ; Extend # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11440..11441 ; Extend # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
+11445 ; Extend # Mc NEWA SIGN VISARGA
+11446 ; Extend # Mn NEWA SIGN NUKTA
114B0..114B2 ; Extend # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II
114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
114B9 ; Extend # Mc TIRHUTA VOWEL SIGN E
@@ -429,6 +442,36 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11726 ; Extend # Mc AHOM VOWEL SIGN E
11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
+11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
+11A07..11A08 ; Extend # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
+11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
+11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA
+11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER
+11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A57..11A58 ; Extend # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A97 ; Extend # Mc SOYOMBO SIGN VISARGA
+11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
+11C2F ; Extend # Mc BHAIKSUKI VOWEL SIGN AA
+11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3E ; Extend # Mc BHAIKSUKI SIGN VISARGA
+11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA
+11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CA9 ; Extend # Mc MARCHEN SUBJOINED LETTER YA
+11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB1 ; Extend # Mc MARCHEN VOWEL SIGN I
+11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB4 ; Extend # Mc MARCHEN VOWEL SIGN O
+11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
+11D47 ; Extend # Mn MASARAM GONDI RA-KARA
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
@@ -447,10 +490,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK
1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
+1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
+1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
+E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-# Total code points: 1967
+# Total code points: 2277
# ================================================
@@ -467,6 +517,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
061C ; Format # Cf ARABIC LETTER MARK
06DD ; Format # Cf ARABIC END OF AYAH
070F ; Format # Cf SYRIAC ABBREVIATION MARK
+08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH
180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR
200B ; Format # Cf ZERO WIDTH SPACE
200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
@@ -479,9 +530,8 @@ FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANN
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG
-E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
-# Total code points: 148
+# Total code points: 53
# ================================================
@@ -776,6 +826,7 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER
0561..0587 ; Lower # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
+1C80..1C88 ; Lower # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D6A ; Lower # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1D6B..1D77 ; Lower # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
@@ -1118,6 +1169,7 @@ FB00..FB06 ; Lower # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE S
FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
10428..1044F ; Lower # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW
+104D8..104FB ; Lower # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA
10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z
@@ -1148,8 +1200,9 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
1D7AA..1D7C2 ; Lower # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
1D7C4..1D7C9 ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL
1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA
+1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA
-# Total code points: 2172
+# Total code points: 2251
# ================================================
@@ -1745,11 +1798,12 @@ A7A2 ; Upper # L& LATIN CAPITAL LETTER K WITH OBLIQUE STROKE
A7A4 ; Upper # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE
A7A6 ; Upper # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE
A7A8 ; Upper # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE
-A7AA..A7AD ; Upper # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT
+A7AA..A7AE ; Upper # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B4 ; Upper # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA
A7B6 ; Upper # L& LATIN CAPITAL LETTER OMEGA
FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW
+104B0..104D3 ; Upper # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA
10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO
1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z
@@ -1783,11 +1837,12 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
1D756..1D76E ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA
1D790..1D7A8 ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA
1D7CA ; Upper # L& MATHEMATICAL BOLD CAPITAL DIGAMMA
+1E900..1E921 ; Upper # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA
1F130..1F149 ; Upper # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z
1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
-# Total code points: 1782
+# Total code points: 1853
# ================================================
@@ -1825,7 +1880,9 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
0824 ; OLetter # Lm SAMARITAN MODIFIER LETTER SHORT A
0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I
0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
+0860..086A ; OLetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; OLetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
+08B6..08BD ; OLetter # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
093D ; OLetter # Lo DEVANAGARI SIGN AVAGRAHA
0950 ; OLetter # Lo DEVANAGARI OM
@@ -1843,6 +1900,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
09DC..09DD ; OLetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E1 ; OLetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
09F0..09F1 ; OLetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
+09FC ; OLetter # Lo BENGALI LETTER VEDIC ANUSVARA
0A05..0A0A ; OLetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
0A0F..0A10 ; OLetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI
0A13..0A28 ; OLetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA
@@ -1891,6 +1949,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA
0C58..0C5A ; OLetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
+0C80 ; OLetter # Lo KANNADA SIGN SPACING CANDRABINDU
0C85..0C8C ; OLetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; OLetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
0C92..0CA8 ; OLetter # Lo [23] KANNADA LETTER O..KANNADA LETTER NA
@@ -1905,6 +1964,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
0D12..0D3A ; OLetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3D ; OLetter # Lo MALAYALAM SIGN AVAGRAHA
0D4E ; OLetter # Lo MALAYALAM LETTER DOT REPH
+0D54..0D56 ; OLetter # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
0D5F..0D61 ; OLetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D7A..0D7F ; OLetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
0D85..0D96 ; OLetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
@@ -1983,7 +2043,8 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
1820..1842 ; OLetter # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
1843 ; OLetter # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877 ; OLetter # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
-1880..18A8 ; OLetter # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA
+1880..1884 ; OLetter # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
+1887..18A8 ; OLetter # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA
18AA ; OLetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
18B0..18F5 ; OLetter # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S
1900..191E ; OLetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA
@@ -2035,12 +2096,12 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT
30A1..30FA ; OLetter # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
30FC..30FE ; OLetter # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; OLetter # Lo KATAKANA DIGRAPH KOTO
-3105..312D ; OLetter # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
+3105..312E ; OLetter # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; OLetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
31A0..31BA ; OLetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; OLetter # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
-4E00..9FD5 ; OLetter # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
+4E00..9FEA ; OLetter # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
A000..A014 ; OLetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; OLetter # Lm YI SYLLABLE WU
A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -2138,7 +2199,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
10280..1029C ; OLetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X
102A0..102D0 ; OLetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
10300..1031F ; OLetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
-10330..10340 ; OLetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
+1032D..10340 ; OLetter # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; OLetter # Nl GOTHIC LETTER NINETY
10342..10349 ; OLetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; OLetter # Nl GOTHIC LETTER NINE HUNDRED
@@ -2207,6 +2268,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1133D ; OLetter # Lo GRANTHA SIGN AVAGRAHA
11350 ; OLetter # Lo GRANTHA OM
1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
+11400..11434 ; OLetter # Lo [53] NEWA LETTER A..NEWA LETTER HA
+11447..1144A ; OLetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI
11480..114AF ; OLetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA
114C4..114C5 ; OLetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG
114C7 ; OLetter # Lo TIRHUTA OM
@@ -2217,7 +2280,21 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
11700..11719 ; OLetter # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
118FF ; OLetter # Lo WARANG CITI OM
+11A00 ; OLetter # Lo ZANABAZAR SQUARE LETTER A
+11A0B..11A32 ; OLetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
+11A3A ; OLetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
+11A50 ; OLetter # Lo SOYOMBO LETTER A
+11A5C..11A83 ; OLetter # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
+11A86..11A89 ; OLetter # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
+11C00..11C08 ; OLetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
+11C0A..11C2E ; OLetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
+11C40 ; OLetter # Lo BHAIKSUKI SIGN AVAGRAHA
+11C72..11C8F ; OLetter # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A
+11D00..11D06 ; OLetter # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
+11D08..11D09 ; OLetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
+11D0B..11D30 ; OLetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
+11D46 ; OLetter # Lo MASARAM GONDI REPHA
12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
@@ -2233,7 +2310,11 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
16F00..16F44 ; OLetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
16F50 ; OLetter # Lo MIAO LETTER NASALIZATION
16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
-1B000..1B001 ; OLetter # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
+16FE0..16FE1 ; OLetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
+17000..187EC ; OLetter # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
+18800..18AF2 ; OLetter # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
+1B000..1B11E ; OLetter # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2
+1B170..1B2FB ; OLetter # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; OLetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; OLetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -2276,9 +2357,10 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
2A700..2B734 ; OLetter # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
+2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
-# Total code points: 106002
+# Total code points: 121354
# ================================================
@@ -2325,16 +2407,20 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
112F0..112F9 ; Numeric # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE
+11450..11459 ; Numeric # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE
11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE
116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
+11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
+11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
+1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
-# Total code points: 542
+# Total code points: 582
# ================================================
@@ -2398,10 +2484,14 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA
1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
112A9 ; STerm # Po MULTANI SECTION MARK
+1144B..1144C ; STerm # Po [2] NEWA DANDA..NEWA DOUBLE DANDA
115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA
115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA
1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
+11A42..11A43 ; STerm # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD
+11A9B..11A9C ; STerm # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
+11C41..11C42 ; STerm # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA
16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA
16AF5 ; STerm # Po BASSA VAH FULL STOP
16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
@@ -2409,7 +2499,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA88 ; STerm # Po SIGNWRITING FULL STOP
-# Total code points: 117
+# Total code points: 125
# ================================================
diff --git a/util/unicode/data/WordBreakProperty.txt b/util/unicode/data/WordBreakProperty.txt
index dc8e82020f..4c5440a894 100644
--- a/util/unicode/data/WordBreakProperty.txt
+++ b/util/unicode/data/WordBreakProperty.txt
@@ -1,10 +1,11 @@
-# WordBreakProperty-8.0.0.txt
-# Date: 2015-02-14, 10:26:15 GMT [MD]
+# WordBreakProperty-10.0.0.txt
+# Date: 2017-03-10, 02:00:42 GMT
+# © 2017 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
#
# Unicode Character Database
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-# For documentation, see http://www.unicode.org/reports/tr44/
+# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
@@ -89,6 +90,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
+08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
0903 ; Extend # Mc DEVANAGARI SIGN VISARGA
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
@@ -131,6 +133,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
0ACD ; Extend # Mn GUJARATI SIGN VIRAMA
0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
+0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU
0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B3C ; Extend # Mn ORIYA SIGN NUKTA
@@ -172,8 +175,9 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
-0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU
+0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
+0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
@@ -243,6 +247,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
17DD ; Extend # Mn KHMER SIGN ATTHACAN
180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA
1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
1923..1926 ; Extend # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU
@@ -307,10 +312,11 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW
1CED ; Extend # Mn VEDIC SIGN TIRYAK
1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE
+1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA
1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
-1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
-1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
-200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
+1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
+1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+200C ; Extend # Cf ZERO WIDTH NON-JOINER
20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1 ; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE
@@ -335,7 +341,7 @@ A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL
A827 ; Extend # Mc SYLOTI NAGRI VOWEL SIGN OO
A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
-A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA
+A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
@@ -417,6 +423,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11234 ; Extend # Mn KHOJKI SIGN ANUSVARA
11235 ; Extend # Mc KHOJKI SIGN VIRAMA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
+1123E ; Extend # Mn KHOJKI SIGN SUKUN
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
@@ -432,6 +439,12 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
+11435..11437 ; Extend # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11440..11441 ; Extend # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
+11445 ; Extend # Mc NEWA SIGN VISARGA
+11446 ; Extend # Mn NEWA SIGN NUKTA
114B0..114B2 ; Extend # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II
114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
114B9 ; Extend # Mc TIRHUTA VOWEL SIGN E
@@ -465,6 +478,36 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11726 ; Extend # Mc AHOM VOWEL SIGN E
11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
+11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
+11A07..11A08 ; Extend # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
+11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
+11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA
+11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER
+11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A57..11A58 ; Extend # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A97 ; Extend # Mc SOYOMBO SIGN VISARGA
+11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
+11C2F ; Extend # Mc BHAIKSUKI VOWEL SIGN AA
+11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3E ; Extend # Mc BHAIKSUKI SIGN VISARGA
+11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA
+11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CA9 ; Extend # Mc MARCHEN SUBJOINED LETTER YA
+11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB1 ; Extend # Mc MARCHEN VOWEL SIGN I
+11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB4 ; Extend # Mc MARCHEN VOWEL SIGN O
+11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
+11D47 ; Extend # Mn MASARAM GONDI RA-KARA
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
@@ -483,10 +526,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK
1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
+1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
+1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
+E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-# Total code points: 1967
+# Total code points: 2276
# ================================================
@@ -501,6 +551,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
061C ; Format # Cf ARABIC LETTER MARK
06DD ; Format # Cf ARABIC END OF AYAH
070F ; Format # Cf SYRIAC ABBREVIATION MARK
+08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH
180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR
200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
@@ -512,9 +563,8 @@ FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANN
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG
-E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG
-# Total code points: 147
+# Total code points: 52
# ================================================
@@ -551,10 +601,15 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
0294 ; ALetter # Lo LATIN LETTER GLOTTAL STOP
0295..02AF ; ALetter # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
02B0..02C1 ; ALetter # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP
+02C2..02C5 ; ALetter # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD
02C6..02D1 ; ALetter # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON
+02D2..02D7 ; ALetter # Sk [6] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER MINUS SIGN
+02DE..02DF ; ALetter # Sk [2] MODIFIER LETTER RHOTIC HOOK..MODIFIER LETTER CROSS ACCENT
02E0..02E4 ; ALetter # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
02EC ; ALetter # Lm MODIFIER LETTER VOICING
+02ED ; ALetter # Sk MODIFIER LETTER UNASPIRATED
02EE ; ALetter # Lm MODIFIER LETTER DOUBLE APOSTROPHE
+02EF..02FF ; ALetter # Sk [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW
0370..0373 ; ALetter # L& [4] GREEK CAPITAL LETTER HETA..GREEK SMALL LETTER ARCHAIC SAMPI
0374 ; ALetter # Lm GREEK NUMERAL SIGN
0376..0377 ; ALetter # L& [2] GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA..GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
@@ -594,7 +649,9 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
0824 ; ALetter # Lm SAMARITAN MODIFIER LETTER SHORT A
0828 ; ALetter # Lm SAMARITAN MODIFIER LETTER I
0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
+0860..086A ; ALetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; ALetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
+08B6..08BD ; ALetter # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
093D ; ALetter # Lo DEVANAGARI SIGN AVAGRAHA
0950 ; ALetter # Lo DEVANAGARI OM
@@ -612,6 +669,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
09DC..09DD ; ALetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E1 ; ALetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
09F0..09F1 ; ALetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
+09FC ; ALetter # Lo BENGALI LETTER VEDIC ANUSVARA
0A05..0A0A ; ALetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
0A0F..0A10 ; ALetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI
0A13..0A28 ; ALetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA
@@ -660,6 +718,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
0C3D ; ALetter # Lo TELUGU SIGN AVAGRAHA
0C58..0C5A ; ALetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
0C60..0C61 ; ALetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
+0C80 ; ALetter # Lo KANNADA SIGN SPACING CANDRABINDU
0C85..0C8C ; ALetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; ALetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI
0C92..0CA8 ; ALetter # Lo [23] KANNADA LETTER O..KANNADA LETTER NA
@@ -674,6 +733,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
0D12..0D3A ; ALetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3D ; ALetter # Lo MALAYALAM SIGN AVAGRAHA
0D4E ; ALetter # Lo MALAYALAM LETTER DOT REPH
+0D54..0D56 ; ALetter # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
0D5F..0D61 ; ALetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D7A..0D7F ; ALetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
0D85..0D96 ; ALetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
@@ -724,7 +784,8 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
1820..1842 ; ALetter # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
1843 ; ALetter # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877 ; ALetter # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
-1880..18A8 ; ALetter # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA
+1880..1884 ; ALetter # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
+1887..18A8 ; ALetter # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA
18AA ; ALetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
18B0..18F5 ; ALetter # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S
1900..191E ; ALetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA
@@ -738,6 +799,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
1C4D..1C4F ; ALetter # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA
1C5A..1C77 ; ALetter # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH
1C78..1C7D ; ALetter # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD
+1C80..1C88 ; ALetter # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
1CE9..1CEC ; ALetter # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL
1CEE..1CF1 ; ALetter # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
1CF5..1CF6 ; ALetter # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
@@ -813,7 +875,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
3005 ; ALetter # Lm IDEOGRAPHIC ITERATION MARK
303B ; ALetter # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
303C ; ALetter # Lo MASU MARK
-3105..312D ; ALetter # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
+3105..312E ; ALetter # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; ALetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
31A0..31BA ; ALetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
A000..A014 ; ALetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
@@ -833,13 +895,15 @@ A69C..A69D ; ALetter # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER
A6A0..A6E5 ; ALetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI
A6E6..A6EF ; ALetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM
A717..A71F ; ALetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
+A720..A721 ; ALetter # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE
A722..A76F ; ALetter # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON
A770 ; ALetter # Lm MODIFIER LETTER US
A771..A787 ; ALetter # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
+A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT
-A790..A7AD ; ALetter # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
+A790..A7AE ; ALetter # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B7 ; ALetter # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7F8..A7F9 ; ALetter # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
@@ -870,6 +934,7 @@ AB11..AB16 ; ALetter # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO
AB20..AB26 ; ALetter # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO
AB28..AB2E ; ALetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
AB30..AB5A ; ALetter # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
+AB5B ; ALetter # Sk MODIFIER BREVE WITH INVERTED BREVE
AB5C..AB5F ; ALetter # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
AB60..AB65 ; ALetter # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
AB70..ABBF ; ALetter # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
@@ -904,7 +969,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
10280..1029C ; ALetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X
102A0..102D0 ; ALetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
10300..1031F ; ALetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
-10330..10340 ; ALetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
+1032D..10340 ; ALetter # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; ALetter # Nl GOTHIC LETTER NINETY
10342..10349 ; ALetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; ALetter # Nl GOTHIC LETTER NINE HUNDRED
@@ -915,6 +980,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
103D1..103D5 ; ALetter # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED
10400..1044F ; ALetter # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW
10450..1049D ; ALetter # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO
+104B0..104D3 ; ALetter # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA
+104D8..104FB ; ALetter # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA
10500..10527 ; ALetter # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE
10530..10563 ; ALetter # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW
10600..10736 ; ALetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664
@@ -976,6 +1043,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1133D ; ALetter # Lo GRANTHA SIGN AVAGRAHA
11350 ; ALetter # Lo GRANTHA OM
1135D..11361 ; ALetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
+11400..11434 ; ALetter # Lo [53] NEWA LETTER A..NEWA LETTER HA
+11447..1144A ; ALetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI
11480..114AF ; ALetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA
114C4..114C5 ; ALetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG
114C7 ; ALetter # Lo TIRHUTA OM
@@ -986,7 +1055,21 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
11680..116AA ; ALetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA
118A0..118DF ; ALetter # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
118FF ; ALetter # Lo WARANG CITI OM
+11A00 ; ALetter # Lo ZANABAZAR SQUARE LETTER A
+11A0B..11A32 ; ALetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
+11A3A ; ALetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
+11A50 ; ALetter # Lo SOYOMBO LETTER A
+11A5C..11A83 ; ALetter # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
+11A86..11A89 ; ALetter # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11AC0..11AF8 ; ALetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
+11C00..11C08 ; ALetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
+11C0A..11C2E ; ALetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
+11C40 ; ALetter # Lo BHAIKSUKI SIGN AVAGRAHA
+11C72..11C8F ; ALetter # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A
+11D00..11D06 ; ALetter # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
+11D08..11D09 ; ALetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
+11D0B..11D30 ; ALetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
+11D46 ; ALetter # Lo MASARAM GONDI REPHA
12000..12399 ; ALetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; ALetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; ALetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
@@ -1002,6 +1085,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
16F00..16F44 ; ALetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
16F50 ; ALetter # Lo MIAO LETTER NASALIZATION
16F93..16F9F ; ALetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
+16FE0..16FE1 ; ALetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
1BC00..1BC6A ; ALetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; ALetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; ALetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -1037,6 +1121,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1D7AA..1D7C2 ; ALetter # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
1D7C4..1D7CB ; ALetter # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1E800..1E8C4 ; ALetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON
+1E900..1E943 ; ALetter # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA
1EE00..1EE03 ; ALetter # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; ALetter # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; ALetter # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
@@ -1074,13 +1159,12 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
-# Total code points: 27697
+# Total code points: 28179
# ================================================
003A ; MidLetter # Po COLON
00B7 ; MidLetter # Po MIDDLE DOT
-02D7 ; MidLetter # Sk MODIFIER LETTER MINUS SIGN
0387 ; MidLetter # Po GREEK ANO TELEIA
05F4 ; MidLetter # Po HEBREW PUNCTUATION GERSHAYIM
2027 ; MidLetter # Po HYPHENATION POINT
@@ -1088,7 +1172,7 @@ FE13 ; MidLetter # Po PRESENTATION FORM FOR VERTICAL COLON
FE55 ; MidLetter # Po SMALL COLON
FF1A ; MidLetter # Po FULLWIDTH COLON
-# Total code points: 9
+# Total code points: 8
# ================================================
@@ -1166,26 +1250,110 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
112F0..112F9 ; Numeric # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE
+11450..11459 ; Numeric # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE
11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE
116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
+11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
+11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE
16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
+1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
-# Total code points: 541
+# Total code points: 581
# ================================================
005F ; ExtendNumLet # Pc LOW LINE
+202F ; ExtendNumLet # Zs NARROW NO-BREAK SPACE
203F..2040 ; ExtendNumLet # Pc [2] UNDERTIE..CHARACTER TIE
2054 ; ExtendNumLet # Pc INVERTED UNDERTIE
FE33..FE34 ; ExtendNumLet # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE
FE4D..FE4F ; ExtendNumLet # Pc [3] DASHED LOW LINE..WAVY LOW LINE
FF3F ; ExtendNumLet # Pc FULLWIDTH LOW LINE
-# Total code points: 10
+# Total code points: 11
+
+# ================================================
+
+261D ; E_Base # So WHITE UP POINTING INDEX
+26F9 ; E_Base # So PERSON WITH BALL
+270A..270D ; E_Base # So [4] RAISED FIST..WRITING HAND
+1F385 ; E_Base # So FATHER CHRISTMAS
+1F3C2..1F3C4 ; E_Base # So [3] SNOWBOARDER..SURFER
+1F3C7 ; E_Base # So HORSE RACING
+1F3CA..1F3CC ; E_Base # So [3] SWIMMER..GOLFER
+1F442..1F443 ; E_Base # So [2] EAR..NOSE
+1F446..1F450 ; E_Base # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN
+1F46E ; E_Base # So POLICE OFFICER
+1F470..1F478 ; E_Base # So [9] BRIDE WITH VEIL..PRINCESS
+1F47C ; E_Base # So BABY ANGEL
+1F481..1F483 ; E_Base # So [3] INFORMATION DESK PERSON..DANCER
+1F485..1F487 ; E_Base # So [3] NAIL POLISH..HAIRCUT
+1F4AA ; E_Base # So FLEXED BICEPS
+1F574..1F575 ; E_Base # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY
+1F57A ; E_Base # So MAN DANCING
+1F590 ; E_Base # So RAISED HAND WITH FINGERS SPLAYED
+1F595..1F596 ; E_Base # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS
+1F645..1F647 ; E_Base # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY
+1F64B..1F64F ; E_Base # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS
+1F6A3 ; E_Base # So ROWBOAT
+1F6B4..1F6B6 ; E_Base # So [3] BICYCLIST..PEDESTRIAN
+1F6C0 ; E_Base # So BATH
+1F6CC ; E_Base # So SLEEPING ACCOMMODATION
+1F918..1F91C ; E_Base # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST
+1F91E..1F91F ; E_Base # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN
+1F926 ; E_Base # So FACE PALM
+1F930..1F939 ; E_Base # So [10] PREGNANT WOMAN..JUGGLING
+1F93D..1F93E ; E_Base # So [2] WATER POLO..HANDBALL
+1F9D1..1F9DD ; E_Base # So [13] ADULT..ELF
+
+# Total code points: 98
+
+# ================================================
+
+1F3FB..1F3FF ; E_Modifier # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
+
+# Total code points: 5
+
+# ================================================
+
+200D ; ZWJ # Cf ZERO WIDTH JOINER
+
+# Total code points: 1
+
+# ================================================
+
+2640 ; Glue_After_Zwj # So FEMALE SIGN
+2642 ; Glue_After_Zwj # So MALE SIGN
+2695..2696 ; Glue_After_Zwj # So [2] STAFF OF AESCULAPIUS..SCALES
+2708 ; Glue_After_Zwj # So AIRPLANE
+2764 ; Glue_After_Zwj # So HEAVY BLACK HEART
+1F308 ; Glue_After_Zwj # So RAINBOW
+1F33E ; Glue_After_Zwj # So EAR OF RICE
+1F373 ; Glue_After_Zwj # So COOKING
+1F393 ; Glue_After_Zwj # So GRADUATION CAP
+1F3A4 ; Glue_After_Zwj # So MICROPHONE
+1F3A8 ; Glue_After_Zwj # So ARTIST PALETTE
+1F3EB ; Glue_After_Zwj # So SCHOOL
+1F3ED ; Glue_After_Zwj # So FACTORY
+1F48B ; Glue_After_Zwj # So KISS MARK
+1F4BB..1F4BC ; Glue_After_Zwj # So [2] PERSONAL COMPUTER..BRIEFCASE
+1F527 ; Glue_After_Zwj # So WRENCH
+1F52C ; Glue_After_Zwj # So MICROSCOPE
+1F5E8 ; Glue_After_Zwj # So LEFT SPEECH BUBBLE
+1F680 ; Glue_After_Zwj # So ROCKET
+1F692 ; Glue_After_Zwj # So FIRE ENGINE
+
+# Total code points: 22
+
+# ================================================
+
+1F466..1F469 ; E_Base_GAZ # So [4] BOY..WOMAN
+
+# Total code points: 4
# EOF
diff --git a/util/unicode/main.cpp b/util/unicode/main.cpp
index c51995499d..0f3c28137d 100644
--- a/util/unicode/main.cpp
+++ b/util/unicode/main.cpp
@@ -274,11 +274,12 @@ static void initJoiningMap()
static const char *grapheme_break_class_string =
"enum GraphemeBreakClass {\n"
- " GraphemeBreak_Other,\n"
+ " GraphemeBreak_Any,\n"
" GraphemeBreak_CR,\n"
" GraphemeBreak_LF,\n"
" GraphemeBreak_Control,\n"
" GraphemeBreak_Extend,\n"
+ " GraphemeBreak_ZWJ,\n"
" GraphemeBreak_RegionalIndicator,\n"
" GraphemeBreak_Prepend,\n"
" GraphemeBreak_SpacingMark,\n"
@@ -286,15 +287,21 @@ static const char *grapheme_break_class_string =
" GraphemeBreak_V,\n"
" GraphemeBreak_T,\n"
" GraphemeBreak_LV,\n"
- " GraphemeBreak_LVT\n"
+ " GraphemeBreak_LVT,\n"
+ " Graphemebreak_E_Base,\n"
+ " Graphemebreak_E_Modifier,\n"
+ " Graphemebreak_Glue_After_Zwj,\n"
+ " Graphemebreak_E_Base_GAZ,\n"
+ " NumGraphemeBreakClasses,\n"
"};\n\n";
enum GraphemeBreakClass {
- GraphemeBreak_Other,
+ GraphemeBreak_Any,
GraphemeBreak_CR,
GraphemeBreak_LF,
GraphemeBreak_Control,
GraphemeBreak_Extend,
+ GraphemeBreak_ZWJ,
GraphemeBreak_RegionalIndicator,
GraphemeBreak_Prepend,
GraphemeBreak_SpacingMark,
@@ -302,9 +309,13 @@ enum GraphemeBreakClass {
GraphemeBreak_V,
GraphemeBreak_T,
GraphemeBreak_LV,
- GraphemeBreak_LVT
+ GraphemeBreak_LVT,
+ Graphemebreak_E_Base,
+ Graphemebreak_E_Modifier,
+ Graphemebreak_Glue_After_Zwj,
+ Graphemebreak_E_Base_GAZ,
- , GraphemeBreak_Unassigned
+ GraphemeBreak_Unassigned
};
static QHash<QByteArray, GraphemeBreakClass> grapheme_break_map;
@@ -315,11 +326,12 @@ static void initGraphemeBreak()
GraphemeBreakClass brk;
const char *name;
} breaks[] = {
- { GraphemeBreak_Other, "Other" },
+ { GraphemeBreak_Any, "Any" },
{ GraphemeBreak_CR, "CR" },
{ GraphemeBreak_LF, "LF" },
{ GraphemeBreak_Control, "Control" },
{ GraphemeBreak_Extend, "Extend" },
+ { GraphemeBreak_ZWJ, "ZWJ" },
{ GraphemeBreak_RegionalIndicator, "Regional_Indicator" },
{ GraphemeBreak_Prepend, "Prepend" },
{ GraphemeBreak_SpacingMark, "SpacingMark" },
@@ -328,6 +340,10 @@ static void initGraphemeBreak()
{ GraphemeBreak_T, "T" },
{ GraphemeBreak_LV, "LV" },
{ GraphemeBreak_LVT, "LVT" },
+ { Graphemebreak_E_Base, "E_Base" },
+ { Graphemebreak_E_Modifier, "E_Modifier" },
+ { Graphemebreak_Glue_After_Zwj, "Glue_After_Zwj" },
+ { Graphemebreak_E_Base_GAZ, "E_Base_GAZ" },
{ GraphemeBreak_Unassigned, 0 }
};
GraphemeBreakList *d = breaks;
@@ -340,11 +356,13 @@ static void initGraphemeBreak()
static const char *word_break_class_string =
"enum WordBreakClass {\n"
- " WordBreak_Other,\n"
+ " WordBreak_Any,\n"
" WordBreak_CR,\n"
" WordBreak_LF,\n"
" WordBreak_Newline,\n"
" WordBreak_Extend,\n"
+ " WordBreak_ZWJ,\n"
+ " WordBreak_Format,\n"
" WordBreak_RegionalIndicator,\n"
" WordBreak_Katakana,\n"
" WordBreak_HebrewLetter,\n"
@@ -355,15 +373,22 @@ static const char *word_break_class_string =
" WordBreak_MidLetter,\n"
" WordBreak_MidNum,\n"
" WordBreak_Numeric,\n"
- " WordBreak_ExtendNumLet\n"
+ " WordBreak_ExtendNumLet,\n"
+ " WordBreak_E_Base,\n"
+ " WordBreak_E_Modifier,\n"
+ " WordBreak_Glue_After_Zwj,\n"
+ " WordBreak_E_Base_GAZ,\n"
+ " NumWordBreakClasses,\n"
"};\n\n";
enum WordBreakClass {
- WordBreak_Other,
+ WordBreak_Any,
WordBreak_CR,
WordBreak_LF,
WordBreak_Newline,
WordBreak_Extend,
+ WordBreak_ZWJ,
+ WordBreak_Format,
WordBreak_RegionalIndicator,
WordBreak_Katakana,
WordBreak_HebrewLetter,
@@ -374,9 +399,13 @@ enum WordBreakClass {
WordBreak_MidLetter,
WordBreak_MidNum,
WordBreak_Numeric,
- WordBreak_ExtendNumLet
+ WordBreak_ExtendNumLet,
+ WordBreak_E_Base,
+ WordBreak_E_Modifier,
+ WordBreak_Glue_After_Zwj,
+ WordBreak_E_Base_GAZ,
- , WordBreak_Unassigned
+ WordBreak_Unassigned
};
static QHash<QByteArray, WordBreakClass> word_break_map;
@@ -387,12 +416,13 @@ static void initWordBreak()
WordBreakClass brk;
const char *name;
} breaks[] = {
- { WordBreak_Other, "Other" },
+ { WordBreak_Any, "Any" },
{ WordBreak_CR, "CR" },
{ WordBreak_LF, "LF" },
{ WordBreak_Newline, "Newline" },
{ WordBreak_Extend, "Extend" },
- { WordBreak_Extend, "Format" },
+ { WordBreak_ZWJ, "ZWJ" },
+ { WordBreak_Format, "Format" },
{ WordBreak_RegionalIndicator, "Regional_Indicator" },
{ WordBreak_Katakana, "Katakana" },
{ WordBreak_HebrewLetter, "Hebrew_Letter" },
@@ -404,6 +434,10 @@ static void initWordBreak()
{ WordBreak_MidNum, "MidNum" },
{ WordBreak_Numeric, "Numeric" },
{ WordBreak_ExtendNumLet, "ExtendNumLet" },
+ { WordBreak_E_Base, "E_Base" },
+ { WordBreak_E_Modifier, "E_Modifier" },
+ { WordBreak_Glue_After_Zwj, "Glue_After_Zwj" },
+ { WordBreak_E_Base_GAZ, "E_Base_GAZ" },
{ WordBreak_Unassigned, 0 }
};
WordBreakList *d = breaks;
@@ -416,7 +450,7 @@ static void initWordBreak()
static const char *sentence_break_class_string =
"enum SentenceBreakClass {\n"
- " SentenceBreak_Other,\n"
+ " SentenceBreak_Any,\n"
" SentenceBreak_CR,\n"
" SentenceBreak_LF,\n"
" SentenceBreak_Sep,\n"
@@ -429,11 +463,12 @@ static const char *sentence_break_class_string =
" SentenceBreak_ATerm,\n"
" SentenceBreak_SContinue,\n"
" SentenceBreak_STerm,\n"
- " SentenceBreak_Close\n"
+ " SentenceBreak_Close,\n"
+ " NumSentenceBreakClasses\n"
"};\n\n";
enum SentenceBreakClass {
- SentenceBreak_Other,
+ SentenceBreak_Any,
SentenceBreak_CR,
SentenceBreak_LF,
SentenceBreak_Sep,
@@ -459,7 +494,7 @@ static void initSentenceBreak()
SentenceBreakClass brk;
const char *name;
} breaks[] = {
- { SentenceBreak_Other, "Other" },
+ { SentenceBreak_Any, "Any" },
{ SentenceBreak_CR, "CR" },
{ SentenceBreak_LF, "LF" },
{ SentenceBreak_Sep, "Sep" },
@@ -494,8 +529,10 @@ static const char *line_break_class_string =
" LineBreak_IN, LineBreak_HY, LineBreak_BA, LineBreak_BB, LineBreak_B2,\n"
" LineBreak_ZW, LineBreak_CM, LineBreak_WJ, LineBreak_H2, LineBreak_H3,\n"
" LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_RI, LineBreak_CB,\n"
- " LineBreak_SA, LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF,\n"
- " LineBreak_BK\n"
+ " LineBreak_EB, LineBreak_EM, LineBreak_ZWJ,\n"
+ " LineBreak_SA, LineBreak_SG, LineBreak_SP,\n"
+ " LineBreak_CR, LineBreak_LF, LineBreak_BK,\n"
+ " NumLineBreakClasses\n"
"};\n\n";
enum LineBreakClass {
@@ -505,10 +542,11 @@ enum LineBreakClass {
LineBreak_IN, LineBreak_HY, LineBreak_BA, LineBreak_BB, LineBreak_B2,
LineBreak_ZW, LineBreak_CM, LineBreak_WJ, LineBreak_H2, LineBreak_H3,
LineBreak_JL, LineBreak_JV, LineBreak_JT, LineBreak_RI, LineBreak_CB,
- LineBreak_SA, LineBreak_SG, LineBreak_SP, LineBreak_CR, LineBreak_LF,
- LineBreak_BK
+ LineBreak_EB, LineBreak_EM, LineBreak_ZWJ,
+ LineBreak_SA, LineBreak_SG, LineBreak_SP,
+ LineBreak_CR, LineBreak_LF, LineBreak_BK,
- , LineBreak_Unassigned
+ LineBreak_Unassigned
};
static QHash<QByteArray, LineBreakClass> line_break_map;
@@ -563,6 +601,9 @@ static void initLineBreak()
{ LineBreak_RI, "RI" },
{ LineBreak_SA, "SA" },
{ LineBreak_AL, "XX" },
+ { LineBreak_EB, "EB" },
+ { LineBreak_EM, "EM" },
+ { LineBreak_ZWJ, "ZWJ" },
{ LineBreak_Unassigned, 0 }
};
LineBreakList *d = breaks;
@@ -768,10 +809,10 @@ static const char *property_string =
" signed short caseFoldDiff : 15;\n"
" ushort unicodeVersion : 8; /* 5 used */\n"
" ushort nfQuickCheck : 8;\n" // could be narrowed
- " ushort graphemeBreakClass : 4; /* 4 used */\n"
- " ushort wordBreakClass : 4; /* 4 used */\n"
+ " ushort graphemeBreakClass : 5; /* 5 used */\n"
+ " ushort wordBreakClass : 5; /* 5 used */\n"
" ushort sentenceBreakClass : 8; /* 4 used */\n"
- " ushort lineBreakClass : 8; /* 6 used */\n"
+ " ushort lineBreakClass : 6; /* 6 used */\n"
" ushort script : 8;\n"
"};\n\n"
"Q_CORE_EXPORT const Properties * QT_FASTCALL properties(uint ucs4) Q_DECL_NOTHROW;\n"
@@ -1034,9 +1075,9 @@ struct UnicodeData {
p.upperCaseSpecial = 0;
p.titleCaseSpecial = 0;
p.caseFoldSpecial = 0;
- p.graphemeBreakClass = GraphemeBreak_Other;
- p.wordBreakClass = WordBreak_Other;
- p.sentenceBreakClass = SentenceBreak_Other;
+ p.graphemeBreakClass = GraphemeBreak_Any;
+ p.wordBreakClass = WordBreak_Any;
+ p.sentenceBreakClass = SentenceBreak_Any;
p.script = QChar::Script_Unknown;
p.nfQuickCheck = 0;
propertyIndex = -1;
@@ -1913,7 +1954,7 @@ static void readWordBreak()
if (codepoint == 0x002E) // FULL STOP
brk = WordBreak_MidNum;
else if (codepoint == 0x003A) // COLON
- brk = WordBreak_Other;
+ brk = WordBreak_Any;
// ] ###
UnicodeData &ud = UnicodeData::valueRef(codepoint);
ud.p.wordBreakClass = brk;
@@ -2456,10 +2497,10 @@ static QByteArray createPropertyInfo()
// " ushort nfQuickCheck : 8;\n"
out += QByteArray::number( p.nfQuickCheck );
out += ", ";
-// " ushort graphemeBreakClass : 4; /* 4 used */\n"
-// " ushort wordBreakClass : 4; /* 4 used */\n"
+// " ushort graphemeBreakClass : 5; /* 5 used */\n"
+// " ushort wordBreakClass : 5; /* 5 used */\n"
// " ushort sentenceBreakClass : 8; /* 4 used */\n"
-// " ushort lineBreakClass : 8; /* 6 used */\n"
+// " ushort lineBreakClass : 6; /* 6 used */\n"
out += QByteArray::number( p.graphemeBreakClass );
out += ", ";
out += QByteArray::number( p.wordBreakClass );