summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/GraphemeBreakProperty.txt
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/unicode/data/GraphemeBreakProperty.txt
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/unicode/data/GraphemeBreakProperty.txt')
-rw-r--r--util/unicode/data/GraphemeBreakProperty.txt175
1 files changed, 157 insertions, 18 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