summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/WordBreakProperty.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/WordBreakProperty.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/WordBreakProperty.txt')
-rw-r--r--util/unicode/data/WordBreakProperty.txt212
1 files changed, 190 insertions, 22 deletions
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