aboutsummaryrefslogtreecommitdiff
path: root/localedata/unicode-gen
diff options
context:
space:
mode:
authorMike FABIAN <mfabian@redhat.com>2017-09-06 11:19:33 +0200
committerMike FABIAN <mfabian@redhat.com>2017-09-06 12:39:49 +0200
commit2ae5be041d9ea89cdd0f37734d72051e8f773947 (patch)
treec3d52a8b19d8be09ad89b6bbe6b8f0b462b98a48 /localedata/unicode-gen
parentaf83ed5c4647bda196fc1a7efebbe8019aa83f4a (diff)
downloadglibc-2ae5be041d9ea89cdd0f37734d72051e8f773947.tar
glibc-2ae5be041d9ea89cdd0f37734d72051e8f773947.tar.gz
glibc-2ae5be041d9ea89cdd0f37734d72051e8f773947.tar.bz2
glibc-2ae5be041d9ea89cdd0f37734d72051e8f773947.zip
Improve utf8_gen.py to set the width for characters with Prepended_Concatenation_Mark property to 1
[BZ #22070] * localedata/unicode-gen/utf8_gen.py: Set the width for characters with Prepended_Concatenation_Mark property to 1 * localedata/charmaps/UTF-8: Updated using the improved script.
Diffstat (limited to 'localedata/unicode-gen')
-rw-r--r--localedata/unicode-gen/Makefile4
-rw-r--r--localedata/unicode-gen/PropList.txt1618
-rwxr-xr-xlocaledata/unicode-gen/utf8_gen.py33
3 files changed, 1648 insertions, 7 deletions
diff --git a/localedata/unicode-gen/Makefile b/localedata/unicode-gen/Makefile
index d62603ed3d..4564670451 100644
--- a/localedata/unicode-gen/Makefile
+++ b/localedata/unicode-gen/Makefile
@@ -40,7 +40,7 @@ UNICODE_VERSION = 10.0.0
PYTHON3 = python3
WGET = wget
-DOWNLOADS = UnicodeData.txt DerivedCoreProperties.txt EastAsianWidth.txt
+DOWNLOADS = UnicodeData.txt DerivedCoreProperties.txt EastAsianWidth.txt PropList.txt
GENERATED = i18n tr_TR UTF-8 translit_combining translit_compat translit_circle translit_cjk_compat translit_font translit_fraction
REPORTS = i18n-report UTF-8-report
@@ -92,7 +92,7 @@ tr_TR: gen_unicode_ctype.py
UTF-8: UnicodeData.txt EastAsianWidth.txt
UTF-8: utf8_gen.py
- $(PYTHON3) utf8_gen.py UnicodeData.txt EastAsianWidth.txt
+ $(PYTHON3) utf8_gen.py UnicodeData.txt EastAsianWidth.txt PropList.txt
UTF-8-report: UTF-8 ../charmaps/UTF-8
UTF-8-report: utf8_compatibility.py
diff --git a/localedata/unicode-gen/PropList.txt b/localedata/unicode-gen/PropList.txt
new file mode 100644
index 0000000000..9a2d0e4b1c
--- /dev/null
+++ b/localedata/unicode-gen/PropList.txt
@@ -0,0 +1,1618 @@
+# PropList-10.0.0.txt
+# Date: 2017-03-10, 08:25:30 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
+# For documentation, see http://www.unicode.org/reports/tr44/
+
+# ================================================
+
+0009..000D ; White_Space # Cc [5] <control-0009>..<control-000D>
+0020 ; White_Space # Zs SPACE
+0085 ; White_Space # Cc <control-0085>
+00A0 ; White_Space # Zs NO-BREAK SPACE
+1680 ; White_Space # Zs OGHAM SPACE MARK
+2000..200A ; White_Space # Zs [11] EN QUAD..HAIR SPACE
+2028 ; White_Space # Zl LINE SEPARATOR
+2029 ; White_Space # Zp PARAGRAPH SEPARATOR
+202F ; White_Space # Zs NARROW NO-BREAK SPACE
+205F ; White_Space # Zs MEDIUM MATHEMATICAL SPACE
+3000 ; White_Space # Zs IDEOGRAPHIC SPACE
+
+# Total code points: 25
+
+# ================================================
+
+061C ; Bidi_Control # Cf ARABIC LETTER MARK
+200E..200F ; Bidi_Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
+202A..202E ; Bidi_Control # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
+2066..2069 ; Bidi_Control # Cf [4] LEFT-TO-RIGHT ISOLATE..POP DIRECTIONAL ISOLATE
+
+# Total code points: 12
+
+# ================================================
+
+200C..200D ; Join_Control # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
+
+# Total code points: 2
+
+# ================================================
+
+002D ; Dash # Pd HYPHEN-MINUS
+058A ; Dash # Pd ARMENIAN HYPHEN
+05BE ; Dash # Pd HEBREW PUNCTUATION MAQAF
+1400 ; Dash # Pd CANADIAN SYLLABICS HYPHEN
+1806 ; Dash # Pd MONGOLIAN TODO SOFT HYPHEN
+2010..2015 ; Dash # Pd [6] HYPHEN..HORIZONTAL BAR
+2053 ; Dash # Po SWUNG DASH
+207B ; Dash # Sm SUPERSCRIPT MINUS
+208B ; Dash # Sm SUBSCRIPT MINUS
+2212 ; Dash # Sm MINUS SIGN
+2E17 ; Dash # Pd DOUBLE OBLIQUE HYPHEN
+2E1A ; Dash # Pd HYPHEN WITH DIAERESIS
+2E3A..2E3B ; Dash # Pd [2] TWO-EM DASH..THREE-EM DASH
+2E40 ; Dash # Pd DOUBLE HYPHEN
+301C ; Dash # Pd WAVE DASH
+3030 ; Dash # Pd WAVY DASH
+30A0 ; Dash # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN
+FE31..FE32 ; Dash # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
+FE58 ; Dash # Pd SMALL EM DASH
+FE63 ; Dash # Pd SMALL HYPHEN-MINUS
+FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
+
+# Total code points: 28
+
+# ================================================
+
+002D ; Hyphen # Pd HYPHEN-MINUS
+00AD ; Hyphen # Cf SOFT HYPHEN
+058A ; Hyphen # Pd ARMENIAN HYPHEN
+1806 ; Hyphen # Pd MONGOLIAN TODO SOFT HYPHEN
+2010..2011 ; Hyphen # Pd [2] HYPHEN..NON-BREAKING HYPHEN
+2E17 ; Hyphen # Pd DOUBLE OBLIQUE HYPHEN
+30FB ; Hyphen # Po KATAKANA MIDDLE DOT
+FE63 ; Hyphen # Pd SMALL HYPHEN-MINUS
+FF0D ; Hyphen # Pd FULLWIDTH HYPHEN-MINUS
+FF65 ; Hyphen # Po HALFWIDTH KATAKANA MIDDLE DOT
+
+# Total code points: 11
+
+# ================================================
+
+0022 ; Quotation_Mark # Po QUOTATION MARK
+0027 ; Quotation_Mark # Po APOSTROPHE
+00AB ; Quotation_Mark # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+00BB ; Quotation_Mark # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+2018 ; Quotation_Mark # Pi LEFT SINGLE QUOTATION MARK
+2019 ; Quotation_Mark # Pf RIGHT SINGLE QUOTATION MARK
+201A ; Quotation_Mark # Ps SINGLE LOW-9 QUOTATION MARK
+201B..201C ; Quotation_Mark # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK
+201D ; Quotation_Mark # Pf RIGHT DOUBLE QUOTATION MARK
+201E ; Quotation_Mark # Ps DOUBLE LOW-9 QUOTATION MARK
+201F ; Quotation_Mark # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK
+2039 ; Quotation_Mark # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+203A ; Quotation_Mark # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+2E42 ; Quotation_Mark # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
+300C ; Quotation_Mark # Ps LEFT CORNER BRACKET
+300D ; Quotation_Mark # Pe RIGHT CORNER BRACKET
+300E ; Quotation_Mark # Ps LEFT WHITE CORNER BRACKET
+300F ; Quotation_Mark # Pe RIGHT WHITE CORNER BRACKET
+301D ; Quotation_Mark # Ps REVERSED DOUBLE PRIME QUOTATION MARK
+301E..301F ; Quotation_Mark # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK
+FE41 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET
+FE42 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET
+FE43 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET
+FE44 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET
+FF02 ; Quotation_Mark # Po FULLWIDTH QUOTATION MARK
+FF07 ; Quotation_Mark # Po FULLWIDTH APOSTROPHE
+FF62 ; Quotation_Mark # Ps HALFWIDTH LEFT CORNER BRACKET
+FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
+
+# Total code points: 30
+
+# ================================================
+
+0021 ; Terminal_Punctuation # Po EXCLAMATION MARK
+002C ; Terminal_Punctuation # Po COMMA
+002E ; Terminal_Punctuation # Po FULL STOP
+003A..003B ; Terminal_Punctuation # Po [2] COLON..SEMICOLON
+003F ; Terminal_Punctuation # Po QUESTION MARK
+037E ; Terminal_Punctuation # Po GREEK QUESTION MARK
+0387 ; Terminal_Punctuation # Po GREEK ANO TELEIA
+0589 ; Terminal_Punctuation # Po ARMENIAN FULL STOP
+05C3 ; Terminal_Punctuation # Po HEBREW PUNCTUATION SOF PASUQ
+060C ; Terminal_Punctuation # Po ARABIC COMMA
+061B ; Terminal_Punctuation # Po ARABIC SEMICOLON
+061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK
+06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP
+0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION
+070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS
+07F8..07F9 ; Terminal_Punctuation # Po [2] NKO COMMA..NKO EXCLAMATION MARK
+0830..083E ; Terminal_Punctuation # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU
+085E ; Terminal_Punctuation # Po MANDAIC PUNCTUATION
+0964..0965 ; Terminal_Punctuation # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
+0E5A..0E5B ; Terminal_Punctuation # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT
+0F08 ; Terminal_Punctuation # Po TIBETAN MARK SBRUL SHAD
+0F0D..0F12 ; Terminal_Punctuation # Po [6] TIBETAN MARK SHAD..TIBETAN MARK RGYA GRAM SHAD
+104A..104B ; Terminal_Punctuation # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
+1361..1368 ; Terminal_Punctuation # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
+166D..166E ; Terminal_Punctuation # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
+16EB..16ED ; Terminal_Punctuation # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION
+1735..1736 ; Terminal_Punctuation # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
+17D4..17D6 ; Terminal_Punctuation # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH
+17DA ; Terminal_Punctuation # Po KHMER SIGN KOOMUUT
+1802..1805 ; Terminal_Punctuation # Po [4] MONGOLIAN COMMA..MONGOLIAN FOUR DOTS
+1808..1809 ; Terminal_Punctuation # Po [2] MONGOLIAN MANCHU COMMA..MONGOLIAN MANCHU FULL STOP
+1944..1945 ; Terminal_Punctuation # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
+1AA8..1AAB ; Terminal_Punctuation # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU
+1B5A..1B5B ; Terminal_Punctuation # Po [2] BALINESE PANTI..BALINESE PAMADA
+1B5D..1B5F ; Terminal_Punctuation # Po [3] BALINESE CARIK PAMUNGKAH..BALINESE CARIK PAREREN
+1C3B..1C3F ; Terminal_Punctuation # Po [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK
+1C7E..1C7F ; Terminal_Punctuation # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
+203C..203D ; Terminal_Punctuation # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG
+2047..2049 ; Terminal_Punctuation # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
+2E2E ; Terminal_Punctuation # Po REVERSED QUESTION MARK
+2E3C ; Terminal_Punctuation # Po STENOGRAPHIC FULL STOP
+2E41 ; Terminal_Punctuation # Po REVERSED COMMA
+3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
+A4FE..A4FF ; Terminal_Punctuation # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP
+A60D..A60F ; Terminal_Punctuation # Po [3] VAI COMMA..VAI QUESTION MARK
+A6F3..A6F7 ; Terminal_Punctuation # Po [5] BAMUM FULL STOP..BAMUM QUESTION MARK
+A876..A877 ; Terminal_Punctuation # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD
+A8CE..A8CF ; Terminal_Punctuation # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
+A92F ; Terminal_Punctuation # Po KAYAH LI SIGN SHYA
+A9C7..A9C9 ; Terminal_Punctuation # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI
+AA5D..AA5F ; Terminal_Punctuation # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
+AADF ; Terminal_Punctuation # Po TAI VIET SYMBOL KOI KOI
+AAF0..AAF1 ; Terminal_Punctuation # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
+ABEB ; Terminal_Punctuation # Po MEETEI MAYEK CHEIKHEI
+FE50..FE52 ; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP
+FE54..FE57 ; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK
+FF01 ; Terminal_Punctuation # Po FULLWIDTH EXCLAMATION MARK
+FF0C ; Terminal_Punctuation # Po FULLWIDTH COMMA
+FF0E ; Terminal_Punctuation # Po FULLWIDTH FULL STOP
+FF1A..FF1B ; Terminal_Punctuation # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON
+FF1F ; Terminal_Punctuation # Po FULLWIDTH QUESTION MARK
+FF61 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC FULL STOP
+FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
+1039F ; Terminal_Punctuation # Po UGARITIC WORD DIVIDER
+103D0 ; Terminal_Punctuation # Po OLD PERSIAN WORD DIVIDER
+10857 ; Terminal_Punctuation # Po IMPERIAL ARAMAIC SECTION SIGN
+1091F ; Terminal_Punctuation # Po PHOENICIAN WORD SEPARATOR
+10A56..10A57 ; Terminal_Punctuation # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
+10AF0..10AF5 ; Terminal_Punctuation # Po [6] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION TWO DOTS
+10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION
+10B99..10B9C ; Terminal_Punctuation # Po [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT
+11047..1104D ; Terminal_Punctuation # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS
+110BE..110C1 ; Terminal_Punctuation # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
+11141..11143 ; Terminal_Punctuation # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
+111C5..111C6 ; Terminal_Punctuation # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
+111CD ; Terminal_Punctuation # Po SHARADA SUTRA MARK
+111DE..111DF ; Terminal_Punctuation # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2
+11238..1123C ; Terminal_Punctuation # Po [5] KHOJKI DANDA..KHOJKI DOUBLE SECTION MARK
+112A9 ; Terminal_Punctuation # Po MULTANI SECTION MARK
+1144B..1144D ; Terminal_Punctuation # Po [3] NEWA DANDA..NEWA COMMA
+1145B ; Terminal_Punctuation # Po NEWA PLACEHOLDER MARK
+115C2..115C5 ; Terminal_Punctuation # Po [4] SIDDHAM DANDA..SIDDHAM SEPARATOR BAR
+115C9..115D7 ; Terminal_Punctuation # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
+11641..11642 ; Terminal_Punctuation # Po [2] MODI DANDA..MODI DOUBLE DANDA
+1173C..1173E ; Terminal_Punctuation # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
+11A42..11A43 ; Terminal_Punctuation # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD
+11A9B..11A9C ; Terminal_Punctuation # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
+11AA1..11AA2 ; Terminal_Punctuation # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2
+11C41..11C43 ; Terminal_Punctuation # Po [3] BHAIKSUKI DANDA..BHAIKSUKI WORD SEPARATOR
+11C71 ; Terminal_Punctuation # Po MARCHEN MARK SHAD
+12470..12474 ; Terminal_Punctuation # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
+16A6E..16A6F ; Terminal_Punctuation # Po [2] MRO DANDA..MRO DOUBLE DANDA
+16AF5 ; Terminal_Punctuation # Po BASSA VAH FULL STOP
+16B37..16B39 ; Terminal_Punctuation # Po [3] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN CIM CHEEM
+16B44 ; Terminal_Punctuation # Po PAHAWH HMONG SIGN XAUS
+1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
+1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON
+
+# Total code points: 252
+
+# ================================================
+
+005E ; Other_Math # Sk CIRCUMFLEX ACCENT
+03D0..03D2 ; Other_Math # L& [3] GREEK BETA SYMBOL..GREEK UPSILON WITH HOOK SYMBOL
+03D5 ; Other_Math # L& GREEK PHI SYMBOL
+03F0..03F1 ; Other_Math # L& [2] GREEK KAPPA SYMBOL..GREEK RHO SYMBOL
+03F4..03F5 ; Other_Math # L& [2] GREEK CAPITAL THETA SYMBOL..GREEK LUNATE EPSILON SYMBOL
+2016 ; Other_Math # Po DOUBLE VERTICAL LINE
+2032..2034 ; Other_Math # Po [3] PRIME..TRIPLE PRIME
+2040 ; Other_Math # Pc CHARACTER TIE
+2061..2064 ; Other_Math # Cf [4] FUNCTION APPLICATION..INVISIBLE PLUS
+207D ; Other_Math # Ps SUPERSCRIPT LEFT PARENTHESIS
+207E ; Other_Math # Pe SUPERSCRIPT RIGHT PARENTHESIS
+208D ; Other_Math # Ps SUBSCRIPT LEFT PARENTHESIS
+208E ; Other_Math # Pe SUBSCRIPT RIGHT PARENTHESIS
+20D0..20DC ; Other_Math # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
+20E1 ; Other_Math # Mn COMBINING LEFT RIGHT ARROW ABOVE
+20E5..20E6 ; Other_Math # Mn [2] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING DOUBLE VERTICAL STROKE OVERLAY
+20EB..20EF ; Other_Math # Mn [5] COMBINING LONG DOUBLE SOLIDUS OVERLAY..COMBINING RIGHT ARROW BELOW
+2102 ; Other_Math # L& DOUBLE-STRUCK CAPITAL C
+2107 ; Other_Math # L& EULER CONSTANT
+210A..2113 ; Other_Math # L& [10] SCRIPT SMALL G..SCRIPT SMALL L
+2115 ; Other_Math # L& DOUBLE-STRUCK CAPITAL N
+2119..211D ; Other_Math # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R
+2124 ; Other_Math # L& DOUBLE-STRUCK CAPITAL Z
+2128 ; Other_Math # L& BLACK-LETTER CAPITAL Z
+2129 ; Other_Math # So TURNED GREEK SMALL LETTER IOTA
+212C..212D ; Other_Math # L& [2] SCRIPT CAPITAL B..BLACK-LETTER CAPITAL C
+212F..2131 ; Other_Math # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F
+2133..2134 ; Other_Math # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O
+2135..2138 ; Other_Math # Lo [4] ALEF SYMBOL..DALET SYMBOL
+213C..213F ; Other_Math # L& [4] DOUBLE-STRUCK SMALL PI..DOUBLE-STRUCK CAPITAL PI
+2145..2149 ; Other_Math # L& [5] DOUBLE-STRUCK ITALIC CAPITAL D..DOUBLE-STRUCK ITALIC SMALL J
+2195..2199 ; Other_Math # So [5] UP DOWN ARROW..SOUTH WEST ARROW
+219C..219F ; Other_Math # So [4] LEFTWARDS WAVE ARROW..UPWARDS TWO HEADED ARROW
+21A1..21A2 ; Other_Math # So [2] DOWNWARDS TWO HEADED ARROW..LEFTWARDS ARROW WITH TAIL
+21A4..21A5 ; Other_Math # So [2] LEFTWARDS ARROW FROM BAR..UPWARDS ARROW FROM BAR
+21A7 ; Other_Math # So DOWNWARDS ARROW FROM BAR
+21A9..21AD ; Other_Math # So [5] LEFTWARDS ARROW WITH HOOK..LEFT RIGHT WAVE ARROW
+21B0..21B1 ; Other_Math # So [2] UPWARDS ARROW WITH TIP LEFTWARDS..UPWARDS ARROW WITH TIP RIGHTWARDS
+21B6..21B7 ; Other_Math # So [2] ANTICLOCKWISE TOP SEMICIRCLE ARROW..CLOCKWISE TOP SEMICIRCLE ARROW
+21BC..21CD ; Other_Math # So [18] LEFTWARDS HARPOON WITH BARB UPWARDS..LEFTWARDS DOUBLE ARROW WITH STROKE
+21D0..21D1 ; Other_Math # So [2] LEFTWARDS DOUBLE ARROW..UPWARDS DOUBLE ARROW
+21D3 ; Other_Math # So DOWNWARDS DOUBLE ARROW
+21D5..21DB ; Other_Math # So [7] UP DOWN DOUBLE ARROW..RIGHTWARDS TRIPLE ARROW
+21DD ; Other_Math # So RIGHTWARDS SQUIGGLE ARROW
+21E4..21E5 ; Other_Math # So [2] LEFTWARDS ARROW TO BAR..RIGHTWARDS ARROW TO BAR
+2308 ; Other_Math # Ps LEFT CEILING
+2309 ; Other_Math # Pe RIGHT CEILING
+230A ; Other_Math # Ps LEFT FLOOR
+230B ; Other_Math # Pe RIGHT FLOOR
+23B4..23B5 ; Other_Math # So [2] TOP SQUARE BRACKET..BOTTOM SQUARE BRACKET
+23B7 ; Other_Math # So RADICAL SYMBOL BOTTOM
+23D0 ; Other_Math # So VERTICAL LINE EXTENSION
+23E2 ; Other_Math # So WHITE TRAPEZIUM
+25A0..25A1 ; Other_Math # So [2] BLACK SQUARE..WHITE SQUARE
+25AE..25B6 ; Other_Math # So [9] BLACK VERTICAL RECTANGLE..BLACK RIGHT-POINTING TRIANGLE
+25BC..25C0 ; Other_Math # So [5] BLACK DOWN-POINTING TRIANGLE..BLACK LEFT-POINTING TRIANGLE
+25C6..25C7 ; Other_Math # So [2] BLACK DIAMOND..WHITE DIAMOND
+25CA..25CB ; Other_Math # So [2] LOZENGE..WHITE CIRCLE
+25CF..25D3 ; Other_Math # So [5] BLACK CIRCLE..CIRCLE WITH UPPER HALF BLACK
+25E2 ; Other_Math # So BLACK LOWER RIGHT TRIANGLE
+25E4 ; Other_Math # So BLACK UPPER LEFT TRIANGLE
+25E7..25EC ; Other_Math # So [6] SQUARE WITH LEFT HALF BLACK..WHITE UP-POINTING TRIANGLE WITH DOT
+2605..2606 ; Other_Math # So [2] BLACK STAR..WHITE STAR
+2640 ; Other_Math # So FEMALE SIGN
+2642 ; Other_Math # So MALE SIGN
+2660..2663 ; Other_Math # So [4] BLACK SPADE SUIT..BLACK CLUB SUIT
+266D..266E ; Other_Math # So [2] MUSIC FLAT SIGN..MUSIC NATURAL SIGN
+27C5 ; Other_Math # Ps LEFT S-SHAPED BAG DELIMITER
+27C6 ; Other_Math # Pe RIGHT S-SHAPED BAG DELIMITER
+27E6 ; Other_Math # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
+27E7 ; Other_Math # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
+27E8 ; Other_Math # Ps MATHEMATICAL LEFT ANGLE BRACKET
+27E9 ; Other_Math # Pe MATHEMATICAL RIGHT ANGLE BRACKET
+27EA ; Other_Math # Ps MATHEMATICAL LEFT DOUBLE ANGLE BRACKET
+27EB ; Other_Math # Pe MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET
+27EC ; Other_Math # Ps MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET
+27ED ; Other_Math # Pe MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET
+27EE ; Other_Math # Ps MATHEMATICAL LEFT FLATTENED PARENTHESIS
+27EF ; Other_Math # Pe MATHEMATICAL RIGHT FLATTENED PARENTHESIS
+2983 ; Other_Math # Ps LEFT WHITE CURLY BRACKET
+2984 ; Other_Math # Pe RIGHT WHITE CURLY BRACKET
+2985 ; Other_Math # Ps LEFT WHITE PARENTHESIS
+2986 ; Other_Math # Pe RIGHT WHITE PARENTHESIS
+2987 ; Other_Math # Ps Z NOTATION LEFT IMAGE BRACKET
+2988 ; Other_Math # Pe Z NOTATION RIGHT IMAGE BRACKET
+2989 ; Other_Math # Ps Z NOTATION LEFT BINDING BRACKET
+298A ; Other_Math # Pe Z NOTATION RIGHT BINDING BRACKET
+298B ; Other_Math # Ps LEFT SQUARE BRACKET WITH UNDERBAR
+298C ; Other_Math # Pe RIGHT SQUARE BRACKET WITH UNDERBAR
+298D ; Other_Math # Ps LEFT SQUARE BRACKET WITH TICK IN TOP CORNER
+298E ; Other_Math # Pe RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
+298F ; Other_Math # Ps LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
+2990 ; Other_Math # Pe RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER
+2991 ; Other_Math # Ps LEFT ANGLE BRACKET WITH DOT
+2992 ; Other_Math # Pe RIGHT ANGLE BRACKET WITH DOT
+2993 ; Other_Math # Ps LEFT ARC LESS-THAN BRACKET
+2994 ; Other_Math # Pe RIGHT ARC GREATER-THAN BRACKET
+2995 ; Other_Math # Ps DOUBLE LEFT ARC GREATER-THAN BRACKET
+2996 ; Other_Math # Pe DOUBLE RIGHT ARC LESS-THAN BRACKET
+2997 ; Other_Math # Ps LEFT BLACK TORTOISE SHELL BRACKET
+2998 ; Other_Math # Pe RIGHT BLACK TORTOISE SHELL BRACKET
+29D8 ; Other_Math # Ps LEFT WIGGLY FENCE
+29D9 ; Other_Math # Pe RIGHT WIGGLY FENCE
+29DA ; Other_Math # Ps LEFT DOUBLE WIGGLY FENCE
+29DB ; Other_Math # Pe RIGHT DOUBLE WIGGLY FENCE
+29FC ; Other_Math # Ps LEFT-POINTING CURVED ANGLE BRACKET
+29FD ; Other_Math # Pe RIGHT-POINTING CURVED ANGLE BRACKET
+FE61 ; Other_Math # Po SMALL ASTERISK
+FE63 ; Other_Math # Pd SMALL HYPHEN-MINUS
+FE68 ; Other_Math # Po SMALL REVERSE SOLIDUS
+FF3C ; Other_Math # Po FULLWIDTH REVERSE SOLIDUS
+FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT
+1D400..1D454 ; Other_Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
+1D456..1D49C ; Other_Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A
+1D49E..1D49F ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D
+1D4A2 ; Other_Math # L& MATHEMATICAL SCRIPT CAPITAL G
+1D4A5..1D4A6 ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K
+1D4A9..1D4AC ; Other_Math # L& [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q
+1D4AE..1D4B9 ; Other_Math # L& [12] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT SMALL D
+1D4BB ; Other_Math # L& MATHEMATICAL SCRIPT SMALL F
+1D4BD..1D4C3 ; Other_Math # L& [7] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL N
+1D4C5..1D505 ; Other_Math # L& [65] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL FRAKTUR CAPITAL B
+1D507..1D50A ; Other_Math # L& [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G
+1D50D..1D514 ; Other_Math # L& [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q
+1D516..1D51C ; Other_Math # L& [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y
+1D51E..1D539 ; Other_Math # L& [28] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B
+1D53B..1D53E ; Other_Math # L& [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G
+1D540..1D544 ; Other_Math # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M
+1D546 ; Other_Math # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O
+1D54A..1D550 ; Other_Math # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y
+1D552..1D6A5 ; Other_Math # L& [340] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL ITALIC SMALL DOTLESS J
+1D6A8..1D6C0 ; Other_Math # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA
+1D6C2..1D6DA ; Other_Math # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA
+1D6DC..1D6FA ; Other_Math # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA
+1D6FC..1D714 ; Other_Math # L& [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA
+1D716..1D734 ; Other_Math # L& [31] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA
+1D736..1D74E ; Other_Math # L& [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA
+1D750..1D76E ; Other_Math # L& [31] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA
+1D770..1D788 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA
+1D78A..1D7A8 ; Other_Math # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA
+1D7AA..1D7C2 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
+1D7C4..1D7CB ; Other_Math # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
+1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
+1EE00..1EE03 ; Other_Math # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
+1EE05..1EE1F ; Other_Math # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
+1EE21..1EE22 ; Other_Math # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
+1EE24 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HEH
+1EE27 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL HAH
+1EE29..1EE32 ; Other_Math # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
+1EE34..1EE37 ; Other_Math # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
+1EE39 ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL DAD
+1EE3B ; Other_Math # Lo ARABIC MATHEMATICAL INITIAL GHAIN
+1EE42 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED JEEM
+1EE47 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED HAH
+1EE49 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED YEH
+1EE4B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED LAM
+1EE4D..1EE4F ; Other_Math # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
+1EE51..1EE52 ; Other_Math # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
+1EE54 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED SHEEN
+1EE57 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED KHAH
+1EE59 ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DAD
+1EE5B ; Other_Math # Lo ARABIC MATHEMATICAL TAILED GHAIN
+1EE5D ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON
+1EE5F ; Other_Math # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF
+1EE61..1EE62 ; Other_Math # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
+1EE64 ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED HEH
+1EE67..1EE6A ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
+1EE6C..1EE72 ; Other_Math # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
+1EE74..1EE77 ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
+1EE79..1EE7C ; Other_Math # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
+1EE7E ; Other_Math # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
+1EE80..1EE89 ; Other_Math # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
+1EE8B..1EE9B ; Other_Math # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
+1EEA1..1EEA3 ; Other_Math # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
+1EEA5..1EEA9 ; Other_Math # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
+1EEAB..1EEBB ; Other_Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
+
+# Total code points: 1362
+
+# ================================================
+
+0030..0039 ; Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE
+0041..0046 ; Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F
+0061..0066 ; Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F
+FF10..FF19 ; Hex_Digit # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
+FF21..FF26 ; Hex_Digit # L& [6] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER F
+FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER F
+
+# Total code points: 44
+
+# ================================================
+
+0030..0039 ; ASCII_Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE
+0041..0046 ; ASCII_Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F
+0061..0066 ; ASCII_Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F
+
+# Total code points: 22
+
+# ================================================
+
+0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI
+05B0..05BD ; Other_Alphabetic # Mn [14] HEBREW POINT SHEVA..HEBREW POINT METEG
+05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE
+05C1..05C2 ; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
+05C4..05C5 ; Other_Alphabetic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
+05C7 ; Other_Alphabetic # Mn HEBREW POINT QAMATS QATAN
+0610..061A ; Other_Alphabetic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA
+064B..0657 ; Other_Alphabetic # Mn [13] ARABIC FATHATAN..ARABIC INVERTED DAMMA
+0659..065F ; Other_Alphabetic # Mn [7] ARABIC ZWARAKAY..ARABIC WAVY HAMZA BELOW
+0670 ; Other_Alphabetic # Mn ARABIC LETTER SUPERSCRIPT ALEF
+06D6..06DC ; Other_Alphabetic # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
+06E1..06E4 ; Other_Alphabetic # Mn [4] ARABIC SMALL HIGH DOTLESS HEAD OF KHAH..ARABIC SMALL HIGH MADDA
+06E7..06E8 ; Other_Alphabetic # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
+06ED ; Other_Alphabetic # Mn ARABIC SMALL LOW MEEM
+0711 ; Other_Alphabetic # Mn SYRIAC LETTER SUPERSCRIPT ALAPH
+0730..073F ; Other_Alphabetic # Mn [16] SYRIAC PTHAHA ABOVE..SYRIAC RWAHA
+07A6..07B0 ; Other_Alphabetic # Mn [11] THAANA ABAFILI..THAANA SUKUN
+0816..0817 ; Other_Alphabetic # Mn [2] SAMARITAN MARK IN..SAMARITAN MARK IN-ALAF
+081B..0823 ; Other_Alphabetic # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
+0825..0827 ; Other_Alphabetic # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
+0829..082C ; Other_Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN
+08D4..08DF ; Other_Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA
+08E3..08E9 ; Other_Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN
+08F0..0902 ; Other_Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA
+0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
+093A ; Other_Alphabetic # Mn DEVANAGARI VOWEL SIGN OE
+093B ; Other_Alphabetic # Mc DEVANAGARI VOWEL SIGN OOE
+093E..0940 ; Other_Alphabetic # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II
+0941..0948 ; Other_Alphabetic # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
+0949..094C ; Other_Alphabetic # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU
+094E..094F ; Other_Alphabetic # Mc [2] DEVANAGARI VOWEL SIGN PRISHTHAMATRA E..DEVANAGARI VOWEL SIGN AW
+0955..0957 ; Other_Alphabetic # Mn [3] DEVANAGARI VOWEL SIGN CANDRA LONG E..DEVANAGARI VOWEL SIGN UUE
+0962..0963 ; Other_Alphabetic # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
+0981 ; Other_Alphabetic # Mn BENGALI SIGN CANDRABINDU
+0982..0983 ; Other_Alphabetic # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
+09BE..09C0 ; Other_Alphabetic # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II
+09C1..09C4 ; Other_Alphabetic # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR
+09C7..09C8 ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
+09CB..09CC ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU
+09D7 ; Other_Alphabetic # Mc BENGALI AU LENGTH MARK
+09E2..09E3 ; Other_Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
+0A01..0A02 ; Other_Alphabetic # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
+0A03 ; Other_Alphabetic # Mc GURMUKHI SIGN VISARGA
+0A3E..0A40 ; Other_Alphabetic # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II
+0A41..0A42 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU
+0A47..0A48 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI
+0A4B..0A4C ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN OO..GURMUKHI VOWEL SIGN AU
+0A51 ; Other_Alphabetic # Mn GURMUKHI SIGN UDAAT
+0A70..0A71 ; Other_Alphabetic # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK
+0A75 ; Other_Alphabetic # Mn GURMUKHI SIGN YAKASH
+0A81..0A82 ; Other_Alphabetic # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA
+0A83 ; Other_Alphabetic # Mc GUJARATI SIGN VISARGA
+0ABE..0AC0 ; Other_Alphabetic # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II
+0AC1..0AC5 ; Other_Alphabetic # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E
+0AC7..0AC8 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
+0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O
+0ACB..0ACC ; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
+0AE2..0AE3 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
+0AFA..0AFC ; Other_Alphabetic # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH
+0B01 ; Other_Alphabetic # Mn ORIYA SIGN CANDRABINDU
+0B02..0B03 ; Other_Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
+0B3E ; Other_Alphabetic # Mc ORIYA VOWEL SIGN AA
+0B3F ; Other_Alphabetic # Mn ORIYA VOWEL SIGN I
+0B40 ; Other_Alphabetic # Mc ORIYA VOWEL SIGN II
+0B41..0B44 ; Other_Alphabetic # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR
+0B47..0B48 ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
+0B4B..0B4C ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
+0B56 ; Other_Alphabetic # Mn ORIYA AI LENGTH MARK
+0B57 ; Other_Alphabetic # Mc ORIYA AU LENGTH MARK
+0B62..0B63 ; Other_Alphabetic # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL
+0B82 ; Other_Alphabetic # Mn TAMIL SIGN ANUSVARA
+0BBE..0BBF ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I
+0BC0 ; Other_Alphabetic # Mn TAMIL VOWEL SIGN II
+0BC1..0BC2 ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU
+0BC6..0BC8 ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI
+0BCA..0BCC ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU
+0BD7 ; Other_Alphabetic # Mc TAMIL AU LENGTH MARK
+0C00 ; Other_Alphabetic # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE
+0C01..0C03 ; Other_Alphabetic # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
+0C3E..0C40 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
+0C41..0C44 ; Other_Alphabetic # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR
+0C46..0C48 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
+0C4A..0C4C ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU
+0C55..0C56 ; Other_Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
+0C62..0C63 ; Other_Alphabetic # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
+0C81 ; Other_Alphabetic # Mn KANNADA SIGN CANDRABINDU
+0C82..0C83 ; Other_Alphabetic # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
+0CBE ; Other_Alphabetic # Mc KANNADA VOWEL SIGN AA
+0CBF ; Other_Alphabetic # Mn KANNADA VOWEL SIGN I
+0CC0..0CC4 ; Other_Alphabetic # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR
+0CC6 ; Other_Alphabetic # Mn KANNADA VOWEL SIGN E
+0CC7..0CC8 ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
+0CCA..0CCB ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
+0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU
+0CD5..0CD6 ; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
+0CE2..0CE3 ; Other_Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
+0D00..0D01 ; Other_Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
+0D02..0D03 ; Other_Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
+0D3E..0D40 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
+0D41..0D44 ; Other_Alphabetic # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
+0D46..0D48 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
+0D4A..0D4C ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
+0D57 ; Other_Alphabetic # Mc MALAYALAM AU LENGTH MARK
+0D62..0D63 ; Other_Alphabetic # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
+0D82..0D83 ; Other_Alphabetic # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
+0DCF..0DD1 ; Other_Alphabetic # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA
+0DD2..0DD4 ; Other_Alphabetic # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA
+0DD6 ; Other_Alphabetic # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA
+0DD8..0DDF ; Other_Alphabetic # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA
+0DF2..0DF3 ; Other_Alphabetic # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA
+0E31 ; Other_Alphabetic # Mn THAI CHARACTER MAI HAN-AKAT
+0E34..0E3A ; Other_Alphabetic # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU
+0E4D ; Other_Alphabetic # Mn THAI CHARACTER NIKHAHIT
+0EB1 ; Other_Alphabetic # Mn LAO VOWEL SIGN MAI KAN
+0EB4..0EB9 ; Other_Alphabetic # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU
+0EBB..0EBC ; Other_Alphabetic # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO
+0ECD ; Other_Alphabetic # Mn LAO NIGGAHITA
+0F71..0F7E ; Other_Alphabetic # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO
+0F7F ; Other_Alphabetic # Mc TIBETAN SIGN RNAM BCAD
+0F80..0F81 ; Other_Alphabetic # Mn [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II
+0F8D..0F97 ; Other_Alphabetic # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA
+0F99..0FBC ; Other_Alphabetic # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA
+102B..102C ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN TALL AA..MYANMAR VOWEL SIGN AA
+102D..1030 ; Other_Alphabetic # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU
+1031 ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN E
+1032..1036 ; Other_Alphabetic # Mn [5] MYANMAR VOWEL SIGN AI..MYANMAR SIGN ANUSVARA
+1038 ; Other_Alphabetic # Mc MYANMAR SIGN VISARGA
+103B..103C ; Other_Alphabetic # Mc [2] MYANMAR CONSONANT SIGN MEDIAL YA..MYANMAR CONSONANT SIGN MEDIAL RA
+103D..103E ; Other_Alphabetic # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA
+1056..1057 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
+1058..1059 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
+105E..1060 ; Other_Alphabetic # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA
+1062 ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN SGAW KAREN EU
+1067..1068 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN WESTERN PWO KAREN EU..MYANMAR VOWEL SIGN WESTERN PWO KAREN UE
+1071..1074 ; Other_Alphabetic # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE
+1082 ; Other_Alphabetic # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA
+1083..1084 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN SHAN AA..MYANMAR VOWEL SIGN SHAN E
+1085..1086 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y
+109C ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN AITON A
+109D ; Other_Alphabetic # Mn MYANMAR VOWEL SIGN AITON AI
+135F ; Other_Alphabetic # Mn ETHIOPIC COMBINING GEMINATION MARK
+1712..1713 ; Other_Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U
+1732..1733 ; Other_Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U
+1752..1753 ; Other_Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
+1772..1773 ; Other_Alphabetic # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
+17B6 ; Other_Alphabetic # Mc KHMER VOWEL SIGN AA
+17B7..17BD ; Other_Alphabetic # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
+17BE..17C5 ; Other_Alphabetic # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
+17C6 ; Other_Alphabetic # Mn KHMER SIGN NIKAHIT
+17C7..17C8 ; Other_Alphabetic # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU
+1885..1886 ; Other_Alphabetic # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
+18A9 ; Other_Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA
+1920..1922 ; Other_Alphabetic # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
+1923..1926 ; Other_Alphabetic # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU
+1927..1928 ; Other_Alphabetic # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
+1929..192B ; Other_Alphabetic # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
+1930..1931 ; Other_Alphabetic # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
+1932 ; Other_Alphabetic # Mn LIMBU SMALL LETTER ANUSVARA
+1933..1938 ; Other_Alphabetic # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
+1A17..1A18 ; Other_Alphabetic # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
+1A19..1A1A ; Other_Alphabetic # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
+1A1B ; Other_Alphabetic # Mn BUGINESE VOWEL SIGN AE
+1A55 ; Other_Alphabetic # Mc TAI THAM CONSONANT SIGN MEDIAL RA
+1A56 ; Other_Alphabetic # Mn TAI THAM CONSONANT SIGN MEDIAL LA
+1A57 ; Other_Alphabetic # Mc TAI THAM CONSONANT SIGN LA TANG LAI
+1A58..1A5E ; Other_Alphabetic # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA
+1A61 ; Other_Alphabetic # Mc TAI THAM VOWEL SIGN A
+1A62 ; Other_Alphabetic # Mn TAI THAM VOWEL SIGN MAI SAT
+1A63..1A64 ; Other_Alphabetic # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA
+1A65..1A6C ; Other_Alphabetic # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW
+1A6D..1A72 ; Other_Alphabetic # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI
+1A73..1A74 ; Other_Alphabetic # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG
+1B00..1B03 ; Other_Alphabetic # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
+1B04 ; Other_Alphabetic # Mc BALINESE SIGN BISAH
+1B35 ; Other_Alphabetic # Mc BALINESE VOWEL SIGN TEDUNG
+1B36..1B3A ; Other_Alphabetic # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA
+1B3B ; Other_Alphabetic # Mc BALINESE VOWEL SIGN RA REPA TEDUNG
+1B3C ; Other_Alphabetic # Mn BALINESE VOWEL SIGN LA LENGA
+1B3D..1B41 ; Other_Alphabetic # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG
+1B42 ; Other_Alphabetic # Mn BALINESE VOWEL SIGN PEPET
+1B43 ; Other_Alphabetic # Mc BALINESE VOWEL SIGN PEPET TEDUNG
+1B80..1B81 ; Other_Alphabetic # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR
+1B82 ; Other_Alphabetic # Mc SUNDANESE SIGN PANGWISAD
+1BA1 ; Other_Alphabetic # Mc SUNDANESE CONSONANT SIGN PAMINGKAL
+1BA2..1BA5 ; Other_Alphabetic # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU
+1BA6..1BA7 ; Other_Alphabetic # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG
+1BA8..1BA9 ; Other_Alphabetic # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
+1BAC..1BAD ; Other_Alphabetic # Mn [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA
+1BE7 ; Other_Alphabetic # Mc BATAK VOWEL SIGN E
+1BE8..1BE9 ; Other_Alphabetic # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE
+1BEA..1BEC ; Other_Alphabetic # Mc [3] BATAK VOWEL SIGN I..BATAK VOWEL SIGN O
+1BED ; Other_Alphabetic # Mn BATAK VOWEL SIGN KARO O
+1BEE ; Other_Alphabetic # Mc BATAK VOWEL SIGN U
+1BEF..1BF1 ; Other_Alphabetic # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H
+1C24..1C2B ; Other_Alphabetic # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU
+1C2C..1C33 ; Other_Alphabetic # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T
+1C34..1C35 ; Other_Alphabetic # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG
+1CF2..1CF3 ; Other_Alphabetic # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
+1DE7..1DF4 ; Other_Alphabetic # Mn [14] COMBINING LATIN SMALL LETTER ALPHA..COMBINING LATIN SMALL LETTER U WITH DIAERESIS
+24B6..24E9 ; Other_Alphabetic # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z
+2DE0..2DFF ; Other_Alphabetic # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
+A674..A67B ; Other_Alphabetic # Mn [8] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC LETTER OMEGA
+A69E..A69F ; Other_Alphabetic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
+A823..A824 ; Other_Alphabetic # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I
+A825..A826 ; Other_Alphabetic # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
+A827 ; Other_Alphabetic # Mc SYLOTI NAGRI VOWEL SIGN OO
+A880..A881 ; Other_Alphabetic # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
+A8B4..A8C3 ; Other_Alphabetic # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
+A8C5 ; Other_Alphabetic # Mn SAURASHTRA SIGN CANDRABINDU
+A926..A92A ; Other_Alphabetic # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O
+A947..A951 ; Other_Alphabetic # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
+A952 ; Other_Alphabetic # Mc REJANG CONSONANT SIGN H
+A980..A982 ; Other_Alphabetic # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR
+A983 ; Other_Alphabetic # Mc JAVANESE SIGN WIGNYAN
+A9B4..A9B5 ; Other_Alphabetic # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG
+A9B6..A9B9 ; Other_Alphabetic # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
+A9BA..A9BB ; Other_Alphabetic # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE
+A9BC ; Other_Alphabetic # Mn JAVANESE VOWEL SIGN PEPET
+A9BD..A9BF ; Other_Alphabetic # Mc [3] JAVANESE CONSONANT SIGN KERET..JAVANESE CONSONANT SIGN CAKRA
+AA29..AA2E ; Other_Alphabetic # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
+AA2F..AA30 ; Other_Alphabetic # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI
+AA31..AA32 ; Other_Alphabetic # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
+AA33..AA34 ; Other_Alphabetic # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA
+AA35..AA36 ; Other_Alphabetic # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA
+AA43 ; Other_Alphabetic # Mn CHAM CONSONANT SIGN FINAL NG
+AA4C ; Other_Alphabetic # Mn CHAM CONSONANT SIGN FINAL M
+AA4D ; Other_Alphabetic # Mc CHAM CONSONANT SIGN FINAL H
+AAB0 ; Other_Alphabetic # Mn TAI VIET MAI KANG
+AAB2..AAB4 ; Other_Alphabetic # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U
+AAB7..AAB8 ; Other_Alphabetic # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA
+AABE ; Other_Alphabetic # Mn TAI VIET VOWEL AM
+AAEB ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN II
+AAEC..AAED ; Other_Alphabetic # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI
+AAEE..AAEF ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU
+AAF5 ; Other_Alphabetic # Mc MEETEI MAYEK VOWEL SIGN VISARGA
+ABE3..ABE4 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP
+ABE5 ; Other_Alphabetic # Mn MEETEI MAYEK VOWEL SIGN ANAP
+ABE6..ABE7 ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP
+ABE8 ; Other_Alphabetic # Mn MEETEI MAYEK VOWEL SIGN UNAP
+ABE9..ABEA ; Other_Alphabetic # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEETEI MAYEK VOWEL SIGN NUNG
+FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
+10376..1037A ; Other_Alphabetic # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII
+10A01..10A03 ; Other_Alphabetic # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
+10A05..10A06 ; Other_Alphabetic # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
+10A0C..10A0F ; Other_Alphabetic # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
+11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU
+11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA
+11002 ; Other_Alphabetic # Mc BRAHMI SIGN VISARGA
+11038..11045 ; Other_Alphabetic # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU
+11082 ; Other_Alphabetic # Mc KAITHI SIGN VISARGA
+110B0..110B2 ; Other_Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
+110B3..110B6 ; Other_Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
+110B7..110B8 ; Other_Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
+11100..11102 ; Other_Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA
+11127..1112B ; Other_Alphabetic # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
+1112C ; Other_Alphabetic # Mc CHAKMA VOWEL SIGN E
+1112D..11132 ; Other_Alphabetic # Mn [6] CHAKMA VOWEL SIGN AI..CHAKMA AU MARK
+11180..11181 ; Other_Alphabetic # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
+11182 ; Other_Alphabetic # Mc SHARADA SIGN VISARGA
+111B3..111B5 ; Other_Alphabetic # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II
+111B6..111BE ; Other_Alphabetic # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
+111BF ; Other_Alphabetic # Mc SHARADA VOWEL SIGN AU
+1122C..1122E ; Other_Alphabetic # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II
+1122F..11231 ; Other_Alphabetic # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
+11232..11233 ; Other_Alphabetic # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
+11234 ; Other_Alphabetic # Mn KHOJKI SIGN ANUSVARA
+11237 ; Other_Alphabetic # Mn KHOJKI SIGN SHADDA
+1123E ; Other_Alphabetic # Mn KHOJKI SIGN SUKUN
+112DF ; Other_Alphabetic # Mn KHUDAWADI SIGN ANUSVARA
+112E0..112E2 ; Other_Alphabetic # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
+112E3..112E8 ; Other_Alphabetic # Mn [6] KHUDAWADI VOWEL SIGN U..KHUDAWADI VOWEL SIGN AU
+11300..11301 ; Other_Alphabetic # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
+11302..11303 ; Other_Alphabetic # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
+1133E..1133F ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I
+11340 ; Other_Alphabetic # Mn GRANTHA VOWEL SIGN II
+11341..11344 ; Other_Alphabetic # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
+11347..11348 ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
+1134B..1134C ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN OO..GRANTHA VOWEL SIGN AU
+11357 ; Other_Alphabetic # Mc GRANTHA AU LENGTH MARK
+11362..11363 ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
+11435..11437 ; Other_Alphabetic # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
+11438..1143F ; Other_Alphabetic # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
+11440..11441 ; Other_Alphabetic # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
+11443..11444 ; Other_Alphabetic # Mn [2] NEWA SIGN CANDRABINDU..NEWA SIGN ANUSVARA
+11445 ; Other_Alphabetic # Mc NEWA SIGN VISARGA
+114B0..114B2 ; Other_Alphabetic # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II
+114B3..114B8 ; Other_Alphabetic # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL
+114B9 ; Other_Alphabetic # Mc TIRHUTA VOWEL SIGN E
+114BA ; Other_Alphabetic # Mn TIRHUTA VOWEL SIGN SHORT E
+114BB..114BE ; Other_Alphabetic # Mc [4] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN AU
+114BF..114C0 ; Other_Alphabetic # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA
+114C1 ; Other_Alphabetic # Mc TIRHUTA SIGN VISARGA
+115AF..115B1 ; Other_Alphabetic # Mc [3] SIDDHAM VOWEL SIGN AA..SIDDHAM VOWEL SIGN II
+115B2..115B5 ; Other_Alphabetic # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR
+115B8..115BB ; Other_Alphabetic # Mc [4] SIDDHAM VOWEL SIGN E..SIDDHAM VOWEL SIGN AU
+115BC..115BD ; Other_Alphabetic # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
+115BE ; Other_Alphabetic # Mc SIDDHAM SIGN VISARGA
+115DC..115DD ; Other_Alphabetic # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
+11630..11632 ; Other_Alphabetic # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II
+11633..1163A ; Other_Alphabetic # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
+1163B..1163C ; Other_Alphabetic # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU
+1163D ; Other_Alphabetic # Mn MODI SIGN ANUSVARA
+1163E ; Other_Alphabetic # Mc MODI SIGN VISARGA
+11640 ; Other_Alphabetic # Mn MODI SIGN ARDHACANDRA
+116AB ; Other_Alphabetic # Mn TAKRI SIGN ANUSVARA
+116AC ; Other_Alphabetic # Mc TAKRI SIGN VISARGA
+116AD ; Other_Alphabetic # Mn TAKRI VOWEL SIGN AA
+116AE..116AF ; Other_Alphabetic # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
+116B0..116B5 ; Other_Alphabetic # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
+1171D..1171F ; Other_Alphabetic # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
+11720..11721 ; Other_Alphabetic # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
+11722..11725 ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
+11726 ; Other_Alphabetic # Mc AHOM VOWEL SIGN E
+11727..1172A ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM
+11A01..11A06 ; Other_Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
+11A07..11A08 ; Other_Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
+11A09..11A0A ; Other_Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
+11A35..11A38 ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA
+11A39 ; Other_Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA
+11A3B..11A3E ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
+11A51..11A56 ; Other_Alphabetic # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
+11A57..11A58 ; Other_Alphabetic # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
+11A59..11A5B ; Other_Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
+11A8A..11A96 ; Other_Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
+11A97 ; Other_Alphabetic # Mc SOYOMBO SIGN VISARGA
+11C2F ; Other_Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA
+11C30..11C36 ; Other_Alphabetic # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
+11C38..11C3D ; Other_Alphabetic # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
+11C3E ; Other_Alphabetic # Mc BHAIKSUKI SIGN VISARGA
+11C92..11CA7 ; Other_Alphabetic # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
+11CA9 ; Other_Alphabetic # Mc MARCHEN SUBJOINED LETTER YA
+11CAA..11CB0 ; Other_Alphabetic # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
+11CB1 ; Other_Alphabetic # Mc MARCHEN VOWEL SIGN I
+11CB2..11CB3 ; Other_Alphabetic # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
+11CB4 ; Other_Alphabetic # Mc MARCHEN VOWEL SIGN O
+11CB5..11CB6 ; Other_Alphabetic # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
+11D31..11D36 ; Other_Alphabetic # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
+11D3A ; Other_Alphabetic # Mn MASARAM GONDI VOWEL SIGN E
+11D3C..11D3D ; Other_Alphabetic # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
+11D3F..11D41 ; Other_Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA
+11D43 ; Other_Alphabetic # Mn MASARAM GONDI SIGN CANDRA
+11D47 ; Other_Alphabetic # Mn MASARAM GONDI RA-KARA
+16B30..16B36 ; Other_Alphabetic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
+16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
+1BC9E ; Other_Alphabetic # Mn DUPLOYAN DOUBLE MARK
+1E000..1E006 ; Other_Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
+1E008..1E018 ; Other_Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
+1E01B..1E021 ; Other_Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
+1E023..1E024 ; Other_Alphabetic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
+1E026..1E02A ; Other_Alphabetic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E947 ; Other_Alphabetic # Mn ADLAM HAMZA
+1F130..1F149 ; Other_Alphabetic # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z
+1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
+1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
+
+# Total code points: 1300
+
+# ================================================
+
+3006 ; Ideographic # Lo IDEOGRAPHIC CLOSING MARK
+3007 ; Ideographic # Nl IDEOGRAPHIC NUMBER ZERO
+3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
+3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
+3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
+4E00..9FEA ; Ideographic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
+F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
+FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
+17000..187EC ; Ideographic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
+18800..18AF2 ; Ideographic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
+1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
+20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
+2A700..2B734 ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
+2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
+2B820..2CEA1 ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
+2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
+2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
+
+# Total code points: 96174
+
+# ================================================
+
+005E ; Diacritic # Sk CIRCUMFLEX ACCENT
+0060 ; Diacritic # Sk GRAVE ACCENT
+00A8 ; Diacritic # Sk DIAERESIS
+00AF ; Diacritic # Sk MACRON
+00B4 ; Diacritic # Sk ACUTE ACCENT
+00B7 ; Diacritic # Po MIDDLE DOT
+00B8 ; Diacritic # Sk CEDILLA
+02B0..02C1 ; Diacritic # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP
+02C2..02C5 ; Diacritic # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD
+02C6..02D1 ; Diacritic # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON
+02D2..02DF ; Diacritic # Sk [14] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER CROSS ACCENT
+02E0..02E4 ; Diacritic # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
+02E5..02EB ; Diacritic # Sk [7] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER YANG DEPARTING TONE MARK
+02EC ; Diacritic # Lm MODIFIER LETTER VOICING
+02ED ; Diacritic # Sk MODIFIER LETTER UNASPIRATED
+02EE ; Diacritic # Lm MODIFIER LETTER DOUBLE APOSTROPHE
+02EF..02FF ; Diacritic # Sk [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW
+0300..034E ; Diacritic # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW
+0350..0357 ; Diacritic # Mn [8] COMBINING RIGHT ARROWHEAD ABOVE..COMBINING RIGHT HALF RING ABOVE
+035D..0362 ; Diacritic # Mn [6] COMBINING DOUBLE BREVE..COMBINING DOUBLE RIGHTWARDS ARROW BELOW
+0374 ; Diacritic # Lm GREEK NUMERAL SIGN
+0375 ; Diacritic # Sk GREEK LOWER NUMERAL SIGN
+037A ; Diacritic # Lm GREEK YPOGEGRAMMENI
+0384..0385 ; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS
+0483..0487 ; Diacritic # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE
+0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
+0591..05A1 ; Diacritic # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
+05A3..05BD ; Diacritic # Mn [27] HEBREW ACCENT MUNAH..HEBREW POINT METEG
+05BF ; Diacritic # Mn HEBREW POINT RAFE
+05C1..05C2 ; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
+05C4 ; Diacritic # Mn HEBREW MARK UPPER DOT
+064B..0652 ; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN
+0657..0658 ; Diacritic # Mn [2] ARABIC INVERTED DAMMA..ARABIC MARK NOON GHUNNA
+06DF..06E0 ; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO
+06E5..06E6 ; Diacritic # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH
+06EA..06EC ; Diacritic # Mn [3] ARABIC EMPTY CENTRE LOW STOP..ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE
+0730..074A ; Diacritic # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
+07A6..07B0 ; Diacritic # Mn [11] THAANA ABAFILI..THAANA SUKUN
+07EB..07F3 ; Diacritic # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
+07F4..07F5 ; Diacritic # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE
+0818..0819 ; Diacritic # Mn [2] SAMARITAN MARK OCCLUSION..SAMARITAN MARK DAGESH
+08E3..08FE ; Diacritic # Mn [28] ARABIC TURNED DAMMA BELOW..ARABIC DAMMA WITH DOT
+093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
+094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
+0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
+0971 ; Diacritic # Lm DEVANAGARI SIGN HIGH SPACING DOT
+09BC ; Diacritic # Mn BENGALI SIGN NUKTA
+09CD ; Diacritic # Mn BENGALI SIGN VIRAMA
+0A3C ; Diacritic # Mn GURMUKHI SIGN NUKTA
+0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA
+0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA
+0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA
+0AFD..0AFF ; Diacritic # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
+0B3C ; Diacritic # Mn ORIYA SIGN NUKTA
+0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA
+0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA
+0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA
+0CBC ; Diacritic # Mn KANNADA SIGN NUKTA
+0CCD ; Diacritic # Mn KANNADA SIGN VIRAMA
+0D3B..0D3C ; Diacritic # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
+0D4D ; Diacritic # Mn MALAYALAM SIGN VIRAMA
+0DCA ; Diacritic # Mn SINHALA SIGN AL-LAKUNA
+0E47..0E4C ; Diacritic # Mn [6] THAI CHARACTER MAITAIKHU..THAI CHARACTER THANTHAKHAT
+0E4E ; Diacritic # Mn THAI CHARACTER YAMAKKAN
+0EC8..0ECC ; Diacritic # Mn [5] LAO TONE MAI EK..LAO CANCELLATION MARK
+0F18..0F19 ; Diacritic # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
+0F35 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
+0F37 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
+0F39 ; Diacritic # Mn TIBETAN MARK TSA -PHRU
+0F3E..0F3F ; Diacritic # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES
+0F82..0F84 ; Diacritic # Mn [3] TIBETAN SIGN NYI ZLA NAA DA..TIBETAN MARK HALANTA
+0F86..0F87 ; Diacritic # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS
+0FC6 ; Diacritic # Mn TIBETAN SYMBOL PADMA GDAN
+1037 ; Diacritic # Mn MYANMAR SIGN DOT BELOW
+1039..103A ; Diacritic # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT
+1087..108C ; Diacritic # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3
+108D ; Diacritic # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE
+108F ; Diacritic # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5
+109A..109B ; Diacritic # Mc [2] MYANMAR SIGN KHAMTI TONE-1..MYANMAR SIGN KHAMTI TONE-3
+17C9..17D3 ; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
+17DD ; Diacritic # Mn KHMER SIGN ATTHACAN
+1939..193B ; Diacritic # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
+1A75..1A7C ; Diacritic # Mn [8] TAI THAM SIGN TONE-1..TAI THAM SIGN KHUEN-LUE KARAN
+1A7F ; Diacritic # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT
+1AB0..1ABD ; Diacritic # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW
+1B34 ; Diacritic # Mn BALINESE SIGN REREKAN
+1B44 ; Diacritic # Mc BALINESE ADEG ADEG
+1B6B..1B73 ; Diacritic # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
+1BAA ; Diacritic # Mc SUNDANESE SIGN PAMAAEH
+1BAB ; Diacritic # Mn SUNDANESE SIGN VIRAMA
+1C36..1C37 ; Diacritic # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA
+1C78..1C7D ; Diacritic # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD
+1CD0..1CD2 ; Diacritic # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
+1CD3 ; Diacritic # Po VEDIC SIGN NIHSHVASA
+1CD4..1CE0 ; Diacritic # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
+1CE1 ; Diacritic # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
+1CE2..1CE8 ; Diacritic # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
+1CED ; Diacritic # Mn VEDIC SIGN TIRYAK
+1CF4 ; Diacritic # Mn VEDIC TONE CANDRA ABOVE
+1CF7 ; Diacritic # Mc VEDIC SIGN ATIKRAMA
+1CF8..1CF9 ; Diacritic # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
+1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
+1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW
+1DF5..1DF9 ; Diacritic # Mn [5] COMBINING UP TACK ABOVE..COMBINING WIDE INVERTED BRIDGE BELOW
+1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+1FBD ; Diacritic # Sk GREEK KORONIS
+1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI
+1FCD..1FCF ; Diacritic # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI
+1FDD..1FDF ; Diacritic # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI
+1FED..1FEF ; Diacritic # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA
+1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA
+2CEF..2CF1 ; Diacritic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
+2E2F ; Diacritic # Lm VERTICAL TILDE
+302A..302D ; Diacritic # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK
+302E..302F ; Diacritic # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
+3099..309A ; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
+309B..309C ; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
+30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
+A66F ; Diacritic # Mn COMBINING CYRILLIC VZMET
+A67C..A67D ; Diacritic # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK
+A67F ; Diacritic # Lm CYRILLIC PAYEROK
+A69C..A69D ; Diacritic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
+A6F0..A6F1 ; Diacritic # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
+A717..A71F ; Diacritic # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
+A720..A721 ; Diacritic # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE
+A788 ; Diacritic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
+A7F8..A7F9 ; Diacritic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
+A8C4 ; Diacritic # Mn SAURASHTRA SIGN VIRAMA
+A8E0..A8F1 ; Diacritic # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
+A92B..A92D ; Diacritic # Mn [3] KAYAH LI TONE PLOPHU..KAYAH LI TONE CALYA PLOPHU
+A92E ; Diacritic # Po KAYAH LI SIGN CWI
+A953 ; Diacritic # Mc REJANG VIRAMA
+A9B3 ; Diacritic # Mn JAVANESE SIGN CECAK TELU
+A9C0 ; Diacritic # Mc JAVANESE PANGKON
+A9E5 ; Diacritic # Mn MYANMAR SIGN SHAN SAW
+AA7B ; Diacritic # Mc MYANMAR SIGN PAO KAREN TONE
+AA7C ; Diacritic # Mn MYANMAR SIGN TAI LAING TONE-2
+AA7D ; Diacritic # Mc MYANMAR SIGN TAI LAING TONE-5
+AABF ; Diacritic # Mn TAI VIET TONE MAI EK
+AAC0 ; Diacritic # Lo TAI VIET TONE MAI NUENG
+AAC1 ; Diacritic # Mn TAI VIET TONE MAI THO
+AAC2 ; Diacritic # Lo TAI VIET TONE MAI SONG
+AAF6 ; Diacritic # Mn MEETEI MAYEK VIRAMA
+AB5B ; Diacritic # Sk MODIFIER BREVE WITH INVERTED BREVE
+AB5C..AB5F ; Diacritic # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
+ABEC ; Diacritic # Mc MEETEI MAYEK LUM IYEK
+ABED ; Diacritic # Mn MEETEI MAYEK APUN IYEK
+FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
+FE20..FE2F ; Diacritic # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
+FF3E ; Diacritic # Sk FULLWIDTH CIRCUMFLEX ACCENT
+FF40 ; Diacritic # Sk FULLWIDTH GRAVE ACCENT
+FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
+FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
+FFE3 ; Diacritic # Sk FULLWIDTH MACRON
+102E0 ; Diacritic # Mn COPTIC EPACT THOUSANDS MARK
+10AE5..10AE6 ; Diacritic # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
+110B9..110BA ; Diacritic # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
+11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA
+11173 ; Diacritic # Mn MAHAJANI SIGN NUKTA
+111C0 ; Diacritic # Mc SHARADA SIGN VIRAMA
+111CA..111CC ; Diacritic # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
+11235 ; Diacritic # Mc KHOJKI SIGN VIRAMA
+11236 ; Diacritic # Mn KHOJKI SIGN NUKTA
+112E9..112EA ; Diacritic # Mn [2] KHUDAWADI SIGN NUKTA..KHUDAWADI SIGN VIRAMA
+1133C ; Diacritic # Mn GRANTHA SIGN NUKTA
+1134D ; Diacritic # Mc GRANTHA SIGN VIRAMA
+11366..1136C ; Diacritic # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
+11370..11374 ; Diacritic # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
+11442 ; Diacritic # Mn NEWA SIGN VIRAMA
+11446 ; Diacritic # Mn NEWA SIGN NUKTA
+114C2..114C3 ; Diacritic # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA
+115BF..115C0 ; Diacritic # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
+1163F ; Diacritic # Mn MODI SIGN VIRAMA
+116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA
+116B7 ; Diacritic # Mn TAKRI SIGN NUKTA
+1172B ; Diacritic # Mn AHOM SIGN KILLER
+11A34 ; Diacritic # Mn ZANABAZAR SQUARE SIGN VIRAMA
+11A47 ; Diacritic # Mn ZANABAZAR SQUARE SUBJOINER
+11A99 ; Diacritic # Mn SOYOMBO SUBJOINER
+11C3F ; Diacritic # Mn BHAIKSUKI SIGN VIRAMA
+11D42 ; Diacritic # Mn MASARAM GONDI SIGN NUKTA
+11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
+16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
+16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
+16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
+1D167..1D169 ; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
+1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
+1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
+1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
+1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
+1E8D0..1E8D6 ; Diacritic # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
+1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
+1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA
+
+# Total code points: 798
+
+# ================================================
+
+00B7 ; Extender # Po MIDDLE DOT
+02D0..02D1 ; Extender # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON
+0640 ; Extender # Lm ARABIC TATWEEL
+07FA ; Extender # Lm NKO LAJANYALAN
+0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK
+0EC6 ; Extender # Lm LAO KO LA
+180A ; Extender # Po MONGOLIAN NIRUGU
+1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
+1AA7 ; Extender # Lm TAI THAM SIGN MAI YAMOK
+1C36 ; Extender # Mn LEPCHA SIGN RAN
+1C7B ; Extender # Lm OL CHIKI RELAA
+3005 ; Extender # Lm IDEOGRAPHIC ITERATION MARK
+3031..3035 ; Extender # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
+309D..309E ; Extender # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
+30FC..30FE ; Extender # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
+A015 ; Extender # Lm YI SYLLABLE WU
+A60C ; Extender # Lm VAI SYLLABLE LENGTHENER
+A9CF ; Extender # Lm JAVANESE PANGRANGKEP
+A9E6 ; Extender # Lm MYANMAR MODIFIER LETTER SHAN REDUPLICATION
+AA70 ; Extender # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION
+AADD ; Extender # Lm TAI VIET SYMBOL SAM
+AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK
+FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
+1135D ; Extender # Lo GRANTHA SIGN PLUTA
+115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3
+11A98 ; Extender # Mn SOYOMBO GEMINATION MARK
+16B42..16B43 ; Extender # Lm [2] PAHAWH HMONG SIGN VOS NRUA..PAHAWH HMONG SIGN IB YAM
+16FE0..16FE1 ; Extender # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
+1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
+
+# Total code points: 44
+
+# ================================================
+
+00AA ; Other_Lowercase # Lo FEMININE ORDINAL INDICATOR
+00BA ; Other_Lowercase # Lo MASCULINE ORDINAL INDICATOR
+02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
+02C0..02C1 ; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP
+02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
+0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI
+037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI
+1D2C..1D6A ; Other_Lowercase # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
+1D78 ; Other_Lowercase # Lm MODIFIER LETTER CYRILLIC EN
+1D9B..1DBF ; Other_Lowercase # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
+2071 ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER I
+207F ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER N
+2090..209C ; Other_Lowercase # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
+2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND
+24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
+2C7C..2C7D ; Other_Lowercase # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
+A69C..A69D ; Other_Lowercase # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
+A770 ; Other_Lowercase # Lm MODIFIER LETTER US
+A7F8..A7F9 ; Other_Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
+AB5C..AB5F ; Other_Lowercase # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
+
+# Total code points: 189
+
+# ================================================
+
+2160..216F ; Other_Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND
+24B6..24CF ; Other_Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z
+1F130..1F149 ; Other_Uppercase # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z
+1F150..1F169 ; Other_Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
+1F170..1F189 ; Other_Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
+
+# Total code points: 120
+
+# ================================================
+
+FDD0..FDEF ; Noncharacter_Code_Point # Cn [32] <noncharacter-FDD0>..<noncharacter-FDEF>
+FFFE..FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFE>..<noncharacter-FFFF>
+1FFFE..1FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-1FFFE>..<noncharacter-1FFFF>
+2FFFE..2FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-2FFFE>..<noncharacter-2FFFF>
+3FFFE..3FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-3FFFE>..<noncharacter-3FFFF>
+4FFFE..4FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-4FFFE>..<noncharacter-4FFFF>
+5FFFE..5FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-5FFFE>..<noncharacter-5FFFF>
+6FFFE..6FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-6FFFE>..<noncharacter-6FFFF>
+7FFFE..7FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-7FFFE>..<noncharacter-7FFFF>
+8FFFE..8FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-8FFFE>..<noncharacter-8FFFF>
+9FFFE..9FFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-9FFFE>..<noncharacter-9FFFF>
+AFFFE..AFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-AFFFE>..<noncharacter-AFFFF>
+BFFFE..BFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-BFFFE>..<noncharacter-BFFFF>
+CFFFE..CFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-CFFFE>..<noncharacter-CFFFF>
+DFFFE..DFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-DFFFE>..<noncharacter-DFFFF>
+EFFFE..EFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-EFFFE>..<noncharacter-EFFFF>
+FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
+10FFFE..10FFFF; Noncharacter_Code_Point # Cn [2] <noncharacter-10FFFE>..<noncharacter-10FFFF>
+
+# Total code points: 66
+
+# ================================================
+
+09BE ; Other_Grapheme_Extend # Mc BENGALI VOWEL SIGN AA
+09D7 ; Other_Grapheme_Extend # Mc BENGALI AU LENGTH MARK
+0B3E ; Other_Grapheme_Extend # Mc ORIYA VOWEL SIGN AA
+0B57 ; Other_Grapheme_Extend # Mc ORIYA AU LENGTH MARK
+0BBE ; Other_Grapheme_Extend # Mc TAMIL VOWEL SIGN AA
+0BD7 ; Other_Grapheme_Extend # Mc TAMIL AU LENGTH MARK
+0CC2 ; Other_Grapheme_Extend # Mc KANNADA VOWEL SIGN UU
+0CD5..0CD6 ; Other_Grapheme_Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
+0D3E ; Other_Grapheme_Extend # Mc MALAYALAM VOWEL SIGN AA
+0D57 ; Other_Grapheme_Extend # Mc MALAYALAM AU LENGTH MARK
+0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA
+0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
+200C ; Other_Grapheme_Extend # Cf ZERO WIDTH NON-JOINER
+302E..302F ; Other_Grapheme_Extend # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK
+FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
+1133E ; Other_Grapheme_Extend # Mc GRANTHA VOWEL SIGN AA
+11357 ; Other_Grapheme_Extend # Mc GRANTHA AU LENGTH MARK
+114B0 ; Other_Grapheme_Extend # Mc TIRHUTA VOWEL SIGN AA
+114BD ; Other_Grapheme_Extend # Mc TIRHUTA VOWEL SIGN SHORT O
+115AF ; Other_Grapheme_Extend # Mc SIDDHAM VOWEL SIGN AA
+1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM
+1D16E..1D172 ; Other_Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5
+E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
+
+# Total code points: 125
+
+# ================================================
+
+2FF0..2FF1 ; IDS_Binary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW
+2FF4..2FFB ; IDS_Binary_Operator # So [8] IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
+
+# Total code points: 10
+
+# ================================================
+
+2FF2..2FF3 ; IDS_Trinary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO MIDDLE AND RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO MIDDLE AND BELOW
+
+# Total code points: 2
+
+# ================================================
+
+2E80..2E99 ; Radical # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
+2E9B..2EF3 ; Radical # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
+2F00..2FD5 ; Radical # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
+
+# Total code points: 329
+
+# ================================================
+
+3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
+4E00..9FEA ; Unified_Ideograph # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
+FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
+FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
+FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
+FA1F ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA1F
+FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21
+FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24
+FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
+20000..2A6D6 ; Unified_Ideograph # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
+2A700..2B734 ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
+2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
+2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
+2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
+
+# Total code points: 87882
+
+# ================================================
+
+034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
+115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
+17B4..17B5 ; Other_Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
+2065 ; Other_Default_Ignorable_Code_Point # Cn <reserved-2065>
+3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER
+FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER
+FFF0..FFF8 ; Other_Default_Ignorable_Code_Point # Cn [9] <reserved-FFF0>..<reserved-FFF8>
+E0000 ; Other_Default_Ignorable_Code_Point # Cn <reserved-E0000>
+E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30] <reserved-E0002>..<reserved-E001F>
+E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reserved-E00FF>
+E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
+
+# Total code points: 3776
+
+# ================================================
+
+0149 ; Deprecated # L& LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
+0673 ; Deprecated # Lo ARABIC LETTER ALEF WITH WAVY HAMZA BELOW
+0F77 ; Deprecated # Mn TIBETAN VOWEL SIGN VOCALIC RR
+0F79 ; Deprecated # Mn TIBETAN VOWEL SIGN VOCALIC LL
+17A3..17A4 ; Deprecated # Lo [2] KHMER INDEPENDENT VOWEL QAQ..KHMER INDEPENDENT VOWEL QAA
+206A..206F ; Deprecated # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
+2329 ; Deprecated # Ps LEFT-POINTING ANGLE BRACKET
+232A ; Deprecated # Pe RIGHT-POINTING ANGLE BRACKET
+E0001 ; Deprecated # Cf LANGUAGE TAG
+
+# Total code points: 15
+
+# ================================================
+
+0069..006A ; Soft_Dotted # L& [2] LATIN SMALL LETTER I..LATIN SMALL LETTER J
+012F ; Soft_Dotted # L& LATIN SMALL LETTER I WITH OGONEK
+0249 ; Soft_Dotted # L& LATIN SMALL LETTER J WITH STROKE
+0268 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE
+029D ; Soft_Dotted # L& LATIN SMALL LETTER J WITH CROSSED-TAIL
+02B2 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J
+03F3 ; Soft_Dotted # L& GREEK LETTER YOT
+0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE
+1D62 ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER I
+1D96 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH RETROFLEX HOOK
+1DA4 ; Soft_Dotted # Lm MODIFIER LETTER SMALL I WITH STROKE
+1DA8 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH CROSSED-TAIL
+1E2D ; Soft_Dotted # L& LATIN SMALL LETTER I WITH TILDE BELOW
+1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
+2071 ; Soft_Dotted # Lm SUPERSCRIPT LATIN SMALL LETTER I
+2148..2149 ; Soft_Dotted # L& [2] DOUBLE-STRUCK ITALIC SMALL I..DOUBLE-STRUCK ITALIC SMALL J
+2C7C ; Soft_Dotted # Lm LATIN SUBSCRIPT SMALL LETTER J
+1D422..1D423 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SMALL I..MATHEMATICAL BOLD SMALL J
+1D456..1D457 ; Soft_Dotted # L& [2] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL J
+1D48A..1D48B ; Soft_Dotted # L& [2] MATHEMATICAL BOLD ITALIC SMALL I..MATHEMATICAL BOLD ITALIC SMALL J
+1D4BE..1D4BF ; Soft_Dotted # L& [2] MATHEMATICAL SCRIPT SMALL I..MATHEMATICAL SCRIPT SMALL J
+1D4F2..1D4F3 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SCRIPT SMALL I..MATHEMATICAL BOLD SCRIPT SMALL J
+1D526..1D527 ; Soft_Dotted # L& [2] MATHEMATICAL FRAKTUR SMALL I..MATHEMATICAL FRAKTUR SMALL J
+1D55A..1D55B ; Soft_Dotted # L& [2] MATHEMATICAL DOUBLE-STRUCK SMALL I..MATHEMATICAL DOUBLE-STRUCK SMALL J
+1D58E..1D58F ; Soft_Dotted # L& [2] MATHEMATICAL BOLD FRAKTUR SMALL I..MATHEMATICAL BOLD FRAKTUR SMALL J
+1D5C2..1D5C3 ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF SMALL I..MATHEMATICAL SANS-SERIF SMALL J
+1D5F6..1D5F7 ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD SMALL I..MATHEMATICAL SANS-SERIF BOLD SMALL J
+1D62A..1D62B ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF ITALIC SMALL I..MATHEMATICAL SANS-SERIF ITALIC SMALL J
+1D65E..1D65F ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J
+1D692..1D693 ; Soft_Dotted # L& [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J
+
+# Total code points: 46
+
+# ================================================
+
+0E40..0E44 ; Logical_Order_Exception # Lo [5] THAI CHARACTER SARA E..THAI CHARACTER SARA AI MAIMALAI
+0EC0..0EC4 ; Logical_Order_Exception # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
+19B5..19B7 ; Logical_Order_Exception # Lo [3] NEW TAI LUE VOWEL SIGN E..NEW TAI LUE VOWEL SIGN O
+19BA ; Logical_Order_Exception # Lo NEW TAI LUE VOWEL SIGN AY
+AAB5..AAB6 ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL E..TAI VIET VOWEL O
+AAB9 ; Logical_Order_Exception # Lo TAI VIET VOWEL UEA
+AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET VOWEL AY
+
+# Total code points: 19
+
+# ================================================
+
+1885..1886 ; Other_ID_Start # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
+2118 ; Other_ID_Start # Sm SCRIPT CAPITAL P
+212E ; Other_ID_Start # So ESTIMATED SYMBOL
+309B..309C ; Other_ID_Start # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
+
+# Total code points: 6
+
+# ================================================
+
+00B7 ; Other_ID_Continue # Po MIDDLE DOT
+0387 ; Other_ID_Continue # Po GREEK ANO TELEIA
+1369..1371 ; Other_ID_Continue # No [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE
+19DA ; Other_ID_Continue # No NEW TAI LUE THAM DIGIT ONE
+
+# Total code points: 12
+
+# ================================================
+
+0021 ; Sentence_Terminal # Po EXCLAMATION MARK
+002E ; Sentence_Terminal # Po FULL STOP
+003F ; Sentence_Terminal # Po QUESTION MARK
+0589 ; Sentence_Terminal # Po ARMENIAN FULL STOP
+061F ; Sentence_Terminal # Po ARABIC QUESTION MARK
+06D4 ; Sentence_Terminal # Po ARABIC FULL STOP
+0700..0702 ; Sentence_Terminal # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP
+07F9 ; Sentence_Terminal # Po NKO EXCLAMATION MARK
+0964..0965 ; Sentence_Terminal # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
+104A..104B ; Sentence_Terminal # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
+1362 ; Sentence_Terminal # Po ETHIOPIC FULL STOP
+1367..1368 ; Sentence_Terminal # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
+166E ; Sentence_Terminal # Po CANADIAN SYLLABICS FULL STOP
+1735..1736 ; Sentence_Terminal # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
+1803 ; Sentence_Terminal # Po MONGOLIAN FULL STOP
+1809 ; Sentence_Terminal # Po MONGOLIAN MANCHU FULL STOP
+1944..1945 ; Sentence_Terminal # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
+1AA8..1AAB ; Sentence_Terminal # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU
+1B5A..1B5B ; Sentence_Terminal # Po [2] BALINESE PANTI..BALINESE PAMADA
+1B5E..1B5F ; Sentence_Terminal # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN
+1C3B..1C3C ; Sentence_Terminal # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL
+1C7E..1C7F ; Sentence_Terminal # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
+203C..203D ; Sentence_Terminal # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG
+2047..2049 ; Sentence_Terminal # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
+2E2E ; Sentence_Terminal # Po REVERSED QUESTION MARK
+2E3C ; Sentence_Terminal # Po STENOGRAPHIC FULL STOP
+3002 ; Sentence_Terminal # Po IDEOGRAPHIC FULL STOP
+A4FF ; Sentence_Terminal # Po LISU PUNCTUATION FULL STOP
+A60E..A60F ; Sentence_Terminal # Po [2] VAI FULL STOP..VAI QUESTION MARK
+A6F3 ; Sentence_Terminal # Po BAMUM FULL STOP
+A6F7 ; Sentence_Terminal # Po BAMUM QUESTION MARK
+A876..A877 ; Sentence_Terminal # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD
+A8CE..A8CF ; Sentence_Terminal # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
+A92F ; Sentence_Terminal # Po KAYAH LI SIGN SHYA
+A9C8..A9C9 ; Sentence_Terminal # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI
+AA5D..AA5F ; Sentence_Terminal # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA
+AAF0..AAF1 ; Sentence_Terminal # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM
+ABEB ; Sentence_Terminal # Po MEETEI MAYEK CHEIKHEI
+FE52 ; Sentence_Terminal # Po SMALL FULL STOP
+FE56..FE57 ; Sentence_Terminal # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK
+FF01 ; Sentence_Terminal # Po FULLWIDTH EXCLAMATION MARK
+FF0E ; Sentence_Terminal # Po FULLWIDTH FULL STOP
+FF1F ; Sentence_Terminal # Po FULLWIDTH QUESTION MARK
+FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP
+10A56..10A57 ; Sentence_Terminal # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA
+11047..11048 ; Sentence_Terminal # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA
+110BE..110C1 ; Sentence_Terminal # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
+11141..11143 ; Sentence_Terminal # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK
+111C5..111C6 ; Sentence_Terminal # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA
+111CD ; Sentence_Terminal # Po SHARADA SUTRA MARK
+111DE..111DF ; Sentence_Terminal # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2
+11238..11239 ; Sentence_Terminal # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA
+1123B..1123C ; Sentence_Terminal # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK
+112A9 ; Sentence_Terminal # Po MULTANI SECTION MARK
+1144B..1144C ; Sentence_Terminal # Po [2] NEWA DANDA..NEWA DOUBLE DANDA
+115C2..115C3 ; Sentence_Terminal # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA
+115C9..115D7 ; Sentence_Terminal # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
+11641..11642 ; Sentence_Terminal # Po [2] MODI DANDA..MODI DOUBLE DANDA
+1173C..1173E ; Sentence_Terminal # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
+11A42..11A43 ; Sentence_Terminal # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD
+11A9B..11A9C ; Sentence_Terminal # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
+11C41..11C42 ; Sentence_Terminal # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA
+16A6E..16A6F ; Sentence_Terminal # Po [2] MRO DANDA..MRO DOUBLE DANDA
+16AF5 ; Sentence_Terminal # Po BASSA VAH FULL STOP
+16B37..16B38 ; Sentence_Terminal # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
+16B44 ; Sentence_Terminal # Po PAHAWH HMONG SIGN XAUS
+1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
+1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP
+
+# Total code points: 128
+
+# ================================================
+
+180B..180D ; Variation_Selector # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+FE00..FE0F ; Variation_Selector # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
+E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
+
+# Total code points: 259
+
+# ================================================
+
+0009..000D ; Pattern_White_Space # Cc [5] <control-0009>..<control-000D>
+0020 ; Pattern_White_Space # Zs SPACE
+0085 ; Pattern_White_Space # Cc <control-0085>
+200E..200F ; Pattern_White_Space # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
+2028 ; Pattern_White_Space # Zl LINE SEPARATOR
+2029 ; Pattern_White_Space # Zp PARAGRAPH SEPARATOR
+
+# Total code points: 11
+
+# ================================================
+
+0021..0023 ; Pattern_Syntax # Po [3] EXCLAMATION MARK..NUMBER SIGN
+0024 ; Pattern_Syntax # Sc DOLLAR SIGN
+0025..0027 ; Pattern_Syntax # Po [3] PERCENT SIGN..APOSTROPHE
+0028 ; Pattern_Syntax # Ps LEFT PARENTHESIS
+0029 ; Pattern_Syntax # Pe RIGHT PARENTHESIS
+002A ; Pattern_Syntax # Po ASTERISK
+002B ; Pattern_Syntax # Sm PLUS SIGN
+002C ; Pattern_Syntax # Po COMMA
+002D ; Pattern_Syntax # Pd HYPHEN-MINUS
+002E..002F ; Pattern_Syntax # Po [2] FULL STOP..SOLIDUS
+003A..003B ; Pattern_Syntax # Po [2] COLON..SEMICOLON
+003C..003E ; Pattern_Syntax # Sm [3] LESS-THAN SIGN..GREATER-THAN SIGN
+003F..0040 ; Pattern_Syntax # Po [2] QUESTION MARK..COMMERCIAL AT
+005B ; Pattern_Syntax # Ps LEFT SQUARE BRACKET
+005C ; Pattern_Syntax # Po REVERSE SOLIDUS
+005D ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET
+005E ; Pattern_Syntax # Sk CIRCUMFLEX ACCENT
+0060 ; Pattern_Syntax # Sk GRAVE ACCENT
+007B ; Pattern_Syntax # Ps LEFT CURLY BRACKET
+007C ; Pattern_Syntax # Sm VERTICAL LINE
+007D ; Pattern_Syntax # Pe RIGHT CURLY BRACKET
+007E ; Pattern_Syntax # Sm TILDE
+00A1 ; Pattern_Syntax # Po INVERTED EXCLAMATION MARK
+00A2..00A5 ; Pattern_Syntax # Sc [4] CENT SIGN..YEN SIGN
+00A6 ; Pattern_Syntax # So BROKEN BAR
+00A7 ; Pattern_Syntax # Po SECTION SIGN
+00A9 ; Pattern_Syntax # So COPYRIGHT SIGN
+00AB ; Pattern_Syntax # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+00AC ; Pattern_Syntax # Sm NOT SIGN
+00AE ; Pattern_Syntax # So REGISTERED SIGN
+00B0 ; Pattern_Syntax # So DEGREE SIGN
+00B1 ; Pattern_Syntax # Sm PLUS-MINUS SIGN
+00B6 ; Pattern_Syntax # Po PILCROW SIGN
+00BB ; Pattern_Syntax # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+00BF ; Pattern_Syntax # Po INVERTED QUESTION MARK
+00D7 ; Pattern_Syntax # Sm MULTIPLICATION SIGN
+00F7 ; Pattern_Syntax # Sm DIVISION SIGN
+2010..2015 ; Pattern_Syntax # Pd [6] HYPHEN..HORIZONTAL BAR
+2016..2017 ; Pattern_Syntax # Po [2] DOUBLE VERTICAL LINE..DOUBLE LOW LINE
+2018 ; Pattern_Syntax # Pi LEFT SINGLE QUOTATION MARK
+2019 ; Pattern_Syntax # Pf RIGHT SINGLE QUOTATION MARK
+201A ; Pattern_Syntax # Ps SINGLE LOW-9 QUOTATION MARK
+201B..201C ; Pattern_Syntax # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK
+201D ; Pattern_Syntax # Pf RIGHT DOUBLE QUOTATION MARK
+201E ; Pattern_Syntax # Ps DOUBLE LOW-9 QUOTATION MARK
+201F ; Pattern_Syntax # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK
+2020..2027 ; Pattern_Syntax # Po [8] DAGGER..HYPHENATION POINT
+2030..2038 ; Pattern_Syntax # Po [9] PER MILLE SIGN..CARET
+2039 ; Pattern_Syntax # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+203A ; Pattern_Syntax # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+203B..203E ; Pattern_Syntax # Po [4] REFERENCE MARK..OVERLINE
+2041..2043 ; Pattern_Syntax # Po [3] CARET INSERTION POINT..HYPHEN BULLET
+2044 ; Pattern_Syntax # Sm FRACTION SLASH
+2045 ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH QUILL
+2046 ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH QUILL
+2047..2051 ; Pattern_Syntax # Po [11] DOUBLE QUESTION MARK..TWO ASTERISKS ALIGNED VERTICALLY
+2052 ; Pattern_Syntax # Sm COMMERCIAL MINUS SIGN
+2053 ; Pattern_Syntax # Po SWUNG DASH
+2055..205E ; Pattern_Syntax # Po [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS
+2190..2194 ; Pattern_Syntax # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
+2195..2199 ; Pattern_Syntax # So [5] UP DOWN ARROW..SOUTH WEST ARROW
+219A..219B ; Pattern_Syntax # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE
+219C..219F ; Pattern_Syntax # So [4] LEFTWARDS WAVE ARROW..UPWARDS TWO HEADED ARROW
+21A0 ; Pattern_Syntax # Sm RIGHTWARDS TWO HEADED ARROW
+21A1..21A2 ; Pattern_Syntax # So [2] DOWNWARDS TWO HEADED ARROW..LEFTWARDS ARROW WITH TAIL
+21A3 ; Pattern_Syntax # Sm RIGHTWARDS ARROW WITH TAIL
+21A4..21A5 ; Pattern_Syntax # So [2] LEFTWARDS ARROW FROM BAR..UPWARDS ARROW FROM BAR
+21A6 ; Pattern_Syntax # Sm RIGHTWARDS ARROW FROM BAR
+21A7..21AD ; Pattern_Syntax # So [7] DOWNWARDS ARROW FROM BAR..LEFT RIGHT WAVE ARROW
+21AE ; Pattern_Syntax # Sm LEFT RIGHT ARROW WITH STROKE
+21AF..21CD ; Pattern_Syntax # So [31] DOWNWARDS ZIGZAG ARROW..LEFTWARDS DOUBLE ARROW WITH STROKE
+21CE..21CF ; Pattern_Syntax # Sm [2] LEFT RIGHT DOUBLE ARROW WITH STROKE..RIGHTWARDS DOUBLE ARROW WITH STROKE
+21D0..21D1 ; Pattern_Syntax # So [2] LEFTWARDS DOUBLE ARROW..UPWARDS DOUBLE ARROW
+21D2 ; Pattern_Syntax # Sm RIGHTWARDS DOUBLE ARROW
+21D3 ; Pattern_Syntax # So DOWNWARDS DOUBLE ARROW
+21D4 ; Pattern_Syntax # Sm LEFT RIGHT DOUBLE ARROW
+21D5..21F3 ; Pattern_Syntax # So [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW
+21F4..22FF ; Pattern_Syntax # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP
+2300..2307 ; Pattern_Syntax # So [8] DIAMETER SIGN..WAVY LINE
+2308 ; Pattern_Syntax # Ps LEFT CEILING
+2309 ; Pattern_Syntax # Pe RIGHT CEILING
+230A ; Pattern_Syntax # Ps LEFT FLOOR
+230B ; Pattern_Syntax # Pe RIGHT FLOOR
+230C..231F ; Pattern_Syntax # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER
+2320..2321 ; Pattern_Syntax # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL
+2322..2328 ; Pattern_Syntax # So [7] FROWN..KEYBOARD
+2329 ; Pattern_Syntax # Ps LEFT-POINTING ANGLE BRACKET
+232A ; Pattern_Syntax # Pe RIGHT-POINTING ANGLE BRACKET
+232B..237B ; Pattern_Syntax # So [81] ERASE TO THE LEFT..NOT CHECK MARK
+237C ; Pattern_Syntax # Sm RIGHT ANGLE WITH DOWNWARDS ZIGZAG ARROW
+237D..239A ; Pattern_Syntax # So [30] SHOULDERED OPEN BOX..CLEAR SCREEN SYMBOL
+239B..23B3 ; Pattern_Syntax # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM
+23B4..23DB ; Pattern_Syntax # So [40] TOP SQUARE BRACKET..FUSE
+23DC..23E1 ; Pattern_Syntax # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET
+23E2..2426 ; Pattern_Syntax # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO
+2427..243F ; Pattern_Syntax # Cn [25] <reserved-2427>..<reserved-243F>
+2440..244A ; Pattern_Syntax # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
+244B..245F ; Pattern_Syntax # Cn [21] <reserved-244B>..<reserved-245F>
+2500..25B6 ; Pattern_Syntax # So [183] BOX DRAWINGS LIGHT HORIZONTAL..BLACK RIGHT-POINTING TRIANGLE
+25B7 ; Pattern_Syntax # Sm WHITE RIGHT-POINTING TRIANGLE
+25B8..25C0 ; Pattern_Syntax # So [9] BLACK RIGHT-POINTING SMALL TRIANGLE..BLACK LEFT-POINTING TRIANGLE
+25C1 ; Pattern_Syntax # Sm WHITE LEFT-POINTING TRIANGLE
+25C2..25F7 ; Pattern_Syntax # So [54] BLACK LEFT-POINTING SMALL TRIANGLE..WHITE CIRCLE WITH UPPER RIGHT QUADRANT
+25F8..25FF ; Pattern_Syntax # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE
+2600..266E ; Pattern_Syntax # So [111] BLACK SUN WITH RAYS..MUSIC NATURAL SIGN
+266F ; Pattern_Syntax # Sm MUSIC SHARP SIGN
+2670..2767 ; Pattern_Syntax # So [248] WEST SYRIAC CROSS..ROTATED FLORAL HEART BULLET
+2768 ; Pattern_Syntax # Ps MEDIUM LEFT PARENTHESIS ORNAMENT
+2769 ; Pattern_Syntax # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT
+276A ; Pattern_Syntax # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT
+276B ; Pattern_Syntax # Pe MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT
+276C ; Pattern_Syntax # Ps MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT
+276D ; Pattern_Syntax # Pe MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT
+276E ; Pattern_Syntax # Ps HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT
+276F ; Pattern_Syntax # Pe HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
+2770 ; Pattern_Syntax # Ps HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT
+2771 ; Pattern_Syntax # Pe HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT
+2772 ; Pattern_Syntax # Ps LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT
+2773 ; Pattern_Syntax # Pe LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT
+2774 ; Pattern_Syntax # Ps MEDIUM LEFT CURLY BRACKET ORNAMENT
+2775 ; Pattern_Syntax # Pe MEDIUM RIGHT CURLY BRACKET ORNAMENT
+2794..27BF ; Pattern_Syntax # So [44] HEAVY WIDE-HEADED RIGHTWARDS ARROW..DOUBLE CURLY LOOP
+27C0..27C4 ; Pattern_Syntax # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET
+27C5 ; Pattern_Syntax # Ps LEFT S-SHAPED BAG DELIMITER
+27C6 ; Pattern_Syntax # Pe RIGHT S-SHAPED BAG DELIMITER
+27C7..27E5 ; Pattern_Syntax # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK
+27E6 ; Pattern_Syntax # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET
+27E7 ; Pattern_Syntax # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET
+27E8 ; Pattern_Syntax # Ps MATHEMATICAL LEFT ANGLE BRACKET
+27E9 ; Pattern_Syntax # Pe MATHEMATICAL RIGHT ANGLE BRACKET
+27EA ; Pattern_Syntax # Ps MATHEMATICAL LEFT DOUBLE ANGLE BRACKET
+27EB ; Pattern_Syntax # Pe MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET
+27EC ; Pattern_Syntax # Ps MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET
+27ED ; Pattern_Syntax # Pe MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET
+27EE ; Pattern_Syntax # Ps MATHEMATICAL LEFT FLATTENED PARENTHESIS
+27EF ; Pattern_Syntax # Pe MATHEMATICAL RIGHT FLATTENED PARENTHESIS
+27F0..27FF ; Pattern_Syntax # Sm [16] UPWARDS QUADRUPLE ARROW..LONG RIGHTWARDS SQUIGGLE ARROW
+2800..28FF ; Pattern_Syntax # So [256] BRAILLE PATTERN BLANK..BRAILLE PATTERN DOTS-12345678
+2900..2982 ; Pattern_Syntax # Sm [131] RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE..Z NOTATION TYPE COLON
+2983 ; Pattern_Syntax # Ps LEFT WHITE CURLY BRACKET
+2984 ; Pattern_Syntax # Pe RIGHT WHITE CURLY BRACKET
+2985 ; Pattern_Syntax # Ps LEFT WHITE PARENTHESIS
+2986 ; Pattern_Syntax # Pe RIGHT WHITE PARENTHESIS
+2987 ; Pattern_Syntax # Ps Z NOTATION LEFT IMAGE BRACKET
+2988 ; Pattern_Syntax # Pe Z NOTATION RIGHT IMAGE BRACKET
+2989 ; Pattern_Syntax # Ps Z NOTATION LEFT BINDING BRACKET
+298A ; Pattern_Syntax # Pe Z NOTATION RIGHT BINDING BRACKET
+298B ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH UNDERBAR
+298C ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH UNDERBAR
+298D ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH TICK IN TOP CORNER
+298E ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
+298F ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
+2990 ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER
+2991 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET WITH DOT
+2992 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET WITH DOT
+2993 ; Pattern_Syntax # Ps LEFT ARC LESS-THAN BRACKET
+2994 ; Pattern_Syntax # Pe RIGHT ARC GREATER-THAN BRACKET
+2995 ; Pattern_Syntax # Ps DOUBLE LEFT ARC GREATER-THAN BRACKET
+2996 ; Pattern_Syntax # Pe DOUBLE RIGHT ARC LESS-THAN BRACKET
+2997 ; Pattern_Syntax # Ps LEFT BLACK TORTOISE SHELL BRACKET
+2998 ; Pattern_Syntax # Pe RIGHT BLACK TORTOISE SHELL BRACKET
+2999..29D7 ; Pattern_Syntax # Sm [63] DOTTED FENCE..BLACK HOURGLASS
+29D8 ; Pattern_Syntax # Ps LEFT WIGGLY FENCE
+29D9 ; Pattern_Syntax # Pe RIGHT WIGGLY FENCE
+29DA ; Pattern_Syntax # Ps LEFT DOUBLE WIGGLY FENCE
+29DB ; Pattern_Syntax # Pe RIGHT DOUBLE WIGGLY FENCE
+29DC..29FB ; Pattern_Syntax # Sm [32] INCOMPLETE INFINITY..TRIPLE PLUS
+29FC ; Pattern_Syntax # Ps LEFT-POINTING CURVED ANGLE BRACKET
+29FD ; Pattern_Syntax # Pe RIGHT-POINTING CURVED ANGLE BRACKET
+29FE..2AFF ; Pattern_Syntax # Sm [258] TINY..N-ARY WHITE VERTICAL BAR
+2B00..2B2F ; Pattern_Syntax # So [48] NORTH EAST WHITE ARROW..WHITE VERTICAL ELLIPSE
+2B30..2B44 ; Pattern_Syntax # Sm [21] LEFT ARROW WITH SMALL CIRCLE..RIGHTWARDS ARROW THROUGH SUPERSET
+2B45..2B46 ; Pattern_Syntax # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW
+2B47..2B4C ; Pattern_Syntax # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR
+2B4D..2B73 ; Pattern_Syntax # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
+2B74..2B75 ; Pattern_Syntax # Cn [2] <reserved-2B74>..<reserved-2B75>
+2B76..2B95 ; Pattern_Syntax # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
+2B96..2B97 ; Pattern_Syntax # Cn [2] <reserved-2B96>..<reserved-2B97>
+2B98..2BB9 ; Pattern_Syntax # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
+2BBA..2BBC ; Pattern_Syntax # Cn [3] <reserved-2BBA>..<reserved-2BBC>
+2BBD..2BC8 ; Pattern_Syntax # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
+2BC9 ; Pattern_Syntax # Cn <reserved-2BC9>
+2BCA..2BD2 ; Pattern_Syntax # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
+2BD3..2BEB ; Pattern_Syntax # Cn [25] <reserved-2BD3>..<reserved-2BEB>
+2BEC..2BEF ; Pattern_Syntax # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
+2BF0..2BFF ; Pattern_Syntax # Cn [16] <reserved-2BF0>..<reserved-2BFF>
+2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
+2E02 ; Pattern_Syntax # Pi LEFT SUBSTITUTION BRACKET
+2E03 ; Pattern_Syntax # Pf RIGHT SUBSTITUTION BRACKET
+2E04 ; Pattern_Syntax # Pi LEFT DOTTED SUBSTITUTION BRACKET
+2E05 ; Pattern_Syntax # Pf RIGHT DOTTED SUBSTITUTION BRACKET
+2E06..2E08 ; Pattern_Syntax # Po [3] RAISED INTERPOLATION MARKER..DOTTED TRANSPOSITION MARKER
+2E09 ; Pattern_Syntax # Pi LEFT TRANSPOSITION BRACKET
+2E0A ; Pattern_Syntax # Pf RIGHT TRANSPOSITION BRACKET
+2E0B ; Pattern_Syntax # Po RAISED SQUARE
+2E0C ; Pattern_Syntax # Pi LEFT RAISED OMISSION BRACKET
+2E0D ; Pattern_Syntax # Pf RIGHT RAISED OMISSION BRACKET
+2E0E..2E16 ; Pattern_Syntax # Po [9] EDITORIAL CORONIS..DOTTED RIGHT-POINTING ANGLE
+2E17 ; Pattern_Syntax # Pd DOUBLE OBLIQUE HYPHEN
+2E18..2E19 ; Pattern_Syntax # Po [2] INVERTED INTERROBANG..PALM BRANCH
+2E1A ; Pattern_Syntax # Pd HYPHEN WITH DIAERESIS
+2E1B ; Pattern_Syntax # Po TILDE WITH RING ABOVE
+2E1C ; Pattern_Syntax # Pi LEFT LOW PARAPHRASE BRACKET
+2E1D ; Pattern_Syntax # Pf RIGHT LOW PARAPHRASE BRACKET
+2E1E..2E1F ; Pattern_Syntax # Po [2] TILDE WITH DOT ABOVE..TILDE WITH DOT BELOW
+2E20 ; Pattern_Syntax # Pi LEFT VERTICAL BAR WITH QUILL
+2E21 ; Pattern_Syntax # Pf RIGHT VERTICAL BAR WITH QUILL
+2E22 ; Pattern_Syntax # Ps TOP LEFT HALF BRACKET
+2E23 ; Pattern_Syntax # Pe TOP RIGHT HALF BRACKET
+2E24 ; Pattern_Syntax # Ps BOTTOM LEFT HALF BRACKET
+2E25 ; Pattern_Syntax # Pe BOTTOM RIGHT HALF BRACKET
+2E26 ; Pattern_Syntax # Ps LEFT SIDEWAYS U BRACKET
+2E27 ; Pattern_Syntax # Pe RIGHT SIDEWAYS U BRACKET
+2E28 ; Pattern_Syntax # Ps LEFT DOUBLE PARENTHESIS
+2E29 ; Pattern_Syntax # Pe RIGHT DOUBLE PARENTHESIS
+2E2A..2E2E ; Pattern_Syntax # Po [5] TWO DOTS OVER ONE DOT PUNCTUATION..REVERSED QUESTION MARK
+2E2F ; Pattern_Syntax # Lm VERTICAL TILDE
+2E30..2E39 ; Pattern_Syntax # Po [10] RING POINT..TOP HALF SECTION SIGN
+2E3A..2E3B ; Pattern_Syntax # Pd [2] TWO-EM DASH..THREE-EM DASH
+2E3C..2E3F ; Pattern_Syntax # Po [4] STENOGRAPHIC FULL STOP..CAPITULUM
+2E40 ; Pattern_Syntax # Pd DOUBLE HYPHEN
+2E41 ; Pattern_Syntax # Po REVERSED COMMA
+2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
+2E43..2E49 ; Pattern_Syntax # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
+2E4A..2E7F ; Pattern_Syntax # Cn [54] <reserved-2E4A>..<reserved-2E7F>
+3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
+3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET
+3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET
+300A ; Pattern_Syntax # Ps LEFT DOUBLE ANGLE BRACKET
+300B ; Pattern_Syntax # Pe RIGHT DOUBLE ANGLE BRACKET
+300C ; Pattern_Syntax # Ps LEFT CORNER BRACKET
+300D ; Pattern_Syntax # Pe RIGHT CORNER BRACKET
+300E ; Pattern_Syntax # Ps LEFT WHITE CORNER BRACKET
+300F ; Pattern_Syntax # Pe RIGHT WHITE CORNER BRACKET
+3010 ; Pattern_Syntax # Ps LEFT BLACK LENTICULAR BRACKET
+3011 ; Pattern_Syntax # Pe RIGHT BLACK LENTICULAR BRACKET
+3012..3013 ; Pattern_Syntax # So [2] POSTAL MARK..GETA MARK
+3014 ; Pattern_Syntax # Ps LEFT TORTOISE SHELL BRACKET
+3015 ; Pattern_Syntax # Pe RIGHT TORTOISE SHELL BRACKET
+3016 ; Pattern_Syntax # Ps LEFT WHITE LENTICULAR BRACKET
+3017 ; Pattern_Syntax # Pe RIGHT WHITE LENTICULAR BRACKET
+3018 ; Pattern_Syntax # Ps LEFT WHITE TORTOISE SHELL BRACKET
+3019 ; Pattern_Syntax # Pe RIGHT WHITE TORTOISE SHELL BRACKET
+301A ; Pattern_Syntax # Ps LEFT WHITE SQUARE BRACKET
+301B ; Pattern_Syntax # Pe RIGHT WHITE SQUARE BRACKET
+301C ; Pattern_Syntax # Pd WAVE DASH
+301D ; Pattern_Syntax # Ps REVERSED DOUBLE PRIME QUOTATION MARK
+301E..301F ; Pattern_Syntax # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK
+3020 ; Pattern_Syntax # So POSTAL MARK FACE
+3030 ; Pattern_Syntax # Pd WAVY DASH
+FD3E ; Pattern_Syntax # Pe ORNATE LEFT PARENTHESIS
+FD3F ; Pattern_Syntax # Ps ORNATE RIGHT PARENTHESIS
+FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT
+
+# Total code points: 2760
+
+# ================================================
+
+0600..0605 ; Prepended_Concatenation_Mark # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
+06DD ; Prepended_Concatenation_Mark # Cf ARABIC END OF AYAH
+070F ; Prepended_Concatenation_Mark # Cf SYRIAC ABBREVIATION MARK
+08E2 ; Prepended_Concatenation_Mark # Cf ARABIC DISPUTED END OF AYAH
+110BD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN
+
+# Total code points: 10
+
+# ================================================
+
+1F1E6..1F1FF ; Regional_Indicator # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
+
+# Total code points: 26
+
+# EOF
diff --git a/localedata/unicode-gen/utf8_gen.py b/localedata/unicode-gen/utf8_gen.py
index 52c79e83c1..26939e25a8 100755
--- a/localedata/unicode-gen/utf8_gen.py
+++ b/localedata/unicode-gen/utf8_gen.py
@@ -215,9 +215,11 @@ def write_header_width(outfile):
# outfile.write("% \"grep '^[^;]*;ZERO WIDTH ' UnicodeData.txt\"\n")
outfile.write("WIDTH\n")
-def process_width(outfile, ulines, elines):
+def process_width(outfile, ulines, elines, plines):
'''ulines are lines from UnicodeData.txt, elines are lines from
- EastAsianWidth.txt
+ EastAsianWidth.txt containing characters with width “W” or “F”,
+ plines are lines from PropList.txt which contain characters
+ with the property “Prepended_Concatenation_Mark”.
'''
width_dict = {}
@@ -230,16 +232,29 @@ def process_width(outfile, ulines, elines):
for key in range(int(code_points[0], 16),
int(code_points[1], 16)+1):
width_dict[key] = 2
+
for line in ulines:
fields = line.split(";")
if fields[4] == "NSM" or fields[2] in ("Cf", "Me", "Mn"):
width_dict[int(fields[0], 16)] = 0
+ for line in plines:
+ # Characters with the property “Prepended_Concatenation_Mark”
+ # should have the width 1:
+ fields = line.split(";")
+ if not '..' in fields[0]:
+ code_points = (fields[0], fields[0])
+ else:
+ code_points = fields[0].split("..")
+ for key in range(int(code_points[0], 16),
+ int(code_points[1], 16)+1):
+ del width_dict[key] # default width is 1
+
# handle special cases for compatibility
for key in list((0x00AD,)):
# https://www.cs.tut.fi/~jkorpela/shy.html
if key in width_dict:
- del width_dict[key]
+ del width_dict[key] # default width is 1
for key in list(range(0x1160, 0x1200)):
width_dict[key] = 0
for key in list(range(0x3248, 0x3250)):
@@ -278,7 +293,7 @@ def process_width(outfile, ulines, elines):
if __name__ == "__main__":
if len(sys.argv) < 3:
- print("USAGE: python3 utf8_gen.py UnicodeData.txt EastAsianWidth.txt")
+ print("USAGE: python3 utf8_gen.py UnicodeData.txt EastAsianWidth.txt PropList.txt")
else:
with open(sys.argv[1], mode='r') as UNIDATA_FILE:
UNICODE_DATA_LINES = UNIDATA_FILE.readlines()
@@ -298,6 +313,11 @@ if __name__ == "__main__":
continue
if re.match(r'^[^;]*;[WF]', LINE):
EAST_ASIAN_WIDTH_LINES.append(LINE.strip())
+ with open(sys.argv[3], mode='r') as PROP_LIST_FILE:
+ PROP_LIST_LINES = []
+ for LINE in PROP_LIST_FILE:
+ if re.match(r'^[^;]*;[\s]*Prepended_Concatenation_Mark', LINE):
+ PROP_LIST_LINES.append(LINE.strip())
with open('UTF-8', mode='w') as OUTFILE:
# Processing UnicodeData.txt and write CHARMAP to UTF-8 file
write_header_charmap(OUTFILE)
@@ -305,5 +325,8 @@ if __name__ == "__main__":
OUTFILE.write("END CHARMAP\n\n")
# Processing EastAsianWidth.txt and write WIDTH to UTF-8 file
write_header_width(OUTFILE)
- process_width(OUTFILE, UNICODE_DATA_LINES, EAST_ASIAN_WIDTH_LINES)
+ process_width(OUTFILE,
+ UNICODE_DATA_LINES,
+ EAST_ASIAN_WIDTH_LINES,
+ PROP_LIST_LINES)
OUTFILE.write("END WIDTH\n")