* Added a unicode directory containing files from unicode.org

as well as extractors for the data.
This commit is contained in:
Abdulaziz Ghuloum 2007-05-19 22:09:30 -04:00
parent caa5eed9a0
commit a1879ccc57
32 changed files with 122092 additions and 24 deletions

Binary file not shown.

View File

@ -13,15 +13,31 @@
(define $write-char
(lambda (c p)
(let ([idx (port-output-index p)])
(if ($fx< idx ($port-output-size p))
(let ([b ($char->fixnum c)])
(if ($fx< b 128)
(begin
($bytevector-set! ($port-output-buffer p) idx b)
($set-port-output-index! p ($fxadd1 idx)))
(($port-handler p) 'write-char c p)))
(($port-handler p) 'write-char c p)))))
(let ([b ($char->fixnum c)])
(cond
[($fx<= b #x7F)
($write-byte b p)]
[($fx<= b #x7FF)
($write-byte
($fxlogor #b11000000 ($fxsra b 6)) p)
($write-byte
($fxlogor #b10000000 ($fxlogand b #b111111)) p)]
[($fx<= b #xFFFF)
($write-byte
($fxlogor #b11100000 ($fxsra b 12)) p)
($write-byte
($fxlogor #b10000000 ($fxlogand ($fxsra b 6) #b111111)) p)
($write-byte
($fxlogor #b10000000 ($fxlogand b #b111111)) p)]
[else
($write-byte
($fxlogor #b11110000 ($fxsra b 18)) p)
($write-byte
($fxlogor #b10000000 ($fxlogand ($fxsra b 12) #b111111)) p)
($write-byte
($fxlogor #b10000000 ($fxlogand ($fxsra b 6) #b111111)) p)
($write-byte
($fxlogor #b10000000 ($fxlogand b #b111111)) p)]))))
(define $write-byte
(lambda (b p)

View File

@ -105,20 +105,15 @@
(write-char #\8 p)
(write-char #\( p)
(let ([n ($bytevector-length x)])
(let ([i
(cond
[(fx> n 0)
(let f ([idx 1] [i (writer ($bytevector-u8-ref x 0) p m h i)])
(cond
[(fx= idx n)
i]
[else
(write-char #\space p)
(f (fxadd1 idx)
(writer (bytevector-u8-ref x idx) p m h i))]))]
[else i])])
(write-char #\) p)
i))))
(when (fx> n 0)
(write-fixnum ($bytevector-u8-ref x 0) p)
(let f ([idx 1] [n n] [x x] [p p])
(unless ($fx= idx n)
(write-char #\space p)
(write-fixnum ($bytevector-u8-ref x idx) p)
(f (fxadd1 idx) n x p)))))
(write-char #\) p)
i))
(define write-record
(lambda (x p m h i)
@ -270,7 +265,8 @@
[(in-map? b subsequents-map)
(write-char c p)]
[else
(write-inline-hex b p)]))))
(write-inline-hex b p)]))
(write-subsequent* str ($fxadd1 i) j p)))
(define write-symbol-hex-esc
(lambda (str p)

View File

@ -0,0 +1,338 @@
# ArabicShaping-5.0.0.txt
# Date: 2006-07-14, 11:23:00 PST [KW]
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2006 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# This file defines the shaping classes for Arabic and Syriac
# positional shaping, repeating in machine readable form the
# information printed in Tables 8-3, 8-7, 8-8, 8-11, 8-12, and
# 8-13 of The Unicode Standard, Version 4.0.
#
# See sections 8.2 and 8.3 of The Unicode Standard, Version 4.0
# for more information.
#
# Each line contains four fields, separated by a semicolon.
#
# Field 0: the code point, in 4-digit hexadecimal
# form, of an Arabic or Syriac character.
# Field 1: gives a short schematic name for that character,
# abbreviated from the normative Unicode character name.
# Field 2: defines the joining type (property name: Joining_Type)
# R Right_Joining
# L Left_Joining
# D Dual_Joining
# C Join_Causing
# U Non_Joining
# T Transparent
# See the Arabic block description for more information on these types.
# Field 3: defines the joining group (property name: Joining_Group)
#
# The values of the joining group are based schematically on character
# names. Where a schematic character name consists of two or more parts separated
# by spaces, the formal Joining_Group property value, as specified in
# PropertyValueAliases.txt, consists of the same name parts joined by
# underscores. Hence, the entry:
#
# 0629; TEH MARBUTA; R; TEH MARBUTA
#
# corresponds to [Joining_Group = Teh_Marbuta].
#
# Note: For historical reasons, the property value [Joining_Group = Hamza_On_Heh_Goal]
# is anachronistically named. It used to apply to both of the following characters
# in earlier versions of the standard:
#
# U+06C2 ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
# U+06C3 ARABIC LETTER TEH MARBUTA GOAL
#
# However, it currently applies only to U+06C3, and *not* to U+06C2.
# To avoid destabilizing existing Joining_Group property aliases, the
# value Hamza_On_Heh_Goal has not been changed, despite the fact that it
# no longer applies to Hamza On Heh Goal, but only to Teh Marbuta Goal.
#
# Note: Code points that are not explicitly listed in this file are
# either of joining type T or U:
#
# - Those that not explicitly listed that are of General Category Mn, Me, or Cf
# have joining type T.
# - All others not explicitly listed have type U.
#
# For an explicit listing of characters of joining type T, see
# the derived property file DerivedJoiningType.txt.
#
# There are currently no characters of type L defined in Unicode.
#
# #############################################################
# Unicode; Schematic Name; Joining Type; Joining Group
# Arabic characters
0600; ARABIC NUMBER SIGN; U; No_Joining_Group
0601; ARABIC SIGN SANAH; U; No_Joining_Group
0602; ARABIC FOOTNOTE MARKER; U; No_Joining_Group
0603; ARABIC SIGN SAFHA; U; No_Joining_Group
060B; AFGHANI SIGN; U; No_Joining_Group
0621; HAMZA; U; No_Joining_Group
0622; MADDA ON ALEF; R; ALEF
0623; HAMZA ON ALEF; R; ALEF
0624; HAMZA ON WAW; R; WAW
0625; HAMZA UNDER ALEF; R; ALEF
0626; HAMZA ON YEH; D; YEH
0627; ALEF; R; ALEF
0628; BEH; D; BEH
0629; TEH MARBUTA; R; TEH MARBUTA
062A; TEH; D; BEH
062B; THEH; D; BEH
062C; JEEM; D; HAH
062D; HAH; D; HAH
062E; KHAH; D; HAH
062F; DAL; R; DAL
0630; THAL; R; DAL
0631; REH; R; REH
0632; ZAIN; R; REH
0633; SEEN; D; SEEN
0634; SHEEN; D; SEEN
0635; SAD; D; SAD
0636; DAD; D; SAD
0637; TAH; D; TAH
0638; ZAH; D; TAH
0639; AIN; D; AIN
063A; GHAIN; D; AIN
0640; TATWEEL; C; No_Joining_Group
0641; FEH; D; FEH
0642; QAF; D; QAF
0643; KAF; D; KAF
0644; LAM; D; LAM
0645; MEEM; D; MEEM
0646; NOON; D; NOON
0647; HEH; D; HEH
0648; WAW; R; WAW
0649; ALEF MAKSURA; D; YEH
064A; YEH; D; YEH
066E; DOTLESS BEH; D; BEH
066F; DOTLESS QAF; D; QAF
0671; HAMZAT WASL ON ALEF; R; ALEF
0672; WAVY HAMZA ON ALEF; R; ALEF
0673; WAVY HAMZA UNDER ALEF; R; ALEF
0674; HIGH HAMZA; U; No_Joining_Group
0675; HIGH HAMZA ALEF; R; ALEF
0676; HIGH HAMZA WAW; R; WAW
0677; HIGH HAMZA WAW WITH DAMMA; R; WAW
0678; HIGH HAMZA YEH; D; YEH
0679; TEH WITH SMALL TAH; D; BEH
067A; TEH WITH 2 DOTS VERTICAL ABOVE; D; BEH
067B; BEH WITH 2 DOTS VERTICAL BELOW; D; BEH
067C; TEH WITH RING; D; BEH
067D; TEH WITH 3 DOTS ABOVE DOWNWARD; D; BEH
067E; TEH WITH 3 DOTS BELOW; D; BEH
067F; TEH WITH 4 DOTS ABOVE; D; BEH
0680; BEH WITH 4 DOTS BELOW; D; BEH
0681; HAMZA ON HAH; D; HAH
0682; HAH WITH 2 DOTS VERTICAL ABOVE; D; HAH
0683; HAH WITH MIDDLE 2 DOTS; D; HAH
0684; HAH WITH MIDDLE 2 DOTS VERTICAL; D; HAH
0685; HAH WITH 3 DOTS ABOVE; D; HAH
0686; HAH WITH MIDDLE 3 DOTS DOWNWARD; D; HAH
0687; HAH WITH MIDDLE 4 DOTS; D; HAH
0688; DAL WITH SMALL TAH; R; DAL
0689; DAL WITH RING; R; DAL
068A; DAL WITH DOT BELOW; R; DAL
068B; DAL WITH DOT BELOW AND SMALL TAH; R; DAL
068C; DAL WITH 2 DOTS ABOVE; R; DAL
068D; DAL WITH 2 DOTS BELOW; R; DAL
068E; DAL WITH 3 DOTS ABOVE; R; DAL
068F; DAL WITH 3 DOTS ABOVE DOWNWARD; R; DAL
0690; DAL WITH 4 DOTS ABOVE; R; DAL
0691; REH WITH SMALL TAH; R; REH
0692; REH WITH SMALL V; R; REH
0693; REH WITH RING; R; REH
0694; REH WITH DOT BELOW; R; REH
0695; REH WITH SMALL V BELOW; R; REH
0696; REH WITH DOT BELOW AND DOT ABOVE; R; REH
0697; REH WITH 2 DOTS ABOVE; R; REH
0698; REH WITH 3 DOTS ABOVE; R; REH
0699; REH WITH 4 DOTS ABOVE; R; REH
069A; SEEN WITH DOT BELOW AND DOT ABOVE; D; SEEN
069B; SEEN WITH 3 DOTS BELOW; D; SEEN
069C; SEEN WITH 3 DOTS BELOW AND 3 DOTS ABOVE; D; SEEN
069D; SAD WITH 2 DOTS BELOW; D; SAD
069E; SAD WITH 3 DOTS ABOVE; D; SAD
069F; TAH WITH 3 DOTS ABOVE; D; TAH
06A0; AIN WITH 3 DOTS ABOVE; D; AIN
06A1; DOTLESS FEH; D; FEH
06A2; FEH WITH DOT MOVED BELOW; D; FEH
06A3; FEH WITH DOT BELOW; D; FEH
06A4; FEH WITH 3 DOTS ABOVE; D; FEH
06A5; FEH WITH 3 DOTS BELOW; D; FEH
06A6; FEH WITH 4 DOTS ABOVE; D; FEH
06A7; QAF WITH DOT ABOVE; D; QAF
06A8; QAF WITH 3 DOTS ABOVE; D; QAF
06A9; KEHEH; D; GAF
06AA; SWASH KAF; D; SWASH KAF
06AB; KAF WITH RING; D; GAF
06AC; KAF WITH DOT ABOVE; D; KAF
06AD; KAF WITH 3 DOTS ABOVE; D; KAF
06AE; KAF WITH 3 DOTS BELOW; D; KAF
06AF; GAF; D; GAF
06B0; GAF WITH RING; D; GAF
06B1; GAF WITH 2 DOTS ABOVE; D; GAF
06B2; GAF WITH 2 DOTS BELOW; D; GAF
06B3; GAF WITH 2 DOTS VERTICAL BELOW; D; GAF
06B4; GAF WITH 3 DOTS ABOVE; D; GAF
06B5; LAM WITH SMALL V; D; LAM
06B6; LAM WITH DOT ABOVE; D; LAM
06B7; LAM WITH 3 DOTS ABOVE; D; LAM
06B8; LAM WITH 3 DOTS BELOW; D; LAM
06B9; NOON WITH DOT BELOW; D; NOON
06BA; DOTLESS NOON; D; NOON
06BB; DOTLESS NOON WITH SMALL TAH; D; NOON
06BC; NOON WITH RING; D; NOON
06BD; NOON WITH 3 DOTS ABOVE; D; NOON
06BE; KNOTTED HEH; D; KNOTTED HEH
06BF; HAH WITH MIDDLE 3 DOTS DOWNWARD AND DOT ABOVE; D; HAH
06C0; HAMZA ON HEH; R; TEH MARBUTA
06C1; HEH GOAL; D; HEH GOAL
06C2; HAMZA ON HEH GOAL; D; HEH GOAL
06C3; TEH MARBUTA GOAL; R; HAMZA ON HEH GOAL
06C4; WAW WITH RING; R; WAW
06C5; WAW WITH BAR; R; WAW
06C6; WAW WITH SMALL V; R; WAW
06C7; WAW WITH DAMMA; R; WAW
06C8; WAW WITH ALEF ABOVE; R; WAW
06C9; WAW WITH INVERTED SMALL V; R; WAW
06CA; WAW WITH 2 DOTS ABOVE; R; WAW
06CB; WAW WITH 3 DOTS ABOVE; R; WAW
06CC; DOTLESS YEH; D; YEH
06CD; YEH WITH TAIL; R; YEH WITH TAIL
06CE; YEH WITH SMALL V; D; YEH
06CF; WAW WITH DOT ABOVE; R; WAW
06D0; YEH WITH 2 DOTS VERTICAL BELOW; D; YEH
06D1; YEH WITH 3 DOTS BELOW; D; YEH
06D2; YEH BARREE; R; YEH BARREE
06D3; HAMZA ON YEH BARREE; R; YEH BARREE
06D5; AE; R; TEH MARBUTA
06DD; ARABIC END OF AYAH; U; No_Joining_Group
06EE; DAL WITH INVERTED V; R; DAL
06EF; REH WITH INVERTED V; R; REH
06FA; SEEN WITH DOT BELOW AND 3 DOTS ABOVE; D; SEEN
06FB; DAD WITH DOT BELOW; D; SAD
06FC; GHAIN WITH DOT BELOW; D; AIN
06FF; HEH WITH INVERTED V; D; KNOTTED HEH
# Syriac characters
0710; ALAPH; R; ALAPH
0712; BETH; D; BETH
0713; GAMAL; D; GAMAL
0714; GAMAL GARSHUNI; D; GAMAL
0715; DALATH; R; DALATH RISH
0716; DOTLESS DALATH RISH; R; DALATH RISH
0717; HE; R; HE
0718; WAW; R; SYRIAC WAW
0719; ZAIN; R; ZAIN
071A; HETH; D; HETH
071B; TETH; D; TETH
071C; TETH GARSHUNI; D; TETH
071D; YUDH; D; YUDH
071E; YUDH HE; R; YUDH HE
071F; KAPH; D; KAPH
0720; LAMADH; D; LAMADH
0721; MIM; D; MIM
0722; NUN; D; NUN
0723; SEMKATH; D; SEMKATH
0724; FINAL SEMKATH; D; FINAL SEMKATH
0725; E; D; E
0726; PE; D; PE
0727; REVERSED PE; D; REVERSED PE
0728; SADHE; R; SADHE
0729; QAPH; D; QAPH
072A; RISH; R; DALATH RISH
072B; SHIN; D; SHIN
072C; TAW; R; TAW
072D; PERSIAN BHETH; D; BETH
072E; PERSIAN GHAMAL; D; GAMAL
072F; PERSIAN DHALATH; R; DALATH RISH
074D; SOGDIAN ZHAIN; R; ZHAIN
074E; SOGDIAN KHAPH; D; KHAPH
074F; SOGDIAN FE; D; FE
# Arabic supplement characters
0750; BEH WITH 3 DOTS HORIZONTALLY BELOW; D; BEH
0751; BEH WITH DOT BELOW AND 3 DOTS ABOVE; D; BEH
0752; BEH WITH 3 DOTS POINTING UPWARDS BELOW; D; BEH
0753; BEH WITH 3 DOTS POINTING UPWARDS BELOW AND 2 DOTS ABOVE; D; BEH
0754; BEH WITH 2 DOTS BELOW AND DOT ABOVE; D; BEH
0755; BEH WITH INVERTED SMALL V BELOW; D; BEH
0756; BEH WITH SMALL V; D; BEH
0757; HAH WITH 2 DOTS ABOVE; D; HAH
0758; HAH WITH 3 DOTS POINTING UPWARDS BELOW; D; HAH
0759; DAL WITH 2 DOTS VERTICALLY BELOW AND SMALL TAH; R; DAL
075A; DAL WITH INVERTED SMALL V BELOW; R; DAL
075B; REH WITH STROKE; R; REH
075C; SEEN WITH 4 DOTS ABOVE; D; SEEN
075D; AIN WITH 2 DOTS ABOVE; D; AIN
075E; AIN WITH 3 DOTS POINTING DOWNWARDS ABOVE; D; AIN
075F; AIN WITH 2 DOTS VERTICALLY ABOVE; D; AIN
0760; FEH WITH 2 DOTS BELOW; D; FEH
0761; FEH WITH 3 DOTS POINTING UPWARDS BELOW; D; FEH
0762; KEHEH WITH DOT ABOVE; D; GAF
0763; KEHEH WITH 3 DOTS ABOVE; D; GAF
0764; KEHEH WITH 3 DOTS POINTING UPWARDS BELOW; D; GAF
0765; MEEM WITH DOT ABOVE; D; MEEM
0766; MEEM WITH DOT BELOW; D; MEEM
0767; NOON WITH 2 DOTS BELOW; D; NOON
0768; NOON WITH SMALL TAH; D; NOON
0769; NOON WITH SMALL V; D; NOON
076A; LAM WITH BAR; D; LAM
076B; REH WITH 2 DOTS VERTICALLY ABOVE; R; REH
076C; REH WITH HAMZA ABOVE; R; REH
076D; SEEN WITH 2 DOTS VERTICALLY ABOVE; D; SEEN
# N'Ko Characters
07CA; NKO A; D; No_Joining_Group
07CB; NKO EE; D; No_Joining_Group
07CC; NKO I; D; No_Joining_Group
07CD; NKO E; D; No_Joining_Group
07CE; NKO U; D; No_Joining_Group
07CF; NKO OO; D; No_Joining_Group
07D0; NKO O; D; No_Joining_Group
07D1; NKO DAGBASINNA; D; No_Joining_Group
07D2; NKO N; D; No_Joining_Group
07D3; NKO BA; D; No_Joining_Group
07D4; NKO PA; D; No_Joining_Group
07D5; NKO TA; D; No_Joining_Group
07D6; NKO JA; D; No_Joining_Group
07D7; NKO CHA; D; No_Joining_Group
07D8; NKO DA; D; No_Joining_Group
07D9; NKO RA; D; No_Joining_Group
07DA; NKO RRA; D; No_Joining_Group
07DB; NKO SA; D; No_Joining_Group
07DC; NKO GBA; D; No_Joining_Group
07DD; NKO FA; D; No_Joining_Group
07DE; NKO KA; D; No_Joining_Group
07DF; NKO LA; D; No_Joining_Group
07E0; NKO NA WOLOSO; D; No_Joining_Group
07E1; NKO MA; D; No_Joining_Group
07E2; NKO NYA; D; No_Joining_Group
07E3; NKO NA; D; No_Joining_Group
07E4; NKO HA; D; No_Joining_Group
07E5; NKO WA; D; No_Joining_Group
07E6; NKO YA; D; No_Joining_Group
07E7; NKO NYA WOLOSO; D; No_Joining_Group
07E8; NKO JONA JA; D; No_Joining_Group
07E9; NKO JONA CHA; D; No_Joining_Group
07EA; NKO JONA RA; D; No_Joining_Group
07FA; NKO LAJANYALAN; C; No_Joining_Group
# Other
200D; ZERO WIDTH JOINER; C; No_Joining_Group
200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group
# EOF

View File

@ -0,0 +1,582 @@
# BidiMirroring-5.0.0.txt
# Date: 2006-02-16, 16:11:00 PST [KW]
#
# Bidi_Mirroring_Glyph Property
#
# This file is an informative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2006 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# This data file lists characters that have the mirrored property
# where there is another Unicode character that typically has a glyph
# that is the mirror image of the original character's glyph.
# The repertoire covered by the file is Unicode 5.0.0.
#
# The file contains a list of lines with mappings from one code point
# to another one for character-based mirroring.
# Note that for "real" mirroring, a rendering engine needs to select
# appropriate alternative glyphs, and that many Unicode characters do not
# have a mirror-image Unicode character.
#
# Each mapping line contains two fields, separated by a semicolon (';').
# Each of the two fields contains a code point represented as a
# variable-length hexadecimal value with 4 to 6 digits.
# A comment indicates where the characters are "BEST FIT" mirroring.
#
# Code points with the "mirrored" property but no appropriate mirrors are
# listed as comments at the end of the file.
#
# For information on bidi mirroring, see UAX #9: Bidirectional Algorithm,
# at http://www.unicode.org/unicode/reports/tr9/
#
# This file was originally created by Markus Scherer.
# Extended for Unicode 3.2, 4.0, 4.1, and 5.0 by Ken Whistler.
#
# ############################################################
0028; 0029 # LEFT PARENTHESIS
0029; 0028 # RIGHT PARENTHESIS
003C; 003E # LESS-THAN SIGN
003E; 003C # GREATER-THAN SIGN
005B; 005D # LEFT SQUARE BRACKET
005D; 005B # RIGHT SQUARE BRACKET
007B; 007D # LEFT CURLY BRACKET
007D; 007B # RIGHT CURLY BRACKET
00AB; 00BB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
00BB; 00AB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0F3A; 0F3B # TIBETAN MARK GUG RTAGS GYON
0F3B; 0F3A # TIBETAN MARK GUG RTAGS GYAS
0F3C; 0F3D # TIBETAN MARK ANG KHANG GYON
0F3D; 0F3C # TIBETAN MARK ANG KHANG GYAS
169B; 169C # OGHAM FEATHER MARK
169C; 169B # OGHAM REVERSED FEATHER MARK
2018; 2019 # [BEST FIT] LEFT SINGLE QUOTATION MARK
2019; 2018 # [BEST FIT] RIGHT SINGLE QUOTATION MARK
201C; 201D # [BEST FIT] LEFT DOUBLE QUOTATION MARK
201D; 201C # [BEST FIT] RIGHT DOUBLE QUOTATION MARK
2039; 203A # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
203A; 2039 # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
2045; 2046 # LEFT SQUARE BRACKET WITH QUILL
2046; 2045 # RIGHT SQUARE BRACKET WITH QUILL
207D; 207E # SUPERSCRIPT LEFT PARENTHESIS
207E; 207D # SUPERSCRIPT RIGHT PARENTHESIS
208D; 208E # SUBSCRIPT LEFT PARENTHESIS
208E; 208D # SUBSCRIPT RIGHT PARENTHESIS
2208; 220B # ELEMENT OF
2209; 220C # NOT AN ELEMENT OF
220A; 220D # SMALL ELEMENT OF
220B; 2208 # CONTAINS AS MEMBER
220C; 2209 # DOES NOT CONTAIN AS MEMBER
220D; 220A # SMALL CONTAINS AS MEMBER
2215; 29F5 # DIVISION SLASH
223C; 223D # TILDE OPERATOR
223D; 223C # REVERSED TILDE
2243; 22CD # ASYMPTOTICALLY EQUAL TO
2252; 2253 # APPROXIMATELY EQUAL TO OR THE IMAGE OF
2253; 2252 # IMAGE OF OR APPROXIMATELY EQUAL TO
2254; 2255 # COLON EQUALS
2255; 2254 # EQUALS COLON
2264; 2265 # LESS-THAN OR EQUAL TO
2265; 2264 # GREATER-THAN OR EQUAL TO
2266; 2267 # LESS-THAN OVER EQUAL TO
2267; 2266 # GREATER-THAN OVER EQUAL TO
2268; 2269 # [BEST FIT] LESS-THAN BUT NOT EQUAL TO
2269; 2268 # [BEST FIT] GREATER-THAN BUT NOT EQUAL TO
226A; 226B # MUCH LESS-THAN
226B; 226A # MUCH GREATER-THAN
226E; 226F # [BEST FIT] NOT LESS-THAN
226F; 226E # [BEST FIT] NOT GREATER-THAN
2270; 2271 # [BEST FIT] NEITHER LESS-THAN NOR EQUAL TO
2271; 2270 # [BEST FIT] NEITHER GREATER-THAN NOR EQUAL TO
2272; 2273 # [BEST FIT] LESS-THAN OR EQUIVALENT TO
2273; 2272 # [BEST FIT] GREATER-THAN OR EQUIVALENT TO
2274; 2275 # [BEST FIT] NEITHER LESS-THAN NOR EQUIVALENT TO
2275; 2274 # [BEST FIT] NEITHER GREATER-THAN NOR EQUIVALENT TO
2276; 2277 # LESS-THAN OR GREATER-THAN
2277; 2276 # GREATER-THAN OR LESS-THAN
2278; 2279 # NEITHER LESS-THAN NOR GREATER-THAN
2279; 2278 # NEITHER GREATER-THAN NOR LESS-THAN
227A; 227B # PRECEDES
227B; 227A # SUCCEEDS
227C; 227D # PRECEDES OR EQUAL TO
227D; 227C # SUCCEEDS OR EQUAL TO
227E; 227F # [BEST FIT] PRECEDES OR EQUIVALENT TO
227F; 227E # [BEST FIT] SUCCEEDS OR EQUIVALENT TO
2280; 2281 # [BEST FIT] DOES NOT PRECEDE
2281; 2280 # [BEST FIT] DOES NOT SUCCEED
2282; 2283 # SUBSET OF
2283; 2282 # SUPERSET OF
2284; 2285 # [BEST FIT] NOT A SUBSET OF
2285; 2284 # [BEST FIT] NOT A SUPERSET OF
2286; 2287 # SUBSET OF OR EQUAL TO
2287; 2286 # SUPERSET OF OR EQUAL TO
2288; 2289 # [BEST FIT] NEITHER A SUBSET OF NOR EQUAL TO
2289; 2288 # [BEST FIT] NEITHER A SUPERSET OF NOR EQUAL TO
228A; 228B # [BEST FIT] SUBSET OF WITH NOT EQUAL TO
228B; 228A # [BEST FIT] SUPERSET OF WITH NOT EQUAL TO
228F; 2290 # SQUARE IMAGE OF
2290; 228F # SQUARE ORIGINAL OF
2291; 2292 # SQUARE IMAGE OF OR EQUAL TO
2292; 2291 # SQUARE ORIGINAL OF OR EQUAL TO
2298; 29B8 # CIRCLED DIVISION SLASH
22A2; 22A3 # RIGHT TACK
22A3; 22A2 # LEFT TACK
22A6; 2ADE # ASSERTION
22A8; 2AE4 # TRUE
22A9; 2AE3 # FORCES
22AB; 2AE5 # DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE
22B0; 22B1 # PRECEDES UNDER RELATION
22B1; 22B0 # SUCCEEDS UNDER RELATION
22B2; 22B3 # NORMAL SUBGROUP OF
22B3; 22B2 # CONTAINS AS NORMAL SUBGROUP
22B4; 22B5 # NORMAL SUBGROUP OF OR EQUAL TO
22B5; 22B4 # CONTAINS AS NORMAL SUBGROUP OR EQUAL TO
22B6; 22B7 # ORIGINAL OF
22B7; 22B6 # IMAGE OF
22C9; 22CA # LEFT NORMAL FACTOR SEMIDIRECT PRODUCT
22CA; 22C9 # RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT
22CB; 22CC # LEFT SEMIDIRECT PRODUCT
22CC; 22CB # RIGHT SEMIDIRECT PRODUCT
22CD; 2243 # REVERSED TILDE EQUALS
22D0; 22D1 # DOUBLE SUBSET
22D1; 22D0 # DOUBLE SUPERSET
22D6; 22D7 # LESS-THAN WITH DOT
22D7; 22D6 # GREATER-THAN WITH DOT
22D8; 22D9 # VERY MUCH LESS-THAN
22D9; 22D8 # VERY MUCH GREATER-THAN
22DA; 22DB # LESS-THAN EQUAL TO OR GREATER-THAN
22DB; 22DA # GREATER-THAN EQUAL TO OR LESS-THAN
22DC; 22DD # EQUAL TO OR LESS-THAN
22DD; 22DC # EQUAL TO OR GREATER-THAN
22DE; 22DF # EQUAL TO OR PRECEDES
22DF; 22DE # EQUAL TO OR SUCCEEDS
22E0; 22E1 # [BEST FIT] DOES NOT PRECEDE OR EQUAL
22E1; 22E0 # [BEST FIT] DOES NOT SUCCEED OR EQUAL
22E2; 22E3 # [BEST FIT] NOT SQUARE IMAGE OF OR EQUAL TO
22E3; 22E2 # [BEST FIT] NOT SQUARE ORIGINAL OF OR EQUAL TO
22E4; 22E5 # [BEST FIT] SQUARE IMAGE OF OR NOT EQUAL TO
22E5; 22E4 # [BEST FIT] SQUARE ORIGINAL OF OR NOT EQUAL TO
22E6; 22E7 # [BEST FIT] LESS-THAN BUT NOT EQUIVALENT TO
22E7; 22E6 # [BEST FIT] GREATER-THAN BUT NOT EQUIVALENT TO
22E8; 22E9 # [BEST FIT] PRECEDES BUT NOT EQUIVALENT TO
22E9; 22E8 # [BEST FIT] SUCCEEDS BUT NOT EQUIVALENT TO
22EA; 22EB # [BEST FIT] NOT NORMAL SUBGROUP OF
22EB; 22EA # [BEST FIT] DOES NOT CONTAIN AS NORMAL SUBGROUP
22EC; 22ED # [BEST FIT] NOT NORMAL SUBGROUP OF OR EQUAL TO
22ED; 22EC # [BEST FIT] DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL
22F0; 22F1 # UP RIGHT DIAGONAL ELLIPSIS
22F1; 22F0 # DOWN RIGHT DIAGONAL ELLIPSIS
22F2; 22FA # ELEMENT OF WITH LONG HORIZONTAL STROKE
22F3; 22FB # ELEMENT OF WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22F4; 22FC # SMALL ELEMENT OF WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22F6; 22FD # ELEMENT OF WITH OVERBAR
22F7; 22FE # SMALL ELEMENT OF WITH OVERBAR
22FA; 22F2 # CONTAINS WITH LONG HORIZONTAL STROKE
22FB; 22F3 # CONTAINS WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22FC; 22F4 # SMALL CONTAINS WITH VERTICAL BAR AT END OF HORIZONTAL STROKE
22FD; 22F6 # CONTAINS WITH OVERBAR
22FE; 22F7 # SMALL CONTAINS WITH OVERBAR
2308; 2309 # LEFT CEILING
2309; 2308 # RIGHT CEILING
230A; 230B # LEFT FLOOR
230B; 230A # RIGHT FLOOR
2329; 232A # LEFT-POINTING ANGLE BRACKET
232A; 2329 # RIGHT-POINTING ANGLE BRACKET
2768; 2769 # MEDIUM LEFT PARENTHESIS ORNAMENT
2769; 2768 # MEDIUM RIGHT PARENTHESIS ORNAMENT
276A; 276B # MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT
276B; 276A # MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT
276C; 276D # MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT
276D; 276C # MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT
276E; 276F # HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT
276F; 276E # HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
2770; 2771 # HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT
2771; 2770 # HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT
2772; 2773 # LIGHT LEFT TORTOISE SHELL BRACKET
2773; 2772 # LIGHT RIGHT TORTOISE SHELL BRACKET
2774; 2775 # MEDIUM LEFT CURLY BRACKET ORNAMENT
2775; 2774 # MEDIUM RIGHT CURLY BRACKET ORNAMENT
27C3; 27C4 # OPEN SUBSET
27C4; 27C3 # OPEN SUPERSET
27C5; 27C6 # LEFT S-SHAPED BAG DELIMITER
27C6; 27C5 # RIGHT S-SHAPED BAG DELIMITER
27D5; 27D6 # LEFT OUTER JOIN
27D6; 27D5 # RIGHT OUTER JOIN
27DD; 27DE # LONG RIGHT TACK
27DE; 27DD # LONG LEFT TACK
27E2; 27E3 # WHITE CONCAVE-SIDED DIAMOND WITH LEFTWARDS TICK
27E3; 27E2 # WHITE CONCAVE-SIDED DIAMOND WITH RIGHTWARDS TICK
27E4; 27E5 # WHITE SQUARE WITH LEFTWARDS TICK
27E5; 27E4 # WHITE SQUARE WITH RIGHTWARDS TICK
27E6; 27E7 # MATHEMATICAL LEFT WHITE SQUARE BRACKET
27E7; 27E6 # MATHEMATICAL RIGHT WHITE SQUARE BRACKET
27E8; 27E9 # MATHEMATICAL LEFT ANGLE BRACKET
27E9; 27E8 # MATHEMATICAL RIGHT ANGLE BRACKET
27EA; 27EB # MATHEMATICAL LEFT DOUBLE ANGLE BRACKET
27EB; 27EA # MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET
2983; 2984 # LEFT WHITE CURLY BRACKET
2984; 2983 # RIGHT WHITE CURLY BRACKET
2985; 2986 # LEFT WHITE PARENTHESIS
2986; 2985 # RIGHT WHITE PARENTHESIS
2987; 2988 # Z NOTATION LEFT IMAGE BRACKET
2988; 2987 # Z NOTATION RIGHT IMAGE BRACKET
2989; 298A # Z NOTATION LEFT BINDING BRACKET
298A; 2989 # Z NOTATION RIGHT BINDING BRACKET
298B; 298C # LEFT SQUARE BRACKET WITH UNDERBAR
298C; 298B # RIGHT SQUARE BRACKET WITH UNDERBAR
298D; 2990 # LEFT SQUARE BRACKET WITH TICK IN TOP CORNER
298E; 298F # RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
298F; 298E # LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
2990; 298D # RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER
2991; 2992 # LEFT ANGLE BRACKET WITH DOT
2992; 2991 # RIGHT ANGLE BRACKET WITH DOT
2993; 2994 # LEFT ARC LESS-THAN BRACKET
2994; 2993 # RIGHT ARC GREATER-THAN BRACKET
2995; 2996 # DOUBLE LEFT ARC GREATER-THAN BRACKET
2996; 2995 # DOUBLE RIGHT ARC LESS-THAN BRACKET
2997; 2998 # LEFT BLACK TORTOISE SHELL BRACKET
2998; 2997 # RIGHT BLACK TORTOISE SHELL BRACKET
29B8; 2298 # CIRCLED REVERSE SOLIDUS
29C0; 29C1 # CIRCLED LESS-THAN
29C1; 29C0 # CIRCLED GREATER-THAN
29C4; 29C5 # SQUARED RISING DIAGONAL SLASH
29C5; 29C4 # SQUARED FALLING DIAGONAL SLASH
29CF; 29D0 # LEFT TRIANGLE BESIDE VERTICAL BAR
29D0; 29CF # VERTICAL BAR BESIDE RIGHT TRIANGLE
29D1; 29D2 # BOWTIE WITH LEFT HALF BLACK
29D2; 29D1 # BOWTIE WITH RIGHT HALF BLACK
29D4; 29D5 # TIMES WITH LEFT HALF BLACK
29D5; 29D4 # TIMES WITH RIGHT HALF BLACK
29D8; 29D9 # LEFT WIGGLY FENCE
29D9; 29D8 # RIGHT WIGGLY FENCE
29DA; 29DB # LEFT DOUBLE WIGGLY FENCE
29DB; 29DA # RIGHT DOUBLE WIGGLY FENCE
29F5; 2215 # REVERSE SOLIDUS OPERATOR
29F8; 29F9 # BIG SOLIDUS
29F9; 29F8 # BIG REVERSE SOLIDUS
29FC; 29FD # LEFT-POINTING CURVED ANGLE BRACKET
29FD; 29FC # RIGHT-POINTING CURVED ANGLE BRACKET
2A2B; 2A2C # MINUS SIGN WITH FALLING DOTS
2A2C; 2A2B # MINUS SIGN WITH RISING DOTS
2A2D; 2A2E # PLUS SIGN IN LEFT HALF CIRCLE
2A2E; 2A2D # PLUS SIGN IN RIGHT HALF CIRCLE
2A34; 2A35 # MULTIPLICATION SIGN IN LEFT HALF CIRCLE
2A35; 2A34 # MULTIPLICATION SIGN IN RIGHT HALF CIRCLE
2A3C; 2A3D # INTERIOR PRODUCT
2A3D; 2A3C # RIGHTHAND INTERIOR PRODUCT
2A64; 2A65 # Z NOTATION DOMAIN ANTIRESTRICTION
2A65; 2A64 # Z NOTATION RANGE ANTIRESTRICTION
2A79; 2A7A # LESS-THAN WITH CIRCLE INSIDE
2A7A; 2A79 # GREATER-THAN WITH CIRCLE INSIDE
2A7D; 2A7E # LESS-THAN OR SLANTED EQUAL TO
2A7E; 2A7D # GREATER-THAN OR SLANTED EQUAL TO
2A7F; 2A80 # LESS-THAN OR SLANTED EQUAL TO WITH DOT INSIDE
2A80; 2A7F # GREATER-THAN OR SLANTED EQUAL TO WITH DOT INSIDE
2A81; 2A82 # LESS-THAN OR SLANTED EQUAL TO WITH DOT ABOVE
2A82; 2A81 # GREATER-THAN OR SLANTED EQUAL TO WITH DOT ABOVE
2A83; 2A84 # LESS-THAN OR SLANTED EQUAL TO WITH DOT ABOVE RIGHT
2A84; 2A83 # GREATER-THAN OR SLANTED EQUAL TO WITH DOT ABOVE LEFT
2A8B; 2A8C # LESS-THAN ABOVE DOUBLE-LINE EQUAL ABOVE GREATER-THAN
2A8C; 2A8B # GREATER-THAN ABOVE DOUBLE-LINE EQUAL ABOVE LESS-THAN
2A91; 2A92 # LESS-THAN ABOVE GREATER-THAN ABOVE DOUBLE-LINE EQUAL
2A92; 2A91 # GREATER-THAN ABOVE LESS-THAN ABOVE DOUBLE-LINE EQUAL
2A93; 2A94 # LESS-THAN ABOVE SLANTED EQUAL ABOVE GREATER-THAN ABOVE SLANTED EQUAL
2A94; 2A93 # GREATER-THAN ABOVE SLANTED EQUAL ABOVE LESS-THAN ABOVE SLANTED EQUAL
2A95; 2A96 # SLANTED EQUAL TO OR LESS-THAN
2A96; 2A95 # SLANTED EQUAL TO OR GREATER-THAN
2A97; 2A98 # SLANTED EQUAL TO OR LESS-THAN WITH DOT INSIDE
2A98; 2A97 # SLANTED EQUAL TO OR GREATER-THAN WITH DOT INSIDE
2A99; 2A9A # DOUBLE-LINE EQUAL TO OR LESS-THAN
2A9A; 2A99 # DOUBLE-LINE EQUAL TO OR GREATER-THAN
2A9B; 2A9C # DOUBLE-LINE SLANTED EQUAL TO OR LESS-THAN
2A9C; 2A9B # DOUBLE-LINE SLANTED EQUAL TO OR GREATER-THAN
2AA1; 2AA2 # DOUBLE NESTED LESS-THAN
2AA2; 2AA1 # DOUBLE NESTED GREATER-THAN
2AA6; 2AA7 # LESS-THAN CLOSED BY CURVE
2AA7; 2AA6 # GREATER-THAN CLOSED BY CURVE
2AA8; 2AA9 # LESS-THAN CLOSED BY CURVE ABOVE SLANTED EQUAL
2AA9; 2AA8 # GREATER-THAN CLOSED BY CURVE ABOVE SLANTED EQUAL
2AAA; 2AAB # SMALLER THAN
2AAB; 2AAA # LARGER THAN
2AAC; 2AAD # SMALLER THAN OR EQUAL TO
2AAD; 2AAC # LARGER THAN OR EQUAL TO
2AAF; 2AB0 # PRECEDES ABOVE SINGLE-LINE EQUALS SIGN
2AB0; 2AAF # SUCCEEDS ABOVE SINGLE-LINE EQUALS SIGN
2AB3; 2AB4 # PRECEDES ABOVE EQUALS SIGN
2AB4; 2AB3 # SUCCEEDS ABOVE EQUALS SIGN
2ABB; 2ABC # DOUBLE PRECEDES
2ABC; 2ABB # DOUBLE SUCCEEDS
2ABD; 2ABE # SUBSET WITH DOT
2ABE; 2ABD # SUPERSET WITH DOT
2ABF; 2AC0 # SUBSET WITH PLUS SIGN BELOW
2AC0; 2ABF # SUPERSET WITH PLUS SIGN BELOW
2AC1; 2AC2 # SUBSET WITH MULTIPLICATION SIGN BELOW
2AC2; 2AC1 # SUPERSET WITH MULTIPLICATION SIGN BELOW
2AC3; 2AC4 # SUBSET OF OR EQUAL TO WITH DOT ABOVE
2AC4; 2AC3 # SUPERSET OF OR EQUAL TO WITH DOT ABOVE
2AC5; 2AC6 # SUBSET OF ABOVE EQUALS SIGN
2AC6; 2AC5 # SUPERSET OF ABOVE EQUALS SIGN
2ACD; 2ACE # SQUARE LEFT OPEN BOX OPERATOR
2ACE; 2ACD # SQUARE RIGHT OPEN BOX OPERATOR
2ACF; 2AD0 # CLOSED SUBSET
2AD0; 2ACF # CLOSED SUPERSET
2AD1; 2AD2 # CLOSED SUBSET OR EQUAL TO
2AD2; 2AD1 # CLOSED SUPERSET OR EQUAL TO
2AD3; 2AD4 # SUBSET ABOVE SUPERSET
2AD4; 2AD3 # SUPERSET ABOVE SUBSET
2AD5; 2AD6 # SUBSET ABOVE SUBSET
2AD6; 2AD5 # SUPERSET ABOVE SUPERSET
2ADE; 22A6 # SHORT LEFT TACK
2AE3; 22A9 # DOUBLE VERTICAL BAR LEFT TURNSTILE
2AE4; 22A8 # VERTICAL BAR DOUBLE LEFT TURNSTILE
2AE5; 22AB # DOUBLE VERTICAL BAR DOUBLE LEFT TURNSTILE
2AEC; 2AED # DOUBLE STROKE NOT SIGN
2AED; 2AEC # REVERSED DOUBLE STROKE NOT SIGN
2AF7; 2AF8 # TRIPLE NESTED LESS-THAN
2AF8; 2AF7 # TRIPLE NESTED GREATER-THAN
2AF9; 2AFA # DOUBLE-LINE SLANTED LESS-THAN OR EQUAL TO
2AFA; 2AF9 # DOUBLE-LINE SLANTED GREATER-THAN OR EQUAL TO
2E02; 2E03 # LEFT SUBSTITUTION BRACKET
2E03; 2E02 # RIGHT SUBSTITUTION BRACKET
2E04; 2E05 # LEFT DOTTED SUBSTITUTION BRACKET
2E05; 2E04 # RIGHT DOTTED SUBSTITUTION BRACKET
2E09; 2E0A # LEFT TRANSPOSITION BRACKET
2E0A; 2E09 # RIGHT TRANSPOSITION BRACKET
2E0C; 2E0D # LEFT RAISED OMISSION BRACKET
2E0D; 2E0C # RIGHT RAISED OMISSION BRACKET
2E1C; 2E1D # LEFT LOW PARAPHRASE BRACKET
2E1D; 2E1C # RIGHT LOW PARAPHRASE BRACKET
3008; 3009 # LEFT ANGLE BRACKET
3009; 3008 # RIGHT ANGLE BRACKET
300A; 300B # LEFT DOUBLE ANGLE BRACKET
300B; 300A # RIGHT DOUBLE ANGLE BRACKET
300C; 300D # [BEST FIT] LEFT CORNER BRACKET
300D; 300C # [BEST FIT] RIGHT CORNER BRACKET
300E; 300F # [BEST FIT] LEFT WHITE CORNER BRACKET
300F; 300E # [BEST FIT] RIGHT WHITE CORNER BRACKET
3010; 3011 # LEFT BLACK LENTICULAR BRACKET
3011; 3010 # RIGHT BLACK LENTICULAR BRACKET
3014; 3015 # LEFT TORTOISE SHELL BRACKET
3015; 3014 # RIGHT TORTOISE SHELL BRACKET
3016; 3017 # LEFT WHITE LENTICULAR BRACKET
3017; 3016 # RIGHT WHITE LENTICULAR BRACKET
3018; 3019 # LEFT WHITE TORTOISE SHELL BRACKET
3019; 3018 # RIGHT WHITE TORTOISE SHELL BRACKET
301A; 301B # LEFT WHITE SQUARE BRACKET
301B; 301A # RIGHT WHITE SQUARE BRACKET
301D; 301E # REVERSED DOUBLE PRIME QUOTATION MARK
301E; 301D # DOUBLE PRIME QUOTATION MARK
FE59; FE5A # SMALL LEFT PARENTHESIS
FE5A; FE59 # SMALL RIGHT PARENTHESIS
FE5B; FE5C # SMALL LEFT CURLY BRACKET
FE5C; FE5B # SMALL RIGHT CURLY BRACKET
FE5D; FE5E # SMALL LEFT TORTOISE SHELL BRACKET
FE5E; FE5D # SMALL RIGHT TORTOISE SHELL BRACKET
FE64; FE65 # SMALL LESS-THAN SIGN
FE65; FE64 # SMALL GREATER-THAN SIGN
FF08; FF09 # FULLWIDTH LEFT PARENTHESIS
FF09; FF08 # FULLWIDTH RIGHT PARENTHESIS
FF1C; FF1E # FULLWIDTH LESS-THAN SIGN
FF1E; FF1C # FULLWIDTH GREATER-THAN SIGN
FF3B; FF3D # FULLWIDTH LEFT SQUARE BRACKET
FF3D; FF3B # FULLWIDTH RIGHT SQUARE BRACKET
FF5B; FF5D # FULLWIDTH LEFT CURLY BRACKET
FF5D; FF5B # FULLWIDTH RIGHT CURLY BRACKET
FF5F; FF60 # FULLWIDTH LEFT WHITE PARENTHESIS
FF60; FF5F # FULLWIDTH RIGHT WHITE PARENTHESIS
FF62; FF63 # [BEST FIT] HALFWIDTH LEFT CORNER BRACKET
FF63; FF62 # [BEST FIT] HALFWIDTH RIGHT CORNER BRACKET
# The following characters have no appropriate mirroring character.
# For these characters it is up to the rendering system
# to provide mirrored glyphs.
# 201A; SINGLE LOW-9 QUOTATION MARK
# 201B; SINGLE HIGH-REVERSED-9 QUOTATION MARK
# 201E; DOUBLE LOW-9 QUOTATION MARK
# 201F; DOUBLE HIGH-REVERSED-9 QUOTATION MARK
# 2140; DOUBLE-STRUCK N-ARY SUMMATION
# 2201; COMPLEMENT
# 2202; PARTIAL DIFFERENTIAL
# 2203; THERE EXISTS
# 2204; THERE DOES NOT EXIST
# 2211; N-ARY SUMMATION
# 2216; SET MINUS
# 221A; SQUARE ROOT
# 221B; CUBE ROOT
# 221C; FOURTH ROOT
# 221D; PROPORTIONAL TO
# 221F; RIGHT ANGLE
# 2220; ANGLE
# 2221; MEASURED ANGLE
# 2222; SPHERICAL ANGLE
# 2224; DOES NOT DIVIDE
# 2226; NOT PARALLEL TO
# 222B; INTEGRAL
# 222C; DOUBLE INTEGRAL
# 222D; TRIPLE INTEGRAL
# 222E; CONTOUR INTEGRAL
# 222F; SURFACE INTEGRAL
# 2230; VOLUME INTEGRAL
# 2231; CLOCKWISE INTEGRAL
# 2232; CLOCKWISE CONTOUR INTEGRAL
# 2233; ANTICLOCKWISE CONTOUR INTEGRAL
# 2239; EXCESS
# 223B; HOMOTHETIC
# 223E; INVERTED LAZY S
# 223F; SINE WAVE
# 2240; WREATH PRODUCT
# 2241; NOT TILDE
# 2242; MINUS TILDE
# 2244; NOT ASYMPTOTICALLY EQUAL TO
# 2245; APPROXIMATELY EQUAL TO
# 2246; APPROXIMATELY BUT NOT ACTUALLY EQUAL TO
# 2247; NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO
# 2248; ALMOST EQUAL TO
# 2249; NOT ALMOST EQUAL TO
# 224A; ALMOST EQUAL OR EQUAL TO
# 224B; TRIPLE TILDE
# 224C; ALL EQUAL TO
# 225F; QUESTIONED EQUAL TO
# 2260; NOT EQUAL TO
# 2262; NOT IDENTICAL TO
# 228C; MULTISET
# 22A7; MODELS
# 22AA; TRIPLE VERTICAL BAR RIGHT TURNSTILE
# 22AC; DOES NOT PROVE
# 22AD; NOT TRUE
# 22AE; DOES NOT FORCE
# 22AF; NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE
# 22B8; MULTIMAP
# 22BE; RIGHT ANGLE WITH ARC
# 22BF; RIGHT TRIANGLE
# 22F5; ELEMENT OF WITH DOT ABOVE
# 22F8; ELEMENT OF WITH UNDERBAR
# 22F9; ELEMENT OF WITH TWO HORIZONTAL STROKES
# 22FF; Z NOTATION BAG MEMBERSHIP
# 2320; TOP HALF INTEGRAL
# 2321; BOTTOM HALF INTEGRAL
# 27C0; THREE DIMENSIONAL ANGLE
# 27D3; LOWER RIGHT CORNER WITH DOT
# 27D4; UPPER LEFT CORNER WITH DOT
# 27DC; LEFT MULTIMAP
# 299B; MEASURED ANGLE OPENING LEFT
# 299C; RIGHT ANGLE VARIANT WITH SQUARE
# 299D; MEASURED RIGHT ANGLE WITH DOT
# 299E; ANGLE WITH S INSIDE
# 299F; ACUTE ANGLE
# 29A0; SPHERICAL ANGLE OPENING LEFT
# 29A1; SPHERICAL ANGLE OPENING UP
# 29A2; TURNED ANGLE
# 29A3; REVERSED ANGLE
# 29A4; ANGLE WITH UNDERBAR
# 29A5; REVERSED ANGLE WITH UNDERBAR
# 29A6; OBLIQUE ANGLE OPENING UP
# 29A7; OBLIQUE ANGLE OPENING DOWN
# 29A8; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING UP AND RIGHT
# 29A9; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING UP AND LEFT
# 29AA; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING DOWN AND RIGHT
# 29AB; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING DOWN AND LEFT
# 29AC; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING RIGHT AND UP
# 29AD; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING LEFT AND UP
# 29AE; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING RIGHT AND DOWN
# 29AF; MEASURED ANGLE WITH OPEN ARM ENDING IN ARROW POINTING LEFT AND DOWN
# 29C2; CIRCLE WITH SMALL CIRCLE TO THE RIGHT
# 29C3; CIRCLE WITH TWO HORIZONTAL STROKES TO THE RIGHT
# 29C9; TWO JOINED SQUARES
# 29CE; RIGHT TRIANGLE ABOVE LEFT TRIANGLE
# 29DC; INCOMPLETE INFINITY
# 29E1; INCREASES AS
# 29E3; EQUALS SIGN AND SLANTED PARALLEL
# 29E4; EQUALS SIGN AND SLANTED PARALLEL WITH TILDE ABOVE
# 29E5; IDENTICAL TO AND SLANTED PARALLEL
# 29E8; DOWN-POINTING TRIANGLE WITH LEFT HALF BLACK
# 29E9; DOWN-POINTING TRIANGLE WITH RIGHT HALF BLACK
# 29F4; RULE-DELAYED
# 29F6; SOLIDUS WITH OVERBAR
# 29F7; REVERSE SOLIDUS WITH HORIZONTAL STROKE
# 2A0A; MODULO TWO SUM
# 2A0B; SUMMATION WITH INTEGRAL
# 2A0C; QUADRUPLE INTEGRAL OPERATOR
# 2A0D; FINITE PART INTEGRAL
# 2A0E; INTEGRAL WITH DOUBLE STROKE
# 2A0F; INTEGRAL AVERAGE WITH SLASH
# 2A10; CIRCULATION FUNCTION
# 2A11; ANTICLOCKWISE INTEGRATION
# 2A12; LINE INTEGRATION WITH RECTANGULAR PATH AROUND POLE
# 2A13; LINE INTEGRATION WITH SEMICIRCULAR PATH AROUND POLE
# 2A14; LINE INTEGRATION NOT INCLUDING THE POLE
# 2A15; INTEGRAL AROUND A POINT OPERATOR
# 2A16; QUATERNION INTEGRAL OPERATOR
# 2A17; INTEGRAL WITH LEFTWARDS ARROW WITH HOOK
# 2A18; INTEGRAL WITH TIMES SIGN
# 2A19; INTEGRAL WITH INTERSECTION
# 2A1A; INTEGRAL WITH UNION
# 2A1B; INTEGRAL WITH OVERBAR
# 2A1C; INTEGRAL WITH UNDERBAR
# 2A1E; LARGE LEFT TRIANGLE OPERATOR
# 2A1F; Z NOTATION SCHEMA COMPOSITION
# 2A20; Z NOTATION SCHEMA PIPING
# 2A21; Z NOTATION SCHEMA PROJECTION
# 2A24; PLUS SIGN WITH TILDE ABOVE
# 2A26; PLUS SIGN WITH TILDE BELOW
# 2A29; MINUS SIGN WITH COMMA ABOVE
# 2A3E; Z NOTATION RELATIONAL COMPOSITION
# 2A57; SLOPING LARGE OR
# 2A58; SLOPING LARGE AND
# 2A6A; TILDE OPERATOR WITH DOT ABOVE
# 2A6B; TILDE OPERATOR WITH RISING DOTS
# 2A6C; SIMILAR MINUS SIMILAR
# 2A6D; CONGRUENT WITH DOT ABOVE
# 2A6F; ALMOST EQUAL TO WITH CIRCUMFLEX ACCENT
# 2A70; APPROXIMATELY EQUAL OR EQUAL TO
# 2A73; EQUALS SIGN ABOVE TILDE OPERATOR
# 2A74; DOUBLE COLON EQUAL
# 2A7B; LESS-THAN WITH QUESTION MARK ABOVE
# 2A7C; GREATER-THAN WITH QUESTION MARK ABOVE
# 2A85; LESS-THAN OR APPROXIMATE
# 2A86; GREATER-THAN OR APPROXIMATE
# 2A87; LESS-THAN AND SINGLE-LINE NOT EQUAL TO
# 2A88; GREATER-THAN AND SINGLE-LINE NOT EQUAL TO
# 2A89; LESS-THAN AND NOT APPROXIMATE
# 2A8A; GREATER-THAN AND NOT APPROXIMATE
# 2A8D; LESS-THAN ABOVE SIMILAR OR EQUAL
# 2A8E; GREATER-THAN ABOVE SIMILAR OR EQUAL
# 2A8F; LESS-THAN ABOVE SIMILAR ABOVE GREATER-THAN
# 2A90; GREATER-THAN ABOVE SIMILAR ABOVE LESS-THAN
# 2A9D; SIMILAR OR LESS-THAN
# 2A9E; SIMILAR OR GREATER-THAN
# 2A9F; SIMILAR ABOVE LESS-THAN ABOVE EQUALS SIGN
# 2AA0; SIMILAR ABOVE GREATER-THAN ABOVE EQUALS SIGN
# 2AA3; DOUBLE NESTED LESS-THAN WITH UNDERBAR
# 2AB1; PRECEDES ABOVE SINGLE-LINE NOT EQUAL TO
# 2AB2; SUCCEEDS ABOVE SINGLE-LINE NOT EQUAL TO
# 2AB5; PRECEDES ABOVE NOT EQUAL TO
# 2AB6; SUCCEEDS ABOVE NOT EQUAL TO
# 2AB7; PRECEDES ABOVE ALMOST EQUAL TO
# 2AB8; SUCCEEDS ABOVE ALMOST EQUAL TO
# 2AB9; PRECEDES ABOVE NOT ALMOST EQUAL TO
# 2ABA; SUCCEEDS ABOVE NOT ALMOST EQUAL TO
# 2AC7; SUBSET OF ABOVE TILDE OPERATOR
# 2AC8; SUPERSET OF ABOVE TILDE OPERATOR
# 2AC9; SUBSET OF ABOVE ALMOST EQUAL TO
# 2ACA; SUPERSET OF ABOVE ALMOST EQUAL TO
# 2ACB; SUBSET OF ABOVE NOT EQUAL TO
# 2ACC; SUPERSET OF ABOVE NOT EQUAL TO
# 2ADC; FORKING
# 2AE2; VERTICAL BAR TRIPLE RIGHT TURNSTILE
# 2AE6; LONG DASH FROM LEFT MEMBER OF DOUBLE VERTICAL
# 2AEE; DOES NOT DIVIDE WITH REVERSED NEGATION SLASH
# 2AF3; PARALLEL WITH TILDE OPERATOR
# 2AFB; TRIPLE SOLIDUS BINARY RELATION
# 2AFD; DOUBLE SOLIDUS OPERATOR
# 301F; LOW DOUBLE PRIME QUOTATION MARK
# 1D6DB; MATHEMATICAL BOLD PARTIAL DIFFERENTIAL
# 1D715; MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL
# 1D74F; MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL
# 1D789; MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL
# 1D7C3; MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
# EOF

View File

@ -0,0 +1,185 @@
# Blocks-5.0.0.txt
# Date: 2006-02-15, 15:40:00 [KW]
#
# Unicode Character Database
# Copyright (c) 1991-2006 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
#
# Note: The casing of block names is not normative.
# For example, "Basic Latin" and "BASIC LATIN" are equivalent.
#
# Format:
# Start Code..End Code; Block Name
# ================================================
# Note: When comparing block names, casing, whitespace, hyphens,
# and underbars are ignored.
# For example, "Latin Extended-A" and "latin extended a" are equivalent.
# For more information on the comparison of property values,
# see UCD.html.
#
# All code points not explicitly listed for Block
# have the value No_Block.
# Property: Block
#
# @missing: 0000..10FFFF; No_Block
0000..007F; Basic Latin
0080..00FF; Latin-1 Supplement
0100..017F; Latin Extended-A
0180..024F; Latin Extended-B
0250..02AF; IPA Extensions
02B0..02FF; Spacing Modifier Letters
0300..036F; Combining Diacritical Marks
0370..03FF; Greek and Coptic
0400..04FF; Cyrillic
0500..052F; Cyrillic Supplement
0530..058F; Armenian
0590..05FF; Hebrew
0600..06FF; Arabic
0700..074F; Syriac
0750..077F; Arabic Supplement
0780..07BF; Thaana
07C0..07FF; NKo
0900..097F; Devanagari
0980..09FF; Bengali
0A00..0A7F; Gurmukhi
0A80..0AFF; Gujarati
0B00..0B7F; Oriya
0B80..0BFF; Tamil
0C00..0C7F; Telugu
0C80..0CFF; Kannada
0D00..0D7F; Malayalam
0D80..0DFF; Sinhala
0E00..0E7F; Thai
0E80..0EFF; Lao
0F00..0FFF; Tibetan
1000..109F; Myanmar
10A0..10FF; Georgian
1100..11FF; Hangul Jamo
1200..137F; Ethiopic
1380..139F; Ethiopic Supplement
13A0..13FF; Cherokee
1400..167F; Unified Canadian Aboriginal Syllabics
1680..169F; Ogham
16A0..16FF; Runic
1700..171F; Tagalog
1720..173F; Hanunoo
1740..175F; Buhid
1760..177F; Tagbanwa
1780..17FF; Khmer
1800..18AF; Mongolian
1900..194F; Limbu
1950..197F; Tai Le
1980..19DF; New Tai Lue
19E0..19FF; Khmer Symbols
1A00..1A1F; Buginese
1B00..1B7F; Balinese
1D00..1D7F; Phonetic Extensions
1D80..1DBF; Phonetic Extensions Supplement
1DC0..1DFF; Combining Diacritical Marks Supplement
1E00..1EFF; Latin Extended Additional
1F00..1FFF; Greek Extended
2000..206F; General Punctuation
2070..209F; Superscripts and Subscripts
20A0..20CF; Currency Symbols
20D0..20FF; Combining Diacritical Marks for Symbols
2100..214F; Letterlike Symbols
2150..218F; Number Forms
2190..21FF; Arrows
2200..22FF; Mathematical Operators
2300..23FF; Miscellaneous Technical
2400..243F; Control Pictures
2440..245F; Optical Character Recognition
2460..24FF; Enclosed Alphanumerics
2500..257F; Box Drawing
2580..259F; Block Elements
25A0..25FF; Geometric Shapes
2600..26FF; Miscellaneous Symbols
2700..27BF; Dingbats
27C0..27EF; Miscellaneous Mathematical Symbols-A
27F0..27FF; Supplemental Arrows-A
2800..28FF; Braille Patterns
2900..297F; Supplemental Arrows-B
2980..29FF; Miscellaneous Mathematical Symbols-B
2A00..2AFF; Supplemental Mathematical Operators
2B00..2BFF; Miscellaneous Symbols and Arrows
2C00..2C5F; Glagolitic
2C60..2C7F; Latin Extended-C
2C80..2CFF; Coptic
2D00..2D2F; Georgian Supplement
2D30..2D7F; Tifinagh
2D80..2DDF; Ethiopic Extended
2E00..2E7F; Supplemental Punctuation
2E80..2EFF; CJK Radicals Supplement
2F00..2FDF; Kangxi Radicals
2FF0..2FFF; Ideographic Description Characters
3000..303F; CJK Symbols and Punctuation
3040..309F; Hiragana
30A0..30FF; Katakana
3100..312F; Bopomofo
3130..318F; Hangul Compatibility Jamo
3190..319F; Kanbun
31A0..31BF; Bopomofo Extended
31C0..31EF; CJK Strokes
31F0..31FF; Katakana Phonetic Extensions
3200..32FF; Enclosed CJK Letters and Months
3300..33FF; CJK Compatibility
3400..4DBF; CJK Unified Ideographs Extension A
4DC0..4DFF; Yijing Hexagram Symbols
4E00..9FFF; CJK Unified Ideographs
A000..A48F; Yi Syllables
A490..A4CF; Yi Radicals
A700..A71F; Modifier Tone Letters
A720..A7FF; Latin Extended-D
A800..A82F; Syloti Nagri
A840..A87F; Phags-pa
AC00..D7AF; Hangul Syllables
D800..DB7F; High Surrogates
DB80..DBFF; High Private Use Surrogates
DC00..DFFF; Low Surrogates
E000..F8FF; Private Use Area
F900..FAFF; CJK Compatibility Ideographs
FB00..FB4F; Alphabetic Presentation Forms
FB50..FDFF; Arabic Presentation Forms-A
FE00..FE0F; Variation Selectors
FE10..FE1F; Vertical Forms
FE20..FE2F; Combining Half Marks
FE30..FE4F; CJK Compatibility Forms
FE50..FE6F; Small Form Variants
FE70..FEFF; Arabic Presentation Forms-B
FF00..FFEF; Halfwidth and Fullwidth Forms
FFF0..FFFF; Specials
10000..1007F; Linear B Syllabary
10080..100FF; Linear B Ideograms
10100..1013F; Aegean Numbers
10140..1018F; Ancient Greek Numbers
10300..1032F; Old Italic
10330..1034F; Gothic
10380..1039F; Ugaritic
103A0..103DF; Old Persian
10400..1044F; Deseret
10450..1047F; Shavian
10480..104AF; Osmanya
10800..1083F; Cypriot Syllabary
10900..1091F; Phoenician
10A00..10A5F; Kharoshthi
12000..123FF; Cuneiform
12400..1247F; Cuneiform Numbers and Punctuation
1D000..1D0FF; Byzantine Musical Symbols
1D100..1D1FF; Musical Symbols
1D200..1D24F; Ancient Greek Musical Notation
1D300..1D35F; Tai Xuan Jing Symbols
1D360..1D37F; Counting Rod Numerals
1D400..1D7FF; Mathematical Alphanumeric Symbols
20000..2A6DF; CJK Unified Ideographs Extension B
2F800..2FA1F; CJK Compatibility Ideographs Supplement
E0000..E007F; Tags
E0100..E01EF; Variation Selectors Supplement
F0000..FFFFF; Supplementary Private Use Area-A
100000..10FFFF; Supplementary Private Use Area-B
# EOF

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,197 @@
# CompositionExclusions-5.0.0.txt
# Date: 2006-05-23, 12:42:00 PST [KW]
#
# This file lists the characters for the Composition Exclusion Table
# defined in UAX #15, Unicode Normalization Forms.
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2006 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# For more information, see
# http://www.unicode.org/unicode/reports/tr15/#Primary Exclusion List Table
#
# For a full derivation of composition exclusions, see the derived property
# Full_Composition_Exclusion in DerivedNormalizationProps.txt
#
# ================================================
# (1) Script Specifics
#
# This list of characters cannot be derived from the UnicodeData.txt file.
# ================================================
0958 # DEVANAGARI LETTER QA
0959 # DEVANAGARI LETTER KHHA
095A # DEVANAGARI LETTER GHHA
095B # DEVANAGARI LETTER ZA
095C # DEVANAGARI LETTER DDDHA
095D # DEVANAGARI LETTER RHA
095E # DEVANAGARI LETTER FA
095F # DEVANAGARI LETTER YYA
09DC # BENGALI LETTER RRA
09DD # BENGALI LETTER RHA
09DF # BENGALI LETTER YYA
0A33 # GURMUKHI LETTER LLA
0A36 # GURMUKHI LETTER SHA
0A59 # GURMUKHI LETTER KHHA
0A5A # GURMUKHI LETTER GHHA
0A5B # GURMUKHI LETTER ZA
0A5E # GURMUKHI LETTER FA
0B5C # ORIYA LETTER RRA
0B5D # ORIYA LETTER RHA
0F43 # TIBETAN LETTER GHA
0F4D # TIBETAN LETTER DDHA
0F52 # TIBETAN LETTER DHA
0F57 # TIBETAN LETTER BHA
0F5C # TIBETAN LETTER DZHA
0F69 # TIBETAN LETTER KSSA
0F76 # TIBETAN VOWEL SIGN VOCALIC R
0F78 # TIBETAN VOWEL SIGN VOCALIC L
0F93 # TIBETAN SUBJOINED LETTER GHA
0F9D # TIBETAN SUBJOINED LETTER DDHA
0FA2 # TIBETAN SUBJOINED LETTER DHA
0FA7 # TIBETAN SUBJOINED LETTER BHA
0FAC # TIBETAN SUBJOINED LETTER DZHA
0FB9 # TIBETAN SUBJOINED LETTER KSSA
FB1D # HEBREW LETTER YOD WITH HIRIQ
FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH
FB2A # HEBREW LETTER SHIN WITH SHIN DOT
FB2B # HEBREW LETTER SHIN WITH SIN DOT
FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT
FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT
FB2E # HEBREW LETTER ALEF WITH PATAH
FB2F # HEBREW LETTER ALEF WITH QAMATS
FB30 # HEBREW LETTER ALEF WITH MAPIQ
FB31 # HEBREW LETTER BET WITH DAGESH
FB32 # HEBREW LETTER GIMEL WITH DAGESH
FB33 # HEBREW LETTER DALET WITH DAGESH
FB34 # HEBREW LETTER HE WITH MAPIQ
FB35 # HEBREW LETTER VAV WITH DAGESH
FB36 # HEBREW LETTER ZAYIN WITH DAGESH
FB38 # HEBREW LETTER TET WITH DAGESH
FB39 # HEBREW LETTER YOD WITH DAGESH
FB3A # HEBREW LETTER FINAL KAF WITH DAGESH
FB3B # HEBREW LETTER KAF WITH DAGESH
FB3C # HEBREW LETTER LAMED WITH DAGESH
FB3E # HEBREW LETTER MEM WITH DAGESH
FB40 # HEBREW LETTER NUN WITH DAGESH
FB41 # HEBREW LETTER SAMEKH WITH DAGESH
FB43 # HEBREW LETTER FINAL PE WITH DAGESH
FB44 # HEBREW LETTER PE WITH DAGESH
FB46 # HEBREW LETTER TSADI WITH DAGESH
FB47 # HEBREW LETTER QOF WITH DAGESH
FB48 # HEBREW LETTER RESH WITH DAGESH
FB49 # HEBREW LETTER SHIN WITH DAGESH
FB4A # HEBREW LETTER TAV WITH DAGESH
FB4B # HEBREW LETTER VAV WITH HOLAM
FB4C # HEBREW LETTER BET WITH RAFE
FB4D # HEBREW LETTER KAF WITH RAFE
FB4E # HEBREW LETTER PE WITH RAFE
# Total code points: 67
# ================================================
# (2) Post Composition Version precomposed characters
#
# These characters cannot be derived solely from the UnicodeData.txt file
# in this version of Unicode.
#
# Note that characters added to the standard after the
# Composition Version and which have canonical decomposition mappings
# are not automatically added to this list of Post Composition
# Version precomposed characters.
# ================================================
2ADC # FORKING
1D15E # MUSICAL SYMBOL HALF NOTE
1D15F # MUSICAL SYMBOL QUARTER NOTE
1D160 # MUSICAL SYMBOL EIGHTH NOTE
1D161 # MUSICAL SYMBOL SIXTEENTH NOTE
1D162 # MUSICAL SYMBOL THIRTY-SECOND NOTE
1D163 # MUSICAL SYMBOL SIXTY-FOURTH NOTE
1D164 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
1D1BB # MUSICAL SYMBOL MINIMA
1D1BC # MUSICAL SYMBOL MINIMA BLACK
1D1BD # MUSICAL SYMBOL SEMIMINIMA WHITE
1D1BE # MUSICAL SYMBOL SEMIMINIMA BLACK
1D1BF # MUSICAL SYMBOL FUSA WHITE
1D1C0 # MUSICAL SYMBOL FUSA BLACK
# Total code points: 14
# ================================================
# (3) Singleton Decompositions
#
# These characters can be derived from the UnicodeData.txt file
# by including all characters whose canonical decomposition
# consists of a single character.
#
# These characters are simply quoted here for reference.
# See also Full_Composition_Exclusion in DerivedNormalizationProps.txt
# ================================================
# 0340..0341 [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK
# 0343 COMBINING GREEK KORONIS
# 0374 GREEK NUMERAL SIGN
# 037E GREEK QUESTION MARK
# 0387 GREEK ANO TELEIA
# 1F71 GREEK SMALL LETTER ALPHA WITH OXIA
# 1F73 GREEK SMALL LETTER EPSILON WITH OXIA
# 1F75 GREEK SMALL LETTER ETA WITH OXIA
# 1F77 GREEK SMALL LETTER IOTA WITH OXIA
# 1F79 GREEK SMALL LETTER OMICRON WITH OXIA
# 1F7B GREEK SMALL LETTER UPSILON WITH OXIA
# 1F7D GREEK SMALL LETTER OMEGA WITH OXIA
# 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA
# 1FBE GREEK PROSGEGRAMMENI
# 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA
# 1FCB GREEK CAPITAL LETTER ETA WITH OXIA
# 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
# 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA
# 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
# 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA
# 1FEE..1FEF [2] GREEK DIALYTIKA AND OXIA..GREEK VARIA
# 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA
# 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA
# 1FFD GREEK OXIA
# 2000..2001 [2] EN QUAD..EM QUAD
# 2126 OHM SIGN
# 212A..212B [2] KELVIN SIGN..ANGSTROM SIGN
# 2329 LEFT-POINTING ANGLE BRACKET
# 232A RIGHT-POINTING ANGLE BRACKET
# F900..FA0D [270] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA0D
# FA10 CJK COMPATIBILITY IDEOGRAPH-FA10
# FA12 CJK COMPATIBILITY IDEOGRAPH-FA12
# FA15..FA1E [10] CJK COMPATIBILITY IDEOGRAPH-FA15..CJK COMPATIBILITY IDEOGRAPH-FA1E
# FA20 CJK COMPATIBILITY IDEOGRAPH-FA20
# FA22 CJK COMPATIBILITY IDEOGRAPH-FA22
# FA25..FA26 [2] CJK COMPATIBILITY IDEOGRAPH-FA25..CJK COMPATIBILITY IDEOGRAPH-FA26
# FA2A..FA2D [4] CJK COMPATIBILITY IDEOGRAPH-FA2A..CJK COMPATIBILITY IDEOGRAPH-FA2D
# FA30..FA6A [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A
# FA70..FAD9 [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
# 2F800..2FA1D [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 924
# ================================================
# (4) Non-Starter Decompositions
#
# These characters can be derived from the UnicodeData file
# by including all characters whose canonical decomposition consists
# of a sequence of characters, the first of which has a non-zero
# combining class.
#
# These characters are simply quoted here for reference.
# See also Full_Composition_Exclusion in DerivedNormalizationProps.txt
# ================================================
# 0344 COMBINING GREEK DIALYTIKA TONOS
# 0F73 TIBETAN VOWEL SIGN II
# 0F75 TIBETAN VOWEL SIGN UU
# 0F81 TIBETAN VOWEL SIGN REVERSED II
# Total code points: 4

View File

@ -0,0 +1,867 @@
# DerivedAge-5.0.0.txt
# Date: 2006-07-14, 17:25:00 PST [MD/KW]
#
# Unicode Character Database
# Copyright (c) 1991-2006 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see UCD.html
#
# Unicode Character Database: Derived Property Data
# This file shows when various code points were first assigned in Unicode.
#
# Caution: When using the Age *property*, all assigned code points
# in each version are included, not just the newly assigned code points.
# For more information, see http://www.unicode.org/reports/tr18/
#
# Notes:
#
# - The term 'assigned' means that a previously reserved code point was assigned
# to be a character (graphic, format, control, or private-use);
# a noncharacter code point; or a surrogate code point.
# For more information, see The Unicode Standard Section 2.4
#
# - Versions are only tracked from 1.1 onwards, since version 1.0
# predated changes required by the ISO 10646 merger.
#
# - The Hangul Syllables that were removed from 2.0 are not included in the 1.1 listing.
#
# - The supplementary private use code points and the non-character code points
# were assigned in version 2.0, but not specifically listed in the UCD
# until versions 3.0 and 3.1 respectively.
#
# - Contiguous ranges are broken into separate lines where they would cross code point
# types: graphic, format, control, private-use, surrogate, noncharacter
#
# For details on the contents of each version, see
# http://www.unicode.org/versions/enumeratedversions.html.
# ================================================
# Property: Age
# All code points not explicitly listed for Age
# have the value unassigned.
# @missing: 0000..10FFFF; unassigned
# ================================================
# Assigned as of Unicode 1.1.0 (June, 1993)
# [excluding removed Hangul Syllables]
0000..001F ; 1.1 # [32] <control-0000>..<control-001F>
0020..007E ; 1.1 # [95] SPACE..TILDE
007F..009F ; 1.1 # [33] <control-007F>..<control-009F>
00A0..00AC ; 1.1 # [13] NO-BREAK SPACE..NOT SIGN
00AD ; 1.1 # SOFT HYPHEN
00AE..01F5 ; 1.1 # [328] REGISTERED SIGN..LATIN SMALL LETTER G WITH ACUTE
01FA..0217 ; 1.1 # [30] LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE..LATIN SMALL LETTER U WITH INVERTED BREVE
0250..02A8 ; 1.1 # [89] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER TC DIGRAPH WITH CURL
02B0..02DE ; 1.1 # [47] MODIFIER LETTER SMALL H..MODIFIER LETTER RHOTIC HOOK
02E0..02E9 ; 1.1 # [10] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER EXTRA-LOW TONE BAR
0300..0345 ; 1.1 # [70] COMBINING GRAVE ACCENT..COMBINING GREEK YPOGEGRAMMENI
0360..0361 ; 1.1 # [2] COMBINING DOUBLE TILDE..COMBINING DOUBLE INVERTED BREVE
0374..0375 ; 1.1 # [2] GREEK NUMERAL SIGN..GREEK LOWER NUMERAL SIGN
037A ; 1.1 # GREEK YPOGEGRAMMENI
037E ; 1.1 # GREEK QUESTION MARK
0384..038A ; 1.1 # [7] GREEK TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS
038C ; 1.1 # GREEK CAPITAL LETTER OMICRON WITH TONOS
038E..03A1 ; 1.1 # [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO
03A3..03CE ; 1.1 # [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS
03D0..03D6 ; 1.1 # [7] GREEK BETA SYMBOL..GREEK PI SYMBOL
03DA ; 1.1 # GREEK LETTER STIGMA
03DC ; 1.1 # GREEK LETTER DIGAMMA
03DE ; 1.1 # GREEK LETTER KOPPA
03E0 ; 1.1 # GREEK LETTER SAMPI
03E2..03F3 ; 1.1 # [18] COPTIC CAPITAL LETTER SHEI..GREEK LETTER YOT
0401..040C ; 1.1 # [12] CYRILLIC CAPITAL LETTER IO..CYRILLIC CAPITAL LETTER KJE
040E..044F ; 1.1 # [66] CYRILLIC CAPITAL LETTER SHORT U..CYRILLIC SMALL LETTER YA
0451..045C ; 1.1 # [12] CYRILLIC SMALL LETTER IO..CYRILLIC SMALL LETTER KJE
045E..0486 ; 1.1 # [41] CYRILLIC SMALL LETTER SHORT U..COMBINING CYRILLIC PSILI PNEUMATA
0490..04C4 ; 1.1 # [53] CYRILLIC CAPITAL LETTER GHE WITH UPTURN..CYRILLIC SMALL LETTER KA WITH HOOK
04C7..04C8 ; 1.1 # [2] CYRILLIC CAPITAL LETTER EN WITH HOOK..CYRILLIC SMALL LETTER EN WITH HOOK
04CB..04CC ; 1.1 # [2] CYRILLIC CAPITAL LETTER KHAKASSIAN CHE..CYRILLIC SMALL LETTER KHAKASSIAN CHE
04D0..04EB ; 1.1 # [28] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER BARRED O WITH DIAERESIS
04EE..04F5 ; 1.1 # [8] CYRILLIC CAPITAL LETTER U WITH MACRON..CYRILLIC SMALL LETTER CHE WITH DIAERESIS
04F8..04F9 ; 1.1 # [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS
0531..0556 ; 1.1 # [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH
0559..055F ; 1.1 # [7] ARMENIAN MODIFIER LETTER LEFT HALF RING..ARMENIAN ABBREVIATION MARK
0561..0587 ; 1.1 # [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
0589 ; 1.1 # ARMENIAN FULL STOP
05B0..05B9 ; 1.1 # [10] HEBREW POINT SHEVA..HEBREW POINT HOLAM
05BB..05C3 ; 1.1 # [9] HEBREW POINT QUBUTS..HEBREW PUNCTUATION SOF PASUQ
05D0..05EA ; 1.1 # [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
05F0..05F4 ; 1.1 # [5] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW PUNCTUATION GERSHAYIM
060C ; 1.1 # ARABIC COMMA
061B ; 1.1 # ARABIC SEMICOLON
061F ; 1.1 # ARABIC QUESTION MARK
0621..063A ; 1.1 # [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN
0640..0652 ; 1.1 # [19] ARABIC TATWEEL..ARABIC SUKUN
0660..066D ; 1.1 # [14] ARABIC-INDIC DIGIT ZERO..ARABIC FIVE POINTED STAR
0670..06B7 ; 1.1 # [72] ARABIC LETTER SUPERSCRIPT ALEF..ARABIC LETTER LAM WITH THREE DOTS ABOVE
06BA..06BE ; 1.1 # [5] ARABIC LETTER NOON GHUNNA..ARABIC LETTER HEH DOACHASHMEE
06C0..06CE ; 1.1 # [15] ARABIC LETTER HEH WITH YEH ABOVE..ARABIC LETTER YEH WITH SMALL V
06D0..06DC ; 1.1 # [13] ARABIC LETTER E..ARABIC SMALL HIGH SEEN
06DD ; 1.1 # ARABIC END OF AYAH
06DE..06ED ; 1.1 # [16] ARABIC START OF RUB EL HIZB..ARABIC SMALL LOW MEEM
06F0..06F9 ; 1.1 # [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE
0901..0903 ; 1.1 # [3] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN VISARGA
0905..0939 ; 1.1 # [53] DEVANAGARI LETTER A..DEVANAGARI LETTER HA
093C..094D ; 1.1 # [18] DEVANAGARI SIGN NUKTA..DEVANAGARI SIGN VIRAMA
0950..0954 ; 1.1 # [5] DEVANAGARI OM..DEVANAGARI ACUTE ACCENT
0958..0970 ; 1.1 # [25] DEVANAGARI LETTER QA..DEVANAGARI ABBREVIATION SIGN
0981..0983 ; 1.1 # [3] BENGALI SIGN CANDRABINDU..BENGALI SIGN VISARGA
0985..098C ; 1.1 # [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L
098F..0990 ; 1.1 # [2] BENGALI LETTER E..BENGALI LETTER AI
0993..09A8 ; 1.1 # [22] BENGALI LETTER O..BENGALI LETTER NA
09AA..09B0 ; 1.1 # [7] BENGALI LETTER PA..BENGALI LETTER RA
09B2 ; 1.1 # BENGALI LETTER LA
09B6..09B9 ; 1.1 # [4] BENGALI LETTER SHA..BENGALI LETTER HA
09BC ; 1.1 # BENGALI SIGN NUKTA
09BE..09C4 ; 1.1 # [7] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN VOCALIC RR
09C7..09C8 ; 1.1 # [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
09CB..09CD ; 1.1 # [3] BENGALI VOWEL SIGN O..BENGALI SIGN VIRAMA
09D7 ; 1.1 # BENGALI AU LENGTH MARK
09DC..09DD ; 1.1 # [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E3 ; 1.1 # [5] BENGALI LETTER YYA..BENGALI VOWEL SIGN VOCALIC LL
09E6..09FA ; 1.1 # [21] BENGALI DIGIT ZERO..BENGALI ISSHAR
0A02 ; 1.1 # GURMUKHI SIGN BINDI
0A05..0A0A ; 1.1 # [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
0A0F..0A10 ; 1.1 # [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI
0A13..0A28 ; 1.1 # [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA
0A2A..0A30 ; 1.1 # [7] GURMUKHI LETTER PA..GURMUKHI LETTER RA
0A32..0A33 ; 1.1 # [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA
0A35..0A36 ; 1.1 # [2] GURMUKHI LETTER VA..GURMUKHI LETTER SHA
0A38..0A39 ; 1.1 # [2] GURMUKHI LETTER SA..GURMUKHI LETTER HA
0A3C ; 1.1 # GURMUKHI SIGN NUKTA
0A3E..0A42 ; 1.1 # [5] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN UU
0A47..0A48 ; 1.1 # [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI
0A4B..0A4D ; 1.1 # [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA
0A59..0A5C ; 1.1 # [4] GURMUKHI LETTER KHHA..GURMUKHI LETTER RRA
0A5E ; 1.1 # GURMUKHI LETTER FA
0A66..0A74 ; 1.1 # [15] GURMUKHI DIGIT ZERO..GURMUKHI EK ONKAR
0A81..0A83 ; 1.1 # [3] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN VISARGA
0A85..0A8B ; 1.1 # [7] GUJARATI LETTER A..GUJARATI LETTER VOCALIC R
0A8D ; 1.1 # GUJARATI VOWEL CANDRA E
0A8F..0A91 ; 1.1 # [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O
0A93..0AA8 ; 1.1 # [22] GUJARATI LETTER O..GUJARATI LETTER NA
0AAA..0AB0 ; 1.1 # [7] GUJARATI LETTER PA..GUJARATI LETTER RA
0AB2..0AB3 ; 1.1 # [2] GUJARATI LETTER LA..GUJARATI LETTER LLA
0AB5..0AB9 ; 1.1 # [5] GUJARATI LETTER VA..GUJARATI LETTER HA
0ABC..0AC5 ; 1.1 # [10] GUJARATI SIGN NUKTA..GUJARATI VOWEL SIGN CANDRA E
0AC7..0AC9 ; 1.1 # [3] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN CANDRA O
0ACB..0ACD ; 1.1 # [3] GUJARATI VOWEL SIGN O..GUJARATI SIGN VIRAMA
0AD0 ; 1.1 # GUJARATI OM
0AE0 ; 1.1 # GUJARATI LETTER VOCALIC RR
0AE6..0AEF ; 1.1 # [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
0B01..0B03 ; 1.1 # [3] ORIYA SIGN CANDRABINDU..ORIYA SIGN VISARGA
0B05..0B0C ; 1.1 # [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
0B0F..0B10 ; 1.1 # [2] ORIYA LETTER E..ORIYA LETTER AI
0B13..0B28 ; 1.1 # [22] ORIYA LETTER O..ORIYA LETTER NA
0B2A..0B30 ; 1.1 # [7] ORIYA LETTER PA..ORIYA LETTER RA
0B32..0B33 ; 1.1 # [2] ORIYA LETTER LA..ORIYA LETTER LLA
0B36..0B39 ; 1.1 # [4] ORIYA LETTER SHA..ORIYA LETTER HA
0B3C..0B43 ; 1.1 # [8] ORIYA SIGN NUKTA..ORIYA VOWEL SIGN VOCALIC R
0B47..0B48 ; 1.1 # [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
0B4B..0B4D ; 1.1 # [3] ORIYA VOWEL SIGN O..ORIYA SIGN VIRAMA
0B56..0B57 ; 1.1 # [2] ORIYA AI LENGTH MARK..ORIYA AU LENGTH MARK
0B5C..0B5D ; 1.1 # [2] ORIYA LETTER RRA..ORIYA LETTER RHA
0B5F..0B61 ; 1.1 # [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL
0B66..0B70 ; 1.1 # [11] ORIYA DIGIT ZERO..ORIYA ISSHAR
0B82..0B83 ; 1.1 # [2] TAMIL SIGN ANUSVARA..TAMIL SIGN VISARGA
0B85..0B8A ; 1.1 # [6] TAMIL LETTER A..TAMIL LETTER UU
0B8E..0B90 ; 1.1 # [3] TAMIL LETTER E..TAMIL LETTER AI
0B92..0B95 ; 1.1 # [4] TAMIL LETTER O..TAMIL LETTER KA
0B99..0B9A ; 1.1 # [2] TAMIL LETTER NGA..TAMIL LETTER CA
0B9C ; 1.1 # TAMIL LETTER JA
0B9E..0B9F ; 1.1 # [2] TAMIL LETTER NYA..TAMIL LETTER TTA
0BA3..0BA4 ; 1.1 # [2] TAMIL LETTER NNA..TAMIL LETTER TA
0BA8..0BAA ; 1.1 # [3] TAMIL LETTER NA..TAMIL LETTER PA
0BAE..0BB5 ; 1.1 # [8] TAMIL LETTER MA..TAMIL LETTER VA
0BB7..0BB9 ; 1.1 # [3] TAMIL LETTER SSA..TAMIL LETTER HA
0BBE..0BC2 ; 1.1 # [5] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN UU
0BC6..0BC8 ; 1.1 # [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI
0BCA..0BCD ; 1.1 # [4] TAMIL VOWEL SIGN O..TAMIL SIGN VIRAMA
0BD7 ; 1.1 # TAMIL AU LENGTH MARK
0BE7..0BF2 ; 1.1 # [12] TAMIL DIGIT ONE..TAMIL NUMBER ONE THOUSAND
0C01..0C03 ; 1.1 # [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
0C05..0C0C ; 1.1 # [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L
0C0E..0C10 ; 1.1 # [3] TELUGU LETTER E..TELUGU LETTER AI
0C12..0C28 ; 1.1 # [23] TELUGU LETTER O..TELUGU LETTER NA
0C2A..0C33 ; 1.1 # [10] TELUGU LETTER PA..TELUGU LETTER LLA
0C35..0C39 ; 1.1 # [5] TELUGU LETTER VA..TELUGU LETTER HA
0C3E..0C44 ; 1.1 # [7] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN VOCALIC RR
0C46..0C48 ; 1.1 # [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
0C4A..0C4D ; 1.1 # [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
0C55..0C56 ; 1.1 # [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
0C60..0C61 ; 1.1 # [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
0C66..0C6F ; 1.1 # [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
0C82..0C83 ; 1.1 # [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C85..0C8C ; 1.1 # [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; 1.1 # [3] KANNADA LETTER E..KANNADA LETTER AI
0C92..0CA8 ; 1.1 # [23] KANNADA LETTER O..KANNADA LETTER NA
0CAA..0CB3 ; 1.1 # [10] KANNADA LETTER PA..KANNADA LETTER LLA
0CB5..0CB9 ; 1.1 # [5] KANNADA LETTER VA..KANNADA LETTER HA
0CBE..0CC4 ; 1.1 # [7] KANNADA VOWEL SIGN AA..KANNADA VOWEL SIGN VOCALIC RR
0CC6..0CC8 ; 1.1 # [3] KANNADA VOWEL SIGN E..KANNADA VOWEL SIGN AI
0CCA..0CCD ; 1.1 # [4] KANNADA VOWEL SIGN O..KANNADA SIGN VIRAMA
0CD5..0CD6 ; 1.1 # [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CDE ; 1.1 # KANNADA LETTER FA
0CE0..0CE1 ; 1.1 # [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL
0CE6..0CEF ; 1.1 # [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0D02..0D03 ; 1.1 # [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C ; 1.1 # [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10 ; 1.1 # [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D28 ; 1.1 # [23] MALAYALAM LETTER O..MALAYALAM LETTER NA
0D2A..0D39 ; 1.1 # [16] MALAYALAM LETTER PA..MALAYALAM LETTER HA
0D3E..0D43 ; 1.1 # [6] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN VOCALIC R
0D46..0D48 ; 1.1 # [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
0D4A..0D4D ; 1.1 # [4] MALAYALAM VOWEL SIGN O..MALAYALAM SIGN VIRAMA
0D57 ; 1.1 # MALAYALAM AU LENGTH MARK
0D60..0D61 ; 1.1 # [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
0D66..0D6F ; 1.1 # [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
0E01..0E3A ; 1.1 # [58] THAI CHARACTER KO KAI..THAI CHARACTER PHINTHU
0E3F..0E5B ; 1.1 # [29] THAI CURRENCY SYMBOL BAHT..THAI CHARACTER KHOMUT
0E81..0E82 ; 1.1 # [2] LAO LETTER KO..LAO LETTER KHO SUNG
0E84 ; 1.1 # LAO LETTER KHO TAM
0E87..0E88 ; 1.1 # [2] LAO LETTER NGO..LAO LETTER CO
0E8A ; 1.1 # LAO LETTER SO TAM
0E8D ; 1.1 # LAO LETTER NYO
0E94..0E97 ; 1.1 # [4] LAO LETTER DO..LAO LETTER THO TAM
0E99..0E9F ; 1.1 # [7] LAO LETTER NO..LAO LETTER FO SUNG
0EA1..0EA3 ; 1.1 # [3] LAO LETTER MO..LAO LETTER LO LING
0EA5 ; 1.1 # LAO LETTER LO LOOT
0EA7 ; 1.1 # LAO LETTER WO
0EAA..0EAB ; 1.1 # [2] LAO LETTER SO SUNG..LAO LETTER HO SUNG
0EAD..0EB9 ; 1.1 # [13] LAO LETTER O..LAO VOWEL SIGN UU
0EBB..0EBD ; 1.1 # [3] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN NYO
0EC0..0EC4 ; 1.1 # [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
0EC6 ; 1.1 # LAO KO LA
0EC8..0ECD ; 1.1 # [6] LAO TONE MAI EK..LAO NIGGAHITA
0ED0..0ED9 ; 1.1 # [10] LAO DIGIT ZERO..LAO DIGIT NINE
0EDC..0EDD ; 1.1 # [2] LAO HO NO..LAO HO MO
10A0..10C5 ; 1.1 # [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10D0..10F6 ; 1.1 # [39] GEORGIAN LETTER AN..GEORGIAN LETTER FI
10FB ; 1.1 # GEORGIAN PARAGRAPH SEPARATOR
1100..1159 ; 1.1 # [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH
115F..11A2 ; 1.1 # [68] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA
11A8..11F9 ; 1.1 # [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH
1E00..1E9A ; 1.1 # [155] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER A WITH RIGHT HALF RING
1EA0..1EF9 ; 1.1 # [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE
1F00..1F15 ; 1.1 # [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D ; 1.1 # [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
1F20..1F45 ; 1.1 # [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
1F48..1F4D ; 1.1 # [6] GREEK CAPITAL LETTER OMICRON WITH PSILI..GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
1F50..1F57 ; 1.1 # [8] GREEK SMALL LETTER UPSILON WITH PSILI..GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI
1F59 ; 1.1 # GREEK CAPITAL LETTER UPSILON WITH DASIA
1F5B ; 1.1 # GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA
1F5D ; 1.1 # GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA
1F5F..1F7D ; 1.1 # [31] GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI..GREEK SMALL LETTER OMEGA WITH OXIA
1F80..1FB4 ; 1.1 # [53] GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
1FB6..1FC4 ; 1.1 # [15] GREEK SMALL LETTER ALPHA WITH PERISPOMENI..GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
1FC6..1FD3 ; 1.1 # [14] GREEK SMALL LETTER ETA WITH PERISPOMENI..GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
1FD6..1FDB ; 1.1 # [6] GREEK SMALL LETTER IOTA WITH PERISPOMENI..GREEK CAPITAL LETTER IOTA WITH OXIA
1FDD..1FEF ; 1.1 # [19] GREEK DASIA AND VARIA..GREEK VARIA
1FF2..1FF4 ; 1.1 # [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
1FF6..1FFE ; 1.1 # [9] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK DASIA
2000..200A ; 1.1 # [11] EN QUAD..HAIR SPACE
200B..200F ; 1.1 # [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK
2010..2027 ; 1.1 # [24] HYPHEN..HYPHENATION POINT
2028..202E ; 1.1 # [7] LINE SEPARATOR..RIGHT-TO-LEFT OVERRIDE
2030..2046 ; 1.1 # [23] PER MILLE SIGN..RIGHT SQUARE BRACKET WITH QUILL
206A..206F ; 1.1 # [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
2070 ; 1.1 # SUPERSCRIPT ZERO
2074..208E ; 1.1 # [27] SUPERSCRIPT FOUR..SUBSCRIPT RIGHT PARENTHESIS
20A0..20AA ; 1.1 # [11] EURO-CURRENCY SIGN..NEW SHEQEL SIGN
20D0..20E1 ; 1.1 # [18] COMBINING LEFT HARPOON ABOVE..COMBINING LEFT RIGHT ARROW ABOVE
2100..2138 ; 1.1 # [57] ACCOUNT OF..DALET SYMBOL
2153..2182 ; 1.1 # [48] VULGAR FRACTION ONE THIRD..ROMAN NUMERAL TEN THOUSAND
2190..21EA ; 1.1 # [91] LEFTWARDS ARROW..UPWARDS WHITE ARROW FROM BAR
2200..22F1 ; 1.1 # [242] FOR ALL..DOWN RIGHT DIAGONAL ELLIPSIS
2300 ; 1.1 # DIAMETER SIGN
2302..237A ; 1.1 # [121] HOUSE..APL FUNCTIONAL SYMBOL ALPHA
2400..2424 ; 1.1 # [37] SYMBOL FOR NULL..SYMBOL FOR NEWLINE
2440..244A ; 1.1 # [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..24EA ; 1.1 # [139] CIRCLED DIGIT ONE..CIRCLED DIGIT ZERO
2500..2595 ; 1.1 # [150] BOX DRAWINGS LIGHT HORIZONTAL..RIGHT ONE EIGHTH BLOCK
25A0..25EF ; 1.1 # [80] BLACK SQUARE..LARGE CIRCLE
2600..2613 ; 1.1 # [20] BLACK SUN WITH RAYS..SALTIRE
261A..266F ; 1.1 # [86] BLACK LEFT POINTING INDEX..MUSIC SHARP SIGN
2701..2704 ; 1.1 # [4] UPPER BLADE SCISSORS..WHITE SCISSORS
2706..2709 ; 1.1 # [4] TELEPHONE LOCATION SIGN..ENVELOPE
270C..2727 ; 1.1 # [28] VICTORY HAND..WHITE FOUR POINTED STAR
2729..274B ; 1.1 # [35] STRESS OUTLINED WHITE STAR..HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK
274D ; 1.1 # SHADOWED WHITE CIRCLE
274F..2752 ; 1.1 # [4] LOWER RIGHT DROP-SHADOWED WHITE SQUARE..UPPER RIGHT SHADOWED WHITE SQUARE
2756 ; 1.1 # BLACK DIAMOND MINUS WHITE X
2758..275E ; 1.1 # [7] LIGHT VERTICAL BAR..HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT
2761..2767 ; 1.1 # [7] CURVED STEM PARAGRAPH SIGN ORNAMENT..ROTATED FLORAL HEART BULLET
2776..2794 ; 1.1 # [31] DINGBAT NEGATIVE CIRCLED DIGIT ONE..HEAVY WIDE-HEADED RIGHTWARDS ARROW
2798..27AF ; 1.1 # [24] HEAVY SOUTH EAST ARROW..NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW
27B1..27BE ; 1.1 # [14] NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW..OPEN-OUTLINED RIGHTWARDS ARROW
3000..3037 ; 1.1 # [56] IDEOGRAPHIC SPACE..IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL
303F ; 1.1 # IDEOGRAPHIC HALF FILL SPACE
3041..3094 ; 1.1 # [84] HIRAGANA LETTER SMALL A..HIRAGANA LETTER VU
3099..309E ; 1.1 # [6] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..HIRAGANA VOICED ITERATION MARK
30A1..30FE ; 1.1 # [94] KATAKANA LETTER SMALL A..KATAKANA VOICED ITERATION MARK
3105..312C ; 1.1 # [40] BOPOMOFO LETTER B..BOPOMOFO LETTER GN
3131..318E ; 1.1 # [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
3190..319F ; 1.1 # [16] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION MAN MARK
3200..321C ; 1.1 # [29] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED HANGUL CIEUC U
3220..3243 ; 1.1 # [36] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH REACH
3260..327B ; 1.1 # [28] CIRCLED HANGUL KIYEOK..CIRCLED HANGUL HIEUH A
327F..32B0 ; 1.1 # [50] KOREAN STANDARD SYMBOL..CIRCLED IDEOGRAPH NIGHT
32C0..32CB ; 1.1 # [12] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DECEMBER
32D0..32FE ; 1.1 # [47] CIRCLED KATAKANA A..CIRCLED KATAKANA WO
3300..3376 ; 1.1 # [119] SQUARE APAATO..SQUARE PC
337B..33DD ; 1.1 # [99] SQUARE ERA NAME HEISEI..SQUARE WB
33E0..33FE ; 1.1 # [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE
4E00..9FA5 ; 1.1 # [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
E000..F8FF ; 1.1 # [6400] <private-use-E000>..<private-use-F8FF>
F900..FA2D ; 1.1 # [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
FB00..FB06 ; 1.1 # [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
FB13..FB17 ; 1.1 # [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
FB1E..FB36 ; 1.1 # [25] HEBREW POINT JUDEO-SPANISH VARIKA..HEBREW LETTER ZAYIN WITH DAGESH
FB38..FB3C ; 1.1 # [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH
FB3E ; 1.1 # HEBREW LETTER MEM WITH DAGESH
FB40..FB41 ; 1.1 # [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH
FB43..FB44 ; 1.1 # [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH
FB46..FBB1 ; 1.1 # [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
FBD3..FD3F ; 1.1 # [365] ARABIC LETTER NG ISOLATED FORM..ORNATE RIGHT PARENTHESIS
FD50..FD8F ; 1.1 # [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
FD92..FDC7 ; 1.1 # [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
FDF0..FDFB ; 1.1 # [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU
FE20..FE23 ; 1.1 # [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
FE30..FE44 ; 1.1 # [21] PRESENTATION FORM FOR VERTICAL TWO DOT LEADER..PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET
FE49..FE52 ; 1.1 # [10] DASHED OVERLINE..SMALL FULL STOP
FE54..FE66 ; 1.1 # [19] SMALL SEMICOLON..SMALL EQUALS SIGN
FE68..FE6B ; 1.1 # [4] SMALL REVERSE SOLIDUS..SMALL COMMERCIAL AT
FE70..FE72 ; 1.1 # [3] ARABIC FATHATAN ISOLATED FORM..ARABIC DAMMATAN ISOLATED FORM
FE74 ; 1.1 # ARABIC KASRATAN ISOLATED FORM
FE76..FEFC ; 1.1 # [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
FEFF ; 1.1 # ZERO WIDTH NO-BREAK SPACE
FF01..FF5E ; 1.1 # [94] FULLWIDTH EXCLAMATION MARK..FULLWIDTH TILDE
FF61..FFBE ; 1.1 # [94] HALFWIDTH IDEOGRAPHIC FULL STOP..HALFWIDTH HANGUL LETTER HIEUH
FFC2..FFC7 ; 1.1 # [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E
FFCA..FFCF ; 1.1 # [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE
FFD2..FFD7 ; 1.1 # [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU
FFDA..FFDC ; 1.1 # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
FFE0..FFE6 ; 1.1 # [7] FULLWIDTH CENT SIGN..FULLWIDTH WON SIGN
FFE8..FFEE ; 1.1 # [7] HALFWIDTH FORMS LIGHT VERTICAL..HALFWIDTH WHITE CIRCLE
FFFD ; 1.1 # REPLACEMENT CHARACTER
FFFE..FFFF ; 1.1 # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
# Total code points: 33979
# ================================================
# Newly assigned in Unicode 2.0.0 (July, 1996)
0591..05A1 ; 2.0 # [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
05A3..05AF ; 2.0 # [13] HEBREW ACCENT MUNAH..HEBREW MARK MASORA CIRCLE
05C4 ; 2.0 # HEBREW MARK UPPER DOT
0F00..0F47 ; 2.0 # [72] TIBETAN SYLLABLE OM..TIBETAN LETTER JA
0F49..0F69 ; 2.0 # [33] TIBETAN LETTER NYA..TIBETAN LETTER KSSA
0F71..0F8B ; 2.0 # [27] TIBETAN VOWEL SIGN AA..TIBETAN SIGN GRU MED RGYINGS
0F90..0F95 ; 2.0 # [6] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER CA
0F97 ; 2.0 # TIBETAN SUBJOINED LETTER JA
0F99..0FAD ; 2.0 # [21] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER WA
0FB1..0FB7 ; 2.0 # [7] TIBETAN SUBJOINED LETTER YA..TIBETAN SUBJOINED LETTER HA
0FB9 ; 2.0 # TIBETAN SUBJOINED LETTER KSSA
1E9B ; 2.0 # LATIN SMALL LETTER LONG S WITH DOT ABOVE
20AB ; 2.0 # DONG SIGN
AC00..D7A3 ; 2.0 # [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH
D800..DFFF ; 2.0 # [2048] <surrogate-D800>..<surrogate-DFFF>
1FFFE..1FFFF ; 2.0 # [2] <noncharacter-1FFFE>..<noncharacter-1FFFF>
2FFFE..2FFFF ; 2.0 # [2] <noncharacter-2FFFE>..<noncharacter-2FFFF>
3FFFE..3FFFF ; 2.0 # [2] <noncharacter-3FFFE>..<noncharacter-3FFFF>
4FFFE..4FFFF ; 2.0 # [2] <noncharacter-4FFFE>..<noncharacter-4FFFF>
5FFFE..5FFFF ; 2.0 # [2] <noncharacter-5FFFE>..<noncharacter-5FFFF>
6FFFE..6FFFF ; 2.0 # [2] <noncharacter-6FFFE>..<noncharacter-6FFFF>
7FFFE..7FFFF ; 2.0 # [2] <noncharacter-7FFFE>..<noncharacter-7FFFF>
8FFFE..8FFFF ; 2.0 # [2] <noncharacter-8FFFE>..<noncharacter-8FFFF>
9FFFE..9FFFF ; 2.0 # [2] <noncharacter-9FFFE>..<noncharacter-9FFFF>
AFFFE..AFFFF ; 2.0 # [2] <noncharacter-AFFFE>..<noncharacter-AFFFF>