2 # Date: 2003-03-20, 20:07:40 GMT [MD]
4 # Unicode Character Database: Extended Properties
5 # For documentation, see UCD.html
6 # Note: Unassigned and Noncharacter codepoints may be omitted
7 # if they have default property values.
8 # ================================================
10 # ================================================
12 0009..000D ; White_Space # Cc [5] <control>..<control>
13 0020 ; White_Space # Zs SPACE
14 0085 ; White_Space # Cc <control>
15 00A0 ; White_Space # Zs NO-BREAK SPACE
16 1680 ; White_Space # Zs OGHAM SPACE MARK
17 180E ; White_Space # Zs MONGOLIAN VOWEL SEPARATOR
18 2000..200A ; White_Space # Zs [11] EN QUAD..HAIR SPACE
19 2028 ; White_Space # Zl LINE SEPARATOR
20 2029 ; White_Space # Zp PARAGRAPH SEPARATOR
21 202F ; White_Space # Zs NARROW NO-BREAK SPACE
22 205F ; White_Space # Zs MEDIUM MATHEMATICAL SPACE
23 3000 ; White_Space # Zs IDEOGRAPHIC SPACE
25 # Total code points: 26
27 # ================================================
29 200E..200F ; Bidi_Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
30 202A..202E ; Bidi_Control # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
32 # Total code points: 7
34 # ================================================
36 200C..200D ; Join_Control # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
38 # Total code points: 2
40 # ================================================
42 002D ; Dash # Pd HYPHEN-MINUS
43 058A ; Dash # Pd ARMENIAN HYPHEN
44 1806 ; Dash # Pd MONGOLIAN TODO SOFT HYPHEN
45 2010..2015 ; Dash # Pd [6] HYPHEN..HORIZONTAL BAR
46 2053 ; Dash # Po SWUNG DASH
47 207B ; Dash # Sm SUPERSCRIPT MINUS
48 208B ; Dash # Sm SUBSCRIPT MINUS
49 2212 ; Dash # Sm MINUS SIGN
50 301C ; Dash # Pd WAVE DASH
51 3030 ; Dash # Pd WAVY DASH
52 FE31..FE32 ; Dash # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
53 FE58 ; Dash # Pd SMALL EM DASH
54 FE63 ; Dash # Pd SMALL HYPHEN-MINUS
55 FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
57 # Total code points: 20
59 # ================================================
61 002D ; Hyphen # Pd HYPHEN-MINUS
62 00AD ; Hyphen # Cf SOFT HYPHEN
63 058A ; Hyphen # Pd ARMENIAN HYPHEN
64 1806 ; Hyphen # Pd MONGOLIAN TODO SOFT HYPHEN
65 2010..2011 ; Hyphen # Pd [2] HYPHEN..NON-BREAKING HYPHEN
66 30FB ; Hyphen # Pc KATAKANA MIDDLE DOT
67 FE63 ; Hyphen # Pd SMALL HYPHEN-MINUS
68 FF0D ; Hyphen # Pd FULLWIDTH HYPHEN-MINUS
69 FF65 ; Hyphen # Pc HALFWIDTH KATAKANA MIDDLE DOT
71 # Total code points: 10
73 # ================================================
75 0022 ; Quotation_Mark # Po QUOTATION MARK
76 0027 ; Quotation_Mark # Po APOSTROPHE
77 00AB ; Quotation_Mark # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
78 00BB ; Quotation_Mark # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
79 2018 ; Quotation_Mark # Pi LEFT SINGLE QUOTATION MARK
80 2019 ; Quotation_Mark # Pf RIGHT SINGLE QUOTATION MARK
81 201A ; Quotation_Mark # Ps SINGLE LOW-9 QUOTATION MARK
82 201B..201C ; Quotation_Mark # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK
83 201D ; Quotation_Mark # Pf RIGHT DOUBLE QUOTATION MARK
84 201E ; Quotation_Mark # Ps DOUBLE LOW-9 QUOTATION MARK
85 201F ; Quotation_Mark # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK
86 2039 ; Quotation_Mark # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK
87 203A ; Quotation_Mark # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
88 300C ; Quotation_Mark # Ps LEFT CORNER BRACKET
89 300D ; Quotation_Mark # Pe RIGHT CORNER BRACKET
90 300E ; Quotation_Mark # Ps LEFT WHITE CORNER BRACKET
91 300F ; Quotation_Mark # Pe RIGHT WHITE CORNER BRACKET
92 301D ; Quotation_Mark # Ps REVERSED DOUBLE PRIME QUOTATION MARK
93 301E..301F ; Quotation_Mark # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK
94 FE41 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET
95 FE42 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET
96 FE43 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET
97 FE44 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET
98 FF02 ; Quotation_Mark # Po FULLWIDTH QUOTATION MARK
99 FF07 ; Quotation_Mark # Po FULLWIDTH APOSTROPHE
100 FF62 ; Quotation_Mark # Ps HALFWIDTH LEFT CORNER BRACKET
101 FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
103 # Total code points: 29
105 # ================================================
107 0021 ; Terminal_Punctuation # Po EXCLAMATION MARK
108 002C ; Terminal_Punctuation # Po COMMA
109 002E ; Terminal_Punctuation # Po FULL STOP
110 003A..003B ; Terminal_Punctuation # Po [2] COLON..SEMICOLON
111 003F ; Terminal_Punctuation # Po QUESTION MARK
112 037E ; Terminal_Punctuation # Po GREEK QUESTION MARK
113 0387 ; Terminal_Punctuation # Po GREEK ANO TELEIA
114 0589 ; Terminal_Punctuation # Po ARMENIAN FULL STOP
115 060C ; Terminal_Punctuation # Po ARABIC COMMA
116 061B ; Terminal_Punctuation # Po ARABIC SEMICOLON
117 061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK
118 06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP
119 0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION
120 070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS
121 0964..0965 ; Terminal_Punctuation # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
122 0E5A..0E5B ; Terminal_Punctuation # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT
123 104A..104B ; Terminal_Punctuation # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
124 1361..1368 ; Terminal_Punctuation # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
125 166D..166E ; Terminal_Punctuation # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
126 16EB..16ED ; Terminal_Punctuation # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION
127 17D4..17D6 ; Terminal_Punctuation # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH
128 17DA ; Terminal_Punctuation # Po KHMER SIGN KOOMUUT
129 1802..1805 ; Terminal_Punctuation # Po [4] MONGOLIAN COMMA..MONGOLIAN FOUR DOTS
130 1808..1809 ; Terminal_Punctuation # Po [2] MONGOLIAN MANCHU COMMA..MONGOLIAN MANCHU FULL STOP
131 1944..1945 ; Terminal_Punctuation # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
132 203C..203D ; Terminal_Punctuation # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG
133 2047..2049 ; Terminal_Punctuation # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
134 3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
135 FE50..FE52 ; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP
136 FE54..FE57 ; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK
137 FF01 ; Terminal_Punctuation # Po FULLWIDTH EXCLAMATION MARK
138 FF0C ; Terminal_Punctuation # Po FULLWIDTH COMMA
139 FF0E ; Terminal_Punctuation # Po FULLWIDTH FULL STOP
140 FF1A..FF1B ; Terminal_Punctuation # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON
141 FF1F ; Terminal_Punctuation # Po FULLWIDTH QUESTION MARK
142 FF61 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC FULL STOP
143 FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
145 # Total code points: 78
147 # ================================================
149 0028 ; Other_Math # Ps LEFT PARENTHESIS
150 0029 ; Other_Math # Pe RIGHT PARENTHESIS
151 002A ; Other_Math # Po ASTERISK
152 002D ; Other_Math # Pd HYPHEN-MINUS
153 002F ; Other_Math # Po SOLIDUS
154 005B ; Other_Math # Ps LEFT SQUARE BRACKET
155 005C ; Other_Math # Po REVERSE SOLIDUS
156 005D ; Other_Math # Pe RIGHT SQUARE BRACKET
157 005E ; Other_Math # Sk CIRCUMFLEX ACCENT
158 007B ; Other_Math # Ps LEFT CURLY BRACKET
159 007D ; Other_Math # Pe RIGHT CURLY BRACKET
160 2016 ; Other_Math # Po DOUBLE VERTICAL LINE
161 2032..2034 ; Other_Math # Po [3] PRIME..TRIPLE PRIME
162 207D ; Other_Math # Ps SUPERSCRIPT LEFT PARENTHESIS
163 207E ; Other_Math # Pe SUPERSCRIPT RIGHT PARENTHESIS
164 208D ; Other_Math # Ps SUBSCRIPT LEFT PARENTHESIS
165 208E ; Other_Math # Pe SUBSCRIPT RIGHT PARENTHESIS
166 20D0..20DC ; Other_Math # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
167 20E1 ; Other_Math # Mn COMBINING LEFT RIGHT ARROW ABOVE
168 2102 ; Other_Math # L& DOUBLE-STRUCK CAPITAL C
169 210A..2113 ; Other_Math # L& [10] SCRIPT SMALL G..SCRIPT SMALL L
170 2115 ; Other_Math # L& DOUBLE-STRUCK CAPITAL N
171 2119..211D ; Other_Math # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R
172 2124 ; Other_Math # L& DOUBLE-STRUCK CAPITAL Z
173 2128 ; Other_Math # L& BLACK-LETTER CAPITAL Z
174 212C..212D ; Other_Math # L& [2] SCRIPT CAPITAL B..BLACK-LETTER CAPITAL C
175 212F..2131 ; Other_Math # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F
176 2133..2134 ; Other_Math # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O
177 2135..2138 ; Other_Math # Lo [4] ALEF SYMBOL..DALET SYMBOL
178 FE35 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS
179 FE36 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS
180 FE37 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET
181 FE38 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET
182 FE47 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET
183 FE48 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET
184 FE59 ; Other_Math # Ps SMALL LEFT PARENTHESIS
185 FE5A ; Other_Math # Pe SMALL RIGHT PARENTHESIS
186 FE5B ; Other_Math # Ps SMALL LEFT CURLY BRACKET
187 FE5C ; Other_Math # Pe SMALL RIGHT CURLY BRACKET
188 FE61 ; Other_Math # Po SMALL ASTERISK
189 FE63 ; Other_Math # Pd SMALL HYPHEN-MINUS
190 FE68 ; Other_Math # Po SMALL REVERSE SOLIDUS
191 FF08 ; Other_Math # Ps FULLWIDTH LEFT PARENTHESIS
192 FF09 ; Other_Math # Pe FULLWIDTH RIGHT PARENTHESIS
193 FF0A ; Other_Math # Po FULLWIDTH ASTERISK
194 FF0D ; Other_Math # Pd FULLWIDTH HYPHEN-MINUS
195 FF0F ; Other_Math # Po FULLWIDTH SOLIDUS
196 FF3B ; Other_Math # Ps FULLWIDTH LEFT SQUARE BRACKET
197 FF3C ; Other_Math # Po FULLWIDTH REVERSE SOLIDUS
198 FF3D ; Other_Math # Pe FULLWIDTH RIGHT SQUARE BRACKET
199 FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT
200 FF5B ; Other_Math # Ps FULLWIDTH LEFT CURLY BRACKET
201 FF5D ; Other_Math # Pe FULLWIDTH RIGHT CURLY BRACKET
202 1D400..1D454 ; Other_Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
203 1D456..1D49C ; Other_Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A
204 1D49E..1D49F ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D
205 1D4A2 ; Other_Math # L& MATHEMATICAL SCRIPT CAPITAL G
206 1D4A5..1D4A6 ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K
207 1D4A9..1D4AC ; Other_Math # L& [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q
208 1D4AE..1D4B9 ; Other_Math # L& [12] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT SMALL D
209 1D4BB ; Other_Math # L& MATHEMATICAL SCRIPT SMALL F
210 1D4BD..1D4C3 ; Other_Math # L& [7] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL N
211 1D4C5..1D505 ; Other_Math # L& [65] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL FRAKTUR CAPITAL B
212 1D507..1D50A ; Other_Math # L& [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G
213 1D50D..1D514 ; Other_Math # L& [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q
214 1D516..1D51C ; Other_Math # L& [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y
215 1D51E..1D539 ; Other_Math # L& [28] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B
216 1D53B..1D53E ; Other_Math # L& [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G
217 1D540..1D544 ; Other_Math # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M
218 1D546 ; Other_Math # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O
219 1D54A..1D550 ; Other_Math # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y
220 1D552..1D6A3 ; Other_Math # L& [338] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL MONOSPACE SMALL Z
221 1D6A8..1D6C0 ; Other_Math # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA
222 1D6C2..1D6DA ; Other_Math # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA
223 1D6DC..1D6FA ; Other_Math # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA
224 1D6FC..1D714 ; Other_Math # L& [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA
225 1D716..1D734 ; Other_Math # L& [31] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA
226 1D736..1D74E ; Other_Math # L& [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA
227 1D750..1D76E ; Other_Math # L& [31] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA
228 1D770..1D788 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA
229 1D78A..1D7A8 ; Other_Math # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA
230 1D7AA..1D7C2 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
231 1D7C4..1D7C9 ; Other_Math # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL
232 1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
234 # Total code points: 1069
236 # ================================================
238 0030..0039 ; Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE
239 0041..0046 ; Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F
240 0061..0066 ; Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F
241 FF10..FF19 ; Hex_Digit # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
242 FF21..FF26 ; Hex_Digit # L& [6] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER F
243 FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER F
245 # Total code points: 44
247 # ================================================
249 0030..0039 ; ASCII_Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE
250 0041..0046 ; ASCII_Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F
251 0061..0066 ; ASCII_Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F
253 # Total code points: 22
255 # ================================================
257 0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI
258 05B0..05B9 ; Other_Alphabetic # Mn [10] HEBREW POINT SHEVA..HEBREW POINT HOLAM
259 05BB..05BD ; Other_Alphabetic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
260 05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE
261 05C1..05C2 ; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
262 05C4 ; Other_Alphabetic # Mn HEBREW MARK UPPER DOT
263 0610..0615 ; Other_Alphabetic # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH
264 064B..0657 ; Other_Alphabetic # Mn [13] ARABIC FATHATAN..ARABIC INVERTED DAMMA
265 0670 ; Other_Alphabetic # Mn ARABIC LETTER SUPERSCRIPT ALEF
266 06D6..06DC ; Other_Alphabetic # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
267 06E1..06E4 ; Other_Alphabetic # Mn [4] ARABIC SMALL HIGH DOTLESS HEAD OF KHAH..ARABIC SMALL HIGH MADDA
268 06E7..06E8 ; Other_Alphabetic # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
269 06ED ; Other_Alphabetic # Mn ARABIC SMALL LOW MEEM
270 0711 ; Other_Alphabetic # Mn SYRIAC LETTER SUPERSCRIPT ALAPH
271 0730..073F ; Other_Alphabetic # Mn [16] SYRIAC PTHAHA ABOVE..SYRIAC RWAHA
272 07A6..07B0 ; Other_Alphabetic # Mn [11] THAANA ABAFILI..THAANA SUKUN
273 0901..0902 ; Other_Alphabetic # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA
274 0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
275 093E..0940 ; Other_Alphabetic # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II
276 0941..0948 ; Other_Alphabetic # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
277 0949..094C ; Other_Alphabetic # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU
278 0962..0963 ; Other_Alphabetic # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
279 0981 ; Other_Alphabetic # Mn BENGALI SIGN CANDRABINDU
280 0982..0983 ; Other_Alphabetic # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
281 09BE..09C0 ; Other_Alphabetic # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II
282 09C1..09C4 ; Other_Alphabetic # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR
283 09C7..09C8 ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
284 09CB..09CC ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU
285 09D7 ; Other_Alphabetic # Mc BENGALI AU LENGTH MARK
286 09E2..09E3 ; Other_Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
287 0A01..0A02 ; Other_Alphabetic # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
288 0A03 ; Other_Alphabetic # Mc GURMUKHI SIGN VISARGA
289 0A3E..0A40 ; Other_Alphabetic # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II
290 0A41..0A42 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU
291 0A47..0A48 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI
292 0A4B..0A4C ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN OO..GURMUKHI VOWEL SIGN AU
293 0A70..0A71 ; Other_Alphabetic # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK
294 0A81..0A82 ; Other_Alphabetic # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA
295 0A83 ; Other_Alphabetic # Mc GUJARATI SIGN VISARGA
296 0ABE..0AC0 ; Other_Alphabetic # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II
297 0AC1..0AC5 ; Other_Alphabetic # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E
298 0AC7..0AC8 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
299 0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O
300 0ACB..0ACC ; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
301 0AE2..0AE3 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
302 0B01 ; Other_Alphabetic # Mn ORIYA SIGN CANDRABINDU
303 0B02..0B03 ; Other_Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
304 0B3E ; Other_Alphabetic # Mc ORIYA VOWEL SIGN AA
305 0B3F ; Other_Alphabetic # Mn ORIYA VOWEL SIGN I
306 0B40 ; Other_Alphabetic # Mc ORIYA VOWEL SIGN II
307 0B41..0B43 ; Other_Alphabetic # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R
308 0B47..0B48 ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
309 0B4B..0B4C ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
310 0B56 ; Other_Alphabetic # Mn ORIYA AI LENGTH MARK
311 0B57 ; Other_Alphabetic # Mc ORIYA AU LENGTH MARK
312 0B82 ; Other_Alphabetic # Mn TAMIL SIGN ANUSVARA
313 0BBE..0BBF ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I
314 0BC0 ; Other_Alphabetic # Mn TAMIL VOWEL SIGN II
315 0BC1..0BC2 ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU
316 0BC6..0BC8 ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI
317 0BCA..0BCC ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU
318 0BD7 ; Other_Alphabetic # Mc TAMIL AU LENGTH MARK
319 0C01..0C03 ; Other_Alphabetic # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
320 0C3E..0C40 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
321 0C41..0C44 ; Other_Alphabetic # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR
322 0C46..0C48 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
323 0C4A..0C4C ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU
324 0C55..0C56 ; Other_Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
325 0C82..0C83 ; Other_Alphabetic # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
326 0CBE ; Other_Alphabetic # Mc KANNADA VOWEL SIGN AA
327 0CBF ; Other_Alphabetic # Mn KANNADA VOWEL SIGN I
328 0CC0..0CC4 ; Other_Alphabetic # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR
329 0CC6 ; Other_Alphabetic # Mn KANNADA VOWEL SIGN E
330 0CC7..0CC8 ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
331 0CCA..0CCB ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
332 0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU
333 0CD5..0CD6 ; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
334 0D02..0D03 ; Other_Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
335 0D3E..0D40 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
336 0D41..0D43 ; Other_Alphabetic # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R
337 0D46..0D48 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
338 0D4A..0D4C ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
339 0D57 ; Other_Alphabetic # Mc MALAYALAM AU LENGTH MARK
340 0D82..0D83 ; Other_Alphabetic # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
341 0DCF..0DD1 ; Other_Alphabetic # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA
342 0DD2..0DD4 ; Other_Alphabetic # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA
343 0DD6 ; Other_Alphabetic # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA
344 0DD8..0DDF ; Other_Alphabetic # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA
345 0DF2..0DF3 ; Other_Alphabetic # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA
346 0E31 ; Other_Alphabetic # Mn THAI CHARACTER MAI HAN-AKAT
347 0E34..0E3A ; Other_Alphabetic # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU
348 0E4D ; Other_Alphabetic # Mn THAI CHARACTER NIKHAHIT
349 0EB1 ; Other_Alphabetic # Mn LAO VOWEL SIGN MAI KAN
350 0EB4..0EB9 ; Other_Alphabetic # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU
351 0EBB..0EBC ; Other_Alphabetic # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO
352 0ECD ; Other_Alphabetic # Mn LAO NIGGAHITA
353 0F71..0F7E ; Other_Alphabetic # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO
354 0F7F ; Other_Alphabetic # Mc TIBETAN SIGN RNAM BCAD
355 0F80..0F81 ; Other_Alphabetic # Mn [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II
356 0F90..0F97 ; Other_Alphabetic # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA
357 0F99..0FBC ; Other_Alphabetic # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA
358 102C ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN AA
359 102D..1030 ; Other_Alphabetic # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU
360 1031 ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN E
361 1032 ; Other_Alphabetic # Mn MYANMAR VOWEL SIGN AI
362 1036 ; Other_Alphabetic # Mn MYANMAR SIGN ANUSVARA
363 1038 ; Other_Alphabetic # Mc MYANMAR SIGN VISARGA
364 1056..1057 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
365 1058..1059 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
366 16EE..16F0 ; Other_Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL
367 1712..1713 ; Other_Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U
368 1732..1733 ; Other_Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U
369 1752..1753 ; Other_Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
370 1772..1773 ; Other_Alphabetic # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
371 17B6 ; Other_Alphabetic # Mc KHMER VOWEL SIGN AA
372 17B7..17BD ; Other_Alphabetic # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
373 17BE..17C5 ; Other_Alphabetic # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
374 17C6 ; Other_Alphabetic # Mn KHMER SIGN NIKAHIT
375 17C7..17C8 ; Other_Alphabetic # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU
376 18A9 ; Other_Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA
377 1920..1922 ; Other_Alphabetic # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
378 1923..1926 ; Other_Alphabetic # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU
379 1927..1928 ; Other_Alphabetic # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
380 1929..192B ; Other_Alphabetic # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
381 1930..1931 ; Other_Alphabetic # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
382 1932 ; Other_Alphabetic # Mn LIMBU SMALL LETTER ANUSVARA
383 1933..1938 ; Other_Alphabetic # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
384 2160..2183 ; Other_Alphabetic # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED
385 FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
386 1034A ; Other_Alphabetic # Nl GOTHIC LETTER NINE HUNDRED
388 # Total code points: 429
390 # ================================================
392 3006 ; Ideographic # Lo IDEOGRAPHIC CLOSING MARK
393 3007 ; Ideographic # Nl IDEOGRAPHIC NUMBER ZERO
394 3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
395 3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
396 3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
397 4E00..9FA5 ; Ideographic # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
398 F900..FA2D ; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
399 20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
400 2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
402 # Total code points: 71053
404 # ================================================
406 005E ; Diacritic # Sk CIRCUMFLEX ACCENT
407 0060 ; Diacritic # Sk GRAVE ACCENT
408 00A8 ; Diacritic # Sk DIAERESIS
409 00AF ; Diacritic # Sk MACRON
410 00B4 ; Diacritic # Sk ACUTE ACCENT
411 00B7 ; Diacritic # Po MIDDLE DOT
412 00B8 ; Diacritic # Sk CEDILLA
413 02B0..02C1 ; Diacritic # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP
414 02C2..02C5 ; Diacritic # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD
415 02C6..02D1 ; Diacritic # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON
416 02D2..02DF ; Diacritic # Sk [14] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER CROSS ACCENT
417 02E0..02E4 ; Diacritic # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
418 02E5..02ED ; Diacritic # Sk [9] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER UNASPIRATED
419 02EE ; Diacritic # Lm MODIFIER LETTER DOUBLE APOSTROPHE
420 02EF..02FF ; Diacritic # Sk [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW
421 0300..034E ; Diacritic # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW
422 0350..0357 ; Diacritic # Mn [8] COMBINING RIGHT ARROWHEAD ABOVE..COMBINING RIGHT HALF RING ABOVE
423 035D..0362 ; Diacritic # Mn [6] COMBINING DOUBLE BREVE..COMBINING DOUBLE RIGHTWARDS ARROW BELOW
424 0374..0375 ; Diacritic # Sk [2] GREEK NUMERAL SIGN..GREEK LOWER NUMERAL SIGN
425 037A ; Diacritic # Lm GREEK YPOGEGRAMMENI
426 0384..0385 ; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS
427 0483..0486 ; Diacritic # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA
428 0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
429 0591..05A1 ; Diacritic # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
430 05A3..05B9 ; Diacritic # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM
431 05BB..05BD ; Diacritic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
432 05BF ; Diacritic # Mn HEBREW POINT RAFE
433 05C1..05C2 ; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
434 05C4 ; Diacritic # Mn HEBREW MARK UPPER DOT
435 064B..0652 ; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN
436 0657..0658 ; Diacritic # Mn [2] ARABIC INVERTED DAMMA..ARABIC MARK NOON GHUNNA
437 06DF..06E0 ; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO
438 06E5..06E6 ; Diacritic # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH
439 06EA..06EC ; Diacritic # Mn [3] ARABIC EMPTY CENTRE LOW STOP..ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE
440 0730..074A ; Diacritic # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
441 07A6..07B0 ; Diacritic # Mn [11] THAANA ABAFILI..THAANA SUKUN
442 093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
443 094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
444 0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
445 09BC ; Diacritic # Mn BENGALI SIGN NUKTA
446 09CD ; Diacritic # Mn BENGALI SIGN VIRAMA
447 0A3C ; Diacritic # Mn GURMUKHI SIGN NUKTA
448 0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA
449 0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA
450 0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA
451 0B3C ; Diacritic # Mn ORIYA SIGN NUKTA
452 0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA
453 0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA
454 0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA
455 0CBC ; Diacritic # Mn KANNADA SIGN NUKTA
456 0CCD ; Diacritic # Mn KANNADA SIGN VIRAMA
457 0D4D ; Diacritic # Mn MALAYALAM SIGN VIRAMA
458 0DCA ; Diacritic # Mn SINHALA SIGN AL-LAKUNA
459 0E47..0E4C ; Diacritic # Mn [6] THAI CHARACTER MAITAIKHU..THAI CHARACTER THANTHAKHAT
460 0E4E ; Diacritic # Mn THAI CHARACTER YAMAKKAN
461 0EC8..0ECC ; Diacritic # Mn [5] LAO TONE MAI EK..LAO CANCELLATION MARK
462 0F18..0F19 ; Diacritic # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
463 0F35 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
464 0F37 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
465 0F39 ; Diacritic # Mn TIBETAN MARK TSA -PHRU
466 0F3E..0F3F ; Diacritic # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES
467 0F82..0F84 ; Diacritic # Mn [3] TIBETAN SIGN NYI ZLA NAA DA..TIBETAN MARK HALANTA
468 0F86..0F87 ; Diacritic # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS
469 0FC6 ; Diacritic # Mn TIBETAN SYMBOL PADMA GDAN
470 1037 ; Diacritic # Mn MYANMAR SIGN DOT BELOW
471 1039 ; Diacritic # Mn MYANMAR SIGN VIRAMA
472 17C9..17D3 ; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
473 17DD ; Diacritic # Mn KHMER SIGN ATTHACAN
474 1939..193B ; Diacritic # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
475 1D2C..1D61 ; Diacritic # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
476 1D62..1D6A ; Diacritic # L& [9] LATIN SUBSCRIPT SMALL LETTER I..GREEK SUBSCRIPT SMALL LETTER CHI
477 1FBD ; Diacritic # Sk GREEK KORONIS
478 1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI
479 1FCD..1FCF ; Diacritic # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI
480 1FDD..1FDF ; Diacritic # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI
481 1FED..1FEF ; Diacritic # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA
482 1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA
483 302A..302F ; Diacritic # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
484 3099..309A ; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
485 309B..309C ; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
486 30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
487 FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
488 FE20..FE23 ; Diacritic # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
489 FF3E ; Diacritic # Sk FULLWIDTH CIRCUMFLEX ACCENT
490 FF40 ; Diacritic # Sk FULLWIDTH GRAVE ACCENT
491 FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
492 FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
493 FFE3 ; Diacritic # Sk FULLWIDTH MACRON
494 1D167..1D169 ; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
495 1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
496 1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
497 1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
498 1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
500 # Total code points: 482
502 # ================================================
504 00B7 ; Extender # Po MIDDLE DOT
505 02D0..02D1 ; Extender # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON
506 0640 ; Extender # Lm ARABIC TATWEEL
507 0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK
508 0EC6 ; Extender # Lm LAO KO LA
509 1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
510 3005 ; Extender # Lm IDEOGRAPHIC ITERATION MARK
511 3031..3035 ; Extender # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
512 309D..309E ; Extender # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
513 30FC..30FE ; Extender # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
514 FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
516 # Total code points: 19
518 # ================================================
520 02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
521 02C0..02C1 ; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP
522 02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
523 0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI
524 037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI
525 1D2C..1D61 ; Other_Lowercase # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI
526 2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND
527 24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
529 # Total code points: 114
531 # ================================================
533 2160..216F ; Other_Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND
534 24B6..24CF ; Other_Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z
536 # Total code points: 42
538 # ================================================
540 FDD0..FDEF ; Noncharacter_Code_Point # Cn [32]
541 FFFE..FFFF ; Noncharacter_Code_Point # Cn [2]
542 1FFFE..1FFFF ; Noncharacter_Code_Point # Cn [2]
543 2FFFE..2FFFF ; Noncharacter_Code_Point # Cn [2]
544 3FFFE..3FFFF ; Noncharacter_Code_Point # Cn [2]
545 4FFFE..4FFFF ; Noncharacter_Code_Point # Cn [2]
546 5FFFE..5FFFF ; Noncharacter_Code_Point # Cn [2]
547 6FFFE..6FFFF ; Noncharacter_Code_Point # Cn [2]
548 7FFFE..7FFFF ; Noncharacter_Code_Point # Cn [2]
549 8FFFE..8FFFF ; Noncharacter_Code_Point # Cn [2]
550 9FFFE..9FFFF ; Noncharacter_Code_Point # Cn [2]
551 AFFFE..AFFFF ; Noncharacter_Code_Point # Cn [2]
552 BFFFE..BFFFF ; Noncharacter_Code_Point # Cn [2]
553 CFFFE..CFFFF ; Noncharacter_Code_Point # Cn [2]
554 DFFFE..DFFFF ; Noncharacter_Code_Point # Cn [2]
555 EFFFE..EFFFF ; Noncharacter_Code_Point # Cn [2]
556 FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2]
557 10FFFE..10FFFF; Noncharacter_Code_Point # Cn [2]
559 # Total code points: 66
561 # ================================================
563 09BE ; Other_Grapheme_Extend # Mc BENGALI VOWEL SIGN AA
564 09D7 ; Other_Grapheme_Extend # Mc BENGALI AU LENGTH MARK
565 0B3E ; Other_Grapheme_Extend # Mc ORIYA VOWEL SIGN AA
566 0B57 ; Other_Grapheme_Extend # Mc ORIYA AU LENGTH MARK
567 0BBE ; Other_Grapheme_Extend # Mc TAMIL VOWEL SIGN AA
568 0BD7 ; Other_Grapheme_Extend # Mc TAMIL AU LENGTH MARK
569 0CC2 ; Other_Grapheme_Extend # Mc KANNADA VOWEL SIGN UU
570 0CD5..0CD6 ; Other_Grapheme_Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
571 0D3E ; Other_Grapheme_Extend # Mc MALAYALAM VOWEL SIGN AA
572 0D57 ; Other_Grapheme_Extend # Mc MALAYALAM AU LENGTH MARK
573 0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA
574 0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA
575 1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM
576 1D16E..1D16F ; Other_Grapheme_Extend # Mc [2] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-2
578 # Total code points: 16
580 # ================================================
582 034F ; Grapheme_Link # Mn COMBINING GRAPHEME JOINER
583 094D ; Grapheme_Link # Mn DEVANAGARI SIGN VIRAMA
584 09CD ; Grapheme_Link # Mn BENGALI SIGN VIRAMA
585 0A4D ; Grapheme_Link # Mn GURMUKHI SIGN VIRAMA
586 0ACD ; Grapheme_Link # Mn GUJARATI SIGN VIRAMA
587 0B4D ; Grapheme_Link # Mn ORIYA SIGN VIRAMA
588 0BCD ; Grapheme_Link # Mn TAMIL SIGN VIRAMA
589 0C4D ; Grapheme_Link # Mn TELUGU SIGN VIRAMA
590 0CCD ; Grapheme_Link # Mn KANNADA SIGN VIRAMA
591 0D4D ; Grapheme_Link # Mn MALAYALAM SIGN VIRAMA
592 0DCA ; Grapheme_Link # Mn SINHALA SIGN AL-LAKUNA
593 0E3A ; Grapheme_Link # Mn THAI CHARACTER PHINTHU
594 1039 ; Grapheme_Link # Mn MYANMAR SIGN VIRAMA
595 17D2 ; Grapheme_Link # Mn KHMER SIGN COENG
597 # Total code points: 14
599 # ================================================
601 2FF0..2FF1 ; IDS_Binary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW
602 2FF4..2FFB ; IDS_Binary_Operator # So [8] IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
604 # Total code points: 10
606 # ================================================
608 2FF2..2FF3 ; IDS_Trinary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO MIDDLE AND RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO MIDDLE AND BELOW
610 # Total code points: 2
612 # ================================================
614 2E80..2E99 ; Radical # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
615 2E9B..2EF3 ; Radical # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
616 2F00..2FD5 ; Radical # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
618 # Total code points: 329
620 # ================================================
622 3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
623 4E00..9FA5 ; Unified_Ideograph # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
624 FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
625 FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
626 FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
627 FA1F ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA1F
628 FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21
629 FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24
630 FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
631 20000..2A6D6 ; Unified_Ideograph # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
633 # Total code points: 70207
635 # ================================================
637 034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
638 115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
639 180B..180D ; Other_Default_Ignorable_Code_Point # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
640 200B ; Other_Default_Ignorable_Code_Point # Zs ZERO WIDTH SPACE
641 2064..2069 ; Other_Default_Ignorable_Code_Point # Cn [6]
642 3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER
643 FE00..FE0F ; Other_Default_Ignorable_Code_Point # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
644 FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER
645 FFF0..FFF8 ; Other_Default_Ignorable_Code_Point # Cn [9]
646 E0000 ; Other_Default_Ignorable_Code_Point # Cn
647 E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30]
648 E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128]
649 E0100..E01EF ; Other_Default_Ignorable_Code_Point # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
650 E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600]
652 # Total code points: 4039
654 # ================================================
656 0340..0341 ; Deprecated # Mn [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK
657 17A3 ; Deprecated # Lo KHMER INDEPENDENT VOWEL QAQ
658 17D3 ; Deprecated # Mn KHMER SIGN BATHAMASAT
659 206A..206F ; Deprecated # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
661 # Total code points: 10
663 # ================================================
665 0069..006A ; Soft_Dotted # L& [2] LATIN SMALL LETTER I..LATIN SMALL LETTER J
666 012F ; Soft_Dotted # L& LATIN SMALL LETTER I WITH OGONEK
667 0268 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE
668 0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
669 0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE
670 1D62 ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER I
671 1E2D ; Soft_Dotted # L& LATIN SMALL LETTER I WITH TILDE BELOW
672 1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
673 2071 ; Soft_Dotted # L& SUPERSCRIPT LATIN SMALL LETTER I
675 # Total code points: 10
677 # ================================================
679 0E40..0E44 ; Logical_Order_Exception # Lo [5] THAI CHARACTER SARA E..THAI CHARACTER SARA AI MAIMALAI
680 0EC0..0EC4 ; Logical_Order_Exception # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
682 # Total code points: 10
684 # ================================================
686 2118 ; Other_ID_Start # So SCRIPT CAPITAL P
687 212E ; Other_ID_Start # So ESTIMATED SYMBOL
688 309B..309C ; Other_ID_Start # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
690 # Total code points: 4
https://perl5.git.perl.org / perl5.git / blob