2 # Date: 2002-03-19,23:31:21 GMT [MD]
4 # Unicode Character Database: Extended Properties
5 # For documentation, see PropList.html
6 # Note: Unassigned and Noncharacter codepoints are omitted,
7 # except when listing Noncharacter or Cn.
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 2000..200A ; White_Space # Zs [11] EN QUAD..HAIR SPACE
18 2028 ; White_Space # Zl LINE SEPARATOR
19 2029 ; White_Space # Zp PARAGRAPH SEPARATOR
20 202F ; White_Space # Zs NARROW NO-BREAK SPACE
21 3000 ; White_Space # Zs IDEOGRAPHIC SPACE
23 # Total code points: 24
25 # ================================================
27 200E..200F ; Bidi_Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
28 202A..202E ; Bidi_Control # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
30 # Total code points: 7
32 # ================================================
34 200C..200D ; Join_Control # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
36 # Total code points: 2
38 # ================================================
40 002D ; Dash # Pd HYPHEN-MINUS
41 00AD ; Dash # Pd SOFT HYPHEN
42 058A ; Dash # Pd ARMENIAN HYPHEN
43 1806 ; Dash # Pd MONGOLIAN TODO SOFT HYPHEN
44 2010..2015 ; Dash # Pd [6] HYPHEN..HORIZONTAL BAR
45 207B ; Dash # Sm SUPERSCRIPT MINUS
46 208B ; Dash # Sm SUBSCRIPT MINUS
47 2212 ; Dash # Sm MINUS SIGN
48 301C ; Dash # Pd WAVE DASH
49 3030 ; Dash # Pd WAVY DASH
50 FE31..FE32 ; Dash # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH
51 FE58 ; Dash # Pd SMALL EM DASH
52 FE63 ; Dash # Pd SMALL HYPHEN-MINUS
53 FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS
55 # Total code points: 20
57 # ================================================
59 002D ; Hyphen # Pd HYPHEN-MINUS
60 00AD ; Hyphen # Pd SOFT HYPHEN
61 058A ; Hyphen # Pd ARMENIAN HYPHEN
62 1806 ; Hyphen # Pd MONGOLIAN TODO SOFT HYPHEN
63 2010..2011 ; Hyphen # Pd [2] HYPHEN..NON-BREAKING HYPHEN
64 30FB ; Hyphen # Pc KATAKANA MIDDLE DOT
65 FE63 ; Hyphen # Pd SMALL HYPHEN-MINUS
66 FF0D ; Hyphen # Pd FULLWIDTH HYPHEN-MINUS
67 FF65 ; Hyphen # Pc HALFWIDTH KATAKANA MIDDLE DOT
69 # Total code points: 10
71 # ================================================
73 0022 ; Quotation_Mark # Po QUOTATION MARK
74 0027 ; Quotation_Mark # Po APOSTROPHE
75 00AB ; Quotation_Mark # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
76 00BB ; Quotation_Mark # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
77 2018 ; Quotation_Mark # Pi LEFT SINGLE QUOTATION MARK
78 2019 ; Quotation_Mark # Pf RIGHT SINGLE QUOTATION MARK
79 201A ; Quotation_Mark # Ps SINGLE LOW-9 QUOTATION MARK
80 201B..201C ; Quotation_Mark # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK
81 201D ; Quotation_Mark # Pf RIGHT DOUBLE QUOTATION MARK
82 201E ; Quotation_Mark # Ps DOUBLE LOW-9 QUOTATION MARK
83 201F ; Quotation_Mark # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK
84 2039 ; Quotation_Mark # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK
85 203A ; Quotation_Mark # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
86 300C ; Quotation_Mark # Ps LEFT CORNER BRACKET
87 300D ; Quotation_Mark # Pe RIGHT CORNER BRACKET
88 300E ; Quotation_Mark # Ps LEFT WHITE CORNER BRACKET
89 300F ; Quotation_Mark # Pe RIGHT WHITE CORNER BRACKET
90 301D ; Quotation_Mark # Ps REVERSED DOUBLE PRIME QUOTATION MARK
91 301E..301F ; Quotation_Mark # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK
92 FE41 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET
93 FE42 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET
94 FE43 ; Quotation_Mark # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET
95 FE44 ; Quotation_Mark # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET
96 FF02 ; Quotation_Mark # Po FULLWIDTH QUOTATION MARK
97 FF07 ; Quotation_Mark # Po FULLWIDTH APOSTROPHE
98 FF62 ; Quotation_Mark # Ps HALFWIDTH LEFT CORNER BRACKET
99 FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET
101 # Total code points: 29
103 # ================================================
105 0021 ; Terminal_Punctuation # Po EXCLAMATION MARK
106 002C ; Terminal_Punctuation # Po COMMA
107 002E ; Terminal_Punctuation # Po FULL STOP
108 003A..003B ; Terminal_Punctuation # Po [2] COLON..SEMICOLON
109 003F ; Terminal_Punctuation # Po QUESTION MARK
110 037E ; Terminal_Punctuation # Po GREEK QUESTION MARK
111 0387 ; Terminal_Punctuation # Po GREEK ANO TELEIA
112 0589 ; Terminal_Punctuation # Po ARMENIAN FULL STOP
113 060C ; Terminal_Punctuation # Po ARABIC COMMA
114 061B ; Terminal_Punctuation # Po ARABIC SEMICOLON
115 061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK
116 06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP
117 0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION
118 070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS
119 0964..0965 ; Terminal_Punctuation # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
120 0E5A..0E5B ; Terminal_Punctuation # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT
121 104A..104B ; Terminal_Punctuation # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION
122 1361..1368 ; Terminal_Punctuation # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR
123 166D..166E ; Terminal_Punctuation # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP
124 16EB..16ED ; Terminal_Punctuation # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION
125 17D4..17D6 ; Terminal_Punctuation # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH
126 17DA ; Terminal_Punctuation # Po KHMER SIGN KOOMUUT
127 1802..1805 ; Terminal_Punctuation # Po [4] MONGOLIAN COMMA..MONGOLIAN FOUR DOTS
128 1808..1809 ; Terminal_Punctuation # Po [2] MONGOLIAN MANCHU COMMA..MONGOLIAN MANCHU FULL STOP
129 203C..203D ; Terminal_Punctuation # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG
130 2048..2049 ; Terminal_Punctuation # Po [2] QUESTION EXCLAMATION MARK..EXCLAMATION QUESTION MARK
131 3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP
132 FE50..FE52 ; Terminal_Punctuation # Po [3] SMALL COMMA..SMALL FULL STOP
133 FE54..FE57 ; Terminal_Punctuation # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK
134 FF01 ; Terminal_Punctuation # Po FULLWIDTH EXCLAMATION MARK
135 FF0C ; Terminal_Punctuation # Po FULLWIDTH COMMA
136 FF0E ; Terminal_Punctuation # Po FULLWIDTH FULL STOP
137 FF1A..FF1B ; Terminal_Punctuation # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON
138 FF1F ; Terminal_Punctuation # Po FULLWIDTH QUESTION MARK
139 FF61 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC FULL STOP
140 FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA
142 # Total code points: 75
144 # ================================================
146 0028 ; Other_Math # Ps LEFT PARENTHESIS
147 0029 ; Other_Math # Pe RIGHT PARENTHESIS
148 002A ; Other_Math # Po ASTERISK
149 002D ; Other_Math # Pd HYPHEN-MINUS
150 002F ; Other_Math # Po SOLIDUS
151 005B ; Other_Math # Ps LEFT SQUARE BRACKET
152 005C ; Other_Math # Po REVERSE SOLIDUS
153 005D ; Other_Math # Pe RIGHT SQUARE BRACKET
154 005E ; Other_Math # Sk CIRCUMFLEX ACCENT
155 007B ; Other_Math # Ps LEFT CURLY BRACKET
156 007D ; Other_Math # Pe RIGHT CURLY BRACKET
157 2016 ; Other_Math # Po DOUBLE VERTICAL LINE
158 2032..2034 ; Other_Math # Po [3] PRIME..TRIPLE PRIME
159 207D ; Other_Math # Ps SUPERSCRIPT LEFT PARENTHESIS
160 207E ; Other_Math # Pe SUPERSCRIPT RIGHT PARENTHESIS
161 208D ; Other_Math # Ps SUBSCRIPT LEFT PARENTHESIS
162 208E ; Other_Math # Pe SUBSCRIPT RIGHT PARENTHESIS
163 20D0..20DC ; Other_Math # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
164 20E1 ; Other_Math # Mn COMBINING LEFT RIGHT ARROW ABOVE
165 2102 ; Other_Math # L& DOUBLE-STRUCK CAPITAL C
166 210A..2113 ; Other_Math # L& [10] SCRIPT SMALL G..SCRIPT SMALL L
167 2115 ; Other_Math # L& DOUBLE-STRUCK CAPITAL N
168 2119..211D ; Other_Math # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R
169 2124 ; Other_Math # L& DOUBLE-STRUCK CAPITAL Z
170 2128 ; Other_Math # L& BLACK-LETTER CAPITAL Z
171 212C..212D ; Other_Math # L& [2] SCRIPT CAPITAL B..BLACK-LETTER CAPITAL C
172 212F..2131 ; Other_Math # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F
173 2133..2134 ; Other_Math # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O
174 2135..2138 ; Other_Math # Lo [4] ALEF SYMBOL..DALET SYMBOL
175 FE35 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS
176 FE36 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS
177 FE37 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET
178 FE38 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET
179 FE59 ; Other_Math # Ps SMALL LEFT PARENTHESIS
180 FE5A ; Other_Math # Pe SMALL RIGHT PARENTHESIS
181 FE5B ; Other_Math # Ps SMALL LEFT CURLY BRACKET
182 FE5C ; Other_Math # Pe SMALL RIGHT CURLY BRACKET
183 FE61 ; Other_Math # Po SMALL ASTERISK
184 FE63 ; Other_Math # Pd SMALL HYPHEN-MINUS
185 FE68 ; Other_Math # Po SMALL REVERSE SOLIDUS
186 FF08 ; Other_Math # Ps FULLWIDTH LEFT PARENTHESIS
187 FF09 ; Other_Math # Pe FULLWIDTH RIGHT PARENTHESIS
188 FF0A ; Other_Math # Po FULLWIDTH ASTERISK
189 FF0D ; Other_Math # Pd FULLWIDTH HYPHEN-MINUS
190 FF0F ; Other_Math # Po FULLWIDTH SOLIDUS
191 FF3B ; Other_Math # Ps FULLWIDTH LEFT SQUARE BRACKET
192 FF3C ; Other_Math # Po FULLWIDTH REVERSE SOLIDUS
193 FF3D ; Other_Math # Pe FULLWIDTH RIGHT SQUARE BRACKET
194 FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT
195 FF5B ; Other_Math # Ps FULLWIDTH LEFT CURLY BRACKET
196 FF5D ; Other_Math # Pe FULLWIDTH RIGHT CURLY BRACKET
197 1D400..1D454 ; Other_Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
198 1D456..1D49C ; Other_Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A
199 1D49E..1D49F ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D
200 1D4A2 ; Other_Math # L& MATHEMATICAL SCRIPT CAPITAL G
201 1D4A5..1D4A6 ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K
202 1D4A9..1D4AC ; Other_Math # L& [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q
203 1D4AE..1D4B9 ; Other_Math # L& [12] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT SMALL D
204 1D4BB ; Other_Math # L& MATHEMATICAL SCRIPT SMALL F
205 1D4BD..1D4C0 ; Other_Math # L& [4] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL K
206 1D4C2..1D4C3 ; Other_Math # L& [2] MATHEMATICAL SCRIPT SMALL M..MATHEMATICAL SCRIPT SMALL N
207 1D4C5..1D505 ; Other_Math # L& [65] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL FRAKTUR CAPITAL B
208 1D507..1D50A ; Other_Math # L& [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G
209 1D50D..1D514 ; Other_Math # L& [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q
210 1D516..1D51C ; Other_Math # L& [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y
211 1D51E..1D539 ; Other_Math # L& [28] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B
212 1D53B..1D53E ; Other_Math # L& [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G
213 1D540..1D544 ; Other_Math # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M
214 1D546 ; Other_Math # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O
215 1D54A..1D550 ; Other_Math # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y
216 1D552..1D6A3 ; Other_Math # L& [338] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL MONOSPACE SMALL Z
217 1D6A8..1D6C0 ; Other_Math # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA
218 1D6C2..1D6DA ; Other_Math # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA
219 1D6DC..1D6FA ; Other_Math # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA
220 1D6FC..1D714 ; Other_Math # L& [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA
221 1D716..1D734 ; Other_Math # L& [31] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA
222 1D736..1D74E ; Other_Math # L& [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA
223 1D750..1D76E ; Other_Math # L& [31] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA
224 1D770..1D788 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA
225 1D78A..1D7A8 ; Other_Math # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA
226 1D7AA..1D7C2 ; Other_Math # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA
227 1D7C4..1D7C9 ; Other_Math # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL
228 1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
230 # Total code points: 1066
232 # ================================================
234 0030..0039 ; Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE
235 0041..0046 ; Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F
236 0061..0066 ; Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F
237 FF10..FF19 ; Hex_Digit # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
238 FF21..FF26 ; Hex_Digit # L& [6] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER F
239 FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER F
241 # Total code points: 44
243 # ================================================
245 0030..0039 ; ASCII_Hex_Digit # Nd [10] DIGIT ZERO..DIGIT NINE
246 0041..0046 ; ASCII_Hex_Digit # L& [6] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER F
247 0061..0066 ; ASCII_Hex_Digit # L& [6] LATIN SMALL LETTER A..LATIN SMALL LETTER F
249 # Total code points: 22
251 # ================================================
253 0345 ; Other_Alphabetic # Mn COMBINING GREEK YPOGEGRAMMENI
254 05B0..05B9 ; Other_Alphabetic # Mn [10] HEBREW POINT SHEVA..HEBREW POINT HOLAM
255 05BB..05BD ; Other_Alphabetic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
256 05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE
257 05C1..05C2 ; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
258 05C4 ; Other_Alphabetic # Mn HEBREW MARK UPPER DOT
259 064B..0655 ; Other_Alphabetic # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
260 0670 ; Other_Alphabetic # Mn ARABIC LETTER SUPERSCRIPT ALEF
261 06D6..06DC ; Other_Alphabetic # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
262 06E1..06E4 ; Other_Alphabetic # Mn [4] ARABIC SMALL HIGH DOTLESS HEAD OF KHAH..ARABIC SMALL HIGH MADDA
263 06E7..06E8 ; Other_Alphabetic # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
264 06ED ; Other_Alphabetic # Mn ARABIC SMALL LOW MEEM
265 0711 ; Other_Alphabetic # Mn SYRIAC LETTER SUPERSCRIPT ALAPH
266 0730..073F ; Other_Alphabetic # Mn [16] SYRIAC PTHAHA ABOVE..SYRIAC RWAHA
267 07A6..07B0 ; Other_Alphabetic # Mn [11] THAANA ABAFILI..THAANA SUKUN
268 0901..0902 ; Other_Alphabetic # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA
269 0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA
270 093E..0940 ; Other_Alphabetic # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II
271 0941..0948 ; Other_Alphabetic # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
272 0949..094C ; Other_Alphabetic # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU
273 0962..0963 ; Other_Alphabetic # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
274 0981 ; Other_Alphabetic # Mn BENGALI SIGN CANDRABINDU
275 0982..0983 ; Other_Alphabetic # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA
276 09BE..09C0 ; Other_Alphabetic # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II
277 09C1..09C4 ; Other_Alphabetic # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR
278 09C7..09C8 ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI
279 09CB..09CC ; Other_Alphabetic # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU
280 09D7 ; Other_Alphabetic # Mc BENGALI AU LENGTH MARK
281 09E2..09E3 ; Other_Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
282 0A02 ; Other_Alphabetic # Mn GURMUKHI SIGN BINDI
283 0A3E..0A40 ; Other_Alphabetic # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II
284 0A41..0A42 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU
285 0A47..0A48 ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI
286 0A4B..0A4C ; Other_Alphabetic # Mn [2] GURMUKHI VOWEL SIGN OO..GURMUKHI VOWEL SIGN AU
287 0A70..0A71 ; Other_Alphabetic # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK
288 0A81..0A82 ; Other_Alphabetic # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA
289 0A83 ; Other_Alphabetic # Mc GUJARATI SIGN VISARGA
290 0ABE..0AC0 ; Other_Alphabetic # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II
291 0AC1..0AC5 ; Other_Alphabetic # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E
292 0AC7..0AC8 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
293 0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O
294 0ACB..0ACC ; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU
295 0B01 ; Other_Alphabetic # Mn ORIYA SIGN CANDRABINDU
296 0B02..0B03 ; Other_Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
297 0B3E ; Other_Alphabetic # Mc ORIYA VOWEL SIGN AA
298 0B3F ; Other_Alphabetic # Mn ORIYA VOWEL SIGN I
299 0B40 ; Other_Alphabetic # Mc ORIYA VOWEL SIGN II
300 0B41..0B43 ; Other_Alphabetic # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R
301 0B47..0B48 ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
302 0B4B..0B4C ; Other_Alphabetic # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
303 0B56 ; Other_Alphabetic # Mn ORIYA AI LENGTH MARK
304 0B57 ; Other_Alphabetic # Mc ORIYA AU LENGTH MARK
305 0B82 ; Other_Alphabetic # Mn TAMIL SIGN ANUSVARA
306 0BBE..0BBF ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I
307 0BC0 ; Other_Alphabetic # Mn TAMIL VOWEL SIGN II
308 0BC1..0BC2 ; Other_Alphabetic # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU
309 0BC6..0BC8 ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI
310 0BCA..0BCC ; Other_Alphabetic # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU
311 0BD7 ; Other_Alphabetic # Mc TAMIL AU LENGTH MARK
312 0C01..0C03 ; Other_Alphabetic # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
313 0C3E..0C40 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
314 0C41..0C44 ; Other_Alphabetic # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR
315 0C46..0C48 ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
316 0C4A..0C4C ; Other_Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU
317 0C55..0C56 ; Other_Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
318 0C82..0C83 ; Other_Alphabetic # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
319 0CBE ; Other_Alphabetic # Mc KANNADA VOWEL SIGN AA
320 0CBF ; Other_Alphabetic # Mn KANNADA VOWEL SIGN I
321 0CC0..0CC4 ; Other_Alphabetic # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR
322 0CC6 ; Other_Alphabetic # Mn KANNADA VOWEL SIGN E
323 0CC7..0CC8 ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
324 0CCA..0CCB ; Other_Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
325 0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU
326 0CD5..0CD6 ; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
327 0D02..0D03 ; Other_Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
328 0D3E..0D40 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
329 0D41..0D43 ; Other_Alphabetic # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R
330 0D46..0D48 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
331 0D4A..0D4C ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
332 0D57 ; Other_Alphabetic # Mc MALAYALAM AU LENGTH MARK
333 0D82..0D83 ; Other_Alphabetic # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA
334 0DCF..0DD1 ; Other_Alphabetic # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA
335 0DD2..0DD4 ; Other_Alphabetic # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA
336 0DD6 ; Other_Alphabetic # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA
337 0DD8..0DDF ; Other_Alphabetic # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA
338 0DF2..0DF3 ; Other_Alphabetic # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA
339 0E31 ; Other_Alphabetic # Mn THAI CHARACTER MAI HAN-AKAT
340 0E34..0E3A ; Other_Alphabetic # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU
341 0E4D ; Other_Alphabetic # Mn THAI CHARACTER NIKHAHIT
342 0EB1 ; Other_Alphabetic # Mn LAO VOWEL SIGN MAI KAN
343 0EB4..0EB9 ; Other_Alphabetic # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU
344 0EBB..0EBC ; Other_Alphabetic # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO
345 0ECD ; Other_Alphabetic # Mn LAO NIGGAHITA
346 0F71..0F7E ; Other_Alphabetic # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO
347 0F7F ; Other_Alphabetic # Mc TIBETAN SIGN RNAM BCAD
348 0F80..0F81 ; Other_Alphabetic # Mn [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II
349 0F90..0F97 ; Other_Alphabetic # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA
350 0F99..0FBC ; Other_Alphabetic # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA
351 102C ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN AA
352 102D..1030 ; Other_Alphabetic # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU
353 1031 ; Other_Alphabetic # Mc MYANMAR VOWEL SIGN E
354 1032 ; Other_Alphabetic # Mn MYANMAR VOWEL SIGN AI
355 1036 ; Other_Alphabetic # Mn MYANMAR SIGN ANUSVARA
356 1038 ; Other_Alphabetic # Mc MYANMAR SIGN VISARGA
357 1056..1057 ; Other_Alphabetic # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR
358 1058..1059 ; Other_Alphabetic # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
359 16EE..16F0 ; Other_Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL
360 1712..1713 ; Other_Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U
361 1732..1733 ; Other_Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U
362 1752..1753 ; Other_Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
363 1772..1773 ; Other_Alphabetic # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
364 17B4..17B6 ; Other_Alphabetic # Mc [3] KHMER VOWEL INHERENT AQ..KHMER VOWEL SIGN AA
365 17B7..17BD ; Other_Alphabetic # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
366 17BE..17C5 ; Other_Alphabetic # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU
367 17C6 ; Other_Alphabetic # Mn KHMER SIGN NIKAHIT
368 17C7..17C8 ; Other_Alphabetic # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU
369 18A9 ; Other_Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA
370 2160..2183 ; Other_Alphabetic # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED
371 FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
372 1034A ; Other_Alphabetic # Nl GOTHIC LETTER NINE HUNDRED
374 # Total code points: 398
376 # ================================================
378 3006 ; Ideographic # Lo IDEOGRAPHIC CLOSING MARK
379 3007 ; Ideographic # Nl IDEOGRAPHIC NUMBER ZERO
380 3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE
381 3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
382 3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
383 4E00..9FA5 ; Ideographic # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
384 F900..FA2D ; Ideographic # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D
385 20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
386 2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
388 # Total code points: 71053
390 # ================================================
392 005E ; Diacritic # Sk CIRCUMFLEX ACCENT
393 0060 ; Diacritic # Sk GRAVE ACCENT
394 00A8 ; Diacritic # Sk DIAERESIS
395 00AF ; Diacritic # Sk MACRON
396 00B4 ; Diacritic # Sk ACUTE ACCENT
397 00B7 ; Diacritic # Po MIDDLE DOT
398 00B8 ; Diacritic # Sk CEDILLA
399 02B0..02B8 ; Diacritic # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
400 02B9..02BA ; Diacritic # Sk [2] MODIFIER LETTER PRIME..MODIFIER LETTER DOUBLE PRIME
401 02BB..02C1 ; Diacritic # Lm [7] MODIFIER LETTER TURNED COMMA..MODIFIER LETTER REVERSED GLOTTAL STOP
402 02C2..02CF ; Diacritic # Sk [14] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER LOW ACUTE ACCENT
403 02D0..02D1 ; Diacritic # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON
404 02D2..02DF ; Diacritic # Sk [14] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER CROSS ACCENT
405 02E0..02E4 ; Diacritic # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
406 02E5..02ED ; Diacritic # Sk [9] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER UNASPIRATED
407 02EE ; Diacritic # Lm MODIFIER LETTER DOUBLE APOSTROPHE
408 0300..034E ; Diacritic # Mn [79] COMBINING GRAVE ACCENT..COMBINING UPWARDS ARROW BELOW
409 0360..0362 ; Diacritic # Mn [3] COMBINING DOUBLE TILDE..COMBINING DOUBLE RIGHTWARDS ARROW BELOW
410 0374..0375 ; Diacritic # Sk [2] GREEK NUMERAL SIGN..GREEK LOWER NUMERAL SIGN
411 037A ; Diacritic # Lm GREEK YPOGEGRAMMENI
412 0384..0385 ; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS
413 0483..0486 ; Diacritic # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA
414 0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
415 0591..05A1 ; Diacritic # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER
416 05A3..05B9 ; Diacritic # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM
417 05BB..05BD ; Diacritic # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG
418 05BF ; Diacritic # Mn HEBREW POINT RAFE
419 05C1..05C2 ; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
420 05C4 ; Diacritic # Mn HEBREW MARK UPPER DOT
421 064B..0652 ; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN
422 06DF..06E0 ; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO
423 06E5..06E6 ; Diacritic # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH
424 06EA..06EC ; Diacritic # Mn [3] ARABIC EMPTY CENTRE LOW STOP..ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE
425 0730..074A ; Diacritic # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
426 07A6..07B0 ; Diacritic # Mn [11] THAANA ABAFILI..THAANA SUKUN
427 093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA
428 094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA
429 0951..0954 ; Diacritic # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT
430 09BC ; Diacritic # Mn BENGALI SIGN NUKTA
431 09CD ; Diacritic # Mn BENGALI SIGN VIRAMA
432 0A3C ; Diacritic # Mn GURMUKHI SIGN NUKTA
433 0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA
434 0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA
435 0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA
436 0B3C ; Diacritic # Mn ORIYA SIGN NUKTA
437 0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA
438 0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA
439 0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA
440 0CCD ; Diacritic # Mn KANNADA SIGN VIRAMA
441 0D4D ; Diacritic # Mn MALAYALAM SIGN VIRAMA
442 0DCA ; Diacritic # Mn SINHALA SIGN AL-LAKUNA
443 0E47..0E4C ; Diacritic # Mn [6] THAI CHARACTER MAITAIKHU..THAI CHARACTER THANTHAKHAT
444 0E4E ; Diacritic # Mn THAI CHARACTER YAMAKKAN
445 0EC8..0ECC ; Diacritic # Mn [5] LAO TONE MAI EK..LAO CANCELLATION MARK
446 0F18..0F19 ; Diacritic # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
447 0F35 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
448 0F37 ; Diacritic # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
449 0F39 ; Diacritic # Mn TIBETAN MARK TSA -PHRU
450 0F3E..0F3F ; Diacritic # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES
451 0F82..0F84 ; Diacritic # Mn [3] TIBETAN SIGN NYI ZLA NAA DA..TIBETAN MARK HALANTA
452 0F86..0F87 ; Diacritic # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS
453 0FC6 ; Diacritic # Mn TIBETAN SYMBOL PADMA GDAN
454 1037 ; Diacritic # Mn MYANMAR SIGN DOT BELOW
455 1039 ; Diacritic # Mn MYANMAR SIGN VIRAMA
456 17C9..17D3 ; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
457 1FBD ; Diacritic # Sk GREEK KORONIS
458 1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI
459 1FCD..1FCF ; Diacritic # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI
460 1FDD..1FDF ; Diacritic # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI
461 1FED..1FEF ; Diacritic # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA
462 1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA
463 302A..302F ; Diacritic # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
464 3099..309A ; Diacritic # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
465 309B..309C ; Diacritic # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
466 30FC ; Diacritic # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK
467 FB1E ; Diacritic # Mn HEBREW POINT JUDEO-SPANISH VARIKA
468 FE20..FE23 ; Diacritic # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF
469 FF3E ; Diacritic # Sk FULLWIDTH CIRCUMFLEX ACCENT
470 FF40 ; Diacritic # Sk FULLWIDTH GRAVE ACCENT
471 FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
472 FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
473 FFE3 ; Diacritic # Sk FULLWIDTH MACRON
474 1D167..1D169 ; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
475 1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
476 1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
477 1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
478 1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
480 # Total code points: 384
482 # ================================================
484 00B7 ; Extender # Po MIDDLE DOT
485 02D0..02D1 ; Extender # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON
486 0640 ; Extender # Lm ARABIC TATWEEL
487 0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK
488 0EC6 ; Extender # Lm LAO KO LA
489 1843 ; Extender # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
490 3005 ; Extender # Lm IDEOGRAPHIC ITERATION MARK
491 3031..3035 ; Extender # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
492 309D..309E ; Extender # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
493 30FC..30FE ; Extender # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
494 FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK
496 # Total code points: 19
498 # ================================================
500 02B0..02B8 ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y
501 02C0..02C1 ; Other_Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP
502 02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
503 0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI
504 037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI
505 2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND
506 24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
508 # Total code points: 60
510 # ================================================
512 2160..216F ; Other_Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND
513 24B6..24CF ; Other_Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z
515 # Total code points: 42
517 # ================================================
519 FDD0..FDEF ; Noncharacter_Code_Point # Cn [32]
520 FFFE..FFFF ; Noncharacter_Code_Point # Cn [2]
521 1FFFE..1FFFF ; Noncharacter_Code_Point # Cn [2]
522 2FFFE..2FFFF ; Noncharacter_Code_Point # Cn [2]
523 3FFFE..3FFFF ; Noncharacter_Code_Point # Cn [2]
524 4FFFE..4FFFF ; Noncharacter_Code_Point # Cn [2]
525 5FFFE..5FFFF ; Noncharacter_Code_Point # Cn [2]
526 6FFFE..6FFFF ; Noncharacter_Code_Point # Cn [2]
527 7FFFE..7FFFF ; Noncharacter_Code_Point # Cn [2]
528 8FFFE..8FFFF ; Noncharacter_Code_Point # Cn [2]
529 9FFFE..9FFFF ; Noncharacter_Code_Point # Cn [2]
530 AFFFE..AFFFF ; Noncharacter_Code_Point # Cn [2]
531 BFFFE..BFFFF ; Noncharacter_Code_Point # Cn [2]
532 CFFFE..CFFFF ; Noncharacter_Code_Point # Cn [2]
533 DFFFE..DFFFF ; Noncharacter_Code_Point # Cn [2]
534 EFFFE..EFFFF ; Noncharacter_Code_Point # Cn [2]
535 FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2]
536 10FFFE..10FFFF; Noncharacter_Code_Point # Cn [2]
538 # Total code points: 66
540 # ================================================
542 FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
544 # Total code points: 2
546 # ================================================
548 094D ; Grapheme_Link # Mn DEVANAGARI SIGN VIRAMA
549 09CD ; Grapheme_Link # Mn BENGALI SIGN VIRAMA
550 0A4D ; Grapheme_Link # Mn GURMUKHI SIGN VIRAMA
551 0ACD ; Grapheme_Link # Mn GUJARATI SIGN VIRAMA
552 0B4D ; Grapheme_Link # Mn ORIYA SIGN VIRAMA
553 0BCD ; Grapheme_Link # Mn TAMIL SIGN VIRAMA
554 0C4D ; Grapheme_Link # Mn TELUGU SIGN VIRAMA
555 0CCD ; Grapheme_Link # Mn KANNADA SIGN VIRAMA
556 0D4D ; Grapheme_Link # Mn MALAYALAM SIGN VIRAMA
557 0DCA ; Grapheme_Link # Mn SINHALA SIGN AL-LAKUNA
558 0E3A ; Grapheme_Link # Mn THAI CHARACTER PHINTHU
559 1039 ; Grapheme_Link # Mn MYANMAR SIGN VIRAMA
560 17D2 ; Grapheme_Link # Mn KHMER SIGN COENG
562 # Total code points: 13
564 # ================================================
566 2FF0..2FF1 ; IDS_Binary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW
567 2FF4..2FFB ; IDS_Binary_Operator # So [8] IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
569 # Total code points: 10
571 # ================================================
573 2FF2..2FF3 ; IDS_Trinary_Operator # So [2] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO MIDDLE AND RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO MIDDLE AND BELOW
575 # Total code points: 2
577 # ================================================
579 2E80..2E99 ; Radical # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
580 2E9B..2EF3 ; Radical # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
581 2F00..2FD5 ; Radical # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
583 # Total code points: 329
585 # ================================================
587 3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
588 4E00..9FA5 ; Unified_Ideograph # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5
589 FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
590 FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
591 FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
592 FA1F ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA1F
593 FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21
594 FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24
595 FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
596 20000..2A6D6 ; Unified_Ideograph # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
598 # Total code points: 70207
600 # ================================================
602 180B..180D ; Other_Default_Ignorable_Code_Point # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
603 2060..2063 ; Other_Default_Ignorable_Code_Point # Cf [4] WORD JOINER..INVISIBLE SEPARATOR
604 2064..2069 ; Other_Default_Ignorable_Code_Point # Cn [6]
605 206A..206F ; Other_Default_Ignorable_Code_Point # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
606 FE00..FE0F ; Other_Default_Ignorable_Code_Point # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
607 FFF0..FFF8 ; Other_Default_Ignorable_Code_Point # Cn [9]
608 FFF9..FFFB ; Other_Default_Ignorable_Code_Point # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
609 E0000 ; Other_Default_Ignorable_Code_Point # Cn
610 E0001 ; Other_Default_Ignorable_Code_Point # Cf LANGUAGE TAG
611 E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30]
612 E0020..E007F ; Other_Default_Ignorable_Code_Point # Cf [96] TAG SPACE..CANCEL TAG
613 E0080..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3968]
615 # Total code points: 4143
617 # ================================================
619 0340..0341 ; Deprecated # Mn [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK
620 206A..206F ; Deprecated # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
622 # Total code points: 8
624 # ================================================
626 0069..006A ; Soft_Dotted # L& [2] LATIN SMALL LETTER I..LATIN SMALL LETTER J
627 012F ; Soft_Dotted # L& LATIN SMALL LETTER I WITH OGONEK
628 0268 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE
629 0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
630 0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE
631 1E2D ; Soft_Dotted # L& LATIN SMALL LETTER I WITH TILDE BELOW
632 1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW
634 # Total code points: 8
636 # ================================================
638 0E40..0E44 ; Logical_Order_Exception # Lo [5] THAI CHARACTER SARA E..THAI CHARACTER SARA AI MAIMALAI
639 0EC0..0EC4 ; Logical_Order_Exception # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
641 # Total code points: 10
https://perl5.git.perl.org / perl5.git / blob