• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# -*- coding: utf-8 -*-
2#
3# NOTE: This file was auto-generated with MetaTools/buildUCD.py.
4# Source: https://unicode.org/Public/UNIDATA/Blocks.txt
5# License: http://unicode.org/copyright.html#License
6#
7# Blocks-11.0.0.txt
8# Date: 2017-10-16, 24:39:00 GMT [KW]
9# © 2017 Unicode®, Inc.
10# For terms of use, see http://www.unicode.org/terms_of_use.html
11#
12# Unicode Character Database
13# For documentation, see http://www.unicode.org/reports/tr44/
14#
15# Format:
16# Start Code..End Code; Block Name
17
18
19RANGES = [
20    0x0000,  # .. 0x007F ; Basic Latin
21    0x0080,  # .. 0x00FF ; Latin-1 Supplement
22    0x0100,  # .. 0x017F ; Latin Extended-A
23    0x0180,  # .. 0x024F ; Latin Extended-B
24    0x0250,  # .. 0x02AF ; IPA Extensions
25    0x02B0,  # .. 0x02FF ; Spacing Modifier Letters
26    0x0300,  # .. 0x036F ; Combining Diacritical Marks
27    0x0370,  # .. 0x03FF ; Greek and Coptic
28    0x0400,  # .. 0x04FF ; Cyrillic
29    0x0500,  # .. 0x052F ; Cyrillic Supplement
30    0x0530,  # .. 0x058F ; Armenian
31    0x0590,  # .. 0x05FF ; Hebrew
32    0x0600,  # .. 0x06FF ; Arabic
33    0x0700,  # .. 0x074F ; Syriac
34    0x0750,  # .. 0x077F ; Arabic Supplement
35    0x0780,  # .. 0x07BF ; Thaana
36    0x07C0,  # .. 0x07FF ; NKo
37    0x0800,  # .. 0x083F ; Samaritan
38    0x0840,  # .. 0x085F ; Mandaic
39    0x0860,  # .. 0x086F ; Syriac Supplement
40    0x0870,  # .. 0x089F ; No_Block
41    0x08A0,  # .. 0x08FF ; Arabic Extended-A
42    0x0900,  # .. 0x097F ; Devanagari
43    0x0980,  # .. 0x09FF ; Bengali
44    0x0A00,  # .. 0x0A7F ; Gurmukhi
45    0x0A80,  # .. 0x0AFF ; Gujarati
46    0x0B00,  # .. 0x0B7F ; Oriya
47    0x0B80,  # .. 0x0BFF ; Tamil
48    0x0C00,  # .. 0x0C7F ; Telugu
49    0x0C80,  # .. 0x0CFF ; Kannada
50    0x0D00,  # .. 0x0D7F ; Malayalam
51    0x0D80,  # .. 0x0DFF ; Sinhala
52    0x0E00,  # .. 0x0E7F ; Thai
53    0x0E80,  # .. 0x0EFF ; Lao
54    0x0F00,  # .. 0x0FFF ; Tibetan
55    0x1000,  # .. 0x109F ; Myanmar
56    0x10A0,  # .. 0x10FF ; Georgian
57    0x1100,  # .. 0x11FF ; Hangul Jamo
58    0x1200,  # .. 0x137F ; Ethiopic
59    0x1380,  # .. 0x139F ; Ethiopic Supplement
60    0x13A0,  # .. 0x13FF ; Cherokee
61    0x1400,  # .. 0x167F ; Unified Canadian Aboriginal Syllabics
62    0x1680,  # .. 0x169F ; Ogham
63    0x16A0,  # .. 0x16FF ; Runic
64    0x1700,  # .. 0x171F ; Tagalog
65    0x1720,  # .. 0x173F ; Hanunoo
66    0x1740,  # .. 0x175F ; Buhid
67    0x1760,  # .. 0x177F ; Tagbanwa
68    0x1780,  # .. 0x17FF ; Khmer
69    0x1800,  # .. 0x18AF ; Mongolian
70    0x18B0,  # .. 0x18FF ; Unified Canadian Aboriginal Syllabics Extended
71    0x1900,  # .. 0x194F ; Limbu
72    0x1950,  # .. 0x197F ; Tai Le
73    0x1980,  # .. 0x19DF ; New Tai Lue
74    0x19E0,  # .. 0x19FF ; Khmer Symbols
75    0x1A00,  # .. 0x1A1F ; Buginese
76    0x1A20,  # .. 0x1AAF ; Tai Tham
77    0x1AB0,  # .. 0x1AFF ; Combining Diacritical Marks Extended
78    0x1B00,  # .. 0x1B7F ; Balinese
79    0x1B80,  # .. 0x1BBF ; Sundanese
80    0x1BC0,  # .. 0x1BFF ; Batak
81    0x1C00,  # .. 0x1C4F ; Lepcha
82    0x1C50,  # .. 0x1C7F ; Ol Chiki
83    0x1C80,  # .. 0x1C8F ; Cyrillic Extended-C
84    0x1C90,  # .. 0x1CBF ; Georgian Extended
85    0x1CC0,  # .. 0x1CCF ; Sundanese Supplement
86    0x1CD0,  # .. 0x1CFF ; Vedic Extensions
87    0x1D00,  # .. 0x1D7F ; Phonetic Extensions
88    0x1D80,  # .. 0x1DBF ; Phonetic Extensions Supplement
89    0x1DC0,  # .. 0x1DFF ; Combining Diacritical Marks Supplement
90    0x1E00,  # .. 0x1EFF ; Latin Extended Additional
91    0x1F00,  # .. 0x1FFF ; Greek Extended
92    0x2000,  # .. 0x206F ; General Punctuation
93    0x2070,  # .. 0x209F ; Superscripts and Subscripts
94    0x20A0,  # .. 0x20CF ; Currency Symbols
95    0x20D0,  # .. 0x20FF ; Combining Diacritical Marks for Symbols
96    0x2100,  # .. 0x214F ; Letterlike Symbols
97    0x2150,  # .. 0x218F ; Number Forms
98    0x2190,  # .. 0x21FF ; Arrows
99    0x2200,  # .. 0x22FF ; Mathematical Operators
100    0x2300,  # .. 0x23FF ; Miscellaneous Technical
101    0x2400,  # .. 0x243F ; Control Pictures
102    0x2440,  # .. 0x245F ; Optical Character Recognition
103    0x2460,  # .. 0x24FF ; Enclosed Alphanumerics
104    0x2500,  # .. 0x257F ; Box Drawing
105    0x2580,  # .. 0x259F ; Block Elements
106    0x25A0,  # .. 0x25FF ; Geometric Shapes
107    0x2600,  # .. 0x26FF ; Miscellaneous Symbols
108    0x2700,  # .. 0x27BF ; Dingbats
109    0x27C0,  # .. 0x27EF ; Miscellaneous Mathematical Symbols-A
110    0x27F0,  # .. 0x27FF ; Supplemental Arrows-A
111    0x2800,  # .. 0x28FF ; Braille Patterns
112    0x2900,  # .. 0x297F ; Supplemental Arrows-B
113    0x2980,  # .. 0x29FF ; Miscellaneous Mathematical Symbols-B
114    0x2A00,  # .. 0x2AFF ; Supplemental Mathematical Operators
115    0x2B00,  # .. 0x2BFF ; Miscellaneous Symbols and Arrows
116    0x2C00,  # .. 0x2C5F ; Glagolitic
117    0x2C60,  # .. 0x2C7F ; Latin Extended-C
118    0x2C80,  # .. 0x2CFF ; Coptic
119    0x2D00,  # .. 0x2D2F ; Georgian Supplement
120    0x2D30,  # .. 0x2D7F ; Tifinagh
121    0x2D80,  # .. 0x2DDF ; Ethiopic Extended
122    0x2DE0,  # .. 0x2DFF ; Cyrillic Extended-A
123    0x2E00,  # .. 0x2E7F ; Supplemental Punctuation
124    0x2E80,  # .. 0x2EFF ; CJK Radicals Supplement
125    0x2F00,  # .. 0x2FDF ; Kangxi Radicals
126    0x2FE0,  # .. 0x2FEF ; No_Block
127    0x2FF0,  # .. 0x2FFF ; Ideographic Description Characters
128    0x3000,  # .. 0x303F ; CJK Symbols and Punctuation
129    0x3040,  # .. 0x309F ; Hiragana
130    0x30A0,  # .. 0x30FF ; Katakana
131    0x3100,  # .. 0x312F ; Bopomofo
132    0x3130,  # .. 0x318F ; Hangul Compatibility Jamo
133    0x3190,  # .. 0x319F ; Kanbun
134    0x31A0,  # .. 0x31BF ; Bopomofo Extended
135    0x31C0,  # .. 0x31EF ; CJK Strokes
136    0x31F0,  # .. 0x31FF ; Katakana Phonetic Extensions
137    0x3200,  # .. 0x32FF ; Enclosed CJK Letters and Months
138    0x3300,  # .. 0x33FF ; CJK Compatibility
139    0x3400,  # .. 0x4DBF ; CJK Unified Ideographs Extension A
140    0x4DC0,  # .. 0x4DFF ; Yijing Hexagram Symbols
141    0x4E00,  # .. 0x9FFF ; CJK Unified Ideographs
142    0xA000,  # .. 0xA48F ; Yi Syllables
143    0xA490,  # .. 0xA4CF ; Yi Radicals
144    0xA4D0,  # .. 0xA4FF ; Lisu
145    0xA500,  # .. 0xA63F ; Vai
146    0xA640,  # .. 0xA69F ; Cyrillic Extended-B
147    0xA6A0,  # .. 0xA6FF ; Bamum
148    0xA700,  # .. 0xA71F ; Modifier Tone Letters
149    0xA720,  # .. 0xA7FF ; Latin Extended-D
150    0xA800,  # .. 0xA82F ; Syloti Nagri
151    0xA830,  # .. 0xA83F ; Common Indic Number Forms
152    0xA840,  # .. 0xA87F ; Phags-pa
153    0xA880,  # .. 0xA8DF ; Saurashtra
154    0xA8E0,  # .. 0xA8FF ; Devanagari Extended
155    0xA900,  # .. 0xA92F ; Kayah Li
156    0xA930,  # .. 0xA95F ; Rejang
157    0xA960,  # .. 0xA97F ; Hangul Jamo Extended-A
158    0xA980,  # .. 0xA9DF ; Javanese
159    0xA9E0,  # .. 0xA9FF ; Myanmar Extended-B
160    0xAA00,  # .. 0xAA5F ; Cham
161    0xAA60,  # .. 0xAA7F ; Myanmar Extended-A
162    0xAA80,  # .. 0xAADF ; Tai Viet
163    0xAAE0,  # .. 0xAAFF ; Meetei Mayek Extensions
164    0xAB00,  # .. 0xAB2F ; Ethiopic Extended-A
165    0xAB30,  # .. 0xAB6F ; Latin Extended-E
166    0xAB70,  # .. 0xABBF ; Cherokee Supplement
167    0xABC0,  # .. 0xABFF ; Meetei Mayek
168    0xAC00,  # .. 0xD7AF ; Hangul Syllables
169    0xD7B0,  # .. 0xD7FF ; Hangul Jamo Extended-B
170    0xD800,  # .. 0xDB7F ; High Surrogates
171    0xDB80,  # .. 0xDBFF ; High Private Use Surrogates
172    0xDC00,  # .. 0xDFFF ; Low Surrogates
173    0xE000,  # .. 0xF8FF ; Private Use Area
174    0xF900,  # .. 0xFAFF ; CJK Compatibility Ideographs
175    0xFB00,  # .. 0xFB4F ; Alphabetic Presentation Forms
176    0xFB50,  # .. 0xFDFF ; Arabic Presentation Forms-A
177    0xFE00,  # .. 0xFE0F ; Variation Selectors
178    0xFE10,  # .. 0xFE1F ; Vertical Forms
179    0xFE20,  # .. 0xFE2F ; Combining Half Marks
180    0xFE30,  # .. 0xFE4F ; CJK Compatibility Forms
181    0xFE50,  # .. 0xFE6F ; Small Form Variants
182    0xFE70,  # .. 0xFEFF ; Arabic Presentation Forms-B
183    0xFF00,  # .. 0xFFEF ; Halfwidth and Fullwidth Forms
184    0xFFF0,  # .. 0xFFFF ; Specials
185    0x10000,  # .. 0x1007F ; Linear B Syllabary
186    0x10080,  # .. 0x100FF ; Linear B Ideograms
187    0x10100,  # .. 0x1013F ; Aegean Numbers
188    0x10140,  # .. 0x1018F ; Ancient Greek Numbers
189    0x10190,  # .. 0x101CF ; Ancient Symbols
190    0x101D0,  # .. 0x101FF ; Phaistos Disc
191    0x10200,  # .. 0x1027F ; No_Block
192    0x10280,  # .. 0x1029F ; Lycian
193    0x102A0,  # .. 0x102DF ; Carian
194    0x102E0,  # .. 0x102FF ; Coptic Epact Numbers
195    0x10300,  # .. 0x1032F ; Old Italic
196    0x10330,  # .. 0x1034F ; Gothic
197    0x10350,  # .. 0x1037F ; Old Permic
198    0x10380,  # .. 0x1039F ; Ugaritic
199    0x103A0,  # .. 0x103DF ; Old Persian
200    0x103E0,  # .. 0x103FF ; No_Block
201    0x10400,  # .. 0x1044F ; Deseret
202    0x10450,  # .. 0x1047F ; Shavian
203    0x10480,  # .. 0x104AF ; Osmanya
204    0x104B0,  # .. 0x104FF ; Osage
205    0x10500,  # .. 0x1052F ; Elbasan
206    0x10530,  # .. 0x1056F ; Caucasian Albanian
207    0x10570,  # .. 0x105FF ; No_Block
208    0x10600,  # .. 0x1077F ; Linear A
209    0x10780,  # .. 0x107FF ; No_Block
210    0x10800,  # .. 0x1083F ; Cypriot Syllabary
211    0x10840,  # .. 0x1085F ; Imperial Aramaic
212    0x10860,  # .. 0x1087F ; Palmyrene
213    0x10880,  # .. 0x108AF ; Nabataean
214    0x108B0,  # .. 0x108DF ; No_Block
215    0x108E0,  # .. 0x108FF ; Hatran
216    0x10900,  # .. 0x1091F ; Phoenician
217    0x10920,  # .. 0x1093F ; Lydian
218    0x10940,  # .. 0x1097F ; No_Block
219    0x10980,  # .. 0x1099F ; Meroitic Hieroglyphs
220    0x109A0,  # .. 0x109FF ; Meroitic Cursive
221    0x10A00,  # .. 0x10A5F ; Kharoshthi
222    0x10A60,  # .. 0x10A7F ; Old South Arabian
223    0x10A80,  # .. 0x10A9F ; Old North Arabian
224    0x10AA0,  # .. 0x10ABF ; No_Block
225    0x10AC0,  # .. 0x10AFF ; Manichaean
226    0x10B00,  # .. 0x10B3F ; Avestan
227    0x10B40,  # .. 0x10B5F ; Inscriptional Parthian
228    0x10B60,  # .. 0x10B7F ; Inscriptional Pahlavi
229    0x10B80,  # .. 0x10BAF ; Psalter Pahlavi
230    0x10BB0,  # .. 0x10BFF ; No_Block
231    0x10C00,  # .. 0x10C4F ; Old Turkic
232    0x10C50,  # .. 0x10C7F ; No_Block
233    0x10C80,  # .. 0x10CFF ; Old Hungarian
234    0x10D00,  # .. 0x10D3F ; Hanifi Rohingya
235    0x10D40,  # .. 0x10E5F ; No_Block
236    0x10E60,  # .. 0x10E7F ; Rumi Numeral Symbols
237    0x10E80,  # .. 0x10EFF ; No_Block
238    0x10F00,  # .. 0x10F2F ; Old Sogdian
239    0x10F30,  # .. 0x10F6F ; Sogdian
240    0x10F70,  # .. 0x10FFF ; No_Block
241    0x11000,  # .. 0x1107F ; Brahmi
242    0x11080,  # .. 0x110CF ; Kaithi
243    0x110D0,  # .. 0x110FF ; Sora Sompeng
244    0x11100,  # .. 0x1114F ; Chakma
245    0x11150,  # .. 0x1117F ; Mahajani
246    0x11180,  # .. 0x111DF ; Sharada
247    0x111E0,  # .. 0x111FF ; Sinhala Archaic Numbers
248    0x11200,  # .. 0x1124F ; Khojki
249    0x11250,  # .. 0x1127F ; No_Block
250    0x11280,  # .. 0x112AF ; Multani
251    0x112B0,  # .. 0x112FF ; Khudawadi
252    0x11300,  # .. 0x1137F ; Grantha
253    0x11380,  # .. 0x113FF ; No_Block
254    0x11400,  # .. 0x1147F ; Newa
255    0x11480,  # .. 0x114DF ; Tirhuta
256    0x114E0,  # .. 0x1157F ; No_Block
257    0x11580,  # .. 0x115FF ; Siddham
258    0x11600,  # .. 0x1165F ; Modi
259    0x11660,  # .. 0x1167F ; Mongolian Supplement
260    0x11680,  # .. 0x116CF ; Takri
261    0x116D0,  # .. 0x116FF ; No_Block
262    0x11700,  # .. 0x1173F ; Ahom
263    0x11740,  # .. 0x117FF ; No_Block
264    0x11800,  # .. 0x1184F ; Dogra
265    0x11850,  # .. 0x1189F ; No_Block
266    0x118A0,  # .. 0x118FF ; Warang Citi
267    0x11900,  # .. 0x119FF ; No_Block
268    0x11A00,  # .. 0x11A4F ; Zanabazar Square
269    0x11A50,  # .. 0x11AAF ; Soyombo
270    0x11AB0,  # .. 0x11ABF ; No_Block
271    0x11AC0,  # .. 0x11AFF ; Pau Cin Hau
272    0x11B00,  # .. 0x11BFF ; No_Block
273    0x11C00,  # .. 0x11C6F ; Bhaiksuki
274    0x11C70,  # .. 0x11CBF ; Marchen
275    0x11CC0,  # .. 0x11CFF ; No_Block
276    0x11D00,  # .. 0x11D5F ; Masaram Gondi
277    0x11D60,  # .. 0x11DAF ; Gunjala Gondi
278    0x11DB0,  # .. 0x11EDF ; No_Block
279    0x11EE0,  # .. 0x11EFF ; Makasar
280    0x11F00,  # .. 0x11FFF ; No_Block
281    0x12000,  # .. 0x123FF ; Cuneiform
282    0x12400,  # .. 0x1247F ; Cuneiform Numbers and Punctuation
283    0x12480,  # .. 0x1254F ; Early Dynastic Cuneiform
284    0x12550,  # .. 0x12FFF ; No_Block
285    0x13000,  # .. 0x1342F ; Egyptian Hieroglyphs
286    0x13430,  # .. 0x143FF ; No_Block
287    0x14400,  # .. 0x1467F ; Anatolian Hieroglyphs
288    0x14680,  # .. 0x167FF ; No_Block
289    0x16800,  # .. 0x16A3F ; Bamum Supplement
290    0x16A40,  # .. 0x16A6F ; Mro
291    0x16A70,  # .. 0x16ACF ; No_Block
292    0x16AD0,  # .. 0x16AFF ; Bassa Vah
293    0x16B00,  # .. 0x16B8F ; Pahawh Hmong
294    0x16B90,  # .. 0x16E3F ; No_Block
295    0x16E40,  # .. 0x16E9F ; Medefaidrin
296    0x16EA0,  # .. 0x16EFF ; No_Block
297    0x16F00,  # .. 0x16F9F ; Miao
298    0x16FA0,  # .. 0x16FDF ; No_Block
299    0x16FE0,  # .. 0x16FFF ; Ideographic Symbols and Punctuation
300    0x17000,  # .. 0x187FF ; Tangut
301    0x18800,  # .. 0x18AFF ; Tangut Components
302    0x18B00,  # .. 0x1AFFF ; No_Block
303    0x1B000,  # .. 0x1B0FF ; Kana Supplement
304    0x1B100,  # .. 0x1B12F ; Kana Extended-A
305    0x1B130,  # .. 0x1B16F ; No_Block
306    0x1B170,  # .. 0x1B2FF ; Nushu
307    0x1B300,  # .. 0x1BBFF ; No_Block
308    0x1BC00,  # .. 0x1BC9F ; Duployan
309    0x1BCA0,  # .. 0x1BCAF ; Shorthand Format Controls
310    0x1BCB0,  # .. 0x1CFFF ; No_Block
311    0x1D000,  # .. 0x1D0FF ; Byzantine Musical Symbols
312    0x1D100,  # .. 0x1D1FF ; Musical Symbols
313    0x1D200,  # .. 0x1D24F ; Ancient Greek Musical Notation
314    0x1D250,  # .. 0x1D2DF ; No_Block
315    0x1D2E0,  # .. 0x1D2FF ; Mayan Numerals
316    0x1D300,  # .. 0x1D35F ; Tai Xuan Jing Symbols
317    0x1D360,  # .. 0x1D37F ; Counting Rod Numerals
318    0x1D380,  # .. 0x1D3FF ; No_Block
319    0x1D400,  # .. 0x1D7FF ; Mathematical Alphanumeric Symbols
320    0x1D800,  # .. 0x1DAAF ; Sutton SignWriting
321    0x1DAB0,  # .. 0x1DFFF ; No_Block
322    0x1E000,  # .. 0x1E02F ; Glagolitic Supplement
323    0x1E030,  # .. 0x1E7FF ; No_Block
324    0x1E800,  # .. 0x1E8DF ; Mende Kikakui
325    0x1E8E0,  # .. 0x1E8FF ; No_Block
326    0x1E900,  # .. 0x1E95F ; Adlam
327    0x1E960,  # .. 0x1EC6F ; No_Block
328    0x1EC70,  # .. 0x1ECBF ; Indic Siyaq Numbers
329    0x1ECC0,  # .. 0x1EDFF ; No_Block
330    0x1EE00,  # .. 0x1EEFF ; Arabic Mathematical Alphabetic Symbols
331    0x1EF00,  # .. 0x1EFFF ; No_Block
332    0x1F000,  # .. 0x1F02F ; Mahjong Tiles
333    0x1F030,  # .. 0x1F09F ; Domino Tiles
334    0x1F0A0,  # .. 0x1F0FF ; Playing Cards
335    0x1F100,  # .. 0x1F1FF ; Enclosed Alphanumeric Supplement
336    0x1F200,  # .. 0x1F2FF ; Enclosed Ideographic Supplement
337    0x1F300,  # .. 0x1F5FF ; Miscellaneous Symbols and Pictographs
338    0x1F600,  # .. 0x1F64F ; Emoticons
339    0x1F650,  # .. 0x1F67F ; Ornamental Dingbats
340    0x1F680,  # .. 0x1F6FF ; Transport and Map Symbols
341    0x1F700,  # .. 0x1F77F ; Alchemical Symbols
342    0x1F780,  # .. 0x1F7FF ; Geometric Shapes Extended
343    0x1F800,  # .. 0x1F8FF ; Supplemental Arrows-C
344    0x1F900,  # .. 0x1F9FF ; Supplemental Symbols and Pictographs
345    0x1FA00,  # .. 0x1FA6F ; Chess Symbols
346    0x1FA70,  # .. 0x1FFFF ; No_Block
347    0x20000,  # .. 0x2A6DF ; CJK Unified Ideographs Extension B
348    0x2A6E0,  # .. 0x2A6FF ; No_Block
349    0x2A700,  # .. 0x2B73F ; CJK Unified Ideographs Extension C
350    0x2B740,  # .. 0x2B81F ; CJK Unified Ideographs Extension D
351    0x2B820,  # .. 0x2CEAF ; CJK Unified Ideographs Extension E
352    0x2CEB0,  # .. 0x2EBEF ; CJK Unified Ideographs Extension F
353    0x2EBF0,  # .. 0x2F7FF ; No_Block
354    0x2F800,  # .. 0x2FA1F ; CJK Compatibility Ideographs Supplement
355    0x2FA20,  # .. 0xDFFFF ; No_Block
356    0xE0000,  # .. 0xE007F ; Tags
357    0xE0080,  # .. 0xE00FF ; No_Block
358    0xE0100,  # .. 0xE01EF ; Variation Selectors Supplement
359    0xE01F0,  # .. 0xEFFFF ; No_Block
360    0xF0000,  # .. 0xFFFFF ; Supplementary Private Use Area-A
361    0x100000,  # .. 0x10FFFF ; Supplementary Private Use Area-B
362]
363
364VALUES = [
365    'Basic Latin',                                     # 0000..007F
366    'Latin-1 Supplement',                              # 0080..00FF
367    'Latin Extended-A',                                # 0100..017F
368    'Latin Extended-B',                                # 0180..024F
369    'IPA Extensions',                                  # 0250..02AF
370    'Spacing Modifier Letters',                        # 02B0..02FF
371    'Combining Diacritical Marks',                     # 0300..036F
372    'Greek and Coptic',                                # 0370..03FF
373    'Cyrillic',                                        # 0400..04FF
374    'Cyrillic Supplement',                             # 0500..052F
375    'Armenian',                                        # 0530..058F
376    'Hebrew',                                          # 0590..05FF
377    'Arabic',                                          # 0600..06FF
378    'Syriac',                                          # 0700..074F
379    'Arabic Supplement',                               # 0750..077F
380    'Thaana',                                          # 0780..07BF
381    'NKo',                                             # 07C0..07FF
382    'Samaritan',                                       # 0800..083F
383    'Mandaic',                                         # 0840..085F
384    'Syriac Supplement',                               # 0860..086F
385    'No_Block',                                        # 0870..089F
386    'Arabic Extended-A',                               # 08A0..08FF
387    'Devanagari',                                      # 0900..097F
388    'Bengali',                                         # 0980..09FF
389    'Gurmukhi',                                        # 0A00..0A7F
390    'Gujarati',                                        # 0A80..0AFF
391    'Oriya',                                           # 0B00..0B7F
392    'Tamil',                                           # 0B80..0BFF
393    'Telugu',                                          # 0C00..0C7F
394    'Kannada',                                         # 0C80..0CFF
395    'Malayalam',                                       # 0D00..0D7F
396    'Sinhala',                                         # 0D80..0DFF
397    'Thai',                                            # 0E00..0E7F
398    'Lao',                                             # 0E80..0EFF
399    'Tibetan',                                         # 0F00..0FFF
400    'Myanmar',                                         # 1000..109F
401    'Georgian',                                        # 10A0..10FF
402    'Hangul Jamo',                                     # 1100..11FF
403    'Ethiopic',                                        # 1200..137F
404    'Ethiopic Supplement',                             # 1380..139F
405    'Cherokee',                                        # 13A0..13FF
406    'Unified Canadian Aboriginal Syllabics',           # 1400..167F
407    'Ogham',                                           # 1680..169F
408    'Runic',                                           # 16A0..16FF
409    'Tagalog',                                         # 1700..171F
410    'Hanunoo',                                         # 1720..173F
411    'Buhid',                                           # 1740..175F
412    'Tagbanwa',                                        # 1760..177F
413    'Khmer',                                           # 1780..17FF
414    'Mongolian',                                       # 1800..18AF
415    'Unified Canadian Aboriginal Syllabics Extended',  # 18B0..18FF
416    'Limbu',                                           # 1900..194F
417    'Tai Le',                                          # 1950..197F
418    'New Tai Lue',                                     # 1980..19DF
419    'Khmer Symbols',                                   # 19E0..19FF
420    'Buginese',                                        # 1A00..1A1F
421    'Tai Tham',                                        # 1A20..1AAF
422    'Combining Diacritical Marks Extended',            # 1AB0..1AFF
423    'Balinese',                                        # 1B00..1B7F
424    'Sundanese',                                       # 1B80..1BBF
425    'Batak',                                           # 1BC0..1BFF
426    'Lepcha',                                          # 1C00..1C4F
427    'Ol Chiki',                                        # 1C50..1C7F
428    'Cyrillic Extended-C',                             # 1C80..1C8F
429    'Georgian Extended',                               # 1C90..1CBF
430    'Sundanese Supplement',                            # 1CC0..1CCF
431    'Vedic Extensions',                                # 1CD0..1CFF
432    'Phonetic Extensions',                             # 1D00..1D7F
433    'Phonetic Extensions Supplement',                  # 1D80..1DBF
434    'Combining Diacritical Marks Supplement',          # 1DC0..1DFF
435    'Latin Extended Additional',                       # 1E00..1EFF
436    'Greek Extended',                                  # 1F00..1FFF
437    'General Punctuation',                             # 2000..206F
438    'Superscripts and Subscripts',                     # 2070..209F
439    'Currency Symbols',                                # 20A0..20CF
440    'Combining Diacritical Marks for Symbols',         # 20D0..20FF
441    'Letterlike Symbols',                              # 2100..214F
442    'Number Forms',                                    # 2150..218F
443    'Arrows',                                          # 2190..21FF
444    'Mathematical Operators',                          # 2200..22FF
445    'Miscellaneous Technical',                         # 2300..23FF
446    'Control Pictures',                                # 2400..243F
447    'Optical Character Recognition',                   # 2440..245F
448    'Enclosed Alphanumerics',                          # 2460..24FF
449    'Box Drawing',                                     # 2500..257F
450    'Block Elements',                                  # 2580..259F
451    'Geometric Shapes',                                # 25A0..25FF
452    'Miscellaneous Symbols',                           # 2600..26FF
453    'Dingbats',                                        # 2700..27BF
454    'Miscellaneous Mathematical Symbols-A',            # 27C0..27EF
455    'Supplemental Arrows-A',                           # 27F0..27FF
456    'Braille Patterns',                                # 2800..28FF
457    'Supplemental Arrows-B',                           # 2900..297F
458    'Miscellaneous Mathematical Symbols-B',            # 2980..29FF
459    'Supplemental Mathematical Operators',             # 2A00..2AFF
460    'Miscellaneous Symbols and Arrows',                # 2B00..2BFF
461    'Glagolitic',                                      # 2C00..2C5F
462    'Latin Extended-C',                                # 2C60..2C7F
463    'Coptic',                                          # 2C80..2CFF
464    'Georgian Supplement',                             # 2D00..2D2F
465    'Tifinagh',                                        # 2D30..2D7F
466    'Ethiopic Extended',                               # 2D80..2DDF
467    'Cyrillic Extended-A',                             # 2DE0..2DFF
468    'Supplemental Punctuation',                        # 2E00..2E7F
469    'CJK Radicals Supplement',                         # 2E80..2EFF
470    'Kangxi Radicals',                                 # 2F00..2FDF
471    'No_Block',                                        # 2FE0..2FEF
472    'Ideographic Description Characters',              # 2FF0..2FFF
473    'CJK Symbols and Punctuation',                     # 3000..303F
474    'Hiragana',                                        # 3040..309F
475    'Katakana',                                        # 30A0..30FF
476    'Bopomofo',                                        # 3100..312F
477    'Hangul Compatibility Jamo',                       # 3130..318F
478    'Kanbun',                                          # 3190..319F
479    'Bopomofo Extended',                               # 31A0..31BF
480    'CJK Strokes',                                     # 31C0..31EF
481    'Katakana Phonetic Extensions',                    # 31F0..31FF
482    'Enclosed CJK Letters and Months',                 # 3200..32FF
483    'CJK Compatibility',                               # 3300..33FF
484    'CJK Unified Ideographs Extension A',              # 3400..4DBF
485    'Yijing Hexagram Symbols',                         # 4DC0..4DFF
486    'CJK Unified Ideographs',                          # 4E00..9FFF
487    'Yi Syllables',                                    # A000..A48F
488    'Yi Radicals',                                     # A490..A4CF
489    'Lisu',                                            # A4D0..A4FF
490    'Vai',                                             # A500..A63F
491    'Cyrillic Extended-B',                             # A640..A69F
492    'Bamum',                                           # A6A0..A6FF
493    'Modifier Tone Letters',                           # A700..A71F
494    'Latin Extended-D',                                # A720..A7FF
495    'Syloti Nagri',                                    # A800..A82F
496    'Common Indic Number Forms',                       # A830..A83F
497    'Phags-pa',                                        # A840..A87F
498    'Saurashtra',                                      # A880..A8DF
499    'Devanagari Extended',                             # A8E0..A8FF
500    'Kayah Li',                                        # A900..A92F
501    'Rejang',                                          # A930..A95F
502    'Hangul Jamo Extended-A',                          # A960..A97F
503    'Javanese',                                        # A980..A9DF
504    'Myanmar Extended-B',                              # A9E0..A9FF
505    'Cham',                                            # AA00..AA5F
506    'Myanmar Extended-A',                              # AA60..AA7F
507    'Tai Viet',                                        # AA80..AADF
508    'Meetei Mayek Extensions',                         # AAE0..AAFF
509    'Ethiopic Extended-A',                             # AB00..AB2F
510    'Latin Extended-E',                                # AB30..AB6F
511    'Cherokee Supplement',                             # AB70..ABBF
512    'Meetei Mayek',                                    # ABC0..ABFF
513    'Hangul Syllables',                                # AC00..D7AF
514    'Hangul Jamo Extended-B',                          # D7B0..D7FF
515    'High Surrogates',                                 # D800..DB7F
516    'High Private Use Surrogates',                     # DB80..DBFF
517    'Low Surrogates',                                  # DC00..DFFF
518    'Private Use Area',                                # E000..F8FF
519    'CJK Compatibility Ideographs',                    # F900..FAFF
520    'Alphabetic Presentation Forms',                   # FB00..FB4F
521    'Arabic Presentation Forms-A',                     # FB50..FDFF
522    'Variation Selectors',                             # FE00..FE0F
523    'Vertical Forms',                                  # FE10..FE1F
524    'Combining Half Marks',                            # FE20..FE2F
525    'CJK Compatibility Forms',                         # FE30..FE4F
526    'Small Form Variants',                             # FE50..FE6F
527    'Arabic Presentation Forms-B',                     # FE70..FEFF
528    'Halfwidth and Fullwidth Forms',                   # FF00..FFEF
529    'Specials',                                        # FFF0..FFFF
530    'Linear B Syllabary',                              # 10000..1007F
531    'Linear B Ideograms',                              # 10080..100FF
532    'Aegean Numbers',                                  # 10100..1013F
533    'Ancient Greek Numbers',                           # 10140..1018F
534    'Ancient Symbols',                                 # 10190..101CF
535    'Phaistos Disc',                                   # 101D0..101FF
536    'No_Block',                                        # 10200..1027F
537    'Lycian',                                          # 10280..1029F
538    'Carian',                                          # 102A0..102DF
539    'Coptic Epact Numbers',                            # 102E0..102FF
540    'Old Italic',                                      # 10300..1032F
541    'Gothic',                                          # 10330..1034F
542    'Old Permic',                                      # 10350..1037F
543    'Ugaritic',                                        # 10380..1039F
544    'Old Persian',                                     # 103A0..103DF
545    'No_Block',                                        # 103E0..103FF
546    'Deseret',                                         # 10400..1044F
547    'Shavian',                                         # 10450..1047F
548    'Osmanya',                                         # 10480..104AF
549    'Osage',                                           # 104B0..104FF
550    'Elbasan',                                         # 10500..1052F
551    'Caucasian Albanian',                              # 10530..1056F
552    'No_Block',                                        # 10570..105FF
553    'Linear A',                                        # 10600..1077F
554    'No_Block',                                        # 10780..107FF
555    'Cypriot Syllabary',                               # 10800..1083F
556    'Imperial Aramaic',                                # 10840..1085F
557    'Palmyrene',                                       # 10860..1087F
558    'Nabataean',                                       # 10880..108AF
559    'No_Block',                                        # 108B0..108DF
560    'Hatran',                                          # 108E0..108FF
561    'Phoenician',                                      # 10900..1091F
562    'Lydian',                                          # 10920..1093F
563    'No_Block',                                        # 10940..1097F
564    'Meroitic Hieroglyphs',                            # 10980..1099F
565    'Meroitic Cursive',                                # 109A0..109FF
566    'Kharoshthi',                                      # 10A00..10A5F
567    'Old South Arabian',                               # 10A60..10A7F
568    'Old North Arabian',                               # 10A80..10A9F
569    'No_Block',                                        # 10AA0..10ABF
570    'Manichaean',                                      # 10AC0..10AFF
571    'Avestan',                                         # 10B00..10B3F
572    'Inscriptional Parthian',                          # 10B40..10B5F
573    'Inscriptional Pahlavi',                           # 10B60..10B7F
574    'Psalter Pahlavi',                                 # 10B80..10BAF
575    'No_Block',                                        # 10BB0..10BFF
576    'Old Turkic',                                      # 10C00..10C4F
577    'No_Block',                                        # 10C50..10C7F
578    'Old Hungarian',                                   # 10C80..10CFF
579    'Hanifi Rohingya',                                 # 10D00..10D3F
580    'No_Block',                                        # 10D40..10E5F
581    'Rumi Numeral Symbols',                            # 10E60..10E7F
582    'No_Block',                                        # 10E80..10EFF
583    'Old Sogdian',                                     # 10F00..10F2F
584    'Sogdian',                                         # 10F30..10F6F
585    'No_Block',                                        # 10F70..10FFF
586    'Brahmi',                                          # 11000..1107F
587    'Kaithi',                                          # 11080..110CF
588    'Sora Sompeng',                                    # 110D0..110FF
589    'Chakma',                                          # 11100..1114F
590    'Mahajani',                                        # 11150..1117F
591    'Sharada',                                         # 11180..111DF
592    'Sinhala Archaic Numbers',                         # 111E0..111FF
593    'Khojki',                                          # 11200..1124F
594    'No_Block',                                        # 11250..1127F
595    'Multani',                                         # 11280..112AF
596    'Khudawadi',                                       # 112B0..112FF
597    'Grantha',                                         # 11300..1137F
598    'No_Block',                                        # 11380..113FF
599    'Newa',                                            # 11400..1147F
600    'Tirhuta',                                         # 11480..114DF
601    'No_Block',                                        # 114E0..1157F
602    'Siddham',                                         # 11580..115FF
603    'Modi',                                            # 11600..1165F
604    'Mongolian Supplement',                            # 11660..1167F
605    'Takri',                                           # 11680..116CF
606    'No_Block',                                        # 116D0..116FF
607    'Ahom',                                            # 11700..1173F
608    'No_Block',                                        # 11740..117FF
609    'Dogra',                                           # 11800..1184F
610    'No_Block',                                        # 11850..1189F
611    'Warang Citi',                                     # 118A0..118FF
612    'No_Block',                                        # 11900..119FF
613    'Zanabazar Square',                                # 11A00..11A4F
614    'Soyombo',                                         # 11A50..11AAF
615    'No_Block',                                        # 11AB0..11ABF
616    'Pau Cin Hau',                                     # 11AC0..11AFF
617    'No_Block',                                        # 11B00..11BFF
618    'Bhaiksuki',                                       # 11C00..11C6F
619    'Marchen',                                         # 11C70..11CBF
620    'No_Block',                                        # 11CC0..11CFF
621    'Masaram Gondi',                                   # 11D00..11D5F
622    'Gunjala Gondi',                                   # 11D60..11DAF
623    'No_Block',                                        # 11DB0..11EDF
624    'Makasar',                                         # 11EE0..11EFF
625    'No_Block',                                        # 11F00..11FFF
626    'Cuneiform',                                       # 12000..123FF
627    'Cuneiform Numbers and Punctuation',               # 12400..1247F
628    'Early Dynastic Cuneiform',                        # 12480..1254F
629    'No_Block',                                        # 12550..12FFF
630    'Egyptian Hieroglyphs',                            # 13000..1342F
631    'No_Block',                                        # 13430..143FF
632    'Anatolian Hieroglyphs',                           # 14400..1467F
633    'No_Block',                                        # 14680..167FF
634    'Bamum Supplement',                                # 16800..16A3F
635    'Mro',                                             # 16A40..16A6F
636    'No_Block',                                        # 16A70..16ACF
637    'Bassa Vah',                                       # 16AD0..16AFF
638    'Pahawh Hmong',                                    # 16B00..16B8F
639    'No_Block',                                        # 16B90..16E3F
640    'Medefaidrin',                                     # 16E40..16E9F
641    'No_Block',                                        # 16EA0..16EFF
642    'Miao',                                            # 16F00..16F9F
643    'No_Block',                                        # 16FA0..16FDF
644    'Ideographic Symbols and Punctuation',             # 16FE0..16FFF
645    'Tangut',                                          # 17000..187FF
646    'Tangut Components',                               # 18800..18AFF
647    'No_Block',                                        # 18B00..1AFFF
648    'Kana Supplement',                                 # 1B000..1B0FF
649    'Kana Extended-A',                                 # 1B100..1B12F
650    'No_Block',                                        # 1B130..1B16F
651    'Nushu',                                           # 1B170..1B2FF
652    'No_Block',                                        # 1B300..1BBFF
653    'Duployan',                                        # 1BC00..1BC9F
654    'Shorthand Format Controls',                       # 1BCA0..1BCAF
655    'No_Block',                                        # 1BCB0..1CFFF
656    'Byzantine Musical Symbols',                       # 1D000..1D0FF
657    'Musical Symbols',                                 # 1D100..1D1FF
658    'Ancient Greek Musical Notation',                  # 1D200..1D24F
659    'No_Block',                                        # 1D250..1D2DF
660    'Mayan Numerals',                                  # 1D2E0..1D2FF
661    'Tai Xuan Jing Symbols',                           # 1D300..1D35F
662    'Counting Rod Numerals',                           # 1D360..1D37F
663    'No_Block',                                        # 1D380..1D3FF
664    'Mathematical Alphanumeric Symbols',               # 1D400..1D7FF
665    'Sutton SignWriting',                              # 1D800..1DAAF
666    'No_Block',                                        # 1DAB0..1DFFF
667    'Glagolitic Supplement',                           # 1E000..1E02F
668    'No_Block',                                        # 1E030..1E7FF
669    'Mende Kikakui',                                   # 1E800..1E8DF
670    'No_Block',                                        # 1E8E0..1E8FF
671    'Adlam',                                           # 1E900..1E95F
672    'No_Block',                                        # 1E960..1EC6F
673    'Indic Siyaq Numbers',                             # 1EC70..1ECBF
674    'No_Block',                                        # 1ECC0..1EDFF
675    'Arabic Mathematical Alphabetic Symbols',          # 1EE00..1EEFF
676    'No_Block',                                        # 1EF00..1EFFF
677    'Mahjong Tiles',                                   # 1F000..1F02F
678    'Domino Tiles',                                    # 1F030..1F09F
679    'Playing Cards',                                   # 1F0A0..1F0FF
680    'Enclosed Alphanumeric Supplement',                # 1F100..1F1FF
681    'Enclosed Ideographic Supplement',                 # 1F200..1F2FF
682    'Miscellaneous Symbols and Pictographs',           # 1F300..1F5FF
683    'Emoticons',                                       # 1F600..1F64F
684    'Ornamental Dingbats',                             # 1F650..1F67F
685    'Transport and Map Symbols',                       # 1F680..1F6FF
686    'Alchemical Symbols',                              # 1F700..1F77F
687    'Geometric Shapes Extended',                       # 1F780..1F7FF
688    'Supplemental Arrows-C',                           # 1F800..1F8FF
689    'Supplemental Symbols and Pictographs',            # 1F900..1F9FF
690    'Chess Symbols',                                   # 1FA00..1FA6F
691    'No_Block',                                        # 1FA70..1FFFF
692    'CJK Unified Ideographs Extension B',              # 20000..2A6DF
693    'No_Block',                                        # 2A6E0..2A6FF
694    'CJK Unified Ideographs Extension C',              # 2A700..2B73F
695    'CJK Unified Ideographs Extension D',              # 2B740..2B81F
696    'CJK Unified Ideographs Extension E',              # 2B820..2CEAF
697    'CJK Unified Ideographs Extension F',              # 2CEB0..2EBEF
698    'No_Block',                                        # 2EBF0..2F7FF
699    'CJK Compatibility Ideographs Supplement',         # 2F800..2FA1F
700    'No_Block',                                        # 2FA20..DFFFF
701    'Tags',                                            # E0000..E007F
702    'No_Block',                                        # E0080..E00FF
703    'Variation Selectors Supplement',                  # E0100..E01EF
704    'No_Block',                                        # E01F0..EFFFF
705    'Supplementary Private Use Area-A',                # F0000..FFFFF
706    'Supplementary Private Use Area-B',                # 100000..10FFFF
707]
708