unicode-blocks-py 6.1.0__py3-none-any.whl

unicode_blocks/__init__.py

@@ -0,0 +1,4 @@
+from .blocks import __version__
+from .blocks import *
+from .cjk import is_cjk, is_cjk_block
+from .globals import *

unicode_blocks/blocks.py

@@ -0,0 +1,492 @@
+# This file is auto-generated on build. Do not edit.
+# This code is licensed under the MIT License.
+# Modified under Unicode License v3. See https://www.unicode.org/license.txt for details.
+
+from .unicodeBlock import UnicodeBlock
+
+__version__ = '6.1.0'
+
+NO_BLOCK = UnicodeBlock(name='No Block', start=-1, end=-1)
+BASIC_LATIN = UnicodeBlock(name='Basic Latin', start=0x0000, end=0x007f, assigned_ranges=[(0x0000, 0x007f)], aliases=['ASCII'])
+LATIN_1_SUPPLEMENT = UnicodeBlock(name='Latin-1 Supplement', start=0x0080, end=0x00ff, assigned_ranges=[(0x0080, 0x00ff)], aliases=['Latin_1_Sup', 'Latin_1'])
+LATIN_EXTENDED_A = UnicodeBlock(name='Latin Extended-A', start=0x0100, end=0x017f, assigned_ranges=[(0x0100, 0x017f)], aliases=['Latin_Ext_A'])
+LATIN_EXTENDED_B = UnicodeBlock(name='Latin Extended-B', start=0x0180, end=0x024f, assigned_ranges=[(0x0180, 0x024f)], aliases=['Latin_Ext_B'])
+IPA_EXTENSIONS = UnicodeBlock(name='IPA Extensions', start=0x0250, end=0x02af, assigned_ranges=[(0x0250, 0x02af)], aliases=['IPA_Ext'])
+SPACING_MODIFIER_LETTERS = UnicodeBlock(name='Spacing Modifier Letters', start=0x02b0, end=0x02ff, assigned_ranges=[(0x02b0, 0x02ff)], aliases=['Modifier_Letters'])
+COMBINING_DIACRITICAL_MARKS = UnicodeBlock(name='Combining Diacritical Marks', start=0x0300, end=0x036f, assigned_ranges=[(0x0300, 0x036f)], aliases=['Diacriticals'])
+GREEK_AND_COPTIC = UnicodeBlock(name='Greek and Coptic', start=0x0370, end=0x03ff, assigned_ranges=[(0x0370, 0x0377), (0x037a, 0x037e), (0x0384, 0x038a), (0x038c, 0x038c), (0x038e, 0x03a1), (0x03a3, 0x03ff)], aliases=['Greek'])
+CYRILLIC = UnicodeBlock(name='Cyrillic', start=0x0400, end=0x04ff, assigned_ranges=[(0x0400, 0x04ff)])
+CYRILLIC_SUPPLEMENT = UnicodeBlock(name='Cyrillic Supplement', start=0x0500, end=0x052f, assigned_ranges=[(0x0500, 0x0527)], aliases=['Cyrillic_Sup', 'Cyrillic_Supplementary'])
+ARMENIAN = UnicodeBlock(name='Armenian', start=0x0530, end=0x058f, assigned_ranges=[(0x0531, 0x0556), (0x0559, 0x055f), (0x0561, 0x0587), (0x0589, 0x058a), (0x058f, 0x058f)])
+HEBREW = UnicodeBlock(name='Hebrew', start=0x0590, end=0x05ff, assigned_ranges=[(0x0591, 0x05c7), (0x05d0, 0x05ea), (0x05f0, 0x05f4)])
+ARABIC = UnicodeBlock(name='Arabic', start=0x0600, end=0x06ff, assigned_ranges=[(0x0600, 0x0604), (0x0606, 0x061b), (0x061e, 0x06ff)])
+SYRIAC = UnicodeBlock(name='Syriac', start=0x0700, end=0x074f, assigned_ranges=[(0x0700, 0x070d), (0x070f, 0x074a), (0x074d, 0x074f)])
+ARABIC_SUPPLEMENT = UnicodeBlock(name='Arabic Supplement', start=0x0750, end=0x077f, assigned_ranges=[(0x0750, 0x077f)], aliases=['Arabic_Sup'])
+THAANA = UnicodeBlock(name='Thaana', start=0x0780, end=0x07bf, assigned_ranges=[(0x0780, 0x07b1)])
+NKO = UnicodeBlock(name='NKo', start=0x07c0, end=0x07ff, assigned_ranges=[(0x07c0, 0x07fa)])
+SAMARITAN = UnicodeBlock(name='Samaritan', start=0x0800, end=0x083f, assigned_ranges=[(0x0800, 0x082d), (0x0830, 0x083e)])
+MANDAIC = UnicodeBlock(name='Mandaic', start=0x0840, end=0x085f, assigned_ranges=[(0x0840, 0x085b), (0x085e, 0x085e)])
+ARABIC_EXTENDED_A = UnicodeBlock(name='Arabic Extended-A', start=0x08a0, end=0x08ff, assigned_ranges=[(0x08a0, 0x08a0), (0x08a2, 0x08ac), (0x08e4, 0x08fe)], aliases=['Arabic_Ext_A'])
+DEVANAGARI = UnicodeBlock(name='Devanagari', start=0x0900, end=0x097f, assigned_ranges=[(0x0900, 0x0977), (0x0979, 0x097f)])
+BENGALI = UnicodeBlock(name='Bengali', start=0x0980, end=0x09ff, assigned_ranges=[(0x0981, 0x0983), (0x0985, 0x098c), (0x098f, 0x0990), (0x0993, 0x09a8), (0x09aa, 0x09b0), (0x09b2, 0x09b2), (0x09b6, 0x09b9), (0x09bc, 0x09c4), (0x09c7, 0x09c8), (0x09cb, 0x09ce), (0x09d7, 0x09d7), (0x09dc, 0x09dd), (0x09df, 0x09e3), (0x09e6, 0x09fb)])
+GURMUKHI = UnicodeBlock(name='Gurmukhi', start=0x0a00, end=0x0a7f, assigned_ranges=[(0x0a01, 0x0a03), (0x0a05, 0x0a0a), (0x0a0f, 0x0a10), (0x0a13, 0x0a28), (0x0a2a, 0x0a30), (0x0a32, 0x0a33), (0x0a35, 0x0a36), (0x0a38, 0x0a39), (0x0a3c, 0x0a3c), (0x0a3e, 0x0a42), (0x0a47, 0x0a48), (0x0a4b, 0x0a4d), (0x0a51, 0x0a51), (0x0a59, 0x0a5c), (0x0a5e, 0x0a5e), (0x0a66, 0x0a75)])
+GUJARATI = UnicodeBlock(name='Gujarati', start=0x0a80, end=0x0aff, assigned_ranges=[(0x0a81, 0x0a83), (0x0a85, 0x0a8d), (0x0a8f, 0x0a91), (0x0a93, 0x0aa8), (0x0aaa, 0x0ab0), (0x0ab2, 0x0ab3), (0x0ab5, 0x0ab9), (0x0abc, 0x0ac5), (0x0ac7, 0x0ac9), (0x0acb, 0x0acd), (0x0ad0, 0x0ad0), (0x0ae0, 0x0ae3), (0x0ae6, 0x0af1)])
+ORIYA = UnicodeBlock(name='Oriya', start=0x0b00, end=0x0b7f, assigned_ranges=[(0x0b01, 0x0b03), (0x0b05, 0x0b0c), (0x0b0f, 0x0b10), (0x0b13, 0x0b28), (0x0b2a, 0x0b30), (0x0b32, 0x0b33), (0x0b35, 0x0b39), (0x0b3c, 0x0b44), (0x0b47, 0x0b48), (0x0b4b, 0x0b4d), (0x0b56, 0x0b57), (0x0b5c, 0x0b5d), (0x0b5f, 0x0b63), (0x0b66, 0x0b77)])
+TAMIL = UnicodeBlock(name='Tamil', start=0x0b80, end=0x0bff, assigned_ranges=[(0x0b82, 0x0b83), (0x0b85, 0x0b8a), (0x0b8e, 0x0b90), (0x0b92, 0x0b95), (0x0b99, 0x0b9a), (0x0b9c, 0x0b9c), (0x0b9e, 0x0b9f), (0x0ba3, 0x0ba4), (0x0ba8, 0x0baa), (0x0bae, 0x0bb9), (0x0bbe, 0x0bc2), (0x0bc6, 0x0bc8), (0x0bca, 0x0bcd), (0x0bd0, 0x0bd0), (0x0bd7, 0x0bd7), (0x0be6, 0x0bfa)])
+TELUGU = UnicodeBlock(name='Telugu', start=0x0c00, end=0x0c7f, assigned_ranges=[(0x0c01, 0x0c03), (0x0c05, 0x0c0c), (0x0c0e, 0x0c10), (0x0c12, 0x0c28), (0x0c2a, 0x0c33), (0x0c35, 0x0c39), (0x0c3d, 0x0c44), (0x0c46, 0x0c48), (0x0c4a, 0x0c4d), (0x0c55, 0x0c56), (0x0c58, 0x0c59), (0x0c60, 0x0c63), (0x0c66, 0x0c6f), (0x0c78, 0x0c7f)])
+KANNADA = UnicodeBlock(name='Kannada', start=0x0c80, end=0x0cff, assigned_ranges=[(0x0c82, 0x0c83), (0x0c85, 0x0c8c), (0x0c8e, 0x0c90), (0x0c92, 0x0ca8), (0x0caa, 0x0cb3), (0x0cb5, 0x0cb9), (0x0cbc, 0x0cc4), (0x0cc6, 0x0cc8), (0x0cca, 0x0ccd), (0x0cd5, 0x0cd6), (0x0cde, 0x0cde), (0x0ce0, 0x0ce3), (0x0ce6, 0x0cef), (0x0cf1, 0x0cf2)])
+MALAYALAM = UnicodeBlock(name='Malayalam', start=0x0d00, end=0x0d7f, assigned_ranges=[(0x0d02, 0x0d03), (0x0d05, 0x0d0c), (0x0d0e, 0x0d10), (0x0d12, 0x0d3a), (0x0d3d, 0x0d44), (0x0d46, 0x0d48), (0x0d4a, 0x0d4e), (0x0d57, 0x0d57), (0x0d60, 0x0d63), (0x0d66, 0x0d75), (0x0d79, 0x0d7f)])
+SINHALA = UnicodeBlock(name='Sinhala', start=0x0d80, end=0x0dff, assigned_ranges=[(0x0d82, 0x0d83), (0x0d85, 0x0d96), (0x0d9a, 0x0db1), (0x0db3, 0x0dbb), (0x0dbd, 0x0dbd), (0x0dc0, 0x0dc6), (0x0dca, 0x0dca), (0x0dcf, 0x0dd4), (0x0dd6, 0x0dd6), (0x0dd8, 0x0ddf), (0x0df2, 0x0df4)])
+THAI = UnicodeBlock(name='Thai', start=0x0e00, end=0x0e7f, assigned_ranges=[(0x0e01, 0x0e3a), (0x0e3f, 0x0e5b)])
+LAO = UnicodeBlock(name='Lao', start=0x0e80, end=0x0eff, assigned_ranges=[(0x0e81, 0x0e82), (0x0e84, 0x0e84), (0x0e87, 0x0e88), (0x0e8a, 0x0e8a), (0x0e8d, 0x0e8d), (0x0e94, 0x0e97), (0x0e99, 0x0e9f), (0x0ea1, 0x0ea3), (0x0ea5, 0x0ea5), (0x0ea7, 0x0ea7), (0x0eaa, 0x0eab), (0x0ead, 0x0eb9), (0x0ebb, 0x0ebd), (0x0ec0, 0x0ec4), (0x0ec6, 0x0ec6), (0x0ec8, 0x0ecd), (0x0ed0, 0x0ed9), (0x0edc, 0x0edf)])
+TIBETAN = UnicodeBlock(name='Tibetan', start=0x0f00, end=0x0fff, assigned_ranges=[(0x0f00, 0x0f47), (0x0f49, 0x0f6c), (0x0f71, 0x0f97), (0x0f99, 0x0fbc), (0x0fbe, 0x0fcc), (0x0fce, 0x0fda)])
+MYANMAR = UnicodeBlock(name='Myanmar', start=0x1000, end=0x109f, assigned_ranges=[(0x1000, 0x109f)])
+GEORGIAN = UnicodeBlock(name='Georgian', start=0x10a0, end=0x10ff, assigned_ranges=[(0x10a0, 0x10c5), (0x10c7, 0x10c7), (0x10cd, 0x10cd), (0x10d0, 0x10ff)])
+HANGUL_JAMO = UnicodeBlock(name='Hangul Jamo', start=0x1100, end=0x11ff, assigned_ranges=[(0x1100, 0x11ff)], aliases=['Jamo'])
+ETHIOPIC = UnicodeBlock(name='Ethiopic', start=0x1200, end=0x137f, assigned_ranges=[(0x1200, 0x1248), (0x124a, 0x124d), (0x1250, 0x1256), (0x1258, 0x1258), (0x125a, 0x125d), (0x1260, 0x1288), (0x128a, 0x128d), (0x1290, 0x12b0), (0x12b2, 0x12b5), (0x12b8, 0x12be), (0x12c0, 0x12c0), (0x12c2, 0x12c5), (0x12c8, 0x12d6), (0x12d8, 0x1310), (0x1312, 0x1315), (0x1318, 0x135a), (0x135d, 0x137c)])
+ETHIOPIC_SUPPLEMENT = UnicodeBlock(name='Ethiopic Supplement', start=0x1380, end=0x139f, assigned_ranges=[(0x1380, 0x1399)], aliases=['Ethiopic_Sup'])
+CHEROKEE = UnicodeBlock(name='Cherokee', start=0x13a0, end=0x13ff, assigned_ranges=[(0x13a0, 0x13f4)])
+UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = UnicodeBlock(name='Unified Canadian Aboriginal Syllabics', start=0x1400, end=0x167f, assigned_ranges=[(0x1400, 0x167f)], aliases=['UCAS', 'Canadian_Syllabics'])
+OGHAM = UnicodeBlock(name='Ogham', start=0x1680, end=0x169f, assigned_ranges=[(0x1680, 0x169c)])
+RUNIC = UnicodeBlock(name='Runic', start=0x16a0, end=0x16ff, assigned_ranges=[(0x16a0, 0x16f0)])
+TAGALOG = UnicodeBlock(name='Tagalog', start=0x1700, end=0x171f, assigned_ranges=[(0x1700, 0x170c), (0x170e, 0x1714)])
+HANUNOO = UnicodeBlock(name='Hanunoo', start=0x1720, end=0x173f, assigned_ranges=[(0x1720, 0x1736)])
+BUHID = UnicodeBlock(name='Buhid', start=0x1740, end=0x175f, assigned_ranges=[(0x1740, 0x1753)])
+TAGBANWA = UnicodeBlock(name='Tagbanwa', start=0x1760, end=0x177f, assigned_ranges=[(0x1760, 0x176c), (0x176e, 0x1770), (0x1772, 0x1773)])
+KHMER = UnicodeBlock(name='Khmer', start=0x1780, end=0x17ff, assigned_ranges=[(0x1780, 0x17dd), (0x17e0, 0x17e9), (0x17f0, 0x17f9)])
+MONGOLIAN = UnicodeBlock(name='Mongolian', start=0x1800, end=0x18af, assigned_ranges=[(0x1800, 0x180e), (0x1810, 0x1819), (0x1820, 0x1877), (0x1880, 0x18aa)])
+UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = UnicodeBlock(name='Unified Canadian Aboriginal Syllabics Extended', start=0x18b0, end=0x18ff, assigned_ranges=[(0x18b0, 0x18f5)], aliases=['UCAS_Ext'])
+LIMBU = UnicodeBlock(name='Limbu', start=0x1900, end=0x194f, assigned_ranges=[(0x1900, 0x191c), (0x1920, 0x192b), (0x1930, 0x193b), (0x1940, 0x1940), (0x1944, 0x194f)])
+TAI_LE = UnicodeBlock(name='Tai Le', start=0x1950, end=0x197f, assigned_ranges=[(0x1950, 0x196d), (0x1970, 0x1974)])
+NEW_TAI_LUE = UnicodeBlock(name='New Tai Lue', start=0x1980, end=0x19df, assigned_ranges=[(0x1980, 0x19ab), (0x19b0, 0x19c9), (0x19d0, 0x19da), (0x19de, 0x19df)])
+KHMER_SYMBOLS = UnicodeBlock(name='Khmer Symbols', start=0x19e0, end=0x19ff, assigned_ranges=[(0x19e0, 0x19ff)])
+BUGINESE = UnicodeBlock(name='Buginese', start=0x1a00, end=0x1a1f, assigned_ranges=[(0x1a00, 0x1a1b), (0x1a1e, 0x1a1f)])
+TAI_THAM = UnicodeBlock(name='Tai Tham', start=0x1a20, end=0x1aaf, assigned_ranges=[(0x1a20, 0x1a5e), (0x1a60, 0x1a7c), (0x1a7f, 0x1a89), (0x1a90, 0x1a99), (0x1aa0, 0x1aad)])
+BALINESE = UnicodeBlock(name='Balinese', start=0x1b00, end=0x1b7f, assigned_ranges=[(0x1b00, 0x1b4b), (0x1b50, 0x1b7c)])
+SUNDANESE = UnicodeBlock(name='Sundanese', start=0x1b80, end=0x1bbf, assigned_ranges=[(0x1b80, 0x1bbf)])
+BATAK = UnicodeBlock(name='Batak', start=0x1bc0, end=0x1bff, assigned_ranges=[(0x1bc0, 0x1bf3), (0x1bfc, 0x1bff)])
+LEPCHA = UnicodeBlock(name='Lepcha', start=0x1c00, end=0x1c4f, assigned_ranges=[(0x1c00, 0x1c37), (0x1c3b, 0x1c49), (0x1c4d, 0x1c4f)])
+OL_CHIKI = UnicodeBlock(name='Ol Chiki', start=0x1c50, end=0x1c7f, assigned_ranges=[(0x1c50, 0x1c7f)])
+SUNDANESE_SUPPLEMENT = UnicodeBlock(name='Sundanese Supplement', start=0x1cc0, end=0x1ccf, assigned_ranges=[(0x1cc0, 0x1cc7)], aliases=['Sundanese_Sup'])
+VEDIC_EXTENSIONS = UnicodeBlock(name='Vedic Extensions', start=0x1cd0, end=0x1cff, assigned_ranges=[(0x1cd0, 0x1cf6)], aliases=['Vedic_Ext'])
+PHONETIC_EXTENSIONS = UnicodeBlock(name='Phonetic Extensions', start=0x1d00, end=0x1d7f, assigned_ranges=[(0x1d00, 0x1d7f)], aliases=['Phonetic_Ext'])
+PHONETIC_EXTENSIONS_SUPPLEMENT = UnicodeBlock(name='Phonetic Extensions Supplement', start=0x1d80, end=0x1dbf, assigned_ranges=[(0x1d80, 0x1dbf)], aliases=['Phonetic_Ext_Sup'])
+COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = UnicodeBlock(name='Combining Diacritical Marks Supplement', start=0x1dc0, end=0x1dff, assigned_ranges=[(0x1dc0, 0x1de6), (0x1dfc, 0x1dff)], aliases=['Diacriticals_Sup'])
+LATIN_EXTENDED_ADDITIONAL = UnicodeBlock(name='Latin Extended Additional', start=0x1e00, end=0x1eff, assigned_ranges=[(0x1e00, 0x1eff)], aliases=['Latin_Ext_Additional'])
+GREEK_EXTENDED = UnicodeBlock(name='Greek Extended', start=0x1f00, end=0x1fff, assigned_ranges=[(0x1f00, 0x1f15), (0x1f18, 0x1f1d), (0x1f20, 0x1f45), (0x1f48, 0x1f4d), (0x1f50, 0x1f57), (0x1f59, 0x1f59), (0x1f5b, 0x1f5b), (0x1f5d, 0x1f5d), (0x1f5f, 0x1f7d), (0x1f80, 0x1fb4), (0x1fb6, 0x1fc4), (0x1fc6, 0x1fd3), (0x1fd6, 0x1fdb), (0x1fdd, 0x1fef), (0x1ff2, 0x1ff4), (0x1ff6, 0x1ffe)], aliases=['Greek_Ext'])
+GENERAL_PUNCTUATION = UnicodeBlock(name='General Punctuation', start=0x2000, end=0x206f, assigned_ranges=[(0x2000, 0x2064), (0x206a, 0x206f)], aliases=['Punctuation'])
+SUPERSCRIPTS_AND_SUBSCRIPTS = UnicodeBlock(name='Superscripts and Subscripts', start=0x2070, end=0x209f, assigned_ranges=[(0x2070, 0x2071), (0x2074, 0x208e), (0x2090, 0x209c)], aliases=['Super_And_Sub'])
+CURRENCY_SYMBOLS = UnicodeBlock(name='Currency Symbols', start=0x20a0, end=0x20cf, assigned_ranges=[(0x20a0, 0x20b9)])
+COMBINING_DIACRITICAL_MARKS_FOR_SYMBOLS = UnicodeBlock(name='Combining Diacritical Marks for Symbols', start=0x20d0, end=0x20ff, assigned_ranges=[(0x20d0, 0x20f0)], aliases=['Diacriticals_For_Symbols', 'Combining_Marks_For_Symbols'])
+LETTERLIKE_SYMBOLS = UnicodeBlock(name='Letterlike Symbols', start=0x2100, end=0x214f, assigned_ranges=[(0x2100, 0x214f)])
+NUMBER_FORMS = UnicodeBlock(name='Number Forms', start=0x2150, end=0x218f, assigned_ranges=[(0x2150, 0x2189)])
+ARROWS = UnicodeBlock(name='Arrows', start=0x2190, end=0x21ff, assigned_ranges=[(0x2190, 0x21ff)])
+MATHEMATICAL_OPERATORS = UnicodeBlock(name='Mathematical Operators', start=0x2200, end=0x22ff, assigned_ranges=[(0x2200, 0x22ff)], aliases=['Math_Operators'])
+MISCELLANEOUS_TECHNICAL = UnicodeBlock(name='Miscellaneous Technical', start=0x2300, end=0x23ff, assigned_ranges=[(0x2300, 0x23f3)], aliases=['Misc_Technical'])
+CONTROL_PICTURES = UnicodeBlock(name='Control Pictures', start=0x2400, end=0x243f, assigned_ranges=[(0x2400, 0x2426)])
+OPTICAL_CHARACTER_RECOGNITION = UnicodeBlock(name='Optical Character Recognition', start=0x2440, end=0x245f, assigned_ranges=[(0x2440, 0x244a)], aliases=['OCR'])
+ENCLOSED_ALPHANUMERICS = UnicodeBlock(name='Enclosed Alphanumerics', start=0x2460, end=0x24ff, assigned_ranges=[(0x2460, 0x24ff)], aliases=['Enclosed_Alphanum'])
+BOX_DRAWING = UnicodeBlock(name='Box Drawing', start=0x2500, end=0x257f, assigned_ranges=[(0x2500, 0x257f)])
+BLOCK_ELEMENTS = UnicodeBlock(name='Block Elements', start=0x2580, end=0x259f, assigned_ranges=[(0x2580, 0x259f)])
+GEOMETRIC_SHAPES = UnicodeBlock(name='Geometric Shapes', start=0x25a0, end=0x25ff, assigned_ranges=[(0x25a0, 0x25ff)])
+MISCELLANEOUS_SYMBOLS = UnicodeBlock(name='Miscellaneous Symbols', start=0x2600, end=0x26ff, assigned_ranges=[(0x2600, 0x26ff)], aliases=['Misc_Symbols'])
+DINGBATS = UnicodeBlock(name='Dingbats', start=0x2700, end=0x27bf, assigned_ranges=[(0x2701, 0x27bf)])
+MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = UnicodeBlock(name='Miscellaneous Mathematical Symbols-A', start=0x27c0, end=0x27ef, assigned_ranges=[(0x27c0, 0x27ef)], aliases=['Misc_Math_Symbols_A'])
+SUPPLEMENTAL_ARROWS_A = UnicodeBlock(name='Supplemental Arrows-A', start=0x27f0, end=0x27ff, assigned_ranges=[(0x27f0, 0x27ff)], aliases=['Sup_Arrows_A'])
+BRAILLE_PATTERNS = UnicodeBlock(name='Braille Patterns', start=0x2800, end=0x28ff, assigned_ranges=[(0x2800, 0x28ff)], aliases=['Braille'])
+SUPPLEMENTAL_ARROWS_B = UnicodeBlock(name='Supplemental Arrows-B', start=0x2900, end=0x297f, assigned_ranges=[(0x2900, 0x297f)], aliases=['Sup_Arrows_B'])
+MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = UnicodeBlock(name='Miscellaneous Mathematical Symbols-B', start=0x2980, end=0x29ff, assigned_ranges=[(0x2980, 0x29ff)], aliases=['Misc_Math_Symbols_B'])
+SUPPLEMENTAL_MATHEMATICAL_OPERATORS = UnicodeBlock(name='Supplemental Mathematical Operators', start=0x2a00, end=0x2aff, assigned_ranges=[(0x2a00, 0x2aff)], aliases=['Sup_Math_Operators'])
+MISCELLANEOUS_SYMBOLS_AND_ARROWS = UnicodeBlock(name='Miscellaneous Symbols and Arrows', start=0x2b00, end=0x2bff, assigned_ranges=[(0x2b00, 0x2b4c), (0x2b50, 0x2b59)], aliases=['Misc_Arrows'])
+GLAGOLITIC = UnicodeBlock(name='Glagolitic', start=0x2c00, end=0x2c5f, assigned_ranges=[(0x2c00, 0x2c2e), (0x2c30, 0x2c5e)])
+LATIN_EXTENDED_C = UnicodeBlock(name='Latin Extended-C', start=0x2c60, end=0x2c7f, assigned_ranges=[(0x2c60, 0x2c7f)], aliases=['Latin_Ext_C'])
+COPTIC = UnicodeBlock(name='Coptic', start=0x2c80, end=0x2cff, assigned_ranges=[(0x2c80, 0x2cf3), (0x2cf9, 0x2cff)])
+GEORGIAN_SUPPLEMENT = UnicodeBlock(name='Georgian Supplement', start=0x2d00, end=0x2d2f, assigned_ranges=[(0x2d00, 0x2d25), (0x2d27, 0x2d27), (0x2d2d, 0x2d2d)], aliases=['Georgian_Sup'])
+TIFINAGH = UnicodeBlock(name='Tifinagh', start=0x2d30, end=0x2d7f, assigned_ranges=[(0x2d30, 0x2d67), (0x2d6f, 0x2d70), (0x2d7f, 0x2d7f)])
+ETHIOPIC_EXTENDED = UnicodeBlock(name='Ethiopic Extended', start=0x2d80, end=0x2ddf, assigned_ranges=[(0x2d80, 0x2d96), (0x2da0, 0x2da6), (0x2da8, 0x2dae), (0x2db0, 0x2db6), (0x2db8, 0x2dbe), (0x2dc0, 0x2dc6), (0x2dc8, 0x2dce), (0x2dd0, 0x2dd6), (0x2dd8, 0x2dde)], aliases=['Ethiopic_Ext'])
+CYRILLIC_EXTENDED_A = UnicodeBlock(name='Cyrillic Extended-A', start=0x2de0, end=0x2dff, assigned_ranges=[(0x2de0, 0x2dff)], aliases=['Cyrillic_Ext_A'])
+SUPPLEMENTAL_PUNCTUATION = UnicodeBlock(name='Supplemental Punctuation', start=0x2e00, end=0x2e7f, assigned_ranges=[(0x2e00, 0x2e3b)], aliases=['Sup_Punctuation'])
+CJK_RADICALS_SUPPLEMENT = UnicodeBlock(name='CJK Radicals Supplement', start=0x2e80, end=0x2eff, assigned_ranges=[(0x2e80, 0x2e99), (0x2e9b, 0x2ef3)], aliases=['CJK_Radicals_Sup'])
+KANGXI_RADICALS = UnicodeBlock(name='Kangxi Radicals', start=0x2f00, end=0x2fdf, assigned_ranges=[(0x2f00, 0x2fd5)], aliases=['Kangxi'])
+IDEOGRAPHIC_DESCRIPTION_CHARACTERS = UnicodeBlock(name='Ideographic Description Characters', start=0x2ff0, end=0x2fff, assigned_ranges=[(0x2ff0, 0x2ffb)], aliases=['IDC'])
+CJK_SYMBOLS_AND_PUNCTUATION = UnicodeBlock(name='CJK Symbols and Punctuation', start=0x3000, end=0x303f, assigned_ranges=[(0x3000, 0x303f)], aliases=['CJK_Symbols'])
+HIRAGANA = UnicodeBlock(name='Hiragana', start=0x3040, end=0x309f, assigned_ranges=[(0x3041, 0x3096), (0x3099, 0x309f)])
+KATAKANA = UnicodeBlock(name='Katakana', start=0x30a0, end=0x30ff, assigned_ranges=[(0x30a0, 0x30ff)])
+BOPOMOFO = UnicodeBlock(name='Bopomofo', start=0x3100, end=0x312f, assigned_ranges=[(0x3105, 0x312d)])
+HANGUL_COMPATIBILITY_JAMO = UnicodeBlock(name='Hangul Compatibility Jamo', start=0x3130, end=0x318f, assigned_ranges=[(0x3131, 0x318e)], aliases=['Compat_Jamo'])
+KANBUN = UnicodeBlock(name='Kanbun', start=0x3190, end=0x319f, assigned_ranges=[(0x3190, 0x319f)])
+BOPOMOFO_EXTENDED = UnicodeBlock(name='Bopomofo Extended', start=0x31a0, end=0x31bf, assigned_ranges=[(0x31a0, 0x31ba)], aliases=['Bopomofo_Ext'])
+CJK_STROKES = UnicodeBlock(name='CJK Strokes', start=0x31c0, end=0x31ef, assigned_ranges=[(0x31c0, 0x31e3)])
+KATAKANA_PHONETIC_EXTENSIONS = UnicodeBlock(name='Katakana Phonetic Extensions', start=0x31f0, end=0x31ff, assigned_ranges=[(0x31f0, 0x31ff)], aliases=['Katakana_Ext'])
+ENCLOSED_CJK_LETTERS_AND_MONTHS = UnicodeBlock(name='Enclosed CJK Letters and Months', start=0x3200, end=0x32ff, assigned_ranges=[(0x3200, 0x321e), (0x3220, 0x32fe)], aliases=['Enclosed_CJK'])
+CJK_COMPATIBILITY = UnicodeBlock(name='CJK Compatibility', start=0x3300, end=0x33ff, assigned_ranges=[(0x3300, 0x33ff)], aliases=['CJK_Compat'])
+CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = UnicodeBlock(name='CJK Unified Ideographs Extension A', start=0x3400, end=0x4dbf, assigned_ranges=[(0x3400, 0x4db5)], aliases=['CJK_Ext_A'])
+YIJING_HEXAGRAM_SYMBOLS = UnicodeBlock(name='Yijing Hexagram Symbols', start=0x4dc0, end=0x4dff, assigned_ranges=[(0x4dc0, 0x4dff)], aliases=['Yijing'])
+CJK_UNIFIED_IDEOGRAPHS = UnicodeBlock(name='CJK Unified Ideographs', start=0x4e00, end=0x9fff, assigned_ranges=[(0x4e00, 0x9fcc)], aliases=['CJK'])
+YI_SYLLABLES = UnicodeBlock(name='Yi Syllables', start=0xa000, end=0xa48f, assigned_ranges=[(0xa000, 0xa48c)])
+YI_RADICALS = UnicodeBlock(name='Yi Radicals', start=0xa490, end=0xa4cf, assigned_ranges=[(0xa490, 0xa4c6)])
+LISU = UnicodeBlock(name='Lisu', start=0xa4d0, end=0xa4ff, assigned_ranges=[(0xa4d0, 0xa4ff)])
+VAI = UnicodeBlock(name='Vai', start=0xa500, end=0xa63f, assigned_ranges=[(0xa500, 0xa62b)])
+CYRILLIC_EXTENDED_B = UnicodeBlock(name='Cyrillic Extended-B', start=0xa640, end=0xa69f, assigned_ranges=[(0xa640, 0xa697), (0xa69f, 0xa69f)], aliases=['Cyrillic_Ext_B'])
+BAMUM = UnicodeBlock(name='Bamum', start=0xa6a0, end=0xa6ff, assigned_ranges=[(0xa6a0, 0xa6f7)])
+MODIFIER_TONE_LETTERS = UnicodeBlock(name='Modifier Tone Letters', start=0xa700, end=0xa71f, assigned_ranges=[(0xa700, 0xa71f)])
+LATIN_EXTENDED_D = UnicodeBlock(name='Latin Extended-D', start=0xa720, end=0xa7ff, assigned_ranges=[(0xa720, 0xa78e), (0xa790, 0xa793), (0xa7a0, 0xa7aa), (0xa7f8, 0xa7ff)], aliases=['Latin_Ext_D'])
+SYLOTI_NAGRI = UnicodeBlock(name='Syloti Nagri', start=0xa800, end=0xa82f, assigned_ranges=[(0xa800, 0xa82b)])
+COMMON_INDIC_NUMBER_FORMS = UnicodeBlock(name='Common Indic Number Forms', start=0xa830, end=0xa83f, assigned_ranges=[(0xa830, 0xa839)], aliases=['Indic_Number_Forms'])
+PHAGS_PA = UnicodeBlock(name='Phags-pa', start=0xa840, end=0xa87f, assigned_ranges=[(0xa840, 0xa877)])
+SAURASHTRA = UnicodeBlock(name='Saurashtra', start=0xa880, end=0xa8df, assigned_ranges=[(0xa880, 0xa8c4), (0xa8ce, 0xa8d9)])
+DEVANAGARI_EXTENDED = UnicodeBlock(name='Devanagari Extended', start=0xa8e0, end=0xa8ff, assigned_ranges=[(0xa8e0, 0xa8fb)], aliases=['Devanagari_Ext'])
+KAYAH_LI = UnicodeBlock(name='Kayah Li', start=0xa900, end=0xa92f, assigned_ranges=[(0xa900, 0xa92f)])
+REJANG = UnicodeBlock(name='Rejang', start=0xa930, end=0xa95f, assigned_ranges=[(0xa930, 0xa953), (0xa95f, 0xa95f)])
+HANGUL_JAMO_EXTENDED_A = UnicodeBlock(name='Hangul Jamo Extended-A', start=0xa960, end=0xa97f, assigned_ranges=[(0xa960, 0xa97c)], aliases=['Jamo_Ext_A'])
+JAVANESE = UnicodeBlock(name='Javanese', start=0xa980, end=0xa9df, assigned_ranges=[(0xa980, 0xa9cd), (0xa9cf, 0xa9d9), (0xa9de, 0xa9df)])
+CHAM = UnicodeBlock(name='Cham', start=0xaa00, end=0xaa5f, assigned_ranges=[(0xaa00, 0xaa36), (0xaa40, 0xaa4d), (0xaa50, 0xaa59), (0xaa5c, 0xaa5f)])
+MYANMAR_EXTENDED_A = UnicodeBlock(name='Myanmar Extended-A', start=0xaa60, end=0xaa7f, assigned_ranges=[(0xaa60, 0xaa7b)], aliases=['Myanmar_Ext_A'])
+TAI_VIET = UnicodeBlock(name='Tai Viet', start=0xaa80, end=0xaadf, assigned_ranges=[(0xaa80, 0xaac2), (0xaadb, 0xaadf)])
+MEETEI_MAYEK_EXTENSIONS = UnicodeBlock(name='Meetei Mayek Extensions', start=0xaae0, end=0xaaff, assigned_ranges=[(0xaae0, 0xaaf6)], aliases=['Meetei_Mayek_Ext'])
+ETHIOPIC_EXTENDED_A = UnicodeBlock(name='Ethiopic Extended-A', start=0xab00, end=0xab2f, assigned_ranges=[(0xab01, 0xab06), (0xab09, 0xab0e), (0xab11, 0xab16), (0xab20, 0xab26), (0xab28, 0xab2e)], aliases=['Ethiopic_Ext_A'])
+MEETEI_MAYEK = UnicodeBlock(name='Meetei Mayek', start=0xabc0, end=0xabff, assigned_ranges=[(0xabc0, 0xabed), (0xabf0, 0xabf9)])
+HANGUL_SYLLABLES = UnicodeBlock(name='Hangul Syllables', start=0xac00, end=0xd7af, assigned_ranges=[(0xac00, 0xd7a3)], aliases=['Hangul'])
+HANGUL_JAMO_EXTENDED_B = UnicodeBlock(name='Hangul Jamo Extended-B', start=0xd7b0, end=0xd7ff, assigned_ranges=[(0xd7b0, 0xd7c6), (0xd7cb, 0xd7fb)], aliases=['Jamo_Ext_B'])
+HIGH_SURROGATES = UnicodeBlock(name='High Surrogates', start=0xd800, end=0xdb7f, assigned_ranges=[(0xd800, 0xdb7f)])
+HIGH_PRIVATE_USE_SURROGATES = UnicodeBlock(name='High Private Use Surrogates', start=0xdb80, end=0xdbff, assigned_ranges=[(0xdb80, 0xdbff)], aliases=['High_PU_Surrogates'])
+LOW_SURROGATES = UnicodeBlock(name='Low Surrogates', start=0xdc00, end=0xdfff, assigned_ranges=[(0xdc00, 0xdfff)])
+PRIVATE_USE_AREA = UnicodeBlock(name='Private Use Area', start=0xe000, end=0xf8ff, assigned_ranges=[(0xe000, 0xf8ff)], aliases=['PUA', 'Private_Use'])
+CJK_COMPATIBILITY_IDEOGRAPHS = UnicodeBlock(name='CJK Compatibility Ideographs', start=0xf900, end=0xfaff, assigned_ranges=[(0xf900, 0xfa6d), (0xfa70, 0xfad9)], aliases=['CJK_Compat_Ideographs'])
+ALPHABETIC_PRESENTATION_FORMS = UnicodeBlock(name='Alphabetic Presentation Forms', start=0xfb00, end=0xfb4f, assigned_ranges=[(0xfb00, 0xfb06), (0xfb13, 0xfb17), (0xfb1d, 0xfb36), (0xfb38, 0xfb3c), (0xfb3e, 0xfb3e), (0xfb40, 0xfb41), (0xfb43, 0xfb44), (0xfb46, 0xfb4f)], aliases=['Alphabetic_PF'])
+ARABIC_PRESENTATION_FORMS_A = UnicodeBlock(name='Arabic Presentation Forms-A', start=0xfb50, end=0xfdff, assigned_ranges=[(0xfb50, 0xfbc1), (0xfbd3, 0xfd3f), (0xfd50, 0xfd8f), (0xfd92, 0xfdc7), (0xfdf0, 0xfdfd)], aliases=['Arabic_PF_A', 'Arabic_Presentation_Forms-A'])
+VARIATION_SELECTORS = UnicodeBlock(name='Variation Selectors', start=0xfe00, end=0xfe0f, assigned_ranges=[(0xfe00, 0xfe0f)], aliases=['VS'])
+VERTICAL_FORMS = UnicodeBlock(name='Vertical Forms', start=0xfe10, end=0xfe1f, assigned_ranges=[(0xfe10, 0xfe19)])
+COMBINING_HALF_MARKS = UnicodeBlock(name='Combining Half Marks', start=0xfe20, end=0xfe2f, assigned_ranges=[(0xfe20, 0xfe26)], aliases=['Half_Marks'])
+CJK_COMPATIBILITY_FORMS = UnicodeBlock(name='CJK Compatibility Forms', start=0xfe30, end=0xfe4f, assigned_ranges=[(0xfe30, 0xfe4f)], aliases=['CJK_Compat_Forms'])
+SMALL_FORM_VARIANTS = UnicodeBlock(name='Small Form Variants', start=0xfe50, end=0xfe6f, assigned_ranges=[(0xfe50, 0xfe52), (0xfe54, 0xfe66), (0xfe68, 0xfe6b)], aliases=['Small_Forms'])
+ARABIC_PRESENTATION_FORMS_B = UnicodeBlock(name='Arabic Presentation Forms-B', start=0xfe70, end=0xfeff, assigned_ranges=[(0xfe70, 0xfe74), (0xfe76, 0xfefc), (0xfeff, 0xfeff)], aliases=['Arabic_PF_B'])
+HALFWIDTH_AND_FULLWIDTH_FORMS = UnicodeBlock(name='Halfwidth and Fullwidth Forms', start=0xff00, end=0xffef, assigned_ranges=[(0xff01, 0xffbe), (0xffc2, 0xffc7), (0xffca, 0xffcf), (0xffd2, 0xffd7), (0xffda, 0xffdc), (0xffe0, 0xffe6), (0xffe8, 0xffee)], aliases=['Half_And_Full_Forms'])
+SPECIALS = UnicodeBlock(name='Specials', start=0xfff0, end=0xffff, assigned_ranges=[(0xfff9, 0xfffd)])
+LINEAR_B_SYLLABARY = UnicodeBlock(name='Linear B Syllabary', start=0x10000, end=0x1007f, assigned_ranges=[(0x10000, 0x1000b), (0x1000d, 0x10026), (0x10028, 0x1003a), (0x1003c, 0x1003d), (0x1003f, 0x1004d), (0x10050, 0x1005d)])
+LINEAR_B_IDEOGRAMS = UnicodeBlock(name='Linear B Ideograms', start=0x10080, end=0x100ff, assigned_ranges=[(0x10080, 0x100fa)])
+AEGEAN_NUMBERS = UnicodeBlock(name='Aegean Numbers', start=0x10100, end=0x1013f, assigned_ranges=[(0x10100, 0x10102), (0x10107, 0x10133), (0x10137, 0x1013f)])
+ANCIENT_GREEK_NUMBERS = UnicodeBlock(name='Ancient Greek Numbers', start=0x10140, end=0x1018f, assigned_ranges=[(0x10140, 0x1018a)])
+ANCIENT_SYMBOLS = UnicodeBlock(name='Ancient Symbols', start=0x10190, end=0x101cf, assigned_ranges=[(0x10190, 0x1019b)])
+PHAISTOS_DISC = UnicodeBlock(name='Phaistos Disc', start=0x101d0, end=0x101ff, assigned_ranges=[(0x101d0, 0x101fd)], aliases=['Phaistos'])
+LYCIAN = UnicodeBlock(name='Lycian', start=0x10280, end=0x1029f, assigned_ranges=[(0x10280, 0x1029c)])
+CARIAN = UnicodeBlock(name='Carian', start=0x102a0, end=0x102df, assigned_ranges=[(0x102a0, 0x102d0)])
+OLD_ITALIC = UnicodeBlock(name='Old Italic', start=0x10300, end=0x1032f, assigned_ranges=[(0x10300, 0x1031e), (0x10320, 0x10323)])
+GOTHIC = UnicodeBlock(name='Gothic', start=0x10330, end=0x1034f, assigned_ranges=[(0x10330, 0x1034a)])
+UGARITIC = UnicodeBlock(name='Ugaritic', start=0x10380, end=0x1039f, assigned_ranges=[(0x10380, 0x1039d), (0x1039f, 0x1039f)])
+OLD_PERSIAN = UnicodeBlock(name='Old Persian', start=0x103a0, end=0x103df, assigned_ranges=[(0x103a0, 0x103c3), (0x103c8, 0x103d5)])
+DESERET = UnicodeBlock(name='Deseret', start=0x10400, end=0x1044f, assigned_ranges=[(0x10400, 0x1044f)])
+SHAVIAN = UnicodeBlock(name='Shavian', start=0x10450, end=0x1047f, assigned_ranges=[(0x10450, 0x1047f)])
+OSMANYA = UnicodeBlock(name='Osmanya', start=0x10480, end=0x104af, assigned_ranges=[(0x10480, 0x1049d), (0x104a0, 0x104a9)])
+CYPRIOT_SYLLABARY = UnicodeBlock(name='Cypriot Syllabary', start=0x10800, end=0x1083f, assigned_ranges=[(0x10800, 0x10805), (0x10808, 0x10808), (0x1080a, 0x10835), (0x10837, 0x10838), (0x1083c, 0x1083c), (0x1083f, 0x1083f)])
+IMPERIAL_ARAMAIC = UnicodeBlock(name='Imperial Aramaic', start=0x10840, end=0x1085f, assigned_ranges=[(0x10840, 0x10855), (0x10857, 0x1085f)])
+PHOENICIAN = UnicodeBlock(name='Phoenician', start=0x10900, end=0x1091f, assigned_ranges=[(0x10900, 0x1091b), (0x1091f, 0x1091f)])
+LYDIAN = UnicodeBlock(name='Lydian', start=0x10920, end=0x1093f, assigned_ranges=[(0x10920, 0x10939), (0x1093f, 0x1093f)])
+MEROITIC_HIEROGLYPHS = UnicodeBlock(name='Meroitic Hieroglyphs', start=0x10980, end=0x1099f, assigned_ranges=[(0x10980, 0x1099f)])
+MEROITIC_CURSIVE = UnicodeBlock(name='Meroitic Cursive', start=0x109a0, end=0x109ff, assigned_ranges=[(0x109a0, 0x109b7), (0x109be, 0x109bf)])
+KHAROSHTHI = UnicodeBlock(name='Kharoshthi', start=0x10a00, end=0x10a5f, assigned_ranges=[(0x10a00, 0x10a03), (0x10a05, 0x10a06), (0x10a0c, 0x10a13), (0x10a15, 0x10a17), (0x10a19, 0x10a33), (0x10a38, 0x10a3a), (0x10a3f, 0x10a47), (0x10a50, 0x10a58)])
+OLD_SOUTH_ARABIAN = UnicodeBlock(name='Old South Arabian', start=0x10a60, end=0x10a7f, assigned_ranges=[(0x10a60, 0x10a7f)])
+AVESTAN = UnicodeBlock(name='Avestan', start=0x10b00, end=0x10b3f, assigned_ranges=[(0x10b00, 0x10b35), (0x10b39, 0x10b3f)])
+INSCRIPTIONAL_PARTHIAN = UnicodeBlock(name='Inscriptional Parthian', start=0x10b40, end=0x10b5f, assigned_ranges=[(0x10b40, 0x10b55), (0x10b58, 0x10b5f)])
+INSCRIPTIONAL_PAHLAVI = UnicodeBlock(name='Inscriptional Pahlavi', start=0x10b60, end=0x10b7f, assigned_ranges=[(0x10b60, 0x10b72), (0x10b78, 0x10b7f)])
+OLD_TURKIC = UnicodeBlock(name='Old Turkic', start=0x10c00, end=0x10c4f, assigned_ranges=[(0x10c00, 0x10c48)])
+RUMI_NUMERAL_SYMBOLS = UnicodeBlock(name='Rumi Numeral Symbols', start=0x10e60, end=0x10e7f, assigned_ranges=[(0x10e60, 0x10e7e)], aliases=['Rumi'])
+BRAHMI = UnicodeBlock(name='Brahmi', start=0x11000, end=0x1107f, assigned_ranges=[(0x11000, 0x1104d), (0x11052, 0x1106f)])
+KAITHI = UnicodeBlock(name='Kaithi', start=0x11080, end=0x110cf, assigned_ranges=[(0x11080, 0x110c1)])
+SORA_SOMPENG = UnicodeBlock(name='Sora Sompeng', start=0x110d0, end=0x110ff, assigned_ranges=[(0x110d0, 0x110e8), (0x110f0, 0x110f9)])
+CHAKMA = UnicodeBlock(name='Chakma', start=0x11100, end=0x1114f, assigned_ranges=[(0x11100, 0x11134), (0x11136, 0x11143)])
+SHARADA = UnicodeBlock(name='Sharada', start=0x11180, end=0x111df, assigned_ranges=[(0x11180, 0x111c8), (0x111d0, 0x111d9)])
+TAKRI = UnicodeBlock(name='Takri', start=0x11680, end=0x116cf, assigned_ranges=[(0x11680, 0x116b7), (0x116c0, 0x116c9)])
+CUNEIFORM = UnicodeBlock(name='Cuneiform', start=0x12000, end=0x123ff, assigned_ranges=[(0x12000, 0x1236e)])
+CUNEIFORM_NUMBERS_AND_PUNCTUATION = UnicodeBlock(name='Cuneiform Numbers and Punctuation', start=0x12400, end=0x1247f, assigned_ranges=[(0x12400, 0x12462), (0x12470, 0x12473)], aliases=['Cuneiform_Numbers'])
+EGYPTIAN_HIEROGLYPHS = UnicodeBlock(name='Egyptian Hieroglyphs', start=0x13000, end=0x1342f, assigned_ranges=[(0x13000, 0x1342e)])
+BAMUM_SUPPLEMENT = UnicodeBlock(name='Bamum Supplement', start=0x16800, end=0x16a3f, assigned_ranges=[(0x16800, 0x16a38)], aliases=['Bamum_Sup'])
+MIAO = UnicodeBlock(name='Miao', start=0x16f00, end=0x16f9f, assigned_ranges=[(0x16f00, 0x16f44), (0x16f50, 0x16f7e), (0x16f8f, 0x16f9f)])
+KANA_SUPPLEMENT = UnicodeBlock(name='Kana Supplement', start=0x1b000, end=0x1b0ff, assigned_ranges=[(0x1b000, 0x1b001)], aliases=['Kana_Sup'])
+BYZANTINE_MUSICAL_SYMBOLS = UnicodeBlock(name='Byzantine Musical Symbols', start=0x1d000, end=0x1d0ff, assigned_ranges=[(0x1d000, 0x1d0f5)], aliases=['Byzantine_Music'])
+MUSICAL_SYMBOLS = UnicodeBlock(name='Musical Symbols', start=0x1d100, end=0x1d1ff, assigned_ranges=[(0x1d100, 0x1d126), (0x1d129, 0x1d1dd)], aliases=['Music'])
+ANCIENT_GREEK_MUSICAL_NOTATION = UnicodeBlock(name='Ancient Greek Musical Notation', start=0x1d200, end=0x1d24f, assigned_ranges=[(0x1d200, 0x1d245)], aliases=['Ancient_Greek_Music'])
+TAI_XUAN_JING_SYMBOLS = UnicodeBlock(name='Tai Xuan Jing Symbols', start=0x1d300, end=0x1d35f, assigned_ranges=[(0x1d300, 0x1d356)], aliases=['Tai_Xuan_Jing'])
+COUNTING_ROD_NUMERALS = UnicodeBlock(name='Counting Rod Numerals', start=0x1d360, end=0x1d37f, assigned_ranges=[(0x1d360, 0x1d371)], aliases=['Counting_Rod'])
+MATHEMATICAL_ALPHANUMERIC_SYMBOLS = UnicodeBlock(name='Mathematical Alphanumeric Symbols', start=0x1d400, end=0x1d7ff, assigned_ranges=[(0x1d400, 0x1d454), (0x1d456, 0x1d49c), (0x1d49e, 0x1d49f), (0x1d4a2, 0x1d4a2), (0x1d4a5, 0x1d4a6), (0x1d4a9, 0x1d4ac), (0x1d4ae, 0x1d4b9), (0x1d4bb, 0x1d4bb), (0x1d4bd, 0x1d4c3), (0x1d4c5, 0x1d505), (0x1d507, 0x1d50a), (0x1d50d, 0x1d514), (0x1d516, 0x1d51c), (0x1d51e, 0x1d539), (0x1d53b, 0x1d53e), (0x1d540, 0x1d544), (0x1d546, 0x1d546), (0x1d54a, 0x1d550), (0x1d552, 0x1d6a5), (0x1d6a8, 0x1d7cb), (0x1d7ce, 0x1d7ff)], aliases=['Math_Alphanum'])
+ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = UnicodeBlock(name='Arabic Mathematical Alphabetic Symbols', start=0x1ee00, end=0x1eeff, assigned_ranges=[(0x1ee00, 0x1ee03), (0x1ee05, 0x1ee1f), (0x1ee21, 0x1ee22), (0x1ee24, 0x1ee24), (0x1ee27, 0x1ee27), (0x1ee29, 0x1ee32), (0x1ee34, 0x1ee37), (0x1ee39, 0x1ee39), (0x1ee3b, 0x1ee3b), (0x1ee42, 0x1ee42), (0x1ee47, 0x1ee47), (0x1ee49, 0x1ee49), (0x1ee4b, 0x1ee4b), (0x1ee4d, 0x1ee4f), (0x1ee51, 0x1ee52), (0x1ee54, 0x1ee54), (0x1ee57, 0x1ee57), (0x1ee59, 0x1ee59), (0x1ee5b, 0x1ee5b), (0x1ee5d, 0x1ee5d), (0x1ee5f, 0x1ee5f), (0x1ee61, 0x1ee62), (0x1ee64, 0x1ee64), (0x1ee67, 0x1ee6a), (0x1ee6c, 0x1ee72), (0x1ee74, 0x1ee77), (0x1ee79, 0x1ee7c), (0x1ee7e, 0x1ee7e), (0x1ee80, 0x1ee89), (0x1ee8b, 0x1ee9b), (0x1eea1, 0x1eea3), (0x1eea5, 0x1eea9), (0x1eeab, 0x1eebb), (0x1eef0, 0x1eef1)], aliases=['Arabic_Math'])
+MAHJONG_TILES = UnicodeBlock(name='Mahjong Tiles', start=0x1f000, end=0x1f02f, assigned_ranges=[(0x1f000, 0x1f02b)], aliases=['Mahjong'])
+DOMINO_TILES = UnicodeBlock(name='Domino Tiles', start=0x1f030, end=0x1f09f, assigned_ranges=[(0x1f030, 0x1f093)], aliases=['Domino'])
+PLAYING_CARDS = UnicodeBlock(name='Playing Cards', start=0x1f0a0, end=0x1f0ff, assigned_ranges=[(0x1f0a0, 0x1f0ae), (0x1f0b1, 0x1f0be), (0x1f0c1, 0x1f0cf), (0x1f0d1, 0x1f0df)])
+ENCLOSED_ALPHANUMERIC_SUPPLEMENT = UnicodeBlock(name='Enclosed Alphanumeric Supplement', start=0x1f100, end=0x1f1ff, assigned_ranges=[(0x1f100, 0x1f10a), (0x1f110, 0x1f12e), (0x1f130, 0x1f16b), (0x1f170, 0x1f19a), (0x1f1e6, 0x1f1ff)], aliases=['Enclosed_Alphanum_Sup'])
+ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = UnicodeBlock(name='Enclosed Ideographic Supplement', start=0x1f200, end=0x1f2ff, assigned_ranges=[(0x1f200, 0x1f202), (0x1f210, 0x1f23a), (0x1f240, 0x1f248), (0x1f250, 0x1f251)], aliases=['Enclosed_Ideographic_Sup'])
+MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = UnicodeBlock(name='Miscellaneous Symbols And Pictographs', start=0x1f300, end=0x1f5ff, assigned_ranges=[(0x1f300, 0x1f320), (0x1f330, 0x1f335), (0x1f337, 0x1f37c), (0x1f380, 0x1f393), (0x1f3a0, 0x1f3c4), (0x1f3c6, 0x1f3ca), (0x1f3e0, 0x1f3f0), (0x1f400, 0x1f43e), (0x1f440, 0x1f440), (0x1f442, 0x1f4f7), (0x1f4f9, 0x1f4fc), (0x1f500, 0x1f53d), (0x1f540, 0x1f543), (0x1f550, 0x1f567), (0x1f5fb, 0x1f5ff)], aliases=['Misc_Pictographs'])
+EMOTICONS = UnicodeBlock(name='Emoticons', start=0x1f600, end=0x1f64f, assigned_ranges=[(0x1f600, 0x1f640), (0x1f645, 0x1f64f)])
+TRANSPORT_AND_MAP_SYMBOLS = UnicodeBlock(name='Transport And Map Symbols', start=0x1f680, end=0x1f6ff, assigned_ranges=[(0x1f680, 0x1f6c5)], aliases=['Transport_And_Map'])
+ALCHEMICAL_SYMBOLS = UnicodeBlock(name='Alchemical Symbols', start=0x1f700, end=0x1f77f, assigned_ranges=[(0x1f700, 0x1f773)], aliases=['Alchemical'])
+CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = UnicodeBlock(name='CJK Unified Ideographs Extension B', start=0x20000, end=0x2a6df, assigned_ranges=[(0x20000, 0x2a6d6)], aliases=['CJK_Ext_B'])
+CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = UnicodeBlock(name='CJK Unified Ideographs Extension C', start=0x2a700, end=0x2b73f, assigned_ranges=[(0x2a700, 0x2b734)], aliases=['CJK_Ext_C'])
+CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = UnicodeBlock(name='CJK Unified Ideographs Extension D', start=0x2b740, end=0x2b81f, assigned_ranges=[(0x2b740, 0x2b81d)], aliases=['CJK_Ext_D'])
+CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = UnicodeBlock(name='CJK Compatibility Ideographs Supplement', start=0x2f800, end=0x2fa1f, assigned_ranges=[(0x2f800, 0x2fa1d)], aliases=['CJK_Compat_Ideographs_Sup'])
+TAGS = UnicodeBlock(name='Tags', start=0xe0000, end=0xe007f, assigned_ranges=[(0xe0001, 0xe0001), (0xe0020, 0xe007f)])
+VARIATION_SELECTORS_SUPPLEMENT = UnicodeBlock(name='Variation Selectors Supplement', start=0xe0100, end=0xe01ef, assigned_ranges=[(0xe0100, 0xe01ef)], aliases=['VS_Sup'])
+SUPPLEMENTARY_PRIVATE_USE_AREA_A = UnicodeBlock(name='Supplementary Private Use Area-A', start=0xf0000, end=0xfffff, assigned_ranges=[(0xf0000, 0xffffd)], aliases=['Sup_PUA_A'])
+SUPPLEMENTARY_PRIVATE_USE_AREA_B = UnicodeBlock(name='Supplementary Private Use Area-B', start=0x100000, end=0x10ffff, assigned_ranges=[(0x100000, 0x10fffd)], aliases=['Sup_PUA_B'])
+
+ALL_BLOCKS = [
+    BASIC_LATIN,
+    LATIN_1_SUPPLEMENT,
+    LATIN_EXTENDED_A,
+    LATIN_EXTENDED_B,
+    IPA_EXTENSIONS,
+    SPACING_MODIFIER_LETTERS,
+    COMBINING_DIACRITICAL_MARKS,
+    GREEK_AND_COPTIC,
+    CYRILLIC,
+    CYRILLIC_SUPPLEMENT,
+    ARMENIAN,
+    HEBREW,
+    ARABIC,
+    SYRIAC,
+    ARABIC_SUPPLEMENT,
+    THAANA,
+    NKO,
+    SAMARITAN,
+    MANDAIC,
+    ARABIC_EXTENDED_A,
+    DEVANAGARI,
+    BENGALI,
+    GURMUKHI,
+    GUJARATI,
+    ORIYA,
+    TAMIL,
+    TELUGU,
+    KANNADA,
+    MALAYALAM,
+    SINHALA,
+    THAI,
+    LAO,
+    TIBETAN,
+    MYANMAR,
+    GEORGIAN,
+    HANGUL_JAMO,
+    ETHIOPIC,
+    ETHIOPIC_SUPPLEMENT,
+    CHEROKEE,
+    UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
+    OGHAM,
+    RUNIC,
+    TAGALOG,
+    HANUNOO,
+    BUHID,
+    TAGBANWA,
+    KHMER,
+    MONGOLIAN,
+    UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED,
+    LIMBU,
+    TAI_LE,
+    NEW_TAI_LUE,
+    KHMER_SYMBOLS,
+    BUGINESE,
+    TAI_THAM,
+    BALINESE,
+    SUNDANESE,
+    BATAK,
+    LEPCHA,
+    OL_CHIKI,
+    SUNDANESE_SUPPLEMENT,
+    VEDIC_EXTENSIONS,
+    PHONETIC_EXTENSIONS,
+    PHONETIC_EXTENSIONS_SUPPLEMENT,
+    COMBINING_DIACRITICAL_MARKS_SUPPLEMENT,
+    LATIN_EXTENDED_ADDITIONAL,
+    GREEK_EXTENDED,
+    GENERAL_PUNCTUATION,
+    SUPERSCRIPTS_AND_SUBSCRIPTS,
+    CURRENCY_SYMBOLS,
+    COMBINING_DIACRITICAL_MARKS_FOR_SYMBOLS,
+    LETTERLIKE_SYMBOLS,
+    NUMBER_FORMS,
+    ARROWS,
+    MATHEMATICAL_OPERATORS,
+    MISCELLANEOUS_TECHNICAL,
+    CONTROL_PICTURES,
+    OPTICAL_CHARACTER_RECOGNITION,
+    ENCLOSED_ALPHANUMERICS,
+    BOX_DRAWING,
+    BLOCK_ELEMENTS,
+    GEOMETRIC_SHAPES,
+    MISCELLANEOUS_SYMBOLS,
+    DINGBATS,
+    MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
+    SUPPLEMENTAL_ARROWS_A,
+    BRAILLE_PATTERNS,
+    SUPPLEMENTAL_ARROWS_B,
+    MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
+    SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
+    MISCELLANEOUS_SYMBOLS_AND_ARROWS,
+    GLAGOLITIC,
+    LATIN_EXTENDED_C,
+    COPTIC,
+    GEORGIAN_SUPPLEMENT,
+    TIFINAGH,
+    ETHIOPIC_EXTENDED,
+    CYRILLIC_EXTENDED_A,
+    SUPPLEMENTAL_PUNCTUATION,
+    CJK_RADICALS_SUPPLEMENT,
+    KANGXI_RADICALS,
+    IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
+    CJK_SYMBOLS_AND_PUNCTUATION,
+    HIRAGANA,
+    KATAKANA,
+    BOPOMOFO,
+    HANGUL_COMPATIBILITY_JAMO,
+    KANBUN,
+    BOPOMOFO_EXTENDED,
+    CJK_STROKES,
+    KATAKANA_PHONETIC_EXTENSIONS,
+    ENCLOSED_CJK_LETTERS_AND_MONTHS,
+    CJK_COMPATIBILITY,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
+    YIJING_HEXAGRAM_SYMBOLS,
+    CJK_UNIFIED_IDEOGRAPHS,
+    YI_SYLLABLES,
+    YI_RADICALS,
+    LISU,
+    VAI,
+    CYRILLIC_EXTENDED_B,
+    BAMUM,
+    MODIFIER_TONE_LETTERS,
+    LATIN_EXTENDED_D,
+    SYLOTI_NAGRI,
+    COMMON_INDIC_NUMBER_FORMS,
+    PHAGS_PA,
+    SAURASHTRA,
+    DEVANAGARI_EXTENDED,
+    KAYAH_LI,
+    REJANG,
+    HANGUL_JAMO_EXTENDED_A,
+    JAVANESE,
+    CHAM,
+    MYANMAR_EXTENDED_A,
+    TAI_VIET,
+    MEETEI_MAYEK_EXTENSIONS,
+    ETHIOPIC_EXTENDED_A,
+    MEETEI_MAYEK,
+    HANGUL_SYLLABLES,
+    HANGUL_JAMO_EXTENDED_B,
+    HIGH_SURROGATES,
+    HIGH_PRIVATE_USE_SURROGATES,
+    LOW_SURROGATES,
+    PRIVATE_USE_AREA,
+    CJK_COMPATIBILITY_IDEOGRAPHS,
+    ALPHABETIC_PRESENTATION_FORMS,
+    ARABIC_PRESENTATION_FORMS_A,
+    VARIATION_SELECTORS,
+    VERTICAL_FORMS,
+    COMBINING_HALF_MARKS,
+    CJK_COMPATIBILITY_FORMS,
+    SMALL_FORM_VARIANTS,
+    ARABIC_PRESENTATION_FORMS_B,
+    HALFWIDTH_AND_FULLWIDTH_FORMS,
+    SPECIALS,
+    LINEAR_B_SYLLABARY,
+    LINEAR_B_IDEOGRAMS,
+    AEGEAN_NUMBERS,
+    ANCIENT_GREEK_NUMBERS,
+    ANCIENT_SYMBOLS,
+    PHAISTOS_DISC,
+    LYCIAN,
+    CARIAN,
+    OLD_ITALIC,
+    GOTHIC,
+    UGARITIC,
+    OLD_PERSIAN,
+    DESERET,
+    SHAVIAN,
+    OSMANYA,
+    CYPRIOT_SYLLABARY,
+    IMPERIAL_ARAMAIC,
+    PHOENICIAN,
+    LYDIAN,
+    MEROITIC_HIEROGLYPHS,
+    MEROITIC_CURSIVE,
+    KHAROSHTHI,
+    OLD_SOUTH_ARABIAN,
+    AVESTAN,
+    INSCRIPTIONAL_PARTHIAN,
+    INSCRIPTIONAL_PAHLAVI,
+    OLD_TURKIC,
+    RUMI_NUMERAL_SYMBOLS,
+    BRAHMI,
+    KAITHI,
+    SORA_SOMPENG,
+    CHAKMA,
+    SHARADA,
+    TAKRI,
+    CUNEIFORM,
+    CUNEIFORM_NUMBERS_AND_PUNCTUATION,
+    EGYPTIAN_HIEROGLYPHS,
+    BAMUM_SUPPLEMENT,
+    MIAO,
+    KANA_SUPPLEMENT,
+    BYZANTINE_MUSICAL_SYMBOLS,
+    MUSICAL_SYMBOLS,
+    ANCIENT_GREEK_MUSICAL_NOTATION,
+    TAI_XUAN_JING_SYMBOLS,
+    COUNTING_ROD_NUMERALS,
+    MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
+    ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS,
+    MAHJONG_TILES,
+    DOMINO_TILES,
+    PLAYING_CARDS,
+    ENCLOSED_ALPHANUMERIC_SUPPLEMENT,
+    ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
+    MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS,
+    EMOTICONS,
+    TRANSPORT_AND_MAP_SYMBOLS,
+    ALCHEMICAL_SYMBOLS,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
+    CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
+    TAGS,
+    VARIATION_SELECTORS_SUPPLEMENT,
+    SUPPLEMENTARY_PRIVATE_USE_AREA_A,
+    SUPPLEMENTARY_PRIVATE_USE_AREA_B,
+]
+
+IDEO_BLOCKS = [
+    KANGXI_RADICALS,
+    CJK_RADICALS_SUPPLEMENT,
+    CJK_COMPATIBILITY_IDEOGRAPHS,
+    CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
+    CJK_UNIFIED_IDEOGRAPHS,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
+    CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
+]
+
+JPAN_BLOCKS = [
+    CJK_COMPATIBILITY,
+    HIRAGANA,
+    KATAKANA,
+    KATAKANA_PHONETIC_EXTENSIONS,
+    KANA_SUPPLEMENT,
+]
+
+KORE_BLOCKS = [
+    HANGUL_SYLLABLES,
+    HANGUL_JAMO,
+    HANGUL_COMPATIBILITY_JAMO,
+    HANGUL_JAMO_EXTENDED_A,
+    HANGUL_JAMO_EXTENDED_B,
+]
+
+PUNC_BLOCKS = [
+    CJK_COMPATIBILITY,
+    CJK_COMPATIBILITY_FORMS,
+    CJK_STROKES,
+    CJK_SYMBOLS_AND_PUNCTUATION,
+    HALFWIDTH_AND_FULLWIDTH_FORMS,
+    ENCLOSED_CJK_LETTERS_AND_MONTHS,
+    ENCLOSED_IDEOGRAPHIC_SUPPLEMENT,
+    IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
+]
+

unicode_blocks/charNormaliser.py

@@ -0,0 +1,17 @@
+class CharNormaliser:
+    @staticmethod
+    def to_codepoint(char: int | str | bytes) -> int:
+        """Convert a character to its Unicode code point.
+        May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+        Returns the Unicode code point as an integer.
+        """
+        if isinstance(char, int):
+            unidec = char
+        elif isinstance(char, bytes):
+            unidec = ord(char.decode("utf-8")[0])
+        elif isinstance(char, str):
+            unidec = ord(char[0])
+        else:
+            raise TypeError(f"Expected str, int, or bytes, got {type(char).__name__}")
+        assert 0 <= unidec < 0x110000, "Code point must be in the range [0, 0x10FFFF]"
+        return unidec

unicode_blocks/cjk.py

@@ -0,0 +1,149 @@
+from .unicodeBlock import UnicodeBlock
+from .charNormaliser import CharNormaliser
+from .blocks import IDEO_BLOCKS, JPAN_BLOCKS, KORE_BLOCKS, PUNC_BLOCKS
+
+CJK_BLOCKS = IDEO_BLOCKS + JPAN_BLOCKS + KORE_BLOCKS + PUNC_BLOCKS
+
+### Individual character checks ###
+
+
+def is_in_blocks(char: str | int | bytes, blocks: list[UnicodeBlock]) -> bool:
+    unidec = CharNormaliser.to_codepoint(char)
+    return any(unidec in block for block in blocks)
+
+
+def is_ideographic_zero(char: str | int | bytes) -> bool:
+    """Check if a character is ideographic zero (U+3007).
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return CharNormaliser.to_codepoint(char) == 0x3007
+
+
+def is_ideographic(char: str | int | bytes) -> bool:
+    """Check if a character is ideographic (hanzi/kanji/hanja/漢字/汉字).
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return is_ideographic_zero(char) or is_in_blocks(char, IDEO_BLOCKS)
+
+
+def is_japanese_kana(char: str | int | bytes) -> bool:
+    """Check if a character is Japanese kana (ひらがな/カタカナ).
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return is_in_blocks(char, JPAN_BLOCKS)
+
+
+def is_japanese(char: str | int | bytes) -> bool:
+    """Check if a character is Japanese (kanji + kana).
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return is_japanese_kana(char) or is_ideographic(char)
+
+
+def is_korean_hangul(char: str | int | bytes) -> bool:
+    """Check if a character is Korean hangul (한글).
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return is_in_blocks(char, KORE_BLOCKS)
+
+
+def is_korean(char: str | int | bytes) -> bool:
+    """Check if a character is Korean (hanja + hangul).
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return is_korean_hangul(char) or is_ideographic(char)
+
+
+def is_cjk_punctuation(char: str | int | bytes) -> bool:
+    """Check if a character is CJK symbol or punctuation.
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return is_in_blocks(char, PUNC_BLOCKS)
+
+
+def is_cjk(char: str | int | bytes) -> bool:
+    """Determine if a character is used in CJK (Chinese, Japanese, Korean) languages.
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    return is_ideographic_zero(char) or is_in_blocks(char, CJK_BLOCKS)
+
+
+### Block checks ###
+
+
+def is_ideographic_block(block: UnicodeBlock) -> bool:
+    """Check if a block is used in ideographic (hanzi/kanji/hanja/漢字/汉字)."""
+    return block in IDEO_BLOCKS
+
+
+def is_japanese_kana_block(block: UnicodeBlock) -> bool:
+    """Check if a block is used in Japanese kana (ひらがな/カタカナ)."""
+    return block in JPAN_BLOCKS
+
+
+def is_japanese_block(block: UnicodeBlock) -> bool:
+    """Check if a block is used in Japanese (kanji + kana)."""
+    return is_japanese_kana_block(block) or is_ideographic_block(block)
+
+
+def is_korean_hangul_block(block: UnicodeBlock) -> bool:
+    """Check if a block is used in Korean hangul (한글)."""
+    return block in KORE_BLOCKS
+
+
+def is_korean_block(block: UnicodeBlock) -> bool:
+    """Check if a block is used in Korean (hanja + hangul)."""
+    return is_korean_hangul_block(block) or is_ideographic_block(block)
+
+
+def is_cjk_punctuation_block(block: UnicodeBlock) -> bool:
+    """Check if a block is used in CJK symbol or punctuation."""
+    return block in PUNC_BLOCKS
+
+
+def is_cjk_block(block: UnicodeBlock) -> bool:
+    """Determine if a block is used in used in CJK (Chinese, Japanese, Korean) languages."""
+    return (
+        is_ideographic_block(block)
+        or is_japanese_block(block)
+        or is_korean_block(block)
+        or is_cjk_punctuation_block(block)
+    )
+
+
+### Block accessors ###
+
+
+def get_ideographic_blocks() -> list[UnicodeBlock]:
+    """Get all Unicode blocks used in ideographic (hanzi/kanji/hanja/漢字/汉字)."""
+    return IDEO_BLOCKS
+
+
+def get_japanese_kana_blocks() -> list[UnicodeBlock]:
+    """Get all Unicode blocks used in Japanese kana (ひらがな/カタカナ)."""
+    return JPAN_BLOCKS
+
+
+def get_japanese_blocks() -> list[UnicodeBlock]:
+    """Get all Unicode blocks used in Japanese (kanji + kana)."""
+    return JPAN_BLOCKS + IDEO_BLOCKS
+
+
+def get_korean_hangul_blocks() -> list[UnicodeBlock]:
+    """Get all Unicode blocks used in Korean hangul (한글)."""
+    return KORE_BLOCKS
+
+
+def get_korean_blocks() -> list[UnicodeBlock]:
+    """Get all Unicode blocks used in Korean (hanja + hangul)."""
+    return KORE_BLOCKS + IDEO_BLOCKS
+
+
+def get_cjk_punctuation_blocks() -> list[UnicodeBlock]:
+    """Get all Unicode blocks used in CJK symbol or punctuation."""
+    return PUNC_BLOCKS
+
+
+def get_cjk_blocks() -> list[UnicodeBlock]:
+    """Get all Unicode blocks used in used in CJK (Chinese, Japanese, Korean) languages."""
+    return CJK_BLOCKS

unicode_blocks/errors.py

@@ -0,0 +1,10 @@
+class UnicodeBlockError(Exception):
+    """Base class for exceptions in this module."""
+
+    pass
+
+
+class InvalidUnicodeBlockNameError(UnicodeBlockError):
+    """Exception raised for invalid Unicode block names."""
+
+    pass

unicode_blocks/globals.py

@@ -0,0 +1,44 @@
+from .unicodeBlock import UnicodeBlock
+from .charNormaliser import CharNormaliser
+from .blocks import ALL_BLOCKS, NO_BLOCK
+from .errors import InvalidUnicodeBlockNameError
+
+
+def all() -> list[UnicodeBlock]:
+    """
+    Get all Unicode blocks.
+    """
+    return ALL_BLOCKS
+
+
+def for_name(name: str) -> UnicodeBlock:
+    """
+    Get the Unicode block for a given name.
+    """
+    blocks = all()
+    for block in blocks:
+        if block.normalised_name == UnicodeBlock.normalise_name(name):
+            return block
+        if UnicodeBlock.normalise_name(name) in block.aliases:
+            return block
+    raise InvalidUnicodeBlockNameError(name)
+
+
+def of(char: str | int | bytes) -> UnicodeBlock:
+    """
+    Get the name of the Unicode block for a given character.
+    May be a str, int, or bytes. Bytes are decoded to str using utf-8.
+    """
+    unidec = CharNormaliser.to_codepoint(char)
+    blocks = all()
+    low, high = 0, len(blocks) - 1
+    while low <= high:
+        mid = (low + high) // 2
+        block = blocks[mid]
+        if unidec in block:
+            return block
+        elif unidec < block.start:
+            high = mid - 1
+        else:
+            low = mid + 1
+    return NO_BLOCK

unicode_blocks/unicodeBlock.py

@@ -0,0 +1,112 @@
+from __future__ import annotations
+
+from functools import total_ordering
+from typing import Optional
+
+from .charNormaliser import CharNormaliser
+
+
+@total_ordering
+class UnicodeBlock:
+    def __init__(
+        self,
+        name: str,
+        start: int,
+        end: int,
+        assigned_ranges: Optional[list[tuple[int, int]]] = None,
+        aliases: Optional[list[str]] = None,
+    ):
+        self.name = name
+        self.start = start
+        self.end = end
+        self.assigned_ranges = AssignedRanges(assigned_ranges) if assigned_ranges else []
+        self.aliases = [self.normalise_name(a) for a in aliases] if aliases else []
+
+    @property
+    def normalised_name(self) -> str:
+        """Return the normalised name of this Unicode block."""
+        return self.normalise_name(self.name)
+
+    @property
+    def variable_name(self) -> str:
+        """Return the variable name of this Unicode block."""
+        return self.to_variable_name(self.name)
+
+    def __contains__(self, char: str | int | bytes) -> bool:
+        """Check if a character is in this Unicode block.
+        May be a str, int, or bytes. Bytes are decoded to str using utf-8."""
+        unidec = CharNormaliser.to_codepoint(char)
+        return self.start <= unidec <= self.end
+
+    def __eq__(self, other: object) -> bool:
+        if not isinstance(other, UnicodeBlock):
+            return NotImplemented
+        return self.start == other.start
+
+    def __lt__(self, other: object) -> bool:
+        """Compare two UnicodeBlock objects based on their start values."""
+        if not isinstance(other, UnicodeBlock):
+            return NotImplemented
+        return self.start < other.start
+
+    def __hash__(self) -> int:
+        return hash((self.start, self.end))
+
+    def __repr__(self) -> str:
+        parts = [
+            f"name={self.name!r}",
+            f"start={self.start:#06x}",
+            f"end={self.end:#06x}",
+        ]
+
+        if self.assigned_ranges:
+            ranges_str = [f"({start:#06x}, {end:#06x})" for start, end in self.assigned_ranges]
+            parts.append(f"assigned_ranges=[{', '.join(ranges_str)}]")
+
+        if self.aliases:
+            parts.append(f"aliases={self.aliases!r}")
+
+        return f"{self.__class__.__name__}({', '.join(parts)})"
+
+    def __len__(self) -> int:
+        """Return the number of available code points in this block."""
+        return self.end - self.start + 1
+
+    @staticmethod
+    def normalise_name(name: str) -> str:
+        """Normalise the name of a Unicode block."""
+        name = name.upper().replace(" ", "").replace("-", "").replace("_", "")
+        if name.startswith("IS"):
+            name = name[2:]
+        return name
+
+    @staticmethod
+    def to_variable_name(name: str) -> str:
+        """Normalise the variable name of a Unicode block."""
+        return name.upper().replace(" ", "_").replace("-", "_")
+
+class AssignedRanges:
+    """A class to represent assigned ranges within a Unicode block."""
+    
+    def __init__(self, ranges: list[tuple[int, int]]):
+        self.ranges = ranges
+
+    def __iter__(self):
+        return iter(self.ranges)
+
+    def __repr__(self) -> str:
+        return f"AssignedRanges({self.ranges})"
+    
+    def __len__(self) -> int:
+        """Return the number of assigned ranges."""
+        if self.ranges is None:
+            return 0
+        return sum(end - start + 1 for start, end in self.ranges)
+    
+    def __contains__(self, char: str | int | bytes) -> bool:
+        """Check if a character is in any of the assigned ranges."""
+        unidec = CharNormaliser.to_codepoint(char)
+        for start, end in self.ranges:
+            if start <= unidec <= end:
+                return True
+        return False

unicode_blocks_py-6.1.0.dist-info/METADATA

@@ -0,0 +1,171 @@
+Metadata-Version: 2.4
+Name: unicode-blocks-py
+Version: 6.1.0
+Summary: Unicode blocks data utility module
+Author-email: NightFurySL2001 <nfsl-fonts@outlook.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/NightFurySL2001/unicode-blocks-py
+Project-URL: Issues, https://github.com/NightFurySL2001/unicode-blocks-py/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# 🧱 Unicode_Blocks 🧱
+
+`unicode_blocks` is a simple utility module for working with Unicode blocks data. [Unicode blocks](https://www.unicode.org/versions/latest/core-spec/chapter-3/#G64189) are continuous ranges of code points defined by the Unicode standard, used to group characters with generally similar purposes or origins.
+
+## Usage
+
+Install this package from PyPI:
+
+```sh
+pip install unicode-blocks-py
+```
+
+The module interface is heavily inspired by Java [`Character.UnicodeBlock`](https://docs.oracle.com/en/java/javase/21/docs/api/java.base/java/lang/Character.UnicodeBlock.html) class and Rust [`unicode_blocks`](https://docs.rs/unicode-blocks/latest/unicode_blocks/) module.
+
+```py
+>>> import unicode_blocks
+>>> unicode_major_version = int(unicode_blocks.__version__.split(".")[0])
+
+# To get Unicode block of a character, input a character string of length 1,
+# UTF-8 encoded bytes, or a positive integer representing a Unicode code point.
+# The following are the same: they decode the character 'a'.
+>>> block = unicode_blocks.of('a')
+>>> block2 = unicode_blocks.of(b'\x61')
+>>> block3 = unicode_blocks.of(97)
+>>> assert block == block2 == block3
+
+# To get Unicode block using name, input the block name.
+# Cases, whitespace, dashes, underscrolls and prefix "is" will be ignored for comparison. See UAX44-LM3.
+# Block name aliases from PropertyValueAliases are also usable here
+>>> ascii_block = unicode_blocks.for_name("BASIC_LATIN")
+>>> ascii_block2 = unicode_blocks.for_name("basiclatin")
+>>> ascii_block3 = unicode_blocks.for_name("isBasicLatin")
+>>> from unicode_blocks import BASIC_LATIN
+>>> assert ascii_block == ascii_block2 == ascii_block3 == BASIC_LATIN
+>>> if unicode_major_version >= 6:
+...     ascii_block4 = unicode_blocks.for_name("ASCII")
+...     assert ascii_block4 == BASIC_LATIN
+
+# Unicode characters currently not assigned will receive No_Block object as per
+# rule D10b in Section 3.4, *Characters and Encoding*, of Unicode
+>>> assert unicode_blocks.of(0xEDCBA) == unicode_blocks.NO_BLOCK
+
+# List through all the defined Unicode blocks at the version
+# NO_BLOCK is not in the list of all blocks
+>>> for block in unicode_blocks.all():
+...     print(block) # doctest: +ELLIPSIS
+UnicodeBlock(...)
+
+# Pythonic helpers: comparisons between blocks, where earlier blocks is smaller than later blocks
+# useful for sorting a list of UnicodeBlocks
+>>> latin1_block = unicode_blocks.for_name("Latin-1 Supplement")
+>>> assert ascii_block < latin1_block
+
+# Get the total defined code points in a block. Does not represent if the block is filled in or not.
+>>> assert len(ascii_block) == 128
+
+# Additional helpers: check for assigned characters in the block
+# Data is loaded from UCD and may change between Unicode versions
+>>> assert len(ascii_block.assigned_ranges) == 128
+>>> assert 'B' in ascii_block.assigned_ranges
+
+# Example where defined Unicode block range is not fully utilised
+>>> bopo_block = unicode_blocks.of('ㄅ')
+>>> assert len(bopo_block) == 48
+>>> bopo_assigned_count = 41 if unicode_major_version < 10 else 42 if unicode_major_version == 10 else 43
+>>> assert len(bopo_block.assigned_ranges) == bopo_assigned_count  # first 5 code points should be unassigned, at least in <=17.0
+>>> assert len(bopo_block) != len(bopo_block.assigned_ranges)
+
+```
+
+The lists of Unicode block objects are available directly in the namespace, or under the `blocks` module.
+
+```py
+# both are equivalent
+>>> from unicode_blocks import BASIC_LATIN
+>>> from unicode_blocks.blocks import BASIC_LATIN
+
+```
+
+Various names are also available in the block:
+
+```py
+>>> from unicode_blocks import BASIC_LATIN
+>>> assert BASIC_LATIN.name == "Basic Latin"  # Official Unicode name as in Blocks.txt
+>>> assert BASIC_LATIN.normalised_name == "BASICLATIN"  # Normalised name under UAX44-LM3
+>>> assert BASIC_LATIN.variable_name == "BASIC_LATIN"  # Variable name in `unicode_blocks.blocks`
+>>> if unicode_major_version >= 6:
+...     assert BASIC_LATIN.aliases == ["ASCII"]  # Official block aliases as in PropertyValueAliases.txt
+
+```
+
+Additional utilities for CJK are specially provided referencing the oxidised version of the module. Selected samples are shown below.
+
+```py
+>>> from unicode_blocks import cjk
+>>> assert cjk.is_cjk('中')
+>>> assert cjk.is_japanese_kana('あ')
+>>> assert cjk.is_korean_hangul('글')
+>>> assert cjk.is_cjk_punctuation('。')
+
+>>> from unicode_blocks import blocks
+>>> assert cjk.is_ideographic_block(blocks.CJK_UNIFIED_IDEOGRAPHS)
+>>> assert cjk.is_cjk_block(blocks.KANGXI_RADICALS)
+>>> assert cjk.is_japanese_block(blocks.KATAKANA_PHONETIC_EXTENSIONS)
+>>> assert cjk.is_korean_block(blocks.HANGUL_COMPATIBILITY_JAMO)
+
+```
+
+> [!WARNING]  
+> Checking `char in unicode_blocks.for_name("is_CJK")` is **NOT** the same as `cjk.is_cjk(char)`!  
+> `unicode_blocks.for_name("is_CJK")` refers to the "CJK" block alias for CJK Unified Ideographs block, while `cjk.is_cjk` checks through (roughly) all Unicode blocks related to CJK including kana, hangul and punctuations.
+
+To check which Unicode version data is used, check against the `__version__` variable in the namespace. (Bug fix release will use `+1` notation)
+
+```sh
+$ python3
+>>> import unicode_blocks
+>>> unicode_blocks.__version__  # doctest: +SKIP
+'17.0.0'
+```
+
+The version will follow the Unicode semver of the data files, optionally followed by additional numbering from this module for bug fixes after a plus sign, i.e. `<Unicode major.minor.patch>(+<additional numbering>)`.
+
+## Update
+
+To update the blocks data from Unicode Character Database, update the `project.version` key in `pyproject.toml` to the Unicode version number, and then run `python3 build_blocks.py`. This will update the `src/unicode_blocks/blocks.py` file, which is automatically generated from UCD data.
+
+Most of these steps should be directly runnable through GitHub Actions.
+
+## Contributing
+
+Contributions are welcome! Please follow these steps:
+
+1.  Clone the repository and install as development mode:
+    ```sh
+    git clone https://github.com/NightFurySL2001/unicode-blocks.git
+    cd unicode-blocks
+    pip install -e .
+    ```
+2.  Create a new branch for your feature or bug fix.
+3.  Work on the feature and run or develop relevant test cases.
+4.  Test the changes by running `pytest`.
+5.  Ensure this README.md is updated with `python -m doctest README.md`.
+6.  Submit a pull request with a clear description of your changes.
+
+## License
+
+This project is licensed under the [MIT License](LICENSE).
+
+## Acknowledgments
+
+-   [Unicode Consortium](https://unicode.org) for maintaining the Unicode standard and providing the Unicode Character Database (UCD). Data modification are done under [Unicode License v3](https://www.unicode.org/license.txt).

unicode_blocks_py-6.1.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+unicode_blocks/__init__.py,sha256=iUzxCYc1FxVX8PowNApt-jSp5hpYtVBtvElZMadV1uY,115
+unicode_blocks/blocks.py,sha256=5j2rqPuG-Ju3sKKP4uAfSqmh_A-tcv9FvLQTqtRMo-U,42566
+unicode_blocks/charNormaliser.py,sha256=lxAhk9Cf5-qK-O1FC89uUw-yZf4jU9PDDWIwWcCv2pU,721
+unicode_blocks/cjk.py,sha256=6Xxz-QXdOGNpz1qBs4zBD2oNK7qlXZHLPp6raXtwhdo,4950
+unicode_blocks/errors.py,sha256=gKvNQMxlpGGOeWcJMwvMMikJPmb0fbqpkYx7pChGpvs,225
+unicode_blocks/globals.py,sha256=pud_WrINy5gXaVcAzTMot14_gaOc6t60SOtu_qo1NrY,1207
+unicode_blocks/unicodeBlock.py,sha256=cwcU4HAJc_Fv9d9KlOJTReyyUR5uhZaR05ywXJvdLw8,3712
+unicode_blocks_py-6.1.0.dist-info/licenses/LICENSE,sha256=hceFGJLSH-s78KSb0ZEsMHuXjDG6IS8FlDxpgOuf06c,1070
+unicode_blocks_py-6.1.0.dist-info/METADATA,sha256=ufucodoQpcIVgfG3Bw2JleLprN8PuxiaUH4xJFTh5w4,7474
+unicode_blocks_py-6.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+unicode_blocks_py-6.1.0.dist-info/top_level.txt,sha256=u-QN9HeyE8pcxDzlh3uuDP4Hb3W4uXMyQHnhDI5fAbw,15
+unicode_blocks_py-6.1.0.dist-info/RECORD,,

unicode_blocks_py-6.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

unicode_blocks_py-6.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright © 2025 NightFurySL2001
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

unicode_blocks_py-6.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+unicode_blocks