1from fontTools import unicodedata 2 3import pytest 4 5 6def test_script(): 7 assert unicodedata.script("a") == "Latn" 8 assert unicodedata.script(chr(0)) == "Zyyy" 9 assert unicodedata.script(chr(0x0378)) == "Zzzz" 10 assert unicodedata.script(chr(0x10FFFF)) == "Zzzz" 11 12 # these were randomly sampled, one character per script 13 assert unicodedata.script(chr(0x1E918)) == 'Adlm' 14 assert unicodedata.script(chr(0x1170D)) == 'Ahom' 15 assert unicodedata.script(chr(0x145A0)) == 'Hluw' 16 assert unicodedata.script(chr(0x0607)) == 'Arab' 17 assert unicodedata.script(chr(0x056C)) == 'Armn' 18 assert unicodedata.script(chr(0x10B27)) == 'Avst' 19 assert unicodedata.script(chr(0x1B41)) == 'Bali' 20 assert unicodedata.script(chr(0x168AD)) == 'Bamu' 21 assert unicodedata.script(chr(0x16ADD)) == 'Bass' 22 assert unicodedata.script(chr(0x1BE5)) == 'Batk' 23 assert unicodedata.script(chr(0x09F3)) == 'Beng' 24 assert unicodedata.script(chr(0x11C5B)) == 'Bhks' 25 assert unicodedata.script(chr(0x3126)) == 'Bopo' 26 assert unicodedata.script(chr(0x1103B)) == 'Brah' 27 assert unicodedata.script(chr(0x2849)) == 'Brai' 28 assert unicodedata.script(chr(0x1A0A)) == 'Bugi' 29 assert unicodedata.script(chr(0x174E)) == 'Buhd' 30 assert unicodedata.script(chr(0x18EE)) == 'Cans' 31 assert unicodedata.script(chr(0x102B7)) == 'Cari' 32 assert unicodedata.script(chr(0x1053D)) == 'Aghb' 33 assert unicodedata.script(chr(0x11123)) == 'Cakm' 34 assert unicodedata.script(chr(0xAA1F)) == 'Cham' 35 assert unicodedata.script(chr(0xAB95)) == 'Cher' 36 assert unicodedata.script(chr(0x1F0C7)) == 'Zyyy' 37 assert unicodedata.script(chr(0x2C85)) == 'Copt' 38 assert unicodedata.script(chr(0x12014)) == 'Xsux' 39 assert unicodedata.script(chr(0x1082E)) == 'Cprt' 40 assert unicodedata.script(chr(0xA686)) == 'Cyrl' 41 assert unicodedata.script(chr(0x10417)) == 'Dsrt' 42 assert unicodedata.script(chr(0x093E)) == 'Deva' 43 assert unicodedata.script(chr(0x1BC4B)) == 'Dupl' 44 assert unicodedata.script(chr(0x1310C)) == 'Egyp' 45 assert unicodedata.script(chr(0x1051C)) == 'Elba' 46 assert unicodedata.script(chr(0x2DA6)) == 'Ethi' 47 assert unicodedata.script(chr(0x10AD)) == 'Geor' 48 assert unicodedata.script(chr(0x2C52)) == 'Glag' 49 assert unicodedata.script(chr(0x10343)) == 'Goth' 50 assert unicodedata.script(chr(0x11371)) == 'Gran' 51 assert unicodedata.script(chr(0x03D0)) == 'Grek' 52 assert unicodedata.script(chr(0x0AAA)) == 'Gujr' 53 assert unicodedata.script(chr(0x0A4C)) == 'Guru' 54 assert unicodedata.script(chr(0x23C9F)) == 'Hani' 55 assert unicodedata.script(chr(0xC259)) == 'Hang' 56 assert unicodedata.script(chr(0x1722)) == 'Hano' 57 assert unicodedata.script(chr(0x108F5)) == 'Hatr' 58 assert unicodedata.script(chr(0x05C2)) == 'Hebr' 59 assert unicodedata.script(chr(0x1B072)) == 'Hira' 60 assert unicodedata.script(chr(0x10847)) == 'Armi' 61 assert unicodedata.script(chr(0x033A)) == 'Zinh' 62 assert unicodedata.script(chr(0x10B66)) == 'Phli' 63 assert unicodedata.script(chr(0x10B4B)) == 'Prti' 64 assert unicodedata.script(chr(0xA98A)) == 'Java' 65 assert unicodedata.script(chr(0x110B2)) == 'Kthi' 66 assert unicodedata.script(chr(0x0CC6)) == 'Knda' 67 assert unicodedata.script(chr(0x3337)) == 'Kana' 68 assert unicodedata.script(chr(0xA915)) == 'Kali' 69 assert unicodedata.script(chr(0x10A2E)) == 'Khar' 70 assert unicodedata.script(chr(0x17AA)) == 'Khmr' 71 assert unicodedata.script(chr(0x11225)) == 'Khoj' 72 assert unicodedata.script(chr(0x112B6)) == 'Sind' 73 assert unicodedata.script(chr(0x0ED7)) == 'Laoo' 74 assert unicodedata.script(chr(0xAB3C)) == 'Latn' 75 assert unicodedata.script(chr(0x1C48)) == 'Lepc' 76 assert unicodedata.script(chr(0x1923)) == 'Limb' 77 assert unicodedata.script(chr(0x1071D)) == 'Lina' 78 assert unicodedata.script(chr(0x100EC)) == 'Linb' 79 assert unicodedata.script(chr(0xA4E9)) == 'Lisu' 80 assert unicodedata.script(chr(0x10284)) == 'Lyci' 81 assert unicodedata.script(chr(0x10926)) == 'Lydi' 82 assert unicodedata.script(chr(0x11161)) == 'Mahj' 83 assert unicodedata.script(chr(0x0D56)) == 'Mlym' 84 assert unicodedata.script(chr(0x0856)) == 'Mand' 85 assert unicodedata.script(chr(0x10AF0)) == 'Mani' 86 assert unicodedata.script(chr(0x11CB0)) == 'Marc' 87 assert unicodedata.script(chr(0x11D28)) == 'Gonm' 88 assert unicodedata.script(chr(0xABDD)) == 'Mtei' 89 assert unicodedata.script(chr(0x1E897)) == 'Mend' 90 assert unicodedata.script(chr(0x109B0)) == 'Merc' 91 assert unicodedata.script(chr(0x10993)) == 'Mero' 92 assert unicodedata.script(chr(0x16F5D)) == 'Plrd' 93 assert unicodedata.script(chr(0x1160B)) == 'Modi' 94 assert unicodedata.script(chr(0x18A8)) == 'Mong' 95 assert unicodedata.script(chr(0x16A48)) == 'Mroo' 96 assert unicodedata.script(chr(0x1128C)) == 'Mult' 97 assert unicodedata.script(chr(0x105B)) == 'Mymr' 98 assert unicodedata.script(chr(0x108AF)) == 'Nbat' 99 assert unicodedata.script(chr(0x19B3)) == 'Talu' 100 assert unicodedata.script(chr(0x1143D)) == 'Newa' 101 assert unicodedata.script(chr(0x07F4)) == 'Nkoo' 102 assert unicodedata.script(chr(0x1B192)) == 'Nshu' 103 assert unicodedata.script(chr(0x169C)) == 'Ogam' 104 assert unicodedata.script(chr(0x1C56)) == 'Olck' 105 assert unicodedata.script(chr(0x10CE9)) == 'Hung' 106 assert unicodedata.script(chr(0x10316)) == 'Ital' 107 assert unicodedata.script(chr(0x10A93)) == 'Narb' 108 assert unicodedata.script(chr(0x1035A)) == 'Perm' 109 assert unicodedata.script(chr(0x103D5)) == 'Xpeo' 110 assert unicodedata.script(chr(0x10A65)) == 'Sarb' 111 assert unicodedata.script(chr(0x10C09)) == 'Orkh' 112 assert unicodedata.script(chr(0x0B60)) == 'Orya' 113 assert unicodedata.script(chr(0x104CF)) == 'Osge' 114 assert unicodedata.script(chr(0x104A8)) == 'Osma' 115 assert unicodedata.script(chr(0x16B12)) == 'Hmng' 116 assert unicodedata.script(chr(0x10879)) == 'Palm' 117 assert unicodedata.script(chr(0x11AF1)) == 'Pauc' 118 assert unicodedata.script(chr(0xA869)) == 'Phag' 119 assert unicodedata.script(chr(0x10909)) == 'Phnx' 120 assert unicodedata.script(chr(0x10B81)) == 'Phlp' 121 assert unicodedata.script(chr(0xA941)) == 'Rjng' 122 assert unicodedata.script(chr(0x16C3)) == 'Runr' 123 assert unicodedata.script(chr(0x0814)) == 'Samr' 124 assert unicodedata.script(chr(0xA88C)) == 'Saur' 125 assert unicodedata.script(chr(0x111C8)) == 'Shrd' 126 assert unicodedata.script(chr(0x1045F)) == 'Shaw' 127 assert unicodedata.script(chr(0x115AD)) == 'Sidd' 128 assert unicodedata.script(chr(0x1D8C0)) == 'Sgnw' 129 assert unicodedata.script(chr(0x0DB9)) == 'Sinh' 130 assert unicodedata.script(chr(0x110F9)) == 'Sora' 131 assert unicodedata.script(chr(0x11A60)) == 'Soyo' 132 assert unicodedata.script(chr(0x1B94)) == 'Sund' 133 assert unicodedata.script(chr(0xA81F)) == 'Sylo' 134 assert unicodedata.script(chr(0x0740)) == 'Syrc' 135 assert unicodedata.script(chr(0x1714)) == 'Tglg' 136 assert unicodedata.script(chr(0x1761)) == 'Tagb' 137 assert unicodedata.script(chr(0x1965)) == 'Tale' 138 assert unicodedata.script(chr(0x1A32)) == 'Lana' 139 assert unicodedata.script(chr(0xAA86)) == 'Tavt' 140 assert unicodedata.script(chr(0x116A5)) == 'Takr' 141 assert unicodedata.script(chr(0x0B8E)) == 'Taml' 142 assert unicodedata.script(chr(0x1754D)) == 'Tang' 143 assert unicodedata.script(chr(0x0C40)) == 'Telu' 144 assert unicodedata.script(chr(0x07A4)) == 'Thaa' 145 assert unicodedata.script(chr(0x0E42)) == 'Thai' 146 assert unicodedata.script(chr(0x0F09)) == 'Tibt' 147 assert unicodedata.script(chr(0x2D3A)) == 'Tfng' 148 assert unicodedata.script(chr(0x114B0)) == 'Tirh' 149 assert unicodedata.script(chr(0x1038B)) == 'Ugar' 150 assert unicodedata.script(chr(0xA585)) == 'Vaii' 151 assert unicodedata.script(chr(0x118CF)) == 'Wara' 152 assert unicodedata.script(chr(0xA066)) == 'Yiii' 153 assert unicodedata.script(chr(0x11A31)) == 'Zanb' 154 155 156def test_script_extension(): 157 assert unicodedata.script_extension("a") == {"Latn"} 158 assert unicodedata.script_extension(chr(0)) == {"Zyyy"} 159 assert unicodedata.script_extension(chr(0x0378)) == {"Zzzz"} 160 assert unicodedata.script_extension(chr(0x10FFFF)) == {"Zzzz"} 161 162 assert unicodedata.script_extension("\u0660") == {'Arab', 'Thaa', 'Yezi'} 163 assert unicodedata.script_extension("\u0964") == { 164 'Beng', 'Deva', 'Dogr', 'Gong', 'Gonm', 'Gran', 'Gujr', 'Guru', 'Knda', 165 'Mahj', 'Mlym', 'Nand', 'Orya', 'Sind', 'Sinh', 'Sylo', 'Takr', 'Taml', 166 'Telu', 'Tirh'} 167 168 169def test_script_name(): 170 assert unicodedata.script_name("Latn") == "Latin" 171 assert unicodedata.script_name("Zyyy") == "Common" 172 assert unicodedata.script_name("Zzzz") == "Unknown" 173 # underscores in long names are replaced by spaces 174 assert unicodedata.script_name("Egyp") == "Egyptian Hieroglyphs" 175 176 with pytest.raises(KeyError): 177 unicodedata.script_name("QQQQ") 178 assert unicodedata.script_name("QQQQ", default="Unknown") 179 180 181def test_script_code(): 182 assert unicodedata.script_code("Latin") == "Latn" 183 assert unicodedata.script_code("Common") == "Zyyy" 184 assert unicodedata.script_code("Unknown") == "Zzzz" 185 # case, whitespace, underscores and hyphens are ignored 186 assert unicodedata.script_code("Egyptian Hieroglyphs") == "Egyp" 187 assert unicodedata.script_code("Egyptian_Hieroglyphs") == "Egyp" 188 assert unicodedata.script_code("egyptianhieroglyphs") == "Egyp" 189 assert unicodedata.script_code("Egyptian-Hieroglyphs") == "Egyp" 190 191 with pytest.raises(KeyError): 192 unicodedata.script_code("Does not exist") 193 assert unicodedata.script_code("Does not exist", default="Zzzz") == "Zzzz" 194 195 196def test_block(): 197 assert unicodedata.block("\x00") == "Basic Latin" 198 assert unicodedata.block("\x7F") == "Basic Latin" 199 assert unicodedata.block("\x80") == "Latin-1 Supplement" 200 assert unicodedata.block("\u1c90") == "Georgian Extended" 201 assert unicodedata.block("\u0870") == "No_Block" 202 203 204def test_ot_tags_from_script(): 205 # simple 206 assert unicodedata.ot_tags_from_script("Latn") == ["latn"] 207 # script mapped to multiple new and old script tags 208 assert unicodedata.ot_tags_from_script("Deva") == ["dev2", "deva"] 209 # exceptions 210 assert unicodedata.ot_tags_from_script("Hira") == ["kana"] 211 # special script codes map to DFLT 212 assert unicodedata.ot_tags_from_script("Zinh") == ["DFLT"] 213 assert unicodedata.ot_tags_from_script("Zyyy") == ["DFLT"] 214 assert unicodedata.ot_tags_from_script("Zzzz") == ["DFLT"] 215 # this is invalid or unknown 216 assert unicodedata.ot_tags_from_script("Aaaa") == ["DFLT"] 217 218 219def test_ot_tag_to_script(): 220 assert unicodedata.ot_tag_to_script("latn") == "Latn" 221 assert unicodedata.ot_tag_to_script("kana") == "Kana" 222 assert unicodedata.ot_tag_to_script("DFLT") == None 223 assert unicodedata.ot_tag_to_script("aaaa") == None 224 assert unicodedata.ot_tag_to_script("beng") == "Beng" 225 assert unicodedata.ot_tag_to_script("bng2") == "Beng" 226 assert unicodedata.ot_tag_to_script("dev2") == "Deva" 227 assert unicodedata.ot_tag_to_script("gjr2") == "Gujr" 228 assert unicodedata.ot_tag_to_script("yi ") == "Yiii" 229 assert unicodedata.ot_tag_to_script("nko ") == "Nkoo" 230 assert unicodedata.ot_tag_to_script("vai ") == "Vaii" 231 assert unicodedata.ot_tag_to_script("lao ") == "Laoo" 232 assert unicodedata.ot_tag_to_script("yi") == "Yiii" 233 234 for invalid_value in ("", " ", "z zz", "zzzzz"): 235 with pytest.raises(ValueError, match="invalid OpenType tag"): 236 unicodedata.ot_tag_to_script(invalid_value) 237 238 239def test_script_horizontal_direction(): 240 assert unicodedata.script_horizontal_direction("Latn") == "LTR" 241 assert unicodedata.script_horizontal_direction("Arab") == "RTL" 242 assert unicodedata.script_horizontal_direction("Thaa") == "RTL" 243 244 with pytest.raises(KeyError): 245 unicodedata.script_horizontal_direction("Azzz") 246 assert unicodedata.script_horizontal_direction("Azzz", 247 default="LTR") == "LTR" 248 249 250if __name__ == "__main__": 251 import sys 252 sys.exit(pytest.main(sys.argv)) 253