def detectScript(txt):
charScript = [script(c) for c in txt]
for i, ch in enumerate(txt):
scr = charScript[i]
if scr in UNKNOWN_SCRIPT:
if i:
scr = charScript[i - 1]
else:
scr = None
cat = category(ch)
if ch in MIRRORED and cat == "Pe":
scr = None
charScript[i] = scr
# Any unknowns should be mapped to the _next_ script
prev = None
for i in range(len(txt) - 1, -1, -1):
if charScript[i] is None:
charScript[i] = prev
else:
prev = charScript[i]
# There may be unknowns at the end of the string, fall back to
# preceding script
prev = "Zxxx" # last resort
for i in range(len(txt)):
if charScript[i] is None:
charScript[i] = prev
else:
prev = charScript[i]
assert None not in charScript
return charScript
def unicodeScriptDirection(uv):
sc = unicodedata.script(chr(uv))
if sc in DFLT_SCRIPTS:
return None
return unicodedata.script_horizontal_direction(sc)
def test_script():
assert unicodedata.script("a") == "Latn"
assert unicodedata.script(unichr(0)) == "Zyyy"
assert unicodedata.script(unichr(0x0378)) == "Zzzz"
assert unicodedata.script(unichr(0x10FFFF)) == "Zzzz"
# these were randomly sampled, one character per script
assert unicodedata.script(unichr(0x1E918)) == 'Adlm'
assert unicodedata.script(unichr(0x1170D)) == 'Ahom'
assert unicodedata.script(unichr(0x145A0)) == 'Hluw'
assert unicodedata.script(unichr(0x0607)) == 'Arab'
assert unicodedata.script(unichr(0x056C)) == 'Armn'
assert unicodedata.script(unichr(0x10B27)) == 'Avst'
assert unicodedata.script(unichr(0x1B41)) == 'Bali'
assert unicodedata.script(unichr(0x168AD)) == 'Bamu'
assert unicodedata.script(unichr(0x16ADD)) == 'Bass'
assert unicodedata.script(unichr(0x1BE5)) == 'Batk'
assert unicodedata.script(unichr(0x09F3)) == 'Beng'
assert unicodedata.script(unichr(0x11C5B)) == 'Bhks'
assert unicodedata.script(unichr(0x3126)) == 'Bopo'
assert unicodedata.script(unichr(0x1103B)) == 'Brah'
assert unicodedata.script(unichr(0x2849)) == 'Brai'
assert unicodedata.script(unichr(0x1A0A)) == 'Bugi'
assert unicodedata.script(unichr(0x174E)) == 'Buhd'
assert unicodedata.script(unichr(0x18EE)) == 'Cans'
assert unicodedata.script(unichr(0x102B7)) == 'Cari'
assert unicodedata.script(unichr(0x1053D)) == 'Aghb'
assert unicodedata.script(unichr(0x11123)) == 'Cakm'
assert unicodedata.script(unichr(0xAA1F)) == 'Cham'
assert unicodedata.script(unichr(0xAB95)) == 'Cher'
assert unicodedata.script(unichr(0x1F0C7)) == 'Zyyy'
assert unicodedata.script(unichr(0x2C85)) == 'Copt'
assert unicodedata.script(unichr(0x12014)) == 'Xsux'
assert unicodedata.script(unichr(0x1082E)) == 'Cprt'
assert unicodedata.script(unichr(0xA686)) == 'Cyrl'
assert unicodedata.script(unichr(0x10417)) == 'Dsrt'
assert unicodedata.script(unichr(0x093E)) == 'Deva'
assert unicodedata.script(unichr(0x1BC4B)) == 'Dupl'
assert unicodedata.script(unichr(0x1310C)) == 'Egyp'
assert unicodedata.script(unichr(0x1051C)) == 'Elba'
assert unicodedata.script(unichr(0x2DA6)) == 'Ethi'
assert unicodedata.script(unichr(0x10AD)) == 'Geor'
assert unicodedata.script(unichr(0x2C52)) == 'Glag'
assert unicodedata.script(unichr(0x10343)) == 'Goth'
assert unicodedata.script(unichr(0x11371)) == 'Gran'
assert unicodedata.script(unichr(0x03D0)) == 'Grek'
assert unicodedata.script(unichr(0x0AAA)) == 'Gujr'
assert unicodedata.script(unichr(0x0A4C)) == 'Guru'
assert unicodedata.script(unichr(0x23C9F)) == 'Hani'
assert unicodedata.script(unichr(0xC259)) == 'Hang'
assert unicodedata.script(unichr(0x1722)) == 'Hano'
assert unicodedata.script(unichr(0x108F5)) == 'Hatr'
assert unicodedata.script(unichr(0x05C2)) == 'Hebr'
assert unicodedata.script(unichr(0x1B072)) == 'Hira'
assert unicodedata.script(unichr(0x10847)) == 'Armi'
assert unicodedata.script(unichr(0x033A)) == 'Zinh'
assert unicodedata.script(unichr(0x10B66)) == 'Phli'
assert unicodedata.script(unichr(0x10B4B)) == 'Prti'
assert unicodedata.script(unichr(0xA98A)) == 'Java'
assert unicodedata.script(unichr(0x110B2)) == 'Kthi'
assert unicodedata.script(unichr(0x0CC6)) == 'Knda'
assert unicodedata.script(unichr(0x3337)) == 'Kana'
assert unicodedata.script(unichr(0xA915)) == 'Kali'
assert unicodedata.script(unichr(0x10A2E)) == 'Khar'
assert unicodedata.script(unichr(0x17AA)) == 'Khmr'
assert unicodedata.script(unichr(0x11225)) == 'Khoj'
assert unicodedata.script(unichr(0x112B6)) == 'Sind'
assert unicodedata.script(unichr(0x0ED7)) == 'Laoo'
assert unicodedata.script(unichr(0xAB3C)) == 'Latn'
assert unicodedata.script(unichr(0x1C48)) == 'Lepc'
assert unicodedata.script(unichr(0x1923)) == 'Limb'
assert unicodedata.script(unichr(0x1071D)) == 'Lina'
assert unicodedata.script(unichr(0x100EC)) == 'Linb'
assert unicodedata.script(unichr(0xA4E9)) == 'Lisu'
assert unicodedata.script(unichr(0x10284)) == 'Lyci'
assert unicodedata.script(unichr(0x10926)) == 'Lydi'
assert unicodedata.script(unichr(0x11161)) == 'Mahj'
assert unicodedata.script(unichr(0x0D56)) == 'Mlym'
assert unicodedata.script(unichr(0x0856)) == 'Mand'
assert unicodedata.script(unichr(0x10AF0)) == 'Mani'
assert unicodedata.script(unichr(0x11CB0)) == 'Marc'
assert unicodedata.script(unichr(0x11D28)) == 'Gonm'
assert unicodedata.script(unichr(0xABDD)) == 'Mtei'
assert unicodedata.script(unichr(0x1E897)) == 'Mend'
assert unicodedata.script(unichr(0x109B0)) == 'Merc'
assert unicodedata.script(unichr(0x10993)) == 'Mero'
assert unicodedata.script(unichr(0x16F5D)) == 'Plrd'
assert unicodedata.script(unichr(0x1160B)) == 'Modi'
assert unicodedata.script(unichr(0x18A8)) == 'Mong'
assert unicodedata.script(unichr(0x16A48)) == 'Mroo'
assert unicodedata.script(unichr(0x1128C)) == 'Mult'
assert unicodedata.script(unichr(0x105B)) == 'Mymr'
assert unicodedata.script(unichr(0x108AF)) == 'Nbat'
assert unicodedata.script(unichr(0x19B3)) == 'Talu'
assert unicodedata.script(unichr(0x1143D)) == 'Newa'
assert unicodedata.script(unichr(0x07F4)) == 'Nkoo'
assert unicodedata.script(unichr(0x1B192)) == 'Nshu'
assert unicodedata.script(unichr(0x169C)) == 'Ogam'
assert unicodedata.script(unichr(0x1C56)) == 'Olck'
assert unicodedata.script(unichr(0x10CE9)) == 'Hung'
assert unicodedata.script(unichr(0x10316)) == 'Ital'
assert unicodedata.script(unichr(0x10A93)) == 'Narb'
assert unicodedata.script(unichr(0x1035A)) == 'Perm'
assert unicodedata.script(unichr(0x103D5)) == 'Xpeo'
assert unicodedata.script(unichr(0x10A65)) == 'Sarb'
assert unicodedata.script(unichr(0x10C09)) == 'Orkh'
assert unicodedata.script(unichr(0x0B60)) == 'Orya'
assert unicodedata.script(unichr(0x104CF)) == 'Osge'
assert unicodedata.script(unichr(0x104A8)) == 'Osma'
assert unicodedata.script(unichr(0x16B12)) == 'Hmng'
assert unicodedata.script(unichr(0x10879)) == 'Palm'
assert unicodedata.script(unichr(0x11AF1)) == 'Pauc'
assert unicodedata.script(unichr(0xA869)) == 'Phag'
assert unicodedata.script(unichr(0x10909)) == 'Phnx'
assert unicodedata.script(unichr(0x10B81)) == 'Phlp'
assert unicodedata.script(unichr(0xA941)) == 'Rjng'
assert unicodedata.script(unichr(0x16C3)) == 'Runr'
assert unicodedata.script(unichr(0x0814)) == 'Samr'
assert unicodedata.script(unichr(0xA88C)) == 'Saur'
assert unicodedata.script(unichr(0x111C8)) == 'Shrd'
assert unicodedata.script(unichr(0x1045F)) == 'Shaw'
assert unicodedata.script(unichr(0x115AD)) == 'Sidd'
assert unicodedata.script(unichr(0x1D8C0)) == 'Sgnw'
assert unicodedata.script(unichr(0x0DB9)) == 'Sinh'
assert unicodedata.script(unichr(0x110F9)) == 'Sora'
assert unicodedata.script(unichr(0x11A60)) == 'Soyo'
assert unicodedata.script(unichr(0x1B94)) == 'Sund'
assert unicodedata.script(unichr(0xA81F)) == 'Sylo'
assert unicodedata.script(unichr(0x0740)) == 'Syrc'
assert unicodedata.script(unichr(0x1714)) == 'Tglg'
assert unicodedata.script(unichr(0x1761)) == 'Tagb'
assert unicodedata.script(unichr(0x1965)) == 'Tale'
assert unicodedata.script(unichr(0x1A32)) == 'Lana'
assert unicodedata.script(unichr(0xAA86)) == 'Tavt'
assert unicodedata.script(unichr(0x116A5)) == 'Takr'
assert unicodedata.script(unichr(0x0B8E)) == 'Taml'
assert unicodedata.script(unichr(0x1754D)) == 'Tang'
assert unicodedata.script(unichr(0x0C40)) == 'Telu'
assert unicodedata.script(unichr(0x07A4)) == 'Thaa'
assert unicodedata.script(unichr(0x0E42)) == 'Thai'
assert unicodedata.script(unichr(0x0F09)) == 'Tibt'
assert unicodedata.script(unichr(0x2D3A)) == 'Tfng'
assert unicodedata.script(unichr(0x114B0)) == 'Tirh'
assert unicodedata.script(unichr(0x1038B)) == 'Ugar'
assert unicodedata.script(unichr(0xA585)) == 'Vaii'
assert unicodedata.script(unichr(0x118CF)) == 'Wara'
assert unicodedata.script(unichr(0xA066)) == 'Yiii'
assert unicodedata.script(unichr(0x11A31)) == 'Zanb'
def test_script():
assert unicodedata.script("a") == "Latn"
assert unicodedata.script(unichr(0)) == "Zyyy"
assert unicodedata.script(unichr(0x0378)) == "Zzzz"
assert unicodedata.script(unichr(0x10FFFF)) == "Zzzz"
# these were randomly sampled, one character per script
assert unicodedata.script(unichr(0x1E918)) == 'Adlm'
assert unicodedata.script(unichr(0x1170D)) == 'Ahom'
assert unicodedata.script(unichr(0x145A0)) == 'Hluw'
assert unicodedata.script(unichr(0x0607)) == 'Arab'
assert unicodedata.script(unichr(0x056C)) == 'Armn'
assert unicodedata.script(unichr(0x10B27)) == 'Avst'
assert unicodedata.script(unichr(0x1B41)) == 'Bali'
assert unicodedata.script(unichr(0x168AD)) == 'Bamu'
assert unicodedata.script(unichr(0x16ADD)) == 'Bass'
assert unicodedata.script(unichr(0x1BE5)) == 'Batk'
assert unicodedata.script(unichr(0x09F3)) == 'Beng'
assert unicodedata.script(unichr(0x11C5B)) == 'Bhks'
assert unicodedata.script(unichr(0x3126)) == 'Bopo'
assert unicodedata.script(unichr(0x1103B)) == 'Brah'
assert unicodedata.script(unichr(0x2849)) == 'Brai'
assert unicodedata.script(unichr(0x1A0A)) == 'Bugi'
assert unicodedata.script(unichr(0x174E)) == 'Buhd'
assert unicodedata.script(unichr(0x18EE)) == 'Cans'
assert unicodedata.script(unichr(0x102B7)) == 'Cari'
assert unicodedata.script(unichr(0x1053D)) == 'Aghb'
assert unicodedata.script(unichr(0x11123)) == 'Cakm'
assert unicodedata.script(unichr(0xAA1F)) == 'Cham'
assert unicodedata.script(unichr(0xAB95)) == 'Cher'
assert unicodedata.script(unichr(0x1F0C7)) == 'Zyyy'
assert unicodedata.script(unichr(0x2C85)) == 'Copt'
assert unicodedata.script(unichr(0x12014)) == 'Xsux'
assert unicodedata.script(unichr(0x1082E)) == 'Cprt'
assert unicodedata.script(unichr(0xA686)) == 'Cyrl'
assert unicodedata.script(unichr(0x10417)) == 'Dsrt'
assert unicodedata.script(unichr(0x093E)) == 'Deva'
assert unicodedata.script(unichr(0x1BC4B)) == 'Dupl'
assert unicodedata.script(unichr(0x1310C)) == 'Egyp'
assert unicodedata.script(unichr(0x1051C)) == 'Elba'
assert unicodedata.script(unichr(0x2DA6)) == 'Ethi'
assert unicodedata.script(unichr(0x10AD)) == 'Geor'
assert unicodedata.script(unichr(0x2C52)) == 'Glag'
assert unicodedata.script(unichr(0x10343)) == 'Goth'
assert unicodedata.script(unichr(0x11371)) == 'Gran'
assert unicodedata.script(unichr(0x03D0)) == 'Grek'
assert unicodedata.script(unichr(0x0AAA)) == 'Gujr'
assert unicodedata.script(unichr(0x0A4C)) == 'Guru'
assert unicodedata.script(unichr(0x23C9F)) == 'Hani'
assert unicodedata.script(unichr(0xC259)) == 'Hang'
assert unicodedata.script(unichr(0x1722)) == 'Hano'
assert unicodedata.script(unichr(0x108F5)) == 'Hatr'
assert unicodedata.script(unichr(0x05C2)) == 'Hebr'
assert unicodedata.script(unichr(0x1B072)) == 'Hira'
assert unicodedata.script(unichr(0x10847)) == 'Armi'
assert unicodedata.script(unichr(0x033A)) == 'Zinh'
assert unicodedata.script(unichr(0x10B66)) == 'Phli'
assert unicodedata.script(unichr(0x10B4B)) == 'Prti'
assert unicodedata.script(unichr(0xA98A)) == 'Java'
assert unicodedata.script(unichr(0x110B2)) == 'Kthi'
assert unicodedata.script(unichr(0x0CC6)) == 'Knda'
assert unicodedata.script(unichr(0x3337)) == 'Kana'
assert unicodedata.script(unichr(0xA915)) == 'Kali'
assert unicodedata.script(unichr(0x10A2E)) == 'Khar'
assert unicodedata.script(unichr(0x17AA)) == 'Khmr'
assert unicodedata.script(unichr(0x11225)) == 'Khoj'
assert unicodedata.script(unichr(0x112B6)) == 'Sind'
assert unicodedata.script(unichr(0x0ED7)) == 'Laoo'
assert unicodedata.script(unichr(0xAB3C)) == 'Latn'
assert unicodedata.script(unichr(0x1C48)) == 'Lepc'
assert unicodedata.script(unichr(0x1923)) == 'Limb'
assert unicodedata.script(unichr(0x1071D)) == 'Lina'
assert unicodedata.script(unichr(0x100EC)) == 'Linb'
assert unicodedata.script(unichr(0xA4E9)) == 'Lisu'
assert unicodedata.script(unichr(0x10284)) == 'Lyci'
assert unicodedata.script(unichr(0x10926)) == 'Lydi'
assert unicodedata.script(unichr(0x11161)) == 'Mahj'
assert unicodedata.script(unichr(0x0D56)) == 'Mlym'
assert unicodedata.script(unichr(0x0856)) == 'Mand'
assert unicodedata.script(unichr(0x10AF0)) == 'Mani'
assert unicodedata.script(unichr(0x11CB0)) == 'Marc'
assert unicodedata.script(unichr(0x11D28)) == 'Gonm'
assert unicodedata.script(unichr(0xABDD)) == 'Mtei'
assert unicodedata.script(unichr(0x1E897)) == 'Mend'
assert unicodedata.script(unichr(0x109B0)) == 'Merc'
assert unicodedata.script(unichr(0x10993)) == 'Mero'
assert unicodedata.script(unichr(0x16F5D)) == 'Plrd'
assert unicodedata.script(unichr(0x1160B)) == 'Modi'
assert unicodedata.script(unichr(0x18A8)) == 'Mong'
assert unicodedata.script(unichr(0x16A48)) == 'Mroo'
assert unicodedata.script(unichr(0x1128C)) == 'Mult'
assert unicodedata.script(unichr(0x105B)) == 'Mymr'
assert unicodedata.script(unichr(0x108AF)) == 'Nbat'
assert unicodedata.script(unichr(0x19B3)) == 'Talu'
assert unicodedata.script(unichr(0x1143D)) == 'Newa'
assert unicodedata.script(unichr(0x07F4)) == 'Nkoo'
assert unicodedata.script(unichr(0x1B192)) == 'Nshu'
assert unicodedata.script(unichr(0x169C)) == 'Ogam'
assert unicodedata.script(unichr(0x1C56)) == 'Olck'
assert unicodedata.script(unichr(0x10CE9)) == 'Hung'
assert unicodedata.script(unichr(0x10316)) == 'Ital'
assert unicodedata.script(unichr(0x10A93)) == 'Narb'
assert unicodedata.script(unichr(0x1035A)) == 'Perm'
assert unicodedata.script(unichr(0x103D5)) == 'Xpeo'
assert unicodedata.script(unichr(0x10A65)) == 'Sarb'
assert unicodedata.script(unichr(0x10C09)) == 'Orkh'
assert unicodedata.script(unichr(0x0B60)) == 'Orya'
assert unicodedata.script(unichr(0x104CF)) == 'Osge'
assert unicodedata.script(unichr(0x104A8)) == 'Osma'
assert unicodedata.script(unichr(0x16B12)) == 'Hmng'
assert unicodedata.script(unichr(0x10879)) == 'Palm'
assert unicodedata.script(unichr(0x11AF1)) == 'Pauc'
assert unicodedata.script(unichr(0xA869)) == 'Phag'
assert unicodedata.script(unichr(0x10909)) == 'Phnx'
assert unicodedata.script(unichr(0x10B81)) == 'Phlp'
assert unicodedata.script(unichr(0xA941)) == 'Rjng'
assert unicodedata.script(unichr(0x16C3)) == 'Runr'
assert unicodedata.script(unichr(0x0814)) == 'Samr'
assert unicodedata.script(unichr(0xA88C)) == 'Saur'
assert unicodedata.script(unichr(0x111C8)) == 'Shrd'
assert unicodedata.script(unichr(0x1045F)) == 'Shaw'
assert unicodedata.script(unichr(0x115AD)) == 'Sidd'
assert unicodedata.script(unichr(0x1D8C0)) == 'Sgnw'
assert unicodedata.script(unichr(0x0DB9)) == 'Sinh'
assert unicodedata.script(unichr(0x110F9)) == 'Sora'
assert unicodedata.script(unichr(0x11A60)) == 'Soyo'
assert unicodedata.script(unichr(0x1B94)) == 'Sund'
assert unicodedata.script(unichr(0xA81F)) == 'Sylo'
assert unicodedata.script(unichr(0x0740)) == 'Syrc'
assert unicodedata.script(unichr(0x1714)) == 'Tglg'
assert unicodedata.script(unichr(0x1761)) == 'Tagb'
assert unicodedata.script(unichr(0x1965)) == 'Tale'
assert unicodedata.script(unichr(0x1A32)) == 'Lana'
assert unicodedata.script(unichr(0xAA86)) == 'Tavt'
assert unicodedata.script(unichr(0x116A5)) == 'Takr'
assert unicodedata.script(unichr(0x0B8E)) == 'Taml'
assert unicodedata.script(unichr(0x1754D)) == 'Tang'
assert unicodedata.script(unichr(0x0C40)) == 'Telu'
assert unicodedata.script(unichr(0x07A4)) == 'Thaa'
assert unicodedata.script(unichr(0x0E42)) == 'Thai'
assert unicodedata.script(unichr(0x0F09)) == 'Tibt'
assert unicodedata.script(unichr(0x2D3A)) == 'Tfng'
assert unicodedata.script(unichr(0x114B0)) == 'Tirh'
assert unicodedata.script(unichr(0x1038B)) == 'Ugar'
assert unicodedata.script(unichr(0xA585)) == 'Vaii'
assert unicodedata.script(unichr(0x118CF)) == 'Wara'
assert unicodedata.script(unichr(0xA066)) == 'Yiii'
assert unicodedata.script(unichr(0x11A31)) == 'Zanb'
def script(value):
char = chr(value)
return unicodedata.script_name(unicodedata.script(char), default="Unknown")
cps_to_value = dict[range, str]()
for line in path.read_text().splitlines():
if not (content := line.partition("#")[0].strip()):
continue
field_0, value = [i.strip() for i in content.split(";")]
start, _, stop = field_0.partition("..")
cps_to_value[range(int(start, 16), int(stop or start, 16) + 1)] = value
script_to_value_to_cps = dict[str, dict[str, list[int]]]()
for cp, value in sorted(
(i, v) for k, v in cps_to_value.items() for i in k):
value_to_cps = script_to_value_to_cps.setdefault(
unicodedata.script_name(unicodedata.script(chr(cp))), {})
value_to_cps.setdefault(value, list()).append(cp)
# yaml.add_representer(
# int,
# lambda dumper, data: dumper.represent_scalar("tag:yaml.org,2002:int", f"0x{data:04X}"),
# )
path = directory / "tests" / (property_name + ".yaml")
with path.open("w") as f:
yaml.dump(
{
k: {
value: [{
i: unicodedata.name(chr(i))
} for i in cps]
for value, cps in v.items()
],
stdin=subprocess.PIPE)
process.communicate(
json.dumps(font, ensure_ascii=False, separators=(',', ':')).encode())
baseName = sys.argv[1]
scaleZh = int(sys.argv[2])
scaleEn = int(sys.argv[3])
font = ReadFont("src/font/{}.otf".format(baseName))
del font['GSUB']
del font['GPOS']
del font['GDEF']
Gc(font)
scriptMap = {}
for cp, name in font['cmap'].items():
cp = int(cp)
isZh = script(chr(cp)) == "Hani"
scriptMap[name] = scriptMap.get(name) or isZh
for name, glyph in font['glyf'].items():
if not scriptMap.get(name):
Transform(glyph, scaleEn / scaleZh, 0, 0, scaleEn / scaleZh, 0, 0,
True)
WriteFont(font,
"build/{}.otf".format(ResolveFileName(baseName, scaleZh, scaleEn)))
