def _get_script_required(script,
unicode_version,
noto_phase,
unicode_only=False,
verbose=False):
needed_chars = set()
if script == "Zsye": # Emoji
# TODO: Check emoji coverage
if not unicode_only:
needed_chars = _emoji_pua_set() # legacy PUA for android emoji
elif script == "Zmth": # Math
if not unicode_only:
needed_chars = _math_set()
elif script == "Zsym": # Symbols
if not unicode_only:
needed_chars = _symbol_set()
elif script == "LGC":
needed_chars = (unicode_data.defined_characters(
scr="Latn", version=unicode_version)
| unicode_data.defined_characters(
scr="Grek", version=unicode_version)
| unicode_data.defined_characters(
scr="Cyrl", version=unicode_version))
if not unicode_only:
needed_chars -= _symbol_set()
needed_chars -= _cjk_set()
elif script == "Aran":
if unicode_only:
needed_chars = unicode_data.defined_characters(
scr="Arab", version=unicode_version)
else:
needed_chars = noto_data.urdu_set()
elif script in ["Hans", "Hant", "Jpan", "Kore"]:
needed_chars = _cjk_set()
else:
needed_chars = unicode_data.defined_characters(scr=script,
version=unicode_version)
if not unicode_only:
needed_chars -= _symbol_set()
if not unicode_only:
needed_chars |= noto_data.get_extra_characters_needed(
script, noto_phase)
try:
needed_chars |= set(
opentype_data.SPECIAL_CHARACTERS_NEEDED[script])
except KeyError:
pass
needed_chars -= noto_data.get_characters_not_needed(script, noto_phase)
if not unicode_only:
needed_chars |= {0, 0xD, 0x20}
if verbose:
sys.stderr.write(script + "\n")
needed_chars &= unicode_data.defined_characters(version=unicode_version)
return needed_chars
def _get_script_required(script,
unicode_version,
noto_phase,
unicode_only=False,
verbose=False):
needed_chars = set()
if script == 'Zsye': # Emoji
# TODO: Check emoji coverage
if not unicode_only:
needed_chars = _emoji_pua_set() # legacy PUA for android emoji
elif script == 'Zmth': # Math
if not unicode_only:
needed_chars = _math_set()
elif script == 'Zsym': # Symbols
if not unicode_only:
needed_chars = _symbol_set()
elif script == 'LGC':
needed_chars = (unicode_data.defined_characters(
scr='Latn', version=unicode_version)
| unicode_data.defined_characters(
scr='Grek', version=unicode_version)
| unicode_data.defined_characters(
scr='Cyrl', version=unicode_version))
if not unicode_only:
needed_chars -= _symbol_set()
needed_chars -= _cjk_set()
elif script == "Aran":
if unicode_only:
needed_chars = unicode_data.defined_characters(
scr='Arab', version=unicode_version)
else:
needed_chars = noto_data.urdu_set()
elif script in ['Hans', 'Hant', 'Jpan', 'Kore']:
needed_chars = _cjk_set()
else:
needed_chars = unicode_data.defined_characters(scr=script,
version=unicode_version)
if not unicode_only:
needed_chars -= _symbol_set()
if not unicode_only:
needed_chars |= noto_data.get_extra_characters_needed(
script, noto_phase)
try:
needed_chars |= set(
opentype_data.SPECIAL_CHARACTERS_NEEDED[script])
except KeyError:
pass
needed_chars -= noto_data.get_characters_not_needed(script, noto_phase)
if not unicode_only:
needed_chars |= {0, 0xd, 0x20}
if verbose:
sys.stderr.write(script + '\n')
needed_chars &= unicode_data.defined_characters(version=unicode_version)
return needed_chars
def _get_script_required(
script, unicode_version, noto_phase, unicode_only=False, verbose=False):
needed_chars = set()
if script == 'Zsye': # Emoji
# TODO: Check emoji coverage
if not unicode_only:
needed_chars = _emoji_pua_set() # legacy PUA for android emoji
elif script == 'Zmth': # Math
if not unicode_only:
needed_chars = _math_set()
elif script == 'Zsym': # Symbols
if not unicode_only:
needed_chars = _symbol_set()
elif script == 'LGC':
needed_chars = (
unicode_data.defined_characters(scr='Latn', version=unicode_version)
| unicode_data.defined_characters(scr='Grek', version=unicode_version)
| unicode_data.defined_characters(scr='Cyrl', version=unicode_version))
if not unicode_only:
needed_chars -= _symbol_set()
needed_chars -= _cjk_set()
elif script == "Aran":
if unicode_only:
needed_chars = unicode_data.defined_characters(
scr='Arab', version=unicode_version)
else:
needed_chars = noto_data.urdu_set()
elif script in ['Hans', 'Hant', 'Jpan', 'Kore']:
needed_chars = _cjk_set()
else:
needed_chars = unicode_data.defined_characters(
scr=script, version=unicode_version)
if not unicode_only:
needed_chars -= _symbol_set()
if not unicode_only:
needed_chars |= noto_data.get_extra_characters_needed(script, noto_phase)
try:
needed_chars |= set(opentype_data.SPECIAL_CHARACTERS_NEEDED[script])
except KeyError:
pass
needed_chars -= noto_data.get_characters_not_needed(script, noto_phase)
if not unicode_only:
needed_chars |= set([0, 0xd, 0x20])
if verbose:
print >> sys.stderr, script,
needed_chars &= unicode_data.defined_characters(version=unicode_version)
return needed_chars