def checkJapanese(name):
asciiSpace = range(32, 33)
asciiDigits = range(48, 64)
hiragana = range(12353, 12448)
katakana = range(12449, 12544)
halfwidthKatakana = range(65381, 65440)
halfwidthCharacter = set(asciiSpace + halfwidthKatakana)
allowedUtf8 = set(asciiSpace + hiragana + katakana + halfwidthKatakana)
te = TextEncoder()
dc = 0.0
for char in (ord(char) for char in te.decodeText(name)):
if char not in allowedUtf8:
if char in asciiDigits:
notify.info('name contains not allowed ascii digits')
return OTPLocalizer.NCNoDigits
else:
notify.info('name contains not allowed utf8 char: 0x%04x' %
char)
return OTPLocalizer.NCBadCharacter % te.encodeWtext(
unichr(char))
elif char in halfwidthCharacter:
dc += 0.5
else:
dc += 1
if dc < 2:
notify.info('name is too short: %0.1f' % dc)
return OTPLocalizer.NCTooShort
elif dc > 8:
notify.info(
'name has been occupied more than eight display cells: %0.1f' %
dc)
return OTPLocalizer.NCGeneric
def checkJapanese(name):
asciiSpace = range(32, 33)
asciiDigits = range(48, 64)
hiragana = range(12353, 12448)
katakana = range(12449, 12544)
halfwidthKatakana = range(65381, 65440)
halfwidthCharacter = set(asciiSpace + halfwidthKatakana)
allowedUtf8 = set(asciiSpace + hiragana + katakana + halfwidthKatakana)
te = TextEncoder()
dc = 0.0
for char in (ord(char) for char in te.decodeText(name)):
if char not in allowedUtf8:
if char in asciiDigits:
notify.info('name contains not allowed ascii digits')
return OTPLocalizer.NCNoDigits
else:
notify.info('name contains not allowed utf8 char: 0x%04x' % char)
return OTPLocalizer.NCBadCharacter % te.encodeWtext(unichr(char))
elif char in halfwidthCharacter:
dc += 0.5
else:
dc += 1
if dc < 2:
notify.info('name is too short: %0.1f' % dc)
return OTPLocalizer.NCTooShort
elif dc > 8:
notify.info('name has been occupied more than eight display cells: %0.1f' % dc)
return OTPLocalizer.NCGeneric
def checkJapanese(name):
# Japan allows ASCII space, hiragana, katakana, and half-width katakana,
# but, allows not ASCII and kanji(CJK) characters for a name
# All Japanese characters are three-byte-encoded utf-8 characters from unicode
# Reference: http://unicode.org/charts/
asciiSpace = range(0x20, 0x21)
asciiDigits = range(0x30, 0x40)
hiragana = range(0x3041, 0x30A0)
katakana = range(0x30A1, 0x3100)
halfwidthKatakana = range(0xFF65, 0xFFA0)
halfwidthCharacter = set(asciiSpace + halfwidthKatakana)
allowedUtf8 = set(asciiSpace + hiragana + katakana + halfwidthKatakana)
te = TextEncoder()
dc = 0.0
# Return None if name is OK, error string if name is not OK
for char in (ord(char) for char in te.decodeText(name)):
if char not in allowedUtf8:
# Notify error string, if not allowed utf-8 character
if char in asciiDigits:
notify.info('name contains not allowed ascii digits')
return OTPLocalizer.NCNoDigits
else:
notify.info('name contains not allowed utf8 char: 0x%04x' %
char)
return OTPLocalizer.NCBadCharacter % te.encodeWtext(
unichr(char))
else:
# Restrict the number of characters, if three-byte-encoded utf-8 character
# The full-width characters would fit into a single display cell,
# and the half-width characters would fit two to a display cell
if char in halfwidthCharacter:
dc += 0.5
else:
dc += 1
# Japan restricts the number of the characters, if occupied less then two display cell
# and more then eight display cell.
if (dc < 2):
notify.info('name is too short: %0.1f' % dc)
return OTPLocalizer.NCTooShort
elif (dc > 8):
notify.info(
'name has been occupied more than eight display cells: %0.1f' %
dc)
return OTPLocalizer.NCGeneric
