def explain_unicode(text):
"""
A utility method that's useful for debugging mysterious Unicode.
It breaks down a string, showing you for each codepoint its number in
hexadecimal, its glyph, its category in the Unicode standard, and its name
in the Unicode standard.
>>> explain_unicode('(╯°□°)╯︵ ┻━┻')
U+0028 ( [Ps] LEFT PARENTHESIS
U+256F ╯ [So] BOX DRAWINGS LIGHT ARC UP AND LEFT
U+00B0 ° [So] DEGREE SIGN
U+25A1 □ [So] WHITE SQUARE
U+00B0 ° [So] DEGREE SIGN
U+0029 ) [Pe] RIGHT PARENTHESIS
U+256F ╯ [So] BOX DRAWINGS LIGHT ARC UP AND LEFT
U+FE35 ︵ [Ps] PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS
U+0020 [Zs] SPACE
U+253B ┻ [So] BOX DRAWINGS HEAVY UP AND HORIZONTAL
U+2501 ━ [So] BOX DRAWINGS HEAVY HORIZONTAL
U+253B ┻ [So] BOX DRAWINGS HEAVY UP AND HORIZONTAL
"""
for char in text:
if is_printable(char):
display = char
else:
display = char.encode('unicode-escape').decode('ascii')
print('U+{code:04X} {display} [{category}] {name}'.format(
display=display_ljust(display, 7),
code=ord(char),
category=unicodedata.category(char),
name=unicodedata.name(char, '<unknown>')))
def explain_unicode(text):
"""
A utility method that's useful for debugging mysterious Unicode.
It breaks down a string, showing you for each codepoint its number in
hexadecimal, its glyph, its category in the Unicode standard, and its name
in the Unicode standard.
>>> explain_unicode('(╯°□°)╯︵ ┻━┻')
U+0028 ( [Ps] LEFT PARENTHESIS
U+256F ╯ [So] BOX DRAWINGS LIGHT ARC UP AND LEFT
U+00B0 ° [So] DEGREE SIGN
U+25A1 □ [So] WHITE SQUARE
U+00B0 ° [So] DEGREE SIGN
U+0029 ) [Pe] RIGHT PARENTHESIS
U+256F ╯ [So] BOX DRAWINGS LIGHT ARC UP AND LEFT
U+FE35 ︵ [Ps] PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS
U+0020 [Zs] SPACE
U+253B ┻ [So] BOX DRAWINGS HEAVY UP AND HORIZONTAL
U+2501 ━ [So] BOX DRAWINGS HEAVY HORIZONTAL
U+253B ┻ [So] BOX DRAWINGS HEAVY UP AND HORIZONTAL
"""
for char in text:
if is_printable(char):
display = char
else:
display = char.encode('unicode-escape').decode('ascii')
print('U+{code:04X} {display} [{category}] {name}'.format(
display=display_ljust(display, 7),
code=ord(char),
category=unicodedata.category(char),
name=unicodedata.name(char, '<unknown>')
))
def TestInput(data):
if len(data) < 1:
return
fdp = atheris.FuzzedDataProvider(data)
ftfy.character_width(chr(fdp.ConsumeIntInRange(1,1114110)))
ftfy.monospaced_width(fdp.ConsumeString(1000))
ftfy.monospaced_width(fdp.ConsumeUnicode(1000))
choice = fdp.ConsumeIntInRange(1,3)
if choice == 1:
ftfy.display_ljust(fdp.ConsumeString(1000),fdp.ConsumeIntInRange(1,2000))
ftfy.display_ljust(fdp.ConsumeUnicode(1000),fdp.ConsumeIntInRange(1,2000))
if choice == 2:
ftfy.display_rjust(fdp.ConsumeString(1000),fdp.ConsumeIntInRange(1,2000))
ftfy.display_rjust(fdp.ConsumeUnicode(1000),fdp.ConsumeIntInRange(1,2000))
if choice == 3:
ftfy.display_center(fdp.ConsumeString(1000),fdp.ConsumeIntInRange(1,2000))
ftfy.display_center(fdp.ConsumeUnicode(1000),fdp.ConsumeIntInRange(1,2000))
fixes.remove_bom(fdp.ConsumeString(1000))
fixes.remove_bom(fdp.ConsumeUnicode(1000))
