def remove_control_and_redundant_space(s: str) -> str:
"""Substitute multiple concatenated control and space characters into single whitespace."""
res = ''
for ch in s:
# Convert Unicode control and space characters into simple whitespaces
ss = ch if not stringprep.in_table_c11_c12(
ch) and not stringprep.in_table_c21_c22(ch) else ' '
res += ss
# Remove redundant spaces
return ' '.join(res.split())
def _process(self, value):
for code in force_text(value):
# TODO: Is this long enough?
if stringprep.in_table_c12(code) or stringprep.in_table_c21_c22(code) or \
stringprep.in_table_c3(code) or stringprep.in_table_c4(code) or \
stringprep.in_table_c5(code) or stringprep.in_table_c6(code) or \
stringprep.in_table_c7(code) or stringprep.in_table_c8(code) or \
stringprep.in_table_c9(code):
self.invalid = False
if stringprep.in_table_d1(code):
self.r_and_al_cat = True
if stringprep.in_table_d2(code):
self.l_cat = True
def _process(self, value):
for code in force_text(value):
# TODO: Is this long enough?
if stringprep.in_table_c12(code) or stringprep.in_table_c21_c22(code) or \
stringprep.in_table_c3(code) or stringprep.in_table_c4(code) or \
stringprep.in_table_c5(code) or stringprep.in_table_c6(code) or \
stringprep.in_table_c7(code) or stringprep.in_table_c8(code) or \
stringprep.in_table_c9(code):
self.invalid = False
if stringprep.in_table_d1(code):
self.r_and_al_cat = True
if stringprep.in_table_d2(code):
self.l_cat = True
def resource_validator(name):
"""Check the *name* of a resource for some really bad characters that shouldn't be used
anywhere in RestAuth.
This filters names containing a slash ("/") or colon (":") and those starting with '.'. It also
filters control characters etc., including those from unicode.
.. deprecated:: 0.7.0
This method is deprecated in favour of the RestAuthCommon.strprep. This method will be
removed in 0.7.1.
:param str name: The name to validate
:returns: False if the name contains any invalid characters, True otherwise.
:rtype: bool
"""
warnings.warn(
'This method is deprecated, use RestAuthCommon.strprep.stringcheck() instead.',
DeprecationWarning)
if PY2 and isinstance(name, str): # pragma: py2
name = name.decode('utf-8')
# filter various dangerous characters
for enc_char in name:
if stringprep.in_table_c12(
enc_char): # C.1.2 Non-ASCII space characters
return False
if stringprep.in_table_c21_c22(enc_char): # C.2 Control characters
return False
if stringprep.in_table_c3(enc_char): # C.3 Private use
return False
if stringprep.in_table_c4(enc_char): # C.4 Non-character code points
return False
if stringprep.in_table_c5(enc_char): # C.5 Surrogate codes
return False
if stringprep.in_table_c6(
enc_char): # C.6 Inappropriate for plain text
return False
if stringprep.in_table_c7(
enc_char): # C.7 Inappropriate for canonical representation
return False
if stringprep.in_table_c8(
enc_char): # C.8 Change display properties or are deprecated
return False
if stringprep.in_table_c9(enc_char): # C.9 Tagging characters
return False
return True
def canonicaliseUsername(username, ignoreSpaces = False, throws = True):
# Read stringprep documentation for the meaning of the tables
chars = list(username)
for c, char in enumerate(chars):
if stringprep.in_table_a1(char):
if throws:
raise ValueError
else:
chars[c] = u""
elif stringprep.in_table_b1(char):
chars[c] = u""
else:
chars[c] = stringprep.map_table_b2(char)
chars = list(stringprep.unicodedata.normalize("NFKC", u"".join(chars)))
for c, char in enumerate(chars):
if ((not ignoreSpaces and stringprep.in_table_c11_c12(char)) or
stringprep.in_table_c21_c22(char) or
stringprep.in_table_c3(char) or
stringprep.in_table_c4(char) or
stringprep.in_table_c5(char) or
stringprep.in_table_c6(char) or
stringprep.in_table_c7(char) or
stringprep.in_table_c8(char) or
stringprep.in_table_c9(char) or
stringprep.unicodedata.category(char) in ("Ps", "Pe", "Pi", "Pf", "Po")):
if throws:
raise ValueError
else:
chars[c] = u""
chars = u"".join(chars)
if throws:
RandAL = map(stringprep.in_table_d1, chars)
for c in RandAL:
if c:
if filter(stringprep.in_table_d2, chars):
raise ValueError
if not RandAL[0] or not RandAL[-1]:
raise ValueError
return chars
def sals_stringprep(string):
"""
TODO: implements bidirectional checks https://tools.ietf.org/html/rfc3454#section-6
"""
new_string = []
for x in string:
if stringprep.in_table_c12(x):
new_string.append(' ')
elif stringprep.in_table_b1(x):
continue
elif stringprep.in_table_c12(x) or stringprep.in_table_c21_c22(x) or stringprep.in_table_c3(x)\
or stringprep.in_table_c4(x) or stringprep.in_table_c5(x) or stringprep.in_table_c6(x)\
or stringprep.in_table_c7(x) or stringprep.in_table_c8(x) or stringprep.in_table_c9(x):
raise PDFGenericError("Invalid input character in password.")
else:
new_string.append(x)
return unicodedata.normalize('NFKC', "".join(c for c in new_string))
def resource_validator(name):
"""Check the *name* of a resource for some really bad characters that shouldn't be used
anywhere in RestAuth.
This filters names containing a slash ("/") or colon (":") and those starting with '.'. It also
filters control characters etc., including those from unicode.
.. deprecated:: 0.7.0
This method is deprecated in favour of the RestAuthCommon.strprep. This method will be
removed in 0.7.1.
:param str name: The name to validate
:returns: False if the name contains any invalid characters, True otherwise.
:rtype: bool
"""
warnings.warn('This method is deprecated, use RestAuthCommon.strprep.stringcheck() instead.',
DeprecationWarning)
if PY2 and isinstance(name, str): # pragma: py2
name = name.decode('utf-8')
# filter various dangerous characters
for enc_char in name:
if stringprep.in_table_c12(enc_char): # C.1.2 Non-ASCII space characters
return False
if stringprep.in_table_c21_c22(enc_char): # C.2 Control characters
return False
if stringprep.in_table_c3(enc_char): # C.3 Private use
return False
if stringprep.in_table_c4(enc_char): # C.4 Non-character code points
return False
if stringprep.in_table_c5(enc_char): # C.5 Surrogate codes
return False
if stringprep.in_table_c6(enc_char): # C.6 Inappropriate for plain text
return False
if stringprep.in_table_c7(enc_char): # C.7 Inappropriate for canonical representation
return False
if stringprep.in_table_c8(enc_char): # C.8 Change display properties or are deprecated
return False
if stringprep.in_table_c9(enc_char): # C.9 Tagging characters
return False
return True
def prohibited_output_profile(string):
"""RFC4013 Prohibited output profile implementation."""
# Implements:
# RFC4013, 2.3. Prohibited Output.
# This profile specifies the following characters as prohibited input:
# - Non-ASCII space characters [StringPrep, C.1.2]
# - ASCII control characters [StringPrep, C.2.1]
# - Non-ASCII control characters [StringPrep, C.2.2]
# - Private Use characters [StringPrep, C.3]
# - Non-character code points [StringPrep, C.4]
# - Surrogate code points [StringPrep, C.5]
# - Inappropriate for plain text characters [StringPrep, C.6]
# - Inappropriate for canonical representation characters [StringPrep, C.7]
# - Change display properties or deprecated characters [StringPrep, C.8]
# - Tagging characters [StringPrep, C.9]
# RFC4013, 2.4. Bidirectional Characters.
# RFC4013, 2.5. Unassigned Code Points.
# Determine how to handle bidirectional characters (RFC3454):
if is_ral_string(string):
# If a string contains any RandALCat characters,
# The string MUST NOT contain any LCat character:
is_prohibited_bidi_ch = in_table_d2
bidi_table = 'D.2'
else:
# Forbid RandALCat characters in LCat string:
is_prohibited_bidi_ch = in_table_d1
bidi_table = 'D.1'
RFC = 'RFC4013'
for c in string:
# RFC4013 2.3. Prohibited Output:
if in_table_c12(c):
raise ValueError('%s: prohibited non-ASCII space characters '
'that cannot be replaced (C.1.2).' % RFC)
if in_table_c21_c22(c):
raise ValueError('%s: prohibited control characters (C.2.1).' %
RFC)
if in_table_c3(c):
raise ValueError('%s: prohibited private Use characters (C.3).' %
RFC)
if in_table_c4(c):
raise ValueError(
'%s: prohibited non-character code points (C.4).' % RFC)
if in_table_c5(c):
raise ValueError('%s: prohibited surrogate code points (C.5).' %
RFC)
if in_table_c6(c):
raise ValueError('%s: prohibited inappropriate for plain text '
'characters (C.6).' % RFC)
if in_table_c7(c):
raise ValueError('%s: prohibited inappropriate for canonical '
'representation characters (C.7).' % RFC)
if in_table_c8(c):
raise ValueError('%s: prohibited change display properties / '
'deprecated characters (C.8).' % RFC)
if in_table_c9(c):
raise ValueError('%s: prohibited tagging characters (C.9).' % RFC)
# RFC4013, 2.4. Bidirectional Characters:
if is_prohibited_bidi_ch(c):
raise ValueError('%s: prohibited bidi characters (%s).' %
(RFC, bidi_table))
# RFC4013, 2.5. Unassigned Code Points:
if in_table_a1(c):
raise ValueError('%s: prohibited unassigned code points (A.1).' %
RFC)
def update_event(self, inp=-1):
self.set_output_val(0, stringprep.in_table_c21_c22(self.input(0)))
