Python stringprep.in_table_a1() Examples

def check_unassigneds(self, string):
        for c in string:
            if stringprep.in_table_a1(c):
                raise UnicodeError("Unassigned code point %s" % repr(c)) 

def check_unassigneds(self, string):
        for c in string:
            if stringprep.in_table_a1(c):
                raise UnicodeError("Unassigned code point %s" % repr(c)) 

def check_unassigneds(self, string):
        for c in string:
            if stringprep.in_table_a1(c):
                raise UnicodeError, "Unassigned code point %s" % repr(c) 

def check_unassigneds(self, string):
        for c in string:
            if stringprep.in_table_a1(c):
                raise UnicodeError, "Unassigned code point %s" % repr(c) 

def saslprep(data, prohibit_unassigned_code_points=True):
        """An implementation of RFC4013 SASLprep.

        :Parameters:
          - `data`: The string to SASLprep. Unicode strings
            (python 2.x unicode, 3.x str) are supported. Byte strings
            (python 2.x str, 3.x bytes) are ignored.
          - `prohibit_unassigned_code_points`: True / False. RFC 3454
            and RFCs for various SASL mechanisms distinguish between
            `queries` (unassigned code points allowed) and
            `stored strings` (unassigned code points prohibited). Defaults
            to ``True`` (unassigned code points are prohibited).

        :Returns:
        The SASLprep'ed version of `data`.
        """
        if not isinstance(data, _text_type):
            return data

        if prohibit_unassigned_code_points:
            prohibited = _PROHIBITED + (stringprep.in_table_a1,)
        else:
            prohibited = _PROHIBITED

        # RFC3454 section 2, step 1 - Map
        # RFC4013 section 2.1 mappings
        # Map Non-ASCII space characters to SPACE (U+0020). Map
        # commonly mapped to nothing characters to, well, nothing.
        in_table_c12 = stringprep.in_table_c12
        in_table_b1 = stringprep.in_table_b1
        data = u"".join(
            [u"\u0020" if in_table_c12(elt) else elt
             for elt in data if not in_table_b1(elt)])

        # RFC3454 section 2, step 2 - Normalize
        # RFC4013 section 2.2 normalization
        data = unicodedata.ucd_3_2_0.normalize('NFKC', data)

        in_table_d1 = stringprep.in_table_d1
        if in_table_d1(data[0]):
            if not in_table_d1(data[-1]):
                # RFC3454, Section 6, #3. If a string contains any
                # RandALCat character, the first and last characters
                # MUST be RandALCat characters.
                raise ValueError("SASLprep: failed bidirectional check")
            # RFC3454, Section 6, #2. If a string contains any RandALCat
            # character, it MUST NOT contain any LCat character.
            prohibited = prohibited + (stringprep.in_table_d2,)
        else:
            # RFC3454, Section 6, #3. Following the logic of #3, if
            # the first character is not a RandALCat, no other character
            # can be either.
            prohibited = prohibited + (in_table_d1,)

        # RFC3454 section 2, step 3 and 4 - Prohibit and check bidi
        for char in data:
            if any(in_table(char) for in_table in prohibited):
                raise ValueError(
                    "SASLprep: failed prohibited character check")

        return data 

def saslprep(data, prohibit_unassigned_code_points=True):
        """An implementation of RFC4013 SASLprep.

        :Parameters:
          - `data`: The string to SASLprep. Unicode strings
            (python 2.x unicode, 3.x str) are supported. Byte strings
            (python 2.x str, 3.x bytes) are ignored.
          - `prohibit_unassigned_code_points`: True / False. RFC 3454
            and RFCs for various SASL mechanisms distinguish between
            `queries` (unassigned code points allowed) and
            `stored strings` (unassigned code points prohibited). Defaults
            to ``True`` (unassigned code points are prohibited).

        :Returns:
        The SASLprep'ed version of `data`.
        """
        if not isinstance(data, _text_type):
            return data

        if prohibit_unassigned_code_points:
            prohibited = _PROHIBITED + (stringprep.in_table_a1,)
        else:
            prohibited = _PROHIBITED

        # RFC3454 section 2, step 1 - Map
        # RFC4013 section 2.1 mappings
        # Map Non-ASCII space characters to SPACE (U+0020). Map
        # commonly mapped to nothing characters to, well, nothing.
        in_table_c12 = stringprep.in_table_c12
        in_table_b1 = stringprep.in_table_b1
        data = u"".join(
            [u"\u0020" if in_table_c12(elt) else elt
             for elt in data if not in_table_b1(elt)])

        # RFC3454 section 2, step 2 - Normalize
        # RFC4013 section 2.2 normalization
        data = unicodedata.ucd_3_2_0.normalize('NFKC', data)

        in_table_d1 = stringprep.in_table_d1
        if in_table_d1(data[0]):
            if not in_table_d1(data[-1]):
                # RFC3454, Section 6, #3. If a string contains any
                # RandALCat character, the first and last characters
                # MUST be RandALCat characters.
                raise ValueError("SASLprep: failed bidirectional check")
            # RFC3454, Section 6, #2. If a string contains any RandALCat
            # character, it MUST NOT contain any LCat character.
            prohibited = prohibited + (stringprep.in_table_d2,)
        else:
            # RFC3454, Section 6, #3. Following the logic of #3, if
            # the first character is not a RandALCat, no other character
            # can be either.
            prohibited = prohibited + (in_table_d1,)

        # RFC3454 section 2, step 3 and 4 - Prohibit and check bidi
        for char in data:
            if any(in_table(char) for in_table in prohibited):
                raise ValueError(
                    "SASLprep: failed prohibited character check")

        return data 

def saslprep(data: str, prohibit_unassigned_code_points=True):
    """An implementation of RFC4013 SASLprep."""

    if data == '':
        return data

    if prohibit_unassigned_code_points:
        prohibited = _PROHIBITED + (stringprep.in_table_a1,)
    else:
        prohibited = _PROHIBITED

    # RFC3454 section 2, step 1 - Map
    # RFC4013 section 2.1 mappings
    # Map Non-ASCII space characters to SPACE (U+0020). Map
    # commonly mapped to nothing characters to, well, nothing.
    in_table_c12 = stringprep.in_table_c12
    in_table_b1 = stringprep.in_table_b1
    data = u"".join(
        [u"\u0020" if in_table_c12(elt) else elt
            for elt in data if not in_table_b1(elt)])

    # RFC3454 section 2, step 2 - Normalize
    # RFC4013 section 2.2 normalization
    data = unicodedata.ucd_3_2_0.normalize('NFKC', data)

    in_table_d1 = stringprep.in_table_d1
    if in_table_d1(data[0]):
        if not in_table_d1(data[-1]):
            # RFC3454, Section 6, #3. If a string contains any
            # RandALCat character, the first and last characters
            # MUST be RandALCat characters.
            raise ValueError("SASLprep: failed bidirectional check")
        # RFC3454, Section 6, #2. If a string contains any RandALCat
        # character, it MUST NOT contain any LCat character.
        prohibited = prohibited + (stringprep.in_table_d2,)
    else:
        # RFC3454, Section 6, #3. Following the logic of #3, if
        # the first character is not a RandALCat, no other character
        # can be either.
        prohibited = prohibited + (in_table_d1,)

    # RFC3454 section 2, step 3 and 4 - Prohibit and check bidi
    for char in data:
        if any(in_table(char) for in_table in prohibited):
            raise ValueError(
                "SASLprep: failed prohibited character check")

    return data 

def saslprep(s, allow_unassigned = False):
    '''
    Prepare Unicode string s according to SASLprep: Stringprep Profile for
    User Names and Passwords, a.k.a. RFC 4013

    If the optional parameter allow_unassigned is set to True,
    unassigned codepoints will be allowed. This is recommended for
    query terms and other non-storing situations only.

    The return value is a Unicode string appropriately prepared.

    Disallowed input leads to a ValueError.
    '''
    if type(s) != type(u''):
        raise TypeError("input must be a Unicode string")
    # phase 1: mapping
    s = u''.join([ stringprep.in_table_c12(ch) and u' ' or ch for ch in unichars(s) if not stringprep.in_table_b1(ch) ])
    # phase 2: normalization
    s = unicodedata.normalize('NFKC', s)
    # phase 3: prohibition
    for ch in unichars(s):
        if stringprep.in_table_c12(ch):
            raise ValueError("prohibited non-ASCII space character")
        if stringprep.in_table_c21(ch):
            raise ValueError("prohibited ASCII control character")
        if stringprep.in_table_c22(ch):
            raise ValueError("prohibited non-ASCII control character")
        if stringprep.in_table_c3(ch):
            raise ValueError("prohibited private use character")
        if stringprep.in_table_c4(ch):
            raise ValueError("prohibited non-character code point")
        if stringprep.in_table_c5(ch):
            raise ValueError("prohibited surrogate code point")
        if stringprep.in_table_c6(ch):
            raise ValueError("prohibited character inappropriate for plain text")
        if stringprep.in_table_c7(ch):
            raise ValueError("prohibited character inappropriate for canonical representation")
        if stringprep.in_table_c8(ch):
            raise ValueError("prohibited character changing display properties, or a deprecated character")
        if stringprep.in_table_c9(ch):
            raise ValueError("prohibited tagging character")
    # phase 4: bidi check
    bidi_map = ''.join([ stringprep.in_table_d1(ch) and 'r' or stringprep.in_table_d2(ch) and 'l' or 'x' for ch in unichars(s) ])
    if 'r' in bidi_map:
        if 'l' in bidi_map:
            raise ValueError("prohibited mixture of strong left-to-right and right-to-left text")
        if bidi_map[0] != 'r' or bidi_map[-1] != 'r':
            raise ValueError("string containing right-to-left text must start and end with right-to-left text")
    # phase 5: unassigned check
    if not allow_unassigned:
        for ch in unichars(s):
            if stringprep.in_table_a1(ch):
                raise ValueError("prohibited unassigned code point")
    return s