Python stringprep.in_table_c8方法代码示例

# 需要导入模块: import stringprep [as 别名]
# 或者: from stringprep import in_table_c8 [as 别名]
def check_bidi(data):
    """
    1) The characters in section 5.8 MUST be prohibited.

    2) If a string contains any RandALCat character, the string MUST NOT
       contain any LCat character.

    3) If a string contains any RandALCat character, a RandALCat
       character MUST be the first character of the string, and a
       RandALCat character MUST be the last character of the string.
    """
    if not data:
        return data

    has_lcat = False
    has_randal = False

    for c in data:
        if stringprep.in_table_c8(c):
            raise StringPrepError("BIDI violation: seciton 6 (1)")
        if stringprep.in_table_d1(c):
            has_randal = True
        elif stringprep.in_table_d2(c):
            has_lcat = True

    if has_randal and has_lcat:
        raise StringPrepError("BIDI violation: section 6 (2)")

    first_randal = stringprep.in_table_d1(data[0])
    last_randal = stringprep.in_table_d1(data[-1])
    if has_randal and not (first_randal and last_randal):
        raise StringPrepError("BIDI violation: section 6 (3)") 

# 需要导入模块: import stringprep [as 别名]
# 或者: from stringprep import in_table_c8 [as 别名]
def nameprep(label):
    # Map
    newlabel = []
    for c in label:
        if stringprep.in_table_b1(c):
            # Map to nothing
            continue
        newlabel.append(stringprep.map_table_b2(c))
    label = u"".join(newlabel)

    # Normalize
    label = unicodedata.normalize("NFKC", label)

    # Prohibit
    for c in label:
        if stringprep.in_table_c12(c) or \
           stringprep.in_table_c22(c) or \
           stringprep.in_table_c3(c) or \
           stringprep.in_table_c4(c) or \
           stringprep.in_table_c5(c) or \
           stringprep.in_table_c6(c) or \
           stringprep.in_table_c7(c) or \
           stringprep.in_table_c8(c) or \
           stringprep.in_table_c9(c):
            raise UnicodeError("Invalid character %r" % c)

    # Check bidi
    RandAL = map(stringprep.in_table_d1, label)
    for c in RandAL:
        if c:
            # There is a RandAL char in the string. Must perform further
            # tests:
            # 1) The characters in section 5.8 MUST be prohibited.
            # This is table C.8, which was already checked
            # 2) If a string contains any RandALCat character, the string
            # MUST NOT contain any LCat character.
            if filter(stringprep.in_table_d2, label):
                raise UnicodeError("Violation of BIDI requirement 2")

            # 3) If a string contains any RandALCat character, a
            # RandALCat character MUST be the first character of the
            # string, and a RandALCat character MUST be the last
            # character of the string.
            if not RandAL[0] or not RandAL[-1]:
                raise UnicodeError("Violation of BIDI requirement 3")

    return label 

# 需要导入模块: import stringprep [as 别名]
# 或者: from stringprep import in_table_c8 [as 别名]
def nameprep(label):
    # Map
    newlabel = []
    for c in label:
        if stringprep.in_table_b1(c):
            # Map to nothing
            continue
        newlabel.append(stringprep.map_table_b2(c))
    label = "".join(newlabel)

    # Normalize
    label = unicodedata.normalize("NFKC", label)

    # Prohibit
    for c in label:
        if stringprep.in_table_c12(c) or \
           stringprep.in_table_c22(c) or \
           stringprep.in_table_c3(c) or \
           stringprep.in_table_c4(c) or \
           stringprep.in_table_c5(c) or \
           stringprep.in_table_c6(c) or \
           stringprep.in_table_c7(c) or \
           stringprep.in_table_c8(c) or \
           stringprep.in_table_c9(c):
            raise UnicodeError("Invalid character %r" % c)

    # Check bidi
    RandAL = [stringprep.in_table_d1(x) for x in label]
    for c in RandAL:
        if c:
            # There is a RandAL char in the string. Must perform further
            # tests:
            # 1) The characters in section 5.8 MUST be prohibited.
            # This is table C.8, which was already checked
            # 2) If a string contains any RandALCat character, the string
            # MUST NOT contain any LCat character.
            if any(stringprep.in_table_d2(x) for x in label):
                raise UnicodeError("Violation of BIDI requirement 2")

            # 3) If a string contains any RandALCat character, a
            # RandALCat character MUST be the first character of the
            # string, and a RandALCat character MUST be the last
            # character of the string.
            if not RandAL[0] or not RandAL[-1]:
                raise UnicodeError("Violation of BIDI requirement 3")

    return label 

# 需要导入模块: import stringprep [as 别名]
# 或者: from stringprep import in_table_c8 [as 别名]
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