Python unicodedata.bidirectional() Examples

The following are 30 code examples of unicodedata.bidirectional(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module unicodedata , or try the search function .
Example #1
Source File: test_regressions.py    From ironpython3 with Apache License 2.0 6 votes vote down vote up
def test_ipy2_gh357(self):
        """https://github.com/IronLanguages/ironpython2/issues/357"""

        import unicodedata

        if is_cli:
            self.assertEqual(unicodedata.name(u'\u4e2d'), '<CJK IDEOGRAPH, FIRST>..<CJK IDEOGRAPH, LAST>')
        else:
            self.assertEqual(unicodedata.name(u'\u4e2d'), 'CJK UNIFIED IDEOGRAPH-4E2D')

        self.assertRaises(ValueError, unicodedata.decimal, u'\u4e2d')
        self.assertEqual(unicodedata.decimal(u'\u4e2d', 0), 0)
        self.assertRaises(ValueError, unicodedata.digit, u'\u4e2d')
        self.assertEqual(unicodedata.digit(u'\u4e2d', 0), 0)
        self.assertRaises(ValueError, unicodedata.numeric, u'\u4e2d')
        self.assertEqual(unicodedata.numeric(u'\u4e2d', 0), 0)
        self.assertEqual(unicodedata.category(u'\u4e2d'), 'Lo')
        self.assertEqual(unicodedata.bidirectional(u'\u4e2d'), 'L')
        self.assertEqual(unicodedata.combining(u'\u4e2d'), 0)
        self.assertEqual(unicodedata.east_asian_width(u'\u4e2d'), 'W')
        self.assertEqual(unicodedata.mirrored(u'\u4e2d'), 0)
        self.assertEqual(unicodedata.decomposition(u'\u4e2d'), '') 
Example #2
Source File: test_regressions.py    From ironpython2 with Apache License 2.0 6 votes vote down vote up
def test_ipy2_gh357(self):
        """https://github.com/IronLanguages/ironpython2/issues/357"""

        import unicodedata

        if is_cli:
            self.assertEqual(unicodedata.name(u'\u4e2d'), '<CJK IDEOGRAPH, FIRST>..<CJK IDEOGRAPH, LAST>')
        else:
            self.assertEqual(unicodedata.name(u'\u4e2d'), 'CJK UNIFIED IDEOGRAPH-4E2D')

        self.assertRaises(ValueError, unicodedata.decimal, u'\u4e2d')
        self.assertEqual(unicodedata.decimal(u'\u4e2d', 0), 0)
        self.assertRaises(ValueError, unicodedata.digit, u'\u4e2d')
        self.assertEqual(unicodedata.digit(u'\u4e2d', 0), 0)
        self.assertRaises(ValueError, unicodedata.numeric, u'\u4e2d')
        self.assertEqual(unicodedata.numeric(u'\u4e2d', 0), 0)
        self.assertEqual(unicodedata.category(u'\u4e2d'), 'Lo')
        self.assertEqual(unicodedata.bidirectional(u'\u4e2d'), 'L')
        self.assertEqual(unicodedata.combining(u'\u4e2d'), 0)
        self.assertEqual(unicodedata.east_asian_width(u'\u4e2d'), 'W')
        self.assertEqual(unicodedata.mirrored(u'\u4e2d'), 0)
        self.assertEqual(unicodedata.decomposition(u'\u4e2d'), '') 
Example #3
Source File: css_match.py    From soupsieve with MIT License 5 votes vote down vote up
def find_bidi(self, el):
        """Get directionality from element text."""

        for node in self.get_children(el, tags=False):

            # Analyze child text nodes
            if self.is_tag(node):

                # Avoid analyzing certain elements specified in the specification.
                direction = DIR_MAP.get(util.lower(self.get_attribute_by_name(node, 'dir', '')), None)
                if (
                    self.get_tag(node) in ('bdi', 'script', 'style', 'textarea', 'iframe') or
                    not self.is_html_tag(node) or
                    direction is not None
                ):
                    continue  # pragma: no cover

                # Check directionality of this node's text
                value = self.find_bidi(node)
                if value is not None:
                    return value

                # Direction could not be determined
                continue  # pragma: no cover

            # Skip `doctype` comments, etc.
            if self.is_special_string(node):
                continue

            # Analyze text nodes for directionality.
            for c in node:
                bidi = unicodedata.bidirectional(c)
                if bidi in ('AL', 'R', 'L'):
                    return ct.SEL_DIR_LTR if bidi == 'L' else ct.SEL_DIR_RTL
        return None 
Example #4
Source File: glyphIgo.py    From glyphIgo with MIT License 5 votes vote down vote up
def __print_Unicode_info(self, char, short):
        name = unicodedata.name(char, "UNKNOWN")
        decCodepoint = ord(char)
        hexCodepoint = hex(decCodepoint)
        lower = char.lower()
        upper = char.upper()
        category = unicodedata.category(char)
        bidirectional = unicodedata.bidirectional(char)
        mirrored = True if (unicodedata.mirrored(char) == 1) else False
        nfc = unicodedata.normalize("NFC", char)
        nfd = unicodedata.normalize("NFD", char)
        if (short):
            print char + "\t" + name + " (U+" + str(hexCodepoint).upper().replace("0X", "") + ")"
        else:
            print "Name          " + name 
            print "Character     " + char 
            print "Dec Codepoint " + str(decCodepoint)
            print "Hex Codepoint " + str(hexCodepoint)
            print "Lowercase     " + lower
            print "Uppercase     " + upper
            print "Category      " + category
            print "Bidirectional " + bidirectional
            print "Mirrored      " + str(mirrored)
            print "NFC           " + nfc
            print "NFD           " + nfd
            print "============="

    # helper: perform a lookup for the given query 
Example #5
Source File: css_match.py    From plugin.git.browser with GNU General Public License v3.0 5 votes vote down vote up
def find_bidi(self, el):
        """Get directionality from element text."""

        for node in self.get_children(el, tags=False):

            # Analyze child text nodes
            if self.is_tag(node):

                # Avoid analyzing certain elements specified in the specification.
                direction = DIR_MAP.get(util.lower(self.get_attribute_by_name(node, 'dir', '')), None)
                if (
                    self.get_tag(node) in ('bdi', 'script', 'style', 'textarea') or
                    direction is not None
                ):
                    continue  # pragma: no cover

                # Check directionality of this node's text
                value = self.find_bidi(node)
                if value is not None:
                    return value

                # Direction could not be determined
                continue  # pragma: no cover

            # Skip `doctype` comments, etc.
            if self.is_special_string(node):
                continue

            # Analyze text nodes for directionality.
            for c in node:
                bidi = unicodedata.bidirectional(c)
                if bidi in ('AL', 'R', 'L'):
                    return ct.SEL_DIR_LTR if bidi == 'L' else ct.SEL_DIR_RTL
        return None 
Example #6
Source File: css_match.py    From bazarr with GNU General Public License v3.0 5 votes vote down vote up
def find_bidi(self, el):
        """Get directionality from element text."""

        for node in self.get_children(el, tags=False):

            # Analyze child text nodes
            if self.is_tag(node):

                # Avoid analyzing certain elements specified in the specification.
                direction = DIR_MAP.get(util.lower(self.get_attribute_by_name(node, 'dir', '')), None)
                if (
                    self.get_tag(node) in ('bdi', 'script', 'style', 'textarea', 'iframe') or
                    not self.is_html_tag(node) or
                    direction is not None
                ):
                    continue  # pragma: no cover

                # Check directionality of this node's text
                value = self.find_bidi(node)
                if value is not None:
                    return value

                # Direction could not be determined
                continue  # pragma: no cover

            # Skip `doctype` comments, etc.
            if self.is_special_string(node):
                continue

            # Analyze text nodes for directionality.
            for c in node:
                bidi = unicodedata.bidirectional(c)
                if bidi in ('AL', 'R', 'L'):
                    return ct.SEL_DIR_LTR if bidi == 'L' else ct.SEL_DIR_RTL
        return None 
Example #7
Source File: __init__.py    From glyphNameFormatter with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up
def lookup(self):
        # look up all the external references we need.
        if self.uniNumber is None:
            return
        try:
            self.uniLetter = unicodeToChar(self.uniNumber)
        except:
            # print("GlyphName value error for %04X" % self.uniNumber)
            return
        if self.uniNumber in mathUniNumbers:
            self.isMath = True
        try:
            self.uniName = unicodelist.get(self.uniNumber)
            if self.uniName is None:
                self.uniNameProcessed = ""
            else:
                self.uniNameProcessed = self.uniName
            # NOTE: this is still a dependency on the unicodedata module.
            # Would be nice to extract this data directly from the unicode data
            # but the algotirhm is ot trivial..
            self.bidiType = unicodedata.bidirectional(self.uniLetter)
        except ValueError:
            self.uniName = None
            self.uniNameProcessed = ""
            self.uniLetter = None
            self.bidiType = None
        except:
            import traceback
            traceback.print_exc()
        self.uniRangeName = getRangeName(self.uniNumber)

    # these can be called by a range processor to set the status of a name. 
Example #8
Source File: core.py    From plugin.program.indigo with GNU General Public License v3.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
            break
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #9
Source File: core.py    From rules_pip with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #10
Source File: core.py    From googletranslate.popclipext with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
            break
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #11
Source File: core.py    From CudaText with Mozilla Public License 2.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #12
Source File: core.py    From bazarr with GNU General Public License v3.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #13
Source File: core.py    From CogAlg with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #14
Source File: core.py    From CTFCrackTools-V2 with GNU General Public License v3.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
            break
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #15
Source File: core.py    From guildai with Apache License 2.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #16
Source File: core.py    From watchmen with Apache License 2.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
            break
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #17
Source File: core.py    From coffeegrindsize with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #18
Source File: core.py    From pyRevit with GNU General Public License v3.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
            break
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #19
Source File: core.py    From Requester with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
            break
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #20
Source File: core.py    From Weapon-Detection-And-Classification with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #21
Source File: core.py    From addon with GNU General Public License v3.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #22
Source File: core.py    From Galaxy_Plugin_Bethesda with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #23
Source File: core.py    From cadquery-freecad-module with GNU Lesser General Public License v3.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #24
Source File: core.py    From scalyr-agent-2 with Apache License 2.0 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
            break
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #25
Source File: core.py    From Hands-On-Application-Development-with-PyCharm with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #26
Source File: core.py    From script.elementum.burst with Do What The F*ck You Want To Public License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #27
Source File: core.py    From stopstalk-deployment with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #28
Source File: core.py    From learn_python3_spider with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #29
Source File: core.py    From learn_python3_spider with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True 
Example #30
Source File: core.py    From cronyo with MIT License 4 votes vote down vote up
def check_bidi(label, check_ltr=False):

    # Bidi rules should only be applied if string contains RTL characters
    bidi_label = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)
        if direction == '':
            # String likely comes from a newer version of Unicode
            raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
        if direction in ['R', 'AL', 'AN']:
            bidi_label = True
    if not bidi_label and not check_ltr:
        return True

    # Bidi rule 1
    direction = unicodedata.bidirectional(label[0])
    if direction in ['R', 'AL']:
        rtl = True
    elif direction == 'L':
        rtl = False
    else:
        raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))

    valid_ending = False
    number_type = False
    for (idx, cp) in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
            # Bidi rule 3
            if direction in ['R', 'AL', 'EN', 'AN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False
            # Bidi rule 4
            if direction in ['AN', 'EN']:
                if not number_type:
                    number_type = direction
                else:
                    if number_type != direction:
                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
        else:
            # Bidi rule 5
            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
                raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
            # Bidi rule 6
            if direction in ['L', 'EN']:
                valid_ending = True
            elif direction != 'NSM':
                valid_ending = False

    if not valid_ending:
        raise IDNABidiError('Label ends with illegal codepoint directionality')

    return True