Python re.UNICODE() Examples

def str_flags_to_int(str_flags):
    flags = 0
    if "i" in str_flags:
        flags |= re.IGNORECASE
    if "l" in str_flags:
        flags |= re.LOCALE
    if "m" in str_flags:
        flags |= re.MULTILINE
    if "s" in str_flags:
        flags |= re.DOTALL
    if "u" in str_flags:
        flags |= re.UNICODE
    if "x" in str_flags:
        flags |= re.VERBOSE

    return flags 

def _encode_regex(name, value, dummy0, dummy1):
    """Encode a python regex or bson.regex.Regex."""
    flags = value.flags
    # Python 2 common case
    if flags == 0:
        return b"\x0B" + name + _make_c_string_check(value.pattern) + b"\x00"
    # Python 3 common case
    elif flags == re.UNICODE:
        return b"\x0B" + name + _make_c_string_check(value.pattern) + b"u\x00"
    else:
        sflags = b""
        if flags & re.IGNORECASE:
            sflags += b"i"
        if flags & re.LOCALE:
            sflags += b"l"
        if flags & re.MULTILINE:
            sflags += b"m"
        if flags & re.DOTALL:
            sflags += b"s"
        if flags & re.UNICODE:
            sflags += b"u"
        if flags & re.VERBOSE:
            sflags += b"x"
        sflags += b"\x00"
        return b"\x0B" + name + _make_c_string_check(value.pattern) + sflags 

def __init__(self, **kwargs):
        """Construct a TINYTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(TINYTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a MEDIUMTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(MEDIUMTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a LONGTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(LONGTEXT, self).__init__(**kwargs) 

def __init__(self, length=None, **kwargs):
        """Construct a VARCHAR.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(VARCHAR, self).__init__(length=length, **kwargs) 

def expandvars(path):
    """
    Args:
        path (pathlike): A path to expand
    Returns:
        `fsnative`

    Like :func:`python:os.path.expandvars` but supports unicode under Windows
    + Python 2 and always returns a `fsnative`.
    """

    path = path2fsn(path)

    def repl_func(match):
        return environ.get(match.group(1), match.group(0))

    path = re.compile(r"\$(\w+)", flags=re.UNICODE).sub(repl_func, path)
    if os.name == "nt":
        path = re.sub(r"%([^%]+)%", repl_func, path)
    return re.sub(r"\$\{([^\}]+)\}", repl_func, path) 

def safe_filename(text, max_length=200):
    """Sanitizes filenames for many operating systems.

    :params text: The unsanitized pending filename.
    """

    # Tidy up ugly formatted filenames.
    text = text.replace('_', ' ')
    text = text.replace(':', ' -')

    # NTFS forbids filenames containing characters in range 0-31 (0x00-0x1F)
    ntfs = [chr(i) for i in range(0, 31)]

    # Removing these SHOULD make most filename safe for a wide range of
    # operating systems.
    paranoid = ['\"', '\#', '\$', '\%', '\'', '\*', '\,', '\.', '\/', '\:',
                '\;', '\<', '\>', '\?', '\\', '\^', '\|', '\~', '\\\\']

    blacklist = re.compile('|'.join(ntfs + paranoid), re.UNICODE)
    filename = blacklist.sub('', text)
    return truncate(filename) 

def str_flags_to_int(str_flags):
    flags = 0
    if "i" in str_flags:
        flags |= re.IGNORECASE
    if "l" in str_flags:
        flags |= re.LOCALE
    if "m" in str_flags:
        flags |= re.MULTILINE
    if "s" in str_flags:
        flags |= re.DOTALL
    if "u" in str_flags:
        flags |= re.UNICODE
    if "x" in str_flags:
        flags |= re.VERBOSE

    return flags 

def str_flags_to_int(str_flags):
    flags = 0
    if "i" in str_flags:
        flags |= re.IGNORECASE
    if "l" in str_flags:
        flags |= re.LOCALE
    if "m" in str_flags:
        flags |= re.MULTILINE
    if "s" in str_flags:
        flags |= re.DOTALL
    if "u" in str_flags:
        flags |= re.UNICODE
    if "x" in str_flags:
        flags |= re.VERBOSE

    return flags 

def str_flags_to_int(str_flags):
    flags = 0
    if "i" in str_flags:
        flags |= re.IGNORECASE
    if "l" in str_flags:
        flags |= re.LOCALE
    if "m" in str_flags:
        flags |= re.MULTILINE
    if "s" in str_flags:
        flags |= re.DOTALL
    if "u" in str_flags:
        flags |= re.UNICODE
    if "x" in str_flags:
        flags |= re.VERBOSE

    return flags 

def str_flags_to_int(str_flags):
    flags = 0
    if "i" in str_flags:
        flags |= re.IGNORECASE
    if "l" in str_flags:
        flags |= re.LOCALE
    if "m" in str_flags:
        flags |= re.MULTILINE
    if "s" in str_flags:
        flags |= re.DOTALL
    if "u" in str_flags:
        flags |= re.UNICODE
    if "x" in str_flags:
        flags |= re.VERBOSE

    return flags 

def __init__(self, pattern, markdown_instance=None):
        """
        Create an instant of an inline pattern.

        Keyword arguments:

        * pattern: A regular expression that matches a pattern

        """
        self.pattern = pattern
        self.compiled_re = re.compile("^(.*?)%s(.*)$" % pattern,
                                      re.DOTALL | re.UNICODE)

        # Api for Markdown to pass safe_mode into instance
        self.safe_mode = False
        if markdown_instance:
            self.markdown = markdown_instance 

def regex(self):
        """
        Returns a compiled regular expression, depending upon the activated
        language-code.
        """
        language_code = get_language()
        if language_code not in self._regex_dict:
            if isinstance(self._regex, six.string_types):
                regex = self._regex
            else:
                regex = force_text(self._regex)
            try:
                compiled_regex = re.compile(regex, re.UNICODE)
            except re.error as e:
                raise ImproperlyConfigured(
                    '"%s" is not a valid regular expression: %s' %
                    (regex, six.text_type(e)))

            self._regex_dict[language_code] = compiled_regex
        return self._regex_dict[language_code] 

def _do_match(self, text):
        if self.use_regex:
            try:
                flags = re.UNICODE
                if not self.case_sensitive:
                    flags |= re.IGNORECASE
                return bool(re.findall(self.pattern, text, flags=flags))
            except Exception as ex:
                logger.warning('Regular expression match failed', exc_info=True)
                raise self.BadPatternException(str(ex))
        else:
            if self.case_sensitive:
                pattern = self.pattern
            else:
                pattern = self.pattern.lower()
                text = text.lower()
            return pattern in text 

def obtainGroups(webcontent, groupNum):
    synonym_list = []
    for group in range(groupNum):
        while not re.search("synonyms-list-group", webcontent.readline(), re.UNICODE):
            continue
        meaning = re.search("Meaning: <b>([^<]+)</b>", webcontent.readline(), re.UNICODE).group(1)
        webcontent.readline() # </div> line
        webcontent.readline() # synonyms-list_content line
        sublist = webcontent.readline().split(',')
        subSynList = []
        for wordContainer in sublist:
            potential_synonym = re.search("<a href=[^>]+>([^<]+)</a>", wordContainer, re.UNICODE)
            if potential_synonym:
                subSynList.append(potential_synonym.group(1))
        synonym_list.append([meaning, subSynList])
    return synonym_list 

def _parser(webcontent):
    end_tag_count=4
    pointer = webcontent.tell()
    end = len(webcontent.getvalue())
    while pointer<end:
        line_curr = webcontent.readline()
        found = re.search("Found ([0-9]+) synonym[ a-z]+([0-9]+) group", line_curr, re.UNICODE)
        notFound = re.search("<div class=\"no-results\">", line_curr, re.UNICODE)
        if found:
            groupNum = int(found.group(2))
            synonymNum = int(found.group(1))
            synonym_list = obtainGroups(webcontent, groupNum)
            webcontent.close()
            return synonym_list
        if notFound:
            webcontent.close()
            return []

    webcontent.close()
    return synonym_list 

def __init__(self, **kwargs):
        """Construct a TINYTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(TINYTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a MEDIUMTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(MEDIUMTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a LONGTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(LONGTEXT, self).__init__(**kwargs) 

def __init__(self, length=None, **kwargs):
        """Construct a VARCHAR.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(VARCHAR, self).__init__(length=length, **kwargs) 

def _fun_into(x):
    if ct.PY3:
            reg1 = re.compile(r'??(.*?)?', re.UNICODE)
            reg2 = re.compile(r'??(.*?)?', re.UNICODE)
            res1 = reg1.findall(x)
            res2 = reg2.findall(x)
            res1 = 0 if len(res1)<1 else float(res1[0])
            res2 = 0 if len(res2)<1 else float(res2[0])
            return res1 + res2
    else:
        if isinstance(x, unicode):
            s1 = unicode('??','utf-8')
            s2 = unicode('??','utf-8')
            s3 = unicode('?','utf-8')
            reg1 = re.compile(r'%s(.*?)%s'%(s1, s3), re.UNICODE)
            reg2 = re.compile(r'%s(.*?)%s'%(s2, s3), re.UNICODE)
            res1 = reg1.findall(x)
            res2 = reg2.findall(x)
            res1 = 0 if len(res1)<1 else float(res1[0])
            res2 = 0 if len(res2)<1 else float(res2[0])
            return res1 + res2
        else:
            return 0 

def __init__(self, expression, error_message='Invalid expression',
                 strict=False, search=False, extract=False,
                 is_unicode=False):

        if strict or not search:
            if not expression.startswith('^'):
                expression = '^(%s)' % expression
        if strict:
            if not expression.endswith('$'):
                expression = '(%s)$' % expression
        if is_unicode:
            if not isinstance(expression, unicodeT):
                expression = expression.decode('utf8')
            self.regex = re.compile(expression, re.UNICODE)
        else:
            self.regex = re.compile(expression)
        self.error_message = error_message
        self.extract = extract
        self.is_unicode = is_unicode or (not(PY2)) 

def transpyler_lexer_factory(transpyler):
    """
    Return a Pygments lexer class for the given transpyler.
    """

    def analyse_text(text):
        return shebang_matches(text, r'pythonw?3(\.\d)?')

    return type(
        transpyler.pygments_class_name,
        (Python3Lexer,),
        dict(
            analyse_text=analyse_text,
            name=transpyler.name,
            aliases=[transpyler.display_name],
            filenames=transpyler.file_extensions,
            mimetypes=transpyler.mimetypes,
            flags=re.MULTILINE | re.UNICODE,
            uni_name="[%s][%s]*" % (uni.xid_start, uni.xid_continue),
            tokens=make_transpyled_tokens(transpyler),
        )
    ) 

def build_regexp(definition, compile=True):
    """
    Build, compile and return a regular expression based on `definition`.

    :Parameter: `definition`: a 4-tuple (group name, prefix, suffix, parts),
        where "parts" is a list of regular expressions and/or regular
        expression definitions to be joined into an or-group.
    """
    name, prefix, suffix, parts = definition
    part_strings = []
    for part in parts:
        if type(part) is tuple:
            part_strings.append(build_regexp(part, None))
        else:
            part_strings.append(part)
    or_group = '|'.join(part_strings)
    regexp = '%(prefix)s(?P<%(name)s>%(or_group)s)%(suffix)s' % locals()
    if compile:
        return re.compile(regexp, re.UNICODE)
    else:
        return regexp 

def test_pass_precompiled_regex(self):
        """
        You can alternatively provide a precompiled regex to the Filter
        instead of a string pattern.
        """
        # Compile our own pattern so that we can specify the
        # ``IGNORECASE`` flag.
        # Note that you are responsible for adding the ``UNICODE`` flag
        # to your compiled regex!
        # noinspection SpellCheckingInspection
        pattern = re.compile(r'\btest\b', re.IGNORECASE | re.UNICODE)

        self.assertFilterPasses(
            self._filter('test march of the TEST penguins', pattern=pattern),
            ['test', 'TEST'],
        ) 

def test_pass_regex_library_support(self):
        """
        The Regex Filter also supports precompiled patterns using the
        ``regex`` library.
        """
        # Roughly, "Hi there!" in Burmese.
        word = '\u101f\u102d\u102f\u1004\u103a\u1038'

        # Note that :py:func:`regex.compile` automatically adds the
        # ``UNICODE`` flag for you when the pattern is a unicode.
        pattern = regex.compile(r'\w+')

        self.assertFilterPasses(
            self._filter(word, pattern=pattern),
            [word],
        ) 

def test_pass_precompiled_regex(self):
        """
        You can alternatively provide a precompiled regex to the Filter
        instead of a string pattern.
        """
        # Compile our own pattern so that we can specify the
        # ``IGNORECASE`` flag.
        # Note that you are responsible for adding the ``UNICODE`` flag
        # to your compiled regex!
        # noinspection SpellCheckingInspection
        pattern = re.compile(r'\btest\b', re.IGNORECASE | re.UNICODE)

        self.assertFilterPasses(
            self._filter('test march of the TEST penguins', pattern=pattern),
            ['', ' march of the ', ' penguins'],
        ) 

def test_pass_regex_library_support(self):
        """
        The Regex Filter also supports precompiled patterns using the
        ``regex`` library.
        """
        # Roughly, "Hi there!" in Burmese.
        word = '\u101f\u102d\u102f\u1004\u103a\u1038!'

        # Note that :py:func:`regex.compile` automatically adds the
        # ``UNICODE`` flag for you when the pattern is a unicode.
        pattern = regex.compile(r'\w+')

        self.assertFilterPasses(
            self._filter(word, pattern=pattern),
            ['', '!'],
        ) 

def build_regexp(definition, compile=True):
    """
    Build, compile and return a regular expression based on `definition`.

    :Parameter: `definition`: a 4-tuple (group name, prefix, suffix, parts),
        where "parts" is a list of regular expressions and/or regular
        expression definitions to be joined into an or-group.
    """
    name, prefix, suffix, parts = definition
    part_strings = []
    for part in parts:
        if type(part) is tuple:
            part_strings.append(build_regexp(part, None))
        else:
            part_strings.append(part)
    or_group = '|'.join(part_strings)
    regexp = '%(prefix)s(?P<%(name)s>%(or_group)s)%(suffix)s' % locals()
    if compile:
        return re.compile(regexp, re.UNICODE)
    else:
        return regexp 

def __init__(self, **kwargs):
        """Construct a TINYTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(TINYTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a MEDIUMTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(MEDIUMTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a LONGTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(LONGTEXT, self).__init__(**kwargs) 

def __init__(self, length=None, **kwargs):
        """Construct a VARCHAR.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(VARCHAR, self).__init__(length=length, **kwargs) 

def __init__(self, pattern, markdown_instance=None):
        """
        Create an instant of an inline pattern.

        Keyword arguments:

        * pattern: A regular expression that matches a pattern

        """
        self.pattern = pattern
        self.compiled_re = re.compile("^(.*?)%s(.*)$" % pattern,
                                      re.DOTALL | re.UNICODE)

        # Api for Markdown to pass safe_mode into instance
        self.safe_mode = False
        if markdown_instance:
            self.markdown = markdown_instance 

def __init__(self, expression, error_message='Invalid expression',
                 strict=False, search=False, extract=False,
                 is_unicode=False):

        if strict or not search:
            if not expression.startswith('^'):
                expression = '^(%s)' % expression
        if strict:
            if not expression.endswith('$'):
                expression = '(%s)$' % expression
        if is_unicode:
            if not isinstance(expression, unicode):
                expression = expression.decode('utf8')
            self.regex = re.compile(expression, re.UNICODE)
        else:
            self.regex = re.compile(expression)
        self.error_message = error_message
        self.extract = extract
        self.is_unicode = is_unicode 

def __init__(self, **kwargs):
        """Construct a TINYTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(TINYTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a MEDIUMTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(MEDIUMTEXT, self).__init__(**kwargs) 

def __init__(self, **kwargs):
        """Construct a LONGTEXT.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(LONGTEXT, self).__init__(**kwargs) 

def __init__(self, length=None, **kwargs):
        """Construct a VARCHAR.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(VARCHAR, self).__init__(length=length, **kwargs) 

def valid_name(name):
    r"""Determine whether or not the given string is a valid
    alphanumeric string.

    Parameters
    ----------
    name : str
        An alphanumeric identifier.

    Returns
    -------
    result : bool
        ``True`` if the name is valid, else ``False``.

    Examples
    --------

    >>> valid_name('alpha')   # True
    >>> valid_name('!alpha')  # False

    """
    identifier = re.compile(r"^[^\d\W]\w*\Z", re.UNICODE)
    result = re.match(identifier, name)
    return result is not None 

def __init__(self, expression, error_message='invalid expression',
                 strict=False, search=False, extract=False,
                 unicode=False):
        if strict or not search:
            if not expression.startswith('^'):
                expression = '^(%s)' % expression
        if strict:
            if not expression.endswith('$'):
                expression = '(%s)$' % expression
        if unicode:
            if not isinstance(expression,unicode):
                expression = expression.decode('utf8')
            self.regex = re.compile(expression,re.UNICODE)
        else:
            self.regex = re.compile(expression)
        self.error_message = error_message
        self.extract = extract
        self.unicode = unicode 

def parse_pocket_export(html_file):
    """Parse Pocket-format bookmarks export files (produced by getpocket.com/export/)"""

    html_file.seek(0)
    pattern = re.compile("^\\s*<li><a href=\"(.+)\" time_added=\"(\\d+)\" tags=\"(.*)\">(.+)</a></li>", re.UNICODE)
    for line in html_file:
        # example line
        # <li><a href="http://example.com/ time_added="1478739709" tags="tag1,tag2">example title</a></li>
        match = pattern.search(line)
        if match:
            fixed_url = match.group(1).replace('http://www.readability.com/read?url=', '')           # remove old readability prefixes to get original url
            time = datetime.fromtimestamp(float(match.group(2)))
            info = {
                'url': fixed_url,
                'domain': domain(fixed_url),
                'base_url': base_url(fixed_url),
                'timestamp': str(time.timestamp()),
                'tags': match.group(3),
                'title': match.group(4).replace(' — Readability', '').replace('http://www.readability.com/read?url=', '') or base_url(fixed_url),
                'sources': [html_file.name],
            }
            info['type'] = get_link_type(info)
            yield info 

def _apply_search_backrefs(pattern, flags=0):
    """Apply the search backrefs to the search pattern."""

    if isinstance(pattern, (compat.string_type, compat.binary_type)):
        re_verbose = bool(VERBOSE & flags)
        re_unicode = None
        if compat.PY3 and bool(ASCII & flags):
            re_unicode = False
        elif bool(UNICODE & flags):
            re_unicode = True
        pattern = SearchTemplate(pattern, re_verbose, re_unicode).apply()
    elif isinstance(pattern, RE_TYPE):
        if flags:
            raise ValueError("Cannot process flags argument with a compiled pattern!")
    else:
        raise TypeError("Not a string or compiled pattern!")
    return pattern 

def preprocessor(text):
    # TODO: Remove punctuation
    # Remove frontmatter

    text = re.sub(r"u'", '', text)
    text = re.sub(r'^\s*---.*---\s*$', '', text,
                  flags=re.DOTALL | re.MULTILINE | re.UNICODE)
    text = re.sub(r'^\s*\+{3}.*\+{3}\s*$', '', text,
                  flags=re.DOTALL | re.MULTILINE | re.UNICODE)
    text = re.sub(r'^\s*```.*?```\s*$', '', text,
                  flags=re.DOTALL | re.MULTILINE)
    text = re.sub(r'`[^`]*`', '', text)
    text = re.sub(r'<[^>]*>', '', text, flags=re.UNICODE |
                  re.DOTALL | re.MULTILINE)
    text = text.replace('<!--more--><!--ad-->', '')
    text = re.sub(r'https?:\/\/.*[\r\n]*', '',
                  text, flags=re.MULTILINE | re.UNICODE)
    text = re.sub(r'[#|*|\[\]:.,]', '', text, flags=re.UNICODE)
    text = re.sub(r'[!"#$%&\'()*+,-./:;<=>[email protected]\[\\\]^_`{|}~]', '', text)
    text = re.sub(r'\d*', '', text)
    text = text.lower()
    text = re.sub(r'[\W]+', ' ', text.lower(), flags=re.UNICODE)

    return text 

def _compile(expr):
    return re.compile(expr, re.UNICODE)

# Note that since _all_string_prefixes includes the empty string,
#  StringPrefix can be the empty string (making it optional). 

def __init__(self):
        #load affix information
        # pass
        self.prefix_letters = stem_const.DEFAULT_PREFIX_LETTERS
        self.suffix_letters = stem_const.DEFAULT_SUFFIX_LETTERS
        self.infix_letters = stem_const.DEFAULT_INFIX_LETTERS
        self.max_prefix_length = stem_const.DEFAULT_MAX_PREFIX
        self.max_suffix_length = stem_const.DEFAULT_MAX_SUFFIX
        self.min_stem_length = stem_const.DEFAULT_MIN_STEM
        self.joker = stem_const.DEFAULT_JOKER
        self.prefix_list = stem_const.DEFAULT_PREFIX_LIST
        self.suffix_list = stem_const.DEFAULT_SUFFIX_LIST
        self.word = u""
        self.unvocalized = u""
        self.normalized = u""
        self.starword = u""
        self.root = u""
        self.left = 0
        self.right = 0
        self.segment_list = []
        #token pattern
        # letters and harakat
        self.token_pat = re.compile(r"[^\w\u064b-\u0652']+", re.UNICODE)
        self.prefixes_tree = self._create_prefix_tree(self.prefix_list)
        self.suffixes_tree = self._create_suffix_tree(self.suffix_list)
    ######################################################################
    #{ Attribut Functions
    ###################################################################### 

def compile(self, rules):
        mapping = {}
        patterns = []
        for rule in rules:
            name = 'rule_{id}'.format(id=id(rule))
            pattern = r'(?P<{name}>{pattern})'.format(
                name=name,
                pattern=rule.pattern
            )
            mapping[name] = rule
            patterns.append(pattern)

        pattern = '|'.join(patterns)
        regexp = re.compile(pattern, re.UNICODE | re.IGNORECASE)
        return regexp, mapping 

def from_native(cls, regex):
        """Convert a Python regular expression into a ``Regex`` instance.

        Note that in Python 3, a regular expression compiled from a
        :class:`str` has the ``re.UNICODE`` flag set. If it is undesirable
        to store this flag in a BSON regular expression, unset it first::

          >>> pattern = re.compile('.*')
          >>> regex = Regex.from_native(pattern)
          >>> regex.flags ^= re.UNICODE
          >>> db.collection.insert({'pattern': regex})

        :Parameters:
          - `regex`: A regular expression object from ``re.compile()``.

        .. warning::
           Python regular expressions use a different syntax and different
           set of flags than MongoDB, which uses `PCRE`_. A regular
           expression retrieved from the server may not compile in
           Python, or may match a different set of strings in Python than
           when used in a MongoDB query.

        .. _PCRE: http://www.pcre.org/
        """
        if not isinstance(regex, RE_TYPE):
            raise TypeError(
                "regex must be a compiled regular expression, not %s"
                % type(regex))

        return Regex(regex.pattern, regex.flags) 

def __init__(self, length=None, **kw):
        """Construct a TEXT.

        :param length: Optional, if provided the server may optimize storage
          by substituting the smallest TEXT type sufficient to store
          ``length`` characters.

        :param charset: Optional, a column-level character set for this string
          value.  Takes precedence to 'ascii' or 'unicode' short-hand.

        :param collation: Optional, a column-level collation for this string
          value.  Takes precedence to 'binary' short-hand.

        :param ascii: Defaults to False: short-hand for the ``latin1``
          character set, generates ASCII in schema.

        :param unicode: Defaults to False: short-hand for the ``ucs2``
          character set, generates UNICODE in schema.

        :param national: Optional. If true, use the server's configured
          national character set.

        :param binary: Defaults to False: short-hand, pick the binary
          collation type that matches the column's character set.  Generates
          BINARY in schema.  This does not affect the type of data stored,
          only the collation of character data.

        """
        super(TEXT, self).__init__(length=length, **kw)