Python re.UNICODE属性代码示例

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def __parse_domain_to_employer_line(self, raw_domain, raw_org):
        """Parse domain to employer lines"""

        d = re.match(self.DOMAIN_REGEX, raw_domain, re.UNICODE)
        if not d:
            cause = "invalid domain format: '%s'" % raw_domain
            raise InvalidFormatError(cause=cause)

        dom = d.group('domain').strip()

        o = re.match(self.ORGANIZATION_REGEX, raw_org, re.UNICODE)
        if not o:
            cause = "invalid organization format: '%s'" % raw_org
            raise InvalidFormatError(cause=cause)

        org = o.group('organization').strip()

        org = self.__encode(org)
        dom = self.__encode(dom)

        return org, dom 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def unmarshal (self, filename):
        """
        Unmarshals (loads from a plain text file) the tagger model. For
        safety, this operation is intended to be performed only on
        newly created taggers (i.e., without any previous model).
       
        @param filename: Name of the file from which the model will
                         be read.
        @type filename: C{string}
        """
        handler = file(filename, "r")
        
        pattern = re.compile(r'^(.+):(.+?)$', re.UNICODE)
        for line in handler.readlines():
            m = re.match(pattern, line)
            text, tag = m.groups()
            self._model[text] = tag
        
        handler.close() 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def render_re(regex):
  """Renders a repr()-style value for a compiled regular expression."""
  actual_flags = []
  if regex.flags:
    flags = [
      (re.IGNORECASE, 'IGNORECASE'),
      (re.LOCALE, 'LOCALE'),
      (re.UNICODE, 'UNICODE'),
      (re.MULTILINE, 'MULTILINE'),
      (re.DOTALL, 'DOTALL'),
      (re.VERBOSE, 'VERBOSE'),
    ]
    for val, name in flags:
      if regex.flags & val:
        actual_flags.append(name)
  if actual_flags:
    return 're.compile(%r, %s)' % (regex.pattern, '|'.join(actual_flags))
  else:
    return 're.compile(%r)' % regex.pattern 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
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 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
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) 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
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) 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def __init__(self, export_comments=None):
        if export_comments is not None:
            if export_comments == 'LINE':
                self.can_export_comments = ['COMMENT']
            elif export_comments == 'MULTILINE':
                self.can_export_comments = ['MULTICOMMENT']
            elif export_comments == 'ALL':
                self.can_export_comments = ['COMMENT', 'MULTICOMMENT']
            else:
                raise ValueError(
                    'Only `LINE`, `MULTILINE` and `ALL` value are allowed for '
                    '`export_comments`. given: `%s`.' % export_comments
                )

        self.lex = lex.lex(
            module=self,
            debug=False,
            reflags=(re.UNICODE | re.MULTILINE),
            errorlog=lex.NullLogger(),
        ) 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
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] 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
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 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def test_bug_6561(self):
        # '\d' should match characters in Unicode category 'Nd'
        # (Number, Decimal Digit), but not those in 'Nl' (Number,
        # Letter) or 'No' (Number, Other).
        decimal_digits = [
            unichr(0x0037), # '\N{DIGIT SEVEN}', category 'Nd'
            unichr(0x0e58), # '\N{THAI DIGIT SIX}', category 'Nd'
            unichr(0xff10), # '\N{FULLWIDTH DIGIT ZERO}', category 'Nd'
            ]
        for x in decimal_digits:
            self.assertEqual(re.match('^\d$', x, re.UNICODE).group(0), x)

        not_decimal_digits = [
            unichr(0x2165), # '\N{ROMAN NUMERAL SIX}', category 'Nl'
            unichr(0x3039), # '\N{HANGZHOU NUMERAL TWENTY}', category 'Nl'
            unichr(0x2082), # '\N{SUBSCRIPT TWO}', category 'No'
            unichr(0x32b4), # '\N{CIRCLED NUMBER THIRTY NINE}', category 'No'
            ]
        for x in not_decimal_digits:
            self.assertIsNone(re.match('^\d$', x, re.UNICODE)) 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def match_nickname_content(self, content: str) -> Tuple[str, str]:
        m = re.match(
            r'^\[(?P<nick>.+?)\] (?P<content>.*)',
            content, flags=re.UNICODE
        )
        return (m.group('nick'), m.group('content')) if m else (None, None) 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def try_set_nick(self, msg):
        # handle command
        user_id = msg.user.id
        target = "%d" % msg.chat_id
        try:
            tmp = msg.content.split()
            cmd = tmp[0][1:].lower()
            args = tmp[1:]
        except:
            return

        if cmd == "nick":
            if len(args) == 1:
                nick = args[0]
                if not re.match(r'^\w', nick, flags=re.UNICODE):
                    self.send_msg(target, "Use a human's nick name, please.")
                    return True
                self.nick_store.set_nickname(user_id, nick)
                content = "Changed nickname to '%s'" % nick
                logger.debug(target, content)
                self.send_msg(target, content)
            else:
                self.send_msg(
                    target,
                    "Invalid Command, use '/nick nickname'"
                    "to change nickname."
                )
            return True 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def __parse_stream(self, stream):
        """Generic method to parse mailmap streams"""

        nline = 0
        lines = stream.split('\n')

        for line in lines:
            nline += 1

            # Ignore blank lines and comments
            m = re.match(self.LINES_TO_IGNORE_REGEX, line, re.UNICODE)
            if m:
                continue

            line = line.strip('\n').strip(' ')
            parts = line.split('>')

            if len(parts) == 0:
                cause = "line %s: invalid format" % str(nline)
                raise InvalidFormatError(cause=cause)

            aliases = []

            for part in parts:
                part = part.replace(',', ' ')
                part = part.strip('\n').strip(' ')

                if len(part) == 0:
                    continue

                if part.find('<') < 0:
                    cause = "line %s: invalid format" % str(nline)
                    raise InvalidFormatError(cause=cause)

                alias = email.utils.parseaddr(part + '>')
                aliases.append(alias)

            yield aliases 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def __validate_email(self, email):
        """Checks if a string looks like an email address"""

        e = re.match(self.EMAIL_ADDRESS_REGEX, email, re.UNICODE)
        if e:
            return email
        else:
            error = "Invalid email address: " + str(email)
            msg = self.GRIMOIRELAB_INVALID_FORMAT % {'error': error}
            raise InvalidFormatError(cause=msg) 

# 需要导入模块: import re [as 别名]
# 或者: from re import UNICODE [as 别名]
def __parse_stream(self, stream, parse_line):
        """Generic method to parse gitdm streams"""

        if not stream:
            raise InvalidFormatError(cause='stream cannot be empty or None')

        nline = 0
        lines = stream.split('\n')

        for line in lines:
            nline += 1

            # Ignore blank lines and comments
            m = re.match(self.LINES_TO_IGNORE_REGEX, line, re.UNICODE)
            if m:
                continue

            m = re.match(self.VALID_LINE_REGEX, line, re.UNICODE)
            if not m:
                cause = "line %s: invalid format" % str(nline)
                raise InvalidFormatError(cause=cause)

            try:
                result = parse_line(m.group(1), m.group(2))
                yield result
            except InvalidFormatError as e:
                cause = "line %s: %s" % (str(nline), e)
                raise InvalidFormatError(cause=cause)