Python regex.DOTALL Examples

The following are 3 code examples of regex.DOTALL(). 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 regex , or try the search function .
Example #1
Source File: utils.py    From chepy with GNU General Public License v3.0 5 votes vote down vote up 
def regex_search(
        self,
        pattern: str,
        ignore_case: bool = False,
        multiline: bool = False,
        dotall: bool = False,
        unicode: bool = False,
        extended: bool = False,
    ):
        """Regex search on current data
        
        Args:
            pattern (str): Required. The regex pattern to search by
            ignore_case (bool, optional): Set case insentive flag. Defaults to False.
            multiline (bool, optional): ^/$ match start/end. Defaults to False.
            dotall (bool, optional): `.` matches newline. Defaults to False.
            unicode (bool, optional): Match unicode characters. Defaults to False.
            extended (bool, optional): Ignore whitespace. Defaults to False.
        
        Returns:
            Chepy: The Chepy object.

        Examples:
            >>> c = Chepy("loLolololoL")
            >>> c.regex_search("ol", ignore_case=True)
        """
        flags = 0
        if ignore_case:
            flags += re.IGNORECASE
        if multiline:
            flags += re.MULTILINE
        if dotall:
            flags += re.DOTALL
        if unicode:
            flags += re.UNICODE
        if extended:
            flags += re.X
        self.state = re.findall(pattern, self._convert_to_str(), flags=flags)
        return self
Example #2
Source File: parsed_text_corrector.py    From lexpredict-contraxsuite with GNU Affero General Public License v3.0 5 votes vote down vote up 
def setup_parser():
        from lexnlp.extract.en.amounts import CURRENCY_SYMBOL_MAP
        symbols = '|'.join([k for k in CURRENCY_SYMBOL_MAP]).replace('$', r'\$')
        ParsedTextCorrector.PATTERN_MONEY_BREAK = ParsedTextCorrector.PATTERN_MONEY_BREAK.format(symbols=symbols)
        ParsedTextCorrector.REGEX_MONEY_BREAK = re.compile(
            ParsedTextCorrector.PATTERN_MONEY_BREAK,
            re.IGNORECASE | re.DOTALL | re.MULTILINE | re.VERBOSE | re.UNICODE)
Example #3
Source File: DataRecognizer.py    From pcapfex with Apache License 2.0 5 votes vote down vote up 
def _buildRegexPatterns(cls):
        regexstr = b''
        for (fileHeader, fileTrailer) in cls.signatures:   
            if fileTrailer is None:
                regexstr += b'(%s.*)|' % (fileHeader,)
            else:
                regexstr += b'(%s.*?%s)|' % (fileHeader, fileTrailer)
       
        cls._regex = re.compile(regexstr[:-1], re.DOTALL)