Python re.ASCII Examples

def test_ascii_and_unicode_flag(self):
        # String patterns
        for flags in (0, re.UNICODE):
            pat = re.compile('\xc0', flags | re.IGNORECASE)
            self.assertNotEqual(pat.match('\xe0'), None)
            pat = re.compile('\w', flags)
            self.assertNotEqual(pat.match('\xe0'), None)
        pat = re.compile('\xc0', re.ASCII | re.IGNORECASE)
        self.assertEqual(pat.match('\xe0'), None)
        pat = re.compile('(?a)\xc0', re.IGNORECASE)
        self.assertEqual(pat.match('\xe0'), None)
        pat = re.compile('\w', re.ASCII)
        self.assertEqual(pat.match('\xe0'), None)
        pat = re.compile('(?a)\w')
        self.assertEqual(pat.match('\xe0'), None)
        # Bytes patterns
        for flags in (0, re.ASCII):
            pat = re.compile(b'\xc0', re.IGNORECASE)
            self.assertEqual(pat.match(b'\xe0'), None)
            pat = re.compile(b'\w')
            self.assertEqual(pat.match(b'\xe0'), None)
        # Incompatibilities
        self.assertRaises(ValueError, re.compile, b'\w', re.UNICODE)
        self.assertRaises(ValueError, re.compile, b'(?u)\w')
        self.assertRaises(ValueError, re.compile, '\w', re.UNICODE | re.ASCII)
        self.assertRaises(ValueError, re.compile, '(?u)\w', re.ASCII)
        self.assertRaises(ValueError, re.compile, '(?a)\w', re.UNICODE)
        self.assertRaises(ValueError, re.compile, '(?au)\w') 

def unquote(s):
    """Turn a string in the form =AB to the ASCII character with value 0xab"""
    return chr(int(s[1:3], 16)) 

def _unquote_match(match):
    """Turn a match in the form =AB to the ASCII character with value 0xab"""
    s = match.group(0)
    return unquote(s)


# Header decoding is done a bit differently 

def formataddr(pair, charset='utf-8'):
    """The inverse of parseaddr(), this takes a 2-tuple of the form
    (realname, email_address) and returns the string value suitable
    for an RFC 2822 From, To or Cc header.

    If the first element of pair is false, then the second element is
    returned unmodified.

    Optional charset if given is the character set that is used to encode
    realname in case realname is not ASCII safe.  Can be an instance of str or
    a Charset-like object which has a header_encode method.  Default is
    'utf-8'.
    """
    name, address = pair
    # The address MUST (per RFC) be ascii, so raise an UnicodeError if it isn't.
    address.encode('ascii')
    if name:
        try:
            name.encode('ascii')
        except UnicodeEncodeError:
            if isinstance(charset, str):
                charset = Charset(charset)
            encoded_name = charset.header_encode(name)
            return "%s <%s>" % (encoded_name, address)
        else:
            quotes = ''
            if specialsre.search(name):
                quotes = '"'
            name = escapesre.sub(r'\\\g<0>', name)
            return '%s%s%s <%s>' % (quotes, name, quotes, address)
    return address 

def open_data(self, url, data=None):
        """Use "data" URL."""
        if not isinstance(url, str):
            raise URLError('data error: proxy support for data protocol currently not implemented')
        # ignore POSTed data
        #
        # syntax of data URLs:
        # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
        # mediatype := [ type "/" subtype ] *( ";" parameter )
        # data      := *urlchar
        # parameter := attribute "=" value
        try:
            [type, data] = url.split(',', 1)
        except ValueError:
            raise IOError('data error', 'bad data URL')
        if not type:
            type = 'text/plain;charset=US-ASCII'
        semi = type.rfind(';')
        if semi >= 0 and '=' not in type[semi:]:
            encoding = type[semi+1:]
            type = type[:semi]
        else:
            encoding = ''
        msg = []
        msg.append('Date: %s'%time.strftime('%a, %d %b %Y %H:%M:%S GMT',
                                            time.gmtime(time.time())))
        msg.append('Content-type: %s' % type)
        if encoding == 'base64':
            # XXX is this encoding/decoding ok?
            data = base64.decodebytes(data.encode('ascii')).decode('latin-1')
        else:
            data = unquote(data)
        msg.append('Content-Length: %d' % len(data))
        msg.append('')
        msg.append(data)
        msg = '\n'.join(msg)
        headers = email.message_from_string(msg)
        f = io.StringIO(msg)
        #f.fileno = None     # needed for addinfourl
        return addinfourl(f, headers, url) 

def unquote(s):
    """Turn a string in the form =AB to the ASCII character with value 0xab"""
    return chr(int(s[1:3], 16)) 

def _unquote_match(match):
    """Turn a match in the form =AB to the ASCII character with value 0xab"""
    s = match.group(0)
    return unquote(s)


# Header decoding is done a bit differently 

def formataddr(pair, charset='utf-8'):
    """The inverse of parseaddr(), this takes a 2-tuple of the form
    (realname, email_address) and returns the string value suitable
    for an RFC 2822 From, To or Cc header.

    If the first element of pair is false, then the second element is
    returned unmodified.

    Optional charset if given is the character set that is used to encode
    realname in case realname is not ASCII safe.  Can be an instance of str or
    a Charset-like object which has a header_encode method.  Default is
    'utf-8'.
    """
    name, address = pair
    # The address MUST (per RFC) be ascii, so raise an UnicodeError if it isn't.
    address.encode('ascii')
    if name:
        try:
            name.encode('ascii')
        except UnicodeEncodeError:
            if isinstance(charset, str):
                charset = Charset(charset)
            encoded_name = charset.header_encode(name)
            return "%s <%s>" % (encoded_name, address)
        else:
            quotes = ''
            if specialsre.search(name):
                quotes = '"'
            name = escapesre.sub(r'\\\g<0>', name)
            return '%s%s%s <%s>' % (quotes, name, quotes, address)
    return address 

def open_data(self, url, data=None):
        """Use "data" URL."""
        if not isinstance(url, str):
            raise URLError('data error: proxy support for data protocol currently not implemented')
        # ignore POSTed data
        #
        # syntax of data URLs:
        # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
        # mediatype := [ type "/" subtype ] *( ";" parameter )
        # data      := *urlchar
        # parameter := attribute "=" value
        try:
            [type, data] = url.split(',', 1)
        except ValueError:
            raise IOError('data error', 'bad data URL')
        if not type:
            type = 'text/plain;charset=US-ASCII'
        semi = type.rfind(';')
        if semi >= 0 and '=' not in type[semi:]:
            encoding = type[semi+1:]
            type = type[:semi]
        else:
            encoding = ''
        msg = []
        msg.append('Date: %s'%time.strftime('%a, %d %b %Y %H:%M:%S GMT',
                                            time.gmtime(time.time())))
        msg.append('Content-type: %s' % type)
        if encoding == 'base64':
            # XXX is this encoding/decoding ok?
            data = base64.decodebytes(data.encode('ascii')).decode('latin-1')
        else:
            data = unquote(data)
        msg.append('Content-Length: %d' % len(data))
        msg.append('')
        msg.append(data)
        msg = '\n'.join(msg)
        headers = email.message_from_string(msg)
        f = io.StringIO(msg)
        #f.fileno = None     # needed for addinfourl
        return addinfourl(f, headers, url) 

def open_data(self, url, data=None):
        """Use "data" URL."""
        if not isinstance(url, str):
            raise URLError('data error: proxy support for data protocol currently not implemented')
        # ignore POSTed data
        #
        # syntax of data URLs:
        # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
        # mediatype := [ type "/" subtype ] *( ";" parameter )
        # data      := *urlchar
        # parameter := attribute "=" value
        try:
            [type, data] = url.split(',', 1)
        except ValueError:
            raise IOError('data error', 'bad data URL')
        if not type:
            type = 'text/plain;charset=US-ASCII'
        semi = type.rfind(';')
        if semi >= 0 and '=' not in type[semi:]:
            encoding = type[semi+1:]
            type = type[:semi]
        else:
            encoding = ''
        msg = []
        msg.append('Date: %s'%time.strftime('%a, %d %b %Y %H:%M:%S GMT',
                                            time.gmtime(time.time())))
        msg.append('Content-type: %s' % type)
        if encoding == 'base64':
            # XXX is this encoding/decoding ok?
            data = base64.decodebytes(data.encode('ascii')).decode('latin-1')
        else:
            data = unquote(data)
        msg.append('Content-Length: %d' % len(data))
        msg.append('')
        msg.append(data)
        msg = '\n'.join(msg)
        headers = email.message_from_string(msg)
        f = io.StringIO(msg)
        #f.fileno = None     # needed for addinfourl
        return addinfourl(f, headers, url) 

def __init__(self, parent, name=None, callback=None, cb_arg=None, cb_self=False):
        self.parent = parent
        self.name = name
        self.callback = callback               # Function called to process result
        if not cb_self:
            self.callback_arg = cb_arg         # Optional arg passed to "callback"
        else:
            self.callback_arg = (self, cb_arg) # Self reference required in callback arg

        self.tag = parent.tagpre + bytes(str(parent.tagnum), 'ASCII')
        parent.tagnum += 1

        self.ready = threading.Event()
        self.response = None
        self.aborted = None
        self.data = None 

def append(self, mailbox, flags, date_time, message, **kw):
        """(typ, [data]) = append(mailbox, flags, date_time, message)
        Append message to named mailbox.
        All args except `message' can be None."""

        name = 'APPEND'
        if not mailbox:
            mailbox = 'INBOX'
        if flags:
            if (flags[0],flags[-1]) != ('(',')'):
                flags = '(%s)' % flags
        else:
            flags = None
        if date_time:
            date_time = Time2Internaldate(date_time)
        else:
            date_time = None
        if isinstance(message, str):
            message = bytes(message, 'ASCII')
        self.literal = self.mapCRLF_cre.sub(CRLF, message)
        try:
            return self._simple_command(name, mailbox, flags, date_time, **kw)
        finally:
            self._release_state_change() 

def _command_completer(self, cb_arg_list):

        # Called for callback commands
        response, cb_arg, error = cb_arg_list
        rqb, kw = cb_arg
        rqb.callback = kw['callback']
        rqb.callback_arg = kw.get('cb_arg')
        if error is not None:
            if __debug__: self._print_log()
            typ, val = error
            rqb.abort(typ, val)
            return
        bye = self._get_untagged_response('BYE', leave=True)
        if bye:
            rqb.abort(self.abort, bye[-1].decode('ASCII', 'replace'))
            return
        typ, dat = response
        if typ == 'BAD':
            if __debug__: self._print_log()
            rqb.abort(self.error, '%s command error: %s %s. Data: %.100s' % (rqb.name, typ, dat, rqb.data))
            return
        if __debug__: self._log(4, '_command_completer(%s, %s, None) = %s' % (response, cb_arg, rqb.tag))
        if 'untagged_response' in kw:
            response = self._untagged_response(typ, dat, kw['untagged_response'])
        rqb.deliver(response) 

def encode(self, inp):
        #
        #  Invoke binascii.b2a_base64 iteratively with
        #  short even length buffers, strip the trailing
        #  line feed from the result and append.  "Even"
        #  means a number that factors to both 6 and 8,
        #  so when it gets to the end of the 8-bit input
        #  there's no partial 6-bit output.
        #
        oup = b''
        if isinstance(inp, str):
            inp = inp.encode('ASCII')
        while inp:
            if len(inp) > 48:
                t = inp[:48]
                inp = inp[48:]
            else:
                t = inp
                inp = b''
            e = binascii.b2a_base64(t)
            if e:
                oup = oup + e[:-1]
        return oup 

def parse150(resp):
    '''Parse the '150' response for a RETR request.
    Returns the expected transfer size or None; size is not guaranteed to
    be present in the 150 message.
    '''
    if resp[:3] != '150':
        raise error_reply(resp)
    global _150_re
    if _150_re is None:
        import re
        _150_re = re.compile(
            "150 .* \((\d+) bytes\)", re.IGNORECASE | re.ASCII)
    m = _150_re.match(resp)
    if not m:
        return None
    return int(m.group(1)) 

def parse227(resp):
    '''Parse the '227' response for a PASV request.
    Raises error_proto if it does not contain '(h1,h2,h3,h4,p1,p2)'
    Return ('host.addr.as.numbers', port#) tuple.'''

    if resp[:3] != '227':
        raise error_reply(resp)
    global _227_re
    if _227_re is None:
        import re
        _227_re = re.compile(r'(\d+),(\d+),(\d+),(\d+),(\d+),(\d+)', re.ASCII)
    m = _227_re.search(resp)
    if not m:
        raise error_proto(resp)
    numbers = m.groups()
    host = '.'.join(numbers[:4])
    port = (int(numbers[4]) << 8) + int(numbers[5])
    return host, port 

def split_provision(value):
    """Return the name and optional version number of a provision.

    The version number, if given, will be returned as a `StrictVersion`
    instance, otherwise it will be `None`.

    >>> split_provision('mypkg')
    ('mypkg', None)
    >>> split_provision(' mypkg( 1.2 ) ')
    ('mypkg', StrictVersion ('1.2'))
    """
    global _provision_rx
    if _provision_rx is None:
        _provision_rx = re.compile(
            "([a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*)(?:\s*\(\s*([^)\s]+)\s*\))?$",
            re.ASCII)
    value = value.strip()
    m = _provision_rx.match(value)
    if not m:
        raise ValueError("illegal provides specification: %r" % value)
    ver = m.group(2) or None
    if ver:
        ver = distutils.version.StrictVersion(ver)
    return m.group(1), ver 

def test_bug_16688(self):
        # Issue 16688: Backreferences make case-insensitive regex fail on
        # non-ASCII strings.
        self.assertEqual(re.findall(r"(?i)(a)\1", "aa \u0100"), ['a'])
        self.assertEqual(re.match(r"(?s).{1,3}", "\u0100\u0100").span(), (0, 2)) 

def expanduser(path):
    """Expand ~ and ~user constructions.  If user or $HOME is unknown,
    do nothing."""
    if isinstance(path, bytes):
        tilde = b'~'
    else:
        tilde = '~'
    if not path.startswith(tilde):
        return path
    sep = _get_sep(path)
    i = path.find(sep, 1)
    if i < 0:
        i = len(path)
    if i == 1:
        if 'HOME' not in os.environ:
            import pwd
            userhome = pwd.getpwuid(os.getuid()).pw_dir
        else:
            userhome = os.environ['HOME']
    else:
        import pwd
        name = path[1:i]
        if isinstance(name, bytes):
            name = str(name, 'ASCII')
        try:
            pwent = pwd.getpwnam(name)
        except KeyError:
            return path
        userhome = pwent.pw_dir
    if isinstance(path, bytes):
        userhome = os.fsencode(userhome)
        root = b'/'
    else:
        root = '/'
    userhome = userhome.rstrip(root)
    return (userhome + path[i:]) or root


# Expand paths containing shell variable substitutions.
# This expands the forms $variable and ${variable} only.
# Non-existent variables are left unchanged. 

def header_decode(s):
    """Decode a string encoded with RFC 2045 MIME header `Q' encoding.

    This function does not parse a full MIME header value encoded with
    quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use
    the high level email.header class for that functionality.
    """
    s = s.replace('_', ' ')
    return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s, re.ASCII) 

def header_decode(s):
    """Decode a string encoded with RFC 2045 MIME header `Q' encoding.

    This function does not parse a full MIME header value encoded with
    quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use
    the high level email.header class for that functionality.
    """
    s = s.replace('_', ' ')
    return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s, re.ASCII) 

def unquote(s):
    """Turn a string in the form =AB to the ASCII character with value 0xab"""
    return chr(int(s[1:3], 16)) 

def _unquote_match(match):
    """Turn a match in the form =AB to the ASCII character with value 0xab"""
    s = match.group(0)
    return unquote(s)


# Header decoding is done a bit differently 

def header_decode(s):
    """Decode a string encoded with RFC 2045 MIME header `Q' encoding.

    This function does not parse a full MIME header value encoded with
    quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use
    the high level email.header class for that functionality.
    """
    s = s.replace('_', ' ')
    return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s, re.ASCII) 

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("sslscan_binary")
    parser.add_argument("output_file")
    args = parser.parse_args()

    with open("config/meta.json", "r", encoding="utf-8") as fp:
        meta = json.load(fp)
    domains = []
    for listing in meta["listings"]:
        if "external" in listing:
            continue
        with open("config/{}.json".format(listing["shortname"]), encoding="utf-8") as fp:
            listing["data"] = json.load(fp)
        for cat in listing["data"]["categories"]:
            for site in cat["sites"]:
                domains.append(site["domain"])

    p = subprocess.Popen([args.sslscan_binary, "--grade", "--usecache"] + domains, stdout=subprocess.PIPE)
    stdout = p.communicate()[0].decode("ascii").strip()
    results = {}
    r = re.compile("\"(.+)\": \"(.+)\"", re.ASCII)
    for l in stdout.splitlines():
        m = r.match(l)
        g = m.groups()
        results[g[0]] = g[1]

    with open(args.output_file, "w", encoding="utf-8") as fp:
        json.dump(results, fp) 

def canonicalize_color(color: str) -> str:
    """
    Given a color of the format '#xxxxxx' or '#xxx', produces one of the
    format '#xxx'. Always produces lowercase hex digits.
    """
    if match('^#[0-9A-Fa-f]{6}$', color, ASCII) is not None:
        # '#xxxxxx' color, stored by current zulip server
        return (color[:2] + color[3] + color[5]).lower()
    elif match('^#[0-9A-Fa-f]{3}$', color, ASCII) is not None:
        # '#xxx' color, which may be stored by the zulip server <= 2.0.0
        # Potentially later versions too
        return color.lower()
    else:
        raise ValueError('Unknown format for color "{}"'.format(color)) 

def expanduser(path):
    """Expand ~ and ~user constructions.  If user or $HOME is unknown,
    do nothing."""
    if isinstance(path, bytes):
        tilde = b'~'
    else:
        tilde = '~'
    if not path.startswith(tilde):
        return path
    sep = _get_sep(path)
    i = path.find(sep, 1)
    if i < 0:
        i = len(path)
    if i == 1:
        if 'HOME' not in os.environ:
            import pwd
            userhome = pwd.getpwuid(os.getuid()).pw_dir
        else:
            userhome = os.environ['HOME']
    else:
        import pwd
        name = path[1:i]
        if isinstance(name, bytes):
            name = str(name, 'ASCII')
        try:
            pwent = pwd.getpwnam(name)
        except KeyError:
            return path
        userhome = pwent.pw_dir
    if isinstance(path, bytes):
        userhome = os.fsencode(userhome)
        root = b'/'
    else:
        root = '/'
    userhome = userhome.rstrip(root)
    return (userhome + path[i:]) or root


# Expand paths containing shell variable substitutions.
# This expands the forms $variable and ${variable} only.
# Non-existent variables are left unchanged. 

def test_normal(self, value, expected):
        flags = 0
        flags = re.ASCII

        assert re.search(r"\w+_index_\w{4}", make_index_name(value, value), flags) 

def unquote(s):
    """Turn a string in the form =AB to the ASCII character with value 0xab"""
    return chr(int(s[1:3], 16)) 

def _unquote_match(match):
    """Turn a match in the form =AB to the ASCII character with value 0xab"""
    s = match.group(0)
    return unquote(s)


# Header decoding is done a bit differently