Python re.ASCII Examples

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 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 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 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 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 __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 _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 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 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 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 encode(self, chars):
        if isinstance(chars, bytes):
            # This is either plain ASCII, or Tk was returning mixed-encoding
            # text to us. Don't try to guess further.
            return chars
        # Preserve a BOM that might have been present on opening
        if self.fileencoding == 'BOM':
            return BOM_UTF8 + chars.encode("utf-8")
        # See whether there is anything non-ASCII in it.
        # If not, no need to figure out the encoding.
        try:
            return chars.encode('ascii')
        except UnicodeError:
            pass
        # Check if there is an encoding declared
        try:
            # a string, let coding_spec slice it to the first two lines
            enc = coding_spec(chars)
            failed = None
        except LookupError as msg:
            failed = msg
            enc = None
        else:
            if not enc:
                # PEP 3120: default source encoding is UTF-8
                enc = 'utf-8'
        if enc:
            try:
                return chars.encode(enc)
            except UnicodeError:
                failed = "Invalid encoding '%s'" % enc
        tkMessageBox.showerror(
            "I/O Error",
            "%s.\nSaving as UTF-8" % failed,
            parent = self.text)
        # Fallback: save as UTF-8, with BOM - ignoring the incorrect
        # declared encoding
        return BOM_UTF8 + chars.encode("utf-8") 

def _connect(self):
        # Create unique tag for this session,
        # and compile tagged response matcher.

        self.tagpre = Int2AP(random.randint(4096, 65535))
        self.tagre = re.compile(br'(?P<tag>'
                        + self.tagpre
                        + br'\d+) (?P<type>[A-Z]+) (?P<data>.*)', re.ASCII)

        # Get server welcome message,
        # request and store CAPABILITY response.

        if __debug__:
            self._cmd_log_len = 10
            self._cmd_log_idx = 0
            self._cmd_log = {}           # Last `_cmd_log_len' interactions
            if self.debug >= 1:
                self._mesg('imaplib version %s' % __version__)
                self._mesg('new IMAP4 connection, tag=%s' % self.tagpre)

        self.welcome = self._get_response()
        if 'PREAUTH' in self.untagged_responses:
            self.state = 'AUTH'
        elif 'OK' in self.untagged_responses:
            self.state = 'NONAUTH'
        else:
            raise self.error(self.welcome)

        self._get_capabilities()
        if __debug__:
            if self.debug >= 3:
                self._mesg('CAPABILITIES: %r' % (self.capabilities,))

        for version in AllowedVersions:
            if not version in self.capabilities:
                continue
            self.PROTOCOL_VERSION = version
            return

        raise self.error('server not IMAP4 compliant') 

def _check_bye(self):

        bye = self._get_untagged_response('BYE', leave=True)
        if bye:
            raise self.abort(bye[-1].decode('ASCII', 'replace')) 

def coding_spec(data):
    """Return the encoding declaration according to PEP 263.

    When checking encoded data, only the first two lines should be passed
    in to avoid a UnicodeDecodeError if the rest of the data is not unicode.
    The first two lines would contain the encoding specification.

    Raise a LookupError if the encoding is declared but unknown.
    """
    if isinstance(data, bytes):
        # This encoding might be wrong. However, the coding
        # spec must be ASCII-only, so any non-ASCII characters
        # around here will be ignored. Decoding to Latin-1 should
        # never fail (except for memory outage)
        lines = data.decode('iso-8859-1')
    else:
        lines = data
    # consider only the first two lines
    if '\n' in lines:
        lst = lines.split('\n', 2)[:2]
    elif '\r' in lines:
        lst = lines.split('\r', 2)[:2]
    else:
        lst = [lines]
    for line in lst:
        match = coding_re.match(line)
        if match is not None:
            break
        if not blank_re.match(line):
            return None
    else:
        return None
    name = match.group(1)
    try:
        codecs.lookup(name)
    except LookupError:
        # The standard encoding error does not indicate the encoding
        raise LookupError("Unknown encoding: "+name)
    return name 

def _get_capabilities(self):
        typ, dat = self.capability()
        if dat == [None]:
            raise self.error('no CAPABILITY response from server')
        dat = str(dat[-1], "ASCII")
        dat = dat.upper()
        self.capabilities = tuple(dat.split()) 

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 OSError('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 is_valid_identifier(var, allow_unicode=False):
    """Return true if var contains a valid Python identifier

    Parameters
    ----------
    val : string
        identifier to check
    allow_unicode : bool (default: False)
        if True, then allow Python 3 style unicode identifiers.
    """
    flags = re.UNICODE if allow_unicode else re.ASCII
    is_valid = re.match(r"^[^\d\W]\w*\Z", var, flags)
    return is_valid and not keyword.iskeyword(var) 

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 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 test_special_escapes(self):
        self.assertEqual(re.search(r"\b(b.)\b",
                                   "abcd abc bcd bx").group(1), "bx")
        self.assertEqual(re.search(r"\B(b.)\B",
                                   "abc bcd bc abxd").group(1), "bx")
        self.assertEqual(re.search(r"\b(b.)\b",
                                   "abcd abc bcd bx", re.ASCII).group(1), "bx")
        self.assertEqual(re.search(r"\B(b.)\B",
                                   "abc bcd bc abxd", re.ASCII).group(1), "bx")
        self.assertEqual(re.search(r"^abc$", "\nabc\n", re.M).group(0), "abc")
        self.assertEqual(re.search(r"^\Aabc\Z$", "abc", re.M).group(0), "abc")
        self.assertIsNone(re.search(r"^\Aabc\Z$", "\nabc\n", re.M))
        self.assertEqual(re.search(br"\b(b.)\b",
                                   b"abcd abc bcd bx").group(1), b"bx")
        self.assertEqual(re.search(br"\B(b.)\B",
                                   b"abc bcd bc abxd").group(1), b"bx")
        self.assertEqual(re.search(br"\b(b.)\b",
                                   b"abcd abc bcd bx", re.LOCALE).group(1), b"bx")
        self.assertEqual(re.search(br"\B(b.)\B",
                                   b"abc bcd bc abxd", re.LOCALE).group(1), b"bx")
        self.assertEqual(re.search(br"^abc$", b"\nabc\n", re.M).group(0), b"abc")
        self.assertEqual(re.search(br"^\Aabc\Z$", b"abc", re.M).group(0), b"abc")
        self.assertIsNone(re.search(br"^\Aabc\Z$", b"\nabc\n", re.M))
        self.assertEqual(re.search(r"\d\D\w\W\s\S",
                                   "1aa! a").group(0), "1aa! a")
        self.assertEqual(re.search(br"\d\D\w\W\s\S",
                                   b"1aa! a").group(0), b"1aa! a")
        self.assertEqual(re.search(r"\d\D\w\W\s\S",
                                   "1aa! a", re.ASCII).group(0), "1aa! a")
        self.assertEqual(re.search(br"\d\D\w\W\s\S",
                                   b"1aa! a", re.LOCALE).group(0), b"1aa! a") 

def _mode_ascii(self):
        self.utf8_enabled = False
        self._encoding = 'ascii'
        self.Literal = re.compile(_Literal, re.ASCII)
        self.Untagged_status = re.compile(_Untagged_status, re.ASCII)