Python re.VERBOSE Examples

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 

def str2int(string):
  numeric_const_pattern = r"""
  [-+]? # optional sign
  (?:
    (?: \d* \. \d+ ) # .1 .12 .123 etc 9.1 etc 98.1 etc
    |
    (?: \d+ \.? ) # 1. 12. 123. etc 1 12 123 etc
  )
  # followed by optional exponent part if desired
  (?: [Ee] [+-]? \d+ ) ?
  """
  rx = re.compile(numeric_const_pattern, re.VERBOSE)
  nb = rx.findall(string)
  for i in enumerate(nb): nb[i[0]] = int(i[1])
  return np.array(nb)

#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!1 

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 is_valid_ip(addr):
    '''Validate an IPV4 address.

    :param addr: IP address to validate.
    :type addr: ``string``
    :returns: True if is valid else False.
    :rtype: ``bool``
    '''

    ip_rx = re.compile(r'''
        ^(((
              [0-1]\d{2}                  # matches 000-199
            | 2[0-4]\d                    # matches 200-249
            | 25[0-5]                     # matches 250-255
            | \d{1,2}                     # matches 0-9, 00-99
        )\.){3})                          # 3 of the preceding stanzas
        ([0-1]\d{2}|2[0-4]\d|25[0-5]|\d{1,2})$     # final octet
    ''', re.VERBOSE)

    try:
        return ip_rx.match(addr.strip())
    except AttributeError:
        # Value was not a string
        return False 

def _split_string(text):
    """
    Split the combined (decoded) string into left, center and right parts

    # See http://stackoverflow.com/questions/27711175/regex-with-multiple-optional-groups for discussion
    """

    ITEM_REGEX = re.compile("""
    (&L(?P<left>.+?))?
    (&C(?P<center>.+?))?
    (&R(?P<right>.+?))?
    $""", re.VERBOSE | re.DOTALL)

    m = ITEM_REGEX.match(text)
    try:
        parts = m.groupdict()
    except AttributeError:
        warn("""Cannot parse header or footer so it will be ignored""")
        parts = {'left':'', 'right':'', 'center':''}
    return parts 

def is_valid_ip(addr):
    '''Validate an IPV4 address.

    :param addr: IP address to validate.
    :type addr: ``string``
    :returns: True if is valid else False.
    :rtype: ``bool``
    '''

    ip_rx = re.compile(r'''
        ^(((
              [0-1]\d{2}                  # matches 000-199
            | 2[0-4]\d                    # matches 200-249
            | 25[0-5]                     # matches 250-255
            | \d{1,2}                     # matches 0-9, 00-99
        )\.){3})                          # 3 of the preceding stanzas
        ([0-1]\d{2}|2[0-4]\d|25[0-5]|\d{1,2})$     # final octet
    ''', re.VERBOSE)

    try:
        return ip_rx.match(addr.strip())
    except AttributeError:
        # Value was not a string
        return False 

def set_memlimit(limit):
    global max_memuse
    global real_max_memuse
    sizes = {
        'k': 1024,
        'm': _1M,
        'g': _1G,
        't': 1024*_1G,
    }
    m = re.match(r'(\d+(\.\d+)?) (K|M|G|T)b?$', limit,
                 re.IGNORECASE | re.VERBOSE)
    if m is None:
        raise ValueError('Invalid memory limit %r' % (limit,))
    memlimit = int(float(m.group(1)) * sizes[m.group(3).lower()])
    real_max_memuse = memlimit
    if memlimit > MAX_Py_ssize_t:
        memlimit = MAX_Py_ssize_t
    if memlimit < _2G - 1:
        raise ValueError('Memory limit %r too low to be useful' % (limit,))
    max_memuse = memlimit 

def conllesp():
    from nltk.corpus import conll2002

    de = """
    .*
    (
    de/SP|
    del/SP
    )
    """
    DE = re.compile(de, re.VERBOSE)

    print()
    print("Spanish CoNLL2002: de(ORG, LOC) -- just the first 10 clauses:")
    print("=" * 45)
    rels = [rel for doc in conll2002.chunked_sents('esp.train')
            for rel in extract_rels('ORG', 'LOC', doc, corpus='conll2002', pattern = DE)]
    for r in rels[:10]: print(clause(r, relsym='DE'))
    print() 

def __init__(self, spectree):
        super().__init__(spectree)
        from falcon.routing.compiled import _FIELD_PATTERN

        self.FIELD_PATTERN = _FIELD_PATTERN
        # NOTE from `falcon.routing.compiled.CompiledRouterNode`
        self.ESCAPE = r'[\.\(\)\[\]\?\$\*\+\^\|]'
        self.ESCAPE_TO = r'\\\g<0>'
        self.EXTRACT = r'{\2}'
        # NOTE this regex is copied from werkzeug.routing._converter_args_re and
        # modified to support only int args
        self.INT_ARGS = re.compile(r'''
            ((?P<name>\w+)\s*=\s*)?
            (?P<value>\d+)\s*
        ''', re.VERBOSE)
        self.INT_ARGS_NAMES = ('num_digits', 'min', 'max') 

def remove_stack_traces(out):
    # this regexp taken from Python 2.5's doctest
    traceback_re = re.compile(r"""
        # Grab the traceback header.  Different versions of Python have
        # said different things on the first traceback line.
        ^(?P<hdr> Traceback\ \(
            (?: most\ recent\ call\ last
            |   innermost\ last
            ) \) :
        )
        \s* $                   # toss trailing whitespace on the header.
        (?P<stack> .*?)         # don't blink: absorb stuff until...
        ^(?=\w)                 #     a line *starts* with alphanum.
        .*?(?P<exception> \w+ ) # exception name
        (?P<msg> [:\n] .*)      # the rest
        """, re.VERBOSE | re.MULTILINE | re.DOTALL)
    blocks = []
    for block in blankline_separated_blocks(out):
        blocks.append(traceback_re.sub(r"\g<hdr>\n...\n\g<exception>\g<msg>", block))
    return "".join(blocks) 

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 _parse(s):
    rx_pattern = re.compile(r"""
        \(CODE .*\)
        |\(ID .*\d\)
    """, re.VERBOSE|re.UNICODE)
    s = re.sub(rx_pattern, '', s)
    s = split(s, '\n')
    fullPhrase = ""
    # loop through the sentences and parse each sentence
    # every time a new sentence marker is found
    for sent in s:
        if list(tokenize.regexp(sent, r'^\(')) != []:
            fullPhrase = _strip_spaces(fullPhrase)               
            if fullPhrase != "":
                yield fullPhrase
            fullPhrase = sent
        else:
            fullPhrase += sent

    # Get the last of the buffer and output a yield
    fullPhrase = _strip_spaces(fullPhrase)
    if fullPhrase != "":
        yield fullPhrase 

def str2float(string):
  numeric_const_pattern = r"""
  [-+]? # optional sign
  (?:
    (?: \d* \. \d+ ) # .1 .12 .123 etc 9.1 etc 98.1 etc
    |
    (?: \d+ \.? ) # 1. 12. 123. etc 1 12 123 etc
  )
  # followed by optional exponent part if desired
  (?: [Ee] [+-]? \d+ ) ?
  """
  rx = re.compile(numeric_const_pattern, re.VERBOSE)
  nb = rx.findall(string)
  for i in enumerate(nb): nb[i[0]] = float(i[1])

  return np.array(nb) 

def date_parser(timestr, parserinfo=None, **kwargs):
    """
    Uses dateutil.parser.parse, but also handles monthly dates of the form
    1999m4, 1999:m4, 1999:mIV, 1999mIV and the same for quarterly data
    with q instead of m. It is not case sensitive. The default for annual
    data is the end of the year, which also differs from dateutil.
    """
    flags = re.IGNORECASE | re.VERBOSE
    if re.search(_q_pattern, timestr, flags):
        y,q = timestr.replace(":","").lower().split('q')
        month, day = _quarter_to_day[q.upper()]
        year = int(y)
    elif re.search(_m_pattern, timestr, flags):
        y,m = timestr.replace(":","").lower().split('m')
        month, day = _month_to_day[m.upper()]
        year = int(y)
        if _is_leap(y) and month == 2:
            day += 1
    elif re.search(_y_pattern, timestr, flags):
        month, day = 12, 31
        year = int(timestr)
    else:
        return to_datetime(timestr, **kwargs)

    return datetime.datetime(year, month, day) 

def set_memlimit(limit):
    global max_memuse
    global real_max_memuse
    sizes = {
        'k': 1024,
        'm': _1M,
        'g': _1G,
        't': 1024*_1G,
    }
    m = re.match(r'(\d+(\.\d+)?) (K|M|G|T)b?$', limit,
                 re.IGNORECASE | re.VERBOSE)
    if m is None:
        raise ValueError('Invalid memory limit %r' % (limit,))
    memlimit = int(float(m.group(1)) * sizes[m.group(3).lower()])
    real_max_memuse = memlimit
    if memlimit > MAX_Py_ssize_t:
        memlimit = MAX_Py_ssize_t
    if memlimit < _2G - 1:
        raise ValueError('Memory limit %r too low to be useful' % (limit,))
    max_memuse = memlimit 

def test_getstatus(self):
        # This pattern should match 'ls -ld /.' on any posix
        # system, however perversely configured.  Even on systems
        # (e.g., Cygwin) where user and group names can have spaces:
        #     drwxr-xr-x   15 Administ Domain U     4096 Aug 12 12:50 /
        #     drwxr-xr-x   15 Joe User My Group     4096 Aug 12 12:50 /
        # Note that the first case above has a space in the group name
        # while the second one has a space in both names.
        # Special attributes supported:
        #   + = has ACLs
        #   @ = has Mac OS X extended attributes
        #   . = has a SELinux security context
        pat = r'''d.........   # It is a directory.
                  [.+@]?       # It may have special attributes.
                  \s+\d+       # It has some number of links.
                  [^/]*        # Skip user, group, size, and date.
                  /\.          # and end with the name of the file.
               '''

        with check_warnings((".*commands.getstatus.. is deprecated",
                             DeprecationWarning)):
            self.assertTrue(re.match(pat, commands.getstatus("/."), re.VERBOSE)) 

def set_memlimit(limit):
    global max_memuse
    global real_max_memuse
    sizes = {
        'k': 1024,
        'm': _1M,
        'g': _1G,
        't': 1024*_1G,
    }
    m = re.match(r'(\d+(\.\d+)?) (K|M|G|T)b?$', limit,
                 re.IGNORECASE | re.VERBOSE)
    if m is None:
        raise ValueError('Invalid memory limit %r' % (limit,))
    memlimit = int(float(m.group(1)) * sizes[m.group(3).lower()])
    real_max_memuse = memlimit
    if memlimit > MAX_Py_ssize_t:
        memlimit = MAX_Py_ssize_t
    if memlimit < _2G - 1:
        raise ValueError('Memory limit %r too low to be useful' % (limit,))
    max_memuse = memlimit 

def simplify_warnings(out):
    warn_re = re.compile(r"""
        # Cut the file and line no, up to the warning name
        ^.*:\d+:\s
        (?P<category>\w+): \s+        # warning category
        (?P<detail>.+) $ \n?          # warning message
        ^ .* $                        # stack frame
        """, re.VERBOSE | re.MULTILINE)
    return warn_re.sub(r"\g<category>: \g<detail>", out) 

def get_yt_id(url):
    pattern = re.compile(
        r"""
        (https?://)?(www\.)?(youtube|youtu|youtube-nocookie)\.
        (com|be)/(watch\?v=|embed/|v/|.+\?v=)?
        (?P<id>[A-Za-z0-9\-=_]{11})""",
        re.VERBOSE,
    )
    match = pattern.match(url)
    if not match:
        return None
    return match.group("id") 

def scp_pull_file(client_ftp, scf_client_ftp, transfer_file, remote_dir,
    scf_outgoing, CLOBBER=False, VERBOSE=False, LIST=False, MODE=0o775):
    #-- remote and scf outgoing versions of file
    remote_file = os.path.join(remote_dir,transfer_file)
    outgoing_file = posixpath.join(scf_outgoing,transfer_file)
    #-- get access and modification time of remote file
    outgoing_atime = scf_client_ftp.stat(outgoing_file).st_atime
    outgoing_mtime = scf_client_ftp.stat(outgoing_file).st_mtime
    #-- check if remote file is newer than the local file
    TEST = False
    OVERWRITE = 'clobber'
    if (transfer_file in client_ftp.listdir(remote_dir)):
        remote_mtime = client_ftp.stat(remote_file).st_mtime
        #-- if remote file is newer: overwrite the local file
        if (even(outgoing_mtime) > even(remote_mtime)):
            TEST = True
            OVERWRITE = 'overwrite'
    else:
        TEST = True
        OVERWRITE = 'new'
    #-- if file does not exist locally, is to be overwritten, or CLOBBER is set
    if TEST or CLOBBER:
        if VERBOSE or LIST:
            print('{0} --> '.format(outgoing_file))
            print('\t{0} ({1})\n'.format(remote_file,OVERWRITE))
        #-- if not only listing files
        if not LIST:
            #-- load scf file contents to BytesIO object
            fileobj = io.BytesIO()
            scf_client_ftp.getfo(outgoing_file, fileobj)
            #-- rewind retrieved binary to start of file
            fileobj.seek(0)
            #-- copy BytesIO object to remote server
            client_ftp.putfo(fileobj, remote_file)
            #-- change the permissions level of the transported file to MODE
            client_ftp.chmod(remote_file, MODE)
            #-- keep modification and access time of scf file
            client_ftp.utime(remote_file, (outgoing_atime, outgoing_mtime))

#-- PURPOSE: rounds a number to an even number less than or equal to original 

def scp_pull_file(client, client_ftp, transfer_file, local_dir, remote_dir,
    CLOBBER=False, VERBOSE=False, LIST=False, MODE=0o775):
    #-- local and remote versions of file
    local_file = os.path.join(local_dir,transfer_file)
    remote_file = posixpath.join(remote_dir,transfer_file)
    #-- check if remote file is newer than the local file
    TEST = False
    OVERWRITE = 'clobber'
    if os.access(local_file, os.F_OK):
        local_mtime = os.stat(local_file).st_mtime
        remote_mtime = client_ftp.stat(remote_file).st_mtime
        #-- if remote file is newer: overwrite the local file
        if (even(remote_mtime) > even(local_mtime)):
            TEST = True
            OVERWRITE = 'overwrite'
    else:
        TEST = True
        OVERWRITE = 'new'
    #-- if file does not exist locally, is to be overwritten, or CLOBBER is set
    if TEST or CLOBBER:
        if VERBOSE or LIST:
            print('{0} --> '.format(remote_file))
            print('\t{0} ({1})\n'.format(local_file,OVERWRITE))
        #-- if not only listing files
        if not LIST:
            #-- copy local files from remote server
            with scp.SCPClient(client.get_transport(), socket_timeout=20) as s:
                s.get(remote_file, local_path=local_file, preserve_times=True)
            #-- change the permissions level of the transported file to MODE
            os.chmod(local_file, MODE)

#-- PURPOSE: rounds a number to an even number less than or equal to original 

def symbolic_ICESat2_files(base_dir, scf_incoming, scf_outgoing, PRODUCT,
    RELEASE, VERSIONS, GRANULES, CYCLES, TRACKS, VERBOSE=False, MODE=0o775):
    #-- find ICESat-2 HDF5 files in the subdirectory for product and release
    TRACKS = np.arange(1,1388) if not np.any(TRACKS) else TRACKS
    CYCLES = np.arange(1,10) if not np.any(CYCLES) else CYCLES
    GRANULES = np.arange(1,15) if not np.any(GRANULES) else GRANULES
    VERSIONS = np.arange(1,10) if not np.any(VERSIONS) else VERSIONS
    regex_track = '|'.join(['{0:04d}'.format(T) for T in TRACKS])
    regex_cycle = '|'.join(['{0:02d}'.format(C) for C in CYCLES])
    regex_granule = '|'.join(['{0:02d}'.format(G) for G in GRANULES])
    regex_version = '|'.join(['{0:02d}'.format(V) for V in VERSIONS])
    #-- compile regular expression operator for extracting data from files
    args = (PRODUCT,regex_track,regex_cycle,regex_granule,RELEASE,regex_version)
    regex_pattern = ('(processed_)?({0})(-\d{{2}})?_(\d{{4}})(\d{{2}})(\d{{2}})'
        '(\d{{2}})(\d{{2}})(\d{{2}})_({1})({2})({3})_({4})_({5})(.*?).h5$')
    rx = re.compile(regex_pattern.format(*args),re.VERBOSE)
    #-- find files within scf_outgoing
    file_transfers = [f for f in os.listdir(scf_outgoing) if rx.match(f)]
    for f in sorted(file_transfers):
        #-- extract parameters from file
        SUB,PRD,HEM,YY,MM,DD,HH,MN,SS,TRK,CYC,GRN,RL,VRS,AUX=rx.findall(f).pop()
        #-- put symlinks in directories similar to NSIDC
        #-- check if data directory exists and recursively create if not
        local_dir = os.path.join(base_dir,'{0}.{1}.{2}'.format(YY,MM,DD))
        os.makedirs(local_dir,MODE) if not os.path.exists(local_dir) else None
        #-- print original and symbolic link of file
        if VERBOSE:
            print('{0} -->'.format(os.path.join(scf_outgoing,f)))
            print('\t{0}'.format(os.path.join(local_dir,f)))
        #-- create symbolic link of file from scf_outgoing to local
        os.symlink(os.path.join(scf_outgoing,f), os.path.join(local_dir,f))

#-- run main program 

def _parse_regex(self, string):
        """Parse output with grouped regex."""
        results = []
        self.regex = re.compile(self.pattern, re.VERBOSE)
        for matches in self.regex.finditer(string):
            results.append(matches.groupdict())
        return results 

def __init__(self):
        pattern = self.reflect()
        self.pos = 0
        self.re = re.compile(pattern, re.VERBOSE)

        self.index2func = {}
        for name, number in self.re.groupindex.items():
            self.index2func[number-1] = getattr(self, 't_' + name) 

def test_ipy3_gh546(self):
        """https://github.com/IronLanguages/ironpython3/issues/546"""
        import re
        _SECT_TMPL = r"""
            \[                                 # [
            (?P<header>[^]]+)                  # very permissive!
            \]                                 # ]
            """
        SECTCRE = re.compile(_SECT_TMPL, re.VERBOSE)
        string = "[some header]"
        match = SECTCRE.match(string)
        self.assertEqual(match.span(), (0, len(string))) 

def test_constants(self):
        self.assertEqual(re.I, re.IGNORECASE)
        self.assertEqual(re.L, re.LOCALE)
        self.assertEqual(re.M, re.MULTILINE)
        self.assertEqual(re.S, re.DOTALL)
        self.assertEqual(re.X, re.VERBOSE) 

def __init__(cls, name, bases, dct):
        super(_TemplateMetaclass, cls).__init__(name, bases, dct)
        if 'pattern' in dct:
            pattern = cls.pattern
        else:
            pattern = _TemplateMetaclass.pattern % {
                'delim' : _re.escape(cls.delimiter),
                'id'    : cls.idpattern,
                }
        cls.pattern = _re.compile(pattern, _re.IGNORECASE | _re.VERBOSE) 

def __init__(self, scriptLanguage, fileLoader, baseDir, varBase, sourceName):
        self.__pattern = re.compile(r"""
            \$<(?:
                (?P<escaped>\$)     |
                (?P<named>[<'][^'>]+)['>]>  |
                (?P<braced>[<'][^'>]+)['>]> |
                (?P<invalid>)
            )
            """, re.VERBOSE)
        self.__resolverClass = scriptLanguage.Resolver
        self.__baseDir = baseDir
        self.__varBase = re.sub(r'[^a-zA-Z0-9_]', '_', varBase, flags=re.DOTALL)
        self.__fileLoader = fileLoader
        self.__sourceName = sourceName 

def __init__(cls, name, bases, dct):
        super(_TemplateMetaclass, cls).__init__(name, bases, dct)
        if 'pattern' in dct:
            pattern = cls.pattern
        else:
            pattern = _TemplateMetaclass.pattern % {
                'delim' : _re.escape(cls.delimiter),
                'id'    : cls.idpattern,
                }
        cls.pattern = _re.compile(pattern, _re.IGNORECASE | _re.VERBOSE)