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 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 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 _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 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 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 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 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 __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 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 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 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 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 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 _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 _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 readtab(self,tabfile,fdict):
        if isinstance(tabfile,types.ModuleType):
            lextab = tabfile
        else:
            if sys.version_info[0] < 3:
                exec("import %s as lextab" % tabfile)
            else:
                env = { }
                exec("import %s as lextab" % tabfile, env,env)
                lextab = env['lextab']

        if getattr(lextab,"_tabversion","0.0") != __tabversion__:
            raise ImportError("Inconsistent PLY version")

        self.lextokens      = lextab._lextokens
        self.lexreflags     = lextab._lexreflags
        self.lexliterals    = lextab._lexliterals
        self.lexstateinfo   = lextab._lexstateinfo
        self.lexstateignore = lextab._lexstateignore
        self.lexstatere     = { }
        self.lexstateretext = { }
        for key,lre in lextab._lexstatere.items():
             titem = []
             txtitem = []
             for i in range(len(lre)):
                  titem.append((re.compile(lre[i][0],lextab._lexreflags | re.VERBOSE),_names_to_funcs(lre[i][1],fdict)))
                  txtitem.append(lre[i][0])
             self.lexstatere[key] = titem
             self.lexstateretext[key] = txtitem
        self.lexstateerrorf = { }
        for key,ef in lextab._lexstateerrorf.items():
             self.lexstateerrorf[key] = fdict[ef]
        self.begin('INITIAL')

    # ------------------------------------------------------------
    # input() - Push a new string into the lexer
    # ------------------------------------------------------------ 

def _form_master_re(relist,reflags,ldict,toknames):
    if not relist: return []
    regex = "|".join(relist)
    try:
        lexre = re.compile(regex,re.VERBOSE | reflags)

        # Build the index to function map for the matching engine
        lexindexfunc = [ None ] * (max(lexre.groupindex.values())+1)
        lexindexnames = lexindexfunc[:]

        for f,i in lexre.groupindex.items():
            handle = ldict.get(f,None)
            if type(handle) in (types.FunctionType, types.MethodType):
                lexindexfunc[i] = (handle,toknames[f])
                lexindexnames[i] = f
            elif handle is not None:
                lexindexnames[i] = f
                if f.find("ignore_") > 0:
                    lexindexfunc[i] = (None,None)
                else:
                    lexindexfunc[i] = (None, toknames[f])
        
        return [(lexre,lexindexfunc)],[regex],[lexindexnames]
    except Exception:
        m = int(len(relist)/2)
        if m == 0: m = 1
        llist, lre, lnames = _form_master_re(relist[:m],reflags,ldict,toknames)
        rlist, rre, rnames = _form_master_re(relist[m:],reflags,ldict,toknames)
        return llist+rlist, lre+rre, lnames+rnames

# -----------------------------------------------------------------------------
# def _statetoken(s,names)
#
# Given a declaration name s of the form "t_" and a dictionary whose keys are
# state names, this function returns a tuple (states,tokenname) where states
# is a tuple of state names and tokenname is the name of the token.  For example,
# calling this with s = "t_foo_bar_SPAM" might return (('foo','bar'),'SPAM')
# ----------------------------------------------------------------------------- 

def escape_ansi_control(error):
    ansi_escape = re.compile(r'''
        \x1B    # ESC
        [@-_]   # 7-bit C1 Fe
        [0-?]*  # Parameter bytes
        [ -/]*  # Intermediate bytes
        [@-~]   # Final byte
    ''', re.VERBOSE)
    sanitized = ""
    for line in error:
        sanitized += ansi_escape.sub('', line) + "\n"
    return sanitized 

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, cls.flags | _re.VERBOSE) 

def __init__(self, defaults=None, dict_type=_default_dict,
                 allow_no_value=False, *, delimiters=('=', ':'),
                 comment_prefixes=('#', ';'), inline_comment_prefixes=None,
                 strict=True, empty_lines_in_values=True,
                 default_section=DEFAULTSECT,
                 interpolation=_UNSET):

        self._dict = dict_type
        self._sections = self._dict()
        self._defaults = self._dict()
        self._proxies = self._dict()
        self._proxies[default_section] = SectionProxy(self, default_section)
        if defaults:
            for key, value in defaults.items():
                self._defaults[self.optionxform(key)] = value
        self._delimiters = tuple(delimiters)
        if delimiters == ('=', ':'):
            self._optcre = self.OPTCRE_NV if allow_no_value else self.OPTCRE
        else:
            d = "|".join(re.escape(d) for d in delimiters)
            if allow_no_value:
                self._optcre = re.compile(self._OPT_NV_TMPL.format(delim=d),
                                          re.VERBOSE)
            else:
                self._optcre = re.compile(self._OPT_TMPL.format(delim=d),
                                          re.VERBOSE)
        self._comment_prefixes = tuple(comment_prefixes or ())
        self._inline_comment_prefixes = tuple(inline_comment_prefixes or ())
        self._strict = strict
        self._allow_no_value = allow_no_value
        self._empty_lines_in_values = empty_lines_in_values
        self.default_section=default_section
        self._interpolation = interpolation
        if self._interpolation is _UNSET:
            self._interpolation = self._DEFAULT_INTERPOLATION
        if self._interpolation is None:
            self._interpolation = Interpolation() 

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 _read(files, conversion_function):
    if type(files) is str: files = (files,)

    for file in files:
        path = os.path.join(get_basedir(), "ycoe/pos", file)
        f = open(path).read()
        rx_pattern = re.compile(r"""
                <.*>_CODE
                |\s.*_ID
        """, re.VERBOSE|re.UNICODE)
        mySents = tokenize.blankline(f)
        for sent in mySents:
            sent= re.sub(rx_pattern, '', sent)
            if sent != "":
                yield conversion_function(sent, sep="_") 

def _word_tokenizer_re(self):
        """Compiles and returns a regular expression for word tokenization"""
        try:
            return self._re_word_tokenizer
        except AttributeError:
            self._re_word_tokenizer = re.compile(
                self._word_tokenize_fmt %
                {
                    'NonWord':   self._re_non_word_chars,
                    'MultiChar': self._re_multi_char_punct,
                    'WordStart': self._re_word_start,
                },
                re.UNICODE | re.VERBOSE
            )
            return self._re_word_tokenizer 

def period_context_re(self):
        """Compiles and returns a regular expression to find contexts
        including possible sentence boundaries."""
        try:
            return self._re_period_context
        except:
            self._re_period_context = re.compile(
                self._period_context_fmt %
                {
                    'NonWord':      self._re_non_word_chars,
                    'SentEndChars': self._re_sent_end_chars,
                },
                re.UNICODE | re.VERBOSE)
            return self._re_period_context 

def _get_suggested_filename(path):
    """Convert a path we got from chromium to a suggested filename.

    Chromium thinks we want to download stuff to ~/Download, so even if we
    don't, we get downloads with a suffix like (1) for files existing there.

    We simply strip the suffix off via regex.

    See https://bugreports.qt.io/browse/QTBUG-56978
    """
    filename = os.path.basename(path)

    suffix_re = re.compile(r"""
      \ ?  # Optional space between filename and suffix
      (
        # Numerical suffix
        \([0-9]+\)
      |
        # ISO-8601 suffix
        # https://cs.chromium.org/chromium/src/base/time/time_to_iso8601.cc
        \ -\ \d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}.\d{3}Z
      )
      (?=\.|$)  # Begin of extension, or filename without extension
    """, re.VERBOSE)

    filename = suffix_re.sub('', filename)
    if not qtutils.version_check('5.9', compiled=False):
        # https://bugreports.qt.io/browse/QTBUG-58155
        filename = urllib.parse.unquote(filename)
        # Doing basename a *second* time because there could be a %2F in
        # there...
        filename = os.path.basename(filename)
    return filename 

def parse_entry(entry):
    """Parse an entry from the remote API."""
    dict_re = re.compile(r"""
        (?P<filename>(?P<code>[a-z]{2}(-[A-Z]{2})?).*\.bdic)
    """, re.VERBOSE)
    match = dict_re.fullmatch(entry['name'])
    if match is not None:
        return match.group('code'), match.group('filename')
    else:
        return None