Gecko [ sachasauda.akalacademy.ac.in ]

Name	Size	Permission
__pycache__	[ DIR ]	drwxr-xr-x
asyncio	[ DIR ]	drwxr-xr-x
collections	[ DIR ]	drwxr-xr-x
concurrent	[ DIR ]	drwxr-xr-x
config-3.5m	[ DIR ]	drwxr-xr-x
ctypes	[ DIR ]	drwxr-xr-x
curses	[ DIR ]	drwxr-xr-x
dbm	[ DIR ]	drwxr-xr-x
distutils	[ DIR ]	drwxr-xr-x
email	[ DIR ]	drwxr-xr-x
encodings	[ DIR ]	drwxr-xr-x
ensurepip	[ DIR ]	drwxr-xr-x
html	[ DIR ]	drwxr-xr-x
http	[ DIR ]	drwxr-xr-x
idlelib	[ DIR ]	drwxr-xr-x
importlib	[ DIR ]	drwxr-xr-x
json	[ DIR ]	drwxr-xr-x
lib-dynload	[ DIR ]	drwxr-xr-x
lib2to3	[ DIR ]	drwxr-xr-x
logging	[ DIR ]	drwxr-xr-x
multiprocessing	[ DIR ]	drwxr-xr-x
plat-linux	[ DIR ]	drwxr-xr-x
pydoc_data	[ DIR ]	drwxr-xr-x
site-packages	[ DIR ]	drwxr-xr-x
sqlite3	[ DIR ]	drwxr-xr-x
tkinter	[ DIR ]	drwxr-xr-x
turtledemo	[ DIR ]	drwxr-xr-x
unittest	[ DIR ]	drwxr-xr-x
urllib	[ DIR ]	drwxr-xr-x
venv	[ DIR ]	drwxr-xr-x
wsgiref	[ DIR ]	drwxr-xr-x
xml	[ DIR ]	drwxr-xr-x
xmlrpc	[ DIR ]	drwxr-xr-x
LICENSE.txt	12.46 KB	-rw-r--r--
__future__.py	4.73 KB	-rw-r--r--
__phello__.foo.py	64 B	-rw-r--r--
_bootlocale.py	1.27 KB	-rw-r--r--
_collections_abc.py	24.21 KB	-rw-r--r--
_compat_pickle.py	8.36 KB	-rw-r--r--
_compression.py	5.21 KB	-rw-r--r--
_dummy_thread.py	5 KB	-rw-r--r--
_markupbase.py	14.26 KB	-rw-r--r--
_osx_support.py	18.67 KB	-rw-r--r--
_pydecimal.py	223.27 KB	-rw-r--r--
_pyio.py	85.91 KB	-rw-r--r--
_sitebuiltins.py	3.04 KB	-rw-r--r--
_strptime.py	21.67 KB	-rw-r--r--
_sysconfigdata.py	18.33 KB	-rw-r--r--
_threading_local.py	7.24 KB	-rw-r--r--
_weakrefset.py	5.57 KB	-rw-r--r--
abc.py	8.43 KB	-rw-r--r--
aifc.py	31.22 KB	-rw-r--r--
antigravity.py	476 B	-rw-r--r--
argparse.py	88.03 KB	-rw-r--r--
ast.py	11.72 KB	-rw-r--r--
asynchat.py	11.69 KB	-rw-r--r--
asyncore.py	19.63 KB	-rw-r--r--
base64.py	20.03 KB	-rwxr-xr-x
bdb.py	22.81 KB	-rw-r--r--
binhex.py	13.63 KB	-rw-r--r--
bisect.py	2.53 KB	-rw-r--r--
bz2.py	12.13 KB	-rw-r--r--
cProfile.py	5.19 KB	-rwxr-xr-x
calendar.py	22.46 KB	-rw-r--r--
cgi.py	35.2 KB	-rwxr-xr-x
cgitb.py	11.74 KB	-rw-r--r--
chunk.py	5.3 KB	-rw-r--r--
cmd.py	14.51 KB	-rw-r--r--
code.py	9.88 KB	-rw-r--r--
codecs.py	35.38 KB	-rw-r--r--
codeop.py	5.85 KB	-rw-r--r--
colorsys.py	3.97 KB	-rw-r--r--
compileall.py	11.44 KB	-rw-r--r--
configparser.py	52.2 KB	-rw-r--r--
contextlib.py	12.16 KB	-rw-r--r--
copy.py	8.74 KB	-rw-r--r--
copyreg.py	6.67 KB	-rw-r--r--
crypt.py	1.83 KB	-rw-r--r--
csv.py	15.75 KB	-rw-r--r--
datetime.py	74.12 KB	-rw-r--r--
decimal.py	320 B	-rw-r--r--
difflib.py	82.23 KB	-rw-r--r--
dis.py	16.94 KB	-rw-r--r--
doctest.py	101.6 KB	-rw-r--r--
dummy_threading.py	2.75 KB	-rw-r--r--
enum.py	21.71 KB	-rw-r--r--
filecmp.py	9.6 KB	-rw-r--r--
fileinput.py	13.92 KB	-rw-r--r--
fnmatch.py	3.09 KB	-rw-r--r--
formatter.py	14.79 KB	-rw-r--r--
fractions.py	24.04 KB	-rw-r--r--
ftplib.py	34.13 KB	-rw-r--r--
functools.py	28.27 KB	-rw-r--r--
genericpath.py	4.26 KB	-rw-r--r--
getopt.py	7.31 KB	-rw-r--r--
getpass.py	5.85 KB	-rw-r--r--
gettext.py	21.03 KB	-rw-r--r--
glob.py	4.95 KB	-rw-r--r--
gzip.py	19.79 KB	-rw-r--r--
hashlib.py	7.79 KB	-rw-r--r--
heapq.py	22.39 KB	-rw-r--r--
hmac.py	4.94 KB	-rw-r--r--
imaplib.py	50.96 KB	-rw-r--r--
imghdr.py	3.67 KB	-rw-r--r--
imp.py	10.43 KB	-rw-r--r--
inspect.py	111.52 KB	-rw-r--r--
io.py	3.32 KB	-rw-r--r--
ipaddress.py	73.96 KB	-rw-r--r--
keyword.py	2.16 KB	-rwxr-xr-x
linecache.py	5.19 KB	-rw-r--r--
locale.py	72.96 KB	-rw-r--r--
lzma.py	12.62 KB	-rw-r--r--
macpath.py	5.77 KB	-rw-r--r--
macurl2path.py	2.67 KB	-rw-r--r--
mailbox.py	76.58 KB	-rw-r--r--
mailcap.py	7.91 KB	-rw-r--r--
mimetypes.py	20.36 KB	-rw-r--r--
modulefinder.py	22.54 KB	-rw-r--r--
netrc.py	5.61 KB	-rw-r--r--
nntplib.py	42.07 KB	-rw-r--r--
ntpath.py	22.26 KB	-rw-r--r--
nturl2path.py	2.39 KB	-rw-r--r--
numbers.py	10 KB	-rw-r--r--
opcode.py	5.75 KB	-rw-r--r--
operator.py	10.61 KB	-rw-r--r--
optparse.py	58.93 KB	-rw-r--r--
os.py	36.17 KB	-rw-r--r--
pathlib.py	45.9 KB	-rw-r--r--
pdb.py	59.71 KB	-rwxr-xr-x
pickle.py	54.86 KB	-rw-r--r--
pickletools.py	89.61 KB	-rw-r--r--
pipes.py	8.71 KB	-rw-r--r--
pkgutil.py	20.85 KB	-rw-r--r--
platform.py	45.05 KB	-rwxr-xr-x
plistlib.py	30.73 KB	-rw-r--r--
poplib.py	14.37 KB	-rw-r--r--
posixpath.py	14.56 KB	-rw-r--r--
pprint.py	20.37 KB	-rw-r--r--
profile.py	21.5 KB	-rwxr-xr-x
pstats.py	25.94 KB	-rw-r--r--
pty.py	4.65 KB	-rw-r--r--
py_compile.py	7.01 KB	-rw-r--r--
pyclbr.py	13.25 KB	-rw-r--r--
pydoc.py	101.21 KB	-rwxr-xr-x
queue.py	8.57 KB	-rw-r--r--
quopri.py	7.08 KB	-rwxr-xr-x
random.py	25.84 KB	-rw-r--r--
re.py	15.14 KB	-rw-r--r--
reprlib.py	5.21 KB	-rw-r--r--
rlcompleter.py	6.16 KB	-rw-r--r--
runpy.py	11.68 KB	-rw-r--r--
sched.py	6.07 KB	-rw-r--r--
selectors.py	18.98 KB	-rw-r--r--
shelve.py	8.33 KB	-rw-r--r--
shlex.py	11.18 KB	-rw-r--r--
shutil.py	39.11 KB	-rw-r--r--
signal.py	2.07 KB	-rw-r--r--
site.py	20.74 KB	-rw-r--r--
smtpd.py	34.53 KB	-rwxr-xr-x
smtplib.py	42.6 KB	-rwxr-xr-x
sndhdr.py	6.27 KB	-rw-r--r--
socket.py	26.5 KB	-rw-r--r--
socketserver.py	24.09 KB	-rw-r--r--
sre_compile.py	17.98 KB	-rw-r--r--
sre_constants.py	6.66 KB	-rw-r--r--
sre_parse.py	34.29 KB	-rw-r--r--
ssl.py	41.36 KB	-rw-r--r--
stat.py	4.92 KB	-rw-r--r--
statistics.py	19.08 KB	-rw-r--r--
string.py	11.58 KB	-rw-r--r--
stringprep.py	12.61 KB	-rw-r--r--
struct.py	257 B	-rw-r--r--
subprocess.py	57.53 KB	-rw-r--r--
sunau.py	17.67 KB	-rw-r--r--
symbol.py	2.05 KB	-rwxr-xr-x
symtable.py	7.02 KB	-rw-r--r--
sysconfig.py	23.77 KB	-rw-r--r--
tabnanny.py	11.14 KB	-rwxr-xr-x
tarfile.py	90.88 KB	-rwxr-xr-x
telnetlib.py	22.48 KB	-rw-r--r--
tempfile.py	26.01 KB	-rw-r--r--
textwrap.py	19.1 KB	-rw-r--r--
this.py	1003 B	-rw-r--r--
threading.py	47.88 KB	-rw-r--r--
timeit.py	12.1 KB	-rwxr-xr-x
token.py	3 KB	-rw-r--r--
tokenize.py	27.14 KB	-rw-r--r--
trace.py	30.8 KB	-rwxr-xr-x
traceback.py	21.66 KB	-rw-r--r--
tracemalloc.py	15.27 KB	-rw-r--r--
tty.py	879 B	-rw-r--r--
turtle.py	140.25 KB	-rw-r--r--
types.py	8.59 KB	-rw-r--r--
typing.py	78.26 KB	-rw-r--r--
uu.py	6.6 KB	-rwxr-xr-x
uuid.py	22.72 KB	-rw-r--r--
warnings.py	15.48 KB	-rw-r--r--
wave.py	17.27 KB	-rw-r--r--
weakref.py	19.99 KB	-rw-r--r--
webbrowser.py	21.31 KB	-rwxr-xr-x
xdrlib.py	5.77 KB	-rw-r--r--
zipapp.py	6.99 KB	-rw-r--r--
zipfile.py	71.95 KB	-rw-r--r--

Code Editor : sre_parse.py

#
# Secret Labs' Regular Expression Engine
#
# convert re-style regular expression to sre pattern
#
# Copyright (c) 1998-2001 by Secret Labs AB.  All rights reserved.
#
# See the sre.py file for information on usage and redistribution.
#

"""Internal support module for sre"""

# XXX: show string offset and offending character for all errors

from sre_constants import *

SPECIAL_CHARS = ".\\[{()*+?^$|"
REPEAT_CHARS = "*+?{"

DIGITS = frozenset("0123456789")

OCTDIGITS = frozenset("01234567")
HEXDIGITS = frozenset("0123456789abcdefABCDEF")
ASCIILETTERS = frozenset("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ")

WHITESPACE = frozenset(" \t\n\r\v\f")

_REPEATCODES = frozenset({MIN_REPEAT, MAX_REPEAT})
_UNITCODES = frozenset({ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY})

ESCAPES = {
    r"\a": (LITERAL, ord("\a")),
    r"\b": (LITERAL, ord("\b")),
    r"\f": (LITERAL, ord("\f")),
    r"\n": (LITERAL, ord("\n")),
    r"\r": (LITERAL, ord("\r")),
    r"\t": (LITERAL, ord("\t")),
    r"\v": (LITERAL, ord("\v")),
    r"\\": (LITERAL, ord("\\"))
}

CATEGORIES = {
    r"\A": (AT, AT_BEGINNING_STRING), # start of string
    r"\b": (AT, AT_BOUNDARY),
    r"\B": (AT, AT_NON_BOUNDARY),
    r"\d": (IN, [(CATEGORY, CATEGORY_DIGIT)]),
    r"\D": (IN, [(CATEGORY, CATEGORY_NOT_DIGIT)]),
    r"\s": (IN, [(CATEGORY, CATEGORY_SPACE)]),
    r"\S": (IN, [(CATEGORY, CATEGORY_NOT_SPACE)]),
    r"\w": (IN, [(CATEGORY, CATEGORY_WORD)]),
    r"\W": (IN, [(CATEGORY, CATEGORY_NOT_WORD)]),
    r"\Z": (AT, AT_END_STRING), # end of string
}

FLAGS = {
    # standard flags
    "i": SRE_FLAG_IGNORECASE,
    "L": SRE_FLAG_LOCALE,
    "m": SRE_FLAG_MULTILINE,
    "s": SRE_FLAG_DOTALL,
    "x": SRE_FLAG_VERBOSE,
    # extensions
    "a": SRE_FLAG_ASCII,
    "t": SRE_FLAG_TEMPLATE,
    "u": SRE_FLAG_UNICODE,
}

class Pattern:
    # master pattern object.  keeps track of global attributes
    def __init__(self):
        self.flags = 0
        self.groupdict = {}
        self.groupwidths = [None]  # group 0
        self.lookbehindgroups = None
    @property
    def groups(self):
        return len(self.groupwidths)
    def opengroup(self, name=None):
        gid = self.groups
        self.groupwidths.append(None)
        if self.groups > MAXGROUPS:
            raise error("too many groups")
        if name is not None:
            ogid = self.groupdict.get(name, None)
            if ogid is not None:
                raise error("redefinition of group name %r as group %d; "
                            "was group %d" % (name, gid,  ogid))
            self.groupdict[name] = gid
        return gid
    def closegroup(self, gid, p):
        self.groupwidths[gid] = p.getwidth()
    def checkgroup(self, gid):
        return gid < self.groups and self.groupwidths[gid] is not None

def checklookbehindgroup(self, gid, source):
        if self.lookbehindgroups is not None:
            if not self.checkgroup(gid):
                raise source.error('cannot refer to an open group')
            if gid >= self.lookbehindgroups:
                raise source.error('cannot refer to group defined in the same '
                                   'lookbehind subpattern')

class SubPattern:
    # a subpattern, in intermediate form
    def __init__(self, pattern, data=None):
        self.pattern = pattern
        if data is None:
            data = []
        self.data = data
        self.width = None
    def dump(self, level=0):
        nl = True
        seqtypes = (tuple, list)
        for op, av in self.data:
            print(level*"  " + str(op), end='')
            if op is IN:
                # member sublanguage
                print()
                for op, a in av:
                    print((level+1)*"  " + str(op), a)
            elif op is BRANCH:
                print()
                for i, a in enumerate(av[1]):
                    if i:
                        print(level*"  " + "OR")
                    a.dump(level+1)
            elif op is GROUPREF_EXISTS:
                condgroup, item_yes, item_no = av
                print('', condgroup)
                item_yes.dump(level+1)
                if item_no:
                    print(level*"  " + "ELSE")
                    item_no.dump(level+1)
            elif isinstance(av, seqtypes):
                nl = False
                for a in av:
                    if isinstance(a, SubPattern):
                        if not nl:
                            print()
                        a.dump(level+1)
                        nl = True
                    else:
                        if not nl:
                            print(' ', end='')
                        print(a, end='')
                        nl = False
                if not nl:
                    print()
            else:
                print('', av)
    def __repr__(self):
        return repr(self.data)
    def __len__(self):
        return len(self.data)
    def __delitem__(self, index):
        del self.data[index]
    def __getitem__(self, index):
        if isinstance(index, slice):
            return SubPattern(self.pattern, self.data[index])
        return self.data[index]
    def __setitem__(self, index, code):
        self.data[index] = code
    def insert(self, index, code):
        self.data.insert(index, code)
    def append(self, code):
        self.data.append(code)
    def getwidth(self):
        # determine the width (min, max) for this subpattern
        if self.width is not None:
            return self.width
        lo = hi = 0
        for op, av in self.data:
            if op is BRANCH:
                i = MAXREPEAT - 1
                j = 0
                for av in av[1]:
                    l, h = av.getwidth()
                    i = min(i, l)
                    j = max(j, h)
                lo = lo + i
                hi = hi + j
            elif op is CALL:
                i, j = av.getwidth()
                lo = lo + i
                hi = hi + j
            elif op is SUBPATTERN:
                i, j = av[1].getwidth()
                lo = lo + i
                hi = hi + j
            elif op in _REPEATCODES:
                i, j = av[2].getwidth()
                lo = lo + i * av[0]
                hi = hi + j * av[1]
            elif op in _UNITCODES:
                lo = lo + 1
                hi = hi + 1
            elif op is GROUPREF:
                i, j = self.pattern.groupwidths[av]
                lo = lo + i
                hi = hi + j
            elif op is GROUPREF_EXISTS:
                i, j = av[1].getwidth()
                if av[2] is not None:
                    l, h = av[2].getwidth()
                    i = min(i, l)
                    j = max(j, h)
                else:
                    i = 0
                lo = lo + i
                hi = hi + j
            elif op is SUCCESS:
                break
        self.width = min(lo, MAXREPEAT - 1), min(hi, MAXREPEAT)
        return self.width

class Tokenizer:
    def __init__(self, string):
        self.istext = isinstance(string, str)
        self.string = string
        if not self.istext:
            string = str(string, 'latin1')
        self.decoded_string = string
        self.index = 0
        self.next = None
        self.__next()
    def __next(self):
        index = self.index
        try:
            char = self.decoded_string[index]
        except IndexError:
            self.next = None
            return
        if char == "\\":
            index += 1
            try:
                char += self.decoded_string[index]
            except IndexError:
                raise error("bad escape (end of pattern)",
                            self.string, len(self.string) - 1) from None
        self.index = index + 1
        self.next = char
    def match(self, char):
        if char == self.next:
            self.__next()
            return True
        return False
    def get(self):
        this = self.next
        self.__next()
        return this
    def getwhile(self, n, charset):
        result = ''
        for _ in range(n):
            c = self.next
            if c not in charset:
                break
            result += c
            self.__next()
        return result
    def getuntil(self, terminator):
        result = ''
        while True:
            c = self.next
            self.__next()
            if c is None:
                if not result:
                    raise self.error("missing group name")
                raise self.error("missing %s, unterminated name" % terminator,
                                 len(result))
            if c == terminator:
                if not result:
                    raise self.error("missing group name", 1)
                break
            result += c
        return result
    def tell(self):
        return self.index - len(self.next or '')
    def seek(self, index):
        self.index = index
        self.__next()

def error(self, msg, offset=0):
        return error(msg, self.string, self.tell() - offset)

# The following three functions are not used in this module anymore, but we keep
# them here (with DeprecationWarnings) for backwards compatibility.

def isident(char):
    import warnings
    warnings.warn('sre_parse.isident() will be removed in 3.5',
                  DeprecationWarning, stacklevel=2)
    return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_"

def isdigit(char):
    import warnings
    warnings.warn('sre_parse.isdigit() will be removed in 3.5',
                  DeprecationWarning, stacklevel=2)
    return "0" <= char <= "9"

def isname(name):
    import warnings
    warnings.warn('sre_parse.isname() will be removed in 3.5',
                  DeprecationWarning, stacklevel=2)
    # check that group name is a valid string
    if not isident(name[0]):
        return False
    for char in name[1:]:
        if not isident(char) and not isdigit(char):
            return False
    return True

def _class_escape(source, escape, nested):
    # handle escape code inside character class
    code = ESCAPES.get(escape)
    if code:
        return code
    code = CATEGORIES.get(escape)
    if code and code[0] is IN:
        return code
    try:
        c = escape[1:2]
        if c == "x":
            # hexadecimal escape (exactly two digits)
            escape += source.getwhile(2, HEXDIGITS)
            if len(escape) != 4:
                raise source.error("incomplete escape %s" % escape, len(escape))
            return LITERAL, int(escape[2:], 16)
        elif c == "u" and source.istext:
            # unicode escape (exactly four digits)
            escape += source.getwhile(4, HEXDIGITS)
            if len(escape) != 6:
                raise source.error("incomplete escape %s" % escape, len(escape))
            return LITERAL, int(escape[2:], 16)
        elif c == "U" and source.istext:
            # unicode escape (exactly eight digits)
            escape += source.getwhile(8, HEXDIGITS)
            if len(escape) != 10:
                raise source.error("incomplete escape %s" % escape, len(escape))
            c = int(escape[2:], 16)
            chr(c) # raise ValueError for invalid code
            return LITERAL, c
        elif c in OCTDIGITS:
            # octal escape (up to three digits)
            escape += source.getwhile(2, OCTDIGITS)
            c = int(escape[1:], 8)
            if c > 0o377:
                raise source.error('octal escape value %s outside of '
                                   'range 0-0o377' % escape, len(escape))
            return LITERAL, c
        elif c in DIGITS:
            raise ValueError
        if len(escape) == 2:
            if c in ASCIILETTERS:
                import warnings
                warnings.warn('bad escape %s' % escape,
                              DeprecationWarning, stacklevel=nested + 6)
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise source.error("bad escape %s" % escape, len(escape))

def _escape(source, escape, state, nested):
    # handle escape code in expression
    code = CATEGORIES.get(escape)
    if code:
        return code
    code = ESCAPES.get(escape)
    if code:
        return code
    try:
        c = escape[1:2]
        if c == "x":
            # hexadecimal escape
            escape += source.getwhile(2, HEXDIGITS)
            if len(escape) != 4:
                raise source.error("incomplete escape %s" % escape, len(escape))
            return LITERAL, int(escape[2:], 16)
        elif c == "u" and source.istext:
            # unicode escape (exactly four digits)
            escape += source.getwhile(4, HEXDIGITS)
            if len(escape) != 6:
                raise source.error("incomplete escape %s" % escape, len(escape))
            return LITERAL, int(escape[2:], 16)
        elif c == "U" and source.istext:
            # unicode escape (exactly eight digits)
            escape += source.getwhile(8, HEXDIGITS)
            if len(escape) != 10:
                raise source.error("incomplete escape %s" % escape, len(escape))
            c = int(escape[2:], 16)
            chr(c) # raise ValueError for invalid code
            return LITERAL, c
        elif c == "0":
            # octal escape
            escape += source.getwhile(2, OCTDIGITS)
            return LITERAL, int(escape[1:], 8)
        elif c in DIGITS:
            # octal escape *or* decimal group reference (sigh)
            if source.next in DIGITS:
                escape += source.get()
                if (escape[1] in OCTDIGITS and escape[2] in OCTDIGITS and
                    source.next in OCTDIGITS):
                    # got three octal digits; this is an octal escape
                    escape += source.get()
                    c = int(escape[1:], 8)
                    if c > 0o377:
                        raise source.error('octal escape value %s outside of '
                                           'range 0-0o377' % escape,
                                           len(escape))
                    return LITERAL, c
            # not an octal escape, so this is a group reference
            group = int(escape[1:])
            if group < state.groups:
                if not state.checkgroup(group):
                    raise source.error("cannot refer to an open group",
                                       len(escape))
                state.checklookbehindgroup(group, source)
                return GROUPREF, group
            raise source.error("invalid group reference", len(escape))
        if len(escape) == 2:
            if c in ASCIILETTERS:
                import warnings
                warnings.warn('bad escape %s' % escape,
                              DeprecationWarning, stacklevel=nested + 6)
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise source.error("bad escape %s" % escape, len(escape))

def _parse_sub(source, state, nested):
    # parse an alternation: a|b|c

items = []
    itemsappend = items.append
    sourcematch = source.match
    start = source.tell()
    while True:
        itemsappend(_parse(source, state, nested + 1))
        if not sourcematch("|"):
            break

if len(items) == 1:
        return items[0]

subpattern = SubPattern(state)
    subpatternappend = subpattern.append

# check if all items share a common prefix
    while True:
        prefix = None
        for item in items:
            if not item:
                break
            if prefix is None:
                prefix = item[0]
            elif item[0] != prefix:
                break
        else:
            # all subitems start with a common "prefix".
            # move it out of the branch
            for item in items:
                del item[0]
            subpatternappend(prefix)
            continue # check next one
        break

# check if the branch can be replaced by a character set
    for item in items:
        if len(item) != 1 or item[0][0] is not LITERAL:
            break
    else:
        # we can store this as a character set instead of a
        # branch (the compiler may optimize this even more)
        subpatternappend((IN, [item[0] for item in items]))
        return subpattern

subpattern.append((BRANCH, (None, items)))
    return subpattern

def _parse_sub_cond(source, state, condgroup, nested):
    item_yes = _parse(source, state, nested + 1)
    if source.match("|"):
        item_no = _parse(source, state, nested + 1)
        if source.next == "|":
            raise source.error("conditional backref with more than two branches")
    else:
        item_no = None
    subpattern = SubPattern(state)
    subpattern.append((GROUPREF_EXISTS, (condgroup, item_yes, item_no)))
    return subpattern

def _parse(source, state, nested):
    # parse a simple pattern
    subpattern = SubPattern(state)

# precompute constants into local variables
    subpatternappend = subpattern.append
    sourceget = source.get
    sourcematch = source.match
    _len = len
    _ord = ord
    verbose = state.flags & SRE_FLAG_VERBOSE

while True:

this = source.next
        if this is None:
            break # end of pattern
        if this in "|)":
            break # end of subpattern
        sourceget()

if verbose:
            # skip whitespace and comments
            if this in WHITESPACE:
                continue
            if this == "#":
                while True:
                    this = sourceget()
                    if this is None or this == "\n":
                        break
                continue

if this[0] == "\\":
            code = _escape(source, this, state, nested + 1)
            subpatternappend(code)

elif this not in SPECIAL_CHARS:
            subpatternappend((LITERAL, _ord(this)))

elif this == "[":
            here = source.tell() - 1
            # character set
            set = []
            setappend = set.append
##          if sourcematch(":"):
##              pass # handle character classes
            if sourcematch("^"):
                setappend((NEGATE, None))
            # check remaining characters
            start = set[:]
            while True:
                this = sourceget()
                if this is None:
                    raise source.error("unterminated character set",
                                       source.tell() - here)
                if this == "]" and set != start:
                    break
                elif this[0] == "\\":
                    code1 = _class_escape(source, this, nested + 1)
                else:
                    code1 = LITERAL, _ord(this)
                if sourcematch("-"):
                    # potential range
                    that = sourceget()
                    if that is None:
                        raise source.error("unterminated character set",
                                           source.tell() - here)
                    if that == "]":
                        if code1[0] is IN:
                            code1 = code1[1][0]
                        setappend(code1)
                        setappend((LITERAL, _ord("-")))
                        break
                    if that[0] == "\\":
                        code2 = _class_escape(source, that, nested + 1)
                    else:
                        code2 = LITERAL, _ord(that)
                    if code1[0] != LITERAL or code2[0] != LITERAL:
                        msg = "bad character range %s-%s" % (this, that)
                        raise source.error(msg, len(this) + 1 + len(that))
                    lo = code1[1]
                    hi = code2[1]
                    if hi < lo:
                        msg = "bad character range %s-%s" % (this, that)
                        raise source.error(msg, len(this) + 1 + len(that))
                    setappend((RANGE, (lo, hi)))
                else:
                    if code1[0] is IN:
                        code1 = code1[1][0]
                    setappend(code1)

# XXX: <fl> should move set optimization to compiler!
            if _len(set)==1 and set[0][0] is LITERAL:
                subpatternappend(set[0]) # optimization
            elif _len(set)==2 and set[0][0] is NEGATE and set[1][0] is LITERAL:
                subpatternappend((NOT_LITERAL, set[1][1])) # optimization
            else:
                # XXX: <fl> should add charmap optimization here
                subpatternappend((IN, set))

elif this in REPEAT_CHARS:
            # repeat previous item
            here = source.tell()
            if this == "?":
                min, max = 0, 1
            elif this == "*":
                min, max = 0, MAXREPEAT

elif this == "+":
                min, max = 1, MAXREPEAT
            elif this == "{":
                if source.next == "}":
                    subpatternappend((LITERAL, _ord(this)))
                    continue
                min, max = 0, MAXREPEAT
                lo = hi = ""
                while source.next in DIGITS:
                    lo += sourceget()
                if sourcematch(","):
                    while source.next in DIGITS:
                        hi += sourceget()
                else:
                    hi = lo
                if not sourcematch("}"):
                    subpatternappend((LITERAL, _ord(this)))
                    source.seek(here)
                    continue
                if lo:
                    min = int(lo)
                    if min >= MAXREPEAT:
                        raise OverflowError("the repetition number is too large")
                if hi:
                    max = int(hi)
                    if max >= MAXREPEAT:
                        raise OverflowError("the repetition number is too large")
                    if max < min:
                        raise source.error("min repeat greater than max repeat",
                                           source.tell() - here)
            else:
                raise AssertionError("unsupported quantifier %r" % (char,))
            # figure out which item to repeat
            if subpattern:
                item = subpattern[-1:]
            else:
                item = None
            if not item or (_len(item) == 1 and item[0][0] is AT):
                raise source.error("nothing to repeat",
                                   source.tell() - here + len(this))
            if item[0][0] in _REPEATCODES:
                raise source.error("multiple repeat",
                                   source.tell() - here + len(this))
            if sourcematch("?"):
                subpattern[-1] = (MIN_REPEAT, (min, max, item))
            else:
                subpattern[-1] = (MAX_REPEAT, (min, max, item))

elif this == ".":
            subpatternappend((ANY, None))

elif this == "(":
            start = source.tell() - 1
            group = True
            name = None
            condgroup = None
            if sourcematch("?"):
                # options
                char = sourceget()
                if char is None:
                    raise source.error("unexpected end of pattern")
                if char == "P":
                    # python extensions
                    if sourcematch("<"):
                        # named group: skip forward to end of name
                        name = source.getuntil(">")
                        if not name.isidentifier():
                            msg = "bad character in group name %r" % name
                            raise source.error(msg, len(name) + 1)
                    elif sourcematch("="):
                        # named backreference
                        name = source.getuntil(")")
                        if not name.isidentifier():
                            msg = "bad character in group name %r" % name
                            raise source.error(msg, len(name) + 1)
                        gid = state.groupdict.get(name)
                        if gid is None:
                            msg = "unknown group name %r" % name
                            raise source.error(msg, len(name) + 1)
                        if not state.checkgroup(gid):
                            raise source.error("cannot refer to an open group",
                                               len(name) + 1)
                        state.checklookbehindgroup(gid, source)
                        subpatternappend((GROUPREF, gid))
                        continue
                    else:
                        char = sourceget()
                        if char is None:
                            raise source.error("unexpected end of pattern")
                        raise source.error("unknown extension ?P" + char,
                                           len(char) + 2)
                elif char == ":":
                    # non-capturing group
                    group = None
                elif char == "#":
                    # comment
                    while True:
                        if source.next is None:
                            raise source.error("missing ), unterminated comment",
                                               source.tell() - start)
                        if sourceget() == ")":
                            break
                    continue
                elif char in "=!<":
                    # lookahead assertions
                    dir = 1
                    if char == "<":
                        char = sourceget()
                        if char is None:
                            raise source.error("unexpected end of pattern")
                        if char not in "=!":
                            raise source.error("unknown extension ?<" + char,
                                               len(char) + 2)
                        dir = -1 # lookbehind
                        lookbehindgroups = state.lookbehindgroups
                        if lookbehindgroups is None:
                            state.lookbehindgroups = state.groups
                    p = _parse_sub(source, state, nested + 1)
                    if dir < 0:
                        if lookbehindgroups is None:
                            state.lookbehindgroups = None
                    if not sourcematch(")"):
                        raise source.error("missing ), unterminated subpattern",
                                           source.tell() - start)
                    if char == "=":
                        subpatternappend((ASSERT, (dir, p)))
                    else:
                        subpatternappend((ASSERT_NOT, (dir, p)))
                    continue
                elif char == "(":
                    # conditional backreference group
                    condname = source.getuntil(")")
                    group = None
                    if condname.isidentifier():
                        condgroup = state.groupdict.get(condname)
                        if condgroup is None:
                            msg = "unknown group name %r" % condname
                            raise source.error(msg, len(condname) + 1)
                    else:
                        try:
                            condgroup = int(condname)
                            if condgroup < 0:
                                raise ValueError
                        except ValueError:
                            msg = "bad character in group name %r" % condname
                            raise source.error(msg, len(condname) + 1) from None
                        if not condgroup:
                            raise source.error("bad group number",
                                               len(condname) + 1)
                        if condgroup >= MAXGROUPS:
                            raise source.error("invalid group reference",
                                               len(condname) + 1)
                    state.checklookbehindgroup(condgroup, source)
                elif char in FLAGS:
                    # flags
                    while True:
                        state.flags |= FLAGS[char]
                        char = sourceget()
                        if char is None:
                            raise source.error("missing )")
                        if char == ")":
                            break
                        if char not in FLAGS:
                            raise source.error("unknown flag", len(char))
                    verbose = state.flags & SRE_FLAG_VERBOSE
                    continue
                else:
                    raise source.error("unknown extension ?" + char,
                                       len(char) + 1)

# parse group contents
            if group is not None:
                try:
                    group = state.opengroup(name)
                except error as err:
                    raise source.error(err.msg, len(name) + 1) from None
            if condgroup:
                p = _parse_sub_cond(source, state, condgroup, nested + 1)
            else:
                p = _parse_sub(source, state, nested + 1)
            if not source.match(")"):
                raise source.error("missing ), unterminated subpattern",
                                   source.tell() - start)
            if group is not None:
                state.closegroup(group, p)
            subpatternappend((SUBPATTERN, (group, p)))

elif this == "^":
            subpatternappend((AT, AT_BEGINNING))

elif this == "$":
            subpattern.append((AT, AT_END))

else:
            raise AssertionError("unsupported special character %r" % (char,))

return subpattern

def fix_flags(src, flags):
    # Check and fix flags according to the type of pattern (str or bytes)
    if isinstance(src, str):
        if flags & SRE_FLAG_LOCALE:
            import warnings
            warnings.warn("LOCALE flag with a str pattern is deprecated. "
                          "Will be an error in 3.6",
                          DeprecationWarning, stacklevel=6)
        if not flags & SRE_FLAG_ASCII:
            flags |= SRE_FLAG_UNICODE
        elif flags & SRE_FLAG_UNICODE:
            raise ValueError("ASCII and UNICODE flags are incompatible")
    else:
        if flags & SRE_FLAG_UNICODE:
            raise ValueError("cannot use UNICODE flag with a bytes pattern")
        if flags & SRE_FLAG_LOCALE and flags & SRE_FLAG_ASCII:
            import warnings
            warnings.warn("ASCII and LOCALE flags are incompatible. "
                          "Will be an error in 3.6",
                          DeprecationWarning, stacklevel=6)
    return flags

def parse(str, flags=0, pattern=None):
    # parse 're' pattern into list of (opcode, argument) tuples

source = Tokenizer(str)

if pattern is None:
        pattern = Pattern()
    pattern.flags = flags
    pattern.str = str

p = _parse_sub(source, pattern, 0)
    p.pattern.flags = fix_flags(str, p.pattern.flags)

if source.next is not None:
        assert source.next == ")"
        raise source.error("unbalanced parenthesis")

if not (flags & SRE_FLAG_VERBOSE) and p.pattern.flags & SRE_FLAG_VERBOSE:
        # the VERBOSE flag was switched on inside the pattern.  to be
        # on the safe side, we'll parse the whole thing again...
        return parse(str, p.pattern.flags)

if flags & SRE_FLAG_DEBUG:
        p.dump()

return p

def parse_template(source, pattern):
    # parse 're' replacement string into list of literals and
    # group references
    s = Tokenizer(source)
    sget = s.get
    groups = []
    literals = []
    literal = []
    lappend = literal.append
    def addgroup(index):
        if literal:
            literals.append(''.join(literal))
            del literal[:]
        groups.append((len(literals), index))
        literals.append(None)
    groupindex = pattern.groupindex
    while True:
        this = sget()
        if this is None:
            break # end of replacement string
        if this[0] == "\\":
            # group
            c = this[1]
            if c == "g":
                name = ""
                if not s.match("<"):
                    raise s.error("missing <")
                name = s.getuntil(">")
                if name.isidentifier():
                    try:
                        index = groupindex[name]
                    except KeyError:
                        raise IndexError("unknown group name %r" % name)
                else:
                    try:
                        index = int(name)
                        if index < 0:
                            raise ValueError
                    except ValueError:
                        raise s.error("bad character in group name %r" % name,
                                      len(name) + 1) from None
                    if index >= MAXGROUPS:
                        raise s.error("invalid group reference",
                                      len(name) + 1)
                addgroup(index)
            elif c == "0":
                if s.next in OCTDIGITS:
                    this += sget()
                    if s.next in OCTDIGITS:
                        this += sget()
                lappend(chr(int(this[1:], 8) & 0xff))
            elif c in DIGITS:
                isoctal = False
                if s.next in DIGITS:
                    this += sget()
                    if (c in OCTDIGITS and this[2] in OCTDIGITS and
                        s.next in OCTDIGITS):
                        this += sget()
                        isoctal = True
                        c = int(this[1:], 8)
                        if c > 0o377:
                            raise s.error('octal escape value %s outside of '
                                          'range 0-0o377' % this, len(this))
                        lappend(chr(c))
                if not isoctal:
                    addgroup(int(this[1:]))
            else:
                try:
                    this = chr(ESCAPES[this][1])
                except KeyError:
                    if c in ASCIILETTERS:
                        import warnings
                        warnings.warn('bad escape %s' % this,
                                      DeprecationWarning, stacklevel=4)
                lappend(this)
        else:
            lappend(this)
    if literal:
        literals.append(''.join(literal))
    if not isinstance(source, str):
        # The tokenizer implicitly decodes bytes objects as latin-1, we must
        # therefore re-encode the final representation.
        literals = [None if s is None else s.encode('latin-1') for s in literals]
    return groups, literals

def expand_template(template, match):
    g = match.group
    empty = match.string[:0]
    groups, literals = template
    literals = literals[:]
    try:
        for index, group in groups:
            literals[index] = g(group) or empty
    except IndexError:
        raise error("invalid group reference")
    return empty.join(literals)

${this.title}

Code Editor : sre_parse.py