Gecko [ dallasfobana2023.variationbd.com ]

Name	Size	Permission
__pycache__	[ DIR ]	drwxr-xr-x
collections	[ DIR ]	drwxr-xr-x
concurrent	[ DIR ]	drwxr-xr-x
config-3.3m	[ 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
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
test	[ 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
__future__.py	4.48 KB	-rw-r--r--
__phello__.foo.py	64 B	-rw-r--r--
_compat_pickle.py	4.24 KB	-rw-r--r--
_dummy_thread.py	4.66 KB	-rw-r--r--
_markupbase.py	14.26 KB	-rw-r--r--
_osx_support.py	18.41 KB	-rw-r--r--
_pyio.py	71.2 KB	-rw-r--r--
_strptime.py	21.17 KB	-rw-r--r--
_sysconfigdata.py	22.31 KB	-rw-r--r--
_threading_local.py	7.24 KB	-rw-r--r--
_weakrefset.py	5.57 KB	-rw-r--r--
abc.py	7.87 KB	-rw-r--r--
aifc.py	30.33 KB	-rw-r--r--
antigravity.py	475 B	-rw-r--r--
argparse.py	86.98 KB	-rw-r--r--
ast.py	11.86 KB	-rw-r--r--
asynchat.py	11.32 KB	-rw-r--r--
asyncore.py	20.27 KB	-rw-r--r--
base64.py	13.66 KB	-rwxr-xr-x
bdb.py	21.38 KB	-rw-r--r--
binhex.py	13.39 KB	-rw-r--r--
bisect.py	2.53 KB	-rw-r--r--
bz2.py	18.04 KB	-rw-r--r--
cProfile.py	6.21 KB	-rwxr-xr-x
calendar.py	22.4 KB	-rw-r--r--
cgi.py	34.72 KB	-rwxr-xr-x
cgitb.py	11.76 KB	-rw-r--r--
chunk.py	5.25 KB	-rw-r--r--
cmd.py	14.51 KB	-rw-r--r--
code.py	9.79 KB	-rw-r--r--
codecs.py	35.11 KB	-rw-r--r--
codeop.py	5.85 KB	-rw-r--r--
colorsys.py	3.6 KB	-rw-r--r--
compileall.py	9.51 KB	-rw-r--r--
configparser.py	48.28 KB	-rw-r--r--
contextlib.py	8.91 KB	-rw-r--r--
copy.py	8.78 KB	-rw-r--r--
copyreg.py	6.46 KB	-rw-r--r--
crypt.py	1.83 KB	-rw-r--r--
csv.py	15.81 KB	-rw-r--r--
datetime.py	73.2 KB	-rw-r--r--
decimal.py	223.2 KB	-rw-r--r--
difflib.py	80.58 KB	-rw-r--r--
dis.py	9.9 KB	-rw-r--r--
doctest.py	100.52 KB	-rw-r--r--
dummy_threading.py	2.75 KB	-rw-r--r--
filecmp.py	9.37 KB	-rw-r--r--
fileinput.py	13.92 KB	-rw-r--r--
fnmatch.py	3.09 KB	-rw-r--r--
formatter.py	14.58 KB	-rw-r--r--
fractions.py	22.49 KB	-rw-r--r--
ftplib.py	39.31 KB	-rw-r--r--
functools.py	13.28 KB	-rw-r--r--
genericpath.py	3.02 KB	-rw-r--r--
getopt.py	7.31 KB	-rw-r--r--
getpass.py	5.66 KB	-rw-r--r--
gettext.py	20.15 KB	-rw-r--r--
glob.py	2.77 KB	-rw-r--r--
gzip.py	23.83 KB	-rw-r--r--
hashlib.py	6.05 KB	-rw-r--r--
heapq.py	17.58 KB	-rw-r--r--
hmac.py	4.34 KB	-rw-r--r--
imaplib.py	48.94 KB	-rw-r--r--
imghdr.py	3.45 KB	-rw-r--r--
imp.py	9.5 KB	-rw-r--r--
inspect.py	77.11 KB	-rw-r--r--
io.py	3.2 KB	-rw-r--r--
ipaddress.py	68.66 KB	-rw-r--r--
keyword.py	2.01 KB	-rwxr-xr-x
linecache.py	3.77 KB	-rw-r--r--
locale.py	91.03 KB	-rw-r--r--
lzma.py	17.04 KB	-rw-r--r--
macpath.py	5.49 KB	-rw-r--r--
macurl2path.py	2.67 KB	-rw-r--r--
mailbox.py	77.24 KB	-rw-r--r--
mailcap.py	7.26 KB	-rw-r--r--
mimetypes.py	20.25 KB	-rw-r--r--
modulefinder.py	22.65 KB	-rw-r--r--
netrc.py	5.61 KB	-rw-r--r--
nntplib.py	41.78 KB	-rw-r--r--
ntpath.py	19.96 KB	-rw-r--r--
nturl2path.py	2.34 KB	-rw-r--r--
numbers.py	10.15 KB	-rw-r--r--
opcode.py	4.98 KB	-rw-r--r--
optparse.py	58.93 KB	-rw-r--r--
os.py	33.96 KB	-rw-r--r--
os2emxpath.py	4.55 KB	-rw-r--r--
pdb.py	59.23 KB	-rwxr-xr-x
pickle.py	46.74 KB	-rw-r--r--
pickletools.py	79.44 KB	-rw-r--r--
pipes.py	8.71 KB	-rw-r--r--
pkgutil.py	21.03 KB	-rw-r--r--
platform.py	49.55 KB	-rwxr-xr-x
plistlib.py	14.43 KB	-rw-r--r--
poplib.py	11.11 KB	-rw-r--r--
posixpath.py	13.92 KB	-rw-r--r--
pprint.py	12.4 KB	-rw-r--r--
profile.py	20.95 KB	-rwxr-xr-x
pstats.py	25.75 KB	-rw-r--r--
pty.py	4.94 KB	-rw-r--r--
py_compile.py	6.56 KB	-rw-r--r--
pyclbr.py	13.12 KB	-rw-r--r--
pydoc.py	99.26 KB	-rwxr-xr-x
queue.py	8.63 KB	-rw-r--r--
quopri.py	7.14 KB	-rwxr-xr-x
random.py	25.06 KB	-rw-r--r--
re.py	14.62 KB	-rw-r--r--
reprlib.py	4.99 KB	-rw-r--r--
rlcompleter.py	5.4 KB	-rw-r--r--
runpy.py	10.17 KB	-rw-r--r--
sched.py	6.25 KB	-rw-r--r--
shelve.py	8.05 KB	-rw-r--r--
shlex.py	11.23 KB	-rw-r--r--
shutil.py	38.23 KB	-rw-r--r--
site.py	21.46 KB	-rw-r--r--
smtpd.py	29.5 KB	-rwxr-xr-x
smtplib.py	37.13 KB	-rwxr-xr-x
sndhdr.py	6.07 KB	-rw-r--r--
socket.py	14.56 KB	-rw-r--r--
socketserver.py	23.63 KB	-rw-r--r--
sre_compile.py	15.96 KB	-rw-r--r--
sre_constants.py	7.06 KB	-rw-r--r--
sre_parse.py	29.5 KB	-rw-r--r--
ssl.py	23.9 KB	-rw-r--r--
stat.py	4.2 KB	-rw-r--r--
string.py	9.19 KB	-rw-r--r--
stringprep.py	12.61 KB	-rw-r--r--
struct.py	238 B	-rw-r--r--
subprocess.py	65.99 KB	-rw-r--r--
sunau.py	17.11 KB	-rw-r--r--
symbol.py	2 KB	-rwxr-xr-x
symtable.py	7.21 KB	-rw-r--r--
sysconfig.py	24.58 KB	-rw-r--r--
tabnanny.py	11.14 KB	-rwxr-xr-x
tarfile.py	86.78 KB	-rwxr-xr-x
telnetlib.py	26.71 KB	-rw-r--r--
tempfile.py	22.47 KB	-rw-r--r--
textwrap.py	16.1 KB	-rw-r--r--
this.py	1003 B	-rw-r--r--
threading.py	44.57 KB	-rw-r--r--
timeit.py	12.1 KB	-rwxr-xr-x
token.py	2.96 KB	-rw-r--r--
tokenize.py	24.29 KB	-rw-r--r--
trace.py	30.75 KB	-rwxr-xr-x
traceback.py	11.7 KB	-rw-r--r--
tty.py	879 B	-rw-r--r--
types.py	3.09 KB	-rw-r--r--
uu.py	6.61 KB	-rwxr-xr-x
uuid.py	21.83 KB	-rw-r--r--
warnings.py	13.5 KB	-rw-r--r--
wave.py	18.14 KB	-rw-r--r--
weakref.py	11.23 KB	-rw-r--r--
webbrowser.py	22.38 KB	-rwxr-xr-x
xdrlib.py	5.25 KB	-rw-r--r--
zipfile.py	64.87 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

import sys

from sre_constants import *

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

DIGITS = set("0123456789")

OCTDIGITS = set("01234567")
HEXDIGITS = set("0123456789abcdefABCDEF")

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

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.open = []
        self.groups = 1
        self.groupdict = {}
    def opengroup(self, name=None):
        gid = self.groups
        self.groups = gid + 1
        if name is not None:
            ogid = self.groupdict.get(name, None)
            if ogid is not None:
                raise error("redefinition of group name %s as group %d; "
                            "was group %d" % (repr(name), gid,  ogid))
            self.groupdict[name] = gid
        self.open.append(gid)
        return gid
    def closegroup(self, gid):
        self.open.remove(gid)
    def checkgroup(self, gid):
        return gid < self.groups and gid not in self.open

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 = 1
        seqtypes = (tuple, list)
        for op, av in self.data:
            print(level*"  " + op, end=' '); nl = 0
            if op == "in":
                # member sublanguage
                print(); nl = 1
                for op, a in av:
                    print((level+1)*"  " + op, a)
            elif op == "branch":
                print(); nl = 1
                i = 0
                for a in av[1]:
                    if i > 0:
                        print(level*"  " + "or")
                    a.dump(level+1); nl = 1
                    i = i + 1
            elif isinstance(av, seqtypes):
                for a in av:
                    if isinstance(a, SubPattern):
                        if not nl: print()
                        a.dump(level+1); nl = 1
                    else:
                        print(a, end=' ') ; nl = 0
            else:
                print(av, end=' ') ; nl = 0
            if not nl: print()
    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:
            return self.width
        lo = hi = 0
        UNITCODES = (ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY)
        REPEATCODES = (MIN_REPEAT, MAX_REPEAT)
        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 == 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
        self.index = 0
        self.__next()
    def __next(self):
        if self.index >= len(self.string):
            self.next = None
            return
        char = self.string[self.index:self.index+1]
        # Special case for the str8, since indexing returns a integer
        # XXX This is only needed for test_bug_926075 in test_re.py
        if char and not self.istext:
            char = chr(char[0])
        if char == "\\":
            try:
                c = self.string[self.index + 1]
            except IndexError:
                raise error("bogus escape (end of line)")
            if not self.istext:
                c = chr(c)
            char = char + c
        self.index = self.index + len(char)
        self.next = char
    def match(self, char, skip=1):
        if char == self.next:
            if skip:
                self.__next()
            return 1
        return 0
    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 tell(self):
        return self.index, self.next
    def seek(self, index):
        self.index, self.next = index

# 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):
    # handle escape code inside character class
    code = ESCAPES.get(escape)
    if code:
        return code
    code = CATEGORIES.get(escape)
    if code and code[0] == 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 ValueError
            return LITERAL, int(escape[2:], 16) & 0xff
        elif c == "u" and source.istext:
            # unicode escape (exactly four digits)
            escape += source.getwhile(4, HEXDIGITS)
            if len(escape) != 6:
                raise ValueError
            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 ValueError
            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)
            return LITERAL, int(escape[1:], 8) & 0xff
        elif c in DIGITS:
            raise ValueError
        if len(escape) == 2:
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise error("bogus escape: %s" % repr(escape))

def _escape(source, escape, state):
    # 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 ValueError
            return LITERAL, int(escape[2:], 16) & 0xff
        elif c == "u" and source.istext:
            # unicode escape (exactly four digits)
            escape += source.getwhile(4, HEXDIGITS)
            if len(escape) != 6:
                raise ValueError
            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 ValueError
            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) & 0xff
        elif c in DIGITS:
            # octal escape *or* decimal group reference (sigh)
            if source.next in DIGITS:
                escape = 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 = escape + source.get()
                    return LITERAL, int(escape[1:], 8) & 0xff
            # not an octal escape, so this is a group reference
            group = int(escape[1:])
            if group < state.groups:
                if not state.checkgroup(group):
                    raise error("cannot refer to open group")
                return GROUPREF, group
            raise ValueError
        if len(escape) == 2:
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise error("bogus escape: %s" % repr(escape))

def _parse_sub(source, state, nested=1):
    # parse an alternation: a|b|c

items = []
    itemsappend = items.append
    sourcematch = source.match
    while 1:
        itemsappend(_parse(source, state))
        if sourcematch("|"):
            continue
        if not nested:
            break
        if not source.next or sourcematch(")", 0):
            break
        else:
            raise error("pattern not properly closed")

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

subpattern = SubPattern(state)
    subpatternappend = subpattern.append

# check if all items share a common prefix
    while 1:
        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] != LITERAL:
            break
    else:
        # we can store this as a character set instead of a
        # branch (the compiler may optimize this even more)
        set = []
        setappend = set.append
        for item in items:
            setappend(item[0])
        subpatternappend((IN, set))
        return subpattern

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

def _parse_sub_cond(source, state, condgroup):
    item_yes = _parse(source, state)
    if source.match("|"):
        item_no = _parse(source, state)
        if source.match("|"):
            raise error("conditional backref with more than two branches")
    else:
        item_no = None
    if source.next and not source.match(")", 0):
        raise error("pattern not properly closed")
    subpattern = SubPattern(state)
    subpattern.append((GROUPREF_EXISTS, (condgroup, item_yes, item_no)))
    return subpattern

_PATTERNENDERS = set("|)")
_ASSERTCHARS = set("=!<")
_LOOKBEHINDASSERTCHARS = set("=!")
_REPEATCODES = set([MIN_REPEAT, MAX_REPEAT])

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

# precompute constants into local variables
    subpatternappend = subpattern.append
    sourceget = source.get
    sourcematch = source.match
    _len = len
    PATTERNENDERS = _PATTERNENDERS
    ASSERTCHARS = _ASSERTCHARS
    LOOKBEHINDASSERTCHARS = _LOOKBEHINDASSERTCHARS
    REPEATCODES = _REPEATCODES

while 1:

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

if state.flags & SRE_FLAG_VERBOSE:
            # skip whitespace and comments
            if this in WHITESPACE:
                continue
            if this == "#":
                while 1:
                    this = sourceget()
                    if this in (None, "\n"):
                        break
                continue

if this and this[0] not in SPECIAL_CHARS:
            subpatternappend((LITERAL, ord(this)))

elif this == "[":
            # character set
            set = []
            setappend = set.append
##          if sourcematch(":"):
##              pass # handle character classes
            if sourcematch("^"):
                setappend((NEGATE, None))
            # check remaining characters
            start = set[:]
            while 1:
                this = sourceget()
                if this == "]" and set != start:
                    break
                elif this and this[0] == "\\":
                    code1 = _class_escape(source, this)
                elif this:
                    code1 = LITERAL, ord(this)
                else:
                    raise error("unexpected end of regular expression")
                if sourcematch("-"):
                    # potential range
                    this = sourceget()
                    if this == "]":
                        if code1[0] is IN:
                            code1 = code1[1][0]
                        setappend(code1)
                        setappend((LITERAL, ord("-")))
                        break
                    elif this:
                        if this[0] == "\\":
                            code2 = _class_escape(source, this)
                        else:
                            code2 = LITERAL, ord(this)
                        if code1[0] != LITERAL or code2[0] != LITERAL:
                            raise error("bad character range")
                        lo = code1[1]
                        hi = code2[1]
                        if hi < lo:
                            raise error("bad character range")
                        setappend((RANGE, (lo, hi)))
                    else:
                        raise error("unexpected end of regular expression")
                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 and this[0] in REPEAT_CHARS:
            # repeat previous item
            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
                here = source.tell()
                min, max = 0, MAXREPEAT
                lo = hi = ""
                while source.next in DIGITS:
                    lo = lo + source.get()
                if sourcematch(","):
                    while source.next in DIGITS:
                        hi = 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 error("bad repeat interval")
            else:
                raise error("not supported")
            # 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] == AT):
                raise error("nothing to repeat")
            if item[0][0] in REPEATCODES:
                raise error("multiple repeat")
            if sourcematch("?"):
                subpattern[-1] = (MIN_REPEAT, (min, max, item))
            else:
                subpattern[-1] = (MAX_REPEAT, (min, max, item))

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

elif this == "(":
            group = 1
            name = None
            condgroup = None
            if sourcematch("?"):
                group = 0
                # options
                if sourcematch("P"):
                    # python extensions
                    if sourcematch("<"):
                        # named group: skip forward to end of name
                        name = ""
                        while 1:
                            char = sourceget()
                            if char is None:
                                raise error("unterminated name")
                            if char == ">":
                                break
                            name = name + char
                        group = 1
                        if not name:
                            raise error("missing group name")
                        if not name.isidentifier():
                            raise error("bad character in group name %r" % name)
                    elif sourcematch("="):
                        # named backreference
                        name = ""
                        while 1:
                            char = sourceget()
                            if char is None:
                                raise error("unterminated name")
                            if char == ")":
                                break
                            name = name + char
                        if not name:
                            raise error("missing group name")
                        if not name.isidentifier():
                            raise error("bad character in backref group name "
                                        "%r" % name)
                        gid = state.groupdict.get(name)
                        if gid is None:
                            raise error("unknown group name")
                        subpatternappend((GROUPREF, gid))
                        continue
                    else:
                        char = sourceget()
                        if char is None:
                            raise error("unexpected end of pattern")
                        raise error("unknown specifier: ?P%s" % char)
                elif sourcematch(":"):
                    # non-capturing group
                    group = 2
                elif sourcematch("#"):
                    # comment
                    while 1:
                        if source.next is None or source.next == ")":
                            break
                        sourceget()
                    if not sourcematch(")"):
                        raise error("unbalanced parenthesis")
                    continue
                elif source.next in ASSERTCHARS:
                    # lookahead assertions
                    char = sourceget()
                    dir = 1
                    if char == "<":
                        if source.next not in LOOKBEHINDASSERTCHARS:
                            raise error("syntax error")
                        dir = -1 # lookbehind
                        char = sourceget()
                    p = _parse_sub(source, state)
                    if not sourcematch(")"):
                        raise error("unbalanced parenthesis")
                    if char == "=":
                        subpatternappend((ASSERT, (dir, p)))
                    else:
                        subpatternappend((ASSERT_NOT, (dir, p)))
                    continue
                elif sourcematch("("):
                    # conditional backreference group
                    condname = ""
                    while 1:
                        char = sourceget()
                        if char is None:
                            raise error("unterminated name")
                        if char == ")":
                            break
                        condname = condname + char
                    group = 2
                    if not condname:
                        raise error("missing group name")
                    if condname.isidentifier():
                        condgroup = state.groupdict.get(condname)
                        if condgroup is None:
                            raise error("unknown group name")
                    else:
                        try:
                            condgroup = int(condname)
                        except ValueError:
                            raise error("bad character in group name")
                else:
                    # flags
                    if not source.next in FLAGS:
                        raise error("unexpected end of pattern")
                    while source.next in FLAGS:
                        state.flags = state.flags | FLAGS[sourceget()]
            if group:
                # parse group contents
                if group == 2:
                    # anonymous group
                    group = None
                else:
                    group = state.opengroup(name)
                if condgroup:
                    p = _parse_sub_cond(source, state, condgroup)
                else:
                    p = _parse_sub(source, state)
                if not sourcematch(")"):
                    raise error("unbalanced parenthesis")
                if group is not None:
                    state.closegroup(group)
                subpatternappend((SUBPATTERN, (group, p)))
            else:
                while 1:
                    char = sourceget()
                    if char is None:
                        raise error("unexpected end of pattern")
                    if char == ")":
                        break
                    raise error("unknown extension")

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

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

elif this and this[0] == "\\":
            code = _escape(source, this, state)
            subpatternappend(code)

else:
            raise error("parser error")

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 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("can't use UNICODE flag with a bytes pattern")
    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)

tail = source.get()
    if tail == ")":
        raise error("unbalanced parenthesis")
    elif tail:
        raise error("bogus characters at end of regular expression")

if flags & SRE_FLAG_DEBUG:
        p.dump()

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)

return p

def parse_template(source, pattern):
    # parse 're' replacement string into list of literals and
    # group references
    s = Tokenizer(source)
    sget = s.get
    p = []
    a = p.append
    def literal(literal, p=p, pappend=a):
        if p and p[-1][0] is LITERAL:
            p[-1] = LITERAL, p[-1][1] + literal
        else:
            pappend((LITERAL, literal))
    sep = source[:0]
    if isinstance(sep, str):
        makechar = chr
    else:
        makechar = chr
    while 1:
        this = sget()
        if this is None:
            break # end of replacement string
        if this and this[0] == "\\":
            # group
            c = this[1:2]
            if c == "g":
                name = ""
                if s.match("<"):
                    while 1:
                        char = sget()
                        if char is None:
                            raise error("unterminated group name")
                        if char == ">":
                            break
                        name = name + char
                if not name:
                    raise error("missing group name")
                try:
                    index = int(name)
                    if index < 0:
                        raise error("negative group number")
                except ValueError:
                    if not name.isidentifier():
                        raise error("bad character in group name")
                    try:
                        index = pattern.groupindex[name]
                    except KeyError:
                        raise IndexError("unknown group name")
                a((MARK, index))
            elif c == "0":
                if s.next in OCTDIGITS:
                    this = this + sget()
                    if s.next in OCTDIGITS:
                        this = this + sget()
                literal(makechar(int(this[1:], 8) & 0xff))
            elif c in DIGITS:
                isoctal = False
                if s.next in DIGITS:
                    this = this + sget()
                    if (c in OCTDIGITS and this[2] in OCTDIGITS and
                        s.next in OCTDIGITS):
                        this = this + sget()
                        isoctal = True
                        literal(makechar(int(this[1:], 8) & 0xff))
                if not isoctal:
                    a((MARK, int(this[1:])))
            else:
                try:
                    this = makechar(ESCAPES[this][1])
                except KeyError:
                    pass
                literal(this)
        else:
            literal(this)
    # convert template to groups and literals lists
    i = 0
    groups = []
    groupsappend = groups.append
    literals = [None] * len(p)
    if isinstance(source, str):
        encode = lambda x: x
    else:
        # The tokenizer implicitly decodes bytes objects as latin-1, we must
        # therefore re-encode the final representation.
        encode = lambda x: x.encode('latin-1')
    for c, s in p:
        if c is MARK:
            groupsappend((i, s))
            # literal[i] is already None
        else:
            literals[i] = encode(s)
        i = i + 1
    return groups, literals

def expand_template(template, match):
    g = match.group
    sep = match.string[:0]
    groups, literals = template
    literals = literals[:]
    try:
        for index, group in groups:
            literals[index] = s = g(group)
            if s is None:
                raise error("unmatched group")
    except IndexError:
        raise error("invalid group reference")
    return sep.join(literals)

${this.title}

Code Editor : sre_parse.py