GIF89a=( õ' 7IAXKgNgYvYx\%wh…hŽth%ˆs%—x¨}9®Œ©€&©‰%¶†(¹–.¹5·œD¹&Çš)ÇŸ5ǘ;Í£*È¡&Õ²)ׯ7×µ<Ñ»4ï°3ø‘HÖ§KͯT÷¨Yÿšqÿ»qÿÔFØ !ù ' !ÿ NETSCAPE2.0 , =( þÀ“pH,È¤rÉl:ŸÐ¨tJ­Z¯Ø¬vËíz¿à°xL.›Ïè´zÍn»ßð¸|N¯Ûïø¼~Ïïûÿ€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§gª«ªE¯°¨¬ª±²Œ¹º¹E¾­”´ÂB¶¯ §Åȸ»ÑD¾¿Á•ÄÅ®° ÝH¾ÒLÀÆDÙ«D¶BÝïðÀ¾DÑÑÔTÌÍíH òGö¨A RÎڐ |¥ ٭&ºìE8œ¹kGÔAÞpx­a¶­ã R2XB®åE8I€Õ6Xî:vT)äžþÀq¦è³¥ì仕F~%xñ  4#ZÔ‰O|-4Bs‘X:= QÉ œš lºÒyXJŠGȦ|s hÏíK–3l7·B|¥$'7Jީܪ‰‡àá”Dæn=Pƒ ¤Òëí‰`䌨ljóá¯Éüv>á–Á¼5 ½.69ûϸd«­ºÀûnlv©‹ªîf{¬ÜãPbŸ  l5‘Ž¯pß ´ ˜3aÅùäI«O’ý·‘áÞ‡˜¾Æ‚ÙÏiÇÿ‹Àƒ #öó)pâš Þ½ ‘Ý{ó)vmÞü%D~ 6f s}ŃƒDØW Eþ`‡þ À…L8xá†ç˜{)x`X/> Ì}mø‚–RØ‘*|`D=‚Ø_ ^ð5 !_…'aä“OÚ—7âcð`D”Cx`ÝÂ¥ä‹éY¹—F¼¤¥Š?¡Õ™ n@`} lď’ÄÉ@4>ñd œ à‘vÒxNÃ×™@žd=ˆgsžG±æ ´²æud &p8Qñ)ˆ«lXD©øÜéAžHìySun jª×k*D¤LH] †¦§C™Jä–´Xb~ʪwStŽ6K,°£qÁœ:9ت:¨þªl¨@¡`‚ûÚ ».Û¬¯t‹ÆSÉ[:°=Š‹„‘Nåû”Ìî{¿ÂA ‡Rà›ÀÙ6úë°Ÿð0Ä_ ½;ÃϱîÉì^ÇÛÇ#Ëë¼ôº!±Ä˜íUîÅÇ;0L1óÁµö«p% AÀºU̬ݵ¼á%霼€‡¯Á~`ÏG¯»À× ­²± =4ªnpð3¾¤³¯­ü¾¦îuÙuµÙ®|%2ÊIÿür¦#0·ÔJ``8È@S@5ê¢ ö×Þ^`8EÜ]ý.뜃Âç 7 ú ȉÞj œ½Dç zý¸iþœÑÙûÄë!ˆÞÀl§Ïw‹*DçI€nEX¯¬¼ &A¬Go¼QföõFç°¯;é¦÷îŽêJ°îúôF5¡ÌQ|îúöXªæ»TÁÏyñêï]ê² o óÎC=öõ›ÒÓPB@ D×½œä(>èCÂxŽ`±«Ÿ–JЀ»Û á¤±p+eE0`ëŽ`A Ú/NE€Ø†À9‚@¤à H½7”à‡%B‰`Àl*ƒó‘–‡8 2ñ%¸ —€:Ù1Á‰E¸àux%nP1ð!‘ðC)¾P81lÑɸF#ˆ€{´âé°ÈB„0>±û °b¡Š´±O‚3È–Ù()yRpbµ¨E.Z‘D8ÊH@% òŒx+%Ù˜Æcü »¸˜fõ¬b·d`Fê™8èXH"ÉÈ-±|1Ô6iI, 2““¬$+](A*jÐ QTÂo‰.ÛU슬Œã„Ž`¯SN¡–¶Äåyše¯ª’­¬‚´b¦Éož œ)åyâ@Ì®3 ÎtT̉°&Ø+žLÀf"Ø-|žçÔ>‡Ðv¦Ðžì\‚ Q1)Ž@Žh#aP72”ˆ™¨$‚ !ù " , =( …7IAXG]KgNgYvYxR"k\%w]'}hŽth%ˆg+ˆs%—r.—m3šx3˜x¨}9®€&©€+¨‡7§‰%¶†(¹–.¹œD¹&ǘ;Í•&ײ)×»4ïÌ6ò§KÍ þ@‘pH,È¤rÉl:ŸÐ¨tJ­Z¯Ø¬vËíz¿à°xL.›Ïè´zÍn»ßð¸|N¯Ûïø¼~Ïïûÿ€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§g «¬ E ±± ¨­¶°ººE Á´”·®C¬²§Ç¶Œ»ÓDÃÕƷ¯Ê±H½ºM×ÁGÚ¬D¶BËÁ½î½DÓôTÏÛßîG»ôõC×CÌ l&âž:'òtU³6ɹ#·Ø)€'Ü.6±&ëÍÈ» K(8p0N?!æ2"ÛˆNIJX>R¼ÐO‚M '¡¨2¸*Ÿþ>#n↠å@‚<[:¡Iïf’ ¤TÚ˘CdbÜÙ“[«ŽEú5MBo¤×@€`@„€Êt W-3 ¶Ÿ¡BíêäjIÝ…Eò9[T…$íêﯧ„…•s»Óȳ¹€ÅÚdc®UUρ#±Ùïldj?´í¼²`\ŽÁðÞu|3'ÖŒ]ë6 ¶S#²‡˜FKLÈ *N E´‘áäŠ$˜›eÄYD„ºq«.è촁ƒs \-ÔjA 9²õ÷å- üúM[Âx(ís÷ì®x€|í¡Ù’p¦‚ ŽkÛTÇDpE@WÜ ²Ç]kŠ1¨ þ€·Yb ÓÁ‰l°*n0 ç™—žzBdОu¾7ĉBl€â‰-ºx~|UåU‰  h*Hœ|e"#"?vpÄiŠe6^ˆ„+qâŠm8 #VÇá ‘å–ÄV„œ|Šè•m"сœn|@›U¶ÆΞ—Špb¥G¨ED”€±Úê2FÌIç? >Éxå Œ± ¡¤„%‘žjŸ‘ꄯ<Ìaà9ijÐ2˜D¦È&›†Z`‚å]wþ¼Â:ç6àB¤7eFJ|õÒ§Õ,¨äàFÇ®cS·Ê¶+B°,‘Þ˜ºNûãØ>PADÌHD¹æž«ÄÀnÌ¥}­#Ë’ë QÀÉSÌÂÇ2ÌXÀ{æk²lQÁ2«ÊðÀ¯w|2Í h‹ÄÂG€,m¾¶ë3ÐÙ6-´ÅE¬L°ÆIij*K½ÀÇqï`DwVÍQXœÚÔpeœ±¬Ñ q˜§Tœ½µƒ°Œìu Â<¶aØ*At¯lmEØ ü ôÛN[P1ÔÛ¦­±$ÜÆ@`ùåDpy¶yXvCAyåB`ŽD¶ 0QwG#¯ æš[^Äþ $ÀÓÝǦ{„L™[±úKÄgÌ;ï£S~¹ìGX.ôgoT.»åˆ°ùŸûù¡?1zö¦Ÿž:ÅgÁ|ìL¹ „®£œŠ‚à0œ]PÁ^p F<"•ç?!,ñ‡N4—…PÄ Á„ö¨Û:Tè@hÀ‹%táÿ:ø-žI<`þ‹p I….)^ 40D#p@ƒj4–؀:²‰1Øâr˜¼F2oW¼#Z†;$Q q” ‘ ÂK¦ñNl#29 !’F@¥Bh·ᏀL!—XFóLH‘Kh¤.«hE&JòG¨¥<™WN!€ÑÙÚˆY„@†>Œž19J" 2,/ &.GXB%ÌRÈ9B6¹W]’î×ÔW¥’IÎ$ ñ‹ÓŒE8YÆ ¼³™ñA5“à®Q.aŸB€&Ø©³ JÁ—! ¦t)K%tœ-¦JF bòNMxLôþ)ÐR¸Ð™‘ èÝ6‘O!THÌ„HÛ ‰ !ù ) , =( …AXKgNgYvYxR"k\%wh…hŽh%ˆg+ˆs%—r.—x3˜x¨}9®€&©€+¨Œ,©‡7§‰%¶†(¹–.¹5·&Çš)ǘ;Í•&×£*Ȳ)ׯ7×»4ï°3øÌ6ò‘HÖ§KÍ»Hó¯T÷¨Yÿ»qÿÇhÿ þÀ”pH,È¤rÉl:ŸÐ¨tJ­Z¯Ø¬vËíz¿à°xL.›Ïè´zÍn»ßð¸|N¯Ûïø¼~Ïïûÿ€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§g ª« E$±²¨ª­ · °²½$E$ÂÕ««D· Í ¿¦Ç¶¸ÌŒ¾³CÃÅÆ E ééH½MÛÂGâªD­ çBêêϾD²ÒaÀà€Š1r­ðÓ¤ ÔožzU!L˜C'¾yW½UGtäÇïÙllê0×àÂuGþ)AÀs[þ·xì ÁxO%ƒûX2ó—  P£n›R/¡ÑšHše+êDm?# —‘Ç£6¡8íJ¡ŸâDiäªM¥Ö„ôj“¬¹£5oQ7°- <‡ *´lãÓŒ2r/a!l)dÈ A™ÈE¢ôÔ͆…ð ;Ö˜c ¡%ß‚’Ùˆâ¸b½—pe~C"BíëÚHïeF2§æŠ8qb t_`urŠeü wÅu3êæPv§h•"ß`íÍxçLĹÜÖ3á  ~Öº“®›¸ÏMDfJÙ °„ÛµáWõ%§œ‚à©–‚X Ó؁)@®Ñ›Eþ´wëuÅSxb8y\mÖzœ¥§ZbºE—ÂLªÌw!y(>¡™wú=Ç|ÅÝs¢d €CÁW)HÜcC$€L Ä7„r.á\{)@ð` @ äXÈ$PD” `šaG:§æˆOˆ72EÐamn]ù"ŒcÊxÑŒ° &dR8`g«iÙŸLR!¦P …d’ä¡“¦ðÎTƒ¦ià|À _ ¥ Qi#¦Šg›Æ ›noMµ ›V ã£)p ç£ÎW…š=Âeªk§†j„ ´®1ß²sÉxéW«jšl|0¯B0Û, \jÛ´›6±¬¶C ÛíWþï|ëÙ‹¸ñzĸV {ì;Ýñn¼òVˆm³I¼³.Ðã¤PN¥ ²µ¼„µCã+¹ÍByî£Ñ¾HŸ›ëê 7ìYÆFTk¨SaoaY$Dµœìï¿Ã29RÈkt Çïfñ ÇÒ:ÀÐSp¹3ÇI¨â¥DZÄ ü9Ïýögñ½­uÔ*3)O‘˜Ö[_hv ,àî×Et Ÿé¶BH€ Õ[ü±64M@ÔSÌM7dÐl5-ÄÙU܍´©zߌ3Ô€3ž„ „ ¶ÛPô½5×g› êÚ˜kN„Ý…0Îj4€Ìë°“#{þÕ3S2çKÜ'ợlø¼Ú2K{° {Û¶?žm𸧠ËI¼nEò='êüóºè^üæÃ_Û=°óž‚ì#Oý¿Í'¡½áo..ÏYìnüñCœO±Áa¿¢Kô½o,üÄËbö²çºíï{ËC Ú— "”Ï{ËK ÍÒw„õ±Oz dÕ¨à:$ ƒô—«v»] A#ð «€¿šéz)Rx׿ˆ¥‚d``èw-îyÏf×K!ð€þ­Ð|ìPľ„=Ì`ý(f” 'Pa ¥ÐBJa%Ðâf§„%Š¡}FàáÝ×6>ÉäŠG"éŽè=ø!oŠ°^FP¼Ø©Q„ÀCÙÁ`(Ž\ÄÝ® ©Â$<n@dÄ E#ììUÒI! ‚#lù‹`k¦ÐÇ'Rró’ZýNBÈMF Í[¤+‹ðɈ-áwj¨¥þ8¾rá ,VÂh„"|½œ=×G_¦Ñ™EØ 0i*%̲˜Æda0mV‚k¾)›;„&6 p>ÓjK “¦Ç# âDÂ:ûc?:R Ó¬fÞéI-Ì“•Ã<ä=™Ï7˜3œ¨˜c2ŒW ,ˆ”8(T™P‰F¡Jhç"‚ ; 403WebShell
403Webshell
Server IP : 172.67.177.218  /  Your IP : 216.73.216.195
Web Server : LiteSpeed
System : Linux premium229.web-hosting.com 4.18.0-553.45.1.lve.el8.x86_64 #1 SMP Wed Mar 26 12:08:09 UTC 2025 x86_64
User : akhalid ( 749)
PHP Version : 8.3.22
Disable Function : NONE
MySQL : OFF  |  cURL : ON  |  WGET : ON  |  Perl : ON  |  Python : ON  |  Sudo : OFF  |  Pkexec : OFF
Directory :  /lib64/python2.7/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :

[ Back ]     

Current File : /lib64/python2.7/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")
ASCIILETTERS = set("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ")

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
    "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 = {}
        self.lookbehind = 0

    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):
        seqtypes = (tuple, list)
        for op, av in self.data:
            print level*"  " + op,
            if op == IN:
                # member sublanguage
                print
                for op, a in av:
                    print (level+1)*"  " + op, a
            elif op == BRANCH:
                print
                for i, a in enumerate(av[1]):
                    if i:
                        print level*"  " + "or"
                    a.dump(level+1)
            elif op == 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 = 0
                for a in av:
                    if isinstance(a, SubPattern):
                        if not nl:
                            print
                        a.dump(level+1)
                        nl = 1
                    else:
                        print a,
                        nl = 0
                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:
            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.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]
        if char[0] == "\\":
            try:
                c = self.string[self.index + 1]
            except IndexError:
                raise error, "bogus escape (end of line)"
            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 tell(self):
        return self.index, self.next
    def seek(self, index):
        self.index, self.next = index

def isident(char):
    return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_"

def isdigit(char):
    return "0" <= char <= "9"

def isname(name):
    # 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] == IN:
        return code
    try:
        c = escape[1:2]
        if c == "x":
            # hexadecimal escape (exactly two digits)
            while source.next in HEXDIGITS and len(escape) < 4:
                escape = escape + source.get()
            escape = escape[2:]
            if len(escape) != 2:
                raise error, "bogus escape: %s" % repr("\\" + escape)
            return LITERAL, int(escape, 16) & 0xff
        elif c in OCTDIGITS:
            # octal escape (up to three digits)
            while source.next in OCTDIGITS and len(escape) < 4:
                escape = escape + source.get()
            escape = escape[1:]
            return LITERAL, int(escape, 8) & 0xff
        elif c in DIGITS:
            raise error, "bogus escape: %s" % repr(escape)
        if len(escape) == 2:
            if sys.py3kwarning and c in ASCIILETTERS:
                import warnings
                if c in 'Uu':
                    warnings.warn('bad escape %s; Unicode escapes are '
                                  'supported only since Python 3.3' % escape,
                                  FutureWarning, stacklevel=nested + 6)
                else:
                    warnings.warnpy3k('bad escape %s' % escape,
                                      DeprecationWarning, stacklevel=nested + 6)
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise error, "bogus escape: %s" % repr(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
            while source.next in HEXDIGITS and len(escape) < 4:
                escape = escape + source.get()
            if len(escape) != 4:
                raise ValueError
            return LITERAL, int(escape[2:], 16) & 0xff
        elif c == "0":
            # octal escape
            while source.next in OCTDIGITS and len(escape) < 4:
                escape = escape + source.get()
            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"
                if state.lookbehind:
                    import warnings
                    warnings.warn('group references in lookbehind '
                                  'assertions are not supported',
                                  RuntimeWarning, stacklevel=nested + 6)
                return GROUPREF, group
            raise ValueError
        if len(escape) == 2:
            if sys.py3kwarning and c in ASCIILETTERS:
                import warnings
                if c in 'Uu':
                    warnings.warn('bad escape %s; Unicode escapes are '
                                  'supported only since Python 3.3' % escape,
                                  FutureWarning, stacklevel=nested + 6)
                else:
                    warnings.warnpy3k('bad escape %s' % escape,
                                      DeprecationWarning, stacklevel=nested + 6)
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise error, "bogus escape: %s" % repr(escape)

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

    items = []
    itemsappend = items.append
    sourcematch = source.match
    while 1:
        itemsappend(_parse(source, state, nested + 1))
        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, nested):
    item_yes = _parse(source, state, nested + 1)
    if source.match("|"):
        item_no = _parse(source, state, nested + 1)
        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, nested):
    # 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, nested + 1)
                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, nested + 1)
                        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 isname(name):
                            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 isname(name):
                            raise error("bad character in backref group name "
                                        "%r" % name)
                        gid = state.groupdict.get(name)
                        if gid is None:
                            msg = "unknown group name: {0!r}".format(name)
                            raise error(msg)
                        if state.lookbehind:
                            import warnings
                            warnings.warn('group references in lookbehind '
                                          'assertions are not supported',
                                          RuntimeWarning, stacklevel=nested + 6)
                        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()
                        state.lookbehind += 1
                    p = _parse_sub(source, state, nested + 1)
                    if dir < 0:
                        state.lookbehind -= 1
                    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 isname(condname):
                        condgroup = state.groupdict.get(condname)
                        if condgroup is None:
                            msg = "unknown group name: {0!r}".format(condname)
                            raise error(msg)
                    else:
                        try:
                            condgroup = int(condname)
                        except ValueError:
                            raise error, "bad character in group name"
                    if state.lookbehind:
                        import warnings
                        warnings.warn('group references in lookbehind '
                                      'assertions are not supported',
                                      RuntimeWarning, stacklevel=nested + 6)
                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, nested + 1)
                else:
                    p = _parse_sub(source, state, nested + 1)
                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, nested + 1)
            subpatternappend(code)

        else:
            raise error, "parser error"

    return subpattern

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)
    if (sys.py3kwarning and
        (p.pattern.flags & SRE_FLAG_LOCALE) and
        (p.pattern.flags & SRE_FLAG_UNICODE)):
        import warnings
        warnings.warnpy3k("LOCALE and UNICODE flags are incompatible",
                          DeprecationWarning, stacklevel=5)

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

    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
    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 type(sep) is type(""):
        makechar = chr
    else:
        makechar = unichr
    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 isname(name):
                        raise error, "bad character in group name"
                    try:
                        index = pattern.groupindex[name]
                    except KeyError:
                        msg = "unknown group name: {0!r}".format(name)
                        raise IndexError(msg)
                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:
                    if sys.py3kwarning and c in ASCIILETTERS:
                        import warnings
                        warnings.warnpy3k('bad escape %s' % this,
                                          DeprecationWarning, stacklevel=4)
                literal(this)
        else:
            literal(this)
    # convert template to groups and literals lists
    i = 0
    groups = []
    groupsappend = groups.append
    literals = [None] * len(p)
    for c, s in p:
        if c is MARK:
            groupsappend((i, s))
            # literal[i] is already None
        else:
            literals[i] = 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)

Youez - 2016 - github.com/yon3zu
LinuXploit