o €e‰<ã@s¢dZddlmZddlZddlmZdZdZdZd Z e d ƒZdd„Zd d„Z dd„Zdd„Zdd„ZGdd„deƒZdd„ZGdd„deƒZGdd„deƒZeƒZGdd„deƒZGdd „d eƒZGd!d"„d"eƒZGd#d$„d$eƒZGd%d&„d&eƒZeƒZd'e_d(e_d)d*„Zd+d,„Zd-d.„Z d/d0„Z!e!d1ƒZ"d2e"_d3e"_dDd4d5„Z#d6d7„Z$d8d9„Z%d:d;„Z&de(_d?e(_eeƒZ)d@e)_dAe)_ee ƒZ*dBe*_dCe*_dS)Ez. Python Lexical Analyser Regular Expressions é)Úabsolute_importNé)ÚErrorsiÿÿÿZbolÚeolÚeofÚ cCs¤t|ƒ}| ¡d}t|ƒ}g}||krPt||ƒ}|d}|d7}||krB|t||ƒkrB|d7}|d7}||krB|t||ƒks.| |¡| |¡||ks|S)z’ Return a list of character codes consisting of pairs [code1a, code1b, code2a, code2b,...] which cover all the characters in |s|. rr)ÚlistÚsortÚlenÚordÚappend)ÚsZ char_listÚiÚnÚresultÚcode1Úcode2©rúCD:\Projects\ConvertPro\env\Lib\site-packages\Cython/Plex/Regexps.pyÚchars_to_rangess"þ ø rcCóLt|tdƒƒ}t|tdƒdƒ}||kr$tdƒtdƒ}||||fSdS)zŠ If the range of characters from code1 to code2-1 includes any lower case letters, return the corresponding upper case range. ÚaÚzrÚAN©ÚmaxrÚmin©rrZcode3Zcode4ÚdrrrÚuppercase_range4órcCr)zŠ If the range of characters from code1 to code2-1 includes any upper case letters, return the corresponding lower case range. rÚZrrNrrrrrÚlowercase_rangeBr r"cs&‡fdd„tdtˆƒdƒDƒ}t|ŽS)zƒ Given a list of codes as returned by chars_to_ranges, return an RE which will match a character in any of the ranges. cs"g|] }tˆ|ˆ|dƒ‘qS)r)Ú CodeRange)Ú.0r©Ú code_listrrÚ Us"zCodeRanges..ré)Úranger ÚAlt)r&Úre_listrr%rÚ CodeRangesPsr,cCs>|tkr |krnntt|tƒtttd|ƒƒSt||ƒS)z CodeRange(code1, code2) is an RE which matches any character with a code |c| in the range |code1| <= |c| < |code2|. r)Únl_coder*ÚRawCodeRangeÚ RawNewline©rrrrrr#Ys þ r#c@sdeZdZdZdZdZdZdd„Zdd„Zdd „Z d d„Z dd „Zdd„Zdd„Z dd„Zdd„ZdS)ÚREaRE is the base class for regular expression constructors. The following operators are defined on REs: re1 + re2 is an RE which matches |re1| followed by |re2| re1 | re2 is an RE which matches either |re1| or |re2| rNcCstd|jjƒ‚)aM This method should add states to |machine| to implement this RE, starting at |initial_state| and ending at |final_state|. If |match_bol| is true, the RE must be able to match at the beginning of a line. If nocase is true, upper and lower case letters should be treated as equivalent. z %s.build_machine not implemented)ÚNotImplementedErrorÚ __class__Ú__name__)ÚselfÚmachineÚ initial_stateÚfinal_stateÚ match_bolÚnocaserrrÚ build_machinevs ÿzRE.build_machinecCs"| ¡}| |¡| ||¡|S)z~ Given a state |s| of machine |m|, return a new state reachable from |s| on character |c| or epsilon. )Ú new_stateÚlink_toÚadd_transition)r5Úmr7Úcr rrrÚ build_opt‚s zRE.build_optcCó t||ƒS©N)ÚSeq©r5ÚotherrrrÚ__add__Œó z RE.__add__cCrBrC)r*rErrrÚ__or__rHz RE.__or__cCs|jr|jS| ¡SrC)ÚstrÚcalc_str©r5rrrÚ__str__’sz RE.__str__cCs t|tƒs| ||d¡dSdS)NzPlex.RE instance)Ú isinstancer1Ú wrong_type©r5ÚnumÚvaluerrrÚcheck_re˜s ÿzRE.check_recCs&t|ƒtdƒkr| ||d¡dSdS)NÚÚstring)ÚtyperOrPrrrÚcheck_stringœsÿzRE.check_stringcCs8| ||¡t|ƒdkrt d||jjt|ƒf¡‚dS)NrzOInvalid value for argument %d of Plex.%s.Expected a string of length 1, got: %s)rWr rZPlexValueErrorr3r4ÚreprrPrrrÚ check_char sÿÿÿz RE.check_charcCsHt|ƒtjkrd|jj|jjf}nt|ƒj}t d||jj||f¡‚)Nz%s.%s instancezt|ƒdkrtt|ƒt|ƒdƒ}nt|ƒ}dt|ƒ|_|S)z; Char(c) is an RE which matches the character |c|. rzChar(%s))r r#rÚ SpecialSymbolrXrJ)r@rrrrÚChar¹s rcc@s<eZdZdZdZdZdZdZdZdd„Z dd„Z dd „ZdS) r.zÒ RawCodeRange(code1, code2) is a low-level RE which matches any character with a code |c| in the range |code1| <= |c| < |code2|, where the range does not include newline. For internal use only. rNcCs&||f|_t||ƒ|_t||ƒ|_dSrC)r)rr")r5rrrrrÚ__init__Ñs zRawCodeRange.__init__cCsX|r | ||t¡}| |j|¡|r(|jr| |j|¡|jr*| |j|¡dSdSdSrC)rAÚBOLr>r)rr"©r5r?r7r8r9r:rrrr;ÖsüzRawCodeRange.build_machinecCsd|j|jfS)NzCodeRange(%d,%d)r0rLrrrrKàszRawCodeRange.calc_str)r4r[r^r_r`rar)rr"rdr;rKrrrrr.Ås r.c@s eZdZdZdZdZdd„ZdS)Ú_RawNewlinezd RawNewline is a low-level RE which matches a newline character. For internal use only. rrcCs8|r | ||t¡}| ||t¡}| ttdf|¡dS©Nr)rAreÚEOLr>r-)r5r?r7r8r9r:r rrrr;ìsz_RawNewline.build_machineN)r4r[r^r_r`rar;rrrrrgäs rgc@s,eZdZdZdZdZdZdd„Zdd„ZdS)rbzx SpecialSymbol(sym) is an RE which matches the special input symbol |sym|, which is one of BOL, EOL or EOF. rNcCs ||_dSrC)Úsym)r5rjrrrrdÿrHzSpecialSymbol.__init__cCs.|r|jtkr| ||t¡}| |j|¡dSrC)rjrirArer>rfrrrr;szSpecialSymbol.build_machine) r4r[r^r_r`rarjrdr;rrrrrbösrbc@ó(eZdZdZdd„Zdd„Zdd„ZdS) rDz]Seq(re1, re2, re3...) is an RE which matches |re1| followed by |re2| followed by |re3|...cGszd}t|ƒD]\}}| ||¡|o|j}q||_||_t|ƒ}d}|r8|d8}||}|jr2d}n|js6n|s$||_dS)Nrr)Ú enumeraterSr`r+r ra)r5r+r`rÚrerarrrrds$ù zSeq.__init__cCs‚|j}t|ƒdkr| |¡dS|}t|ƒ}t|ƒD]$\} } | |dkr)| ¡}n|}| |||||¡|}| jp=|o=| j}qdS©Nrr)r+r r=rlr<r;rar`)r5r?r7r8r9r:r+Ús1rrrmÚs2rrrr;!s ùzSeq.build_machinecCódd tt|jƒ¡S)NzSeq(%s)ú,©ÚjoinÚmaprJr+rLrrrrK1ózSeq.calc_strN©r4r[r^r_rdr;rKrrrrrD s rDc@rk) r*zRAlt(re1, re2, re3...) is an RE which matches either |re1| or |re2| or |re3|...cGs~||_d}d}g}g}d}|D]!}| ||¡|jr"| |¡d}n| |¡|jr,d}|d7}q||_||_||_||_dSrn)r+rSr`rraÚnullable_resÚnon_nullable_res)r5r+r`rarxryrrmrrrrd9s& zAlt.__init__cCs\|jD]}| |||||¡q|jr*|r| ||t¡}|jD] }| |||d|¡qdSdS)Nr)rxr;ryrAre)r5r?r7r8r9r:rmrrrr;Os üzAlt.build_machinecCrq)NzAlt(%s)rrrsrLrrrrKXrvzAlt.calc_strNrwrrrrr*5s r*c@rk) ÚRep1z@Rep1(re) is an RE which matches one or more repetitions of |re|.cCs&| d|¡||_|j|_|j|_dSrh)rSrmr`ra)r5rmrrrrd_sz Rep1.__init__cCsN| ¡}| ¡}| |¡|j ||||p|jj|¡| |¡| |¡dSrC)r<r=rmr;ra)r5r?r7r8r9r:rorprrrr;es zRep1.build_machinecCs d|jS)NzRep1(%s)©rmrLrrrrKmrHz Rep1.calc_strNrwrrrrrz\s rzc@s0eZdZdZdZdZdd„Zdd„Zdd„ZdS) Ú SwitchCasezÓ SwitchCase(re, nocase) is an RE which matches the same strings as RE, but treating upper and lower case letters according to |nocase|. If |nocase| is true, case is ignored, otherwise it is not. NcCs ||_||_|j|_|j|_dSrC)rmr:r`ra)r5rmr:rrrrdzszSwitchCase.__init__cCs|j |||||j¡dSrC)rmr;r:rfrrrr;€sÿzSwitchCase.build_machinecCs|jrd}nd}d||jfS)NÚNoCaseÚCasez%s(%s))r:rm)r5ÚnamerrrrK„szSwitchCase.calc_str) r4r[r^r_rmr:rdr;rKrrrrr|qsr|z8 Empty is an RE which matches the empty string. ÚEmptycCs$tttt|ƒƒŽ}dt|ƒ|_|S)z@ Str1(s) is an RE which matches the literal string |s|. úStr(%s))rDÚtuplerurcrXrJ©r rrrrÚStr1›sr„cGsDt|ƒdkrt|dƒStttt|ƒƒŽ}dd tt|ƒ¡|_|S)zŽ Str(s) is an RE which matches the literal string |s|. Str(s1, s2, s3, ...) is an RE which matches any of |s1| or |s2| or |s3|... rrrrr)r r„r*r‚rurtrXrJ)ÚstrsrrrrÚStr¤s r†cCstt|ƒƒ}dt|ƒ|_|S)zH Any(s) is an RE which matches any character in the string |s|. zAny(%s))r,rrXrJrƒrrrÚAny±sr‡cCs:t|ƒ}| dt¡| t¡t|ƒ}dt|ƒ|_|S)zp AnyBut(s) is an RE which matches any character (including newline) which is not in the string |s|. rz AnyBut(%s))rÚinsertÚmaxintrr,rXrJ)r ÚrangesrrrrÚAnyButºs r‹rTzT AnyChar is an RE which matches any single character (including a newline). ÚAnyCharc Csˆ|rtt|ƒt|ƒdƒ}d||f|_|Sg}tdt|ƒdƒD]}| tt||ƒt||dƒdƒ¡q t|Ž}dt|ƒ|_|S)a Range(c1, c2) is an RE which matches any single character in the range |c1| to |c2| inclusive. Range(s) where |s| is a string of even length is an RE which matches any single character in the ranges |s[0]| to |s[1]|, |s[2]| to |s[3]|,... rzRange(%s,%s)rr(z Range(%s))r#rrJr)r rr*rX)rorprrŠrrrrÚRangeÏsû*rcCst|tƒ}d||_|S)zI Opt(re) is an RE which matches either |re| or the empty string. zOpt(%s))r*r€rJ©rmrrrrÚOptâs rcCstt|ƒƒ}d||_|S)zJ Rep(re) is an RE which matches zero or more repetitions of |re|. zRep(%s))rrzrJrŽrrrÚRepës rcCót|ddS)z€ NoCase(re) is an RE which matches the same strings as RE, but treating upper and lower case letters as equivalent. r©r:©r|r{rrrr}ôsr}cCr‘)z¶ Case(re) is an RE which matches the same strings as RE, but treating upper and lower case letters as distinct, i.e. it cancels the effect of any enclosing NoCase(). rr’r“r{rrrr~üsr~z= Bol is an RE which matches the beginning of a line. ÚBolz7 Eol is an RE which matches the end of a line. ÚEolz9 Eof is an RE which matches the end of the file. ÚEofrC)+r_Ú __future__rrZrTrr‰reriZEOFrr-rrr"r,r#Úobjectr1rcr.rgr/rbrDr*rzr|r€rJr„r†r‡r‹rŒrrrr}r~r”r•r–rrrrÚsj O+'"ÿ ÿ ÿÿÿ