*h:NSrSSKr"SS\5r"SS5r"SS5rg) z This module contains a tokenizer for Excel formulae. The tokenizer is based on the Javascript tokenizer found at http://ewbi.blogs.com/develops/2004/12/excel_formula_p.html written by Eric Bachtal Nc\rSrSrSrSrg)TokenizerError z$Base class for all Tokenizer errors.N)__name__ __module__ __qualname____firstlineno____doc____static_attributes__rW/home/mande/repo/quber/.venv/lib/python3.13/site-packages/openpyxl/formula/tokenizer.pyrr s.r rc \rSrSrSr\R "S5r\R "S5r\R "S5\R "S5S.r Sr S r S r S r S rS rSrSrSrSrSrSrSrSSjrSrSrSrg) TokenizeraB A tokenizer for Excel worksheet formulae. Converts a str string representing an Excel formula (in A1 notation) into a sequence of `Token` objects. `formula`: The str string to tokenize Tokenizer defines a method `._parse()` to parse the formula into tokens, which can then be accessed through the `.items` attribute. z^[1-9](\.[0-9]+)?[Ee]$z[ \n]+z"(?:[^"]*"")*[^"]*"(?!")z'(?:[^']*'')*[^']*'(?!')"')z#NULL!z#DIV/0!z#VALUE!z#REF!z#NAME?z#NUM!z#N/Az #GETTING_DATAz,;}) +-*/^&=><%chXl/Ul/UlSUl/UlUR 5 g)Nr)formulaitems token_stackoffsettoken_parse)selfrs r__init__Tokenizer.__init__.s-     r c \UR(agUR(dgURSS:XaU=RS- slO>URR[ UR[R 55 gSUR 4SUR4SUR4SUR4S UR4S UR4S UR4S UR4S UR44 n0nUH)up4UR[R!X455 M+ UR[#UR5:aUR%5(aM:URURnXPR&;aUR)5 XR;aU=RX%"5- slO0UR*RU5 U=RS- slUR[#UR5:aMUR)5 g)z5Populate self.items with the tokens from the formula.Nr=z"'[#  z +-*/^&=><%z{()}z;,)rrrappendTokenLITERAL _parse_string_parse_brackets _parse_error_parse_whitespace_parse_operator _parse_opener _parse_closer_parse_separatorupdatedictfromkeyslencheck_scientific_notation TOKEN_ENDERS save_tokenr)r consumers dispatchercharsconsumer curr_chars rrTokenizer._parse7s ;; ||  \\!_ # KK1 K JJ  eDLL%--@ A  D&& ' $&& ' $## $ $(( ) 4)) * 4// 0 4%% & 4%% & 4(( )   (OE   dmmE< = )kkC ----// T[[1I---!& z466  !!), q kkC -- r cURSS9 URURnUS;deURUnUR URURS5nUc%US:XaSOSn[ SUS UR35eUR S 5nUS:Xa/URR[RU55 OURRU5 [U5$) ay Parse a "-delimited string or '-delimited link. The offset must be pointing to either a single quote ("'") or double quote ('"') character. The strings are parsed according to Excel rules where to escape the delimiter you just double it up. E.g., "abc""def" in Excel is parsed as 'abc"def' in Python. Returns the number of characters matched. (Does not update self.offset) : can_followrNrstringlinkz%Reached end of formula while parsing z in r) assert_empty_tokenrrSTRING_REGEXESmatchrgrouprr'r( make_operandrr5)rdelimregexrGsubtypes rr*Tokenizer._parse_string_s 3/ T[[) """##E* DLL67 ="'3,hFG #H QUVZVbVbUc!de e A C< JJ  e007 8 JJ  e $5zr cURURS:Xde[R"SURURS5Vs/sHoR 5S4PM nn[R"SURURS5Vs/sHoR 5S4PM nnSn[ X#-5HWupVXF- nUS:XdMUS-nUR RURURURU-5 Us $ [SUR35es snfs snf) z| Consume all the text between square brackets []. Returns the number of characters matched. (Does not update self.offset) r"z\[Nr!z\]rzEncountered unmatched '[' in ) rrrefinditerstartsortedrr'r)rtleftsrights open_countidx open_close outer_rights rr+Tokenizer._parse_brackets{s4||DKK(C///UDLL$>?A?%&'')Q? A++eT\\$++,%?@B@'(779b/@ B %en5OC  $JQ!Ag  !!LLT[[;-FGI"" 6t{{m5QUQ]Q]P^^_`aar cTURURS;deURR[ URUR[R 55 UR RURURS5R5$)zn Consume a string of consecutive spaces. Returns the number of spaces found. (Does not update self.offset). )r$r%N) rrrr'r(WSPACE WSPACE_RErGendrs rr-Tokenizer._parse_whitespacesv||DKK(K777 % T[[ 95<<HI~~##DLL$>?CCEEr cURURURS-S;aXURR[ URURURS-[R 55 gURURnUS;deUS:Xa[ S[R 5nGOUS;a[ U[R 5nOUR(d[ U[R5nO[S[UR55S5nU=(ae UR[R:H=(dA UR[R :H=(d UR[R:HnU(a[ U[R 5nO[ U[R5nURRU5 g) z} Consume the characters constituting an operator. Returns the number of characters consumed. (Does not update self.offset) )z>=z<=z<>z %*/^&=><+-%z*/^&=>,Tokenizer._parse_operator..s)4$8qFFell2$8s"1 1Nr!)rrrr'r(OP_INOP_POSTOP_PREnextreversedrLCLOSErqOPERAND)rr=rprevis_infixs rr.Tokenizer._parse_operatorsm << DKK!O 48J J JJ  e T[[q9  LL- L(((  #u}}-E ) #)U[[1E)U\\2E4HTZZ$8459;D  +.99 -.99 -  i5i6 % r cURURS;deURURS:Xa&UR5 [R S5nOiUR (aCSR UR 5S-nUR SS2 [R U5nO[R S5nURRU5 URRU5 g)zi Consumes a ( or { character. Returns the number of characters consumed. (Does not update self.offset) )({rr^rNr!) rrrEr( make_subexprrbrr'r)rr token_values rr/Tokenizer._parse_openers||DKK(J666 << $ +  # # %%%c*E ZZ''$**-3K 1 %%k2E%%c*E %  &r cFURURS;deURR5R 5nUR URUR:wa[ SUR-5eURRU5 g)zi Consumes a } or ) character. Returns the number of characters consumed. (Does not update self.offset) ))}zMismatched ( and { pair in '%s'r!) rrrpop get_closervaluerrr')rrs rr0Tokenizer._parse_closers||DKK(J666  $$&113 ;;$,,t{{3 3 1DLL@B B % r cURURnUS;deUS:Xa[RS5nO_URSR nU[R :Xa[S[R5nO[RS5nURRU5 g![a [S[R5nNBf=f)zi Consumes a ; or , character. Returns the number of characters consumed. (Does not update self.offset) );,rrOrr!) rrr(make_separatorrrqPARENrv IndexErrorrr')rr=rtop_types rr1Tokenizer._parse_separatorsLL- J&&&  ((-E 6++B/44u{{*!#u{{3E!005E %  0c5;;/ 0sB99$C C cHURURnUS;a[UR5S:ajURR SR UR55(a1URRU5 U=RS- slgg)z Consumes a + or - character if part of a number in sci. notation. Returns True if the character was consumed and self.offset was updated, False otherwise. z+-r!r^TF)rrr5rSN_RErGrbr')rr=s rr6#Tokenizer.check_scientific_notationsvLL-   Oq(JJ$$RWWTZZ%899 JJ  i ( KK1 Kr cUR(a:URSU;a&[SURSURS35egg)a  Ensure that there's no token currently being parsed. Or if there is a token being parsed, it must end with a character in can_follow. If there are unconsumed token contents, it means we hit an unexpected token transition. In this case, we raise a TokenizerError rOz!Unexpected character at position r_rN)rrrr)rrBs rrETokenizer.assert_empty_token'sJ ::$**R. : #DT[[MQVW[WcWcVdde!fg g;:r cUR(aWURR[R SR UR555 URSS2 gg)z9If there's a token being parsed, add it to the item list.r^N)rrr'r(rIrbrjs rr8Tokenizer.save_token5sC :: JJ  e001DE F 1  r cUR(dgURSR[R:XaURSR$SSR SUR55-$)z+Convert the parsed tokens back to a string.r^rr c38# UHoRv M g7frp)r)rrrs rrt#Tokenizer.render..AsAjU[[js)rrqr(r)rrbrjs rrenderTokenizer.render;sXzz ZZ]  5== 0::a=&& &RWWAdjjAAAAr )rrrrrN)r)rrr r r rPcompilerrhrFr`r7rrr*r+r,r-r.r/r0r1r6rEr8rr rr rrrs  JJ0 1E 9%I ZZ2 3 ZZ2 3 N5K$L&P8M2b$ F$L, 2" h Br rc\rSrSrSr/SQrSrSrSrSr Sr S r S r S r S rS rSSjrSrSrSrSrSrSr\S5rSrSr\S Sj5rSrSrSr\S5rSr g)!r(iDa  A token in an Excel formula. Tokens have three attributes: * `value`: The string value parsed that led to this token * `type`: A string identifying the type of token * `subtype`: A string identifying subtype of the token (optional, and defaults to "") rrqrLr)r|FUNCARRAYrSEPzOPERATOR-PREFIXzOPERATOR-INFIXzOPERATOR-POSTFIXz WHITE-SPACEc(XlX lX0lgrpr)rrtype_rLs rrToken.__init___s   r TEXTNUMBERLOGICALERRORRANGEcdSRURURUR5$)Nz {0} {1} {2}:)formatrqrLrrjs r__repr__Token.__repr__qs#%%diitzzJJr cBURS5(a URnONURS5(a URnO+US;a URnO[ U5 UR nU"XRU5$![ a URnN+f=f)zCreate an operand token.rr#)TRUEFALSE) rarrrfloatr ValueErrorrr|clsrrLs rrIToken.make_operandts   C hhG   c " "iiG ' 'kkG $e **5++w// $)) $sBBBOPENr{cNUSS;deU(a/[R"SU5(de[RnO>US;a[RnO'US;a[R nO[RnUS;a UR O URnU"XU5$)zu Create a subexpression token. `value`: The value of the token `func`: If True, force the token to be of type FUNC rO)rrrrz.+\(|\)z{}z()r&)rPrGr(rrrr{r)rrfuncrrLs rrToken.make_subexpsRy0000 88K// //JJE d]KKE d]KKEJJE$}#))#((5))r c(URURURUR4;deURUR :XdeURUR:XaSOSnUR XRUR:HS9$)z6Return a closing token that matches this token's type.rr)r)rqrrrrLrr)rrs rrToken.get_closerstyyTYY DJJ????||tyy(((yyDJJ.CII,BCCr ARGROWctUS;deUS:Xa URO URnU"XRU5$)zCreate a separator token)rrr)rrrrs rrToken.make_separators8 """"c\#''sww5''7++r )rLrqrN)r^)F)!rrr r r __slots__r)r|rrrrrxrvrwrgrrrrrrr classmethodrIrr{rrrrrr rr rr(r(Ds -IGG D E E C F E G F D FG E EK002 D E***D C C,,r r()r rP Exceptionrrr(rr rrs6 /Y/qBqBh z,z,r