î æ^Q\j8ã@sXdZddlZGdd„deƒZGdd„deƒZGdd„deƒZdS) zÇ 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 éNc@seZdZdZdS)ÚTokenizerErrorz$Base class for all Tokenizer errors.N)Ú__name__Ú __module__Ú __qualname__Ú__doc__©rrúO/var/www/dbchiro/venv/lib/python3.4/site-packages/openpyxl/formula/tokenizer.pyr s rc@seZdZdZejdƒZejdƒZiejdƒd6ejdƒd6Zd.Z dZ dd„Z dd„Z dd„Z dd„Zdd„Zdd„Zdd„Zdd „Zd!d"„Zd#d$„Zd%d&„Zd'd(„Zd)d*„Zd+d,„Zd-S)/Ú Tokenizeraf A tokenizer for Excel worksheet formulae. Converts a unicode string representing an Excel formula (in A1 notation) into a sequence of `Token` objects. `formula`: The unicode 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]$z +z"(?:[^"]*"")*[^"]*"(?!")ú"z'(?:[^']*'')*[^']*'(?!')ú'ú#NULL!ú#DIV/0!ú#VALUE!ú#REF!ú#NAME?ú#NUM!ú#N/Aú #GETTING_DATAz,;}) +-*/^&=><%cCs;||_g|_g|_d|_g|_|jƒdS)Nr)ÚformulaÚitemsÚ token_stackÚoffsetÚtokenÚ_parse)ÚselfrrrrÚ__init__.s      zTokenizer.__init__c Cs­|jr dS|jsdS|jddkr?|jd7_n#|jjt|jtjƒƒdSd|jfd|jfd|jfd|j fd |j fd |j fd |j fd |j ff}i}x-|D]%\}}|jtj||ƒƒqÕWxž|jt|jƒkrž|jƒr+qn|j|j}||jkrW|jƒn||kr||j||ƒ7_q|jj|ƒ|jd7_qW|jƒdS) z5Populate self.items with the tokens from the formula.Nrú=éz"'ú[ú#ú z +-*/^&=><%z{(z)}z;,)rrrÚappendÚTokenÚLITERALÚ _parse_stringÚ_parse_bracketsÚ _parse_errorÚ_parse_whitespaceÚ_parse_operatorÚ _parse_openerÚ _parse_closerÚ_parse_separatorÚupdateÚdictÚfromkeysÚlenÚcheck_scientific_notationÚ TOKEN_ENDERSÚ save_tokenr)rZ consumersZ dispatcherÚcharsZconsumerÚ curr_charrrrr7s<            zTokenizer._parsecCsé|jƒ|j|j}|dks,t‚|j|}|j|j|jd…ƒ}|dkr˜|dkrvdnd}td||jfƒ‚n|jdƒ}|dkrÏ|jj t j |ƒƒn|j j |ƒt |ƒS) a¹ Parse a "-delimited string or '-delimited link. The offset must be pointing to either a single quote ("'") or double quote ('"') character. The strings are parsed according to Excel rules where to escape the delimiter you just double it up. E.g., "abc""def" in Excel is parsed as 'abc"def' in Python. Returns the number of characters matched. (Does not update self.offset) r r NÚstringÚlinkz-Reached end of formula while parsing %s in %sr)r r )Úassert_empty_tokenrrÚAssertionErrorÚSTRING_REGEXESÚmatchrÚgrouprr!r"Ú make_operandrr/)rÚdelimÚregexr:Úsubtyperrrr$^s    zTokenizer._parse_stringcCs…|j|jdkst‚|jjd|jƒd}|dkrZtd|jƒ‚n|jj|j|j|…ƒ||jS)zœ Consume all the text between square brackets []. Returns the number of characters matched. (Does not update self.offset) rú]rrzEncountered unmatched '[' in %s)rrr8Úfindrrr!)rÚrightrrrr%|s  zTokenizer._parse_bracketscCs¢|jƒ|j|jdks&t‚|j|jd…}xC|jD]8}|j|ƒrF|jjtj |ƒƒt |ƒSqFWt d|j|jfƒ‚dS)zà Consume the text following a '#' as an error. Looks for a match in self.ERROR_CODES and returns the number of characters matched. (Does not update self.offset) rNz)Invalid error code at position %d in '%s') r7rrr8Ú ERROR_CODESÚ startswithrr!r"r<r/r)rZ subformulaÚerrrrrr&Œs zTokenizer._parse_errorcCs^|j|jdkst‚|jjtdtjƒƒ|jj|j|jd…ƒj ƒS)z† Consume a string of consecutive spaces. Returns the number of spaces found. (Does not update self.offset). r N) rrr8rr!r"ÚWSPACEÚ WSPACE_REr:Úend)rrrrr'ŸszTokenizer._parse_whitespacecCs`|j|j|jd…d krZ|jjt|j|j|jd…tjƒƒdS|j|j}|dks|t‚|dkrtdtjƒ}n¯|dkr¾t|tjƒ}nŽ|jsÜt|tjƒ}np|jd }|j tj kp|j tjkp|j tj k}|r:t|tjƒ}nt|tjƒ}|jj|ƒdS) zœ Consume the characters constituting an operator. Returns the number of charactes consumed. (Does not update self.offset) éú>=ú<=ú<>z %*/^&=><+-ú%z*/^&=>8sz#Tokenizer.render..)rrSr"r#r_rZ)rrrrÚrender2s  zTokenizer.renderN)r r rrrrrr)rrrrÚreÚcompilererGr9rCr1rrr$r%r&r'r(r)r*r+r0r7r2rhrrrrr s.  '    %     r c@s÷eZdZdZdddgZdZdZdZdZd Z d Z d Z d Z d Z dZddd„ZdZdZdZdZdZdd„Zedd„ƒZdZdZeddd„ƒZd d!„Zd"Zd#Zed$d%„ƒZd&S)'r"a) 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 "") r_rSr?r#rTÚFUNCÚARRAYrdÚSEPzOPERATOR-PREFIXzOPERATOR-INFIXzOPERATOR-POSTFIXz WHITE-SPACErXcCs||_||_||_dS)N)r_rSr?)rr_Útype_r?rrrrVs  zToken.__init__ÚTEXTÚNUMBERÚLOGICALÚERRORÚRANGEcCsdj|j|j|jƒS)Nz {0} {1} {2}:)ÚformatrSr?r_)rrrrÚ__repr__hszToken.__repr__c Cs–|jdƒr|j}nh|jdƒr6|j}nM|dkrN|j}n5yt|ƒ|j}Wntk r‚|j}YnX|||j|ƒS)zCreate an operand token.r rÚTRUEÚFALSE)zTRUEzFALSE) rDrorrrqÚfloatrpÚ ValueErrorrsrT)Úclsr_r?rrrr<ks       zToken.make_operandÚOPENrRFcCs§|d d kst‚|r@tjd|ƒs4t‚tj}n9|dkrXtj}n!|dkrptj}n tj}|d krŽ|jn|j}||||ƒS) z• Create a subexpression token. `value`: The value of the token `func`: If True, force the token to be of type FUNC rrWr\rVr[z.+\(|\)z{}z()z)}rN)rWr\rVr[) r8rir:r"rkrlrdrRr{)rzr_Úfuncrnr?rrrrYˆs       zToken.make_subexpcCs||j|j|j|jfks't‚|j|jks?t‚|j|jkrWdnd}|j|d|j|jkƒS)z6Return a closing token that matches this token's type.r\r[r|)rSrkrlrdr8r?r{rY)rr_rrrr^žs'zToken.get_closerÚARGÚROWcCsC|dkst‚|dkr'|jn|j}|||j|ƒS)zCreate a separator tokenrar`)rar`)r8r}r~rm)rzr_r?rrrrb°szToken.make_separatorN)rrrrÚ __slots__r#rTrkrlrdrmrQrOrPrFrrorprqrrrsruÚ classmethodr<r{rRrYr^r}r~rbrrrrr";s8    r")rriÚ ExceptionrÚobjectr r"rrrrÚs  ÿ,