Ë
|
dñúhð: ã óN d Z ddlZ G d de« Z G d d« Z G d d« Zy) 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
|
é Nc ó e Zd ZdZy)ÚTokenizerErrorz$Base class for all Tokenizer errors.N)Ú__name__Ú
|
__module__Ú __qualname__Ú__doc__© ó úMH:\Change_password\venv_build\Lib\site-packages\openpyxl/formula/tokenizer.pyr r s Ú.r
|
r c ó e Zd ZdZ ej
|
d« Z ej
|
d« Z ej
|
d« ej
|
d« dZdZ dZ
|
d Z d
|
Z d Z d Zd Zd Zd Zd Zd Zd Zd ZddZd Zd Zy)Ú Tokenizera^
|
A tokenizer for Excel worksheet formulae.
|
|
Converts a str string representing an Excel formula (in A1 notation)
|
into a sequence of `Token` objects.
|
|
`formula`: The str string to tokenize
|
|
Tokenizer defines a method `._parse()` to parse the formula into tokens,
|
which can then be accessed through the `.items` attribute.
|
|
z^[1-9](\.[0-9]+)?[Ee]$z[ \n]+z"(?:[^"]*"")*[^"]*"(?!")z'(?:[^']*'')*[^']*'(?!')©ú"ú')z#NULL!z#DIV/0!z#VALUE!z#REF!z#NAME?z#NUM!z#N/Az #GETTING_DATAz,;}) +-*/^&=><%c ój || _ g | _ g | _ d| _ g | _ | j « y )Nr )ÚformulaÚitemsÚ token_stackÚoffsetÚtokenÚ_parse)Úselfr s r Ú__init__zTokenizer.__init__. s/ Ø Ø
|
Ø Ôà Ø
|
Ø r
|
c
|
ó2 | j ry| j sy| j d dk( r| xj dz c_ n>| j j t | j t j
|
« « yd| j fd| j fd| j fd| j fd | j fd
|
| j fd | j fd | j fd | j ff }i }|D ]* \ }}|j t j! ||« « , | j t# | j « k r½| j% « r3| j | j }|| j& v r| j) « ||v r | xj || « z c_ n0| j* j |« | xj dz c_ | j t# | j « k r½| j) « y)z5Populate self.items with the tokens from the formula.Nr ú=é z"'ú[ú#ú ú
|
z
|
+-*/^&=><%z{(ú)}z;,)r r r ÚappendÚTokenÚLITERALÚ _parse_stringÚ_parse_bracketsÚ _parse_errorÚ_parse_whitespaceÚ_parse_operatorÚ _parse_openerÚ _parse_closerÚ_parse_separatorÚupdateÚdictÚfromkeysÚlenÚcheck_scientific_notationÚ TOKEN_ENDERSÚ
|
save_tokenr )r Ú consumersÚ
|
dispatcherÚcharsÚconsumerÚ curr_chars r r zTokenizer._parse7 sÄ à ;;Ø Ø||Ø Ø \\!_ Ò #Ø KK1Ñ Kà JJ× Ñ e D§L¡L´%·-±-Ó @Ô AØ à D×&Ñ&Ð 'Ø $×&Ñ&Ð 'Ø $×#Ñ#Ð $Ø $×(Ñ(Ð )Ø 4×)Ñ)Ð *Ø 4×/Ñ/Ð 0Ø 4×%Ñ%Ð &Ø 4×%Ñ%Ð &Ø 4×(Ñ(Ð )ð
|
|
ð
|
Ø (ò >OE8Ø × Ñ dmm¨E°8Ó <Õ =ð >àkkC § ¡ Ó -Ò-Ø×-Ñ-Ô/ØØ T§[¡[Ñ1IØD× -Ñ -Ñ-ØÔ!ØJÑ&Ø Ð 4z¨)Ñ 4Ó 6Ñ6 ð
|
|
×!Ñ! )Ô,Ø qÑ ð kkC § ¡ Ó -Ó-ð Õr
|
c ó | j d¬« | j | j }|dv sJ | j | }|j | j | j d « }|$|dk( rdnd}t d| d | j « |j d
|
« }|dk( r9| j j t j |« « t |« S | j j |« t |« S ) 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)
|
|
ú:©Ú
|
can_followr Nr ÚstringÚlinkz%Reached end of formula while parsing z in r ) Úassert_empty_tokenr r ÚSTRING_REGEXESÚmatchr Úgroupr r" r# Ú make_operandr r0 )r ÚdelimÚregexrA Úsubtypes r r% zTokenizer._parse_string_ sñ ð × Ñ ¨3Ð Ô/Ø T[[Ñ)Ø
|
Ñ"Ð"Ð"Ø×#Ñ# EÑ*Ø DLL¨¯©¨ Ð 6Ó7Ø =Ø"'¨3¢,h°FGÜ Ð#HÈÈ ÐQUÐVZ×VbÑVbÐUcÐ!dÓeÐ eØ AØ C<Ø JJ× Ñ e× 0Ñ 0°Ó 7Ô 8ô 5zÐð JJ× Ñ eÔ $Ü5zÐr
|
c ó~ | j | j dk( sJ t j d| j | j d « D cg c] }|j « df }}t j d| j | j d « D cg c] }|j « df }}d}t ||z « D ]W \ }}||z }|dk( s|dz }| j j | j | j | j |z « |c S t d| j « c c}w c c}w ) z
|
Consume all the text between square brackets [].
|
|
Returns the number of characters matched. (Does not update
|
self.offset)
|
|
r z\[Nr z\]éÿÿÿÿr z Encountered unmatched '[' in ) r r ÚreÚfinditerÚstartÚsortedr r" r )r ÚtÚleftsÚrightsÚ
|
open_countÚidxÚ
|
open_closeÚ outer_rights r r& zTokenizer._parse_brackets{ s7 ð ||DKKÑ(¨CÒ/Ð/Ð/äU D§L¡L°·±° Ð$>Ó?öA A!'')Q ð Að Aô ++e T§\¡\°$·+±+°,Ð%?Ó@öB a1779b/ð Bð Bð
|
Ü % e¨f¡nÓ 5ò #OCØ *Ñ $JØQØ ! Ag Ø
|
|
×!Ñ!ØLL §¡¨T¯[©[¸;Ñ-FÐGôIà"Ò"ð #ô Ð <¸T¿\¹\¸NÐ KÓLÐLùò AùòBs ÁD5ÂD:c óð | j d¬« | j | j dk( sJ | j | j d }| j D ]y }|j |« s| j
|
j t j dj | j « |z « « | j dd
= t |« c S t d| j d| j d« ) zÃ
|
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)
|
|
ú!r; r NÚ z Invalid error code at position ú in 'r ) r? r r Ú ERROR_CODESÚ
|
startswithr r" r# rC Újoinr r0 r )r Ú
|
subformulaÚerrs r r' zTokenizer._parse_error sÔ ð × Ñ ¨3Ð Ô/Ø||DKKÑ(¨CÒ/Ð/Ð/Ø\\ $§+¡+ ,Ð/
|
Ø×#Ñ#ò CØ×$Ñ$ SÕ)Ø
|
|
×!Ñ!¤%×"4Ñ"4°R·W±W¸T¿Z¹ZÓ5HÈ3Ñ5NÓ"OÔPØJJqMÜ3xð ô
|
Ð >¸t¿{¹{¸mÈ5ÐQU×Q]ÑQ]ÐP^Ð^_Ð `ÓaÐar
|
c óP | j | j dv sJ | j j t | j | j t j
|
« « | j j | j | j d « j « S )z
|
Consume a string of consecutive spaces.
|
|
Returns the number of spaces found. (Does not update self.offset).
|
|
)r r N) r r r r" r# ÚWSPACEÚ WSPACE_RErA Úend©r s r r( zTokenizer._parse_whitespace¦ sv ð ||DKKÑ(¨KÑ7Ð7Ð7Ø
|
|
×Ñ% § ¡ ¨T¯[©[Ñ 9¼5¿<¹<ÓHÔIØ~~×#Ñ# D§L¡L°·±° Ð$>Ó?×CÑCÓEÐEr
|
c ó¾ | j | j | j dz dv rX| j j t | j | j | j dz t j
|
« « y| j | j }|dv sJ |dk( r t dt j « }n|dv rt |t j
|
« }nã| j st |t j « }n¼t d t | j « D « d« }|xr[ |j t j k( xs< |j t j k( xs |j t j k( }|rt |t j
|
« }nt |t j « }| j j |« y) z
|
Consume the characters constituting an operator.
|
|
Returns the number of characters consumed. (Does not update
|
self.offset)
|
|
é )z>=z<=z<>z
|
%*/^&=><+-ú%z*/^&=><c 3 óZ K | ]# }|j t j k7 r| % y w©N)Útyper# r^ )Ú.0Úis r ú <genexpr>z,Tokenizer._parse_operator.<locals>.<genexpr>É s' è ø ò 4qØ FF¤e§l¡lÒ 2ô ñ 4ùs )+Nr )r r r r" r# ÚOP_INÚOP_POSTÚOP_PREÚnextÚreversedrF ÚCLOSErg ÚOPERAND)r r8 r ÚprevÚis_infixs r r) zTokenizer._parse_operator± sm ð << D§K¡K°!¡OÐ 4Ð8JÑ JØ JJ× Ñ eØ T[[¨¯©°q© Ð9Ü ó ô ð ØLL §¡Ñ- ØLÑ(Ð(Ð(Ø Ò Ü#u}}Ó-EØ )Ñ #Ü)¤U§[¡[Ó1EàÜ)¤U§\¡\Ó2Eäñ 4¤H¨T¯Z©ZÓ$8ô 4Ø59ó;Dàò Ø ¤§ ¡ Ñ+ò .Ø99¤§ ¡ Ñ-ò.à99¤§ ¡ Ñ-ð ñ
|
Ü i¬¯©Ó5ä i¬¯ © Ó6Ø
|
|
×Ñ%Ô Ør
|
c óö | j | j dv sJ | j | j dk( r&| j « t j d« }nd| j
|
rCdj | j
|
« dz }| j
|
dd
= t j |« }nt j d« }| j j |« | j j |« y)z
|
Consumes a ( or { character.
|
|
Returns the number of characters consumed. (Does not update
|
self.offset)
|
|
)ú(ú{rv rV ru Nr )
|
r r r? r# Ú make_subexpr rZ r r" r )r r Ú token_values r r* zTokenizer._parse_opener× s ð ||DKKÑ(¨JÑ6Ð6Ð6Ø << Ñ $¨Ò +Ø × #Ñ #Ô %Ü×%Ñ% cÓ*EØ ZZØ '' $§*¡*Ó-°Ñ3KØ
|
|
1 Ü×%Ñ% kÓ2Eä×%Ñ% cÓ*EØ
|
|
×Ñ%Ô Ø ×Ñ× Ñ Ô&Ør
|
c ó@ | j | j dv sJ | j j « j « }|j
|
| j | j k7 rt d| j z « | j j |« y)z
|
Consumes a } or ) character.
|
|
Returns the number of characters consumed. (Does not update
|
self.offset)
|
|
)ú)ú}z Mismatched ( and { pair in '%s'r ) r r r ÚpopÚ
|
get_closerÚvaluer r r" )r r s r r+ zTokenizer._parse_closerí s
ð ||DKKÑ(¨JÑ6Ð6Ð6Ø× Ñ ×$Ñ$Ó&×1Ñ1Ó3Ø ;;$,, t§{¡{Ñ3Ò 3Ü Ø1°D·L±LÑ@óBð Bà
|
|
×Ñ%Ô Ør
|
c ó¼ | j | j }|dv sJ |dk( rt j d« }n^ | j d j
|
}|t j k( rt dt j « }nt j d« } | j j |« y# t $ r t dt j « }Y Aw xY w)z
|
Consumes a ; or , character.
|
|
Returns the number of characters consumed. (Does not update
|
self.offset)
|
|
)ú;ú,r rH r r ) r r r# Úmake_separatorr rg ÚPARENrk Ú
|
IndexErrorr r" )r r8 r Útop_types r r, zTokenizer._parse_separatorý s» ð LL §¡Ñ- ØJÑ&Ð&Ð&Ø Ò Ü×(Ñ(¨Ó-Eð 6Ø ×+Ñ+¨BÑ/×4Ñ4ð u{{Ò*Ü ! #¤u§{¡{Ó 3Eä !× 0Ñ 0°Ó 5EØ
|
|
×Ñ%Ô Øøô ò 0Ü c¤5§;¡;Ó/ð 0ús ¼B5 Â5#CÃCc ó8 | j | j }|dv r}t | j « dk\ re| j j dj | j « « r1| j j |« | xj dz c_ yy)z¾
|
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 rV TF)r r r0 r ÚSN_RErA rZ r" )r r8 s r r1 z#Tokenizer.check_scientific_notation ss ð LL §¡Ñ- Ø Ñ Ü
|
|
O qÒ(ØJJ×$Ñ$ R§W¡W¨T¯Z©ZÓ%8Ô9Ø JJ× Ñ iÔ (Ø KK1Ñ KØØr
|
c ó | j r8| j d |vr&t d| j d| j d« yy)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
|
|
rH z!Unexpected character at position rW r N)r r r r )r r< s r r? z Tokenizer.assert_empty_token' sJ ð ::$** R.°
|
Ñ:Ü Ð#DÀTÇ[Á[ÀMÐQVÐW[×WcÑWcÐVdÐdeÐ!fÓgÐ gð ;:r
|
c óÊ | j rW| j j t j dj | j « « « | j dd
= yy)z9If there's a token being parsed, add it to the item list.rV N)r r r" r# rC rZ ra s r r3 zTokenizer.save_token5 sC à ::Ø JJ× Ñ e× 0Ñ 0°·±¸¿¹Ó1DÓ EÔ FØ
|
|
1 ð r
|
c óì | j sy| j d j t j k( r| j d j S ddj d | j D « « z S )z+Convert the parsed tokens back to a string.rV r r c 3 ó4 K | ] }|j y wrf )r~ )rh r s r rj z#Tokenizer.render.<locals>.<genexpr>A s è ø Ò A¨UU[[Ñ Aùs )r rg r# r$ r~ rZ ra s r ÚrenderzTokenizer.render; sX àzzØØ ZZ]× Ñ ¤5§=¡=Ò 0Ø::a=×&Ñ&Ð &ØRWWÑ A°d·j±jÔ AÓAÑAÐAr
|
N)r )r r r r rI Úcompiler r_ r@ rX r2 r r r% r& r' r( r) r* r+ r, r1 r? r3 r r r
|
r r r sª ñ ð BJJÐ0Ó 1EØ
|
|
9Ó%Ið RZZÐ2Ó 3Ø RZZÐ2Ó 3ñ Nð5Kà$Lòò&òPò8Mò2bò$ Fò$òLò,ò ò2ó" hò ó Br
|
r c óª e Zd ZdZg d¢ZdZdZdZdZdZ dZ
|
d Z d
|
Z d Z d Zd d ZdZdZdZdZdZd Zed « ZdZdZed d« Zd ZdZ dZ ed « Z y ) r# a)
|
A token in an Excel formula.
|
|
Tokens have three attributes:
|
|
* `value`: The string value parsed that led to this token
|
* `type`: A string identifying the type of token
|
* `subtype`: A string identifying subtype of the token (optional, and
|
defaults to "")
|
|
©r~ rg rF r$ rq ÚFUNCÚARRAYr ÚSEPzOPERATOR-PREFIXzOPERATOR-INFIXzOPERATOR-POSTFIXz WHITE-SPACEc ó. || _ || _ || _ y rf r )r r~ Útype_rF s r r zToken.__init___ s Ø
|
Ø Ø r
|
ÚTEXTÚNUMBERÚLOGICALÚERRORÚRANGEc ód dj | j | j | j « S )Nz {0} {1} {2}:)Úformatrg rF r~ ra s r Ú__repr__zToken.__repr__q s# Ø ×%Ñ% d§i¡i°· ± ¸t¿z¹zÓJÐJr
|
c ó* |j d« r | j }nG|j d« r | j }n)|dv r | j }n t |« | j
|
} | || j |« S # t $ r | j }Y +w xY w)zCreate an operand token.r r )ÚTRUEÚFALSE) rY r r r Úfloatr Ú
|
ValueErrorr rq ©Úclsr~ rF s r rC zToken.make_operandt s ð × Ñ CÔ ØhhGØ × Ñ cÔ "ØiiGØ Ð'Ñ 'ØkkGð $Üe Ø **ñ 5#++ wÓ/Ð/øô ò $Ø ))ð $ús ÁA: Á:BÂBÚOPENrp c ó* |d dv sJ |r)t j d|« sJ t j }n:|dv rt j }n%|dv rt j
|
}nt j }|dv r | j n | j } | |||« S )z
|
Create a subexpression token.
|
|
`value`: The value of the token
|
`func`: If True, force the token to be of type FUNC
|
|
rH )rv r{ ru rz z.+\(|\)z{}z()r! )rI rA r# r r r rp r¤ )r£ r~ Úfuncr rF s r rw zToken.make_subexp s ð RyÐ 0Ñ0Ð0Ð0Ù Ü88K¨Ô/Ð /Ð/ÜJJEØ d]ÜKKEØ d]ÜKKEäJJEØ $¨}#))°#·(±(Ù5% Ó)Ð)r
|
c ó( | j | j | j | j fv sJ | j | j
|
k( sJ | j | j k( rdnd}| j || j | j k( ¬« S )z6Return a closing token that matches this token's type.r{ rz )r¦ )rg r r r rF r¤ rw )r r~ s r r} zToken.get_closer§ sv àyyTYY¨¯
|
©
|
°D·J±JÐ ?Ñ?Ð?Ð?Ø||tyyÒ(Ð(Ð(Øyy D§J¡JÒ.°CØ× Ñ ¨D¯I©I¸¿¹Ñ,BÐ ÓCÐCr
|
ÚARGÚROWc óp |dv sJ |dk( r | j n | j } | || j |« S )zCreate a separator token)r r r )r¨ r© r r¢ s r r zToken.make_separator¹ s: ð
|
Ñ"Ð"Ð"Ø " c\#''¨s¯w©wÙ5#'' 7Ó+Ð+r
|
N)rV )F) r r r r Ú __slots__r$ rq r r r r rm rk rl r^ r r r r r r r Ú classmethodrC r¤ rp rw r} r¨ r© r r r
|
r r# r# D s¼ ñ
|
ò -IàGØGØ DØ EØ EØ
|
CØ FØ EØ GØ Fó ð DØ FØGØ EØ EòKð ñ0ó ð0ð2 DØ Eàò*ó ð*ò*Dð CØ
|
Càñ,ó ñ,r
|
r# )r rI Ú Exceptionr r r# r r
|
r ú<module>r® s6 ðñó
|
ô/Yô /÷qBñ qB÷h z,ò z,r
|
|
