o ѭjR@sdZddlZddlZddlZddlmZmZddlmZddl m Z m Z m Z m Z mZddlmZmZmZmZmZmZddlmZgdZed Zgd Zed d ZGd ddeZGdddedZ Gddde Z!Gddde"Z#GdddZ$e$Z%Gddde&Z'GdddZ(ddZ)GdddZ*e*Z+d d!Z,Gd"d#d#Z-Gd$d%d%eZ.Gd&d'd'eZ/Gd(d)d)e e/dZ0Gd*d+d+Z1Gd,d-d-e0Z2d.d/Z3Gd0d1d1e/Z4Gd2d3d3e0e4dZ5dS)4z pygments.lexer ~~~~~~~~~~~~~~ Base lexer classes. :copyright: Copyright 2006-present by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. N) apply_filtersFilter)get_filter_by_name)ErrorTextOther Whitespace _TokenType) get_bool_opt get_int_opt get_list_optmake_analysatorFuture guess_decode) regex_opt) Lexer RegexLexerExtendedRegexLexerDelegatingLexer LexerContextincludeinheritbygroupsusingthisdefaultwordsline_rez.*? ))sutf-8)szutf-32)szutf-32be)szutf-16)szutf-16becCdS)Nxr!r!K/var/www/html/CropPilot/venv/lib/python3.10/site-packages/pygments/lexer.py"r%c@eZdZdZddZdS) LexerMetaz This metaclass automagically converts ``analyse_text`` methods into static methods which always return float values. cCs(d|vr t|d|d<t||||S)N analyse_text)r type__new__)mcsnamebasesdr!r!r$r++szLexerMeta.__new__N)__name__ __module__ __qualname____doc__r+r!r!r!r$r(%s r(c@sneZdZdZdZgZgZgZgZdZ dZ dZ dZ ddZ ddZdd Zd d Zd d ZdddZddZdS)ra" Lexer for a specific language. See also :doc:`lexerdevelopment`, a high-level guide to writing lexers. Lexer classes have attributes used for choosing the most appropriate lexer based on various criteria. .. autoattribute:: name :no-value: .. autoattribute:: aliases :no-value: .. autoattribute:: filenames :no-value: .. autoattribute:: alias_filenames .. autoattribute:: mimetypes :no-value: .. autoattribute:: priority Lexers included in Pygments should have two additional attributes: .. autoattribute:: url :no-value: .. autoattribute:: version_added :no-value: Lexers included in Pygments may have additional attributes: .. autoattribute:: _example :no-value: You can pass options to the constructor. The basic options recognized by all lexers and processed by the base `Lexer` class are: ``stripnl`` Strip leading and trailing newlines from the input (default: True). ``stripall`` Strip all leading and trailing whitespace from the input (default: False). ``ensurenl`` Make sure that the input ends with a newline (default: True). This is required for some lexers that consume input linewise. .. versionadded:: 1.3 ``tabsize`` If given and greater than 0, expand tabs in the input (default: 0). ``encoding`` If given, must be an encoding name. This encoding will be used to convert the input string to Unicode, if it is not already a Unicode string (default: ``'guess'``, which uses a simple UTF-8 / Locale / Latin1 detection. Can also be ``'chardet'`` to use the chardet library, if it is installed. ``inencoding`` Overrides the ``encoding`` if given. NrcKs||_t|dd|_t|dd|_t|dd|_t|dd|_|dd |_|d p-|j|_g|_ t |d d D]}| |q8d S)a This constructor takes arbitrary options as keyword arguments. Every subclass must first process its own options and then call the `Lexer` constructor, since it processes the basic options like `stripnl`. An example looks like this: .. sourcecode:: python def __init__(self, **options): self.compress = options.get('compress', '') Lexer.__init__(self, **options) As these options must all be specifiable as strings (due to the command line usage), there are various utility functions available to help with that, see `Utilities`_. stripnlTstripallFensurenltabsizerencodingguess inencodingfiltersr!N) optionsr r4r5r6r r7getr8r;r add_filter)selfr<filter_r!r!r$__init__s zLexer.__init__cCs.|jrd|jjd|jdSd|jjdS)Nz)r< __class__r0r?r!r!r$__repr__szLexer.__repr__cKs*t|ts t|fi|}|j|dS)z8 Add a new stream filter to this lexer. N) isinstancerrr;append)r?r@r<r!r!r$r>s zLexer.add_filtercCr)a A static method which is called for lexer guessing. It should analyse the text and return a float in the range from ``0.0`` to ``1.0``. If it returns ``0.0``, the lexer will not be selected as the most probable one, if it returns ``1.0``, it will be selected immediately. This is used by `guess_lexer`. The `LexerMeta` metaclass automatically wraps this function so that it works like a static method (no ``self`` or ``cls`` parameter) and the return value is automatically converted to `float`. If the return value is an object that is boolean `False` it's the same as if the return values was ``0.0``. Nr!)textr!r!r$r)r&zLexer.analyse_textc Csvt|tsy|jdkrt|\}}nu|jdkrezddl}Wnty-}ztd|d}~wwd}tD]\}}||rI|t|d |d}nq2|durb| |dd}| | dp_d d}|}n!| |j}|d rx|td d}n |d r|td d}| d d }| d d }|j r|}n|jr|d }|jdkr||j}|jr|d s|d 7}|S)zVApply preprocessing such as decoding the input, removing BOM and normalizing newlines.r9chardetrNzkTo enable chardet encoding guessing, please install the chardet library from http://chardet.feedparser.org/replaceir8ruz   )rFstrr8rrI ImportError _encoding_map startswithlendecodedetectr=rJr5stripr4r7 expandtabsr6endswith) r?rH_rIedecodedbomr8encr!r!r$_preprocess_lexer_inputsR               zLexer._preprocess_lexer_inputFcs4fdd}|}|st|j}|S)ae This method is the basic interface of a lexer. It is called by the `highlight()` function. It must process the text and return an iterable of ``(tokentype, value)`` pairs from `text`. Normally, you don't need to override this method. The default implementation processes the options recognized by all lexers (`stripnl`, `stripall` and so on), and then yields all tokens from `get_tokens_unprocessed()`, with the ``index`` dropped. If `unfiltered` is set to `True`, the filtering mechanism is bypassed even if filters are defined. c3s&D] \}}}||fVqdSN)get_tokens_unprocessed)rWtvr?rHr!r$streamer s z"Lexer.get_tokens..streamer)r\rr;)r?rH unfilteredrbstreamr!rar$ get_tokenss zLexer.get_tokenscCst)aS This method should process the text and return an iterable of ``(index, tokentype, value)`` tuples where ``index`` is the starting position of the token within the input text. It must be overridden by subclasses. It is recommended to implement it as a generator to maximize effectiveness. )NotImplementedErrorrar!r!r$r^s zLexer.get_tokens_unprocessed)F)r0r1r2r3r-aliases filenamesalias_filenames mimetypespriorityurl version_added_examplerArEr>r)r\rer^r!r!r!r$r1s$; / r) metaclassc@s$eZdZdZefddZddZdS)ra  This lexer takes two lexer as arguments. A root lexer and a language lexer. First everything is scanned using the language lexer, afterwards all ``Other`` tokens are lexed using the root lexer. The lexers from the ``template`` lexer package use this base lexer. cKs<|di||_|di||_||_tj|fi|dSNr!) root_lexerlanguage_lexerneedlerrA)r? _root_lexer_language_lexer_needler<r!r!r$rA+szDelegatingLexer.__init__cCsd}g}g}|j|D]$\}}}||jur(|r#|t||fg}||7}q ||||fq |r<|t||ft||j|S)N)rrr^rsrGrQ do_insertionsrq)r?rHbuffered insertions lng_bufferir_r`r!r!r$r^1s   z&DelegatingLexer.get_tokens_unprocessedN)r0r1r2r3rrAr^r!r!r!r$r!s rc@eZdZdZdS)rzI Indicates that a state should include rules from another state. Nr0r1r2r3r!r!r!r$rHsrc@r')_inheritzC Indicates the a state should inherit from its superclass. cCr)Nrr!rDr!r!r$rESz_inherit.__repr__N)r0r1r2r3rEr!r!r!r$rOs rc@s eZdZdZddZddZdS)combinedz: Indicates a state combined from multiple states. cGs t||Sr])tupler+)clsargsr!r!r$r+^s zcombined.__new__cGsdSr]r!)r?rr!r!r$rAaszcombined.__init__N)r0r1r2r3r+rAr!r!r!r$rYs rc@sFeZdZdZddZdddZdddZdd d Zd d Zd dZ dS) _PseudoMatchz: A pseudo match object constructed from a string. cCs||_||_dSr])_text_start)r?startrHr!r!r$rAks z_PseudoMatch.__init__NcCs|jSr])rr?argr!r!r$rosz_PseudoMatch.startcCs|jt|jSr])rrQrrr!r!r$endrsz_PseudoMatch.endcCs|rtd|jS)Nz No such group) IndexErrorrrr!r!r$groupusz_PseudoMatch.groupcCs|jfSr])rrDr!r!r$groupszsz_PseudoMatch.groupscCsiSr]r!rDr!r!r$ groupdict}rz_PseudoMatch.groupdictr]) r0r1r2r3rArrrrrr!r!r!r$rfs    rcsdfdd }|S)zL Callback that yields multiple actions for each group in the match. Nc3stD]O\}}|durqt|tur)||d}|r(||d||fVq||d}|durT|r>||d|_||t||d||D]}|rS|VqLq|r^||_dSdS)N) enumerater*r rrposrr)lexermatchctxr|actiondataitemrr!r$callbacks, zbygroups..callbackr]r!)rrr!rr$rsrc@r})_ThiszX Special singleton used for indicating the caller class. Used by ``using``. Nr~r!r!r!r$rsrc slidvrd}t|ttfr|d<nd|fd<tur+dfdd }|Sdfdd }|S) a Callback that processes the match with a different lexer. The keyword arguments are forwarded to the lexer, except `state` which is handled separately. `state` specifies the state that the new lexer will start in, and can be an enumerable such as ('root', 'inline', 'string') or a simple string which is assumed to be on top of the root state. Note: For that to work, `_other` must not be an `ExtendedRegexLexer`. statestackrootNc 3srt|j}||jdi|}n|}|}|j|fiD] \}}}||||fVq'|r>||_dSdSrp) dictr<updaterCrr^rrr rrrr/lxsr|r_r`) gt_kwargskwargsr!r$rs   zusing..callbackc 3stt|j}|di|}|}|j|fiD] \}}}||||fVq!|r8||_dSdSrp)rr<rrr^rrrr_otherrrr!r$rs   r])poprFlistrr)rrrrr!rr$rs     rc@r')rz Indicates a state or state action (e.g. #pop) to apply. For example default('#pop') is equivalent to ('', Token, '#pop') Note that state tuples may be used as well. .. versionadded:: 2.0 cCs ||_dSr])r)r?rr!r!r$rAs zdefault.__init__N)r0r1r2r3rAr!r!r!r$rs rc@s"eZdZdZdddZddZdS) rz Indicates a list of literal words that is transformed into an optimized regex that matches any of the words. .. versionadded:: 2.0 rwcCs||_||_||_dSr])rprefixsuffix)r?rrrr!r!r$rAs zwords.__init__cCst|j|j|jdS)Nrr)rrrrrDr!r!r$r=sz words.getN)rwrw)r0r1r2r3rAr=r!r!r!r$rs  rc@sJeZdZdZddZddZddZdd Zdd d Zd dZ ddZ d S)RegexLexerMetazw Metaclass for RegexLexer, creates the self._tokens attribute from self.tokens on the first instantiation. cCs t|tr |}t||jS)zBPreprocess the regular expression component of a token definition.)rFrr=recompiler)rregexrflagsrr!r!r$_process_regexs zRegexLexerMeta._process_regexcCs&t|tust|sJd||S)z5Preprocess the token component of a token definition.z0token type must be simple type or callable, not )r*r callable)rtokenr!r!r$_process_tokenszRegexLexerMeta._process_tokencCs t|tr0|dkr dS||vr|fS|dkr|S|dddkr)t|dd SJd|t|trdd |j}|jd 7_g}|D]}||ksRJd ||||||qE|||<|fSt|tr~|D]}||vs{|d vs{Jd|qk|SJd |)z=Preprocess the state transition action of a token definition.#pop#pushNz#pop:Fzunknown new state z_tmp_%drzcircular state ref )rrzunknown new state def )rFrMintr_tmpnameextend_process_stater)r new_state unprocessed processed tmp_stateitokensistater!r!r$_process_new_states<      z!RegexLexerMeta._process_new_statec Cst|ts Jd||ddksJd|||vr!||Sg}||<|j}||D]}t|trM||ks@Jd|||||t|q.t|trSq.t|trm||j ||}| t dj d|fq.t|tuszJd|z ||d||}Wnty} ztd |dd |d |d | | d} ~ ww||d } t|dkrd}n ||d||}| || |fq.|S)z%Preprocess a single state definition.zwrong state name r#zinvalid state name zcircular state reference rwNzwrong rule def zuncompilable regex z in state z of z: r)rFrMflagsrrrrrrrrGrrrr*rr Exception ValueErrorrrQ) rrrrtokensrtdefrrexerrrr!r!r$r)sD      &  zRegexLexerMeta._process_stateNcCs<i}|j|<|p |j|}t|D] }||||q|S)z-Preprocess a dictionary of token definitions.) _all_tokensrrr)rr- tokendefsrrr!r!r$process_tokendefTs  zRegexLexerMeta.process_tokendefc Csi}i}|jD]_}|jdi}|D]Q\}}||}|dur;|||<z|t}Wn ty5Yqw|||<q||d}|durFq||||d<z|t} Wn ty^Yqw|| ||<qq|S)a Merge tokens from superclasses in MRO order, returning a single tokendef dictionary. Any state that is not defined by a subclass will be inherited automatically. States that *are* defined by subclasses will, by default, override that state in the superclass. If a subclass wishes to inherit definitions from a superclass, it can use the special value "inherit", which will cause the superclass' state definition to be included at that point in the state. rNr)__mro____dict__r=itemsindexrrr) rr inheritablectoksrrcuritems inherit_ndx new_inh_ndxr!r!r$ get_tokendefs\s6      zRegexLexerMeta.get_tokendefscOsRd|jvri|_d|_t|dr|jrn |d||_tj |g|Ri|S)z:Instantiate cls after preprocessing its token definitions._tokensrtoken_variantsrw) rrrhasattrrrrrr*__call__)rrkwdsr!r!r$rs zRegexLexerMeta.__call__r]) r0r1r2r3rrrrrrrr!r!r!r$rs# + 1rc@s$eZdZdZejZiZdddZdS)rz Base for simple stateful regular expression-based lexers. Simplifies the lexing process so that you need only provide a list of states and regular expressions. rc csd}|j}t|}||d} |D]\}}} |||} | r|dur:t|tur2||| fVn||| EdH| }| durt| trm| D]"} | dkrZt|dkrY| qI| dkrf| |dqI| | qIn,t| t rt | t|kr|dd=n|| d=n| dkr| |dnJd| ||d}n3qz'||d krd g}|d }|t d fV|d7}Wq|t||fV|d7}Wn tyYdSwq) z~ Split ``text`` into (tokentype, text) pairs. ``stack`` is the initial stack (default: ``['root']``) rrrNrrFwrong state def: rKr)rrr*r rrrFrrQrrGrabsrrr) r?rHrrr statestack statetokensrexmatchrrmrr!r!r$r^s`          #    z!RegexLexer.get_tokens_unprocessedNr) r0r1r2r3r MULTILINErrr^r!r!r!r$rs rc@s"eZdZdZdddZddZdS)rz9 A helper object that holds lexer position data. NcCs*||_||_|p t||_|pdg|_dS)Nr)rHrrQrr)r?rHrrrr!r!r$rAszLexerContext.__init__cCsd|jd|jd|jdS)Nz LexerContext(z, ))rHrrrDr!r!r$rEszLexerContext.__repr__NN)r0r1r2r3rArEr!r!r!r$rs  rc@seZdZdZdddZdS)rzE A RegexLexer that uses a context object to store its state. Nc cs |j}|st|d}|d}n |}||jd}|j} |D]\}}}|||j|j} | r|durYt|turG|j|| fV| |_n||| |EdH|sY||jd}|durt |t r|D]'} | dkrwt |jdkrv|j qd| dkr|j |jdqd|j | qdn1t |trt|t |jkr|jdd=n|j|d=n|dkr|j |jdnJd |||jd}nHqz;|j|jkrWdS||jd krdg|_|d}|jtd fV|jd7_Wq|jt||jfV|jd7_Wn tyYdSwq) z Split ``text`` into (tokentype, text) pairs. If ``context`` is given, use this lexer context instead. rrrrNrrFrrK)rrrrHrrr*r rrFrrQrrGrrrrr) r?rHcontextrrrrrrrrr!r!r$r^sn       # z)ExtendedRegexLexer.get_tokens_unprocessedr)r0r1r2r3r^r!r!r!r$r src cst|}zt|\}}Wnty|EdHYdSwd}d}|D]{\}}}|dur.|}d} |r|t||kr|| ||} | rP||| fV|t| 7}|D]\} } } || | fV|t| 7}qR||} zt|\}}Wn ty{d}Yn w|r|t||ks:| t|kr|||| dfV|t|| 7}q#|r|pd}|D]\}}}|||fV|t|7}qzt|\}}Wn tyd}YdSw|sdSdS)ag Helper for lexers which must combine the results of several sublexers. ``insertions`` is a list of ``(index, itokens)`` pairs. Each ``itokens`` iterable should be inserted at position ``index`` into the token stream given by the ``tokens`` argument. The result is a combined token stream. TODO: clean up the code here. NTrF)iternext StopIterationrQ)rzrrrrealposinsleftr|r_r`olditmpvalit_indexit_tokenit_valuepr!r!r$rxSs\          rxc@r')ProfilingRegexLexerMetaz>Metaclass for ProfilingRegexLexer, collects regex timing info.csLt|trt|j|j|jdn|t|tjffdd }|S)Nrcs`jdfddg}t}|||}t}|dd7<|d||7<|S)Nrrr r) _prof_data setdefaulttimer)rHrendposinfot0rest1rcompiledrrr!r$ match_funcsz:ProfilingRegexLexerMeta._process_regex..match_func) rFrrrrrrsysmaxsize)rrrrrr!rr$rs   z&ProfilingRegexLexerMeta._process_regexN)r0r1r2r3rr!r!r!r$rs rc@s"eZdZdZgZdZdddZdS)ProfilingRegexLexerzFDrop-in replacement for RegexLexer that does profiling of its regexes.rc#sjjit||EdHjj}tdd|Dfdddd}tdd|D}t t djj t ||ft d t d d t d |D]}t d |qSt d dS)NcssP|]#\\}}\}}|t|ddddd|d|d||fVqdS)zu'z\\\NAi)reprrTrJ).0rrnr_r!r!r$ s  z=ProfilingRegexLexer.get_tokens_unprocessed..cs |jSr])_prof_sort_indexr"rDr!r$r%s z.T)keyreversecss|]}|dVqdS)Nr!)r r#r!r!r$rsz2Profiling result for %s lexing %d chars in %.3f mszn==============================================================================================================z$%-20s %-64s ncalls tottime percall)rrzn--------------------------------------------------------------------------------------------------------------z%-20s %-65s %5d %8.4f %8.4f) rCrrGrr^rsortedrsumprintr0rQ)r?rHrrawdatar sum_totalr/r!rDr$r^s*    z*ProfilingRegexLexer.get_tokens_unprocessedNr)r0r1r2r3rrr^r!r!r!r$rs r)6r3rrrpygments.filterrrpygments.filtersrpygments.tokenrrrrr pygments.utilr r r r rrpygments.regexoptr__all__rrrO staticmethod_default_analyser*r(rrrMrrrrrrrrrrrrrrrrrxrrr!r!r!r$sH       q' 4 (aH@