a jS@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$d%d%eZ.Gd&d'd'eZ/Gd(d)d)e e/dZ0Gd*d+d+Z1Gd,d-d-e0Z2d.d/Z3Gd0d1d1e/Z4Gd2d3d3e0e4dZ5dS)4z pygments.lexer ~~~~~~~~~~~~~~ Base lexer classes. :copyright: Copyright 2006-present by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. N) apply_filtersFilter)get_filter_by_name)ErrorTextOther Whitespace _TokenType) get_bool_opt get_int_opt get_list_optmake_analysatorFuture guess_decode) regex_opt) Lexer RegexLexerExtendedRegexLexerDelegatingLexer LexerContextincludeinheritbygroupsusingthisdefaultwordsline_rez.*? ))sutf-8)szutf-32)szutf-32be)szutf-16)szutf-16becCsdS)Nxr r 4E:\soccer\ml_env\Lib\site-packages\pygments/lexer.py"r$c@seZdZdZddZdS) LexerMetaz This metaclass automagically converts ``analyse_text`` methods into static methods which always return float values. cCs(d|vrt|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&%sr&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 pZ|j|_g|_ t |d d D]}| |qpd 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 r2r3r4r r5getr6r9r add_filter)selfr:filter_r r r#__init__szLexer.__init__cCs2|jrd|jjd|jdSd|jjdSdS)Nz)r: __class__r.r=r r r#__repr__szLexer.__repr__cKs*t|tst|fi|}|j|dS)z8 Add a new stream filter to this lexer. N) isinstancerrr9append)r=r>r:r r r#r<s zLexer.add_filtercCsdS)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'szLexer.analyse_textc Cst|ts|jdkr"t|\}}n|jdkrz ddl}Wn.tyf}ztd|WYd}~n d}~00d}tD].\}}||rp|t|d |d}qqp|dur| |dd}| | dpd d}|}n&| |j}|d r|td d}n|d r|td d}| d d }| d d }|j rD|}n|jrV|d }|jdkrn||j}|jr|d s|d 7}|S)zVApply preprocessing such as decoding the input, removing BOM and normalizing newlines.r7chardetrNzkTo enable chardet encoding guessing, please install the chardet library from http://chardet.feedparser.org/replaceir6ruz   )rDstrr6rrG ImportError _encoding_map startswithlendecodedetectr;rHr3stripr2r5 expandtabsr4endswith) r=rF_rGedecodedbomr6encr r r#_preprocess_lexer_inputsJ               zLexer._preprocess_lexer_inputFcs4fdd}|}|s0t|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$D]\}}}||fVq dSN)get_tokens_unprocessed)rUtvr=rFr r#streamer sz"Lexer.get_tokens..streamer)rZrr9)r=rF unfilteredr`streamr r_r# get_tokenss  zLexer.get_tokenscCstdS)aS This method should process the text and return an iterable of ``(index, tokentype, value)`` tuples where ``index`` is the starting position of the token within the input text. It must be overridden by subclasses. It is recommended to implement it as a generator to maximize effectiveness. N)NotImplementedErrorr_r r r#r\s zLexer.get_tokens_unprocessed)F)r.r/r0r1r+aliases filenamesalias_filenames mimetypespriorityurl version_added_exampler?rCr<r'rZrcr\r r r r#r1s";/ r) metaclassc@s$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<|fi||_|fi||_||_tj|fi|dSr[) root_lexerlanguage_lexerneedlerr?)r= _root_lexer_language_lexer_needler:r r r#r?+szDelegatingLexer.__init__cCsd}g}g}|j|D]H\}}}||jurP|rF|t||fg}||7}q||||fq|rx|t||ft||j|S)N)ror\rprErO do_insertionsrn)r=rFbuffered insertions lng_bufferir]r^r r r#r\1s   z&DelegatingLexer.get_tokens_unprocessedN)r.r/r0r1rr?r\r r r r#r!s rc@seZdZdZdS)rzI Indicates that a state should include rules from another state. Nr.r/r0r1r r r r#rHsrc@seZdZdZddZdS)_inheritzD Indicates that a state should inherit from its superclass. cCsdS)Nrr rBr r r#rCSsz_inherit.__repr__N)r.r/r0r1rCr r r r#r{Osr{c@s eZdZdZddZddZdS)combinedz: Indicates a state combined from multiple states. cGs t||Sr[)tupler))clsargsr r r#r)^szcombined.__new__cGsdSr[r )r=rr r r#r?aszcombined.__init__N)r.r/r0r1r)r?r r r r#r|Ysr|c@sFeZdZdZddZdddZdddZdd d Zd d Zd dZ dS) _PseudoMatchz: A pseudo match object constructed from a string. cCs||_||_dSr[)_text_start)r=startrFr r r#r?ksz_PseudoMatch.__init__NcCs|jSr[)rr=argr r r#rosz_PseudoMatch.startcCs|jt|jSr[)rrOrrr r r#endrsz_PseudoMatch.endcCs|r td|jS)Nz No such group) IndexErrorrrr r r#groupusz_PseudoMatch.groupcCs|jfSr[)rrBr r r#groupszsz_PseudoMatch.groupscCsiSr[r rBr r r# groupdict}sz_PseudoMatch.groupdict)N)N)N) r.r/r0r1r?rrrrrr r r r#rfs   rcsdfdd }|S)zL Callback that yields multiple actions for each group in the match. Nc3stD]\}}|durqqt|turR||d}|r||d||fVq||d}|dur|r|||d|_||t||d||D]}|r|Vqq|r||_dS)N) enumerater(r rrposrr)lexermatchctxryactiondataitemrr r#callbacks$  zbygroups..callback)Nr )rrr rr#rsrc@seZdZdZdS)_ThiszX Special singleton used for indicating the caller class. Used by ``using``. Nrzr r r r#rsrc sjidvr:d}t|ttfr.|d<n d|fd<turTdfdd }nd fdd }|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 3szr*t|j}||jfi|}n|}|}|j|fiD]\}}}||||fVqL|rv||_dSr[) dictr:updaterArr\rrr rrrr-lxsryr]r^) gt_kwargskwargsr r#rs   zusing..callbackc 3snt|j}|fi|}|}|j|fiD]\}}}||||fVq@|rj||_dSr[)rr:rrr\rrrr_otherrrr r#rs   )N)N)poprDlistr}r)rrrrr rr#rs     rc@seZdZdZddZdS)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#r?szdefault.__init__N)r.r/r0r1r?r r r r#rsrc@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 rtcCs||_||_||_dSr[)rprefixsuffix)r=rrrr r r#r?szwords.__init__cCst|j|j|jdS)Nrr)rrrrrBr r r#r;sz words.getN)rtrt)r.r/r0r1r?r;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.)rDrr;recompiler)r~regexrflagsrr r r#_process_regexs zRegexLexerMeta._process_regexcCs&t|tus"t|s"Jd||S)z5Preprocess the token component of a token definition.z0token type must be simple type or callable, not )r(r callable)r~tokenr r r#_process_tokenszRegexLexerMeta._process_tokencCst|trf|dkrdS||vr$|fS|dkr0|S|dddkrRt|dd SdsdJd|nt|trd |j}|jd 7_g}|D].}||ksJd ||||||q|||<|fSt|tr|D] }||vs|d vsJd|q|SdsJd |dS)z=Preprocess the state transition action of a token definition.#pop#pushNz#pop:Fzunknown new state z_tmp_%drzcircular state ref )rrzunknown new state def )rDrKintr|_tmpnameextend_process_stater})r~ new_state unprocessed processed tmp_stateitokensistater r r#_process_new_states<     z!RegexLexerMeta._process_new_statec Cst|tsJd||ddks2Jd|||vrB||Sg}||<|j}||D]@}t|tr||ksJd|||||t|q\t|trq\t|tr||j ||}| t dj d|fq\t|tusJd|z||d||}WnLtyX} z2td |dd |d |d | | WYd} ~ n d} ~ 00||d } t|dkr|d}n||d||}| || |fq\|S)z%Preprocess a single state definition.zwrong state name r#zinvalid state name zcircular state reference rtNzwrong rule def zuncompilable regex z in state z of z: r)rDrKflagsrrrr{rrrrErrrr(r}r Exception ValueErrorrrO) r~rrrtokensrtdefrrexerrrr r r#r)s@     < zRegexLexerMeta._process_stateNcCs<i}|j|<|p|j|}t|D]}||||q$|S)z-Preprocess a dictionary of token definitions.) _all_tokensrrr)r~r+ tokendefsrrr r r#process_tokendefTs  zRegexLexerMeta.process_tokendefc Csi}i}|jD]}|jdi}|D]\}}||}|durz|||<z|t}WntynYq(Yn0|||<q(||d}|durq(||||d<z|t} WntyYq(0|| ||<q(q|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) r~r inheritablectoksrrcuritems inherit_ndx new_inh_ndxr r r# get_tokendefs\s0       zRegexLexerMeta.get_tokendefscOsRd|jvr:i|_d|_t|dr(|jr(n|d||_tj |g|Ri|S)z:Instantiate cls after preprocessing its token definitions._tokensrtoken_variantsrt) rrrhasattrrrrrr(__call__)r~rkwdsr r r#rs zRegexLexerMeta.__call__)N) r.r/r0r1rrrrrrrr r r r#rs#+ 1rc@s$eZdZdZejZiZdddZdS)rz Base for simple stateful regular expression-based lexers. Simplifies the lexing process so that you need only provide a list of states and regular expressions. rc csd}|j}t|}||d}|D]*\}}} |||} | r"|durrt|turb||| fVn||| EdH| }| durJt| tr| D]D} | dkrt|dkr| q| dkr| |dq| | qndt| t rt | t|kr|dd=n || d=n.| dkr*| |dnds>Jd| ||d}qq"zP||d krd g}|d }|t d fV|d7}Wq|t||fV|d7}WqtyYqYq0qdS) z~ Split ``text`` into (tokentype, text) pairs. ``stack`` is the initial stack (default: ``['root']``) rrNrrrFwrong state def: rIr)rrr(r rrrDr}rOrrErabsrrr) r=rFrrr statestack statetokensrexmatchrrmrr r r#r\sR              z!RegexLexer.get_tokens_unprocessedN)r) r.r/r0r1r MULTILINErrr\r r r r#rsrc@s"eZdZdZdddZddZdS)rz9 A helper object that holds lexer position data. NcCs*||_||_|pt||_|p"dg|_dS)Nr)rFrrOrr)r=rFrrrr r r#r?szLexerContext.__init__cCsd|jd|jd|jdS)Nz LexerContext(z, ))rFrrrBr r r#rCszLexerContext.__repr__)NN)r.r/r0r1r?rCr r r r#rs rc@seZdZdZdddZdS)rzE A RegexLexer that uses a context object to store its state. Nc cs<|j}|st|d}|d}n|}||jd}|j}|D]b\}}}|||j|j} | r:|durt|tur|j|| fV| |_n$||| |EdH|s||jd}|durt |t r|D]P} | dkrt |jdkr|j q| dkr|j |jdq|j | qnnt |trZt|t |jkrL|jdd=n |j|d=n2|dkrx|j |jdndsJd |||jd}q6q:zz|j|jkrWq8||jd krdg|_|d}|jtd fV|jd7_Wq6|jt||jfV|jd7_Wq6ty4Yq8Yq60q6dS) z Split ``text`` into (tokentype, text) pairs. If ``context`` is given, use this lexer context instead. rrrNrrrFrrI)rrrrFrrr(r rrDr}rOrrErrrrr) r=rFcontextrrrrrrrrr r r#r\s`          z)ExtendedRegexLexer.get_tokens_unprocessed)NN)r.r/r0r1r\r r r r#r src cst|}zt|\}}Wnty6|EdHYdS0d}d}|D]\}}}|durZ|}d} |r|t||kr|| ||} | r||| fV|t| 7}|D]"\} } } || | fV|t| 7}q||} zt|\}}Wq^tyd}YqYq^0q^| t|krD|||| dfV|t|| 7}qD|r|pDd}|D]$\}}}|||fV|t|7}qJzt|\}}Wntyd}YqYn0q6dS)ag Helper for lexers which must combine the results of several sublexers. ``insertions`` is a list of ``(index, itokens)`` pairs. Each ``itokens`` iterable should be inserted at position ``index`` into the token stream given by the ``tokens`` argument. The result is a combined token stream. TODO: clean up the code here. NTrF)iternext StopIterationrO)rwrrrrealposinsleftryr]r^olditmpvalit_indexit_tokenit_valuepr r r#ruSsN        ruc@seZdZdZddZdS)ProfilingRegexLexerMetaz>Metaclass for ProfilingRegexLexer, collects regex timing info.csLt|tr t|j|j|jdn|t|tjffdd }|S)Nrcs`jdfddg}t}|||}t}|dd7<|d||7<|S)Nrrrr) _prof_data setdefaulttimer)rFrendposinfot0rest1r~compiledrrr r# match_funcsz:ProfilingRegexLexerMeta._process_regex..match_func) rDrrrrrrsysmaxsize)r~rrrrr rr#rs   z&ProfilingRegexLexerMeta._process_regexN)r.r/r0r1rr r r r#rsrc@s"eZdZdZgZdZdddZdS)ProfilingRegexLexerzFDrop-in replacement for RegexLexer that does profiling of its regexes.rc#sjjit||EdHjj}tdd|Dfdddd}tdd|D}t t djj t ||ft d t d d t d |D]}t d |qt d dS)NcssN|]F\\}}\}}|t|ddddd|d|d||fVqdS)zu'z\\\NAi)reprrRrH).0rrnr]r r r# sz=ProfilingRegexLexer.get_tokens_unprocessed..cs |jSr[)_prof_sort_indexr!rBr r#r$r%z.T)keyreversecss|]}|dVqdS)Nr )rr"r r r#rr%z2Profiling result for %s lexing %d chars in %.3f mszn==============================================================================================================z$%-20s %-64s ncalls tottime percall)rrzn--------------------------------------------------------------------------------------------------------------z%-20s %-65s %5d %8.4f %8.4f) rArrErr\rsortedrsumprintr.rO)r=rFrrawdatar sum_totalr-r rBr#r\s(   z*ProfilingRegexLexer.get_tokens_unprocessedN)r)r.r/r0r1rrr\r r r r#rsr)6r1rrrZpygments.filterrrZpygments.filtersrZpygments.tokenrrrrr Z pygments.utilr r r r rrZpygments.regexoptr__all__rrrM staticmethod_default_analyser(r&rrrKrr{rr}r|rrrrrrrrrrrrurrr r r r#sF       q' 4 (aH@