=wg0dZddlmZddlmZmZddlmZddlm Z m Z Gdde Z Gdd e Z Gd d e ZGd d e ZGdde ZGdde ZGddeZy)zM This module contains helper functions for correcting typos in user queries. ) bisect_left)heappush heapreplace) highlight) iteritemsxrangeceZdZdZddZdZy) Correctorz| Base class for spelling correction objects. Concrete sub-classes should implement the ``_suggestions`` method. c|j}g}||||D]2}t||kr t||||dkDs't||4t |d}|D cgc]\} } |  c} } Scc} } w)aR :param text: the text to check. This word will **not** be added to the suggestions, even if it appears in the word graph. :param limit: only return up to this many suggestions. If there are not enough terms in the field within ``maxdist`` of the given word, the returned list will be shorter than this number. :param maxdist: the largest edit distance from the given word to look at. Values higher than 2 are not very effective or efficient. :param prefix: require suggestions to share a prefix of this length with the given word. This is often justifiable since most misspellings do not involve the first letter of the word. Using a prefix dramatically decreases the time it takes to generate the list of words. rcd|dz |dfS)Nr)xs F/var/www/horilla/myenv/lib/python3.12/site-packages/whoosh/spelling.pyz#Corrector.suggest..Is1qt8QqT*:)key) _suggestionslenrrsorted) selftextlimitmaxdistprefixrheapitemsugs_sugs rsuggestzCorrector.suggest/s~ ((  w7 (D4y5 t$QD$'  (d :;"&'3'''s! A1ct)a) Low-level method that yields a series of (score, "suggestion") tuples. :param text: the text to check. :param maxdist: the maximum edit distance. :param prefix: require suggestions to share a prefix of this length with the given word. NotImplementedError)rrrrs rrzCorrector._suggestionsLs "!rN)r)__name__ __module__ __qualname____doc__r!rrrrr r )s (: "rr ceZdZdZdZdZy)ReaderCorrectorz Suggests corrections based on the content of a field in a reader. Ranks suggestions by the edit distance, then by highest to lowest frequency. c.||_||_||_yN)reader fieldnamefieldobj)rr/r0r1s r__init__zReaderCorrector.__init__bs "  rc# K|j}|j}|j}|j|}|j |}|j ||||D]#} ||| xsd} d|d| z dzzz } | | f%yw)N)rr rg?g?)r/ frequencyr0schemaspelling_fieldname terms_within) rrrrr/freqr0r1sugfieldr fscores rrzReaderCorrector._suggestionsgsNN ==+..y9&&xwv&N CY$)AC!GcM23E#,   sBBNr'r(r)r*r2rrrrr,r,Zs! rr,c2eZdZdZdZdZGddeZy) ListCorrectorzP Suggests corrections based on the content of a sorted list of strings. c||_yr.)wordlist)rr@s rr2zListCorrector.__init__{s   rc# Kddlm}ddlm}t }t d|dzD]b}||||j }|j|j} ||| D]!} | |vs|j| d|z | f#dyw)Nr)levenshtein_automaton)find_all_matchesr ) whoosh.automata.levrBwhoosh.automata.fsarCsetrto_dfaSkipperr@add) rrrrrBrCseenidfaskr s rrzListCorrector._suggestions~s=8u7Q;' -A'gv>EEGCdmm,B'R0 -d?HHSMw;,, - -s A,B/BceZdZdZdZy)ListCorrector.Skipperc ||_d|_y)Nr)datarK)rrQs rr2zListCorrector.Skipper.__init__sDIDFrc|j|j|k(r|S|xjdz c_t|j||j}|t|jkr|j|Sy)Nr )rQrKrr)rwposs r__call__zListCorrector.Skipper.__call__s`yy A% FFaKFdiiDFF3CS^#yy~%rN)r'r(r)r2rUrrrrHrOs   rrHN)r'r(r)r*r2robjectrHrrrr>r>vs! - & rr>ceZdZdZdZdZy)MultiCorrectorz; Merges suggestions from a list of sub-correctors. c ||_||_yr.) correctorsop)rrZr[s rr2zMultiCorrector.__init__s$rc|j}i}|jD]6}|j|||D]\}}||vr||||||<|||< 8t|Sr.)r[rZrr) rrrrr[rJcorrr;r s rrzMultiCorrector._suggestionssu WWOO &D"//gvF & s$; "49e 4DI %DI  & & rNr<rrrrXrXs rrXc"eZdZdZdZdZdZy) Correctiona Represents the corrected version of a user query string. Has the following attributes: ``query`` The corrected :class:`whoosh.query.Query` object. ``string`` The corrected user query string. ``original_query`` The original :class:`whoosh.query.Query` object that was corrected. ``original_string`` The original user query string. ``tokens`` A list of token objects representing the corrected words. You can also use the :meth:`Correction.format_string` method to reformat the corrected query string using a :class:`whoosh.highlight.Formatter` class. For example, to display the corrected query string as HTML with the changed words emphasized:: from whoosh import highlight correction = mysearcher.correct_query(q, qstring) hf = highlight.HtmlFormatter(classname="change") html = correction.format_string(hf) c||_||_||_||_|jr)|j t j |_yd|_y)N)original_queryqueryoriginal_stringtokens format_stringr NullFormatterstring)rqqstringcorr_qres rr2zCorrection.__init__sK &   ,,Y-D-D-FGDKDKrch|jjd|jd|jdS)N(z, )) __class__r'rcrhrs r__repr__zCorrection.__repr__s&#~~66 #{{, ,rc|jsyt|tr|}tj|j|j }|j |dS)a Highlights the corrected words in the original query string using the given :class:`~whoosh.highlight.Formatter`. :param formatter: A :class:`whoosh.highlight.Formatter` instance. :return: the output of the formatter (usually a string). raT)replace)rd isinstancetyperFragmentreformat_fragment)r formatterfragments rrfzCorrection.format_stringsS## i &! I%%d&:&:DKKH((4(@@rN)r'r(r)r*r2rqrfrrrr_r_s8 ,Arr_c"eZdZdZdZdZdZy)QueryCorrectorzD Base class for objects that correct words in a user query. c||_yr.r0)rr0s rr2zQueryCorrector.__init__s "rct)a Returns a :class:`Correction` object representing the corrected form of the given query. :param q: the original :class:`whoosh.query.Query` tree to be corrected. :param qstring: the original user query. This may be None if the original query string is not available, in which case the ``Correction.string`` attribute will also be None. :rtype: :class:`Correction` r#)rrirjs r correct_queryzQueryCorrector.correct_querys "!rc|jSr.r}rps rfieldzQueryCorrector.field s ~~rN)r'r(r)r*r2rrrrrr{r{s# "rr{ceZdZdZddZdZy)SimpleQueryCorrectora A simple query corrector based on a mapping of field names to :class:`Corrector` objects, and a list of ``("fieldname", "text")`` tuples to correct. And terms in the query that appear in list of term tuples are corrected using the appropriate corrector. Ncd||_|xsi|_t||_||_||_y)a :param correctors: a dictionary mapping field names to :class:`Corrector` objects. :param terms: a sequence of ``("fieldname", "text")`` tuples representing terms to be corrected. :param aliases: a dictionary mapping field names in the query to field names for spelling suggestions. :param prefix: suggested replacement words must share this number of initial characters with the original word. Increasing this even to just ``1`` can dramatically speed up suggestions, and may be justifiable since spellling mistakes rarely involve the first letter of a word. :param maxdist: the maximum number of "edits" (insertions, deletions, subsitutions, or transpositions of letters) allowed between the original word and any suggestion. Values higher than ``2`` may be slow. N)rZaliases frozensettermsetrr)rrZtermsrrrs rr2zSimpleQueryCorrector.__init__s0&%}"  '   rc|j}|j}|j}|j}|j}g}|} |j D]} | j } |j| | } | | jf|vs2|| } | j| j||}|sX|d}| j| j | j|} | j| _ || _|j| t||| |S)N)rrr)rZrrrr all_tokensr0getrr!rsoriginalappendr_)rrirjrZrrrrcorrected_tokens corrected_qtokenfnameanamecrr s rrz"SimpleQueryCorrector.correct_query.s __ ,,,,,,  \\^ 3EOOEKKu-Euzz"g-u%yyFGyLq'C#."5"5eoo6;jj##GK&+ZZEN!$EJ$++E2+ 3.!Wk3CDDr)Nrr&)r'r(r)r*r2rrrrrr s2)ErrN)r*bisectrheapqrrwhooshr whoosh.compatrrrVr r,r>rXr_r{rrrrrsu8'+ ."."bi8"I"JY.;A;A@V6JE>JEr