h~.,SSKrSSKrSSKrSSKJr SSKJrJrJrJ r J r J r J r J r SSKJr SSKJr SSKJrJr SSKJr SS KJrJr SS KJr SS KJrJr SS KJ r SS KJ!r!J"r"J#r# SSK$J%r% SSK&J'r' S\ \ S\\(\44Sjr)Sr*"SS\'5r+Sr,g)N)Path)AnyCallableDictIterableListOptionalTupleUnion)Model)util)ErrorsWarnings)Language)Lookups load_lookups)Scorer)DocToken)Example)SimpleFrozenListloggerregistry)Vocab)Pipeexamplesreturnc 2[R"US40UD6$)Nlemma)rscore_token_attr)rkwargss S/home/james-whalen/.local/lib/python3.13/site-packages/spacy/pipeline/lemmatizer.pylemmatizer_scorer%s  " "8W ? ??c[$N)r%r&r$make_lemmatizer_scorerr*s r&c*\rSrSrSr\S\S\\\\\44Sj5r S'SS\ S.S \ S \ \ S \S\S \S \ \SS4Sjjjr\S5rS\S\4SjrS(SSS.S\ \/\\4S\ \S\ \4Sjjjr\R64S\SS4SjjrS\S\\4SjrS\S\\4SjrS\S\4Sjr \!"5S.S\"\\#4S \\4S!jjr$\!"5S.S\"\\#4S \\SS4S"jjr%\!"5S.S \\S\&4S#jjr'\!"5S.S$\&S \\SS4S%jjr(S&r)g)) Lemmatizerz The Lemmatizer supports simple part-of-speech-sensitive suffix rules and lookup tables. DOCS: https://spacy.io/api/lemmatizer moderc:US:XaS//4$US:XaS/SS/4$//4$)zReturns the lookups configuration settings for a given mode for use in Lemmatizer.load_lookups. mode (str): The lemmatizer mode. RETURNS (Tuple[List[str], List[str]]): The required and optional lookup tables for this mode. lookup lemma_lookuprule lemma_rules lemma_exc lemma_indexr))clsr.s r$get_lookups_configLemmatizer.get_lookups_config%s< 8 #$b) ) V^"Ok=%AB BBxr&r0F)r. overwritescorervocabmodelnamer9r:NcXlX lX0lX@l[ 5UlXPlSUlURS:XaURUl OwURS:XaURUl OUURS3n[X5(d&[[RR!US95e[#X5Ul 0UlX`lg)aInitialize a Lemmatizer. vocab (Vocab): The vocab. model (Model): A model (not yet implemented). name (str): The component name. Defaults to "lemmatizer". mode (str): The lemmatizer mode: "lookup", "rule". Defaults to "lookup". overwrite (bool): Whether to overwrite existing lemmas. Defaults to `False`. scorer (Optional[Callable]): The scoring method. Defaults to Scorer.score_token_attr for the attribute "lemma". DOCS: https://spacy.io/api/lemmatizer#init Fr0r2 _lemmatize)r.N)r;r<r=_moderlookupsr9 _validatedr.lookup_lemmatize lemmatizerule_lemmatizehasattr ValueErrorrE1003formatgetattrcacher:)selfr;r<r=r.r9r: mode_attrs r$__init__Lemmatizer.__init__4s.    y " 99 !22DN YY& !00DN99+Z0I4++ !4!4$!4!?@@$T5DN  r&cUR$r()r@)rLs r$r.Lemmatizer.mode^s zzr&doccjUR(dUR[R5 UR 5nUH?nUR (dUR S:XdM&URU5SUlMA U$![anU"URX/U5 SnAgSnAff=f)zApply the lemmatizer to one document. doc (Doc): The Doc to process. RETURNS (Doc): The processed Doc. DOCS: https://spacy.io/api/lemmatizer#call rN) rB_validate_tablesrE1004get_error_handlerr9r!rDlemma_ Exceptionr=)rLrR error_handlertokenes r$__call__Lemmatizer.__call__bs  ! !&,, /..0  5>>U[[A%5#'>>%#8#;ELJ 5 $))T5! 4 4 5s$B *B B2B--B2)nlprA get_examplesr^rAcURUR5upEUc[R"S5 [ UR R US9n[ UR R USS9nURH#nURXvRU55 M% X0l UR[R5 g)aInitialize the lemmatizer and load in data. get_examples (Callable[[], Iterable[Example]]): Function that returns a representative sample of gold-standard Example objects. nlp (Language): The current nlp object the component is part of. lookups (Lookups): The lookups object containing the (optional) tables such as "lemma_rules", "lemma_index", "lemma_exc" and "lemma_lookup". Defaults to None. Nz2Lemmatizer: loading tables from spacy-lookups-data)langtablesF)rarbstrict)r7r.rdebugrr;rarb set_table get_tablerArTrrU)rLr_r^rArequired_tablesoptional_tablesoptional_lookupstables r$ initializeLemmatizer.initializeus ,0+B+B499+M( ? LLM N" PG+ZZ___U  *00!!%)C)CE)JK1  fll+r& error_messagec URUR5up#UHJnX@R;dM[UR URUURR S95e SUlg)z8Check that the lookups are correct for the current mode.)r.rbfoundTN)r7r.rArGrIrbrB)rLrmrgrhrjs r$rTLemmatizer._validate_tablessm+/+B+B499+M($ELL( !((!YY."ll11)%r&rZcURRS05nURURUR5n[ U[ 5(aU/nU$)zLemmatize using a lookup-based approach. token (Token): The token to lemmatize. RETURNS (list): The available lemmas for the string. DOCS: https://spacy.io/api/lemmatizer#lookup_lemmatize r1)rArfgettext isinstancestr)rLrZ lookup_tableresults r$rCLemmatizer.lookup_lemmatizesM||--nbA !!%**ejj9 fc " "XF r&cURURURR4nX R;aURU$UR nUR R5nUS;a;US:Xa$[R"[R5 UR5/$URU5(aUR5/$URRS05nURRS05nURRS05n[UR!U5UR!U5UR!U545(dUS:XaU/$UR5/$UR!U05nUR!U05n UR!U05n Un UR5n/n /n U HupUR#U5(dMUS[%U5[%U5- U-nU(dMCUU;dUR'5(dU R)U5 MqU R)U5 M [+[,R/U 55n U R!U/5HnUU ;dM U R1SU5 M U (dU R3U 5 U (dU R)U 5 XRU'U $) zLemmatize using a rule-based approach. token (Token): The token to lemmatize. RETURNS (list): The available lemmas for the string. DOCS: https://spacy.io/api/lemmatizer#rule_lemmatize )eolspacerzr5r4r3propnNr)orthposmorphkeyrKrspos_lowerwarningswarnrW108 is_base_formrArfanyrrendswithlenisalphaappendlistdictfromkeysinsertextend)rLrZ cache_keystringuniv_pos index_table exc_table rules_tableindex exceptionsrulesorigforms oov_formsoldnewforms r$rELemmatizer.rule_lemmatizescZZEKKOO<  "::i( (::##% + +2~ hmm,LLN# #   U # #LLN# #ll,,]B? LL**;; ll,,]B? ) h')   7"x ''"-]]8R0 "- HCs##6F c#h 67#=U]$,,..LL&$$T*T]]5)* NN62.D5  Q%/ LL # LL  % 9 r&cg)zCheck whether the token is a base form that does not need further analysis for lemmatization. token (Token): The token. RETURNS (bool): Whether the token is a base form. DOCS: https://spacy.io/api/lemmatizer#is_base_form Fr))rLrZs r$rLemmatizer.is_base_formsr&excludepathrc`^^0nUU4SjUS'U4SjUS'[R"XT5 g)zSerialize the pipe to disk. path (str / Path): Path to a directory. exclude (Iterable[str]): String names of serialization fields to exclude. DOCS: https://spacy.io/api/lemmatizer#to_disk c8>TRRUTS9$Nr)r;to_diskprrLs r$$Lemmatizer.to_disk..stzz'9'9!W'9'Mr&r;c:>TRRU5$r()rArrrLs r$rrs)=)=a)@r&rAN)rr)rLrr serializes` ` r$rLemmatizer.to_disks, M '@ ) Tg.r&c^^0nUU4SjUS'U4SjUS'[R"XT5 TR5 T$)a Load the pipe from disk. Modifies the object in place and returns it. path (str / Path): Path to a directory. exclude (Iterable[str]): String names of serialization fields to exclude. RETURNS (Lemmatizer): The modified Lemmatizer object. DOCS: https://spacy.io/api/lemmatizer#from_disk c8>TRRUTS9$r)r; from_diskrs r$r&Lemmatizer.from_disk..s)=)=a)=)Qr&r;c:>TRRU5$r()rArrs r$rrs4<<+A+A!+Dr&rA)rrrT)rLrr deserializes` ` r$rLemmatizer.from_disk s=8: Q G!D I t'2  r&c~^^0nUU4SjUS'TRRUS'[R"UT5$)zSerialize the pipe to a bytestring. exclude (Iterable[str]): String names of serialization fields to exclude. RETURNS (bytes): The serialized object. DOCS: https://spacy.io/api/lemmatizer#to_bytes c6>TRRTS9$r)r;to_bytes)rrLsr$r%Lemmatizer.to_bytes..%sTZZ%8%8%8%Ir&r;rA)rArr)rLrrs`` r$rLemmatizer.to_bytess9 I '#||44 )}}Y00r& bytes_datac^^0nUU4SjUS'U4SjUS'[R"XT5 TR5 T$)zLoad the pipe from a bytestring. bytes_data (bytes): The serialized pipe. exclude (Iterable[str]): String names of serialization fields to exclude. RETURNS (Lemmatizer): The loaded Lemmatizer. DOCS: https://spacy.io/api/lemmatizer#from_bytes c8>TRRUTS9$r)r; from_bytes)brrLs r$r'Lemmatizer.from_bytes..5s)>)>q')>)Rr&r;c:>TRRU5$r()rAr)rrLs r$rr6s4<<+B+B1+Er&rA)rrrT)rLrrrs` ` r$rLemmatizer.from_bytes)s=8: R G!E I  9  r&) r@rBrKrDrAr<r=r9r:r;) lemmatizerr()*__name__ __module__ __qualname____firstlineno____doc__ classmethodrur rr7r%rr r boolrrNpropertyr.rr\rrrrrkrE912rTrrCrErrr rrrbytesrr__static_attributes__r)r&r$r,r,s- c eDItCy4H.I  $! ( %5((( (  (("( (T5C5C5*CG,#'%) ,xHW,=(=>?,h  , '" ,85;KK c D  e S AEAd3iAF % D CSBT /#t)$ /2:3- / CSBT#t)$2:3- $4D3E 18C= 1% 1>N=O-5c] r&r,c|US:Xa"[R"S5nUR$[S[SU35e)Nmake_lemmatizerzspacy.pipeline.factorieszmodule z has no attribute ) importlib import_modulerAttributeErrorr)r=modules r$ __getattr__r=sA   (()CD%%% 78*,>tfE FFr&)-rsysrpathlibrtypingrrrrrr r r thinc.apir rzrerrorsrrlanguagerrArrr:rtokensrrtrainingrrrrr;rpiperrur%r*r,rr)r&r$rs{ NNN%+55@x0@tCH~@\\@ Gr&