JL i2ddlmZddlmZGddeZy))load)StemmerIc(eZdZdZdZdZdZdZy) RSLPStemmerug A stemmer for Portuguese. >>> from nltk.stem import RSLPStemmer >>> st = RSLPStemmer() >>> # opening lines of Erico Verissimo's "Música ao Longe" >>> text = ''' ... Clarissa risca com giz no quadro-negro a paisagem que os alunos ... devem copiar . Uma casinha de porta e janela , em cima duma ... coxilha .''' >>> for token in text.split(): # doctest: +NORMALIZE_WHITESPACE ... print(st.stem(token)) clariss risc com giz no quadro-negr a pais que os alun dev copi . uma cas de port e janel , em cim dum coxilh . c^g|_|jj|jd|jj|jd|jj|jd|jj|jd|jj|jd|jj|jd|jj|jdy)Nzstep0.ptzstep1.ptzstep2.ptzstep3.ptzstep4.ptzstep5.ptzstep6.pt)_modelappend read_rule)selfs T/mnt/ssd/data/python-lab/Trading/venv/lib/python3.12/site-packages/nltk/stem/rslp.py__init__zRSLPStemmer.__init__5s  4>>*56 4>>*56 4>>*56 4>>*56 4>>*56 4>>*56 4>>*56c ~td|zdjd}|jd}|Dcgc] }|dk7s | }}|Dcgc] }|ddk7s |}}|Dcgc]}|jd d }}g}|D]}g}|jd }|j |dd d |j t |d |j |d d d |j |djdDcgc]}|d d  c}|j ||Scc}wcc}wcc}wcc}w)Nznltk:stemmers/rslp/raw)formatutf8 r#z  ,)rdecodesplitreplacer int)r filenameruleslineslineruletokenstokens r r zRSLPStemmer.read_rule@sF*X5eDKKFS D!"'6$42:66"':$47c>::9>>fd+>> DDZZ%F KKq !B ( KKF1I ' KKq !B ( KK&)//#2FGqG H LL # & 77:?$Hs# D+D+ D0D0"D5 D: c^|j}|ddk(r|j|d}|ddk(r|j|d}|j|d}|j|d}|}|j|d}||k(r+|}|j|d }||k(r|j|d }|S) Nrsrarrr)lower apply_rule)r word prev_words r stemzRSLPStemmer.stemaszz| 8s???4+D 8s???4+DtQ'tQ' tQ' 9 I??4+Dy tQ/ rc|j|}|D]H}t|d}|| d|dk(st|||dzk\s3||dvs;|d| |dz}|S|S)Nrrrr)rlen)r r/ rule_indexr!r$ suffix_lengths r r.zRSLPStemmer.apply_rules J' DQLM]NO$Q/t9 Q 7747*#Om^4tAw>   rN)__name__ __module__ __qualname____doc__r r r1r.rr rr$s 7B< rrN) nltk.datar nltk.stem.apirrr:rr r=s@"e(er