ó ù`]c@s\ddlmZddlZddlmZddlmZedefd„ƒYƒZdS(iÿÿÿÿ(tunicode_literalsN(tStemmerI(tpython_2_unicode_compatiblet RegexpStemmercBs,eZdZdd„Zd„Zd„ZRS(uä A stemmer that uses regular expressions to identify morphological affixes. Any substrings that match the regular expressions will be removed. >>> from nltk.stem import RegexpStemmer >>> st = RegexpStemmer('ing$|s$|e$|able$', min=4) >>> st.stem('cars') 'car' >>> st.stem('mass') 'mas' >>> st.stem('was') 'was' >>> st.stem('bee') 'bee' >>> st.stem('compute') 'comput' >>> st.stem('advisable') 'advis' :type regexp: str or regexp :param regexp: The regular expression that should be used to identify morphological affixes. :type min: int :param min: The minimum length of string to stem icCs7t|dƒs!tj|ƒ}n||_||_dS(Nupattern(thasattrtretcompilet_regexpt_min(tselftregexptmin((s/lib/python2.7/site-packages/nltk/stem/regexp.pyt__init__-s cCs0t|ƒ|jkr|S|jjd|ƒSdS(Nu(tlenRRtsub(R tword((s/lib/python2.7/site-packages/nltk/stem/regexp.pytstem4scCsdj|jjƒS(Nu(tformatRtpattern(R ((s/lib/python2.7/site-packages/nltk/stem/regexp.pyt__repr__:s(t__name__t __module__t__doc__R RR(((s/lib/python2.7/site-packages/nltk/stem/regexp.pyRs  (t __future__RRt nltk.stem.apiRt nltk.compatRR(((s/lib/python2.7/site-packages/nltk/stem/regexp.pyt s