Edit: romanian_stemmer.py
# Generated by Snowball 2.2.0 - https://snowballstem.org/ from .basestemmer import BaseStemmer from .among import Among class RomanianStemmer(BaseStemmer): ''' This class implements the stemming algorithm defined by a snowball script. Generated by Snowball 2.2.0 - https://snowballstem.org/ ''' a_0 = [ Among(u"", -1, 3), Among(u"I", 0, 1), Among(u"U", 0, 2) ] a_1 = [ Among(u"ea", -1, 3), Among(u"a\u0163ia", -1, 7), Among(u"aua", -1, 2), Among(u"iua", -1, 4), Among(u"a\u0163ie", -1, 7), Among(u"ele", -1, 3), Among(u"ile", -1, 5), Among(u"iile", 6, 4), Among(u"iei", -1, 4), Among(u"atei", -1, 6), Among(u"ii", -1, 4), Among(u"ului", -1, 1), Among(u"ul", -1, 1), Among(u"elor", -1, 3), Among(u"ilor", -1, 4), Among(u"iilor", 14, 4) ] a_2 = [ Among(u"icala", -1, 4), Among(u"iciva", -1, 4), Among(u"ativa", -1, 5), Among(u"itiva", -1, 6), Among(u"icale", -1, 4), Among(u"a\u0163iune", -1, 5), Among(u"i\u0163iune", -1, 6), Among(u"atoare", -1, 5), Among(u"itoare", -1, 6), Among(u"\u0103toare", -1, 5), Among(u"icitate", -1, 4), Among(u"abilitate", -1, 1), Among(u"ibilitate", -1, 2), Among(u"ivitate", -1, 3), Among(u"icive", -1, 4), Among(u"ative", -1, 5), Among(u"itive", -1, 6), Among(u"icali", -1, 4), Among(u"atori", -1, 5), Among(u"icatori", 18, 4), Among(u"itori", -1, 6), Among(u"\u0103tori", -1, 5), Among(u"icitati", -1, 4), Among(u"abilitati", -1, 1), Among(u"ivitati", -1, 3), Among(u"icivi", -1, 4), Among(u"ativi", -1, 5), Among(u"itivi", -1, 6), Among(u"icit\u0103i", -1, 4), Among(u"abilit\u0103i", -1, 1), Among(u"ivit\u0103i", -1, 3), Among(u"icit\u0103\u0163i", -1, 4), Among(u"abilit\u0103\u0163i", -1, 1), Among(u"ivit\u0103\u0163i", -1, 3), Among(u"ical", -1, 4), Among(u"ator", -1, 5), Among(u"icator", 35, 4), Among(u"itor", -1, 6), Among(u"\u0103tor", -1, 5), Among(u"iciv", -1, 4), Among(u"ativ", -1, 5), Among(u"itiv", -1, 6), Among(u"ical\u0103", -1, 4), Among(u"iciv\u0103", -1, 4), Among(u"ativ\u0103", -1, 5), Among(u"itiv\u0103", -1, 6) ] a_3 = [ Among(u"ica", -1, 1), Among(u"abila", -1, 1), Among(u"ibila", -1, 1), Among(u"oasa", -1, 1), Among(u"ata", -1, 1), Among(u"ita", -1, 1), Among(u"anta", -1, 1), Among(u"ista", -1, 3), Among(u"uta", -1, 1), Among(u"iva", -1, 1), Among(u"ic", -1, 1), Among(u"ice", -1, 1), Among(u"abile", -1, 1), Among(u"ibile", -1, 1), Among(u"isme", -1, 3), Among(u"iune", -1, 2), Among(u"oase", -1, 1), Among(u"ate", -1, 1), Among(u"itate", 17, 1), Among(u"ite", -1, 1), Among(u"ante", -1, 1), Among(u"iste", -1, 3), Among(u"ute", -1, 1), Among(u"ive", -1, 1), Among(u"ici", -1, 1), Among(u"abili", -1, 1), Among(u"ibili", -1, 1), Among(u"iuni", -1, 2), Among(u"atori", -1, 1), Among(u"osi", -1, 1), Among(u"ati", -1, 1), Among(u"itati", 30, 1), Among(u"iti", -1, 1), Among(u"anti", -1, 1), Among(u"isti", -1, 3), Among(u"uti", -1, 1), Among(u"i\u015Fti", -1, 3), Among(u"ivi", -1, 1), Among(u"it\u0103i", -1, 1), Among(u"o\u015Fi", -1, 1), Among(u"it\u0103\u0163i", -1, 1), Among(u"abil", -1, 1), Among(u"ibil", -1, 1), Among(u"ism", -1, 3), Among(u"ator", -1, 1), Among(u"os", -1, 1), Among(u"at", -1, 1), Among(u"it", -1, 1), Among(u"ant", -1, 1), Among(u"ist", -1, 3), Among(u"ut", -1, 1), Among(u"iv", -1, 1), Among(u"ic\u0103", -1, 1), Among(u"abil\u0103", -1, 1), Among(u"ibil\u0103", -1, 1), Among(u"oas\u0103", -1, 1), Among(u"at\u0103", -1, 1), Among(u"it\u0103", -1, 1), Among(u"ant\u0103", -1, 1), Among(u"ist\u0103", -1, 3), Among(u"ut\u0103", -1, 1), Among(u"iv\u0103", -1, 1) ] a_4 = [ Among(u"ea", -1, 1), Among(u"ia", -1, 1), Among(u"esc", -1, 1), Among(u"\u0103sc", -1, 1), Among(u"ind", -1, 1), Among(u"\u00E2nd", -1, 1), Among(u"are", -1, 1), Among(u"ere", -1, 1), Among(u"ire", -1, 1), Among(u"\u00E2re", -1, 1), Among(u"se", -1, 2), Among(u"ase", 10, 1), Among(u"sese", 10, 2), Among(u"ise", 10, 1), Among(u"use", 10, 1), Among(u"\u00E2se", 10, 1), Among(u"e\u015Fte", -1, 1), Among(u"\u0103\u015Fte", -1, 1), Among(u"eze", -1, 1), Among(u"ai", -1, 1), Among(u"eai", 19, 1), Among(u"iai", 19, 1), Among(u"sei", -1, 2), Among(u"e\u015Fti", -1, 1), Among(u"\u0103\u015Fti", -1, 1), Among(u"ui", -1, 1), Among(u"ezi", -1, 1), Among(u"\u00E2i", -1, 1), Among(u"a\u015Fi", -1, 1), Among(u"se\u015Fi", -1, 2), Among(u"ase\u015Fi", 29, 1), Among(u"sese\u015Fi", 29, 2), Among(u"ise\u015Fi", 29, 1), Among(u"use\u015Fi", 29, 1), Among(u"\u00E2se\u015Fi", 29, 1), Among(u"i\u015Fi", -1, 1), Among(u"u\u015Fi", -1, 1), Among(u"\u00E2\u015Fi", -1, 1), Among(u"a\u0163i", -1, 2), Among(u"ea\u0163i", 38, 1), Among(u"ia\u0163i", 38, 1), Among(u"e\u0163i", -1, 2), Among(u"i\u0163i", -1, 2), Among(u"\u00E2\u0163i", -1, 2), Among(u"ar\u0103\u0163i", -1, 1), Among(u"ser\u0103\u0163i", -1, 2), Among(u"aser\u0103\u0163i", 45, 1), Among(u"seser\u0103\u0163i", 45, 2), Among(u"iser\u0103\u0163i", 45, 1), Among(u"user\u0103\u0163i", 45, 1), Among(u"\u00E2ser\u0103\u0163i", 45, 1), Among(u"ir\u0103\u0163i", -1, 1), Among(u"ur\u0103\u0163i", -1, 1), Among(u"\u00E2r\u0103\u0163i", -1, 1), Among(u"am", -1, 1), Among(u"eam", 54, 1), Among(u"iam", 54, 1), Among(u"em", -1, 2), Among(u"asem", 57, 1), Among(u"sesem", 57, 2), Among(u"isem", 57, 1), Among(u"usem", 57, 1), Among(u"\u00E2sem", 57, 1), Among(u"im", -1, 2), Among(u"\u00E2m", -1, 2), Among(u"\u0103m", -1, 2), Among(u"ar\u0103m", 65, 1), Among(u"ser\u0103m", 65, 2), Among(u"aser\u0103m", 67, 1), Among(u"seser\u0103m", 67, 2), Among(u"iser\u0103m", 67, 1), Among(u"user\u0103m", 67, 1), Among(u"\u00E2ser\u0103m", 67, 1), Among(u"ir\u0103m", 65, 1), Among(u"ur\u0103m", 65, 1), Among(u"\u00E2r\u0103m", 65, 1), Among(u"au", -1, 1), Among(u"eau", 76, 1), Among(u"iau", 76, 1), Among(u"indu", -1, 1), Among(u"\u00E2ndu", -1, 1), Among(u"ez", -1, 1), Among(u"easc\u0103", -1, 1), Among(u"ar\u0103", -1, 1), Among(u"ser\u0103", -1, 2), Among(u"aser\u0103", 84, 1), Among(u"seser\u0103", 84, 2), Among(u"iser\u0103", 84, 1), Among(u"user\u0103", 84, 1), Among(u"\u00E2ser\u0103", 84, 1), Among(u"ir\u0103", -1, 1), Among(u"ur\u0103", -1, 1), Among(u"\u00E2r\u0103", -1, 1), Among(u"eaz\u0103", -1, 1) ] a_5 = [ Among(u"a", -1, 1), Among(u"e", -1, 1), Among(u"ie", 1, 1), Among(u"i", -1, 1), Among(u"\u0103", -1, 1) ] g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 32, 0, 0, 4] B_standard_suffix_removed = False I_p2 = 0 I_p1 = 0 I_pV = 0 def __r_prelude(self): while True: v_1 = self.cursor try: try: while True: v_2 = self.cursor try: if not self.in_grouping(RomanianStemmer.g_v, 97, 259): raise lab2() self.bra = self.cursor try: v_3 = self.cursor try: if not self.eq_s(u"u"): raise lab4() self.ket = self.cursor if not self.in_grouping(RomanianStemmer.g_v, 97, 259): raise lab4() if not self.slice_from(u"U"): return False raise lab3() except lab4: pass self.cursor = v_3 if not self.eq_s(u"i"): raise lab2() self.ket = self.cursor if not self.in_grouping(RomanianStemmer.g_v, 97, 259): raise lab2() if not self.slice_from(u"I"): return False except lab3: pass self.cursor = v_2 raise lab1() except lab2: pass self.cursor = v_2 if self.cursor >= self.limit: raise lab0() self.cursor += 1 except lab1: pass continue except lab0: pass self.cursor = v_1 break return True def __r_mark_regions(self): self.I_pV = self.limit self.I_p1 = self.limit self.I_p2 = self.limit v_1 = self.cursor try: try: v_2 = self.cursor try: if not self.in_grouping(RomanianStemmer.g_v, 97, 259): raise lab2() try: v_3 = self.cursor try: if not self.out_grouping(RomanianStemmer.g_v, 97, 259): raise lab4() if not self.go_out_grouping(RomanianStemmer.g_v, 97, 259): raise lab4() self.cursor += 1 raise lab3() except lab4: pass self.cursor = v_3 if not self.in_grouping(RomanianStemmer.g_v, 97, 259): raise lab2() if not self.go_in_grouping(RomanianStemmer.g_v, 97, 259): raise lab2() self.cursor += 1 except lab3: pass raise lab1() except lab2: pass self.cursor = v_2 if not self.out_grouping(RomanianStemmer.g_v, 97, 259): raise lab0() try: v_4 = self.cursor try: if not self.out_grouping(RomanianStemmer.g_v, 97, 259): raise lab6() if not self.go_out_grouping(RomanianStemmer.g_v, 97, 259): raise lab6() self.cursor += 1 raise lab5() except lab6: pass self.cursor = v_4 if not self.in_grouping(RomanianStemmer.g_v, 97, 259): raise lab0() if self.cursor >= self.limit: raise lab0() self.cursor += 1 except lab5: pass except lab1: pass self.I_pV = self.cursor except lab0: pass self.cursor = v_1 v_5 = self.cursor try: if not self.go_out_grouping(RomanianStemmer.g_v, 97, 259): raise lab7() self.cursor += 1 if not self.go_in_grouping(RomanianStemmer.g_v, 97, 259): raise lab7() self.cursor += 1 self.I_p1 = self.cursor if not self.go_out_grouping(RomanianStemmer.g_v, 97, 259): raise lab7() self.cursor += 1 if not self.go_in_grouping(RomanianStemmer.g_v, 97, 259): raise lab7() self.cursor += 1 self.I_p2 = self.cursor except lab7: pass self.cursor = v_5 return True def __r_postlude(self): while True: v_1 = self.cursor try: self.bra = self.cursor among_var = self.find_among(RomanianStemmer.a_0) if among_var == 0: raise lab0() self.ket = self.cursor if among_var == 1: if not self.slice_from(u"i"): return False elif among_var == 2: if not self.slice_from(u"u"): return False else: if self.cursor >= self.limit: raise lab0() self.cursor += 1 continue except lab0: pass self.cursor = v_1 break return True def __r_RV(self): if not self.I_pV <= self.cursor: return False return True def __r_R1(self): if not self.I_p1 <= self.cursor: return False return True def __r_R2(self): if not self.I_p2 <= self.cursor: return False return True def __r_step_0(self): self.ket = self.cursor among_var = self.find_among_b(RomanianStemmer.a_1) if among_var == 0: return False self.bra = self.cursor if not self.__r_R1(): return False if among_var == 1: if not self.slice_del(): return False elif among_var == 2: if not self.slice_from(u"a"): return False elif among_var == 3: if not self.slice_from(u"e"): return False elif among_var == 4: if not self.slice_from(u"i"): return False elif among_var == 5: v_1 = self.limit - self.cursor try: if not self.eq_s_b(u"ab"): raise lab0() return False except lab0: pass self.cursor = self.limit - v_1 if not self.slice_from(u"i"): return False elif among_var == 6: if not self.slice_from(u"at"): return False else: if not self.slice_from(u"a\u0163i"): return False return True def __r_combo_suffix(self): v_1 = self.limit - self.cursor self.ket = self.cursor among_var = self.find_among_b(RomanianStemmer.a_2) if among_var == 0: return False self.bra = self.cursor if not self.__r_R1(): return False if among_var == 1: if not self.slice_from(u"abil"): return False elif among_var == 2: if not self.slice_from(u"ibil"): return False elif among_var == 3: if not self.slice_from(u"iv"): return False elif among_var == 4: if not self.slice_from(u"ic"): return False elif among_var == 5: if not self.slice_from(u"at"): return False else: if not self.slice_from(u"it"): return False self.B_standard_suffix_removed = True self.cursor = self.limit - v_1 return True def __r_standard_suffix(self): self.B_standard_suffix_removed = False while True: v_1 = self.limit - self.cursor try: if not self.__r_combo_suffix(): raise lab0() continue except lab0: pass self.cursor = self.limit - v_1 break self.ket = self.cursor among_var = self.find_among_b(RomanianStemmer.a_3) if among_var == 0: return False self.bra = self.cursor if not self.__r_R2(): return False if among_var == 1: if not self.slice_del(): return False elif among_var == 2: if not self.eq_s_b(u"\u0163"): return False self.bra = self.cursor if not self.slice_from(u"t"): return False else: if not self.slice_from(u"ist"): return False self.B_standard_suffix_removed = True return True def __r_verb_suffix(self): if self.cursor < self.I_pV: return False v_2 = self.limit_backward self.limit_backward = self.I_pV self.ket = self.cursor among_var = self.find_among_b(RomanianStemmer.a_4) if among_var == 0: self.limit_backward = v_2 return False self.bra = self.cursor if among_var == 1: try: v_3 = self.limit - self.cursor try: if not self.out_grouping_b(RomanianStemmer.g_v, 97, 259): raise lab1() raise lab0() except lab1: pass self.cursor = self.limit - v_3 if not self.eq_s_b(u"u"): self.limit_backward = v_2 return False except lab0: pass if not self.slice_del(): return False else: if not self.slice_del(): return False self.limit_backward = v_2 return True def __r_vowel_suffix(self): self.ket = self.cursor if self.find_among_b(RomanianStemmer.a_5) == 0: return False self.bra = self.cursor if not self.__r_RV(): return False if not self.slice_del(): return False return True def _stem(self): v_1 = self.cursor self.__r_prelude() self.cursor = v_1 self.__r_mark_regions() self.limit_backward = self.cursor self.cursor = self.limit v_3 = self.limit - self.cursor self.__r_step_0() self.cursor = self.limit - v_3 v_4 = self.limit - self.cursor self.__r_standard_suffix() self.cursor = self.limit - v_4 v_5 = self.limit - self.cursor try: try: v_6 = self.limit - self.cursor try: if not self.B_standard_suffix_removed: raise lab2() raise lab1() except lab2: pass self.cursor = self.limit - v_6 if not self.__r_verb_suffix(): raise lab0() except lab1: pass except lab0: pass self.cursor = self.limit - v_5 v_7 = self.limit - self.cursor self.__r_vowel_suffix() self.cursor = self.limit - v_7 self.cursor = self.limit_backward v_8 = self.cursor self.__r_postlude() self.cursor = v_8 return True class lab0(BaseException): pass class lab1(BaseException): pass class lab2(BaseException): pass class lab3(BaseException): pass class lab4(BaseException): pass class lab5(BaseException): pass class lab6(BaseException): pass class lab7(BaseException): pass
Cancel