# Generated from swedish.sbl by Snowball 3.1.1 - https://snowballstem.org/ from .basestemmer import BaseStemmer from .among import Among class SwedishStemmer(BaseStemmer): ''' This class implements the stemming algorithm defined by a snowball script. Generated from swedish.sbl by Snowball 3.1.1 - https://snowballstem.org/ ''' g_v = {"a", "e", "i", "o", "u", "y", "ä", "å", "ö"} g_s_ending = {"b", "c", "d", "f", "g", "h", "j", "k", "l", "m", "n", "o", "p", "r", "t", "v", "y"} g_ost_ending = {"i", "k", "l", "n", "p", "r", "t", "u", "v"} I_p1 = 0 def __r_mark_regions(self): self.I_p1 = self.limit v_1 = self.cursor if self.cursor + 3 > self.limit: return False self.cursor += 3 I_x = self.cursor self.cursor = v_1 if not self.go_out_grouping(SwedishStemmer.g_v): return False self.cursor += 1 if not self.go_in_grouping(SwedishStemmer.g_v): return False self.cursor += 1 self.I_p1 = self.cursor try: if self.I_p1 >= I_x: raise lab0() self.I_p1 = I_x except lab0: pass return True def __r_et_condition(self): v_1 = self.limit - self.cursor if not self.out_grouping_b(SwedishStemmer.g_v): return False if not self.in_grouping_b(SwedishStemmer.g_v): return False if self.cursor <= self.limit_backward: return False self.cursor = self.limit - v_1 v_2 = self.limit - self.cursor try: if self.find_among_b(SwedishStemmer.a_0) == 0: raise lab0() return False except lab0: pass self.cursor = self.limit - v_2 return True def __r_main_suffix(self): if self.cursor < self.I_p1: return False v_2 = self.limit_backward self.limit_backward = self.I_p1 self.ket = self.cursor among_var = self.find_among_b(SwedishStemmer.a_1) if among_var == 0: self.limit_backward = v_2 return False self.bra = self.cursor self.limit_backward = v_2 if among_var == 1: self.slice_del() elif among_var == 2: while True: v_3 = self.limit - self.cursor try: if not self.eq_s_b("et"): raise lab0() if not self.__r_et_condition(): raise lab0() self.bra = self.cursor break except lab0: pass self.cursor = self.limit - v_3 if not self.in_grouping_b(SwedishStemmer.g_s_ending): return False break self.slice_del() else: if not self.__r_et_condition(): return False self.slice_del() return True def __r_consonant_pair(self): if self.cursor < self.I_p1: return False v_2 = self.limit_backward self.limit_backward = self.I_p1 v_3 = self.limit - self.cursor if self.find_among_b(SwedishStemmer.a_2) == 0: self.limit_backward = v_2 return False self.cursor = self.limit - v_3 self.ket = self.cursor if self.cursor <= self.limit_backward: self.limit_backward = v_2 return False self.cursor -= 1 self.bra = self.cursor self.slice_del() self.limit_backward = v_2 return True def __r_other_suffix(self): if self.cursor < self.I_p1: return False v_2 = self.limit_backward self.limit_backward = self.I_p1 self.ket = self.cursor among_var = self.find_among_b(SwedishStemmer.a_3) if among_var == 0: self.limit_backward = v_2 return False self.bra = self.cursor self.limit_backward = v_2 if among_var == 1: self.slice_del() elif among_var == 2: if not self.in_grouping_b(SwedishStemmer.g_ost_ending): return False self.slice_from("ös") else: self.slice_from("full") return True def _stem(self): v_1 = self.cursor self.__r_mark_regions() self.cursor = v_1 self.limit_backward = self.cursor self.cursor = self.limit v_2 = self.limit - self.cursor self.__r_main_suffix() self.cursor = self.limit - v_2 v_3 = self.limit - self.cursor self.__r_consonant_pair() self.cursor = self.limit - v_3 v_4 = self.limit - self.cursor self.__r_other_suffix() self.cursor = self.limit - v_4 self.cursor = self.limit_backward return True a_0 = [ Among("fab", -1, -1), Among("h", -1, -1), Among("pak", -1, -1), Among("rak", -1, -1), Among("stak", -1, -1), Among("kom", -1, -1), Among("iet", -1, -1), Among("cit", -1, -1), Among("dit", -1, -1), Among("alit", -1, -1), Among("ilit", -1, -1), Among("mit", -1, -1), Among("nit", -1, -1), Among("pit", -1, -1), Among("rit", -1, -1), Among("sit", -1, -1), Among("tit", -1, -1), Among("uit", -1, -1), Among("ivit", -1, -1), Among("kvit", -1, -1), Among("xit", -1, -1) ] a_1 = [ Among("a", -1, 1), Among("arna", 0, 1), Among("erna", 0, 1), Among("heterna", 2, 1), Among("orna", 0, 1), Among("ad", -1, 1), Among("e", -1, 1), Among("ade", 6, 1), Among("ande", 6, 1), Among("arne", 6, 1), Among("are", 6, 1), Among("aste", 6, 1), Among("en", -1, 1), Among("anden", 12, 1), Among("aren", 12, 1), Among("heten", 12, 1), Among("ern", -1, 1), Among("ar", -1, 1), Among("er", -1, 1), Among("heter", 18, 1), Among("or", -1, 1), Among("s", -1, 2), Among("as", 21, 1), Among("arnas", 22, 1), Among("ernas", 22, 1), Among("ornas", 22, 1), Among("es", 21, 1), Among("ades", 26, 1), Among("andes", 26, 1), Among("ens", 21, 1), Among("arens", 29, 1), Among("hetens", 29, 1), Among("erns", 21, 1), Among("at", -1, 1), Among("et", -1, 3), Among("andet", 34, 1), Among("het", 34, 1), Among("ast", -1, 1) ] a_2 = [ Among("dd", -1, -1), Among("gd", -1, -1), Among("nn", -1, -1), Among("dt", -1, -1), Among("gt", -1, -1), Among("kt", -1, -1), Among("tt", -1, -1) ] a_3 = [ Among("ig", -1, 1), Among("lig", 0, 1), Among("els", -1, 1), Among("fullt", -1, 3), Among("öst", -1, 2) ] class lab0(BaseException): pass