192 lines
5.3 KiB
Python
192 lines
5.3 KiB
Python
|
# Generated by Snowball 2.2.0 - https://snowballstem.org/
|
||
|
|
|
||
|
|
from .basestemmer import BaseStemmer
|
||
|
|
from .among import Among
|
||
|
|
|
||
|
|
|
||
|
|
class NorwegianStemmer(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"a", -1, 1),
|
||
|
|
Among(u"e", -1, 1),
|
||
|
|
Among(u"ede", 1, 1),
|
||
|
|
Among(u"ande", 1, 1),
|
||
|
|
Among(u"ende", 1, 1),
|
||
|
|
Among(u"ane", 1, 1),
|
||
|
|
Among(u"ene", 1, 1),
|
||
|
|
Among(u"hetene", 6, 1),
|
||
|
|
Among(u"erte", 1, 3),
|
||
|
|
Among(u"en", -1, 1),
|
||
|
|
Among(u"heten", 9, 1),
|
||
|
|
Among(u"ar", -1, 1),
|
||
|
|
Among(u"er", -1, 1),
|
||
|
|
Among(u"heter", 12, 1),
|
||
|
|
Among(u"s", -1, 2),
|
||
|
|
Among(u"as", 14, 1),
|
||
|
|
Among(u"es", 14, 1),
|
||
|
|
Among(u"edes", 16, 1),
|
||
|
|
Among(u"endes", 16, 1),
|
||
|
|
Among(u"enes", 16, 1),
|
||
|
|
Among(u"hetenes", 19, 1),
|
||
|
|
Among(u"ens", 14, 1),
|
||
|
|
Among(u"hetens", 21, 1),
|
||
|
|
Among(u"ers", 14, 1),
|
||
|
|
Among(u"ets", 14, 1),
|
||
|
|
Among(u"et", -1, 1),
|
||
|
|
Among(u"het", 25, 1),
|
||
|
|
Among(u"ert", -1, 3),
|
||
|
|
Among(u"ast", -1, 1)
|
||
|
|
]
|
||
|
|
|
||
|
|
a_1 = [
|
||
|
|
Among(u"dt", -1, -1),
|
||
|
|
Among(u"vt", -1, -1)
|
||
|
|
]
|
||
|
|
|
||
|
|
a_2 = [
|
||
|
|
Among(u"leg", -1, 1),
|
||
|
|
Among(u"eleg", 0, 1),
|
||
|
|
Among(u"ig", -1, 1),
|
||
|
|
Among(u"eig", 2, 1),
|
||
|
|
Among(u"lig", 2, 1),
|
||
|
|
Among(u"elig", 4, 1),
|
||
|
|
Among(u"els", -1, 1),
|
||
|
|
Among(u"lov", -1, 1),
|
||
|
|
Among(u"elov", 7, 1),
|
||
|
|
Among(u"slov", 7, 1),
|
||
|
|
Among(u"hetslov", 9, 1)
|
||
|
|
]
|
||
|
|
|
||
|
|
g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 48, 0, 128]
|
||
|
|
|
||
|
|
g_s_ending = [119, 125, 149, 1]
|
||
|
|
|
||
|
|
I_x = 0
|
||
|
|
I_p1 = 0
|
||
|
|
|
||
|
|
def __r_mark_regions(self):
|
||
|
|
self.I_p1 = self.limit
|
||
|
|
v_1 = self.cursor
|
||
|
|
c = self.cursor + 3
|
||
|
|
if c > self.limit:
|
||
|
|
return False
|
||
|
|
self.cursor = c
|
||
|
|
self.I_x = self.cursor
|
||
|
|
self.cursor = v_1
|
||
|
|
if not self.go_out_grouping(NorwegianStemmer.g_v, 97, 248):
|
||
|
|
return False
|
||
|
|
if not self.go_in_grouping(NorwegianStemmer.g_v, 97, 248):
|
||
|
|
return False
|
||
|
|
self.cursor += 1
|
||
|
|
self.I_p1 = self.cursor
|
||
|
|
try:
|
||
|
|
if not self.I_p1 < self.I_x:
|
||
|
|
raise lab0()
|
||
|
|
self.I_p1 = self.I_x
|
||
|
|
except lab0: pass
|
||
|
|
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(NorwegianStemmer.a_0)
|
||
|
|
if among_var == 0:
|
||
|
|
self.limit_backward = v_2
|
||
|
|
return False
|
||
|
|
self.bra = self.cursor
|
||
|
|
self.limit_backward = v_2
|
||
|
|
if among_var == 1:
|
||
|
|
if not self.slice_del():
|
||
|
|
return False
|
||
|
|
|
||
|
|
elif among_var == 2:
|
||
|
|
try:
|
||
|
|
v_3 = self.limit - self.cursor
|
||
|
|
try:
|
||
|
|
if not self.in_grouping_b(NorwegianStemmer.g_s_ending, 98, 122):
|
||
|
|
raise lab1()
|
||
|
|
raise lab0()
|
||
|
|
except lab1: pass
|
||
|
|
self.cursor = self.limit - v_3
|
||
|
|
if not self.eq_s_b(u"k"):
|
||
|
|
return False
|
||
|
|
if not self.out_grouping_b(NorwegianStemmer.g_v, 97, 248):
|
||
|
|
return False
|
||
|
|
except lab0: pass
|
||
|
|
if not self.slice_del():
|
||
|
|
return False
|
||
|
|
|
||
|
|
else:
|
||
|
|
if not self.slice_from(u"er"):
|
||
|
|
return False
|
||
|
|
return True
|
||
|
|
|
||
|
|
def __r_consonant_pair(self):
|
||
|
|
v_1 = self.limit - self.cursor
|
||
|
|
if self.cursor < self.I_p1:
|
||
|
|
return False
|
||
|
|
v_3 = self.limit_backward
|
||
|
|
self.limit_backward = self.I_p1
|
||
|
|
self.ket = self.cursor
|
||
|
|
if self.find_among_b(NorwegianStemmer.a_1) == 0:
|
||
|
|
self.limit_backward = v_3
|
||
|
|
return False
|
||
|
|
self.bra = self.cursor
|
||
|
|
self.limit_backward = v_3
|
||
|
|
self.cursor = self.limit - v_1
|
||
|
|
if self.cursor <= self.limit_backward:
|
||
|
|
return False
|
||
|
|
self.cursor -= 1
|
||
|
|
self.bra = self.cursor
|
||
|
|
if not self.slice_del():
|
||
|
|
return False
|
||
|
|
|
||
|
|
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
|
||
|
|
if self.find_among_b(NorwegianStemmer.a_2) == 0:
|
||
|
|
self.limit_backward = v_2
|
||
|
|
return False
|
||
|
|
self.bra = self.cursor
|
||
|
|
self.limit_backward = v_2
|
||
|
|
if not self.slice_del():
|
||
|
|
return False
|
||
|
|
|
||
|
|
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
|
||
|
|
|
||
|
|
|
||
|
|
class lab0(BaseException): pass
|
||
|
|
|
||
|
|
|
||
|
|
class lab1(BaseException): pass
|