You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
293 lines
8.0 KiB
293 lines
8.0 KiB
# Generated by Snowball 2.0.0 - https://snowballstem.org/
|
|
|
|
from .basestemmer import BaseStemmer
|
|
from .among import Among
|
|
|
|
|
|
class DanishStemmer(BaseStemmer):
|
|
'''
|
|
This class implements the stemming algorithm defined by a snowball script.
|
|
Generated by Snowball 2.0.0 - https://snowballstem.org/
|
|
'''
|
|
|
|
a_0 = [
|
|
Among(u"hed", -1, 1),
|
|
Among(u"ethed", 0, 1),
|
|
Among(u"ered", -1, 1),
|
|
Among(u"e", -1, 1),
|
|
Among(u"erede", 3, 1),
|
|
Among(u"ende", 3, 1),
|
|
Among(u"erende", 5, 1),
|
|
Among(u"ene", 3, 1),
|
|
Among(u"erne", 3, 1),
|
|
Among(u"ere", 3, 1),
|
|
Among(u"en", -1, 1),
|
|
Among(u"heden", 10, 1),
|
|
Among(u"eren", 10, 1),
|
|
Among(u"er", -1, 1),
|
|
Among(u"heder", 13, 1),
|
|
Among(u"erer", 13, 1),
|
|
Among(u"s", -1, 2),
|
|
Among(u"heds", 16, 1),
|
|
Among(u"es", 16, 1),
|
|
Among(u"endes", 18, 1),
|
|
Among(u"erendes", 19, 1),
|
|
Among(u"enes", 18, 1),
|
|
Among(u"ernes", 18, 1),
|
|
Among(u"eres", 18, 1),
|
|
Among(u"ens", 16, 1),
|
|
Among(u"hedens", 24, 1),
|
|
Among(u"erens", 24, 1),
|
|
Among(u"ers", 16, 1),
|
|
Among(u"ets", 16, 1),
|
|
Among(u"erets", 28, 1),
|
|
Among(u"et", -1, 1),
|
|
Among(u"eret", 30, 1)
|
|
]
|
|
|
|
a_1 = [
|
|
Among(u"gd", -1, -1),
|
|
Among(u"dt", -1, -1),
|
|
Among(u"gt", -1, -1),
|
|
Among(u"kt", -1, -1)
|
|
]
|
|
|
|
a_2 = [
|
|
Among(u"ig", -1, 1),
|
|
Among(u"lig", 0, 1),
|
|
Among(u"elig", 1, 1),
|
|
Among(u"els", -1, 1),
|
|
Among(u"l\u00F8st", -1, 2)
|
|
]
|
|
|
|
g_c = [119, 223, 119, 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 = [239, 254, 42, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 16]
|
|
|
|
I_x = 0
|
|
I_p1 = 0
|
|
S_ch = ""
|
|
|
|
def __r_mark_regions(self):
|
|
# (, line 31
|
|
self.I_p1 = self.limit
|
|
# test, line 35
|
|
v_1 = self.cursor
|
|
# (, line 35
|
|
# hop, line 35
|
|
c = self.cursor + 3
|
|
if 0 > c or c > self.limit:
|
|
return False
|
|
self.cursor = c
|
|
# setmark x, line 35
|
|
self.I_x = self.cursor
|
|
self.cursor = v_1
|
|
# goto grouping v, line 36
|
|
if not self.go_out_grouping(DanishStemmer.g_v, 97, 248):
|
|
return False
|
|
# gopast non v, line 36
|
|
if not self.go_in_grouping(DanishStemmer.g_v, 97, 248):
|
|
return False
|
|
self.cursor += 1
|
|
# setmark p1, line 36
|
|
self.I_p1 = self.cursor
|
|
# try, line 37
|
|
try:
|
|
# (, line 37
|
|
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):
|
|
# (, line 42
|
|
# setlimit, line 43
|
|
if self.cursor < self.I_p1:
|
|
return False
|
|
v_2 = self.limit_backward
|
|
self.limit_backward = self.I_p1
|
|
# (, line 43
|
|
# [, line 43
|
|
self.ket = self.cursor
|
|
# substring, line 43
|
|
among_var = self.find_among_b(DanishStemmer.a_0)
|
|
if among_var == 0:
|
|
self.limit_backward = v_2
|
|
return False
|
|
# ], line 43
|
|
self.bra = self.cursor
|
|
self.limit_backward = v_2
|
|
if among_var == 1:
|
|
# (, line 50
|
|
# delete, line 50
|
|
if not self.slice_del():
|
|
return False
|
|
|
|
elif among_var == 2:
|
|
# (, line 52
|
|
if not self.in_grouping_b(DanishStemmer.g_s_ending, 97, 229):
|
|
return False
|
|
# delete, line 52
|
|
if not self.slice_del():
|
|
return False
|
|
|
|
return True
|
|
|
|
def __r_consonant_pair(self):
|
|
# (, line 56
|
|
# test, line 57
|
|
v_1 = self.limit - self.cursor
|
|
# (, line 57
|
|
# setlimit, line 58
|
|
if self.cursor < self.I_p1:
|
|
return False
|
|
v_3 = self.limit_backward
|
|
self.limit_backward = self.I_p1
|
|
# (, line 58
|
|
# [, line 58
|
|
self.ket = self.cursor
|
|
# substring, line 58
|
|
if self.find_among_b(DanishStemmer.a_1) == 0:
|
|
self.limit_backward = v_3
|
|
return False
|
|
# ], line 58
|
|
self.bra = self.cursor
|
|
self.limit_backward = v_3
|
|
self.cursor = self.limit - v_1
|
|
# next, line 64
|
|
if self.cursor <= self.limit_backward:
|
|
return False
|
|
self.cursor -= 1
|
|
# ], line 64
|
|
self.bra = self.cursor
|
|
# delete, line 64
|
|
if not self.slice_del():
|
|
return False
|
|
|
|
return True
|
|
|
|
def __r_other_suffix(self):
|
|
# (, line 67
|
|
# do, line 68
|
|
v_1 = self.limit - self.cursor
|
|
try:
|
|
# (, line 68
|
|
# [, line 68
|
|
self.ket = self.cursor
|
|
# literal, line 68
|
|
if not self.eq_s_b(u"st"):
|
|
raise lab0()
|
|
# ], line 68
|
|
self.bra = self.cursor
|
|
# literal, line 68
|
|
if not self.eq_s_b(u"ig"):
|
|
raise lab0()
|
|
# delete, line 68
|
|
if not self.slice_del():
|
|
return False
|
|
|
|
except lab0: pass
|
|
self.cursor = self.limit - v_1
|
|
# setlimit, line 69
|
|
if self.cursor < self.I_p1:
|
|
return False
|
|
v_3 = self.limit_backward
|
|
self.limit_backward = self.I_p1
|
|
# (, line 69
|
|
# [, line 69
|
|
self.ket = self.cursor
|
|
# substring, line 69
|
|
among_var = self.find_among_b(DanishStemmer.a_2)
|
|
if among_var == 0:
|
|
self.limit_backward = v_3
|
|
return False
|
|
# ], line 69
|
|
self.bra = self.cursor
|
|
self.limit_backward = v_3
|
|
if among_var == 1:
|
|
# (, line 72
|
|
# delete, line 72
|
|
if not self.slice_del():
|
|
return False
|
|
|
|
# do, line 72
|
|
v_4 = self.limit - self.cursor
|
|
# call consonant_pair, line 72
|
|
self.__r_consonant_pair()
|
|
self.cursor = self.limit - v_4
|
|
elif among_var == 2:
|
|
# (, line 74
|
|
# <-, line 74
|
|
if not self.slice_from(u"l\u00F8s"):
|
|
return False
|
|
return True
|
|
|
|
def __r_undouble(self):
|
|
# (, line 77
|
|
# setlimit, line 78
|
|
if self.cursor < self.I_p1:
|
|
return False
|
|
v_2 = self.limit_backward
|
|
self.limit_backward = self.I_p1
|
|
# (, line 78
|
|
# [, line 78
|
|
self.ket = self.cursor
|
|
if not self.in_grouping_b(DanishStemmer.g_c, 98, 122):
|
|
self.limit_backward = v_2
|
|
return False
|
|
# ], line 78
|
|
self.bra = self.cursor
|
|
# -> ch, line 78
|
|
self.S_ch = self.slice_to()
|
|
if self.S_ch == '':
|
|
return False
|
|
self.limit_backward = v_2
|
|
# name ch, line 79
|
|
if not self.eq_s_b(self.S_ch):
|
|
return False
|
|
# delete, line 80
|
|
if not self.slice_del():
|
|
return False
|
|
|
|
return True
|
|
|
|
def _stem(self):
|
|
# (, line 84
|
|
# do, line 86
|
|
v_1 = self.cursor
|
|
# call mark_regions, line 86
|
|
self.__r_mark_regions()
|
|
self.cursor = v_1
|
|
# backwards, line 87
|
|
self.limit_backward = self.cursor
|
|
self.cursor = self.limit
|
|
# (, line 87
|
|
# do, line 88
|
|
v_2 = self.limit - self.cursor
|
|
# call main_suffix, line 88
|
|
self.__r_main_suffix()
|
|
self.cursor = self.limit - v_2
|
|
# do, line 89
|
|
v_3 = self.limit - self.cursor
|
|
# call consonant_pair, line 89
|
|
self.__r_consonant_pair()
|
|
self.cursor = self.limit - v_3
|
|
# do, line 90
|
|
v_4 = self.limit - self.cursor
|
|
# call other_suffix, line 90
|
|
self.__r_other_suffix()
|
|
self.cursor = self.limit - v_4
|
|
# do, line 91
|
|
v_5 = self.limit - self.cursor
|
|
# call undouble, line 91
|
|
self.__r_undouble()
|
|
self.cursor = self.limit - v_5
|
|
self.cursor = self.limit_backward
|
|
return True
|
|
|
|
|
|
class lab0(BaseException): pass
|