scylla 0.5.0 → 0.6.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +4 -2
- data/Gemfile.lock +16 -1
- data/lib/scylla/classifier.rb +1 -1
- data/lib/scylla/generator.rb +16 -4
- data/lib/scylla/lms/afrikaans.lm +232 -232
- data/lib/scylla/lms/arabic.lm +175 -175
- data/lib/scylla/lms/bulgarian.lm +225 -225
- data/lib/scylla/lms/catalan.lm +309 -309
- data/lib/scylla/lms/danish.lm +167 -167
- data/lib/scylla/lms/english.lm +398 -398
- data/lib/scylla/lms/finnish.lm +237 -237
- data/lib/scylla/lms/french.lm +148 -148
- data/lib/scylla/lms/german.lm +258 -258
- data/lib/scylla/lms/greek.lm +236 -236
- data/lib/scylla/lms/hebrew.lm +154 -154
- data/lib/scylla/lms/hindi.lm +139 -139
- data/lib/scylla/lms/icelandic.lm +239 -239
- data/lib/scylla/lms/indonesian.lm +244 -244
- data/lib/scylla/lms/italian.lm +248 -248
- data/lib/scylla/lms/japanese.lm +90 -90
- data/lib/scylla/lms/korean.lm +306 -306
- data/lib/scylla/lms/norwegian.lm +193 -193
- data/lib/scylla/lms/polish.lm +241 -241
- data/lib/scylla/lms/portuguese.lm +232 -232
- data/lib/scylla/lms/romanian.lm +246 -246
- data/lib/scylla/lms/slovak.lm +242 -242
- data/lib/scylla/lms/slovenian.lm +229 -229
- data/lib/scylla/lms/spanish.lm +164 -164
- data/lib/scylla/lms/swedish.lm +157 -157
- data/lib/scylla/lms/tagalog.lm +247 -247
- data/lib/scylla/lms/thai.lm +252 -252
- data/lib/scylla/lms/turkish.lm +285 -285
- data/lib/scylla/lms/vietnamese.lm +250 -250
- data/lib/scylla/lms/welsh.lm +248 -248
- data/lib/scylla/resources.rb +1 -9
- data/lib/scylla.rb +4 -0
- data/scylla.gemspec +2 -120
- data/source_texts/english.txt +62 -27
- data/test/classifier_test.rb +1 -3
- data/test/fixtures/lms/danish.lm +173 -173
- data/test/fixtures/lms/english.lm +220 -220
- data/test/fixtures/lms/french.lm +175 -175
- data/test/fixtures/lms/german.lm +254 -254
- data/test/fixtures/lms/hindi.lm +139 -139
- data/test/fixtures/lms/italian.lm +236 -236
- data/test/fixtures/lms/japanese.lm +88 -88
- data/test/fixtures/lms/norwegian.lm +182 -182
- data/test/fixtures/lms/spanish.lm +164 -164
- data/test/fixtures/test_languages/spanish +0 -1
- data/test/generator_test.rb +13 -0
- data/test/helper.rb +2 -0
- metadata +18 -25
- data/.document +0 -5
- data/lib/scylla/lms/13375P33K.lm +0 -400
- data/scylla-0.1.0.gem +0 -0
- data/source_texts/13375P33K.txt +0 -199
- data/test/fixtures/lms/13375p33k.lm +0 -400
- data/test/fixtures/source_texts/13375P33K.txt +0 -199
data/Gemfile
CHANGED
@@ -8,10 +8,12 @@ source "http://rubygems.org"
|
|
8
8
|
group :development do
|
9
9
|
gem "bundler", "~> 1.0.0"
|
10
10
|
gem "jeweler", "~> 1.6.4"
|
11
|
+
gem "mail"
|
12
|
+
gem "sanitize"
|
11
13
|
end
|
12
14
|
|
13
15
|
group :test do
|
14
16
|
gem "shoulda", ">= 0"
|
15
|
-
gem "mocha"
|
16
|
-
gem "ruby-debug",
|
17
|
+
gem "mocha"
|
18
|
+
gem "ruby-debug", "~> 0.10.4"
|
17
19
|
end
|
data/Gemfile.lock
CHANGED
@@ -3,13 +3,21 @@ GEM
|
|
3
3
|
specs:
|
4
4
|
columnize (0.3.4)
|
5
5
|
git (1.2.5)
|
6
|
+
i18n (0.6.0)
|
6
7
|
jeweler (1.6.4)
|
7
8
|
bundler (~> 1.0)
|
8
9
|
git (>= 1.2.5)
|
9
10
|
rake
|
10
11
|
linecache (0.46)
|
11
12
|
rbx-require-relative (> 0.0.4)
|
13
|
+
mail (2.3.0)
|
14
|
+
i18n (>= 0.4.0)
|
15
|
+
mime-types (~> 1.16)
|
16
|
+
treetop (~> 1.4.8)
|
17
|
+
mime-types (1.16)
|
12
18
|
mocha (0.9.12)
|
19
|
+
nokogiri (1.4.7)
|
20
|
+
polyglot (0.3.2)
|
13
21
|
rake (0.9.2)
|
14
22
|
rbx-require-relative (0.0.5)
|
15
23
|
ruby-debug (0.10.4)
|
@@ -17,7 +25,12 @@ GEM
|
|
17
25
|
ruby-debug-base (~> 0.10.4.0)
|
18
26
|
ruby-debug-base (0.10.4)
|
19
27
|
linecache (>= 0.3)
|
28
|
+
sanitize (2.0.3)
|
29
|
+
nokogiri (>= 1.4.4, < 1.6)
|
20
30
|
shoulda (2.11.3)
|
31
|
+
treetop (1.4.10)
|
32
|
+
polyglot
|
33
|
+
polyglot (>= 0.3.1)
|
21
34
|
|
22
35
|
PLATFORMS
|
23
36
|
ruby
|
@@ -25,6 +38,8 @@ PLATFORMS
|
|
25
38
|
DEPENDENCIES
|
26
39
|
bundler (~> 1.0.0)
|
27
40
|
jeweler (~> 1.6.4)
|
28
|
-
|
41
|
+
mail
|
42
|
+
mocha
|
29
43
|
ruby-debug (~> 0.10.4)
|
44
|
+
sanitize
|
30
45
|
shoulda
|
data/lib/scylla/classifier.rb
CHANGED
@@ -5,7 +5,7 @@ module Scylla
|
|
5
5
|
# limit : Up to how many matching language results should be displayed
|
6
6
|
# ngrams : The total number of ngrams that are stored for each language
|
7
7
|
# threshold: The threshold score for matches
|
8
|
-
def initialize(limit = 10, ngrams = 400, threshold = 1.
|
8
|
+
def initialize(limit = 10, ngrams = 400, threshold = 1.05)
|
9
9
|
@limit = limit
|
10
10
|
@ngrams = ngrams
|
11
11
|
@threshold = threshold
|
data/lib/scylla/generator.rb
CHANGED
@@ -1,3 +1,6 @@
|
|
1
|
+
require 'sanitize'
|
2
|
+
require 'cgi'
|
3
|
+
|
1
4
|
module Scylla
|
2
5
|
class Generator
|
3
6
|
attr_accessor :dirtext, :dirlm, :minsize
|
@@ -10,7 +13,7 @@ module Scylla
|
|
10
13
|
@minsize = minsize
|
11
14
|
end
|
12
15
|
|
13
|
-
#
|
16
|
+
# Loads all the .txt files in the specified source training text folder
|
14
17
|
# and creates language maps using ngram frequencies. The maps are stored in
|
15
18
|
# lib/scylla/lms as .lm files
|
16
19
|
def train
|
@@ -26,7 +29,7 @@ module Scylla
|
|
26
29
|
# lib/scylla/lms
|
27
30
|
def write_lm(path)
|
28
31
|
text = ""
|
29
|
-
File.open(path).each { |line| text += line
|
32
|
+
File.open(path).each { |line| text += clean(line) }
|
30
33
|
p "Creating language map for " + path
|
31
34
|
lm = create_lm(text, true)
|
32
35
|
lmname = File.join(@dirlm, File.basename(path, ".txt") + ".lm")
|
@@ -41,12 +44,21 @@ module Scylla
|
|
41
44
|
end
|
42
45
|
end
|
43
46
|
|
44
|
-
|
47
|
+
def clean(string)
|
48
|
+
string.strip!
|
49
|
+
string = Sanitize.clean(string)
|
50
|
+
string = CGI.unescapeHTML(string)
|
51
|
+
string.gsub!(/(?:http|https):\/\/[a-z0-9]+(?:[\-\.]{1}[a-z0-9]+)*\.[a-z]{2,5}(?:(?::[0-9]{1,5})?\/[^\s]*)?/, "")
|
52
|
+
string.gsub!(/[\*\^><!\"#\$%&\'\(\)\*\+:;=\?@\{\}\[\]|-]/,"")
|
53
|
+
string.strip
|
54
|
+
end
|
55
|
+
|
56
|
+
# Creates a language map for a given input string.
|
45
57
|
# The frequencies boolean specifies whether or not the method should
|
46
58
|
# return the freqencies of the ngrams, or simply an array in sorted order
|
47
59
|
def create_lm(input, frequencies = false)
|
48
60
|
text = ""
|
49
|
-
input.each_line {|line| text += line
|
61
|
+
input.each_line {|line| text += clean(line) }
|
50
62
|
input = text
|
51
63
|
ngram = Hash.new
|
52
64
|
input.split(/[\d\s\[\]]/).each do |word|
|
data/lib/scylla/lms/afrikaans.lm
CHANGED
@@ -8,26 +8,27 @@ r 224
|
|
8
8
|
t 206
|
9
9
|
s 202
|
10
10
|
d 190
|
11
|
-
e_
|
11
|
+
e_ 144
|
12
12
|
l 126
|
13
13
|
g 125
|
14
14
|
m 124
|
15
15
|
ie 123
|
16
16
|
k 122
|
17
|
-
n_
|
17
|
+
n_ 112
|
18
18
|
t_ 92
|
19
19
|
h 89
|
20
|
-
an 83
|
21
20
|
er 83
|
21
|
+
an 83
|
22
22
|
v 82
|
23
23
|
y 81
|
24
24
|
_d 76
|
25
|
+
ie_ 76
|
25
26
|
aa 75
|
26
|
-
|
27
|
-
_h 73
|
27
|
+
_h 74
|
28
28
|
w 73
|
29
29
|
di 73
|
30
30
|
s_ 71
|
31
|
+
_n 69
|
31
32
|
_v 66
|
32
33
|
en 65
|
33
34
|
. 62
|
@@ -38,7 +39,6 @@ u 59
|
|
38
39
|
_di 58
|
39
40
|
_s 57
|
40
41
|
et 56
|
41
|
-
_n 56
|
42
42
|
_m 53
|
43
43
|
die 51
|
44
44
|
b 50
|
@@ -47,354 +47,354 @@ ee 47
|
|
47
47
|
ni 46
|
48
48
|
_w 46
|
49
49
|
in 46
|
50
|
-
_die 45
|
51
50
|
die_ 45
|
51
|
+
_die 45
|
52
52
|
an_ 45
|
53
53
|
et_ 44
|
54
|
-
_e 43
|
55
54
|
p 43
|
55
|
+
_e 43
|
56
56
|
de 42
|
57
57
|
_die_ 41
|
58
58
|
_o 40
|
59
|
-
._
|
59
|
+
._ 38
|
60
60
|
nd 36
|
61
|
-
_g 35
|
62
|
-
el 35
|
63
61
|
ar 35
|
64
62
|
at 35
|
65
|
-
|
63
|
+
_g 35
|
64
|
+
el 35
|
66
65
|
oe 34
|
67
66
|
k_ 34
|
68
67
|
wa 34
|
69
|
-
|
68
|
+
nie 34
|
70
69
|
, 33
|
70
|
+
g_ 33
|
71
71
|
_a 33
|
72
|
+
_ni 33
|
72
73
|
he 32
|
73
74
|
oo 32
|
74
|
-
g_ 32
|
75
75
|
_nie 32
|
76
|
+
,_ 31
|
76
77
|
ek 30
|
77
|
-
,_ 30
|
78
|
-
om 29
|
79
78
|
_i 29
|
80
|
-
|
79
|
+
om 29
|
80
|
+
_wa 28
|
81
81
|
me 28
|
82
|
-
|
83
|
-
_k 28
|
82
|
+
en_ 28
|
84
83
|
_he 28
|
84
|
+
_k 28
|
85
|
+
va 28
|
85
86
|
aan 28
|
86
|
-
_wa 28
|
87
87
|
is 27
|
88
|
-
_en 26
|
89
88
|
f 26
|
89
|
+
_en 26
|
90
90
|
at_ 26
|
91
91
|
_ge 26
|
92
|
-
es 25
|
93
92
|
or 25
|
94
|
-
|
95
|
-
as 24
|
96
|
-
_t 24
|
97
|
-
ma 24
|
93
|
+
es 25
|
98
94
|
er_ 24
|
95
|
+
it 24
|
99
96
|
on 24
|
97
|
+
het 24
|
100
98
|
_b 24
|
101
|
-
|
99
|
+
ma 24
|
100
|
+
_t 24
|
102
101
|
l_ 24
|
103
|
-
|
102
|
+
m_ 24
|
104
103
|
aar 24
|
104
|
+
as 24
|
105
105
|
d_ 23
|
106
106
|
van 23
|
107
|
-
li 22
|
108
|
-
_het 22
|
109
|
-
ou 22
|
110
107
|
ra 22
|
108
|
+
ou 22
|
109
|
+
_het 22
|
110
|
+
li 22
|
111
111
|
_va 21
|
112
|
-
be 21
|
113
112
|
het_ 21
|
114
|
-
|
115
|
-
|
116
|
-
rd 20
|
117
|
-
ng 20
|
113
|
+
be 21
|
114
|
+
da 20
|
118
115
|
om_ 20
|
119
116
|
al 20
|
120
|
-
|
121
|
-
|
117
|
+
ng 20
|
118
|
+
_het_ 20
|
119
|
+
rd 20
|
120
|
+
te_ 19
|
122
121
|
st 19
|
123
|
-
ke 19
|
124
|
-
' 19
|
125
122
|
_en_ 19
|
123
|
+
_van 19
|
124
|
+
ke 19
|
125
|
+
van_ 18
|
126
|
+
is_ 18
|
126
127
|
sy 18
|
127
128
|
ag 18
|
128
|
-
is_ 18
|
129
129
|
sy_ 18
|
130
|
-
|
131
|
-
te_ 18
|
132
|
-
re 17
|
133
|
-
and 17
|
134
|
-
aar_ 17
|
135
|
-
se 17
|
130
|
+
_van_ 17
|
136
131
|
ro 17
|
137
132
|
- 17
|
138
|
-
|
139
|
-
|
140
|
-
le 17
|
141
|
-
der 17
|
133
|
+
aar_ 17
|
134
|
+
_ma 17
|
142
135
|
ar_ 17
|
136
|
+
re 17
|
137
|
+
nie_ 17
|
143
138
|
nde 17
|
144
|
-
|
139
|
+
se 17
|
140
|
+
le 17
|
141
|
+
and 17
|
142
|
+
der 17
|
143
|
+
hy 17
|
144
|
+
as_ 16
|
145
145
|
_hy 16
|
146
|
-
_me 16
|
147
146
|
H 16
|
148
|
-
we 16
|
149
|
-
as_ 16
|
150
147
|
ei 16
|
148
|
+
_me 16
|
149
|
+
_H 16
|
151
150
|
aan_ 16
|
152
|
-
|
153
|
-
|
151
|
+
_nie_ 16
|
152
|
+
we 16
|
154
153
|
ho 15
|
155
|
-
em 15
|
156
|
-
so 15
|
157
|
-
nie_ 15
|
158
154
|
_sy_ 15
|
159
|
-
_sy 15
|
160
|
-
_' 15
|
161
|
-
ko 15
|
162
155
|
it_ 15
|
163
|
-
|
156
|
+
ko 15
|
157
|
+
em 15
|
158
|
+
ns 15
|
164
159
|
ig 15
|
165
|
-
|
160
|
+
ik 15
|
161
|
+
so 15
|
162
|
+
_sy 15
|
163
|
+
rs 14
|
164
|
+
in_ 14
|
166
165
|
hy_ 14
|
167
|
-
mo 14
|
168
166
|
ha 14
|
167
|
+
si 14
|
168
|
+
vo 14
|
169
|
+
nt 14
|
169
170
|
vi 14
|
171
|
+
mo 14
|
170
172
|
ve 14
|
171
|
-
nt 14
|
172
|
-
_nie_ 14
|
173
|
-
vo 14
|
174
|
-
rs 14
|
175
|
-
si 14
|
176
|
-
in_ 14
|
177
|
-
ou_ 13
|
178
|
-
'n_ 13
|
179
|
-
_in 13
|
180
|
-
_be 13
|
181
|
-
_'n 13
|
182
|
-
_'n_ 13
|
183
173
|
no 13
|
184
|
-
_vi 13
|
185
|
-
_hy_ 13
|
186
174
|
rt 13
|
175
|
+
_n_ 13
|
176
|
+
ou_ 13
|
187
177
|
u_ 13
|
178
|
+
_in 13
|
179
|
+
eer 13
|
180
|
+
_hy_ 13
|
181
|
+
wo 13
|
182
|
+
e, 13
|
188
183
|
ag_ 13
|
184
|
+
_be 13
|
185
|
+
e,_ 13
|
186
|
+
_vi 13
|
189
187
|
op 13
|
190
|
-
e, 13
|
191
|
-
wo 13
|
192
|
-
eer 13
|
193
|
-
ed 12
|
194
|
-
ing 12
|
195
|
-
ne 12
|
196
|
-
e,_ 12
|
197
|
-
ver 12
|
198
|
-
ew 12
|
199
|
-
_te_ 12
|
200
188
|
ek_ 12
|
201
189
|
_vo 12
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
_om 12
|
190
|
+
_te_ 12
|
191
|
+
ew 12
|
192
|
+
ver 12
|
206
193
|
_om_ 12
|
207
|
-
|
194
|
+
ne 12
|
195
|
+
was 12
|
196
|
+
_is 12
|
197
|
+
e. 12
|
208
198
|
al_ 12
|
199
|
+
wat 12
|
200
|
+
ing 12
|
201
|
+
_om 12
|
202
|
+
_te 12
|
203
|
+
ed 12
|
204
|
+
_so 11
|
209
205
|
_is_ 11
|
206
|
+
vir_ 11
|
207
|
+
ord 11
|
210
208
|
bl 11
|
209
|
+
vir 11
|
210
|
+
ka 11
|
211
|
+
_ko 11
|
211
212
|
ta 11
|
212
|
-
_mo 11
|
213
|
-
_no 11
|
214
|
-
_so 11
|
215
|
-
moe 11
|
216
|
-
ord 11
|
217
213
|
met 11
|
218
|
-
|
214
|
+
wat_ 11
|
219
215
|
_was 11
|
220
|
-
ka 11
|
221
|
-
vir 11
|
222
|
-
ir 11
|
223
216
|
_on 11
|
224
|
-
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
wat_ 11
|
229
|
-
e. 11
|
217
|
+
_mo 11
|
218
|
+
ir 11
|
219
|
+
moe 11
|
220
|
+
maa 11
|
230
221
|
S 11
|
222
|
+
_p 11
|
223
|
+
_ha 11
|
224
|
+
_no 11
|
225
|
+
ir_ 11
|
231
226
|
met_ 10
|
232
|
-
|
233
|
-
|
234
|
-
nge 10
|
235
|
-
was_ 10
|
236
|
-
vr 10
|
237
|
-
_aa 10
|
227
|
+
sta 10
|
228
|
+
_aan 10
|
238
229
|
to 10
|
239
|
-
|
240
|
-
|
241
|
-
|
230
|
+
f_ 10
|
231
|
+
nder 10
|
232
|
+
sie 10
|
242
233
|
_in_ 10
|
243
234
|
oor 10
|
244
|
-
|
245
|
-
nder 10
|
246
|
-
eg 10
|
247
|
-
lik 10
|
235
|
+
_vir 10
|
248
236
|
E 10
|
237
|
+
_vir_ 10
|
249
238
|
ui 10
|
250
239
|
_da 10
|
240
|
+
was_ 10
|
241
|
+
ers 10
|
242
|
+
vr 10
|
243
|
+
ri 10
|
244
|
+
_was_ 10
|
245
|
+
lik 10
|
246
|
+
raa 10
|
247
|
+
_aa 10
|
251
248
|
_ve 10
|
252
|
-
sta 10
|
253
249
|
nk 10
|
254
|
-
|
255
|
-
|
256
|
-
|
257
|
-
|
258
|
-
|
259
|
-
_ver 9
|
250
|
+
nge 10
|
251
|
+
eg 10
|
252
|
+
p_ 10
|
253
|
+
A 9
|
254
|
+
de_ 9
|
260
255
|
ges 9
|
256
|
+
_wat 9
|
257
|
+
pr 9
|
261
258
|
ie. 9
|
262
259
|
ll 9
|
263
|
-
|
264
|
-
_met 9
|
265
|
-
de_ 9
|
260
|
+
_ver 9
|
266
261
|
_ho 9
|
267
|
-
_vr 9
|
268
|
-
_moe 9
|
269
|
-
pr 9
|
270
262
|
el_ 9
|
263
|
+
_vr 9
|
264
|
+
_Hy 9
|
265
|
+
_met 9
|
266
|
+
man 9
|
271
267
|
_ek 9
|
268
|
+
_met_ 9
|
269
|
+
_se 9
|
272
270
|
_maa 9
|
273
|
-
Hy 9
|
274
|
-
_wat 9
|
275
271
|
og 9
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
_met_ 9
|
272
|
+
Hy 9
|
273
|
+
_moe 9
|
274
|
+
wor 8
|
280
275
|
rte 8
|
281
|
-
_l 8
|
282
|
-
_my 8
|
283
276
|
aat 8
|
284
|
-
M 8
|
285
|
-
wor 8
|
286
|
-
_Hy 8
|
287
|
-
_my_ 8
|
288
|
-
ga 8
|
289
277
|
my_ 8
|
290
|
-
|
291
|
-
|
278
|
+
ak 8
|
279
|
+
j 8
|
292
280
|
es_ 8
|
293
|
-
|
281
|
+
_al 8
|
294
282
|
_op 8
|
295
|
-
din 8
|
296
|
-
kl 8
|
297
|
-
_Hy_ 8
|
298
|
-
taa 8
|
299
283
|
_ek_ 8
|
300
|
-
|
284
|
+
nie. 8
|
285
|
+
_Hy_ 8
|
286
|
+
D 8
|
287
|
+
_l 8
|
301
288
|
_to 8
|
302
|
-
|
303
|
-
|
304
|
-
ak 8
|
305
|
-
sk 8
|
289
|
+
my 8
|
290
|
+
ga 8
|
306
291
|
_nie. 8
|
292
|
+
_my_ 8
|
293
|
+
taa 8
|
294
|
+
Hy_ 8
|
307
295
|
_r 8
|
308
|
-
|
309
|
-
|
296
|
+
din 8
|
297
|
+
M 8
|
310
298
|
na 8
|
311
|
-
_al 8
|
312
|
-
_wat_ 8
|
313
299
|
pa 8
|
314
|
-
|
315
|
-
|
316
|
-
|
317
|
-
|
318
|
-
|
319
|
-
|
320
|
-
|
321
|
-
|
322
|
-
_pr 7
|
300
|
+
_wat_ 8
|
301
|
+
word 8
|
302
|
+
sk 8
|
303
|
+
ewe 8
|
304
|
+
eu 8
|
305
|
+
_my 8
|
306
|
+
kl 8
|
307
|
+
een 8
|
323
308
|
ier 7
|
309
|
+
ke_ 7
|
310
|
+
_dit 7
|
311
|
+
op_ 7
|
312
|
+
og_ 7
|
313
|
+
gaa 7
|
324
314
|
er. 7
|
325
|
-
|
315
|
+
dit 7
|
316
|
+
gaan 7
|
326
317
|
_maar 7
|
327
|
-
oe_ 7
|
328
|
-
nd_ 7
|
329
|
-
id 7
|
330
|
-
do 7
|
331
|
-
ders 7
|
332
|
-
ke_ 7
|
333
318
|
_ges 7
|
334
319
|
r. 7
|
335
|
-
|
336
|
-
|
320
|
+
ur 7
|
321
|
+
wee 7
|
337
322
|
end 7
|
323
|
+
oe_ 7
|
324
|
+
staa 7
|
325
|
+
_pr 7
|
326
|
+
e._ 7
|
327
|
+
ste 7
|
338
328
|
_st 7
|
339
|
-
|
329
|
+
ie,_ 7
|
330
|
+
la 7
|
331
|
+
gew 7
|
332
|
+
ie, 7
|
333
|
+
maar_ 7
|
334
|
+
id 7
|
335
|
+
nd_ 7
|
336
|
+
do 7
|
337
|
+
a_ 7
|
338
|
+
lin 7
|
340
339
|
tee 7
|
341
|
-
|
342
|
-
|
343
|
-
gaan 7
|
344
|
-
_ne 7
|
345
|
-
wee 7
|
346
|
-
ger 7
|
347
|
-
oet 7
|
340
|
+
ti 7
|
341
|
+
le_ 7
|
348
342
|
s. 7
|
343
|
+
ders 7
|
344
|
+
ger 7
|
345
|
+
br 7
|
346
|
+
erd 7
|
349
347
|
maar 7
|
350
|
-
|
351
|
-
|
352
|
-
|
353
|
-
|
354
|
-
|
355
|
-
|
356
|
-
|
348
|
+
O 7
|
349
|
+
uit 7
|
350
|
+
ng_ 7
|
351
|
+
_ne 7
|
352
|
+
oet 7
|
353
|
+
rs_ 6
|
354
|
+
ns_ 6
|
355
|
+
ent 6
|
357
356
|
nog 6
|
357
|
+
dat 6
|
358
|
+
_wi 6
|
359
|
+
nig 6
|
360
|
+
rm 6
|
361
|
+
oet_ 6
|
358
362
|
eer_ 6
|
359
|
-
_bl 6
|
360
|
-
_hier 6
|
361
|
-
_hi 6
|
362
|
-
ns_ 6
|
363
|
-
gaan_ 6
|
364
|
-
toe 6
|
365
|
-
yd 6
|
366
|
-
lle 6
|
367
363
|
ens 6
|
368
|
-
|
369
|
-
_u 6
|
370
|
-
nders 6
|
371
|
-
dat_ 6
|
372
|
-
os 6
|
373
|
-
hi 6
|
374
|
-
eid 6
|
364
|
+
inde 6
|
375
365
|
_wo 6
|
376
|
-
|
377
|
-
|
378
|
-
|
379
|
-
|
366
|
+
_hie 6
|
367
|
+
_hi 6
|
368
|
+
eke 6
|
369
|
+
il 6
|
370
|
+
_ui 6
|
371
|
+
ie._ 6
|
372
|
+
wi 6
|
380
373
|
nda 6
|
374
|
+
_hier 6
|
375
|
+
ing_ 6
|
376
|
+
lle 6
|
377
|
+
hie 6
|
378
|
+
toe 6
|
379
|
+
os 6
|
380
|
+
eni 6
|
381
381
|
aak 6
|
382
|
-
|
383
|
-
|
384
|
-
|
382
|
+
dat_ 6
|
383
|
+
yd 6
|
384
|
+
hi 6
|
385
385
|
mer 6
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
rs_ 6
|
390
|
-
nig 6
|
386
|
+
kom 6
|
387
|
+
hier 6
|
388
|
+
_uit 6
|
391
389
|
lo 6
|
392
|
-
|
393
|
-
r,_ 6
|
394
|
-
ie._ 6
|
390
|
+
_nog 6
|
395
391
|
ad 6
|
396
|
-
|
397
|
-
|
398
|
-
eke 6
|
399
|
-
ige 6
|
392
|
+
s._ 6
|
393
|
+
eid 6
|
400
394
|
eli 6
|
395
|
+
_nie, 6
|
396
|
+
r, 6
|
397
|
+
_bl 6
|
398
|
+
gaan_ 6
|
399
|
+
ige 6
|
400
|
+
am 6
|