semantic-compressor 2.0__py3-none-any.whl → 2.2__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- compressor/resources/nltk_data/tokenizers/punkt_tab/README +98 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/czech/abbrev_types.txt +118 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/czech/collocations.tab +96 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/czech/ortho_context.tab +52789 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/czech/sent_starters.txt +54 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/danish/abbrev_types.txt +211 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/danish/collocations.tab +101 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/danish/ortho_context.tab +53913 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/danish/sent_starters.txt +64 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/abbrev_types.txt +99 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/collocations.tab +37 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/ortho_context.tab +32208 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/sent_starters.txt +54 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txt +156 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/english/collocations.tab +37 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/english/ortho_context.tab +20366 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/english/sent_starters.txt +39 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/abbrev_types.txt +48 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/collocations.tab +100 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/ortho_context.tab +68544 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/sent_starters.txt +89 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/abbrev_types.txt +81 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/collocations.tab +167 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/ortho_context.tab +79765 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/sent_starters.txt +86 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/french/abbrev_types.txt +61 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/french/collocations.tab +18 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/french/ortho_context.tab +26726 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/french/sent_starters.txt +48 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/german/abbrev_types.txt +71 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/german/collocations.tab +28 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/german/ortho_context.tab +60260 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/german/sent_starters.txt +107 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/greek/abbrev_types.txt +100 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/greek/collocations.tab +7 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/greek/ortho_context.tab +29624 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/greek/sent_starters.txt +54 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/italian/abbrev_types.txt +125 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/italian/collocations.tab +6 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/italian/ortho_context.tab +29929 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/italian/sent_starters.txt +40 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/abbrev_types.txt +285 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/collocations.tab +153 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/ortho_context.tab +10520 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/sent_starters.txt +14 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/abbrev_types.txt +106 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/collocations.tab +54 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/ortho_context.tab +54125 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/sent_starters.txt +63 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/polish/abbrev_types.txt +225 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/polish/collocations.tab +57 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/polish/ortho_context.tab +81425 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/polish/sent_starters.txt +71 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/abbrev_types.txt +72 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/collocations.tab +5 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/ortho_context.tab +30167 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/sent_starters.txt +40 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/russian/abbrev_types.txt +1989 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/russian/collocations.tab +0 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/russian/ortho_context.tab +1 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/russian/sent_starters.txt +0 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/abbrev_types.txt +73 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/collocations.tab +74 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/ortho_context.tab +35434 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/sent_starters.txt +58 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/abbrev_types.txt +66 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/collocations.tab +7 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/ortho_context.tab +27443 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/sent_starters.txt +46 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/abbrev_types.txt +39 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/collocations.tab +8 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/ortho_context.tab +44485 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/sent_starters.txt +49 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/abbrev_types.txt +67 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/collocations.tab +14 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/ortho_context.tab +45926 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/sent_starters.txt +87 -0
- compressor/resources/nltk_data/tokenizers/punkt_tab.zip +0 -0
- compressor/semantic.py +1 -1
- {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/METADATA +1 -1
- {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/RECORD +84 -6
- {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/LICENSE +0 -0
- {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/WHEEL +0 -0
- {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,49 @@
|
|
1
|
+
de
|
2
|
+
här
|
3
|
+
vi
|
4
|
+
händelser
|
5
|
+
utredaren
|
6
|
+
man
|
7
|
+
orsaken
|
8
|
+
då
|
9
|
+
lägg
|
10
|
+
däremot
|
11
|
+
efter
|
12
|
+
regi
|
13
|
+
dessutom
|
14
|
+
kanske
|
15
|
+
jäs
|
16
|
+
under
|
17
|
+
dessa
|
18
|
+
det
|
19
|
+
nu
|
20
|
+
vid
|
21
|
+
därefter
|
22
|
+
detta
|
23
|
+
förutom
|
24
|
+
sen
|
25
|
+
men
|
26
|
+
detsamma
|
27
|
+
sedan
|
28
|
+
jag
|
29
|
+
därmed
|
30
|
+
vad
|
31
|
+
enligt
|
32
|
+
därför
|
33
|
+
samtidigt
|
34
|
+
vidare
|
35
|
+
problemet
|
36
|
+
leden
|
37
|
+
anna
|
38
|
+
den
|
39
|
+
nej
|
40
|
+
även
|
41
|
+
hans
|
42
|
+
denna
|
43
|
+
först
|
44
|
+
hon
|
45
|
+
trots
|
46
|
+
när
|
47
|
+
i
|
48
|
+
många
|
49
|
+
han
|
@@ -0,0 +1,67 @@
|
|
1
|
+
f.y
|
2
|
+
bşk
|
3
|
+
kaçabilir
|
4
|
+
a.ü
|
5
|
+
ç.y
|
6
|
+
f.a
|
7
|
+
yaşındayım
|
8
|
+
işletilen
|
9
|
+
r.i
|
10
|
+
g.h
|
11
|
+
sn
|
12
|
+
s.h.h
|
13
|
+
cevaplandırdı
|
14
|
+
başlatılıp,
|
15
|
+
s.b
|
16
|
+
dr
|
17
|
+
'dı
|
18
|
+
org
|
19
|
+
g.t
|
20
|
+
idi
|
21
|
+
indi
|
22
|
+
st
|
23
|
+
hazırlamıştım
|
24
|
+
prof
|
25
|
+
k
|
26
|
+
bulamadı
|
27
|
+
doç
|
28
|
+
erdi
|
29
|
+
a.ş
|
30
|
+
ü
|
31
|
+
s.ö
|
32
|
+
lt
|
33
|
+
akşamcı
|
34
|
+
kazanıyorlar
|
35
|
+
kaldırıyordu
|
36
|
+
m
|
37
|
+
um
|
38
|
+
t.t
|
39
|
+
f.b
|
40
|
+
s.a
|
41
|
+
hz
|
42
|
+
dı
|
43
|
+
e.ü
|
44
|
+
ltd
|
45
|
+
sonuçlanmadı
|
46
|
+
ö.k
|
47
|
+
'di
|
48
|
+
bg
|
49
|
+
t.c
|
50
|
+
vs
|
51
|
+
kg
|
52
|
+
b.ü
|
53
|
+
müd
|
54
|
+
s
|
55
|
+
s.n
|
56
|
+
h.ç
|
57
|
+
'dur
|
58
|
+
öğrendim
|
59
|
+
b.v
|
60
|
+
bulunacak
|
61
|
+
kalmıştım
|
62
|
+
kom
|
63
|
+
s.o.s
|
64
|
+
göndermişlerdi
|
65
|
+
yrd
|
66
|
+
h.g
|
67
|
+
kaçınılmazdı
|
@@ -0,0 +1,14 @@
|
|
1
|
+
##number## maddesinde
|
2
|
+
##number## maddesi
|
3
|
+
##number## paralelin
|
4
|
+
##number## madde
|
5
|
+
##number## maddesinin
|
6
|
+
##number## maddesiyle
|
7
|
+
##number## maddesine
|
8
|
+
##number## maddesindeki
|
9
|
+
a 'yı
|
10
|
+
##number## maddesinden
|
11
|
+
##number## yüzyıl
|
12
|
+
##number## maddelerinde
|
13
|
+
a 'nın
|
14
|
+
##number## dakikasında
|