semantic-compressor 2.1__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
- {semantic_compressor-2.1.dist-info → semantic_compressor-2.2.dist-info}/METADATA +1 -1
- {semantic_compressor-2.1.dist-info → semantic_compressor-2.2.dist-info}/RECORD +83 -5
- {semantic_compressor-2.1.dist-info → semantic_compressor-2.2.dist-info}/LICENSE +0 -0
- {semantic_compressor-2.1.dist-info → semantic_compressor-2.2.dist-info}/WHEEL +0 -0
- {semantic_compressor-2.1.dist-info → semantic_compressor-2.2.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,58 @@
|
|
1
|
+
komunisti
|
2
|
+
ko
|
3
|
+
podobno
|
4
|
+
kljub
|
5
|
+
čeprav
|
6
|
+
res
|
7
|
+
mislim
|
8
|
+
tako
|
9
|
+
te
|
10
|
+
po
|
11
|
+
največ
|
12
|
+
v
|
13
|
+
vse
|
14
|
+
seveda
|
15
|
+
pri
|
16
|
+
ob
|
17
|
+
nisem
|
18
|
+
zanimivo
|
19
|
+
kdor
|
20
|
+
člani
|
21
|
+
skupščina
|
22
|
+
kajti
|
23
|
+
odbor
|
24
|
+
zato
|
25
|
+
takrat
|
26
|
+
mateja
|
27
|
+
predsedstvo
|
28
|
+
predsednik
|
29
|
+
ker
|
30
|
+
dejstvo
|
31
|
+
gre
|
32
|
+
tečajnica
|
33
|
+
prav
|
34
|
+
če
|
35
|
+
najnižje
|
36
|
+
gordana
|
37
|
+
izvršni
|
38
|
+
menim
|
39
|
+
saša
|
40
|
+
tu
|
41
|
+
a
|
42
|
+
skratka
|
43
|
+
ta
|
44
|
+
hkrati
|
45
|
+
med
|
46
|
+
žal
|
47
|
+
toda
|
48
|
+
morda
|
49
|
+
poleg
|
50
|
+
vsi
|
51
|
+
pihal
|
52
|
+
prvič
|
53
|
+
večina
|
54
|
+
mar
|
55
|
+
vendar
|
56
|
+
recimo
|
57
|
+
prepričan
|
58
|
+
to
|
@@ -0,0 +1,66 @@
|
|
1
|
+
ss
|
2
|
+
t
|
3
|
+
c
|
4
|
+
ll
|
5
|
+
cc
|
6
|
+
j.c.n.ll
|
7
|
+
at
|
8
|
+
res
|
9
|
+
ath
|
10
|
+
z
|
11
|
+
dr
|
12
|
+
f.l
|
13
|
+
atl
|
14
|
+
uu
|
15
|
+
r
|
16
|
+
d
|
17
|
+
lea
|
18
|
+
ají
|
19
|
+
aps
|
20
|
+
esp
|
21
|
+
íes
|
22
|
+
w.o
|
23
|
+
lit
|
24
|
+
dgt
|
25
|
+
ee.uu
|
26
|
+
j
|
27
|
+
k
|
28
|
+
p
|
29
|
+
zim
|
30
|
+
inh
|
31
|
+
m
|
32
|
+
arg
|
33
|
+
g
|
34
|
+
u.p
|
35
|
+
esc
|
36
|
+
etc
|
37
|
+
ing
|
38
|
+
s.a
|
39
|
+
ea_
|
40
|
+
alh
|
41
|
+
vv
|
42
|
+
f
|
43
|
+
s
|
44
|
+
ale
|
45
|
+
j.d
|
46
|
+
jn
|
47
|
+
ajo
|
48
|
+
l
|
49
|
+
n
|
50
|
+
ch
|
51
|
+
avda
|
52
|
+
mt
|
53
|
+
d.a
|
54
|
+
?í
|
55
|
+
sr
|
56
|
+
h
|
57
|
+
kas
|
58
|
+
oo
|
59
|
+
j.t
|
60
|
+
cc.oo
|
61
|
+
aa
|
62
|
+
s.o.s
|
63
|
+
w
|
64
|
+
a.d.n
|
65
|
+
m.c
|
66
|
+
k.a
|