nlpir 0.1.0-x86-linux → 1.0.0-x86-linux
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +160 -23
- data/bin/lib.txt +1738 -0
- data/bin/libNLPIR.so +0 -0
- data/lib/Data/Configure.xml +4 -3
- data/{test/Data/NLPIR.user → lib/Data/DocExtractor.user} +0 -0
- data/lib/Data/English/English.pdat +0 -0
- data/lib/Data/English/English.pos +0 -0
- data/lib/Data/English/English.ung +0 -0
- data/lib/Data/English/English.wordlist +0 -0
- data/lib/Data/English/Irrel2regular.map +0 -0
- data/lib/Data/English/ne.pdat +0 -0
- data/lib/Data/English/ne.pos +0 -0
- data/lib/Data/English/ne.wordlist +0 -0
- data/lib/Data/FTU8.pdat +0 -0
- data/lib/Data/FTU8.wordlist +0 -0
- data/lib/Data/FTU82GBK.map +0 -0
- data/lib/Data/FieldDict.pdat +0 -0
- data/lib/Data/FieldDict.pos +0 -0
- data/lib/Data/GBK2FTU8.map +0 -0
- data/lib/Data/ICTPOS.map +4 -0
- data/lib/Data/NLPIR.user +0 -0
- data/lib/Data/NewWord.lst +26 -0
- data/lib/Data/PKU.map +4 -0
- data/lib/Data/PKU_First.map +4 -0
- data/lib/Data/UserDict.pdat +0 -0
- data/lib/Data/location.map +0 -0
- data/{test/Data/FieldDict.pdat → lib/Data/location.pdat} +0 -0
- data/lib/Data/location.wordlist +0 -0
- data/lib/Data/sentiment.pdat +0 -0
- data/lib/Data/sentiment.ung +0 -0
- data/lib/nlpir.rb +129 -104
- data/lib/nlpir/version.rb +1 -1
- data/nlpir.gemspec +1 -1
- data/test/findnewword.txt +103 -0
- data/test/test_nlpir.rb +137 -133
- data/test/test_result.txt +52 -35
- metadata +32 -90
- data/test/Data/BIG2GBK.map +0 -0
- data/test/Data/BIG5.pdat +0 -0
- data/test/Data/BIG5.wordlist +0 -0
- data/test/Data/BiWord.big +0 -0
- data/test/Data/Configure.xml +0 -15
- data/test/Data/CoreDict.pdat +0 -0
- data/test/Data/CoreDict.pos +0 -0
- data/test/Data/CoreDict.unig +0 -0
- data/test/Data/FieldDict.pos +0 -0
- data/test/Data/GBK.pdat +0 -0
- data/test/Data/GBK.wordlist +0 -0
- data/test/Data/GBK2BIG.map +0 -0
- data/test/Data/GBK2GBKC.map +0 -0
- data/test/Data/GBK2UTF.map +0 -0
- data/test/Data/GBKA.pdat +0 -0
- data/test/Data/GBKA.wordlist +0 -0
- data/test/Data/GBKA2UTF.map +0 -0
- data/test/Data/GBKC.pdat +0 -0
- data/test/Data/GBKC.wordlist +0 -0
- data/test/Data/GBKC2GBK.map +0 -0
- data/test/Data/GranDict.pdat +6 -3371
- data/test/Data/GranDict.pos +0 -0
- data/test/Data/ICTPOS.map +0 -96
- data/test/Data/NLPIR.ctx +0 -0
- data/test/Data/NLPIR_First.map +0 -96
- data/test/Data/NewWord.lst +0 -3
- data/test/Data/PKU.map +0 -96
- data/test/Data/PKU_First.map +0 -96
- data/test/Data/UTF2GBK.map +0 -0
- data/test/Data/UTF2GBKA.map +0 -0
- data/test/Data/UTF8.pdat +0 -0
- data/test/Data/UTF8.wordlist +0 -0
- data/test/Data/UserDict.pdat +0 -0
- data/test/Data/charset.type +0 -0
- data/test/Data/nr.ctx +0 -0
- data/test/Data/nr.fsa +0 -0
- data/test/Data/nr.role +0 -0
data/test/Data/GranDict.pos
DELETED
Binary file
|
data/test/Data/ICTPOS.map
DELETED
@@ -1,96 +0,0 @@
|
|
1
|
-
1
|
2
|
-
4
|
3
|
-
a
|
4
|
-
ad
|
5
|
-
ag
|
6
|
-
al
|
7
|
-
an
|
8
|
-
b
|
9
|
-
bl
|
10
|
-
c
|
11
|
-
cc
|
12
|
-
d
|
13
|
-
dg
|
14
|
-
dl
|
15
|
-
e
|
16
|
-
f
|
17
|
-
h
|
18
|
-
k
|
19
|
-
m
|
20
|
-
Mg
|
21
|
-
mq
|
22
|
-
n
|
23
|
-
ng
|
24
|
-
nl
|
25
|
-
nr
|
26
|
-
nr1
|
27
|
-
nr2
|
28
|
-
nrf
|
29
|
-
nrj
|
30
|
-
ns
|
31
|
-
nsf
|
32
|
-
nt
|
33
|
-
nz
|
34
|
-
o
|
35
|
-
p
|
36
|
-
pba
|
37
|
-
pbei
|
38
|
-
q
|
39
|
-
qt
|
40
|
-
qv
|
41
|
-
r
|
42
|
-
Rg
|
43
|
-
rr
|
44
|
-
ry
|
45
|
-
rys
|
46
|
-
ryt
|
47
|
-
ryv
|
48
|
-
rz
|
49
|
-
rzs
|
50
|
-
rzt
|
51
|
-
rzv
|
52
|
-
s
|
53
|
-
t
|
54
|
-
tg
|
55
|
-
u
|
56
|
-
ude1
|
57
|
-
ude2
|
58
|
-
ude3
|
59
|
-
udeng
|
60
|
-
udh
|
61
|
-
uguo
|
62
|
-
ule
|
63
|
-
ulian
|
64
|
-
uls
|
65
|
-
usuo
|
66
|
-
uyy
|
67
|
-
uzhe
|
68
|
-
uzhi
|
69
|
-
v
|
70
|
-
vd
|
71
|
-
vf
|
72
|
-
vg
|
73
|
-
vi
|
74
|
-
vl
|
75
|
-
vn
|
76
|
-
vshi
|
77
|
-
vx
|
78
|
-
vyou
|
79
|
-
w
|
80
|
-
wb
|
81
|
-
wd
|
82
|
-
wf
|
83
|
-
wj
|
84
|
-
wky
|
85
|
-
wkz
|
86
|
-
wm
|
87
|
-
wn
|
88
|
-
wp
|
89
|
-
ws
|
90
|
-
wt
|
91
|
-
ww
|
92
|
-
wyy
|
93
|
-
wyz
|
94
|
-
x
|
95
|
-
y
|
96
|
-
z
|
data/test/Data/NLPIR.ctx
DELETED
Binary file
|
data/test/Data/NLPIR_First.map
DELETED
@@ -1,96 +0,0 @@
|
|
1
|
-
1
|
2
|
-
4
|
3
|
-
a
|
4
|
-
a
|
5
|
-
a
|
6
|
-
a
|
7
|
-
a
|
8
|
-
b
|
9
|
-
b
|
10
|
-
c
|
11
|
-
c
|
12
|
-
d
|
13
|
-
d
|
14
|
-
d
|
15
|
-
e
|
16
|
-
f
|
17
|
-
h
|
18
|
-
k
|
19
|
-
m
|
20
|
-
m
|
21
|
-
m
|
22
|
-
n
|
23
|
-
n
|
24
|
-
n
|
25
|
-
n
|
26
|
-
n
|
27
|
-
n
|
28
|
-
n
|
29
|
-
n
|
30
|
-
n
|
31
|
-
n
|
32
|
-
n
|
33
|
-
n
|
34
|
-
o
|
35
|
-
p
|
36
|
-
p
|
37
|
-
p
|
38
|
-
q
|
39
|
-
q
|
40
|
-
q
|
41
|
-
r
|
42
|
-
R
|
43
|
-
r
|
44
|
-
r
|
45
|
-
r
|
46
|
-
r
|
47
|
-
r
|
48
|
-
r
|
49
|
-
r
|
50
|
-
r
|
51
|
-
r
|
52
|
-
s
|
53
|
-
t
|
54
|
-
t
|
55
|
-
u
|
56
|
-
u
|
57
|
-
u
|
58
|
-
u
|
59
|
-
u
|
60
|
-
u
|
61
|
-
u
|
62
|
-
u
|
63
|
-
u
|
64
|
-
u
|
65
|
-
u
|
66
|
-
u
|
67
|
-
u
|
68
|
-
u
|
69
|
-
v
|
70
|
-
v
|
71
|
-
v
|
72
|
-
v
|
73
|
-
v
|
74
|
-
v
|
75
|
-
v
|
76
|
-
v
|
77
|
-
v
|
78
|
-
v
|
79
|
-
w
|
80
|
-
w
|
81
|
-
w
|
82
|
-
w
|
83
|
-
w
|
84
|
-
w
|
85
|
-
w
|
86
|
-
w
|
87
|
-
w
|
88
|
-
w
|
89
|
-
w
|
90
|
-
w
|
91
|
-
w
|
92
|
-
w
|
93
|
-
w
|
94
|
-
x
|
95
|
-
y
|
96
|
-
z
|
data/test/Data/NewWord.lst
DELETED
data/test/Data/PKU.map
DELETED
@@ -1,96 +0,0 @@
|
|
1
|
-
1
|
2
|
-
4
|
3
|
-
a
|
4
|
-
ad
|
5
|
-
g
|
6
|
-
l
|
7
|
-
an
|
8
|
-
b
|
9
|
-
l
|
10
|
-
c
|
11
|
-
cc
|
12
|
-
d
|
13
|
-
g
|
14
|
-
l
|
15
|
-
e
|
16
|
-
f
|
17
|
-
h
|
18
|
-
k
|
19
|
-
m
|
20
|
-
Mg
|
21
|
-
mq
|
22
|
-
n
|
23
|
-
g
|
24
|
-
l
|
25
|
-
nr
|
26
|
-
nr
|
27
|
-
nr
|
28
|
-
nr
|
29
|
-
nr
|
30
|
-
ns
|
31
|
-
ns
|
32
|
-
nt
|
33
|
-
nz
|
34
|
-
o
|
35
|
-
p
|
36
|
-
p
|
37
|
-
p
|
38
|
-
q
|
39
|
-
qt
|
40
|
-
qv
|
41
|
-
r
|
42
|
-
Rg
|
43
|
-
r
|
44
|
-
r
|
45
|
-
r
|
46
|
-
r
|
47
|
-
r
|
48
|
-
r
|
49
|
-
r
|
50
|
-
r
|
51
|
-
r
|
52
|
-
s
|
53
|
-
t
|
54
|
-
tg
|
55
|
-
u
|
56
|
-
u
|
57
|
-
u
|
58
|
-
u
|
59
|
-
u
|
60
|
-
u
|
61
|
-
u
|
62
|
-
u
|
63
|
-
u
|
64
|
-
u
|
65
|
-
u
|
66
|
-
u
|
67
|
-
u
|
68
|
-
u
|
69
|
-
v
|
70
|
-
v
|
71
|
-
v
|
72
|
-
g
|
73
|
-
v
|
74
|
-
v
|
75
|
-
vn
|
76
|
-
v
|
77
|
-
v
|
78
|
-
v
|
79
|
-
w
|
80
|
-
w
|
81
|
-
w
|
82
|
-
w
|
83
|
-
w
|
84
|
-
w
|
85
|
-
w
|
86
|
-
w
|
87
|
-
w
|
88
|
-
w
|
89
|
-
w
|
90
|
-
w
|
91
|
-
w
|
92
|
-
w
|
93
|
-
w
|
94
|
-
x
|
95
|
-
y
|
96
|
-
z
|
data/test/Data/PKU_First.map
DELETED
@@ -1,96 +0,0 @@
|
|
1
|
-
1
|
2
|
-
4
|
3
|
-
a
|
4
|
-
a
|
5
|
-
g
|
6
|
-
l
|
7
|
-
a
|
8
|
-
b
|
9
|
-
l
|
10
|
-
c
|
11
|
-
c
|
12
|
-
d
|
13
|
-
g
|
14
|
-
l
|
15
|
-
e
|
16
|
-
f
|
17
|
-
h
|
18
|
-
k
|
19
|
-
m
|
20
|
-
m
|
21
|
-
m
|
22
|
-
n
|
23
|
-
g
|
24
|
-
l
|
25
|
-
n
|
26
|
-
n
|
27
|
-
n
|
28
|
-
n
|
29
|
-
n
|
30
|
-
n
|
31
|
-
n
|
32
|
-
n
|
33
|
-
n
|
34
|
-
o
|
35
|
-
p
|
36
|
-
p
|
37
|
-
p
|
38
|
-
q
|
39
|
-
q
|
40
|
-
q
|
41
|
-
r
|
42
|
-
R
|
43
|
-
r
|
44
|
-
r
|
45
|
-
r
|
46
|
-
r
|
47
|
-
r
|
48
|
-
r
|
49
|
-
r
|
50
|
-
r
|
51
|
-
r
|
52
|
-
s
|
53
|
-
t
|
54
|
-
t
|
55
|
-
u
|
56
|
-
u
|
57
|
-
u
|
58
|
-
u
|
59
|
-
u
|
60
|
-
u
|
61
|
-
u
|
62
|
-
u
|
63
|
-
u
|
64
|
-
u
|
65
|
-
u
|
66
|
-
u
|
67
|
-
u
|
68
|
-
u
|
69
|
-
v
|
70
|
-
v
|
71
|
-
v
|
72
|
-
g
|
73
|
-
v
|
74
|
-
v
|
75
|
-
v
|
76
|
-
v
|
77
|
-
v
|
78
|
-
v
|
79
|
-
w
|
80
|
-
w
|
81
|
-
w
|
82
|
-
w
|
83
|
-
w
|
84
|
-
w
|
85
|
-
w
|
86
|
-
w
|
87
|
-
w
|
88
|
-
w
|
89
|
-
w
|
90
|
-
w
|
91
|
-
w
|
92
|
-
w
|
93
|
-
w
|
94
|
-
x
|
95
|
-
y
|
96
|
-
z
|
data/test/Data/UTF2GBK.map
DELETED
Binary file
|
data/test/Data/UTF2GBKA.map
DELETED
Binary file
|
data/test/Data/UTF8.pdat
DELETED
Binary file
|
data/test/Data/UTF8.wordlist
DELETED
Binary file
|
data/test/Data/UserDict.pdat
DELETED
Binary file
|
data/test/Data/charset.type
DELETED
Binary file
|
data/test/Data/nr.ctx
DELETED
Binary file
|
data/test/Data/nr.fsa
DELETED
Binary file
|
data/test/Data/nr.role
DELETED
Binary file
|