mmseg 0.2.0
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.
- data/lib/dict.txt +211206 -0
- data/lib/mmseg.rb +36 -0
- metadata +80 -0
data/lib/mmseg.rb
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
#encoding:utf-8
|
2
|
+
class Mmseg
|
3
|
+
def initialize(dic_path=File.dirname(__FILE__)+"/dict.txt")
|
4
|
+
@dict=Hash.new
|
5
|
+
@result=""
|
6
|
+
s=File.open(dic_path)
|
7
|
+
@dict=Hash.new(0)
|
8
|
+
while str=s.gets
|
9
|
+
str=str.chomp
|
10
|
+
@dict[str]=1
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def segment(str)
|
15
|
+
str=str.chomp
|
16
|
+
left=str
|
17
|
+
while left.length>0
|
18
|
+
if @dict[str]==1 or str.length==1
|
19
|
+
@result+=str+" "
|
20
|
+
len=str.length
|
21
|
+
left=left[len..-1]
|
22
|
+
str=left
|
23
|
+
else
|
24
|
+
str=str[0..-2]
|
25
|
+
end
|
26
|
+
end
|
27
|
+
return @result
|
28
|
+
end
|
29
|
+
|
30
|
+
end
|
31
|
+
|
32
|
+
#test
|
33
|
+
|
34
|
+
#mmseg=Mmseg.new("i://dict.txt")
|
35
|
+
#mmseg=Mmseg.new()
|
36
|
+
#puts mmseg.segment("今天天气不错")
|
metadata
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: mmseg
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.2.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- lining
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-10-10 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: bundler
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '1.3'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '1.3'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
description: ! '"This is a Chinese segmentation tool using mmseg"'
|
47
|
+
email:
|
48
|
+
- lining@i.mbox.nagoya-u.ac.jp
|
49
|
+
executables: []
|
50
|
+
extensions: []
|
51
|
+
extra_rdoc_files: []
|
52
|
+
files:
|
53
|
+
- lib/mmseg.rb
|
54
|
+
- lib/dict.txt
|
55
|
+
homepage: http://tjjtds.me
|
56
|
+
licenses:
|
57
|
+
- MIT
|
58
|
+
post_install_message:
|
59
|
+
rdoc_options: []
|
60
|
+
require_paths:
|
61
|
+
- lib
|
62
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
63
|
+
none: false
|
64
|
+
requirements:
|
65
|
+
- - ! '>='
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: '0'
|
68
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
69
|
+
none: false
|
70
|
+
requirements:
|
71
|
+
- - ! '>='
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
version: '0'
|
74
|
+
requirements: []
|
75
|
+
rubyforge_project:
|
76
|
+
rubygems_version: 1.8.25
|
77
|
+
signing_key:
|
78
|
+
specification_version: 3
|
79
|
+
summary: ! '"Just a toy"'
|
80
|
+
test_files: []
|