cseg 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +52 -0
- data/Rakefile +1 -0
- data/cseg.gemspec +28 -0
- data/data/pkumodle.data +0 -0
- data/lib/cseg/version.rb +3 -0
- data/lib/cseg.rb +53 -0
- metadata +55 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 gyorou
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
# Cseg
|
2
|
+
|
3
|
+
Use MIRA to train a large amount of features.
|
4
|
+
|
5
|
+
Segment chinese sentences into words in high speed and correctly.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
gem 'cseg'
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install cseg
|
20
|
+
|
21
|
+
you need to install CRF++ first and set the environment environment variables.
|
22
|
+
|
23
|
+
Here is the site of CRF++ and you should follow the manual
|
24
|
+
|
25
|
+
## Usage
|
26
|
+
|
27
|
+
require "cseg"
|
28
|
+
|
29
|
+
a=Kurumi.segment("屌丝是一种自我讽刺")
|
30
|
+
|
31
|
+
=>屌丝
|
32
|
+
|
33
|
+
是
|
34
|
+
|
35
|
+
一
|
36
|
+
|
37
|
+
种
|
38
|
+
|
39
|
+
自我
|
40
|
+
|
41
|
+
讽刺
|
42
|
+
|
43
|
+
the result will be an array.
|
44
|
+
|
45
|
+
|
46
|
+
## Contributing
|
47
|
+
|
48
|
+
1. Fork it
|
49
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
50
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
51
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
52
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/cseg.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'cseg/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "cseg"
|
8
|
+
gem.version = Cseg::VERSION
|
9
|
+
gem.authors = ["gyorou"]
|
10
|
+
gem.email = ["gyorou@tjjtds.com"]
|
11
|
+
gem.description = %q{"a chinese segmentation tool using CRF"}
|
12
|
+
gem.summary = %q{""}
|
13
|
+
gem.homepage = ""
|
14
|
+
|
15
|
+
gem.files = [".gitignore",
|
16
|
+
"LICENSE.txt",
|
17
|
+
"README.md",
|
18
|
+
"Gemfile",
|
19
|
+
"data/pkumodle.data",
|
20
|
+
"lib/cseg/version.rb",
|
21
|
+
"lib/cseg.rb",
|
22
|
+
"cseg.gemspec",
|
23
|
+
"Rakefile",
|
24
|
+
]
|
25
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
26
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
27
|
+
gem.require_paths = ["lib","data"]
|
28
|
+
end
|
data/data/pkumodle.data
ADDED
Binary file
|
data/lib/cseg/version.rb
ADDED
data/lib/cseg.rb
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
# encoding:utf-8
|
2
|
+
require "cseg/version"
|
3
|
+
require "tempfile"
|
4
|
+
class Kurumi
|
5
|
+
# since crf++ can only read from file
|
6
|
+
#@tmpfile.read{|file| file=nil}
|
7
|
+
@modle=File.expand_path("../../data/pkumodle.data", __FILE__)
|
8
|
+
@result=Array.new
|
9
|
+
def self.segment(str)
|
10
|
+
tmpstr=""
|
11
|
+
for i in 0..str.length-1
|
12
|
+
tmpstr+=str[i]+"\n"
|
13
|
+
end
|
14
|
+
#@tmpfile=nil
|
15
|
+
@tmp=Tempfile::new("tmp")
|
16
|
+
@resultfile=Tempfile::new("result")
|
17
|
+
@tmp.write(tmpstr)
|
18
|
+
@tmp.rewind
|
19
|
+
#@tmpfile.close
|
20
|
+
system("crf_test -m #{@modle} #{@tmp.path}>#{@resultfile.path}")
|
21
|
+
@resultfile.rewind
|
22
|
+
# puts @resultfile.read
|
23
|
+
# puts @tmp.read
|
24
|
+
|
25
|
+
word=""
|
26
|
+
@resultfile.read.each_line{|line|
|
27
|
+
token=line.chomp.split(" ")
|
28
|
+
if token[1]=="B"or token[1]=="O"
|
29
|
+
if word!=""
|
30
|
+
@result.push(word)
|
31
|
+
end
|
32
|
+
word=token[0]
|
33
|
+
elsif token[1]=="I"
|
34
|
+
word+=token[0]
|
35
|
+
else
|
36
|
+
#nil
|
37
|
+
if word!=""
|
38
|
+
@result.push(word)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
# @result.push(line.chomp.split(" ")[0])
|
42
|
+
|
43
|
+
}
|
44
|
+
|
45
|
+
@resultfile.close(true)
|
46
|
+
@tmp.close(true)
|
47
|
+
return @result
|
48
|
+
# puts $?
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
# result=Cseg.segment("���?�z??�܁C���ꊼ�k??�I??��")
|
53
|
+
# print result
|
metadata
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: cseg
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- gyorou
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2014-02-13 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: ! '"a chinese segmentation tool using CRF"'
|
15
|
+
email:
|
16
|
+
- gyorou@tjjtds.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- .gitignore
|
22
|
+
- LICENSE.txt
|
23
|
+
- README.md
|
24
|
+
- Gemfile
|
25
|
+
- data/pkumodle.data
|
26
|
+
- lib/cseg/version.rb
|
27
|
+
- lib/cseg.rb
|
28
|
+
- cseg.gemspec
|
29
|
+
- Rakefile
|
30
|
+
homepage: ''
|
31
|
+
licenses: []
|
32
|
+
post_install_message:
|
33
|
+
rdoc_options: []
|
34
|
+
require_paths:
|
35
|
+
- lib
|
36
|
+
- data
|
37
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
38
|
+
none: false
|
39
|
+
requirements:
|
40
|
+
- - ! '>='
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '0'
|
43
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
44
|
+
none: false
|
45
|
+
requirements:
|
46
|
+
- - ! '>='
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
version: '0'
|
49
|
+
requirements: []
|
50
|
+
rubyforge_project:
|
51
|
+
rubygems_version: 1.8.24
|
52
|
+
signing_key:
|
53
|
+
specification_version: 3
|
54
|
+
summary: ! '""'
|
55
|
+
test_files: []
|