rmmseg-cpp-traditional 0.0.2
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/.gitignore +17 -0
- data/Gemfile +4 -0
- data/History.txt +21 -0
- data/LICENSE.txt +22 -0
- data/Manifest.txt +43 -0
- data/README +111 -0
- data/README.md +29 -0
- data/Rakefile +19 -0
- data/bin/rmmseg +63 -0
- data/data/chars.dic +12638 -0
- data/data/words.dic +120308 -0
- data/ext/rmmseg/algor.cpp +222 -0
- data/ext/rmmseg/algor.h +80 -0
- data/ext/rmmseg/chunk.h +59 -0
- data/ext/rmmseg/dict.cpp +230 -0
- data/ext/rmmseg/dict.h +34 -0
- data/ext/rmmseg/extconf.rb +17 -0
- data/ext/rmmseg/memory.cpp +9 -0
- data/ext/rmmseg/memory.h +43 -0
- data/ext/rmmseg/rmmseg.cpp +263 -0
- data/ext/rmmseg/rules.h +86 -0
- data/ext/rmmseg/token.h +19 -0
- data/ext/rmmseg/word.h +44 -0
- data/lib/rmmseg/dictionary.rb +59 -0
- data/lib/rmmseg/ferret.rb +64 -0
- data/lib/rmmseg-cpp-traditional/version.rb +7 -0
- data/lib/rmmseg-cpp-traditional.rb +9 -0
- data/lib/rmmseg.rb +3 -0
- data/misc/convert.rb +114 -0
- data/misc/ferret_example.rb +59 -0
- data/misc/homepage.erb +196 -0
- data/misc/homepage.html +1212 -0
- data/rmmseg-cpp-traditional.gemspec +19 -0
- data/spec/rmmseg_spec.rb +8 -0
- data/spec/spec_helper.rb +17 -0
- data/tasks/ann.rake +81 -0
- data/tasks/bones.rake +21 -0
- data/tasks/gem.rake +126 -0
- data/tasks/git.rake +41 -0
- data/tasks/homepage.rake +15 -0
- data/tasks/manifest.rake +49 -0
- data/tasks/notes.rake +28 -0
- data/tasks/post_load.rake +39 -0
- data/tasks/rdoc.rake +51 -0
- data/tasks/rubyforge.rake +58 -0
- data/tasks/setup.rb +268 -0
- data/tasks/spec.rake +55 -0
- data/tasks/svn.rake +48 -0
- data/tasks/test.rake +38 -0
- data/test/test_rmmseg.rb +0 -0
- metadata +116 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/History.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
== 0.2.9 / 2011-09-10
|
2
|
+
|
3
|
+
* Fix GC-related bugs in Ruby C extension.
|
4
|
+
|
5
|
+
== 0.2.8 / 2010-03-22
|
6
|
+
|
7
|
+
* Minor release, fixed building bugs in Ruby 1.9.
|
8
|
+
|
9
|
+
== 0.2.7 / 2008-09-17
|
10
|
+
|
11
|
+
* Fix various stupid bugs (typo) that cause problems under MacOSX.
|
12
|
+
|
13
|
+
== 0.2.6 / 2008-08-14
|
14
|
+
|
15
|
+
* Fix the problem that hang up when required (OS: MacOSX-Leopard)
|
16
|
+
|
17
|
+
== 0.2.5 / 2008-06-07
|
18
|
+
|
19
|
+
* Created homepage on Rubyforge.
|
20
|
+
* Gem can be installed directly from Rubyforge now.
|
21
|
+
* Added rdoc for native extensions.
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 MichaelHsu
|
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/Manifest.txt
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
History.txt
|
2
|
+
Manifest.txt
|
3
|
+
README
|
4
|
+
Rakefile
|
5
|
+
bin/rmmseg
|
6
|
+
data/chars.dic
|
7
|
+
data/words.dic
|
8
|
+
ext/rmmseg/algor.cpp
|
9
|
+
ext/rmmseg/algor.h
|
10
|
+
ext/rmmseg/chunk.h
|
11
|
+
ext/rmmseg/dict.cpp
|
12
|
+
ext/rmmseg/dict.h
|
13
|
+
ext/rmmseg/extconf.rb
|
14
|
+
ext/rmmseg/memory.cpp
|
15
|
+
ext/rmmseg/memory.h
|
16
|
+
ext/rmmseg/rmmseg.cpp
|
17
|
+
ext/rmmseg/rules.h
|
18
|
+
ext/rmmseg/token.h
|
19
|
+
ext/rmmseg/word.h
|
20
|
+
lib/rmmseg.rb
|
21
|
+
lib/rmmseg/dictionary.rb
|
22
|
+
lib/rmmseg/ferret.rb
|
23
|
+
misc/convert.rb
|
24
|
+
misc/ferret_example.rb
|
25
|
+
misc/homepage.erb
|
26
|
+
misc/homepage.html
|
27
|
+
spec/rmmseg_spec.rb
|
28
|
+
spec/spec_helper.rb
|
29
|
+
tasks/ann.rake
|
30
|
+
tasks/bones.rake
|
31
|
+
tasks/gem.rake
|
32
|
+
tasks/git.rake
|
33
|
+
tasks/homepage.rake
|
34
|
+
tasks/manifest.rake
|
35
|
+
tasks/notes.rake
|
36
|
+
tasks/post_load.rake
|
37
|
+
tasks/rdoc.rake
|
38
|
+
tasks/rubyforge.rake
|
39
|
+
tasks/setup.rb
|
40
|
+
tasks/spec.rake
|
41
|
+
tasks/svn.rake
|
42
|
+
tasks/test.rake
|
43
|
+
test/test_rmmseg.rb
|
data/README
ADDED
@@ -0,0 +1,111 @@
|
|
1
|
+
rmmseg-cpp
|
2
|
+
by pluskid
|
3
|
+
http://rmmseg-cpp.rubyforge.org
|
4
|
+
|
5
|
+
== DESCRIPTION:
|
6
|
+
|
7
|
+
rmmseg-cpp is a high performance Chinese word segmentation utility for
|
8
|
+
Ruby. It features full "Ferret":http://ferret.davebalmain.com/ integration
|
9
|
+
as well as support for normal Ruby program usage.
|
10
|
+
|
11
|
+
rmmseg-cpp is a re-written of the original
|
12
|
+
RMMSeg(http://rmmseg.rubyforge.org/) gem in C++. RMMSeg is written
|
13
|
+
in pure Ruby. Though I tried hard to tweak RMMSeg, it just consumes
|
14
|
+
lots of memory and the segmenting process is rather slow.
|
15
|
+
|
16
|
+
The interface is almost identical to RMMSeg but the performance is
|
17
|
+
much better. This gem is always preferable in production
|
18
|
+
use. However, if you want to understand how the MMSEG segmenting
|
19
|
+
algorithm works, the source code of RMMSeg is a better choice than
|
20
|
+
this.
|
21
|
+
|
22
|
+
== FEATURES/PROBLEMS:
|
23
|
+
|
24
|
+
* Runs fast and the memory consumption is small.
|
25
|
+
* Support user customized dictionaries.
|
26
|
+
* Easy Ferret integration.
|
27
|
+
|
28
|
+
== SYNOPSIS:
|
29
|
+
|
30
|
+
=== A simple script
|
31
|
+
|
32
|
+
rmmseg-cpp provides a simple script, which can read the text from
|
33
|
+
standard input and print the segmented result to standard output. Try
|
34
|
+
<tt>rmmseg -h</tt> for help on the options.
|
35
|
+
|
36
|
+
=== In a normal Ruby program
|
37
|
+
|
38
|
+
To use rmmseg-cpp in normal Ruby program, first load the package and
|
39
|
+
init by loading the dictionaries:
|
40
|
+
|
41
|
+
require 'rubygems'
|
42
|
+
require 'rmmseg'
|
43
|
+
|
44
|
+
RMMSeg::Dictionary.load_dictionaries
|
45
|
+
|
46
|
+
If you want to add customized dictionaries, append them to
|
47
|
+
+RMMSeg::Dictionary.dictionaries+ before calling +load_dictionaries+.
|
48
|
+
The formats of chars.dic and words.dic are NOT the same:
|
49
|
+
|
50
|
+
* For chars.dic, each line contains freq, a space, and then the character
|
51
|
+
* For words.dic, each line contains length, a space, and then the word.
|
52
|
+
|
53
|
+
Note length mean the length of the word, i.e. the number of characters
|
54
|
+
of the word, not number of bytes. WARNING: there should be a newline at
|
55
|
+
the end of every dictionary file.
|
56
|
+
|
57
|
+
Then create a +Algorithm+ object and call +next_token+ until got a
|
58
|
+
+nil+:
|
59
|
+
|
60
|
+
algor = RMMSeg::Algorithm.new(text)
|
61
|
+
loop do
|
62
|
+
tok = algor.next_token
|
63
|
+
break if tok.nil?
|
64
|
+
puts "#{tok.text} [#{tok.start}..#{tok.end}]"
|
65
|
+
end
|
66
|
+
|
67
|
+
=== With Ferret
|
68
|
+
|
69
|
+
To use rmmseg-cpp with Ferret, just use the analyzer provided:
|
70
|
+
|
71
|
+
analyzer = RMMSeg::Ferret::Analyzer.new { |tokenizer|
|
72
|
+
Ferret::Analysis::LowerCaseFilter.new(tokenizer)
|
73
|
+
}
|
74
|
+
|
75
|
+
index = Ferret::Index::Index.new(:analyzer => analyzer)
|
76
|
+
|
77
|
+
See <tt>misc/ferret_example.rb</tt> for a complete example.
|
78
|
+
|
79
|
+
== REQUIREMENTS:
|
80
|
+
|
81
|
+
* ruby 1.8.x
|
82
|
+
* g++
|
83
|
+
|
84
|
+
== INSTALL:
|
85
|
+
|
86
|
+
* sudo gem install rmmseg-cpp
|
87
|
+
|
88
|
+
== LICENSE:
|
89
|
+
|
90
|
+
(The MIT License)
|
91
|
+
|
92
|
+
Copyright (c) 2008 FIXME (different license?)
|
93
|
+
|
94
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
95
|
+
a copy of this software and associated documentation files (the
|
96
|
+
'Software'), to deal in the Software without restriction, including
|
97
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
98
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
99
|
+
permit persons to whom the Software is furnished to do so, subject to
|
100
|
+
the following conditions:
|
101
|
+
|
102
|
+
The above copyright notice and this permission notice shall be
|
103
|
+
included in all copies or substantial portions of the Software.
|
104
|
+
|
105
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
106
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
107
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
108
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
109
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
110
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
111
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# Rmmseg::Cpp::Traditional
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'rmmseg-cpp-traditional'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install rmmseg-cpp-traditional
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
# -*- Ruby -*-
|
2
|
+
|
3
|
+
load 'tasks/setup.rb'
|
4
|
+
|
5
|
+
ensure_in_path 'lib'
|
6
|
+
require 'rmmseg'
|
7
|
+
|
8
|
+
task :default => 'spec:run'
|
9
|
+
|
10
|
+
PROJ.name = 'rmmseg-cpp'
|
11
|
+
PROJ.version = '0.2.9'
|
12
|
+
PROJ.authors = 'pluskid'
|
13
|
+
PROJ.email = 'pluskid@gmail.com'
|
14
|
+
PROJ.url = 'http://rmmseg-cpp.rubyforge.org'
|
15
|
+
PROJ.rubyforge.name = 'rmmseg-cpp'
|
16
|
+
|
17
|
+
PROJ.spec.opts << '--color'
|
18
|
+
|
19
|
+
# EOF
|
data/bin/rmmseg
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require File.expand_path(
|
4
|
+
File.join(File.dirname(__FILE__), '..', 'lib', 'rmmseg'))
|
5
|
+
|
6
|
+
require 'getoptlong'
|
7
|
+
|
8
|
+
def print_usage
|
9
|
+
puts <<EOF
|
10
|
+
#{__FILE__} Segment Chinese text. Read from stdin and print to stdout.
|
11
|
+
|
12
|
+
Options:
|
13
|
+
-h
|
14
|
+
--help Print this message
|
15
|
+
|
16
|
+
-s
|
17
|
+
--separator Select the separator of the segmented text. Default is
|
18
|
+
space.
|
19
|
+
EOF
|
20
|
+
exit 0
|
21
|
+
end
|
22
|
+
|
23
|
+
separator = " "
|
24
|
+
|
25
|
+
optparser = GetoptLong.new
|
26
|
+
optparser.set_options(["-s", "--separator", GetoptLong::REQUIRED_ARGUMENT],
|
27
|
+
["-h", "--help", GetoptLong::NO_ARGUMENT])
|
28
|
+
|
29
|
+
loop do
|
30
|
+
begin
|
31
|
+
opt, arg = optparser.get
|
32
|
+
break if not opt
|
33
|
+
|
34
|
+
case opt
|
35
|
+
when "-h"
|
36
|
+
print_usage
|
37
|
+
|
38
|
+
when "-s"
|
39
|
+
separator = arg
|
40
|
+
end
|
41
|
+
|
42
|
+
rescue => err
|
43
|
+
puts err
|
44
|
+
exit 1
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
RMMSeg::Dictionary.load_dictionaries
|
49
|
+
algor = RMMSeg::Algorithm.new(STDIN.read)
|
50
|
+
tok = algor.next_token
|
51
|
+
unless tok.nil?
|
52
|
+
print tok.text
|
53
|
+
|
54
|
+
loop do
|
55
|
+
tok = algor.next_token
|
56
|
+
break if tok.nil?
|
57
|
+
print separator
|
58
|
+
print tok.text
|
59
|
+
end
|
60
|
+
puts
|
61
|
+
end
|
62
|
+
|
63
|
+
# EOF
|