niku-yma4r 0.0.1
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/ChangeLog +4 -0
- data/README +29 -0
- data/Rakefile +144 -0
- data/lib/yma4r.rb +82 -0
- data/lib/yma_parser.rb +39 -0
- data/test/test_helper.rb +3 -0
- data/test/yma4r_test.rb +5 -0
- metadata +79 -0
data/ChangeLog
ADDED
data/README
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
|
2
|
+
= yma4r
|
3
|
+
|
4
|
+
|
5
|
+
== Description
|
6
|
+
|
7
|
+
|
8
|
+
== Installation
|
9
|
+
|
10
|
+
=== Archive Installation
|
11
|
+
|
12
|
+
rake install
|
13
|
+
|
14
|
+
=== Gem Installation
|
15
|
+
|
16
|
+
gem install yma4r
|
17
|
+
|
18
|
+
|
19
|
+
== Features/Problems
|
20
|
+
|
21
|
+
|
22
|
+
== Synopsis
|
23
|
+
|
24
|
+
|
25
|
+
== Copyright
|
26
|
+
|
27
|
+
Author:: niku <niku@>
|
28
|
+
Copyright:: Copyright (c) 2008 niku
|
29
|
+
License::
|
data/Rakefile
ADDED
@@ -0,0 +1,144 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
require 'rake/clean'
|
4
|
+
require 'rake/testtask'
|
5
|
+
require 'rake/packagetask'
|
6
|
+
require 'rake/gempackagetask'
|
7
|
+
require 'rake/rdoctask'
|
8
|
+
require 'rake/contrib/rubyforgepublisher'
|
9
|
+
require 'rake/contrib/sshpublisher'
|
10
|
+
require 'fileutils'
|
11
|
+
require 'lib/yma4r'
|
12
|
+
include FileUtils
|
13
|
+
|
14
|
+
NAME = "yma4r"
|
15
|
+
AUTHOR = "niku"
|
16
|
+
EMAIL = "niku@niku.name"
|
17
|
+
DESCRIPTION = "yma4r is Yahoo Morphological Analyzer wrapper For Ruby"
|
18
|
+
RUBYFORGE_PROJECT = "yma4r"
|
19
|
+
HOMEPATH = "http://github.com/#{AUTHOR}/#{RUBYFORGE_PROJECT}"
|
20
|
+
BIN_FILES = %w( )
|
21
|
+
|
22
|
+
VERS = Yma4r::VERSION
|
23
|
+
REV = File.read(".svn/entries")[/committed-rev="(d+)"/, 1] rescue nil
|
24
|
+
CLEAN.include ['**/.*.sw?', '*.gem', '.config']
|
25
|
+
RDOC_OPTS = [
|
26
|
+
'--title', "#{NAME} documentation",
|
27
|
+
"--charset", "utf-8",
|
28
|
+
"--opname", "index.html",
|
29
|
+
"--line-numbers",
|
30
|
+
"--main", "README",
|
31
|
+
"--inline-source",
|
32
|
+
]
|
33
|
+
|
34
|
+
task :default => [:test]
|
35
|
+
task :package => [:clean]
|
36
|
+
|
37
|
+
Rake::TestTask.new("test") do |t|
|
38
|
+
t.libs << "test"
|
39
|
+
t.pattern = "test/**/*_test.rb"
|
40
|
+
t.verbose = true
|
41
|
+
end
|
42
|
+
|
43
|
+
spec = Gem::Specification.new do |s|
|
44
|
+
s.name = NAME
|
45
|
+
s.version = VERS
|
46
|
+
s.platform = Gem::Platform::RUBY
|
47
|
+
s.has_rdoc = true
|
48
|
+
s.extra_rdoc_files = ["README", "ChangeLog"]
|
49
|
+
s.rdoc_options += RDOC_OPTS + ['--exclude', '^(examples|extras)/']
|
50
|
+
s.summary = DESCRIPTION
|
51
|
+
s.description = DESCRIPTION
|
52
|
+
s.author = AUTHOR
|
53
|
+
s.email = EMAIL
|
54
|
+
s.homepage = HOMEPATH
|
55
|
+
s.executables = BIN_FILES
|
56
|
+
s.rubyforge_project = RUBYFORGE_PROJECT
|
57
|
+
s.bindir = "bin"
|
58
|
+
s.require_path = "lib"
|
59
|
+
#s.autorequire = ""
|
60
|
+
s.test_files = Dir["test/*_test.rb"]
|
61
|
+
|
62
|
+
s.add_dependency('classx', '>=0.0.5')
|
63
|
+
#s.required_ruby_version = '>= 1.8.2'
|
64
|
+
|
65
|
+
s.files = %w(README ChangeLog Rakefile) +
|
66
|
+
Dir.glob("{bin,doc,test,lib,templates,generator,extras,website,script}/**/*") +
|
67
|
+
Dir.glob("ext/**/*.{h,c,rb}") +
|
68
|
+
Dir.glob("examples/**/*.rb") +
|
69
|
+
Dir.glob("tools/*.rb") +
|
70
|
+
Dir.glob("rails/*.rb")
|
71
|
+
|
72
|
+
s.extensions = FileList["ext/**/extconf.rb"].to_a
|
73
|
+
end
|
74
|
+
|
75
|
+
Rake::GemPackageTask.new(spec) do |p|
|
76
|
+
p.need_tar = true
|
77
|
+
p.gem_spec = spec
|
78
|
+
end
|
79
|
+
|
80
|
+
task :install do
|
81
|
+
name = "#{NAME}-#{VERS}.gem"
|
82
|
+
sh %{rake package}
|
83
|
+
sh %{sudo gem install pkg/#{name}}
|
84
|
+
end
|
85
|
+
|
86
|
+
task :uninstall => [:clean] do
|
87
|
+
sh %{sudo gem uninstall #{NAME}}
|
88
|
+
end
|
89
|
+
|
90
|
+
|
91
|
+
Rake::RDocTask.new do |rdoc|
|
92
|
+
rdoc.rdoc_dir = 'html'
|
93
|
+
rdoc.options += RDOC_OPTS
|
94
|
+
rdoc.template = "resh"
|
95
|
+
#rdoc.template = "#{ENV['template']}.rb" if ENV['template']
|
96
|
+
if ENV['DOC_FILES']
|
97
|
+
rdoc.rdoc_files.include(ENV['DOC_FILES'].split(/,\s*/))
|
98
|
+
else
|
99
|
+
rdoc.rdoc_files.include('README', 'ChangeLog')
|
100
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
101
|
+
rdoc.rdoc_files.include('ext/**/*.c')
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
desc "Publish to RubyForge"
|
106
|
+
task :rubyforge => [:rdoc, :package] do
|
107
|
+
require 'rubyforge'
|
108
|
+
Rake::RubyForgePublisher.new(RUBYFORGE_PROJECT, 'niku').upload
|
109
|
+
end
|
110
|
+
|
111
|
+
desc 'Package and upload the release to rubyforge.'
|
112
|
+
task :release => [:clean, :package] do |t|
|
113
|
+
v = ENV["VERSION"] or abort "Must supply VERSION=x.y.z"
|
114
|
+
abort "Versions don't match #{v} vs #{VERS}" unless v == VERS
|
115
|
+
pkg = "pkg/#{NAME}-#{VERS}"
|
116
|
+
|
117
|
+
require 'rubyforge'
|
118
|
+
rf = RubyForge.new.configure
|
119
|
+
puts "Logging in"
|
120
|
+
rf.login
|
121
|
+
|
122
|
+
c = rf.userconfig
|
123
|
+
# c["release_notes"] = description if description
|
124
|
+
# c["release_changes"] = changes if changes
|
125
|
+
c["preformatted"] = true
|
126
|
+
|
127
|
+
files = [
|
128
|
+
"#{pkg}.tgz",
|
129
|
+
"#{pkg}.gem"
|
130
|
+
].compact
|
131
|
+
|
132
|
+
puts "Releasing #{NAME} v. #{VERS}"
|
133
|
+
rf.add_release RUBYFORGE_PROJECT, NAME, VERS, *files
|
134
|
+
end
|
135
|
+
|
136
|
+
desc 'Show information about the gem.'
|
137
|
+
task :debug_gem do
|
138
|
+
puts spec.to_ruby
|
139
|
+
end
|
140
|
+
|
141
|
+
desc 'Update gem spec'
|
142
|
+
task :gemspec do
|
143
|
+
open("#{NAME}.gemspec", 'w').write spec.to_ruby
|
144
|
+
end
|
data/lib/yma4r.rb
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'rubygems'
|
3
|
+
require 'classx'
|
4
|
+
class Yma4r
|
5
|
+
include ClassX
|
6
|
+
extend ClassX::Commandable
|
7
|
+
require 'net/http'
|
8
|
+
|
9
|
+
has :appid,
|
10
|
+
:desc => 'アプリケーションID。'
|
11
|
+
|
12
|
+
has :sentence,
|
13
|
+
:desc => '解析対象のテキストです。',
|
14
|
+
:writable => true,
|
15
|
+
:optional => true
|
16
|
+
|
17
|
+
has :results,
|
18
|
+
:desc => '解析結果の種類をコンマで区切って指定します。',
|
19
|
+
:default => proc { 'ma' },
|
20
|
+
:validate => proc { |val| val.is_a? 'ma' || 'uniq' },
|
21
|
+
:writable => true,
|
22
|
+
:optional => true
|
23
|
+
|
24
|
+
has :response,
|
25
|
+
:desc => 'ma_response, uniq_response のデフォルト設定です。word に返される形態素情報をコンマで区切って指定します。無指定の場合は "surface,reading,pos" になります。',
|
26
|
+
:default => proc { 'surface,reading,pos' },
|
27
|
+
:validate => proc { |val| val.is_a? 'surface' || 'reading' || 'pos' || 'baseform' || 'feature' },
|
28
|
+
:optional => true
|
29
|
+
|
30
|
+
has :filter,
|
31
|
+
:desc => 'ma_filter, uniq_filter のデフォルト設定です。解析結果として出力する品詞番号を "|" で区切って指定します。',
|
32
|
+
:default => proc { '1|2|3|4|5|6|7|8|9|10|11|12|13' },
|
33
|
+
:optional => true
|
34
|
+
|
35
|
+
has :ma_response,
|
36
|
+
:desc => 'ma_result 内の word に返される形態素情報をコンマで区切って指定します。無指定の場合 response の指定が用いられます。',
|
37
|
+
:default => nil,
|
38
|
+
:optional => true
|
39
|
+
|
40
|
+
has :ma_filter,
|
41
|
+
:desc => 'ma_result 内に解析結果として出力する品詞番号を "|" で区切って指定します。無指定の場合 filter の指定が用いられます。',
|
42
|
+
:default => nil,
|
43
|
+
:optional => true
|
44
|
+
|
45
|
+
has :uniq_response,
|
46
|
+
:desc => 'uniq_result 内の word に返される形態素情報をコンマで区切って指定します。無指定の場合 response の指定が用いられます。',
|
47
|
+
:default => nil,
|
48
|
+
:optional => true
|
49
|
+
|
50
|
+
has :uniq_filter,
|
51
|
+
:desc => 'uniq_result 内に解析結果として出力する品詞番号を "|" で区切って指定します。無指定の場合 filter の指定が用いられます。',
|
52
|
+
:default => nil,
|
53
|
+
:optional => true
|
54
|
+
|
55
|
+
has :uniq_by_baseform,
|
56
|
+
:desc => 'このパラメータが true ならば、基本形の同一性により、uniq_result の結果を求めます。',
|
57
|
+
:default => proc { false },
|
58
|
+
:optional => true
|
59
|
+
|
60
|
+
def analyse
|
61
|
+
YmaParser.new(request)
|
62
|
+
end
|
63
|
+
|
64
|
+
def request
|
65
|
+
host = 'jlp.yahooapis.jp'
|
66
|
+
path = '/MAService/V1/parse'
|
67
|
+
Net::HTTP.start(host){ |http| http.post(path, query_string) }.body
|
68
|
+
end
|
69
|
+
|
70
|
+
def query_hash
|
71
|
+
keys = ['appid', 'sentence', 'results', 'response', 'filter', 'ma_response', 'ma_filter', 'uniq_response', 'uniq_filter', 'uniq_by_baseform']
|
72
|
+
vals = [appid, sentence, results , response, filter, ma_response, ma_filter, uniq_response, uniq_filter, uniq_by_baseform]
|
73
|
+
alist = keys.zip(vals)
|
74
|
+
Hash[*alist.flatten]
|
75
|
+
end
|
76
|
+
|
77
|
+
def query_string
|
78
|
+
query_hash.map{ |key,val| "#{URI.encode(key)}=#{URI.encode(val)}" if val }.compact.join('&')
|
79
|
+
end
|
80
|
+
|
81
|
+
private :request, :query_hash, :query_string
|
82
|
+
end
|
data/lib/yma_parser.rb
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
class YmaParser
|
2
|
+
require 'rexml/document'
|
3
|
+
|
4
|
+
attr_reader :xml
|
5
|
+
|
6
|
+
class YmaResult
|
7
|
+
def initialize(set)
|
8
|
+
@set = set
|
9
|
+
end
|
10
|
+
|
11
|
+
def surface
|
12
|
+
@set.elements['surface'].text
|
13
|
+
end
|
14
|
+
|
15
|
+
def reading
|
16
|
+
@set.elements['reading'].text
|
17
|
+
end
|
18
|
+
|
19
|
+
def pos
|
20
|
+
@set.elements['pos'].text
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def initialize(xml)
|
25
|
+
@xml = REXML::Document.new(xml)
|
26
|
+
end
|
27
|
+
|
28
|
+
def total_count
|
29
|
+
@xml.elements['//total_count'].text.to_i
|
30
|
+
end
|
31
|
+
|
32
|
+
def filtered_count
|
33
|
+
@xml.elements['//filtered_count'].text.to_i
|
34
|
+
end
|
35
|
+
|
36
|
+
def word_list
|
37
|
+
@xml.elements['//word_list'].map { |set| YmaResult.new(set) }
|
38
|
+
end
|
39
|
+
end
|
data/test/test_helper.rb
ADDED
data/test/yma4r_test.rb
ADDED
metadata
ADDED
@@ -0,0 +1,79 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: niku-yma4r
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- niku
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2008-11-13 00:00:00 -08:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: classx
|
17
|
+
version_requirement:
|
18
|
+
version_requirements: !ruby/object:Gem::Requirement
|
19
|
+
requirements:
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 0.0.5
|
23
|
+
version:
|
24
|
+
description: yma4r is Yahoo Morphological Analyzer wrapper For Ruby
|
25
|
+
email: niku@niku.name
|
26
|
+
executables: []
|
27
|
+
|
28
|
+
extensions: []
|
29
|
+
|
30
|
+
extra_rdoc_files:
|
31
|
+
- README
|
32
|
+
- ChangeLog
|
33
|
+
files:
|
34
|
+
- README
|
35
|
+
- ChangeLog
|
36
|
+
- Rakefile
|
37
|
+
- test/test_helper.rb
|
38
|
+
- test/yma4r_test.rb
|
39
|
+
- lib/yma4r.rb
|
40
|
+
- lib/yma_parser.rb
|
41
|
+
has_rdoc: true
|
42
|
+
homepage: http://github.com/niku/yma4r
|
43
|
+
post_install_message:
|
44
|
+
rdoc_options:
|
45
|
+
- --title
|
46
|
+
- yma4r documentation
|
47
|
+
- --charset
|
48
|
+
- utf-8
|
49
|
+
- --opname
|
50
|
+
- index.html
|
51
|
+
- --line-numbers
|
52
|
+
- --main
|
53
|
+
- README
|
54
|
+
- --inline-source
|
55
|
+
- --exclude
|
56
|
+
- ^(examples|extras)/
|
57
|
+
require_paths:
|
58
|
+
- lib
|
59
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
60
|
+
requirements:
|
61
|
+
- - ">="
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
version: "0"
|
64
|
+
version:
|
65
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
66
|
+
requirements:
|
67
|
+
- - ">="
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: "0"
|
70
|
+
version:
|
71
|
+
requirements: []
|
72
|
+
|
73
|
+
rubyforge_project: yma4r
|
74
|
+
rubygems_version: 1.2.0
|
75
|
+
signing_key:
|
76
|
+
specification_version: 2
|
77
|
+
summary: yma4r is Yahoo Morphological Analyzer wrapper For Ruby
|
78
|
+
test_files:
|
79
|
+
- test/yma4r_test.rb
|