bimyou_segmenter 1.1.1 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/bimyou_segmenter +6 -2
- data/lib/bimyou_segmenter/aozora_model.rb +11 -4
- data/lib/bimyou_segmenter/version.rb +1 -1
- data/test/bimyou_segmenter_test.rb +12 -0
- metadata +34 -49
data/bin/bimyou_segmenter
CHANGED
@@ -68,7 +68,9 @@ if (ARGV.size == 0)
|
|
68
68
|
s = NKF.nkf(nkf_option, s)
|
69
69
|
end
|
70
70
|
begin
|
71
|
-
|
71
|
+
unless (s.empty?)
|
72
|
+
puts s
|
73
|
+
end
|
72
74
|
rescue Errno::EPIPE
|
73
75
|
exit 0
|
74
76
|
end
|
@@ -84,7 +86,9 @@ else
|
|
84
86
|
if (nkf_option)
|
85
87
|
s = NKF.nkf(nkf_option, s)
|
86
88
|
end
|
87
|
-
|
89
|
+
unless (s.empty?)
|
90
|
+
puts s
|
91
|
+
end
|
88
92
|
end
|
89
93
|
end
|
90
94
|
end
|
@@ -16,6 +16,7 @@ module BimyouSegmenter
|
|
16
16
|
end
|
17
17
|
|
18
18
|
white_space = options[:white_space].nil? ? false : options[:white_space]
|
19
|
+
symbol = options[:symbol].nil? ? true : options[:symbol]
|
19
20
|
|
20
21
|
wakachi = []
|
21
22
|
text_chars = text.chars.to_a
|
@@ -155,17 +156,23 @@ module BimyouSegmenter
|
|
155
156
|
end
|
156
157
|
end
|
157
158
|
wakachi << word
|
158
|
-
|
159
|
-
wakachi
|
160
|
-
else
|
161
|
-
wakachi.reject{|v| v.match(WHITE_SPACE) }
|
159
|
+
unless (white_space)
|
160
|
+
wakachi = wakachi.reject{|v| v.match(WHITE_SPACE) }
|
162
161
|
end
|
162
|
+
unless (symbol)
|
163
|
+
wakachi = wakachi.reject{|v| v.match(SYMBOL) }
|
164
|
+
end
|
165
|
+
wakachi
|
163
166
|
end
|
164
167
|
|
165
168
|
private
|
166
169
|
KANJI = Regexp.new('[々〇ヵヶ' + [0x3400].pack('U') + '-' + [0x9FFF].pack('U') +
|
167
170
|
[0xF900].pack('U') + '-' + [0xFAFF].pack('U') +
|
168
171
|
[0x20000].pack('U') + '-' + [0x2FFFF].pack('U') + ']')
|
172
|
+
SYMBOL = Regexp.new('^[^々〇' + [0x3400].pack('U') + '-' + [0x9FFF].pack('U') +
|
173
|
+
[0xF900].pack('U') + '-' + [0xFAFF].pack('U') +
|
174
|
+
[0x20000].pack('U') + '-' + [0x2FFFF].pack('U') +
|
175
|
+
'\s ぁ-ゞァ-ヾa-zA-Za-zA-Z0-90-9]+$')
|
169
176
|
WHITE_SPACE = /[\s ]/
|
170
177
|
|
171
178
|
def self.char_types(chars)
|
@@ -33,6 +33,18 @@ class BimyouSegmenterTest < Test::Unit::TestCase
|
|
33
33
|
assert_equal tokens[2], "\r"
|
34
34
|
assert_equal tokens[3], "\n"
|
35
35
|
assert_equal tokens[4], " "
|
36
|
+
|
37
|
+
tokens = BimyouSegmenter.segment("「私はトマトです。」", :symbol => false)
|
38
|
+
assert_equal tokens.size, 4
|
39
|
+
assert_equal tokens[0], "私"
|
40
|
+
assert_equal tokens[1], "は"
|
41
|
+
assert_equal tokens[2], "トマト"
|
42
|
+
assert_equal tokens[3], "です"
|
43
|
+
|
44
|
+
tokens = BimyouSegmenter.segment("hello. world? = !", :symbol => false)
|
45
|
+
assert_equal tokens.size, 2
|
46
|
+
assert_equal tokens[0], "hello"
|
47
|
+
assert_equal tokens[1], "world"
|
36
48
|
|
37
49
|
assert_equal BimyouSegmenter.segment("").size, 0
|
38
50
|
assert_equal BimyouSegmenter.segment(nil).size, 0
|
metadata
CHANGED
@@ -1,44 +1,35 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: bimyou_segmenter
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
5
|
-
|
6
|
-
- 1
|
7
|
-
- 1
|
8
|
-
- 1
|
9
|
-
version: 1.1.1
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.2.0
|
5
|
+
prerelease:
|
10
6
|
platform: ruby
|
11
|
-
authors:
|
7
|
+
authors:
|
12
8
|
- nagadomi
|
13
9
|
autorequire:
|
14
10
|
bindir: bin
|
15
11
|
cert_chain: []
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
dependencies:
|
20
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2012-06-01 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
21
15
|
name: test-unit
|
22
|
-
|
23
|
-
|
24
|
-
requirements:
|
25
|
-
- -
|
26
|
-
- !ruby/object:Gem::Version
|
27
|
-
|
28
|
-
- 0
|
29
|
-
version: "0"
|
16
|
+
requirement: &5715420 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
30
22
|
type: :development
|
31
|
-
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *5715420
|
32
25
|
description: Japanese Word Segmenter
|
33
|
-
email:
|
26
|
+
email:
|
34
27
|
- nagadomi@nurs.or.jp
|
35
|
-
executables:
|
28
|
+
executables:
|
36
29
|
- bimyou_segmenter
|
37
30
|
extensions: []
|
38
|
-
|
39
31
|
extra_rdoc_files: []
|
40
|
-
|
41
|
-
files:
|
32
|
+
files:
|
42
33
|
- .gitignore
|
43
34
|
- Changelog
|
44
35
|
- Gemfile
|
@@ -52,36 +43,30 @@ files:
|
|
52
43
|
- lib/bimyou_segmenter/version.rb
|
53
44
|
- test/bimyou_segmenter_test.rb
|
54
45
|
- test/test_helper.rb
|
55
|
-
has_rdoc: true
|
56
46
|
homepage: http://github.com/nagadomi/bimyou_segmenter
|
57
47
|
licenses: []
|
58
|
-
|
59
48
|
post_install_message:
|
60
49
|
rdoc_options: []
|
61
|
-
|
62
|
-
require_paths:
|
50
|
+
require_paths:
|
63
51
|
- lib
|
64
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
requirements:
|
73
|
-
- -
|
74
|
-
- !ruby/object:Gem::Version
|
75
|
-
|
76
|
-
- 0
|
77
|
-
version: "0"
|
52
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
54
|
+
requirements:
|
55
|
+
- - ! '>='
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
version: '0'
|
58
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
59
|
+
none: false
|
60
|
+
requirements:
|
61
|
+
- - ! '>='
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
version: '0'
|
78
64
|
requirements: []
|
79
|
-
|
80
65
|
rubyforge_project:
|
81
|
-
rubygems_version: 1.
|
66
|
+
rubygems_version: 1.8.10
|
82
67
|
signing_key:
|
83
68
|
specification_version: 3
|
84
69
|
summary: Japanese Word Segmenter
|
85
|
-
test_files:
|
70
|
+
test_files:
|
86
71
|
- test/bimyou_segmenter_test.rb
|
87
72
|
- test/test_helper.rb
|