sekka 1.2.1 → 1.2.2
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.
- checksums.yaml +7 -0
- data/Rakefile +20 -11
- data/VERSION.yml +1 -1
- data/bin/sekka-server +14 -17
- data/emacs/sekka.el +1 -1
- data/lib/sekka/convert-jisyo.nnd +3 -1
- data/lib/sekka/sekkaversion.rb +2 -2
- data/test/sekka-dump-out-1.txt +1 -1
- metadata +28 -54
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7f2b64092011062870613c3906c9855418ca0e68
|
4
|
+
data.tar.gz: f2b131d6ff3d7b7f181a078fac541e03ac6d5b4c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b5091ad9ac65a240b45208acff8299269cfcf9210c7b95ccb92d61af5c52bc1cb1836201a9b7049c5c044011fcbae4840b5b20c5b140570456ee958de7ab1bc6
|
7
|
+
data.tar.gz: a782b597e4c870ca2cd3cf7deb32063b6183fe78d8cf0bc01ad54ceb5f2a2cb7905a9bc86ddbfefca0143944c3738a949ef5a89db46fe82583c873e7f251d5a9
|
data/Rakefile
CHANGED
@@ -52,7 +52,7 @@ begin
|
|
52
52
|
"sekka-server",
|
53
53
|
"sekka-benchmark",
|
54
54
|
"sekka-path"]
|
55
|
-
gemspec.required_ruby_version = '>= 1.9.
|
55
|
+
gemspec.required_ruby_version = '>= 1.9.2'
|
56
56
|
gemspec.add_dependency( "eventmachine" )
|
57
57
|
gemspec.add_dependency( "memcache-client" )
|
58
58
|
gemspec.add_dependency( "nendo", "= 0.6.4" )
|
@@ -70,7 +70,7 @@ end
|
|
70
70
|
|
71
71
|
task :compile do
|
72
72
|
# generate version.rb
|
73
|
-
dictVersion = "1.
|
73
|
+
dictVersion = "1.3.0"
|
74
74
|
vh = Jeweler::VersionHelper.new "."
|
75
75
|
open( "./lib/sekka/sekkaversion.rb", "w" ) {|f|
|
76
76
|
f.puts( "class SekkaVersion" )
|
@@ -144,7 +144,7 @@ task :test do
|
|
144
144
|
end
|
145
145
|
files.each {|filename|
|
146
146
|
nendopath = `which nendo`.chomp
|
147
|
-
sh sprintf( "
|
147
|
+
sh sprintf( "ruby -I ./lib %s %s", nendopath, filename )
|
148
148
|
}
|
149
149
|
sh "cat test.record"
|
150
150
|
end
|
@@ -204,18 +204,27 @@ task :dumpL do
|
|
204
204
|
end
|
205
205
|
|
206
206
|
|
207
|
-
|
208
|
-
|
209
|
-
|
210
|
-
sh "time ruby -I ./lib /usr/local/bin/nendo ./data/hiragana_phrase_in_webcorpus.nnd ./data/6gm-0000.txt | sort | uniq > /tmp/tmp.txt"
|
211
|
-
sh "time ruby -I ./lib /usr/local/bin/nendo ./data/writing_phrase_filter.nnd /tmp/tmp.txt | sort | uniq > ./data/SKK-JISYO.hiragana-phrase"
|
207
|
+
task :phrase => [ "/tmp/jawiki.txt.gz", "./data/wikipedia/jawiki.hiragana.txt" ] do
|
208
|
+
sh "sort ./data/wikipedia/jawiki.hiragana.txt | uniq -c | sort > ./data/wikipedia/ranking.txt"
|
209
|
+
sh "ruby -I ./lib /usr/local/bin/nendo ./data/hiragana_phrase_in_wikipedia2.nnd ./data/wikipedia/ranking.txt > ./data/SKK-JISYO.hiragana-phrase"
|
212
210
|
end
|
213
211
|
|
214
|
-
file "./data/
|
215
|
-
sh "
|
216
|
-
sh "
|
212
|
+
file "./data/wikipedia/jawiki.hiragana.txt" do
|
213
|
+
sh "zcat /tmp/jawiki.txt.gz | mecab --input-buffer-size=65536 -O wakati --output=/tmp/jawiki.wakati.txt"
|
214
|
+
sh "ruby -I ./lib /usr/local/bin/nendo ./data/hiragana_phrase_in_wikipedia.nnd /tmp/jawiki.wakati.txt > ./data/wikipedia/jawiki.hiragana.txt"
|
215
|
+
sh "rm -f /tmp/jawiki.wakati.txt"
|
217
216
|
end
|
218
217
|
|
218
|
+
file "/tmp/jawiki.txt.gz" do
|
219
|
+
sh "mkdir -p ./data/wikipedia/txt"
|
220
|
+
sh "wget http://dumps.wikimedia.org/jawiki/latest/jawiki-latest-pages-articles.xml.bz2 -O /tmp/jawiki-latest-pages-articles.xml.bz2"
|
221
|
+
sh "wp2txt --input-file /tmp/jawiki-latest-pages-articles.xml.bz2 --output-dir ./data/wikipedia/txt"
|
222
|
+
sh "cat ./data/wikipedia/txt/*.txt | gzip -c > /tmp/jawiki.txt.gz"
|
223
|
+
sh "rm -f ./data/wikipedia/txt/*.txt"
|
224
|
+
sh "rm -f /tmp/jawiki-latest-pages-articles.xml.bz2"
|
225
|
+
end
|
226
|
+
|
227
|
+
|
219
228
|
task :phrase2 => [ "./data/ipadic.all.utf8.txt" ] do
|
220
229
|
sh "time ruby -I ./lib /usr/local/bin/nendo ./data/hiragana_phrase_in_ipadic.nnd ./data/ipadic.all.utf8.txt | sort | uniq > ./data/SKK-JISYO.hiragana-phrase2"
|
221
230
|
end
|
data/VERSION.yml
CHANGED
data/bin/sekka-server
CHANGED
@@ -22,17 +22,19 @@ DICTTYPE = if ENV.has_key?( 'SEKKA_AZIK' )
|
|
22
22
|
"N"
|
23
23
|
end
|
24
24
|
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
25
|
+
DICTSIZE = if ENV.has_key?( 'SEKKA_LARGE' )
|
26
|
+
"LARGE"
|
27
|
+
else
|
28
|
+
"SMALL"
|
29
|
+
end
|
29
30
|
|
30
|
-
|
31
|
-
|
31
|
+
TC_OPTS = "#xmsiz=256m"
|
32
|
+
TC_FILE = DICTDIR + "/SEKKA-JISYO.#{DICTSIZE}.#{DICTTYPE}.tch" + TC_OPTS
|
33
|
+
TSVFILE = DICTDIR + "/SEKKA-JISYO.#{DICTSIZE}.#{DICTTYPE}.tsv"
|
34
|
+
SUMFILE = DICTDIR + "/SEKKA-JISYO.#{DICTSIZE}.#{DICTTYPE}.md5"
|
32
35
|
|
33
|
-
|
34
|
-
|
35
|
-
DICTDIR + "/SEKKA-JISYO.SMALL.#{DICTTYPE}.tch" + TC_OPTS ]
|
36
|
+
URLURL = DICTURL + "/SEKKA-JISYO.#{DICTSIZE}.#{DICTTYPE}.url"
|
37
|
+
SUMURL = DICTURL + "/SEKKA-JISYO.#{DICTSIZE}.#{DICTTYPE}.md5"
|
36
38
|
|
37
39
|
MEMCACHED = "localhost:11211" # memcahced
|
38
40
|
|
@@ -147,12 +149,9 @@ def main
|
|
147
149
|
|
148
150
|
case dictType
|
149
151
|
when :tokyocabinet
|
150
|
-
#
|
151
|
-
list = TC_FILE_LIST.select { |name| File.exist?( name ) }
|
152
|
-
|
153
|
-
# redisサーバーに辞書が投入済みか確認する
|
152
|
+
# TokyoCabinetに辞書が投入済みか確認する
|
154
153
|
ok = checkJisyoIsInstalled( dictType, TC_FILE )
|
155
|
-
|
154
|
+
unless ok
|
156
155
|
# tsvファイルをuploadする
|
157
156
|
STDERR.printf( "Info: Uploading...\n" )
|
158
157
|
cmd = sprintf( "sekka-jisyo restore %s %s", TSVFILE, TC_FILE )
|
@@ -160,10 +159,8 @@ def main
|
|
160
159
|
system( cmd )
|
161
160
|
end
|
162
161
|
STDERR.printf( "Info: [OK]\n" )
|
162
|
+
dictSource = TC_FILE
|
163
163
|
|
164
|
-
# 存在する.tchファイルの中で一番最初のファイルを使う。
|
165
|
-
list = TC_FILE_LIST.select { |name| File.exist?( name ) }
|
166
|
-
dictSource = list[0]
|
167
164
|
when :redis
|
168
165
|
# redisサーバーに辞書が投入済みか確認する
|
169
166
|
ok = checkJisyoIsInstalled( dictType, dictSource )
|
data/emacs/sekka.el
CHANGED
data/lib/sekka/convert-jisyo.nnd
CHANGED
@@ -86,11 +86,13 @@
|
|
86
86
|
|
87
87
|
|
88
88
|
(define (convert-skk-jisyo-f f)
|
89
|
+
(define progressbar-format "%E |%B| %p%% %t")
|
89
90
|
(let1 progress (ProgressBar.create (alist->hash-table
|
90
91
|
`(
|
91
92
|
[title . "convert "]
|
92
93
|
[total . ,(file-length f)]
|
93
|
-
[output . ,STDERR]
|
94
|
+
[output . ,STDERR]
|
95
|
+
[format . ,progressbar-format])))
|
94
96
|
(define (gen-sekka-entries line)
|
95
97
|
(progress.increment)
|
96
98
|
|
data/lib/sekka/sekkaversion.rb
CHANGED
data/test/sekka-dump-out-1.txt
CHANGED
metadata
CHANGED
@@ -1,52 +1,46 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sekka
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.2.
|
5
|
-
prerelease:
|
4
|
+
version: 1.2.2
|
6
5
|
platform: ruby
|
7
6
|
authors:
|
8
7
|
- Kiyoka Nishiyama
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
date: 2013-03-
|
11
|
+
date: 2013-03-24 00:00:00.000000000 Z
|
13
12
|
dependencies:
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
14
|
name: eventmachine
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
17
|
-
none: false
|
18
16
|
requirements:
|
19
|
-
- -
|
17
|
+
- - '>='
|
20
18
|
- !ruby/object:Gem::Version
|
21
19
|
version: '0'
|
22
20
|
type: :runtime
|
23
21
|
prerelease: false
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
25
|
-
none: false
|
26
23
|
requirements:
|
27
|
-
- -
|
24
|
+
- - '>='
|
28
25
|
- !ruby/object:Gem::Version
|
29
26
|
version: '0'
|
30
27
|
- !ruby/object:Gem::Dependency
|
31
28
|
name: memcache-client
|
32
29
|
requirement: !ruby/object:Gem::Requirement
|
33
|
-
none: false
|
34
30
|
requirements:
|
35
|
-
- -
|
31
|
+
- - '>='
|
36
32
|
- !ruby/object:Gem::Version
|
37
33
|
version: '0'
|
38
34
|
type: :runtime
|
39
35
|
prerelease: false
|
40
36
|
version_requirements: !ruby/object:Gem::Requirement
|
41
|
-
none: false
|
42
37
|
requirements:
|
43
|
-
- -
|
38
|
+
- - '>='
|
44
39
|
- !ruby/object:Gem::Version
|
45
40
|
version: '0'
|
46
41
|
- !ruby/object:Gem::Dependency
|
47
42
|
name: nendo
|
48
43
|
requirement: !ruby/object:Gem::Requirement
|
49
|
-
none: false
|
50
44
|
requirements:
|
51
45
|
- - '='
|
52
46
|
- !ruby/object:Gem::Version
|
@@ -54,7 +48,6 @@ dependencies:
|
|
54
48
|
type: :runtime
|
55
49
|
prerelease: false
|
56
50
|
version_requirements: !ruby/object:Gem::Requirement
|
57
|
-
none: false
|
58
51
|
requirements:
|
59
52
|
- - '='
|
60
53
|
- !ruby/object:Gem::Version
|
@@ -62,87 +55,76 @@ dependencies:
|
|
62
55
|
- !ruby/object:Gem::Dependency
|
63
56
|
name: distributed-trie
|
64
57
|
requirement: !ruby/object:Gem::Requirement
|
65
|
-
none: false
|
66
58
|
requirements:
|
67
|
-
- -
|
59
|
+
- - '>='
|
68
60
|
- !ruby/object:Gem::Version
|
69
61
|
version: '0'
|
70
62
|
type: :runtime
|
71
63
|
prerelease: false
|
72
64
|
version_requirements: !ruby/object:Gem::Requirement
|
73
|
-
none: false
|
74
65
|
requirements:
|
75
|
-
- -
|
66
|
+
- - '>='
|
76
67
|
- !ruby/object:Gem::Version
|
77
68
|
version: '0'
|
78
69
|
- !ruby/object:Gem::Dependency
|
79
70
|
name: rack
|
80
71
|
requirement: !ruby/object:Gem::Requirement
|
81
|
-
none: false
|
82
72
|
requirements:
|
83
|
-
- -
|
73
|
+
- - '>='
|
84
74
|
- !ruby/object:Gem::Version
|
85
75
|
version: '0'
|
86
76
|
type: :runtime
|
87
77
|
prerelease: false
|
88
78
|
version_requirements: !ruby/object:Gem::Requirement
|
89
|
-
none: false
|
90
79
|
requirements:
|
91
|
-
- -
|
80
|
+
- - '>='
|
92
81
|
- !ruby/object:Gem::Version
|
93
82
|
version: '0'
|
94
83
|
- !ruby/object:Gem::Dependency
|
95
84
|
name: ruby-progressbar
|
96
85
|
requirement: !ruby/object:Gem::Requirement
|
97
|
-
none: false
|
98
86
|
requirements:
|
99
|
-
- -
|
87
|
+
- - '>='
|
100
88
|
- !ruby/object:Gem::Version
|
101
89
|
version: '0'
|
102
90
|
type: :runtime
|
103
91
|
prerelease: false
|
104
92
|
version_requirements: !ruby/object:Gem::Requirement
|
105
|
-
none: false
|
106
93
|
requirements:
|
107
|
-
- -
|
94
|
+
- - '>='
|
108
95
|
- !ruby/object:Gem::Version
|
109
96
|
version: '0'
|
110
97
|
- !ruby/object:Gem::Dependency
|
111
98
|
name: eventmachine
|
112
99
|
requirement: !ruby/object:Gem::Requirement
|
113
|
-
none: false
|
114
100
|
requirements:
|
115
|
-
- -
|
101
|
+
- - '>='
|
116
102
|
- !ruby/object:Gem::Version
|
117
103
|
version: '0'
|
118
104
|
type: :runtime
|
119
105
|
prerelease: false
|
120
106
|
version_requirements: !ruby/object:Gem::Requirement
|
121
|
-
none: false
|
122
107
|
requirements:
|
123
|
-
- -
|
108
|
+
- - '>='
|
124
109
|
- !ruby/object:Gem::Version
|
125
110
|
version: '0'
|
126
111
|
- !ruby/object:Gem::Dependency
|
127
112
|
name: memcache-client
|
128
113
|
requirement: !ruby/object:Gem::Requirement
|
129
|
-
none: false
|
130
114
|
requirements:
|
131
|
-
- -
|
115
|
+
- - '>='
|
132
116
|
- !ruby/object:Gem::Version
|
133
117
|
version: '0'
|
134
118
|
type: :runtime
|
135
119
|
prerelease: false
|
136
120
|
version_requirements: !ruby/object:Gem::Requirement
|
137
|
-
none: false
|
138
121
|
requirements:
|
139
|
-
- -
|
122
|
+
- - '>='
|
140
123
|
- !ruby/object:Gem::Version
|
141
124
|
version: '0'
|
142
125
|
- !ruby/object:Gem::Dependency
|
143
126
|
name: nendo
|
144
127
|
requirement: !ruby/object:Gem::Requirement
|
145
|
-
none: false
|
146
128
|
requirements:
|
147
129
|
- - '='
|
148
130
|
- !ruby/object:Gem::Version
|
@@ -150,7 +132,6 @@ dependencies:
|
|
150
132
|
type: :runtime
|
151
133
|
prerelease: false
|
152
134
|
version_requirements: !ruby/object:Gem::Requirement
|
153
|
-
none: false
|
154
135
|
requirements:
|
155
136
|
- - '='
|
156
137
|
- !ruby/object:Gem::Version
|
@@ -158,49 +139,43 @@ dependencies:
|
|
158
139
|
- !ruby/object:Gem::Dependency
|
159
140
|
name: distributed-trie
|
160
141
|
requirement: !ruby/object:Gem::Requirement
|
161
|
-
none: false
|
162
142
|
requirements:
|
163
|
-
- -
|
143
|
+
- - '>='
|
164
144
|
- !ruby/object:Gem::Version
|
165
145
|
version: '0'
|
166
146
|
type: :runtime
|
167
147
|
prerelease: false
|
168
148
|
version_requirements: !ruby/object:Gem::Requirement
|
169
|
-
none: false
|
170
149
|
requirements:
|
171
|
-
- -
|
150
|
+
- - '>='
|
172
151
|
- !ruby/object:Gem::Version
|
173
152
|
version: '0'
|
174
153
|
- !ruby/object:Gem::Dependency
|
175
154
|
name: rack
|
176
155
|
requirement: !ruby/object:Gem::Requirement
|
177
|
-
none: false
|
178
156
|
requirements:
|
179
|
-
- -
|
157
|
+
- - '>='
|
180
158
|
- !ruby/object:Gem::Version
|
181
159
|
version: '0'
|
182
160
|
type: :runtime
|
183
161
|
prerelease: false
|
184
162
|
version_requirements: !ruby/object:Gem::Requirement
|
185
|
-
none: false
|
186
163
|
requirements:
|
187
|
-
- -
|
164
|
+
- - '>='
|
188
165
|
- !ruby/object:Gem::Version
|
189
166
|
version: '0'
|
190
167
|
- !ruby/object:Gem::Dependency
|
191
168
|
name: ruby-progressbar
|
192
169
|
requirement: !ruby/object:Gem::Requirement
|
193
|
-
none: false
|
194
170
|
requirements:
|
195
|
-
- -
|
171
|
+
- - '>='
|
196
172
|
- !ruby/object:Gem::Version
|
197
173
|
version: '0'
|
198
174
|
type: :runtime
|
199
175
|
prerelease: false
|
200
176
|
version_requirements: !ruby/object:Gem::Requirement
|
201
|
-
none: false
|
202
177
|
requirements:
|
203
|
-
- -
|
178
|
+
- - '>='
|
204
179
|
- !ruby/object:Gem::Version
|
205
180
|
version: '0'
|
206
181
|
description: Sekka is a SKK like input method. Sekka server provides REST Based API.
|
@@ -263,26 +238,25 @@ files:
|
|
263
238
|
- README.md
|
264
239
|
homepage: http://github.com/kiyoka/sekka
|
265
240
|
licenses: []
|
241
|
+
metadata: {}
|
266
242
|
post_install_message:
|
267
243
|
rdoc_options: []
|
268
244
|
require_paths:
|
269
245
|
- lib
|
270
246
|
required_ruby_version: !ruby/object:Gem::Requirement
|
271
|
-
none: false
|
272
247
|
requirements:
|
273
|
-
- -
|
248
|
+
- - '>='
|
274
249
|
- !ruby/object:Gem::Version
|
275
|
-
version: 1.9.
|
250
|
+
version: 1.9.2
|
276
251
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
277
|
-
none: false
|
278
252
|
requirements:
|
279
|
-
- -
|
253
|
+
- - '>='
|
280
254
|
- !ruby/object:Gem::Version
|
281
255
|
version: '0'
|
282
256
|
requirements: []
|
283
257
|
rubyforge_project:
|
284
|
-
rubygems_version:
|
258
|
+
rubygems_version: 2.0.3
|
285
259
|
signing_key:
|
286
|
-
specification_version:
|
260
|
+
specification_version: 4
|
287
261
|
summary: Sekka is a SKK like input method.
|
288
262
|
test_files: []
|