opener-tree-tagger 3.0.3 → 3.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +13 -5
- data/README.md +1 -1
- data/ext/hack/support.rb +27 -0
- data/lib/opener/tree_tagger.rb +18 -10
- data/lib/opener/tree_tagger/version.rb +1 -1
- data/opener-tree-tagger.gemspec +0 -1
- metadata +62 -76
- data/lib/opener/tree_tagger/error_layer.rb +0 -89
checksums.yaml
CHANGED
@@ -1,7 +1,15 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
YTc4NTA2YmQzYzVlZTZlMjhmNzk0NmFmZjI0NzBmZTU1MzU4YzNkMQ==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
MDc0OTUzZTI3YjVmYjZlMjA1YzNjYTI2NjY0ZGJkMDVjY2YwOTdmZg==
|
5
7
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
NGNhNzhmOThhZWQ5N2FmNGU3YzQ1MzBlYTM4YTU0MDNjZGY0YTQ0NzZmMzZi
|
10
|
+
ZDdkN2I0NDFjODRjZjM3MTVmMTc4NGJmZTJiOTJhODIzMDI3MTFiODRhYTll
|
11
|
+
OTA5ZGE5M2NjMTBiMjc1NTkwNmIwOGIxMmE1MzU3YTRiMmU5NDE=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
Mjc2M2NkMWZjNTg2ODZkYzA5MjljNmFlMjk4ZTVkMDkxMzFiMjhmNjE1M2Rk
|
14
|
+
ZGFhODVmYWVhZjY1ZDc4ZmU0YWY0NDAzMGQ0NTNjZDMwOTdhYzQ4MGNkNTQ4
|
15
|
+
MTgwOTNlYjQ4ZDY3NWNjZTAxN2Y3MzEwNDEzNWU1OWMzZDFjZGM=
|
data/README.md
CHANGED
@@ -101,7 +101,7 @@ The component is a fat wrapper around the actual language technology core. You c
|
|
101
101
|
Where to go from here
|
102
102
|
---------------------
|
103
103
|
|
104
|
-
* [Check the project
|
104
|
+
* [Check the project websitere](http://opener-project.github.io)
|
105
105
|
* [Checkout the webservice](http://opener.olery.com/tree-tagger)
|
106
106
|
|
107
107
|
Report problem/Get help
|
data/ext/hack/support.rb
CHANGED
@@ -27,6 +27,15 @@ PRE_INSTALL_REQUIREMENTS = File.expand_path(
|
|
27
27
|
__FILE__
|
28
28
|
)
|
29
29
|
|
30
|
+
# Path to the vendor directory for C code.
|
31
|
+
VENDOR_DIRECTORY = File.expand_path('../../../core/vendor', __FILE__)
|
32
|
+
|
33
|
+
# Path to the directory to install vendored C code into.
|
34
|
+
VENDOR_BUILD_DIRECTORY = File.expand_path(
|
35
|
+
'../../../core/vendor/build',
|
36
|
+
__FILE__
|
37
|
+
)
|
38
|
+
|
30
39
|
##
|
31
40
|
# Verifies the requirements to install thi Gem.
|
32
41
|
#
|
@@ -36,3 +45,21 @@ def verify_requirements
|
|
36
45
|
require_executable('pip')
|
37
46
|
require_version('pip', pip_version, '1.3.1')
|
38
47
|
end
|
48
|
+
|
49
|
+
def install_tree_tagger
|
50
|
+
#return if ENV['TREE_TAGGER_PATH']
|
51
|
+
|
52
|
+
build = VENDOR_BUILD_DIRECTORY
|
53
|
+
cd build do
|
54
|
+
sh "curl -o tree-tagger-linux-3.2.tar.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/tree-tagger-linux-3.2.tar.gz"
|
55
|
+
sh "curl -o tagger-scripts.tar.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/tagger-scripts.tar.gz"
|
56
|
+
sh "curl -o install-tagger.sh http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/install-tagger.sh"
|
57
|
+
sh "curl -o dutch-par-linux-3.2-utf8.bin.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/dutch-par-linux-3.2-utf8.bin.gz"
|
58
|
+
sh "curl -o french-par-linux-3.2-utf8.bin.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/french-par-linux-3.2-utf8.bin.gz"
|
59
|
+
sh "curl -o german-par-linux-3.2-utf8.bin.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/german-par-linux-3.2-utf8.bin.gz"
|
60
|
+
sh "curl -o italian-par-linux-3.2-utf8.bin.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/italian-par-linux-3.2-utf8.bin.gz"
|
61
|
+
sh "curl -o spanish-par-linux-3.2-utf8.bin.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/spanish-par-linux-3.2-utf8.bin.gz"
|
62
|
+
sh "curl -o english-par-linux-3.2.bin.gz http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/english-par-linux-3.2.bin.gz"
|
63
|
+
sh "sh install-tagger.sh"
|
64
|
+
end
|
65
|
+
end
|
data/lib/opener/tree_tagger.rb
CHANGED
@@ -1,10 +1,8 @@
|
|
1
1
|
require 'open3'
|
2
2
|
require 'optparse'
|
3
|
-
require 'nokogiri'
|
4
3
|
|
5
4
|
require_relative 'tree_tagger/version'
|
6
5
|
require_relative 'tree_tagger/cli'
|
7
|
-
require_relative 'tree_tagger/error_layer'
|
8
6
|
|
9
7
|
module Opener
|
10
8
|
class TreeTagger
|
@@ -31,13 +29,15 @@ module Opener
|
|
31
29
|
end
|
32
30
|
|
33
31
|
def run(input)
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
end
|
32
|
+
stdout, stderr, process = capture(input)
|
33
|
+
|
34
|
+
if process.success?
|
35
|
+
STDERR.puts(stderr) unless stderr.empty?
|
36
|
+
else
|
37
|
+
abort stderr
|
38
|
+
end
|
39
|
+
|
40
|
+
return stdout, stderr, process
|
41
41
|
end
|
42
42
|
|
43
43
|
def capture(input)
|
@@ -45,11 +45,19 @@ module Opener
|
|
45
45
|
end
|
46
46
|
|
47
47
|
def command
|
48
|
-
|
48
|
+
c = "#{adjust_python_path} #{prepend_tree_tagger_path} python -E -OO #{kernel} #{args.join(' ')}"
|
49
|
+
puts c
|
50
|
+
c
|
49
51
|
end
|
50
52
|
|
51
53
|
protected
|
52
54
|
|
55
|
+
def prepend_tree_tagger_path
|
56
|
+
#unless ENV['TREE_TAGGER_PATH']
|
57
|
+
path = File.expand_path('../../../core/vendor/build', __FILE__)
|
58
|
+
return "TREE_TAGGER_PATH=#{path}"
|
59
|
+
end
|
60
|
+
|
53
61
|
##
|
54
62
|
# @return [String]
|
55
63
|
#
|
data/opener-tree-tagger.gemspec
CHANGED
metadata
CHANGED
@@ -1,157 +1,143 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: opener-tree-tagger
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 3.0
|
4
|
+
version: 3.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- rubenIzquierdo
|
8
8
|
- sparkboxx
|
9
|
-
autorequire:
|
9
|
+
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2014-
|
12
|
+
date: 2014-05-26 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: opener-daemons
|
16
|
-
version_requirements: !ruby/object:Gem::Requirement
|
17
|
-
requirements:
|
18
|
-
- - '>='
|
19
|
-
- !ruby/object:Gem::Version
|
20
|
-
version: '0'
|
21
16
|
requirement: !ruby/object:Gem::Requirement
|
22
17
|
requirements:
|
23
|
-
- - '>='
|
18
|
+
- - ! '>='
|
24
19
|
- !ruby/object:Gem::Version
|
25
20
|
version: '0'
|
26
|
-
prerelease: false
|
27
21
|
type: :runtime
|
28
|
-
|
29
|
-
name: opener-build-tools
|
22
|
+
prerelease: false
|
30
23
|
version_requirements: !ruby/object:Gem::Requirement
|
31
24
|
requirements:
|
32
|
-
- - '>='
|
25
|
+
- - ! '>='
|
33
26
|
- !ruby/object:Gem::Version
|
34
|
-
version: 0
|
27
|
+
version: '0'
|
28
|
+
- !ruby/object:Gem::Dependency
|
29
|
+
name: opener-build-tools
|
35
30
|
requirement: !ruby/object:Gem::Requirement
|
36
31
|
requirements:
|
37
|
-
- - '>='
|
32
|
+
- - ! '>='
|
38
33
|
- !ruby/object:Gem::Version
|
39
34
|
version: 0.2.7
|
40
|
-
prerelease: false
|
41
35
|
type: :runtime
|
42
|
-
|
43
|
-
name: rake
|
36
|
+
prerelease: false
|
44
37
|
version_requirements: !ruby/object:Gem::Requirement
|
45
38
|
requirements:
|
46
|
-
- - '>='
|
39
|
+
- - ! '>='
|
47
40
|
- !ruby/object:Gem::Version
|
48
|
-
version:
|
41
|
+
version: 0.2.7
|
42
|
+
- !ruby/object:Gem::Dependency
|
43
|
+
name: rake
|
49
44
|
requirement: !ruby/object:Gem::Requirement
|
50
45
|
requirements:
|
51
|
-
- - '>='
|
46
|
+
- - ! '>='
|
52
47
|
- !ruby/object:Gem::Version
|
53
48
|
version: '0'
|
54
|
-
prerelease: false
|
55
49
|
type: :runtime
|
56
|
-
|
57
|
-
name: sinatra
|
50
|
+
prerelease: false
|
58
51
|
version_requirements: !ruby/object:Gem::Requirement
|
59
52
|
requirements:
|
60
|
-
- - '>='
|
53
|
+
- - ! '>='
|
61
54
|
- !ruby/object:Gem::Version
|
62
55
|
version: '0'
|
56
|
+
- !ruby/object:Gem::Dependency
|
57
|
+
name: sinatra
|
63
58
|
requirement: !ruby/object:Gem::Requirement
|
64
59
|
requirements:
|
65
|
-
- - '>='
|
60
|
+
- - ! '>='
|
66
61
|
- !ruby/object:Gem::Version
|
67
62
|
version: '0'
|
68
|
-
prerelease: false
|
69
63
|
type: :runtime
|
70
|
-
|
71
|
-
name: httpclient
|
64
|
+
prerelease: false
|
72
65
|
version_requirements: !ruby/object:Gem::Requirement
|
73
66
|
requirements:
|
74
|
-
- - '>='
|
67
|
+
- - ! '>='
|
75
68
|
- !ruby/object:Gem::Version
|
76
69
|
version: '0'
|
70
|
+
- !ruby/object:Gem::Dependency
|
71
|
+
name: httpclient
|
77
72
|
requirement: !ruby/object:Gem::Requirement
|
78
73
|
requirements:
|
79
|
-
- - '>='
|
74
|
+
- - ! '>='
|
80
75
|
- !ruby/object:Gem::Version
|
81
76
|
version: '0'
|
82
|
-
prerelease: false
|
83
77
|
type: :runtime
|
84
|
-
|
85
|
-
name: puma
|
78
|
+
prerelease: false
|
86
79
|
version_requirements: !ruby/object:Gem::Requirement
|
87
80
|
requirements:
|
88
|
-
- - '>='
|
81
|
+
- - ! '>='
|
89
82
|
- !ruby/object:Gem::Version
|
90
83
|
version: '0'
|
84
|
+
- !ruby/object:Gem::Dependency
|
85
|
+
name: puma
|
91
86
|
requirement: !ruby/object:Gem::Requirement
|
92
87
|
requirements:
|
93
|
-
- - '>='
|
88
|
+
- - ! '>='
|
94
89
|
- !ruby/object:Gem::Version
|
95
90
|
version: '0'
|
96
|
-
prerelease: false
|
97
91
|
type: :runtime
|
98
|
-
|
99
|
-
name: opener-webservice
|
92
|
+
prerelease: false
|
100
93
|
version_requirements: !ruby/object:Gem::Requirement
|
101
94
|
requirements:
|
102
|
-
- - '>='
|
95
|
+
- - ! '>='
|
103
96
|
- !ruby/object:Gem::Version
|
104
97
|
version: '0'
|
98
|
+
- !ruby/object:Gem::Dependency
|
99
|
+
name: opener-webservice
|
105
100
|
requirement: !ruby/object:Gem::Requirement
|
106
101
|
requirements:
|
107
|
-
- - '>='
|
102
|
+
- - ! '>='
|
108
103
|
- !ruby/object:Gem::Version
|
109
104
|
version: '0'
|
110
|
-
prerelease: false
|
111
105
|
type: :runtime
|
112
|
-
|
113
|
-
name: nokogiri
|
106
|
+
prerelease: false
|
114
107
|
version_requirements: !ruby/object:Gem::Requirement
|
115
108
|
requirements:
|
116
|
-
- - '>='
|
109
|
+
- - ! '>='
|
117
110
|
- !ruby/object:Gem::Version
|
118
111
|
version: '0'
|
112
|
+
- !ruby/object:Gem::Dependency
|
113
|
+
name: rspec
|
119
114
|
requirement: !ruby/object:Gem::Requirement
|
120
115
|
requirements:
|
121
|
-
- - '>='
|
116
|
+
- - ! '>='
|
122
117
|
- !ruby/object:Gem::Version
|
123
118
|
version: '0'
|
119
|
+
type: :development
|
124
120
|
prerelease: false
|
125
|
-
type: :runtime
|
126
|
-
- !ruby/object:Gem::Dependency
|
127
|
-
name: rspec
|
128
121
|
version_requirements: !ruby/object:Gem::Requirement
|
129
122
|
requirements:
|
130
|
-
- - '>='
|
123
|
+
- - ! '>='
|
131
124
|
- !ruby/object:Gem::Version
|
132
125
|
version: '0'
|
126
|
+
- !ruby/object:Gem::Dependency
|
127
|
+
name: cucumber
|
133
128
|
requirement: !ruby/object:Gem::Requirement
|
134
129
|
requirements:
|
135
|
-
- - '>='
|
130
|
+
- - ! '>='
|
136
131
|
- !ruby/object:Gem::Version
|
137
132
|
version: '0'
|
138
|
-
prerelease: false
|
139
133
|
type: :development
|
140
|
-
|
141
|
-
name: cucumber
|
134
|
+
prerelease: false
|
142
135
|
version_requirements: !ruby/object:Gem::Requirement
|
143
136
|
requirements:
|
144
|
-
- - '>='
|
145
|
-
- !ruby/object:Gem::Version
|
146
|
-
version: '0'
|
147
|
-
requirement: !ruby/object:Gem::Requirement
|
148
|
-
requirements:
|
149
|
-
- - '>='
|
137
|
+
- - ! '>='
|
150
138
|
- !ruby/object:Gem::Version
|
151
139
|
version: '0'
|
152
|
-
|
153
|
-
type: :development
|
154
|
-
description: 'Ruby wrapped KAF based Tree Tagger for 6 languages '
|
140
|
+
description: ! 'Ruby wrapped KAF based Tree Tagger for 6 languages '
|
155
141
|
email:
|
156
142
|
- ruben.izquierdobevia@vu.nl
|
157
143
|
- wilco@olery.com
|
@@ -163,11 +149,6 @@ extensions:
|
|
163
149
|
- ext/hack/Rakefile
|
164
150
|
extra_rdoc_files: []
|
165
151
|
files:
|
166
|
-
- README.md
|
167
|
-
- bin/tree-tagger
|
168
|
-
- bin/tree-tagger-daemon
|
169
|
-
- bin/tree-tagger-server
|
170
|
-
- config.ru
|
171
152
|
- core/dutch.map.treetagger.kaf.csv
|
172
153
|
- core/english.map.treetagger.kaf.csv
|
173
154
|
- core/french.map.treetagger.kaf.csv
|
@@ -179,37 +160,42 @@ files:
|
|
179
160
|
- exec/tree-tagger.rb
|
180
161
|
- ext/hack/Rakefile
|
181
162
|
- ext/hack/support.rb
|
182
|
-
- lib/opener/tree_tagger.rb
|
183
163
|
- lib/opener/tree_tagger/cli.rb
|
184
|
-
- lib/opener/tree_tagger/error_layer.rb
|
185
164
|
- lib/opener/tree_tagger/public/markdown.css
|
186
165
|
- lib/opener/tree_tagger/server.rb
|
187
166
|
- lib/opener/tree_tagger/version.rb
|
188
167
|
- lib/opener/tree_tagger/views/index.erb
|
189
168
|
- lib/opener/tree_tagger/views/result.erb
|
169
|
+
- lib/opener/tree_tagger.rb
|
170
|
+
- config.ru
|
190
171
|
- opener-tree-tagger.gemspec
|
191
172
|
- pre_install_requirements.txt
|
173
|
+
- README.md
|
174
|
+
- bin/tree-tagger
|
175
|
+
- bin/tree-tagger-daemon
|
176
|
+
- bin/tree-tagger-server
|
192
177
|
homepage: http://opener-project.github.com/
|
193
178
|
licenses: []
|
194
179
|
metadata: {}
|
195
|
-
post_install_message:
|
180
|
+
post_install_message:
|
196
181
|
rdoc_options: []
|
197
182
|
require_paths:
|
198
183
|
- lib
|
199
184
|
required_ruby_version: !ruby/object:Gem::Requirement
|
200
185
|
requirements:
|
201
|
-
- - '>='
|
186
|
+
- - ! '>='
|
202
187
|
- !ruby/object:Gem::Version
|
203
188
|
version: '0'
|
204
189
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
205
190
|
requirements:
|
206
|
-
- - '>='
|
191
|
+
- - ! '>='
|
207
192
|
- !ruby/object:Gem::Version
|
208
193
|
version: '0'
|
209
194
|
requirements: []
|
210
|
-
rubyforge_project:
|
211
|
-
rubygems_version: 2.
|
212
|
-
signing_key:
|
195
|
+
rubyforge_project:
|
196
|
+
rubygems_version: 2.1.11
|
197
|
+
signing_key:
|
213
198
|
specification_version: 4
|
214
199
|
summary: Ruby wrapped KAF based Tree Tagger for 6 languages
|
215
200
|
test_files: []
|
201
|
+
has_rdoc:
|
@@ -1,89 +0,0 @@
|
|
1
|
-
module Opener
|
2
|
-
class TreeTagger
|
3
|
-
##
|
4
|
-
# Add Error Layer to KAF file instead of throwing an error.
|
5
|
-
#
|
6
|
-
class ErrorLayer
|
7
|
-
attr_accessor :input, :document, :error, :klass
|
8
|
-
|
9
|
-
def initialize(input, error, klass)
|
10
|
-
@input = input.to_s
|
11
|
-
# Make sure there is always a document, even if it is empty.
|
12
|
-
@document = Nokogiri::XML(input) rescue Nokogiri::XML(nil)
|
13
|
-
@error = error
|
14
|
-
@klass = klass
|
15
|
-
end
|
16
|
-
|
17
|
-
def add
|
18
|
-
if is_xml?
|
19
|
-
unless has_errors_layer?
|
20
|
-
add_errors_layer
|
21
|
-
end
|
22
|
-
else
|
23
|
-
add_root
|
24
|
-
add_text
|
25
|
-
add_errors_layer
|
26
|
-
end
|
27
|
-
add_error
|
28
|
-
|
29
|
-
xml = !!document.encoding ? document.to_xml : document.to_xml(:encoding => "UTF-8")
|
30
|
-
|
31
|
-
return xml
|
32
|
-
end
|
33
|
-
|
34
|
-
##
|
35
|
-
# Check if the document is a valid XML file.
|
36
|
-
#
|
37
|
-
def is_xml?
|
38
|
-
!!document.root
|
39
|
-
end
|
40
|
-
|
41
|
-
##
|
42
|
-
# Add root element to the XML file.
|
43
|
-
#
|
44
|
-
def add_root
|
45
|
-
root = Nokogiri::XML::Node.new "KAF", document
|
46
|
-
document.add_child(root)
|
47
|
-
end
|
48
|
-
|
49
|
-
##
|
50
|
-
# Check if the document already has an errors layer.
|
51
|
-
#
|
52
|
-
def has_errors_layer?
|
53
|
-
!!document.at('errors')
|
54
|
-
end
|
55
|
-
|
56
|
-
##
|
57
|
-
# Add errors element to the XML file.
|
58
|
-
#
|
59
|
-
def add_errors_layer
|
60
|
-
node = Nokogiri::XML::Node.new "errors", document
|
61
|
-
document.root.add_child(node)
|
62
|
-
end
|
63
|
-
|
64
|
-
##
|
65
|
-
# Add the text file incase it is not a valid XML document. More
|
66
|
-
# info for debugging.
|
67
|
-
#
|
68
|
-
def add_text
|
69
|
-
node = Nokogiri::XML::Node.new "raw", document
|
70
|
-
node.inner_html = input
|
71
|
-
document.root.add_child(node)
|
72
|
-
|
73
|
-
end
|
74
|
-
|
75
|
-
##
|
76
|
-
# Add the actual error to the errors layer.
|
77
|
-
#
|
78
|
-
def add_error
|
79
|
-
node = document.at('errors')
|
80
|
-
error_node = Nokogiri::XML::Node.new "error", node
|
81
|
-
error_node['class'] = klass.to_s
|
82
|
-
error_node['version'] = klass::VERSION
|
83
|
-
error_node.inner_html = error
|
84
|
-
node.add_child(error_node)
|
85
|
-
end
|
86
|
-
|
87
|
-
end # ErrorLayer
|
88
|
-
end # TreeTagger
|
89
|
-
end # Opener
|