vn_tagger 0.0.6 → 0.1.0
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 +4 -4
- data/README.md +4 -2
- data/lib/vn_tagger/tagger.rb +5 -1
- data/lib/vn_tagger/version.rb +1 -1
- data/spec/vn_tagger/tagger_spec.rb +3 -0
- data/vn_tagger.gemspec +3 -3
- metadata +5 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: eb1eff57d9490c011b4d340c0d167a20245b8c5c
|
4
|
+
data.tar.gz: b411874dc1e8f7b574cc8995224f6f091bbb5206
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: ddce5c31d971c282ba08599a5b49cd38d46ec5e0c178b5b455b47324c941470ef8b4f15fa0f5c8162460105fcaa39344809100a6e2b6f2a856e5df7e6412716b
|
7
|
+
data.tar.gz: 7c96f95660818f66a11607d5056546e188e18cdb7a504babe57bb27eb3fcd4102e244e9768982a442b624e3d4a1929f223c35970dd6349d843a4a2f62f67dc3d
|
data/README.md
CHANGED
@@ -14,7 +14,7 @@ Or install it yourself as:
|
|
14
14
|
|
15
15
|
$ gem install vn_tagger
|
16
16
|
|
17
|
-
## Usage
|
17
|
+
## Usage Example
|
18
18
|
|
19
19
|
```ruby
|
20
20
|
text = 'Mourinho là huấn luyện viên của Chelsea'
|
@@ -22,9 +22,11 @@ document = VnTagger::Tagger.tag(text)
|
|
22
22
|
|
23
23
|
document.to_xml # => "<?xml version=\"1.0\"?>\n<doc>\n\t<s>\n\t\t<w pos=\"Np\">Mourinho</w>\n\t\t<w pos=\"V\">là</w>\n\t\t<w pos=\"N\">huấn luyện viên</w>\n\t\t<w pos=\"E\">của</w>\n\t\t<w pos=\"Np\">Chelsea</w>\n\t\t<w pos=\".\">.</w>\n\t</s>\n</doc>\n"
|
24
24
|
document.class # => Nokogiri::Xml::Document
|
25
|
+
keys = document.xpath("//w")
|
26
|
+
keys.first.attr('pos') # => 'Np'
|
27
|
+
keys.first.child.text #=> 'Mourinho'
|
25
28
|
```
|
26
29
|
|
27
|
-
|
28
30
|
## Contributing
|
29
31
|
|
30
32
|
1. Fork it ( https://github.com/hieuk09/vn_tagger/fork )
|
data/lib/vn_tagger/tagger.rb
CHANGED
@@ -8,7 +8,7 @@ module VnTagger
|
|
8
8
|
OUTPUT = File.join(ROOT_PATH, 'output.xml')
|
9
9
|
|
10
10
|
def initialize(text)
|
11
|
-
@text = text
|
11
|
+
@text = normalize(text)
|
12
12
|
end
|
13
13
|
|
14
14
|
def tag
|
@@ -39,5 +39,9 @@ module VnTagger
|
|
39
39
|
file.close
|
40
40
|
doc
|
41
41
|
end
|
42
|
+
|
43
|
+
def normalize(string)
|
44
|
+
string.to_s.gsub(/(\"|\')/, '')
|
45
|
+
end
|
42
46
|
end
|
43
47
|
end
|
data/lib/vn_tagger/version.rb
CHANGED
@@ -5,9 +5,12 @@ describe VnTagger::Tagger do
|
|
5
5
|
let(:text) { 'HLV cùa Chelsea không hối tiếc vì hành động bỏ về sớm trong trận gặp Aston Villa.' }
|
6
6
|
let(:tagger) { described_class.new(text) }
|
7
7
|
let(:result) { tagger.tag }
|
8
|
+
let(:key) { result.xpath("//w").first }
|
8
9
|
|
9
10
|
it 'returns xml tagged text' do
|
10
11
|
expect(result).to be_a(Nokogiri::XML::Document)
|
12
|
+
expect(key.attr('pos')).to eq 'Np'
|
13
|
+
expect(key.child.text).to eq 'HLV'
|
11
14
|
end
|
12
15
|
end
|
13
16
|
end
|
data/vn_tagger.gemspec
CHANGED
@@ -8,9 +8,9 @@ Gem::Specification.new do |spec|
|
|
8
8
|
spec.version = VnTagger::VERSION
|
9
9
|
spec.authors = ["Hieu Nguyen"]
|
10
10
|
spec.email = ["hieuk09@gmail.com"]
|
11
|
-
spec.summary = %q{This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese texts.
|
12
|
-
spec.description = %q{This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese texts.
|
13
|
-
spec.homepage = ""
|
11
|
+
spec.summary = %q{This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese texts. }
|
12
|
+
spec.description = %q{This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese texts. }
|
13
|
+
spec.homepage = "https://github.com/hieuk09/ruby_vn_tagger"
|
14
14
|
spec.license = "MIT"
|
15
15
|
|
16
16
|
spec.files = `git ls-files -z`.split("\x0")
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: vn_tagger
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0
|
4
|
+
version: 0.1.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Hieu Nguyen
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-12-
|
11
|
+
date: 2014-12-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -67,7 +67,7 @@ dependencies:
|
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '0'
|
69
69
|
description: 'This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese
|
70
|
-
texts.
|
70
|
+
texts. '
|
71
71
|
email:
|
72
72
|
- hieuk09@gmail.com
|
73
73
|
executables: []
|
@@ -103,7 +103,7 @@ files:
|
|
103
103
|
- vn.hus.nlp.tagger-4.2.0.jar
|
104
104
|
- vnTagger.sh
|
105
105
|
- vn_tagger.gemspec
|
106
|
-
homepage:
|
106
|
+
homepage: https://github.com/hieuk09/ruby_vn_tagger
|
107
107
|
licenses:
|
108
108
|
- MIT
|
109
109
|
metadata: {}
|
@@ -127,7 +127,7 @@ rubyforge_project:
|
|
127
127
|
rubygems_version: 2.4.3
|
128
128
|
signing_key:
|
129
129
|
specification_version: 4
|
130
|
-
summary: This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese texts.
|
130
|
+
summary: This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese texts.
|
131
131
|
test_files:
|
132
132
|
- spec/spec_helper.rb
|
133
133
|
- spec/vn_tagger/tagger_spec.rb
|