vn_tagger 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +28 -0
- data/Gemfile +5 -0
- data/LICENSE.txt +22 -0
- data/README.md +34 -0
- data/Rakefile +2 -0
- data/VN_TAGGER LICENSE.txt +5 -0
- data/lib/commons-cli-1.2.jar +0 -0
- data/lib/edu.stanford.nlp.tagger-2.0.jar +0 -0
- data/lib/vn.hus.nlp.fsm-1.0.0.jar +0 -0
- data/lib/vn.hus.nlp.tokenizer-4.1.1.jar +0 -0
- data/lib/vn.hus.nlp.utils-1.0.0.jar +0 -0
- data/lib/vn_tagger.rb +7 -0
- data/lib/vn_tagger/tagger.rb +44 -0
- data/lib/vn_tagger/version.rb +3 -0
- data/resources/automata/dfaLexicon.xml +123032 -0
- data/resources/automata/externalLexicon.xml +7 -0
- data/resources/bigram/bigram.xml +211658 -0
- data/resources/bigram/unigram.xml +24309 -0
- data/resources/lexers/lexers.xml +68 -0
- data/resources/models/vtb.tagger +0 -0
- data/resources/models/vtb.tagger.props +36 -0
- data/resources/normalization/rules.txt +15 -0
- data/resources/prefix/namedEntityPrefix.xml +34 -0
- data/spec/spec_helper.rb +9 -0
- data/spec/vn_tagger/tagger_spec.rb +14 -0
- data/spec/vn_tagger_spec.rb +6 -0
- data/vn.hus.nlp.tagger-4.2.0.jar +0 -0
- data/vnTagger.sh +28 -0
- data/vn_tagger.gemspec +25 -0
- metadata +134 -0
@@ -0,0 +1,68 @@
|
|
1
|
+
<?xml version="1.0" encoding="utf-8" standalone="yes"?>
|
2
|
+
<!-- (C) phuonglh@gmail.com -->
|
3
|
+
<corpus id="resources/lexers/lexers.xml">
|
4
|
+
<body>
|
5
|
+
<w msd="numbersign">#</w>
|
6
|
+
<w msd="ampersand">&</w>
|
7
|
+
<w msd="date_mm-dd-yy">(0*[1-9]|1[012])-(0*[1-9]|[12][0-9]|3[01])-\d\d</w>
|
8
|
+
<w msd="date_mm/dd/yy">(0*[1-9]|1[012])/(0*[1-9]|[12][0-9]|3[01])/\d\d</w>
|
9
|
+
<w msd="date_mm.dd.yy">(0*[1-9]|1[012])\.(0*[1-9]|[12][0-9]|3[01])\.\d\d</w>
|
10
|
+
<w msd="date_dd-mm-yy">([12][0-9]|3[01]|0*[1-9])-(1[012]||0*[1-9])-\d\d</w>
|
11
|
+
<w msd="date_dd/mm/yy">([12][0-9]|3[01]|0*[1-9])/(1[012]||0*[1-9])/\d\d</w>
|
12
|
+
<w msd="date_dd.mm.yy">([12][0-9]|3[01]|0*[1-9])[\.](1[012]||0*[1-9])[\.]\d\d</w>
|
13
|
+
<w msd="date_dd-mm-yyyy">([12][0-9]|3[01]|0*[1-9])-(1[012]||0*[1-9])-(19|20)\d\d</w>
|
14
|
+
<w msd="date_dd/mm/yyyy">([12][0-9]|3[01]|0*[1-9])/(1[012]||0*[1-9])/(19|20)\d\d</w>
|
15
|
+
<w msd="date_dd.mm.yyyy">([12][0-9]|3[01]|0*[1-9])\.(1[012]||0*[1-9])\.(19|20)\d\d</w>
|
16
|
+
<w msd="date_dd-mm">(0*[1-9]|[12][0-9]|3[01])[-/\.](1[012]|0*[1-9])</w>
|
17
|
+
<w msd="date_mm-yy">(0*[1-9]|1[012])[-/\.]\d\d</w>
|
18
|
+
<w msd="date_mm-yyyy">(0*[1-9]|1[012])[-/\.](19|20)\d\d</w>
|
19
|
+
<w msd="date_yyyy">(19|20)\d\d</w>
|
20
|
+
<w msd="date_mm-dd-yyyy">(0*[1-9]|1[012])-([12][0-9]|3[01]|0*[1-9])-(19|20)\d\d</w>
|
21
|
+
<w msd="date_mm/dd/yyyy">(0*[1-9]|1[012])/([12][0-9]|3[01]|0*[1-9])/(19|20)\d\d</w>
|
22
|
+
<w msd="date_mm.dd.yyyy">(0*[1-9]|1[012])\.([12][0-9]|3[01]|0*[1-9])\.(19|20)\d\d</w>
|
23
|
+
<w msd="date_yyyy-mm-dd">(19|20)\d\d-(0*[1-9]|1[012])-([12][0-9]|3[01]|0*[1-9])</w>
|
24
|
+
<w msd="date_yyyy/mm/dd">(19|20)\d\d/(0*[1-9]|1[012])/([12][0-9]|3[01]|0*[1-9])</w>
|
25
|
+
<w msd="date_yyyy.mm.dd">(19|20)\d\d\.(0*[1-9]|1[012])\.([12][0-9]|3[01]|0*[1-9])</w>
|
26
|
+
<w msd="hhmmss">([0-1]\d|[2][0-3]):[0-5]\d:[0-5]\d</w>
|
27
|
+
<w msd="percent">([0-9]*[\.,])?[0-9]+%</w>
|
28
|
+
<w msd="name1">[A-ZÁÂĐÍÔƯỨÝỶ][aàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz]*</w>
|
29
|
+
<w msd="name2">([A-ZÁÂĐÍÔƯỨÝỶ][aàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz]*)(\s+[A-ZÁÂĐÍÔƯỨÝỶ][aàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz]+)*</w>
|
30
|
+
<w msd="phrase">([AÀẢÃÁẠĂẰẲẴẮẶÂẦẨẪẤẬBCDĐEÈẺẼÉẸÊỀỂỄẾỆFGHIÌỈĨÍỊJKLMNOÒỎÕÓỌÔỒỔỖỐỘƠỜỞỠỚỢPQRSTUÙỦŨÚỤƯỪỬỮỨỰVWXYỲỶỸÝỴZ])?([aàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz\s])*([aàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz])+$*</w>
|
31
|
+
<w msd="allcaps">([AÀẢÃÁẠĂẰẲẴẮẶÂẦẨẪẤẬBCDĐEÈẺẼÉẸÊỀỂỄẾỆFGHIÌỈĨÍỊJKLMNOÒỎÕÓỌÔỒỔỖỐỘƠỜỞỠỚỢPQRSTUÙỦŨÚỤƯỪỬỮỨỰVWXYỲỶỸÝỴZ]+)(\s*[AÀẢÃÁẠĂẰẲẴẮẶÂẦẨẪẤẬBCDĐEÈẺẼÉẸÊỀỂỄẾỆFGHIÌỈĨÍỊJKLMNOÒỎÕÓỌÔỒỔỖỐỘƠỜỞỠỚỢPQRSTUÙỦŨÚỤƯỪỬỮỨỰVWXYỲỶỸÝỴZ]+)*[^aàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz/\)\(\?!\.;:,\-"']</w>
|
32
|
+
<w msd="fraction">(\d+)/(\d+)</w>
|
33
|
+
<w msd="email">(\w[-._\w]*\w@\w[-._\w]*\w\.\w{2,3})</w>
|
34
|
+
<w msd="return">(^$)</w>
|
35
|
+
<w msd="fslash">/</w>
|
36
|
+
<w msd="langle"><</w>
|
37
|
+
<w msd="xmltags"></*\w*></w>
|
38
|
+
<w msd="equal">=</w>
|
39
|
+
<w msd="rangle">></w>
|
40
|
+
<w msd="aroba">@</w>
|
41
|
+
<w msd="number1">[+]?([0-9]*)?[0-9]+([\.,]\d+)*</w>
|
42
|
+
<!--
|
43
|
+
<w msd="number2">[+]?([0-9]*)?[0-9]+([\.,]\d+)*(\s|tỉ|tỷ|triệu|ngàn|nghìn|trăm|chục)*</w>
|
44
|
+
-->
|
45
|
+
<w msd="degree">[-+]?([0-9]*[\.,])?[0-9]+°</w>
|
46
|
+
<w msd="ponctuation">[\\?!\\.:;,\-"']</w>
|
47
|
+
<w msd="dollar">\$</w>
|
48
|
+
<w msd="lparen">\(</w>
|
49
|
+
<w msd="rparen">\)</w>
|
50
|
+
<w msd="asterisk">\*</w>
|
51
|
+
<w msd="plus">\+</w>
|
52
|
+
<w msd="minus">\-</w>
|
53
|
+
<w msd="ellipsis">\.\.\.</w>
|
54
|
+
<w msd="residual">\W</w>
|
55
|
+
<w msd="lbracket">\[</w>
|
56
|
+
<w msd="bslash">\\</w>
|
57
|
+
<w msd="rbracket">\]</w>
|
58
|
+
<w msd="entity0">\d+([\.,]\d+)*[A-Zaàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz]+\d+$</w>
|
59
|
+
<w msd="entity1">[A-Zaàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz]+(\d)*$</w>
|
60
|
+
<w msd="entity2">[A-Zaàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz\d]+([\.\-/][\dA-Zaàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz]+)*[\dA-Zaàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz]+</w>
|
61
|
+
<w msd="space">\s+</w>
|
62
|
+
<w msd="word">\w</w>
|
63
|
+
<w msd="lcbrace">\{</w>
|
64
|
+
<w msd="rcbrace">\}</w>
|
65
|
+
<w msd="underscore">_</w>
|
66
|
+
<w msd="pound">£</w>
|
67
|
+
</body>
|
68
|
+
</corpus>
|
Binary file
|
@@ -0,0 +1,36 @@
|
|
1
|
+
## tagger training invoked at Thu Aug 05 14:33:50 CEST 2010 with arguments:
|
2
|
+
model = resources/models/vtb.tagger
|
3
|
+
arch = left5words,vietnameseunknowns
|
4
|
+
trainFile = data/vtb-20091030.tagged.txt
|
5
|
+
closedClassTags =
|
6
|
+
closedClassTagThreshold = 40
|
7
|
+
curWordMinFeatureThresh = 2
|
8
|
+
debug = true
|
9
|
+
debugPrefix =
|
10
|
+
tagSeparator = /
|
11
|
+
encoding = UTF-8
|
12
|
+
initFromTrees = false
|
13
|
+
iterations = 100
|
14
|
+
lang = vietnamese
|
15
|
+
learnClosedClassTags = false
|
16
|
+
minFeatureThresh = 2
|
17
|
+
openClassTags =
|
18
|
+
rareWordMinFeatureThresh = 10
|
19
|
+
rareWordThresh = 6
|
20
|
+
search = qn
|
21
|
+
sgml = false
|
22
|
+
sigmaSquared = 0.5
|
23
|
+
regL1 = 1.0
|
24
|
+
tagInside =
|
25
|
+
tokenize = false
|
26
|
+
tokenizerFactory =
|
27
|
+
tokenizerOptions =
|
28
|
+
treeRange =
|
29
|
+
treeNormalizer =
|
30
|
+
treeTransformer =
|
31
|
+
verbose = false
|
32
|
+
veryCommonWordThresh = 50
|
33
|
+
xmlInput =
|
34
|
+
outputFile =
|
35
|
+
outputFormat = slashTags
|
36
|
+
outputFormatOptions =
|
@@ -0,0 +1,34 @@
|
|
1
|
+
<?xml version="1.0" encoding="utf-8" standalone="yes"?>
|
2
|
+
<corpus id="resources/prefix/namedEntityPrefix.xml">
|
3
|
+
<body>
|
4
|
+
<!-- classificator prefix -->
|
5
|
+
<w>ông</w>
|
6
|
+
<w>bà</w>
|
7
|
+
<w>bác</w>
|
8
|
+
<w>chú</w>
|
9
|
+
<w>cô</w>
|
10
|
+
<w>thím</w>
|
11
|
+
<w>dì</w>
|
12
|
+
<w>cậu</w>
|
13
|
+
<w>cụ</w>
|
14
|
+
<w>mợ</w>
|
15
|
+
<w>ngài</w>
|
16
|
+
<w>anh</w>
|
17
|
+
<w>chị</w>
|
18
|
+
<w>thằng</w>
|
19
|
+
<w>cái</w>
|
20
|
+
<w>vua</w>
|
21
|
+
<!-- organization prefix -->
|
22
|
+
<w>tỉnh</w>
|
23
|
+
<w>huyện</w>
|
24
|
+
<w>xã</w>
|
25
|
+
<w>phường</w>
|
26
|
+
<w>bộ</w>
|
27
|
+
<w>sở</w>
|
28
|
+
<w>cục</w>
|
29
|
+
<w>ban</w>
|
30
|
+
<w>ngành</w>
|
31
|
+
<!-- Other prefix -->
|
32
|
+
<w>theo</w>
|
33
|
+
</body>
|
34
|
+
</corpus>
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
require 'byebug'
|
3
|
+
|
4
|
+
describe VnTagger::Tagger do
|
5
|
+
describe '#tag' do
|
6
|
+
let(:text) { 'HLV cùa Chelsea không hối tiếc vì hành động bỏ về sớm trong trận gặp Aston Villa.' }
|
7
|
+
let(:tagger) { described_class.new(text) }
|
8
|
+
let(:result) { tagger.tag }
|
9
|
+
|
10
|
+
it 'returns xml tagged text' do
|
11
|
+
expect(result).to be_a(Nokogiri::XML::Document)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
Binary file
|
data/vnTagger.sh
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
#!/bin/sh
|
2
|
+
|
3
|
+
# The main program to run
|
4
|
+
PROGRAM="${BASH_SOURCE%/*}/vn.hus.nlp.tagger-4.2.0.jar"
|
5
|
+
|
6
|
+
# Get the java command
|
7
|
+
#
|
8
|
+
if [ -z "$JAVACMD" ] ; then
|
9
|
+
if [ -n "$JAVA_HOME" ] ; then
|
10
|
+
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
|
11
|
+
JAVACMD="$JAVA_HOME/jre/sh/java"
|
12
|
+
else
|
13
|
+
JAVACMD="$JAVA_HOME/bin/java"
|
14
|
+
fi
|
15
|
+
else
|
16
|
+
JAVACMD=`which java 2> /dev/null`
|
17
|
+
if [ -z "$JAVACMD" ] ; then
|
18
|
+
JAVACMD=java
|
19
|
+
fi
|
20
|
+
fi
|
21
|
+
fi
|
22
|
+
|
23
|
+
# Run the programme
|
24
|
+
#
|
25
|
+
$JAVACMD -mx500m -jar $PROGRAM $@
|
26
|
+
|
27
|
+
|
28
|
+
|
data/vn_tagger.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'vn_tagger/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "vn_tagger"
|
8
|
+
spec.version = VnTagger::VERSION
|
9
|
+
spec.authors = ["Hieu Nguyen"]
|
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 = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib", 'lib/vn_tagger']
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_development_dependency "rspec"
|
24
|
+
spec.add_development_dependency "byebug"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,134 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: vn_tagger
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.4
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Hieu Nguyen
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-12-17 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: byebug
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: 'This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese
|
70
|
+
texts.'' '
|
71
|
+
email:
|
72
|
+
- hieuk09@gmail.com
|
73
|
+
executables: []
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- ".gitignore"
|
78
|
+
- Gemfile
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- VN_TAGGER LICENSE.txt
|
83
|
+
- lib/commons-cli-1.2.jar
|
84
|
+
- lib/edu.stanford.nlp.tagger-2.0.jar
|
85
|
+
- lib/vn.hus.nlp.fsm-1.0.0.jar
|
86
|
+
- lib/vn.hus.nlp.tokenizer-4.1.1.jar
|
87
|
+
- lib/vn.hus.nlp.utils-1.0.0.jar
|
88
|
+
- lib/vn_tagger.rb
|
89
|
+
- lib/vn_tagger/tagger.rb
|
90
|
+
- lib/vn_tagger/version.rb
|
91
|
+
- resources/automata/dfaLexicon.xml
|
92
|
+
- resources/automata/externalLexicon.xml
|
93
|
+
- resources/bigram/bigram.xml
|
94
|
+
- resources/bigram/unigram.xml
|
95
|
+
- resources/lexers/lexers.xml
|
96
|
+
- resources/models/vtb.tagger
|
97
|
+
- resources/models/vtb.tagger.props
|
98
|
+
- resources/normalization/rules.txt
|
99
|
+
- resources/prefix/namedEntityPrefix.xml
|
100
|
+
- spec/spec_helper.rb
|
101
|
+
- spec/vn_tagger/tagger_spec.rb
|
102
|
+
- spec/vn_tagger_spec.rb
|
103
|
+
- vn.hus.nlp.tagger-4.2.0.jar
|
104
|
+
- vnTagger.sh
|
105
|
+
- vn_tagger.gemspec
|
106
|
+
homepage: ''
|
107
|
+
licenses:
|
108
|
+
- MIT
|
109
|
+
metadata: {}
|
110
|
+
post_install_message:
|
111
|
+
rdoc_options: []
|
112
|
+
require_paths:
|
113
|
+
- lib
|
114
|
+
- lib/vn_tagger
|
115
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
116
|
+
requirements:
|
117
|
+
- - ">="
|
118
|
+
- !ruby/object:Gem::Version
|
119
|
+
version: '0'
|
120
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
125
|
+
requirements: []
|
126
|
+
rubyforge_project:
|
127
|
+
rubygems_version: 2.4.3
|
128
|
+
signing_key:
|
129
|
+
specification_version: 4
|
130
|
+
summary: This is a wrapper for vn_tagger library, a A POS tagger for Vietnamese texts.'
|
131
|
+
test_files:
|
132
|
+
- spec/spec_helper.rb
|
133
|
+
- spec/vn_tagger/tagger_spec.rb
|
134
|
+
- spec/vn_tagger_spec.rb
|