lulalala_address_tokenizer 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 +7 -0
- data/.gitignore +9 -0
- data/Gemfile +4 -0
- data/README.md +38 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/lulalala_address_tokenizer.rb +45 -0
- data/lib/lulalala_address_tokenizer/version.rb +3 -0
- data/lulalala_address_tokenizer.gemspec +27 -0
- metadata +95 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 37508767abe6d7128484245eae8ab83ff0baf168
|
|
4
|
+
data.tar.gz: 78e8693219023cf0e6223335b250d69808ccfc37
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: abcd4427aa3d668dd846f7cda3a23810348d1abc70aeac1875d383150ebec3d9d0d5cc56a57bdd8656bde4234efe74584499fd7ca45a8c0cc896561faac5afe7
|
|
7
|
+
data.tar.gz: c008a2ec2f92cfa4ec7456ec965f456ab4b87e5931ba0f1c78c4b04055dee0e0163141ad02a0ffa3354c618f5d7c56d434a6eba21b75a6be4389eb72d99a1207
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
# LulalalaAddressTokenizer
|
|
2
|
+
|
|
3
|
+
Postal addresses tokenizer using Wapiti model.
|
|
4
|
+
|
|
5
|
+
Intended for addresses in CJK (Chinese, Japanese Korean) characters.
|
|
6
|
+
After wapiti model labels each token(character), this gem combines adjacent word of the same label together.
|
|
7
|
+
This is important for CJK languages because its phrases (combination of words) are not separated by spaces.
|
|
8
|
+
|
|
9
|
+
台灣地址分詞用
|
|
10
|
+
|
|
11
|
+
## Installation
|
|
12
|
+
|
|
13
|
+
Add this line to your application's Gemfile:
|
|
14
|
+
|
|
15
|
+
```ruby
|
|
16
|
+
gem 'lulalala_address_tokenizer'
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
And then execute:
|
|
20
|
+
|
|
21
|
+
$ bundle
|
|
22
|
+
|
|
23
|
+
Or install it yourself as:
|
|
24
|
+
|
|
25
|
+
$ gem install lulalala_address_tokenizer
|
|
26
|
+
|
|
27
|
+
## Usage
|
|
28
|
+
|
|
29
|
+
```
|
|
30
|
+
tokenizer = LulalalaAddressTokenizer.new('address.mod')
|
|
31
|
+
tokenizer.parse("AA縣BB鎮CC路D號")
|
|
32
|
+
# {"city"=>"AA縣", "district"=>"BB鎮", "street"=>"CC路", "housenumber"=>"D號"}
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
## Contributing
|
|
36
|
+
|
|
37
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/lulalala_address_tokenizer.
|
|
38
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
|
|
3
|
+
require "bundler/setup"
|
|
4
|
+
require "lulalala_address_tokenizer"
|
|
5
|
+
|
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
|
8
|
+
|
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
|
10
|
+
# require "pry"
|
|
11
|
+
# Pry.start
|
|
12
|
+
|
|
13
|
+
require "irb"
|
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
require "lulalala_address_tokenizer/version"
|
|
2
|
+
require "wapiti"
|
|
3
|
+
|
|
4
|
+
class LulalalaAddressTokenizer
|
|
5
|
+
# @params model_path [#read]
|
|
6
|
+
def initialize(model_path)
|
|
7
|
+
@model = Wapiti.load(model_path)
|
|
8
|
+
end
|
|
9
|
+
|
|
10
|
+
# @params address [String]
|
|
11
|
+
def parse(address)
|
|
12
|
+
segments = []
|
|
13
|
+
address.chars.each do |ch|
|
|
14
|
+
segments << "#{ch} n"
|
|
15
|
+
end
|
|
16
|
+
result = @model.label [segments]
|
|
17
|
+
join(result.first)
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
private
|
|
21
|
+
|
|
22
|
+
def join(segments)
|
|
23
|
+
result = {}
|
|
24
|
+
|
|
25
|
+
current_phase = ''
|
|
26
|
+
previous_mark = nil
|
|
27
|
+
segments.each do |s|
|
|
28
|
+
mark = s.last
|
|
29
|
+
ss = s.first.split(' ')
|
|
30
|
+
word = ss.first
|
|
31
|
+
|
|
32
|
+
if previous_mark == mark
|
|
33
|
+
current_phase << word
|
|
34
|
+
else
|
|
35
|
+
result[previous_mark] = current_phase
|
|
36
|
+
previous_mark = mark
|
|
37
|
+
current_phase = word
|
|
38
|
+
end
|
|
39
|
+
end
|
|
40
|
+
result[previous_mark] = current_phase
|
|
41
|
+
|
|
42
|
+
result.shift
|
|
43
|
+
result
|
|
44
|
+
end
|
|
45
|
+
end
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
|
4
|
+
require 'lulalala_address_tokenizer/version'
|
|
5
|
+
|
|
6
|
+
Gem::Specification.new do |spec|
|
|
7
|
+
spec.name = "lulalala_address_tokenizer"
|
|
8
|
+
spec.version = LulalalaAddressTokenizer::VERSION
|
|
9
|
+
spec.authors = ["lulalala"]
|
|
10
|
+
spec.email = ["mark@goodlife.tw"]
|
|
11
|
+
|
|
12
|
+
spec.summary = %q{Postal addresses tokenizer using Wapiti model}
|
|
13
|
+
spec.description = %q{Postal addresses tokenizer using Wapiti model}
|
|
14
|
+
spec.homepage = "https://github.com/lulalala/address_tokenizer"
|
|
15
|
+
|
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
|
17
|
+
f.match(%r{^(test|spec|features)/})
|
|
18
|
+
end
|
|
19
|
+
spec.bindir = "exe"
|
|
20
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
|
21
|
+
spec.require_paths = ["lib"]
|
|
22
|
+
|
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.13"
|
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
|
25
|
+
|
|
26
|
+
spec.add_dependency "wapiti"
|
|
27
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: lulalala_address_tokenizer
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- lulalala
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: exe
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2016-11-20 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: '1.13'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - "~>"
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '1.13'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: rake
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - "~>"
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '10.0'
|
|
34
|
+
type: :development
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - "~>"
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '10.0'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: wapiti
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - ">="
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '0'
|
|
48
|
+
type: :runtime
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - ">="
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '0'
|
|
55
|
+
description: Postal addresses tokenizer using Wapiti model
|
|
56
|
+
email:
|
|
57
|
+
- mark@goodlife.tw
|
|
58
|
+
executables: []
|
|
59
|
+
extensions: []
|
|
60
|
+
extra_rdoc_files: []
|
|
61
|
+
files:
|
|
62
|
+
- ".gitignore"
|
|
63
|
+
- Gemfile
|
|
64
|
+
- README.md
|
|
65
|
+
- Rakefile
|
|
66
|
+
- bin/console
|
|
67
|
+
- bin/setup
|
|
68
|
+
- lib/lulalala_address_tokenizer.rb
|
|
69
|
+
- lib/lulalala_address_tokenizer/version.rb
|
|
70
|
+
- lulalala_address_tokenizer.gemspec
|
|
71
|
+
homepage: https://github.com/lulalala/address_tokenizer
|
|
72
|
+
licenses: []
|
|
73
|
+
metadata: {}
|
|
74
|
+
post_install_message:
|
|
75
|
+
rdoc_options: []
|
|
76
|
+
require_paths:
|
|
77
|
+
- lib
|
|
78
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
79
|
+
requirements:
|
|
80
|
+
- - ">="
|
|
81
|
+
- !ruby/object:Gem::Version
|
|
82
|
+
version: '0'
|
|
83
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
84
|
+
requirements:
|
|
85
|
+
- - ">="
|
|
86
|
+
- !ruby/object:Gem::Version
|
|
87
|
+
version: '0'
|
|
88
|
+
requirements: []
|
|
89
|
+
rubyforge_project:
|
|
90
|
+
rubygems_version: 2.4.5
|
|
91
|
+
signing_key:
|
|
92
|
+
specification_version: 4
|
|
93
|
+
summary: Postal addresses tokenizer using Wapiti model
|
|
94
|
+
test_files: []
|
|
95
|
+
has_rdoc:
|