law-japan 0.0.1 → 0.0.2
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 +4 -4
- data/bin/law-japan +8 -0
- data/law-japan.gemspec +1 -2
- data/lib/law/japan.rb +1 -1
- data/lib/law/japan/cli.rb +17 -0
- data/lib/law/japan/e_gov.rb +11 -44
- data/lib/law/japan/git.rb +54 -0
- data/lib/law/japan/version.rb +1 -1
- metadata +16 -28
- data/lib/law/japan/e_gov/converter.rb +0 -45
- data/lib/law/japan/e_gov/downloader.rb +0 -75
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 5e20792ff38fdcd20a8852d256e7b1d704ba28ef
|
|
4
|
+
data.tar.gz: 58d5cd169c6cbbb82fd1ed9c795895bc469451b7
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: f5abdf09ecda9d49492ce30c434b81a0a43e3e81237eb42a67732dc6437dd50e836b19323380a42354f767feacd829dca9359a52ca507981ef8120a106f9b7d9
|
|
7
|
+
data.tar.gz: f700e710471e50d18dcea55c20a451a232e04d3816889310337d0c82d10acc460def9cdbbe67bde857ca8539ad56945ce3da30745f92e52a381410e2e17bc753
|
data/bin/law-japan
ADDED
data/law-japan.gemspec
CHANGED
|
@@ -19,10 +19,9 @@ Gem::Specification.new do |spec|
|
|
|
19
19
|
spec.require_paths = ["lib"]
|
|
20
20
|
|
|
21
21
|
spec.add_dependency "git"
|
|
22
|
+
spec.add_dependency "thor"
|
|
22
23
|
|
|
23
24
|
spec.add_development_dependency "bundler", "~> 1.5"
|
|
24
25
|
spec.add_development_dependency "rake"
|
|
25
26
|
spec.add_development_dependency "pry"
|
|
26
|
-
spec.add_development_dependency "mechanize"
|
|
27
|
-
spec.add_development_dependency "nokogiri"
|
|
28
27
|
end
|
data/lib/law/japan.rb
CHANGED
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
require "law/japan"
|
|
2
|
+
|
|
3
|
+
require "thor"
|
|
4
|
+
|
|
5
|
+
class Law::Japan::CLI < Thor
|
|
6
|
+
desc "install", "Install git repo"
|
|
7
|
+
def install
|
|
8
|
+
e_gov = Law::Japan::EGov::CLI.new
|
|
9
|
+
e_gov.install
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
desc "update", "Pull the latest data"
|
|
13
|
+
def update
|
|
14
|
+
e_gov = Law::Japan::EGov::CLI.new
|
|
15
|
+
e_gov.pull
|
|
16
|
+
end
|
|
17
|
+
end
|
data/lib/law/japan/e_gov.rb
CHANGED
|
@@ -1,55 +1,22 @@
|
|
|
1
1
|
require "law/japan"
|
|
2
|
+
require "law/japan/git"
|
|
2
3
|
|
|
3
|
-
require "git"
|
|
4
4
|
require "logger"
|
|
5
5
|
|
|
6
6
|
class Law::Japan::EGov
|
|
7
|
-
|
|
7
|
+
include Law::Japan::Git
|
|
8
8
|
|
|
9
|
-
|
|
10
|
-
|
|
9
|
+
HomeDir = File.join(Law::Japan::HomeDir, "e_gov")
|
|
10
|
+
RepoDir = File.join(HomeDir, "repo")
|
|
11
|
+
RepoURL = "https://github.com/riywo/law-japan-e_gov-text.git"
|
|
11
12
|
|
|
12
|
-
def initialize
|
|
13
|
-
|
|
13
|
+
def initialize(repo_dir: nil, repo_url: nil, logger: nil)
|
|
14
|
+
@repo_dir = repo_dir || RepoDir
|
|
15
|
+
@repo_url = repo_url || RepoURL
|
|
16
|
+
@logger = logger || Logger.new(STDOUT)
|
|
14
17
|
end
|
|
15
18
|
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
text_git.pull
|
|
19
|
-
end
|
|
20
|
-
|
|
21
|
-
def download!
|
|
22
|
-
Downloader.new(html_data_dir).download!
|
|
23
|
-
end
|
|
24
|
-
|
|
25
|
-
def convert!
|
|
26
|
-
Converter.new(html_data_dir, text_data_dir).convert!
|
|
27
|
-
end
|
|
28
|
-
|
|
29
|
-
private
|
|
30
|
-
|
|
31
|
-
def html_data_dir
|
|
32
|
-
File.join(html_git.dir.path, "data")
|
|
33
|
-
end
|
|
34
|
-
|
|
35
|
-
def text_data_dir
|
|
36
|
-
File.join(text_git.dir.path, "data")
|
|
37
|
-
end
|
|
38
|
-
|
|
39
|
-
def git_open_or_clone(repo_url, name)
|
|
40
|
-
Git.open(File.join(SourceDir, name), log: Logger.new(STDOUT))
|
|
41
|
-
rescue
|
|
42
|
-
Git.clone(repo_url, name, path: SourceDir, log: Logger.new(STDOUT))
|
|
43
|
-
end
|
|
44
|
-
|
|
45
|
-
def html_git
|
|
46
|
-
@html_git ||= git_open_or_clone(HtmlRepoURL, "html")
|
|
47
|
-
end
|
|
48
|
-
|
|
49
|
-
def text_git
|
|
50
|
-
@text_git ||= git_open_or_clone(TextRepoURL, "text")
|
|
19
|
+
class CLI < Law::Japan::EGov
|
|
20
|
+
include Law::Japan::Git::CLI
|
|
51
21
|
end
|
|
52
22
|
end
|
|
53
|
-
|
|
54
|
-
require "law/japan/e_gov/downloader"
|
|
55
|
-
require "law/japan/e_gov/converter"
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
require "law/japan"
|
|
2
|
+
|
|
3
|
+
require "git"
|
|
4
|
+
|
|
5
|
+
module Law::Japan::Git
|
|
6
|
+
def data_dir
|
|
7
|
+
@data_dir ||= File.join(git.dir.path, "data")
|
|
8
|
+
end
|
|
9
|
+
|
|
10
|
+
private
|
|
11
|
+
|
|
12
|
+
def git
|
|
13
|
+
unless @git
|
|
14
|
+
begin
|
|
15
|
+
@git ||= ::Git.open(repo_dir, log: logger)
|
|
16
|
+
rescue ArgumentError
|
|
17
|
+
raise "#{repo_dir} has not been ready yet"
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
origin_url = @git.remote("origin").url
|
|
21
|
+
if origin_url != repo_url
|
|
22
|
+
raise "origin url(#{origin_url}) must be #{repo_url}"
|
|
23
|
+
end
|
|
24
|
+
end
|
|
25
|
+
@git
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
def repo_dir
|
|
29
|
+
@repo_dir
|
|
30
|
+
end
|
|
31
|
+
|
|
32
|
+
def repo_url
|
|
33
|
+
@repo_url
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
def logger
|
|
37
|
+
@logger
|
|
38
|
+
end
|
|
39
|
+
|
|
40
|
+
module CLI
|
|
41
|
+
def install
|
|
42
|
+
FileUtils.rm_rf(repo_dir)
|
|
43
|
+
|
|
44
|
+
name = File.basename(repo_dir)
|
|
45
|
+
path = File.dirname(repo_dir)
|
|
46
|
+
FileUtils.mkdir_p(path)
|
|
47
|
+
::Git.clone(repo_url, name, path: path)
|
|
48
|
+
end
|
|
49
|
+
|
|
50
|
+
def pull
|
|
51
|
+
git.pull
|
|
52
|
+
end
|
|
53
|
+
end
|
|
54
|
+
end
|
data/lib/law/japan/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: law-japan
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ryosuke IWANAGA
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2014-02-
|
|
11
|
+
date: 2014-02-16 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: git
|
|
@@ -25,27 +25,13 @@ dependencies:
|
|
|
25
25
|
- !ruby/object:Gem::Version
|
|
26
26
|
version: '0'
|
|
27
27
|
- !ruby/object:Gem::Dependency
|
|
28
|
-
name:
|
|
29
|
-
requirement: !ruby/object:Gem::Requirement
|
|
30
|
-
requirements:
|
|
31
|
-
- - "~>"
|
|
32
|
-
- !ruby/object:Gem::Version
|
|
33
|
-
version: '1.5'
|
|
34
|
-
type: :development
|
|
35
|
-
prerelease: false
|
|
36
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
-
requirements:
|
|
38
|
-
- - "~>"
|
|
39
|
-
- !ruby/object:Gem::Version
|
|
40
|
-
version: '1.5'
|
|
41
|
-
- !ruby/object:Gem::Dependency
|
|
42
|
-
name: rake
|
|
28
|
+
name: thor
|
|
43
29
|
requirement: !ruby/object:Gem::Requirement
|
|
44
30
|
requirements:
|
|
45
31
|
- - ">="
|
|
46
32
|
- !ruby/object:Gem::Version
|
|
47
33
|
version: '0'
|
|
48
|
-
type: :
|
|
34
|
+
type: :runtime
|
|
49
35
|
prerelease: false
|
|
50
36
|
version_requirements: !ruby/object:Gem::Requirement
|
|
51
37
|
requirements:
|
|
@@ -53,21 +39,21 @@ dependencies:
|
|
|
53
39
|
- !ruby/object:Gem::Version
|
|
54
40
|
version: '0'
|
|
55
41
|
- !ruby/object:Gem::Dependency
|
|
56
|
-
name:
|
|
42
|
+
name: bundler
|
|
57
43
|
requirement: !ruby/object:Gem::Requirement
|
|
58
44
|
requirements:
|
|
59
|
-
- - "
|
|
45
|
+
- - "~>"
|
|
60
46
|
- !ruby/object:Gem::Version
|
|
61
|
-
version: '
|
|
47
|
+
version: '1.5'
|
|
62
48
|
type: :development
|
|
63
49
|
prerelease: false
|
|
64
50
|
version_requirements: !ruby/object:Gem::Requirement
|
|
65
51
|
requirements:
|
|
66
|
-
- - "
|
|
52
|
+
- - "~>"
|
|
67
53
|
- !ruby/object:Gem::Version
|
|
68
|
-
version: '
|
|
54
|
+
version: '1.5'
|
|
69
55
|
- !ruby/object:Gem::Dependency
|
|
70
|
-
name:
|
|
56
|
+
name: rake
|
|
71
57
|
requirement: !ruby/object:Gem::Requirement
|
|
72
58
|
requirements:
|
|
73
59
|
- - ">="
|
|
@@ -81,7 +67,7 @@ dependencies:
|
|
|
81
67
|
- !ruby/object:Gem::Version
|
|
82
68
|
version: '0'
|
|
83
69
|
- !ruby/object:Gem::Dependency
|
|
84
|
-
name:
|
|
70
|
+
name: pry
|
|
85
71
|
requirement: !ruby/object:Gem::Requirement
|
|
86
72
|
requirements:
|
|
87
73
|
- - ">="
|
|
@@ -97,7 +83,8 @@ dependencies:
|
|
|
97
83
|
description: This is a library for Japanese laws
|
|
98
84
|
email:
|
|
99
85
|
- riywo.jp@gmail.com
|
|
100
|
-
executables:
|
|
86
|
+
executables:
|
|
87
|
+
- law-japan
|
|
101
88
|
extensions: []
|
|
102
89
|
extra_rdoc_files: []
|
|
103
90
|
files:
|
|
@@ -107,11 +94,12 @@ files:
|
|
|
107
94
|
- LICENSE.txt
|
|
108
95
|
- README.md
|
|
109
96
|
- Rakefile
|
|
97
|
+
- bin/law-japan
|
|
110
98
|
- law-japan.gemspec
|
|
111
99
|
- lib/law/japan.rb
|
|
100
|
+
- lib/law/japan/cli.rb
|
|
112
101
|
- lib/law/japan/e_gov.rb
|
|
113
|
-
- lib/law/japan/
|
|
114
|
-
- lib/law/japan/e_gov/downloader.rb
|
|
102
|
+
- lib/law/japan/git.rb
|
|
115
103
|
- lib/law/japan/version.rb
|
|
116
104
|
homepage: https://github.com/riywo/law-japan
|
|
117
105
|
licenses:
|
|
@@ -1,45 +0,0 @@
|
|
|
1
|
-
require "law/japan/e_gov"
|
|
2
|
-
require "find"
|
|
3
|
-
require "nokogiri"
|
|
4
|
-
require "logger"
|
|
5
|
-
|
|
6
|
-
class Law::Japan::EGov::Converter
|
|
7
|
-
attr_reader :html_dir, :text_dir
|
|
8
|
-
|
|
9
|
-
def initialize(html_dir, text_dir)
|
|
10
|
-
@html_dir = html_dir
|
|
11
|
-
@text_dir = text_dir
|
|
12
|
-
end
|
|
13
|
-
|
|
14
|
-
def convert!
|
|
15
|
-
logger.info "Start converting all laws"
|
|
16
|
-
convert
|
|
17
|
-
logger.info "Finish converting all laws"
|
|
18
|
-
end
|
|
19
|
-
|
|
20
|
-
private
|
|
21
|
-
|
|
22
|
-
def logger
|
|
23
|
-
@logger ||= Logger.new STDOUT
|
|
24
|
-
end
|
|
25
|
-
|
|
26
|
-
def convert
|
|
27
|
-
Dir.chdir(html_dir) do
|
|
28
|
-
Dir.glob(File.join("**", "*.html")) do |path|
|
|
29
|
-
convert_html(path)
|
|
30
|
-
end
|
|
31
|
-
end
|
|
32
|
-
end
|
|
33
|
-
|
|
34
|
-
def convert_html(path)
|
|
35
|
-
dirname = File.dirname(path)
|
|
36
|
-
basename = File.basename(path, ".html")
|
|
37
|
-
target_dir = File.join(text_dir, dirname)
|
|
38
|
-
target_file = File.join(target_dir, "#{basename}.txt")
|
|
39
|
-
logger.info "Converting to #{target_file}"
|
|
40
|
-
|
|
41
|
-
FileUtils.mkdir_p target_dir
|
|
42
|
-
text = Nokogiri::HTML(open(path)).css("body").first.text
|
|
43
|
-
File.write(target_file, text)
|
|
44
|
-
end
|
|
45
|
-
end
|
|
@@ -1,75 +0,0 @@
|
|
|
1
|
-
require "law/japan/e_gov"
|
|
2
|
-
require "mechanize"
|
|
3
|
-
|
|
4
|
-
class Law::Japan::EGov::Downloader
|
|
5
|
-
module Mechanize::Form::Clearable
|
|
6
|
-
refine Mechanize::Form do
|
|
7
|
-
def clear_buttons
|
|
8
|
-
@clicked_buttons = []
|
|
9
|
-
end
|
|
10
|
-
end
|
|
11
|
-
end
|
|
12
|
-
using Mechanize::Form::Clearable
|
|
13
|
-
|
|
14
|
-
attr_reader :root_dir
|
|
15
|
-
def initialize(root_dir)
|
|
16
|
-
@root_dir = root_dir
|
|
17
|
-
end
|
|
18
|
-
|
|
19
|
-
def download!
|
|
20
|
-
logger.info "Start downloading all laws"
|
|
21
|
-
download
|
|
22
|
-
logger.info "Finish downloading all laws"
|
|
23
|
-
end
|
|
24
|
-
|
|
25
|
-
private
|
|
26
|
-
|
|
27
|
-
def logger
|
|
28
|
-
@logger ||= Logger.new STDOUT
|
|
29
|
-
end
|
|
30
|
-
|
|
31
|
-
def agent
|
|
32
|
-
unless @agent
|
|
33
|
-
@agent = Mechanize.new { |a| a.user_agent_alias = "Windows IE 9" }
|
|
34
|
-
@agent.log = Logger.new STDOUT
|
|
35
|
-
end
|
|
36
|
-
@agent
|
|
37
|
-
end
|
|
38
|
-
|
|
39
|
-
def index_page
|
|
40
|
-
@index_page ||= agent.get("http://law.e-gov.go.jp/cgi-bin/idxsearch.cgi")
|
|
41
|
-
end
|
|
42
|
-
|
|
43
|
-
def category_form
|
|
44
|
-
index_page.forms_with(name: "index")[2]
|
|
45
|
-
end
|
|
46
|
-
|
|
47
|
-
def download
|
|
48
|
-
category_form.buttons.each do |button|
|
|
49
|
-
category_name = button.node.next.text.gsub(/[ ]+/, "")
|
|
50
|
-
|
|
51
|
-
category_form.clear_buttons
|
|
52
|
-
list_page = agent.submit(category_form, button)
|
|
53
|
-
sleep 1
|
|
54
|
-
|
|
55
|
-
list_page.links.each do |link|
|
|
56
|
-
law_name = link.text
|
|
57
|
-
h_file_name = CGI.parse(link.uri.query)["H_FILE_NAME"].first
|
|
58
|
-
if h_file_name =~ /^([MTSH]\d{2})/
|
|
59
|
-
law_url = "http://law.e-gov.go.jp/htmldata/#{$1}/#{h_file_name}.html"
|
|
60
|
-
law_file = File.join(root_dir, category_name, "#{h_file_name}.html")
|
|
61
|
-
if File.exists? law_file
|
|
62
|
-
logger.info "File already exists for #{law_name} (#{law_file})"
|
|
63
|
-
else
|
|
64
|
-
logger.info "Start downloading for #{law_name} (url: #{law_url}, file: #{law_file})"
|
|
65
|
-
agent.download(law_url, law_file)
|
|
66
|
-
logger.info "Finish downloading for #{law_name} (url: #{law_url}, file: #{law_file})"
|
|
67
|
-
sleep 2
|
|
68
|
-
end
|
|
69
|
-
else
|
|
70
|
-
logger.warn "Invalid H_FILE_NAME #{h_file_name} for #{law_file}"
|
|
71
|
-
end
|
|
72
|
-
end
|
|
73
|
-
end
|
|
74
|
-
end
|
|
75
|
-
end
|