web_loader 0.9.0

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA256:
3
+ metadata.gz: 2ed8a99e656a31617dee550c63429228f43a2a115bdda906188ae52686c53910
4
+ data.tar.gz: 834b58c25960ddc529c471453cfa8aeeb497cebbfe2a3d3a7aa13845b1e16553
5
+ SHA512:
6
+ metadata.gz: bad1f2388b2fad7358d6caa914855e612670da8015d16d4d2b5ddd34241956fc38083ba43a274dbbd9c4a2d58aa50d5c28dea3a535ff6f4c371fa624d666ccf4
7
+ data.tar.gz: a6de1f0c0d61a36287f432733c2e52aad5008d6fa204cce3b5edfba656114d559ef11075dcd6d6bc122c97d8c78c43fae22303196fcdfb3ed1767fbc389b3c3d
data/.idea/.gitignore ADDED
@@ -0,0 +1,8 @@
1
+ # Default ignored files
2
+ /shelf/
3
+ /workspace.xml
4
+ # Editor-based HTTP Client requests
5
+ /httpRequests/
6
+ # Datasource local storage ignored files
7
+ /dataSources/
8
+ /dataSources.local.xml
data/.idea/misc.xml ADDED
@@ -0,0 +1,6 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <project version="4">
3
+ <component name="ProjectRootManager" version="2" project-jdk-name="rbenv: 3.1.4" project-jdk-type="RUBY_SDK">
4
+ <output url="file://$PROJECT_DIR$/out" />
5
+ </component>
6
+ </project>
data/.idea/modules.xml ADDED
@@ -0,0 +1,8 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <project version="4">
3
+ <component name="ProjectModuleManager">
4
+ <modules>
5
+ <module fileurl="file://$PROJECT_DIR$/web_loader.iml" filepath="$PROJECT_DIR$/web_loader.iml" />
6
+ </modules>
7
+ </component>
8
+ </project>
data/.idea/vcs.xml ADDED
@@ -0,0 +1,6 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <project version="4">
3
+ <component name="VcsDirectoryMappings">
4
+ <mapping directory="" vcs="Git" />
5
+ </component>
6
+ </project>
@@ -0,0 +1,84 @@
1
+ # Contributor Covenant Code of Conduct
2
+
3
+ ## Our Pledge
4
+
5
+ We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
6
+
7
+ We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
8
+
9
+ ## Our Standards
10
+
11
+ Examples of behavior that contributes to a positive environment for our community include:
12
+
13
+ * Demonstrating empathy and kindness toward other people
14
+ * Being respectful of differing opinions, viewpoints, and experiences
15
+ * Giving and gracefully accepting constructive feedback
16
+ * Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
17
+ * Focusing on what is best not just for us as individuals, but for the overall community
18
+
19
+ Examples of unacceptable behavior include:
20
+
21
+ * The use of sexualized language or imagery, and sexual attention or
22
+ advances of any kind
23
+ * Trolling, insulting or derogatory comments, and personal or political attacks
24
+ * Public or private harassment
25
+ * Publishing others' private information, such as a physical or email
26
+ address, without their explicit permission
27
+ * Other conduct which could reasonably be considered inappropriate in a
28
+ professional setting
29
+
30
+ ## Enforcement Responsibilities
31
+
32
+ Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
33
+
34
+ Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
35
+
36
+ ## Scope
37
+
38
+ This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
39
+
40
+ ## Enforcement
41
+
42
+ Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at src@srcw.net. All complaints will be reviewed and investigated promptly and fairly.
43
+
44
+ All community leaders are obligated to respect the privacy and security of the reporter of any incident.
45
+
46
+ ## Enforcement Guidelines
47
+
48
+ Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
49
+
50
+ ### 1. Correction
51
+
52
+ **Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
53
+
54
+ **Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
55
+
56
+ ### 2. Warning
57
+
58
+ **Community Impact**: A violation through a single incident or series of actions.
59
+
60
+ **Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
61
+
62
+ ### 3. Temporary Ban
63
+
64
+ **Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
65
+
66
+ **Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
67
+
68
+ ### 4. Permanent Ban
69
+
70
+ **Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
71
+
72
+ **Consequence**: A permanent ban from any sort of public interaction within the community.
73
+
74
+ ## Attribution
75
+
76
+ This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0,
77
+ available at https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
78
+
79
+ Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity).
80
+
81
+ [homepage]: https://www.contributor-covenant.org
82
+
83
+ For answers to common questions about this code of conduct, see the FAQ at
84
+ https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/translations.
data/Gemfile ADDED
@@ -0,0 +1,10 @@
1
+ # frozen_string_literal: true
2
+
3
+ source "https://rubygems.org"
4
+
5
+ # Specify your gem's dependencies in web_loader.gemspec
6
+ gemspec
7
+
8
+ gem "rake", "~> 13.0"
9
+
10
+ gem "minitest", "~> 5.0"
data/Gemfile.lock ADDED
@@ -0,0 +1,21 @@
1
+ PATH
2
+ remote: .
3
+ specs:
4
+ web_loader (0.9.0)
5
+
6
+ GEM
7
+ remote: https://rubygems.org/
8
+ specs:
9
+ minitest (5.15.0)
10
+ rake (13.0.6)
11
+
12
+ PLATFORMS
13
+ x86_64-darwin-22
14
+
15
+ DEPENDENCIES
16
+ minitest (~> 5.0)
17
+ rake (~> 13.0)
18
+ web_loader!
19
+
20
+ BUNDLED WITH
21
+ 2.4.10
data/LICENSE.txt ADDED
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2023 src
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in
13
+ all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21
+ THE SOFTWARE.
data/README.md ADDED
@@ -0,0 +1,39 @@
1
+ # WebLoader
2
+
3
+ TODO: Delete this and the text below, and describe your gem
4
+
5
+ Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/web_loader`. To experiment with that code, run `bin/console` for an interactive prompt.
6
+
7
+ ## Installation
8
+
9
+ TODO: Replace `UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG` with your gem name right after releasing it to RubyGems.org. Please do not do it earlier due to security reasons. Alternatively, replace this section with instructions to install your gem from git if you don't plan to release to RubyGems.org.
10
+
11
+ Install the gem and add to the application's Gemfile by executing:
12
+
13
+ $ bundle add UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
14
+
15
+ If bundler is not being used to manage dependencies, install the gem by executing:
16
+
17
+ $ gem install UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
18
+
19
+ ## Usage
20
+
21
+ TODO: Write usage instructions here
22
+
23
+ ## Development
24
+
25
+ After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
26
+
27
+ To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
28
+
29
+ ## Contributing
30
+
31
+ Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/web_loader. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/[USERNAME]/web_loader/blob/master/CODE_OF_CONDUCT.md).
32
+
33
+ ## License
34
+
35
+ The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
36
+
37
+ ## Code of Conduct
38
+
39
+ Everyone interacting in the WebLoader project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/web_loader/blob/master/CODE_OF_CONDUCT.md).
data/Rakefile ADDED
@@ -0,0 +1,12 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "bundler/gem_tasks"
4
+ require "rake/testtask"
5
+
6
+ Rake::TestTask.new(:test) do |t|
7
+ t.libs << "test"
8
+ t.libs << "lib"
9
+ t.test_files = FileList["test/**/test_*.rb"]
10
+ end
11
+
12
+ task default: :test
data/build.sh ADDED
@@ -0,0 +1,18 @@
1
+ #!/bin/sh
2
+ # rmagick for sierra
3
+ export PKG_CONFIG_PATH=/usr/local/opt/imagemagick@6/lib/pkgconfig
4
+ #export PATH=/usr/local/Cellar/imagemagick@6/6.9.7-5/bin:$PATH
5
+
6
+ bundle_dir=./vendor/bundle
7
+ if [ -d "$bundle_dir" ] ; then
8
+ /bin/rm -rf "$bundle_dir"
9
+ bundle update
10
+ else
11
+ /bin/rm -rf "$bundle_dir"
12
+ bundle install --path "$bundle_dir"
13
+ fi
14
+
15
+
16
+
17
+
18
+
data/exe/web_loader ADDED
@@ -0,0 +1,3 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "web_loader"
@@ -0,0 +1,56 @@
1
+ require 'digest/md5'
2
+ require 'fileutils'
3
+ require 'yaml'
4
+
5
+ module WebLoader
6
+
7
+ # 以下のようなファイルをキャッシュディレクトリの下に作成。
8
+ # キャッシュディレクトリは絶対パスであることを想定している。
9
+ # __cache__055a266970912bcbd34f88692528c20e.html
10
+ # __cache__055a266970912bcbd34f88692528c20e.yml
11
+ #
12
+ class Cache
13
+ PREFIX = "__cache__"
14
+ # CACHE_LIMIT = 3600
15
+ CACHE_LIMIT = 60
16
+
17
+ def self.basename(url)
18
+ Digest::MD5.hexdigest(url)
19
+ end
20
+
21
+ def self.header_filename(dir, url)
22
+ File.join(dir, PREFIX + basename(url) + ".yml")
23
+ end
24
+
25
+ def self.content_filename(dir, url)
26
+ File.join(dir, PREFIX + basename(url) + ".html")
27
+ end
28
+
29
+ def self.load_content(dir, url)
30
+ header_path = header_filename(dir, url)
31
+ content_path = content_filename(dir, url)
32
+ content = nil
33
+ if FileTest.file?(header_path) && FileTest.file?(content_path)
34
+ content = File.read(content_path)
35
+ end
36
+ content
37
+ end
38
+
39
+ def self.write(dir, url, code, content)
40
+ header_path = header_filename(dir, url)
41
+ YAML.dump({"url" => url, "code" => code}, open(header_path, "w"))
42
+ content_path = content_filename(dir, url)
43
+ File.write(content_path, content)
44
+ end
45
+
46
+ def self.clear(dir)
47
+ Dir.glob("#{dir}/#{PREFIX}*.{yml,html}").each do |path|
48
+ diff = Time.now - File.mtime(path)
49
+ # 1時間以上昔のキャッシュは使用しない
50
+ too_old_cache = diff > CACHE_LIMIT
51
+ FileUtils.rm(path) if too_old_cache
52
+ end
53
+ end
54
+
55
+ end
56
+ end
@@ -0,0 +1,80 @@
1
+ require 'open-uri'
2
+ require 'net/http'
3
+ require 'uri'
4
+ require 'kconv'
5
+
6
+ module WebLoader
7
+ class Command
8
+ include WebLoader::Utils
9
+
10
+ USER_AGENT = "WebLoader"
11
+ CACHE_DIR = './cache'
12
+
13
+ def self.save_image(url, file)
14
+ # キャッシュせず単に保存する
15
+ cmd= Command.new
16
+ cmd.use_cache = false
17
+ cmd.binary = true
18
+ content = cmd.load(url)
19
+ File.binwrite(file, content)
20
+ end
21
+
22
+ def initialize
23
+ @use_cache = true
24
+ @load_cache_page = false #キャッシュを読み込んだかどうか
25
+ @cache_dir = File.expand_path(CACHE_DIR)
26
+ @user_agent = "#{USER_AGENT}/#{VERSION}"
27
+ @binary = false
28
+ end
29
+
30
+ attr_reader :load_cache_page
31
+ attr_accessor :use_cache, :cache_dir, :binary, :user_agent
32
+
33
+ def load(url, limit = 10)
34
+ raise ArgumentError, 'HTTP redirect too deep' if limit == 0
35
+
36
+ @load_cache_page = false
37
+ content = try_load_cache(url)
38
+ if content
39
+ @load_cache_page = true
40
+ return content
41
+ end
42
+
43
+ uri = URI.parse(url)
44
+ http = Net::HTTP.new(uri.host, uri.port)
45
+ if uri.scheme == 'https'
46
+ http.use_ssl = true
47
+ http.verify_mode = OpenSSL::SSL::VERIFY_NONE
48
+ end
49
+ response, = http.get(uri.request_uri, 'User-Agent' => @user_agent) # request_uri=path + '?' + query
50
+ case response
51
+ when Net::HTTPSuccess
52
+ # responseがNet::HTTPSuccessのサブクラスの場合成功とみなし読み込んだ内容を返す
53
+ body = response.body
54
+ unless @binary
55
+ # デフォルトでは ASCII-8BITが帰ってくる。
56
+ # Content-Typeのcharsetとみなす。
57
+ # https://bugs.ruby-lang.org/issues/2567
58
+ encoding = response.type_params['charset']
59
+ body = toutf8(body, encoding)
60
+ end
61
+ Cache.write(@cache_dir, url, response.code, body) if @use_cache
62
+ return body
63
+ when Net::HTTPRedirection
64
+ load_page(self.class.to_redirect_url(uri, response['location']), limit - 1)
65
+ else
66
+ puts "error #{url}"
67
+ # それ以外は対応した例外を発生
68
+ response.value
69
+ end
70
+ end
71
+
72
+ private
73
+ def try_load_cache(url)
74
+ return nil unless @use_cache
75
+ Cache.clear(@cache_dir)
76
+ Cache.load_content(@cache_dir, url)
77
+ end
78
+
79
+ end
80
+ end
@@ -0,0 +1,46 @@
1
+ module WebLoader
2
+ module Utils
3
+ UTF_8 = 'UTF-8'
4
+ def toutf8(str, response_encoding)
5
+ # 2022/04/04(月)
6
+ # GITHUBのアポストロフィ(&#x2019 U+2019)が文字化け問題に対処するために新設。
7
+ # 原因は直接Kconv.toutf8にresponse.bodyをわたしていたことなので(Kconvのguessが失敗していたと思われる)、
8
+ # response.type_paramsを見てそれにforce_encodingすることで対処する。渡されているcharsetとWebページの文字コードが一致していればこれで問題はないはず。
9
+ org_str = str.dup
10
+ result = str
11
+ begin
12
+ if response_encoding.to_s.length > 0 # nilでないかつ長さが0以上
13
+ # responseで指定された文字コードであるとみなす
14
+ str.force_encoding(response_encoding)
15
+ if str.valid_encoding?
16
+ # 指定された文字コードとみなせた場合
17
+ if response_encoding != UTF_8
18
+ # エンコーディングがUTF8じゃない場合返還する
19
+ result = str.encode(UTF_8, invalid: :replace, undef: :replace)
20
+ else
21
+ # UTF8の場合そのまま
22
+ result = str
23
+ end
24
+ else
25
+ # 指定された文字コードとみなせない場合元の文字列を返す
26
+ result = org_str
27
+ end
28
+ else
29
+ # responseで文字コードが指定されていない場合Kconvを使用
30
+ result = Kconv.toutf8(str)
31
+ end
32
+ rescue => ex
33
+ puts ex.message
34
+ end
35
+ result
36
+ end
37
+
38
+ def to_redirect_url(orig_uri, location)
39
+ redirect_url = location
40
+ if location =~ /^\//
41
+ redirect_url = URI.join(orig_uri, location).to_s
42
+ end
43
+ redirect_url
44
+ end
45
+ end
46
+ end
@@ -0,0 +1,5 @@
1
+ # frozen_string_literal: true
2
+
3
+ module WebLoader
4
+ VERSION = "0.9.0"
5
+ end
data/lib/web_loader.rb ADDED
@@ -0,0 +1,12 @@
1
+ # frozen_string_literal: true
2
+
3
+ require_relative "web_loader/version"
4
+ require_relative "web_loader/utils"
5
+ require_relative "web_loader/cache"
6
+ require_relative "web_loader/command"
7
+
8
+ module WebLoader
9
+ class Error < StandardError; end
10
+ # Your code goes here...
11
+
12
+ end
@@ -0,0 +1,4 @@
1
+ module WebLoader
2
+ VERSION: String
3
+ # See the writing guide of rbs: https://github.com/ruby/rbs#guides
4
+ end
data/web_loader.iml ADDED
@@ -0,0 +1,17 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <module type="RUBY_MODULE" version="4">
3
+ <component name="NewModuleRootManager" inherit-compiler-output="true">
4
+ <exclude-output />
5
+ <content url="file://$MODULE_DIR$" />
6
+ <orderEntry type="inheritedJdk" />
7
+ <orderEntry type="sourceFolder" forTests="false" />
8
+ <orderEntry type="library" scope="PROVIDED" name="bundler (v2.4.10, rbenv: 3.1.4) [gem]" level="application" />
9
+ <orderEntry type="library" scope="PROVIDED" name="minitest (v5.15.0, rbenv: 3.1.4) [gem]" level="application" />
10
+ <orderEntry type="library" scope="PROVIDED" name="rake (v13.0.6, rbenv: 3.1.4) [gem]" level="application" />
11
+ </component>
12
+ <component name="RakeTasksCache">
13
+ <option name="myRootTask">
14
+ <RakeTaskImpl id="rake" />
15
+ </option>
16
+ </component>
17
+ </module>
metadata ADDED
@@ -0,0 +1,66 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: web_loader
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.9.0
5
+ platform: ruby
6
+ authors:
7
+ - src
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2023-07-31 00:00:00.000000000 Z
12
+ dependencies: []
13
+ description: Web loader.
14
+ email:
15
+ - src@srcw.net
16
+ executables:
17
+ - web_loader
18
+ extensions: []
19
+ extra_rdoc_files: []
20
+ files:
21
+ - ".idea/.gitignore"
22
+ - ".idea/misc.xml"
23
+ - ".idea/modules.xml"
24
+ - ".idea/vcs.xml"
25
+ - CODE_OF_CONDUCT.md
26
+ - Gemfile
27
+ - Gemfile.lock
28
+ - LICENSE.txt
29
+ - README.md
30
+ - Rakefile
31
+ - build.sh
32
+ - exe/web_loader
33
+ - lib/web_loader.rb
34
+ - lib/web_loader/cache.rb
35
+ - lib/web_loader/command.rb
36
+ - lib/web_loader/utils.rb
37
+ - lib/web_loader/version.rb
38
+ - sig/web_loader.rbs
39
+ - web_loader.iml
40
+ homepage: https://srcw.net
41
+ licenses:
42
+ - MIT
43
+ metadata:
44
+ homepage_uri: https://srcw.net
45
+ source_code_uri: https://srcw.net
46
+ changelog_uri: https://srcw.net
47
+ post_install_message:
48
+ rdoc_options: []
49
+ require_paths:
50
+ - lib
51
+ required_ruby_version: !ruby/object:Gem::Requirement
52
+ requirements:
53
+ - - ">="
54
+ - !ruby/object:Gem::Version
55
+ version: 2.6.0
56
+ required_rubygems_version: !ruby/object:Gem::Requirement
57
+ requirements:
58
+ - - ">="
59
+ - !ruby/object:Gem::Version
60
+ version: '0'
61
+ requirements: []
62
+ rubygems_version: 3.2.33
63
+ signing_key:
64
+ specification_version: 4
65
+ summary: Web loader.
66
+ test_files: []