auto-correct 0.1.0.pre0 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 764ae2dccd3a0b65e9e5b071a3568620ade98d52
-  data.tar.gz: 01a7ea3ed26327875a22530df5722af6a5253f14
+SHA256:
+  metadata.gz: 12a8889fb7704f8233e1d83e029b0ae04565674396d549744e8c5a6d21156b4d
+  data.tar.gz: 042ab0e095196c62bc50f66bb9014fd71c93bcf48a815ca711e8c14e147b8a78
 SHA512:
-  metadata.gz: 8253513e4b424534a08ef122023b2d7c03c1f1fe518f4028bd0658e87884eee5bba95e9f002b0dd915c0f57bf08e8fc7f06c6710c15cd3a1020ec8f55a0ef494
-  data.tar.gz: 00fb083fcf99ddfbd779a57ad0a847ffc41e7dbff551ada550a35ba6a8118d50290af6c880897e97c549f2bb0425a56b54a44de7b14b356114990014863205cf
+  metadata.gz: 167d2641cf2f49f7b562e96d1c6ac38c27c8d212f07af3a42fc210fab4297635f1e82a67bc0e56026a984c3d4ff15b358bf0efe0d004aecbd6071fb414a59868
+  data.tar.gz: 4a2c9591624888b1ae8d1c5ece57a85a06d38f4f533e265fb0ac011093dfff244d549406762a01a2d87f523cafa7fa56960551fec06d6ccb6398b335f0268cbe

data/README.md

@@ -1,62 +1,97 @@
 # auto-correct
 
-自动纠正中文英文混排是一些不够好的写法，纠正错误的名词大小写。
+Automatically add whitespace between CJK (Chinese, Japanese, Korean) and half-width characters (alphabetical letters, numerical digits and symbols).
 
-Before
+中文、日语、韩语 + 英文混排自动纠正补充空格，此方式已在 Ruby China 使用多年，支持 HTML 处理。
 
-```
-[经验之谈]转行做ruby程序员的8个月, mysql 经验
-```
+[![Gem Version](https://badge.fury.io/rb/auto-correct.svg)](https://rubygems.org/gems/auto-correct) [![Build
+Status](https://api.travis-ci.org/huacnlee/auto-correct.svg?branch=master&.svg)](http://travis-ci.org/huacnlee/auto-correct)
 
-After
 
-```
-[经验之谈] 转行做 Ruby 程序员的 8 个月, MySQL 经验
-```
+## Other implements
+
+- Ruby - [auto-correct](https://github.com/huacnlee/auto-correct).
+- Go - [go-auto-correct](https://github.com/huacnlee/go-auto-correct).
+- Rust - [auto-correct.rs](https://github.com/huacnlee/auto-correct.rs).
+
+## Features
+
+- Auto add spacings between CJK (Chinese) and English words.
+- HTML content support.
+
+[Examples](https://github.com/huacnlee/auto-correct/blob/master/test/format_test.rb)
 
-[![Gem Version](https://badge.fury.io/rb/auto-space.png)](https://rubygems.org/gems/auto-space) [![Build
-Status](https://secure.travis-ci.org/huacnlee/auto-space.png?branch=master&.png)](http://travis-ci.org/huacnlee/auto-space)
+## Usage
 
-## 使用说明
+`AutoCorrect.format` method for plain text.
 
-```irb
-irb> require 'auto-correct'
-true
+```ruby
+AutoCorrect.format("那里找到Ruby China App下载地址")
+# => "那里找到 Ruby China App 下载地址"
 
-irb> "关于SSH连接的Permission denied(publickey).".auto_space!
-关于 SSH 连接的 Permission denied (publickey).
+AutoCorrect.format("Ruby 2.7版本第1次发布")
+# => "Ruby 2.7 版本第 1 次发布"
 
-irb> "怎样追踪一个repo的新feature 和进展呢?".auto_space!
-怎样追踪一个 repo 的新 feature 和进展呢?
+AutoCorrect.format("于3月10日开始")
+# => "于 3 月 10 日开始"
 
-irb> "vps上sessions不生效，但在本地的环境是ok的，why？".auto_space!
-vps 上 sessions 不生效，但在本地的环境是 OK 的，why?
+AutoCorrect.format("包装日期为2013年3月10日")
+# => "包装日期为2013年3月10日"
 
-irb> "bootstrap control-group对齐问题".auto_space!
-bootstrap control-group 对齐问
+AutoCorrect.format("生产环境中使用Ruby")
+# => "生产环境中使用 Ruby"
+
+AutoCorrect.format("本番環境でRubyを使用する")
+# => "本番環境で Ruby を使用する"
+
+AutoCorrect.format("프로덕션환경에서Ruby사용")
+# => "프로덕션환경에서 Ruby 사용"
+```
+
+`AutoCorrect.format_html` method for HTML content.
+
+```ruby
+AutoCorrect.format_html("<div><p>长桥LongBridge App下载</p><p>最新版本1.0</p></div>")
+# => "<div><p>长桥 LongBridge App 下载</p><p>最新版本 1.0</p></div>"
 ```
 
-## 性能
+## Benchmark
 
-详见 Rakefile
+Run `rake bench` to test:
 
 ```
-$ rake benchmark
-       user     system      total        real
-100 times  0.000000   0.000000   0.000000 (  0.002223)
-1000 times  0.030000   0.000000   0.030000 (  0.024711)
-10000 times  0.230000   0.000000   0.230000 (  0.240850)
+Warming up --------------------------------------
+     format 50 chars     1.886k i/100ms
+    format 100 chars     1.060k i/100ms
+    format 400 chars   342.000  i/100ms
+         format_html    85.000  i/100ms
+Calculating -------------------------------------
+     format 50 chars     18.842k (± 1.5%) i/s -     94.300k in   5.005815s
+    format 100 chars     10.357k (± 1.8%) i/s -     51.940k in   5.016770s
+    format 400 chars      3.336k (± 2.2%) i/s -     16.758k in   5.026230s
+         format_html    839.761  (± 2.1%) i/s -      4.250k in   5.063225s
 ```
 
-## TODO
+| Total chars | Duration |
+| ----- | ------- |
+| 50  | 0.33 ms |
+| 100  | 0.60 ms |
+| 400  | 2 ms |
+
+### FormatHTML
 
-* 'Foo'的"Bar" -> 'Foo' 的 "Bar"
-* 什么,时候 -> 什么, 时候 -> 什么，时候
+| Total chars | Duration |
+| ----- | ------- |
+| 2K  | 7 ms |
 
-## 应用案例
+## Use cases
 
-* [Ruby China](http://ruby-china.org) - 目前整站的标题都做了自动转换处理。
+* [Ruby China](https://ruby-china.org) - 目前整站的标题都做了自动转换处理。
 
-## 参考内容
+## Links
 
 * [Chinese Copywriting Guidelines](https://github.com/sparanoid/chinese-copywriting-guidelines)
+
+## License
+
+This project under MIT license.

data/lib/auto-correct.rb

@@ -1,40 +1,11 @@
-# coding: utf-8
-require "auto-correct/dicts"
+require "auto-correct/strategery"
+require "auto-correct/base"
+require "auto-correct/format"
+require "auto-correct/html"
+require "auto-correct/string"
+require "auto-correct/version"
 
-class String
-  def auto_space!
-    self.gsub! /((?![年月日号])\p{Han})([a-zA-Z0-9+$@#\[\(\/‘“])/u do
-      "#$1 #$2"
-    end
-
-    self.gsub! /([a-zA-Z0-9+$’”\]\)@#!\/]|[\d[年月日]]{2,})((?![年月日号])\p{Han})/u do
-      "#$1 #$2"
-    end
-    
-    # Fix () [] near the English and number
-    self.gsub! /([a-zA-Z0-9]+)([\[\(‘“])/u do
-      "#$1 #$2"
-    end
-    
-    self.gsub! /([\)\]’”])([a-zA-Z0-9]+)/u do
-      "#$1 #$2"
-    end
-    
-    self
-  end
-  
-  def auto_correct!
-    self.auto_space!
-    
-    self.gsub! /([\d\p{Han}]|\s|^)([a-zA-Z\d\-\_\.]+)([\d\p{Han}]|\s|$)/u do
-      key = "#$2".downcase
-      if AutoCorrect::DICTS.has_key?(key)
-        ["#$1",AutoCorrect::DICTS[key],"#$3"].join("")
-      else
-        "#$1#$2#$3"
-      end
-    end
-    
-    self
-  end
+class AutoCorrect
 end
+
+String.send :include, AutoCorrect::String

data/lib/auto-correct/base.rb

@@ -0,0 +1,13 @@
+class AutoCorrect
+  @@strategies = []
+
+  class << self
+    def rule(one, other, space: false, reverse: false)
+      @@strategies << AutoCorrect::Strategery.new(one, other, space: space, reverse: reverse)
+    end
+
+    def strategies
+      @@strategies
+    end
+  end
+end

data/lib/auto-correct/format.rb

@@ -0,0 +1,50 @@
+class AutoCorrect
+  CJK = '\p{Han}|\p{Hangul}|\p{Hanunoo}|\p{Katakana}|\p{Hiragana}|\p{Bopomofo}'
+  SPACE = "[ ]"
+
+  # rubocop:disable Style/StringLiterals
+  # EnglishLetter
+  rule "#{CJK}", '[0-9a-zA-Z]', space: true, reverse: true
+
+  # SpecialSymbol
+  rule "#{CJK}", '[\|+$@#*]', space: true, reverse: true
+  rule "#{CJK}", '[\[\(‘“]', space: true
+  rule '[’”\]\)!%]', "#{CJK}", space: true
+  rule '[”\]\)!]', '[a-zA-Z0-9]+', space: true
+
+  # FullwidthPunctuation
+  rule %r([\w#{CJK}]), '[，。！？：；」》】”’]', reverse: true
+  rule '[‘“【「《]', %r([\w#{CJK}]), reverse: true
+
+  class << self
+    FULLDATE_RE = /#{SPACE}{0,}\d+#{SPACE}{0,}年#{SPACE}{0,}\d+#{SPACE}{0,}月#{SPACE}{0,}\d+#{SPACE}{0,}[日号]#{SPACE}{0,}/u
+    DASH_HAN_RE = /([#{CJK}）】」》”’])([\-]+)([#{CJK}（【「《“‘])/
+    LEFT_QUOTE_RE = /#{SPACE}([（【「《])/
+    RIGHT_QUOTE_RE = /([）】」》])#{SPACE}/
+
+    def format(str)
+      out = str
+      self.strategies.each do |s|
+        out = s.format(out)
+      end
+      out = remove_full_date_spacing(out)
+      out = space_dash_with_hans(out)
+      out
+    end
+
+    private
+
+      def remove_full_date_spacing(str)
+        str.gsub(FULLDATE_RE) do |m|
+          m.gsub(/\s+/, "")
+        end
+      end
+
+      def space_dash_with_hans(str)
+        str = str.gsub(DASH_HAN_RE, '\1 \2 \3')
+        str = str.gsub(LEFT_QUOTE_RE, '\1')
+        str = str.gsub(RIGHT_QUOTE_RE, '\1')
+        str
+      end
+  end
+end

data/lib/auto-correct/html.rb

@@ -0,0 +1,14 @@
+require "nokogiri"
+
+class AutoCorrect
+  class << self
+    def format_html(html)
+      doc = Nokogiri::HTML(html)
+      doc.traverse do |node|
+        next unless node.node_type == Nokogiri::XML::Node::TEXT_NODE
+        node.content = AutoCorrect.format(node.content)
+      end
+      doc.css("body").inner_html
+    end
+  end
+end

data/lib/auto-correct/strategery.rb

@@ -0,0 +1,43 @@
+class AutoCorrect
+  class Strategery
+    attr_reader :space, :reverse
+    attr_reader :add_space_rules, :remove_space_rules
+
+    def initialize(one, other, space: false, reverse: false)
+      @space = space
+      @reverse = reverse
+
+      @add_space_rules = [
+        /(#{one})(#{other})/u,
+        /(#{other})(#{one})/u
+      ]
+
+      @remove_space_rules = [
+        /(#{one})#{SPACE}+(#{other})/u,
+        /(#{other})#{SPACE}+(#{one})/u
+      ]
+    end
+
+    def format(str)
+      self.space ? add_space(str) : remove_space(str)
+    end
+
+    def add_space(str)
+      r0, r1 = add_space_rules
+      str = str.gsub(r0) { "#$1 #$2" }
+      if self.reverse
+        str = str.gsub(r1) { "#$1 #$2" }
+      end
+      str
+    end
+
+    def remove_space(str)
+      r0, r1 = remove_space_rules
+      str = str.gsub(r0) { "#$1 #$2" }
+      if self.reverse
+        str = str.gsub(r1) { "#$1 #$2" }
+      end
+      str
+    end
+  end
+end

data/lib/auto-correct/string.rb

@@ -0,0 +1,13 @@
+class AutoCorrect
+  module String
+    def auto_space!
+      ActiveSupport::Deprecation.warn("String.auto_space! is deprecated and will be removed in auto-corrrect 1.0, please use AutoCorrect.format instead.")
+      self.sub!(self, AutoCorrect.format(self))
+    end
+
+    def auto_correct!
+      ActiveSupport::Deprecation.warn("String.auto_correct! is deprecated and will be removed in auto-corrrect 1.0, please use AutoCorrect.format instead.")
+      self.sub!(self, AutoCorrect.format(self))
+    end
+  end
+end

data/lib/auto-correct/version.rb

@@ -0,0 +1,3 @@
+class AutoCorrect
+  VERSION = "0.3.1"
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: auto-correct
 version: !ruby/object:Gem::Version
-  version: 0.1.0.pre0
+  version: 0.3.1
 platform: ruby
 authors:
 - Luikore
@@ -9,23 +9,24 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-15 00:00:00.000000000 Z
+date: 2020-08-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: activesupport
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.0
+        version: '1.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.0
-description: "自动给中文英文之间加入合理的空格"
+        version: '1.4'
+description: Automatically add whitespace between Chinese and and half-width characters
+  (alphabetical letters, numerical digits and symbols).
 email:
 - usurffx@gmail.com
 - huacnlee@gmail.com
@@ -35,7 +36,12 @@ extra_rdoc_files: []
 files:
 - README.md
 - lib/auto-correct.rb
-- lib/auto-correct/dicts.rb
+- lib/auto-correct/base.rb
+- lib/auto-correct/format.rb
+- lib/auto-correct/html.rb
+- lib/auto-correct/strategery.rb
+- lib/auto-correct/string.rb
+- lib/auto-correct/version.rb
 homepage: https://github.com/huacnlee/auto-correct
 licenses: []
 metadata: {}
@@ -50,14 +56,13 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
-summary: "自动给中文英文之间加入合理的空格"
+summary: Automatically add whitespace between Chinese and and half-width characters
+  (alphabetical letters, numerical digits and symbols).
 test_files: []
-has_rdoc: 

data/lib/auto-correct/dicts.rb

@@ -1,103 +0,0 @@
-module AutoCorrect
-  DICTS             = {
-    # Ruby
-    "ruby"          => "Ruby",
-    "rails"         => "Rails",
-    "rubygems"      => "RubyGems",
-    "ror"           => "Ruby on Rails",
-    "rubyconf"      => "RubyConf",
-    "railsconf"     => "RailsConf",
-    "rubytuesday"   => "Ruby Tuesday",
-    "jruby"         => "JRuby",
-    "mruby"         => "mRuby",
-    "rvm"           => "RVM",
-    "rbenv"         => "rbenv",
-    "yard"          => "YARD",
-    "rdoc"          => "RDoc",
-    "rspec"         => "RSpec",
-    "minitest"      => "MiniTest",
-    "coffeescript"  => "CoffeeScript",
-    "scss"          => "SCSS",
-    "sass"          => "Sass",
-    "sidekiq"       => "Sidekiq",
-    "railscasts"    => "RailsCasts",
-    "execjs"        => "ExecJS",
-
-    # Python
-
-    # Node.js
-    "nodejs"        => "Node.js",
-
-    # Go
-    
-    # Cocoa
-    "reactivecocoa" => "ReactiveCocoa",
-
-    # Programming
-    "ssh"           => "SSH",
-    "css"           => "CSS",
-    "html"          => "HTML",
-    "javascript"    => "JavaScript",
-    "js"            => "JS",
-    "png"           => "PNG",
-    "dsl"           => "DSL",
-    "tdd"           => "TDD",
-    "bdd"           => "BDD",
-
-    # Sites
-    "github"        => "GitHub",
-    "gist"          => "Gist",
-    "ruby_china"    => "Ruby China",
-    "ruby-china"    => "Ruby China",
-    "rubychina"     => "Ruby China",
-    "v2ex"          => "V2EX",
-    "heroku"        => "Heroku",
-    "stackoverflow" => "Stack Overflow",
-    "stackexchange" => "StackExchange",
-    
-
-    # Databases
-    "mysql"         => "MySQL",
-    "postgresql"    => "PostgreSQL",
-    "sqlite"        => "SQLite",
-    "mongodb"       => "MongoDB",
-    "rethinkdb"     => "RethinkDB",
-    "elasticsearch" => "Elasticsearch",
-    "sphinx"        => "Sphinx",
-
-    # OpenSource Projects
-    "gitlab"        => "GitLab",
-    "gitlabci"      => "GitLab CI",
-    "fontawsome"    => "FontAwsome",
-    "bootstrap"     => "Bootstrap",
-    "less"          => "Less",
-    "jquery"        => "jQuery",
-    "requirejs"     => "RequireJS",
-    "underscore"    => "Underscore",
-    "backbone"      => "Backbone",
-    "seajs"         => "SeaJS",
-    "imagemagick"   => "ImageMagick",
-    
-    # Tools
-    "vim"           => "VIM",
-    "emacs"         => "Emacs",
-    "textmate"      => "TextMate",
-    "sublime"       => "Sublime",
-    "rubymine"      => "RubyMine",
-    "sequelpro"     => "Sequel Pro",
-    "virtualbox"    => "VirtualBox",
-    "safari"        => "Safari",
-    "chrome"        => "Chrome",
-    "ie"            => "IE",
-
-    # Misc
-    "ios"           => "iOS",
-    "iphone"        => "iPhone",
-    "android"       => "Android",
-    "osx"           => "OS X",
-    "mac"           => "Mac",
-    "api"           => "API",
-    "wi-fi"         => "Wi-Fi",
-    "wifi"          => "Wi-Fi"
-  }
-end