kaomoji 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cb3a3759e4087b91a709bf25adf55e69574f752a97c9fe1941be46cbedf55f08
-  data.tar.gz: 2be52cc419294ffb779e196ead7b1a30ace3865bbd5bd9a998f22f2ada803a1c
+  metadata.gz: 03573bed50d415dc40056a6dcb03c4654bd9ab07a9986ce1323399179b104ec9
+  data.tar.gz: afa6dbd4fa5e159d59ddf1ce184301a9f8de49cf1c0a399ed092be1b6de14ab0
 SHA512:
-  metadata.gz: 2df611913af6faf99f0678851e0bc5be230efaebc921676b35e2ba5fdcf5828cbd09107fc6dd6beec8bfdba536e7c78cec9819a95ba3ecb00a8991d9a0d74d6c
-  data.tar.gz: 10f56f5fedcc3e2d8348c19830b88044d62c2a84c91ee5c742b51f938976da4fc7b43290141d86a82c13aaeff2f825bc60f8eaaf5979eb9d6ef26581fe3381f0
+  metadata.gz: a7841381ac945f022cfa8d8aa8f2f3a330ac7708594901e52b97a96475ef772ba74c38da3743155d7093796d4dab9b47354acf249986d4c9553688f69b75a867
+  data.tar.gz: 2c4b3b51093aba9945498f92cd26785fb08e84f40fc8b42ae4c0656f1fcab76bddb48e48d144bd4e5c67d60944799db72960d7df01f7ac2a5305cbfbf9682674

data/.gitignore

@@ -6,3 +6,4 @@
 /pkg/
 /spec/reports/
 /tmp/
+kaomoji-*.gem

data/Gemfile.lock

@@ -0,0 +1,45 @@
+PATH
+  remote: .
+  specs:
+    kaomoji (0.1.0)
+      unicode-x
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    minitest (5.11.3)
+    rake (10.5.0)
+    unicode-blocks (1.5.0)
+    unicode-categories (1.5.0)
+    unicode-confusable (1.6.0)
+    unicode-display_width (1.6.0)
+    unicode-emoji (2.1.0)
+    unicode-name (1.8.0)
+      unicode-types (~> 1.5)
+    unicode-numeric_value (1.6.0)
+    unicode-scripts (1.5.0)
+    unicode-sequence_name (1.4.0)
+    unicode-types (1.5.0)
+    unicode-x (12.1.0)
+      unicode-blocks (>= 1.5, < 2.0)
+      unicode-categories (>= 1.5, < 2.0)
+      unicode-confusable (>= 1.6, < 2.0)
+      unicode-display_width (>= 1.6, < 2.0)
+      unicode-emoji (>= 2.0, < 3.0)
+      unicode-name (>= 1.8, < 2.0)
+      unicode-numeric_value (>= 1.6, < 2.0)
+      unicode-scripts (>= 1.5, < 2.0)
+      unicode-sequence_name (>= 1.4, < 2.0)
+      unicode-types (>= 1.5, < 2.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 2.0)
+  kaomoji!
+  minitest (~> 5.0)
+  rake (~> 10.0)
+
+BUNDLED WITH
+   2.0.1

data/README.md

@@ -1,8 +1,7 @@
 # Kaomoji
 
-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/kaomoji`. To experiment with that code, run `bin/console` for an interactive prompt.
-
-TODO: Delete this and the text above, and describe your gem
+Kaomoji can extract some thing like kaomoji from your strings.
+There are many noise so you have to filter with your hand.
 
 ## Installation
 
@@ -22,7 +21,13 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+You can get kaomoji from some strings.
+
+```ruby
+Kaomoji.get_unicode_kaomojis('(・3・)＼(^o^)／ぷにう')
+=>(・3・)＼(^o^)／
+```
+
 
 ## Development
 
@@ -32,7 +37,7 @@ To install this gem onto your local machine, run `bundle exec rake install`. To
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/kaomoji. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+Bug reports and pull requests are welcome on GitHub at https://github.com/colorbox/kaomoji. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
 
 ## License
 
@@ -40,4 +45,4 @@ The gem is available as open source under the terms of the [MIT License](https:/
 
 ## Code of Conduct
 
-Everyone interacting in the Kaomoji project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/kaomoji/blob/master/CODE_OF_CONDUCT.md).
+Everyone interacting in the Kaomoji project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/colorbox/kaomoji/blob/master/CODE_OF_CONDUCT.md).

data/kaomoji.gemspec

@@ -33,6 +33,8 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
+  spec.add_dependency 'unicode-x'
+
   spec.add_development_dependency "bundler", "~> 2.0"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "minitest", "~> 5.0"

data/lib/kaomoji.rb

@@ -1,6 +1,104 @@
-require "kaomoji/version"
+require 'kaomoji/version'
+require 'unicode/x'
 
 module Kaomoji
-  class Error < StandardError; end
-  # Your code goes here...
+  class << self
+    def kaomoji_parts?(chr)
+      kaomoji_group_categories = %w(Pc Pd Pe Pf Pi Po Ps Sc Sk Sm So)
+      japanese_group = %w(Basic\ Latin Hiragana CJK\ Unified\ Ideographs Fullwidth\ ASCII\ Variants)
+      return !japanese_group.include?(::Unicode::Blocks.blocks(chr).first) || kaomoji_group_categories.include?(::Unicode::Categories.categories(chr).first)
+    end
+
+    def normal_char?(chr)
+      normal_char_blocks = %w(Lc Ll Lm Lo Lt Lu Nd Nl)
+      target_block = ::Unicode::Categories.categories(chr)
+      normal_char_blocks.include?(target_block.first)
+    end
+
+    def get_unicode_kaomojis(str)
+      return [] if str.chars.length.zero?
+
+      kaomojis = (0..str.chars.size-1).map{|i| get_one_unicode_kaomoji_at_index(i, str) if kaomoji_parts?(str.chars[i]) }.uniq.compact
+      kaomojis.select{|k|valid_kaomoji?(k)}.reject{|target|kaomojis.map{|kaomoji| (kaomoji!=target) && kaomoji.include?(target)}.any?}
+    end
+
+    def get_one_unicode_kaomoji_at_index(index, str)
+      start = get_kaomoji_left_side(index, str)
+      last = get_kaomoji_right_side(index, str)
+      str.chars[start..last].join
+    end
+
+    THRESHOLD=2
+
+    def get_kaomoji_right_side(start_index, str)
+      return start_index if start_index==str.chars.length-1
+      last = start_index
+      count = 0
+      str.chars[start_index..str.length-1].each_with_index do |chr, index|
+        if kaomoji_parts?(chr)
+          count = 0
+          last = start_index + index
+        elsif normal_char?(chr)
+          count += 1
+        end
+        return last if count > THRESHOLD || index == str.chars[start_index..str.length-1].length - 1
+      end
+    end
+
+    def get_kaomoji_left_side(start_index, str)
+      return 0 if start_index.zero?
+      first = start_index
+      count = 0
+      str.chars[0..start_index].reverse.each_with_index do |chr, index|
+        if kaomoji_parts?(chr)
+          count = 0
+          first = start_index - index
+        elsif normal_char?(chr)
+          count += 1
+        end
+        return first if count > THRESHOLD || index == start_index-1
+      end
+    end
+
+    def unicode_kaomojis(threshold = 2, str)
+      kaomojis = []
+      current=[]
+      count=0
+      str.split('').each do |chr|
+        if kaomoji_parts?(chr)
+          current.push(chr)
+          count=0
+        else
+          count+=1
+        end
+
+        pp [chr,count]
+        if count > threshold
+          kaomoji = current.join
+          kaomojis.push(kaomoji) if valid_kaomoji?(kaomoji)
+          current=[]
+          count=0
+        end
+      end
+
+      if current.count > 0
+        kaomoji = current.join
+        kaomojis.push(kaomoji) if valid_kaomoji?(kaomoji)
+      end
+
+      kaomojis
+    end
+
+    def valid_kaomoji?(kaomoji)
+      kaomoji.length > 3 && !half_of_normal_chars(kaomoji)
+    end
+
+    def half_of_normal_chars(str)
+      normal_chars = %w(Lc Ll Lm Lo Lt Lu Nd Nl)
+      normal_words_count =str.split('').map{|chr|::Unicode::Categories.categories(chr).map{|block|normal_chars.include?(block)}.any? ? 1 : 0}.sum.to_f
+      all_count = str.length.to_f
+      result = (normal_words_count / all_count) > 0.5
+      result
+    end
+  end
 end

data/lib/kaomoji/version.rb

@@ -1,3 +1,3 @@
 module Kaomoji
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: kaomoji
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - colorbox
@@ -10,6 +10,20 @@ bindir: exe
 cert_chain: []
 date: 2019-06-04 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: unicode-x
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -63,6 +77,7 @@ files:
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
 - Gemfile
+- Gemfile.lock
 - LICENSE.txt
 - README.md
 - Rakefile