sensitive_word_filter 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 19204d951c5ad743e31cf097fff02014ff781b2e9c61a94eb25a878df247a0cf
+  data.tar.gz: bfb3648c45c29ffe76b1889eb1833a37feccd1237d6c72d750ae9a7d02d6ba98
+SHA512:
+  metadata.gz: 0b1cf3d5298f6eebe0455f975d50e992bcc9d3a8d225f4b228eea9ddd0d15bd5437e06095203a9891f570c6325cfed6a752945862771369a249e7d3c4e2f088d
+  data.tar.gz: 577fa3e37b1220e652e3813a990f10f655414868f855c890c5fa7a9c8213cc104906d5bac0bd6244e7ff2db1e19e3e6c91154eb7996e51345f00de19c2387ae4

data/README.md

@@ -0,0 +1,45 @@
+# SensitiveWordFilter
+
+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/sensitive_word_filter`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'sensitive_word_filter'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install sensitive_word_filter
+
+## Usage
+
+    SensitiveWordFilter.scan('色情电影')
+    SensitiveWordFilter.scan('色情电影', ['./text.text'])
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+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 tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/sensitive_word_filter. 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]/sensitive_word_filter/blob/master/CODE_OF_CONDUCT.md).
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the SensitiveWordFilter project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/sensitive_word_filter/blob/master/CODE_OF_CONDUCT.md).

data/lib/sensitive_word_filter.rb

@@ -0,0 +1,27 @@
+require "sensitive_word_filter/version"
+require "sensitive_word_filter/load"
+require "sensitive_word_filter/scan"
+
+module SensitiveWordFilter
+  class Error < StandardError; end
+
+  def self.scan(text='', file_paths=[])
+    Filter.new(file_paths).scan(text)
+  end
+
+  class Filter
+    attr_reader :file_paths
+
+    def initialize(file_paths=[])
+      if file_paths.empty?
+        raise Error.new('sensitive words file path is empty')
+      else
+        @words = Load.new(file_paths).load
+      end
+    end
+
+    def scan(text='')
+      Scan.new(@words).scan(text)
+    end
+  end
+end

data/lib/sensitive_word_filter/dfa_tree.rb

@@ -0,0 +1,36 @@
+module SensitiveWordFilter
+  class DfaTree
+    Word = Struct.new(:is_end, :value)
+
+    attr_accessor :words, :tree
+
+    def initialize(words=nil)
+      @tree = Hash.new
+      @words = words || []
+    end
+
+    def dfa_tree
+      words.each do |word|
+        word_hash = tree
+  
+        _word = word.strip
+        word_length = _word.length
+  
+        (1..word_length).each do |i|
+          c = _word[i-1]
+          if word_hash[c].nil?
+            if i == word_length
+              word_hash[c] = Word.new(true, Hash.new)
+            else
+              word_hash[c] = Word.new(false, Hash.new)
+              word_hash = word_hash[c].value
+            end
+          else
+            word_hash = word_hash[c].value
+          end
+        end
+      end
+      tree
+    end
+  end
+end

data/lib/sensitive_word_filter/load.rb

@@ -0,0 +1,33 @@
+module SensitiveWordFilter
+  class Load
+    attr_accessor :words
+    attr_reader :file_paths
+
+    def initialize(file_paths)
+      @file_paths = file_paths
+      @words = Array.new
+    end
+
+    def load
+      if file_paths.is_a?(Array)
+        file_paths.each do |file_path|
+          _load(file_path)
+        end
+      else
+        _load(file_paths)
+      end
+
+      words
+    end
+
+    private
+
+    def _load(file_path)
+      f = File.open(file_path, "r")
+      f.each_line do |line|
+        words.push(line.gsub("\n", ''))
+      end
+      f.close
+    end
+  end
+end

data/lib/sensitive_word_filter/scan.rb

@@ -0,0 +1,52 @@
+require "sensitive_word_filter/dfa_tree"
+
+module SensitiveWordFilter
+  class Scan
+    attr_accessor :sensitive_map
+
+    def initialize(words=[])
+      @sensitive_map = DfaTree.new(words).dfa_tree
+    end
+
+    def scan(text = '')
+      return [] if  text.nil?
+      _scan(gsub_text(text))
+    end
+
+    private
+
+    def _scan(text = '', sensitive_words = [], sensitive_hash = sensitive_map, temp_text = '')
+      c = text[0]
+      return sensitive_words if text.empty?
+      return sensitive_words if c.empty?
+
+      text_size = text.length
+      w = sensitive_hash[c]
+
+      if w.nil?
+        if temp_text.size > 0
+          new_text = temp_text + text
+          new_length = new_text.length
+          text = new_text[1..(new_length-1)]
+        else
+          text = text[1..(text_size-1)]
+        end
+        temp_text = ''
+        send(__method__, text, sensitive_words)
+      else
+        temp_text += c
+        text = text[1..(text_size-1)]
+        if w.is_end
+          sensitive_words.push(temp_text)
+          send(__method__, text, sensitive_words)
+        else
+          send(__method__, text, sensitive_words, w.value, temp_text)
+        end
+      end
+    end
+
+    def gsub_text(text)
+      text.strip.gsub(/[`~!@#$^&*()=|{}':;',\\\[\]\.<>\/?~！@#￥……&*（）——|{}【】'；：""'。，、？]|\s/,'')
+    end
+  end
+end

data/lib/sensitive_word_filter/version.rb

@@ -0,0 +1,3 @@
+module SensitiveWordFilter
+  VERSION = "0.1.1"
+end

metadata

@@ -0,0 +1,54 @@
+--- !ruby/object:Gem::Specification
+name: sensitive_word_filter
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- sanm1992
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2020-10-10 00:00:00.000000000 Z
+dependencies: []
+description: sensitive word filter base on DFA
+email:
+- 1320695403@qq.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- lib/sensitive_word_filter.rb
+- lib/sensitive_word_filter/dfa_tree.rb
+- lib/sensitive_word_filter/load.rb
+- lib/sensitive_word_filter/scan.rb
+- lib/sensitive_word_filter/version.rb
+homepage: https://github.com/sanm1992/sensitive_word_filter
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+  homepage_uri: https://github.com/sanm1992/sensitive_word_filter
+  source_code_uri: https://github.com/sanm1992/sensitive_word_filter
+  changelog_uri: https://github.com/sanm1992/sensitive_word_filter
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.6.2
+signing_key: 
+specification_version: 4
+summary: sensitive word filter
+test_files: []