censor_bear 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3b7bf815d7375b755966c23467029b2219e3a3c3645bc93d0796b9afb0720bdc
-  data.tar.gz: 82a58299728acbeca22d1bf5ec0739ed2a07d4150e6c48639decc0a652f9480a
+  metadata.gz: 0cdef69a9d04136c6116ed8245122bda98d27849a91e313487282be5d0640c4d
+  data.tar.gz: 5088b2e4f868403f242b62344af06edbe47daf4e90bbbaa264848e7c982e574d
 SHA512:
-  metadata.gz: c403de59e6da357406191a1cbbeecba4dc0b1fcadd5fca74ffdd6ba32a3fca4f63fdd0c0b32d02db6956916e28bb998ca180080eaa6c0296235fbf731d58b7de
-  data.tar.gz: 84e32c7fc6e3d029829fcbc6bf65da0901a816e7a411a37cb09beb75cf2e0fecd2de9a929c708038f40b9476e5d725becc449539f737a8d734f168e7d8063eaa
+  metadata.gz: 3b9138dc7b8af468e6fb59960f1bdc6801927c986758c90d709f49ce408b4a6127bf520e5480198c667717f24a2bfc9cd657938e385a5440c3c811862f47f682
+  data.tar.gz: 80966dea001f69dd7db9a1a64d6c687a67062a39fd01b2809a3a1c5d9b028b2066526e69594730805f76c975c49255da8974e6063e2446e7136aa2cf8bd61d89

data/db/migrate/20211126133758_create_censor_bear_stop_words.rb

@@ -12,5 +12,7 @@ class CreateCensorBearStopWords < ActiveRecord::Migration[6.1]
 
       t.timestamps
     end
+
+    add_index :censor_bear_stop_words, :key, unique: true
   end
 end

data/lib/censor_bear/censor.rb

@@ -10,6 +10,9 @@ module CensorBear
   end
 
   class Censor
+    QQ_REG = /(?:[加茄qQ企鹅号码\s]{1,}|[群号]{1,}|[叩叩]{1,}|[抠抠]{1,}|[扣扣]{1,})(?:[\u4e00-\u9eff]*)(?:[:，：]?)([\d\s]{6,})/
+    WX_REG = /(?:[加+微＋+➕薇？vV威卫星♥❤姓xX信]{2,}|weixin|weix)(?:[，❤️.\s]?)(?:[\u4e00-\u9eff]?)(?:[:，：]?)([\w\s]{6,})/
+
     def initialize(content, type = 'ugc')
       @is_mod = false
       @mod_words = []
@@ -21,6 +24,27 @@ module CensorBear
       return Result.new(@content) if @content.blank?
       return Result.new(@content) unless CensorBear::StopWord::FIELDS.include?(@type)
 
+      if @content.match(QQ_REG)
+        CensorBear::Log.create(
+          original_content: @content,
+          action: "#{@type}_regex_qq",
+          filtered_content: nil,
+          mod_words: @mod_words
+        )
+        raise NotPassedException
+      end
+
+      if @content.match(WX_REG)
+        @is_mod = true
+        CensorBear::Log.create(
+          original_content: @content,
+          action: "#{@type}_regex_wx",
+          filtered_content: nil,
+          mod_words: @mod_words
+        )
+        raise NotPassedException
+      end
+
       local_check
 
       # 用户相关类型直接封禁，速错

data/lib/censor_bear/configuration.rb

@@ -8,5 +8,10 @@ module CensorBear
 
     # user name method, default: "name"
     attr_accessor :user_name_method
+
+    # import task file locaation
+    attr_accessor :import_file_path
+    attr_accessor :format_from_file_path
+    attr_accessor :format_dest_file_path
   end
 end

data/lib/censor_bear/version.rb

@@ -1,3 +1,3 @@
 module CensorBear
-  VERSION = '0.1.0'
+  VERSION = '0.1.1'
 end

data/lib/censor_bear.rb

@@ -17,6 +17,9 @@ module CensorBear
       @config.user_class = 'User'
       @config.current_user_method = 'current_user'
       @config.user_name_method = 'name'
+      @config.import_file_path = "#{Rails.root}/tmp/dest_sensitives.txt"
+      @config.format_from_file_path = "#{Rails.root}/tmp/from_sensitives.txt"
+      @config.format_dest_file_path = "#{Rails.root}/tmp/dest_sensitives.txt"
       @config
     end
 

data/lib/tasks/censor_bear_tasks.rake

@@ -1,4 +1,58 @@
-# desc "Explaining what the task does"
-# task :censor_bear do
-#   # Task goes here
-# end
+namespace :censor_bear do
+  desc 'Format words'
+  task format: :environment do
+    from_file = File.read(CensorBear.config.format_from_file_path)
+    File.open(CensorBear.config.format_dest_file_path, 'w') do |f|
+      from_file.each_line do |word|
+        line = "#{word.strip!}={BANNED}|{BANNED}|{BANNED}|{BANNED}\r\n"
+        f.write(line)
+        f.flush
+      end
+    end
+  end
+
+  desc 'Import words'
+  task import: :environment do
+    is_overwrite = true
+    file = File.read(CensorBear.config.import_file_path)
+    # lines = doc.split(/\n/)
+    file.each_line do |line|
+      line.strip!
+      key, rule_str = line.split('=')
+      rules = rule_str.split('|')
+      ugc = parse(rules[0]).blank? ? 'replace' : parse(rules[0])
+      username = parse(rules[1]) || 'ignore'
+      signature = parse(rules[2]) || 'ignore'
+      dialog = parse(rules[3]) || 'ignore'
+      nickname = parse(rules[1]) || 'ignore'
+      replacement = ugc == 'replace' ? rules[0] : '**'
+
+      payload = {
+        key: key,
+        ugc: ugc,
+        username: username,
+        signature: signature,
+        dialog: dialog,
+        nickname: nickname,
+        replacement: replacement,
+        user_id: User.last&.id,
+        created_at: Time.now,
+        updated_at: Time.now
+      }
+
+      word = CensorBear::StopWord.find_by(key: key)
+      if word
+        word.update_columns(payload) if is_overwrite
+      else
+        CensorBear::StopWord.create(payload)
+      end
+    end
+  end
+
+  def parse(rule)
+    return nil if rule.blank?
+
+    r = rule.match(/^{(\w+)}$/)
+    r.blank? ? nil : r[1].downcase
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: censor_bear
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - 42up
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-11-30 00:00:00.000000000 Z
+date: 2021-12-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails