Class: BadWordDetector

Inherits:
Object
  • Object
show all
Defined in:
lib/bad_word_detector.rb,
lib/bad_word_detector/version.rb

Constant Summary collapse

VERSION = 
"0.0.5"

Instance Method Summary collapse

Constructor Details

#initialize(rules = nil, library = nil, whitelist = nil) ⇒ BadWordDetector

Create new badword checker

Parameters:

  • rules (Hash<String,Array<Hash<String, any>>>) (defaults to: nil) —

    Hash where values are arrays of Hash<[‘symbol’, ‘weight’], any> where weight is optional

  • library (Array<String>) (defaults to: nil) —

    Array of bad words to find

  • whitelist (Array<String>) (defaults to: nil) —

    Array of words that is acceptable. Used in false-positive check



21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/bad_word_detector.rb', line 21

def initialize(rules = nil, library = nil,  whitelist = nil)
  confdir = File.expand_path(File.dirname(__FILE__) + "/conf")
  rules_file = if rules.is_a? String 
    rules 
  else 
    "#{confdir}/rules.yaml" 
  end
  library_file = if library.is_a? String 
    library 
  else 
    "#{confdir}/library.yaml" 
  end
  whitelist_file = if whitelist.is_a? String 
    whitelist 
  else 
    "#{confdir}/whitelist.yaml" 
  end
  unless rules.is_a? Hash
    rules = YAML.load_file(rules_file)  
  end
  unless library.is_a? Array
    library = YAML.load_file(library_file)
  end
  unless whitelist.is_a? Array
    whitelist = YAML.load_file(whitelist_file)
  end

  @rule_sets = rules.select do |key, _|
    key.to_s.length == 1
  end.hmap do |key, rule|
    key = key.to_s
    rule = rule.map do |item|
      Rule.new(key, item['symbol'], item['weight'])
    end
    rule << Rule.new(key, key, 3)
    [key, rule]
  end

  @string_sets = rules.select do |key, _|
    key.to_s.length > 1
  end.hmap do |key, rule|
    key = key.to_s
    rule = rule.map do |item|
      Rule.new(key, item['symbol'], item['weight'])
    end
    [key, rule]
  end
  @library = PrefixTree.new library
  @whitelist = Whitelist.new whitelist
  @library.freeze
  @whitelist.freeze
  @rule_sets.freeze
  @string_sets.freeze
  self.freeze
  true
end

Instance Method Details

#find(text, return_white = false) ⇒ BadWord?

Searches string for some word in library

Parameters:

  • text (String) —

    String to search

  • return_white (Boolean) (defaults to: false) —

    Flag to indicate if search should return whitelist word

Returns:

  • (BadWord, nil) —

    BadWord object, containing information about found word and it’s position in text



87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
 
# File 'lib/bad_word_detector.rb', line 87

def find(text, return_white = false)
  downcased = text.downcase
  length = text.length
  index = 0
  while index < length
    found = find_part(downcased, index)
    if found 
      word = BadWord.new(
        found[:word], 
        text, 
        index, 
        found[:length], 
        @whitelist)
      if not word.white? or return_white
        return word
      end
    end
    index += 1
  end
end

#inspect ⇒ Object 



107
108
109
 
# File 'lib/bad_word_detector.rb', line 107

def inspect
  "#<#{self.class.name}:#{self.object_id}>"
end