Class: Kleene::NaiveOnlineRegex

Inherits:
Object
  • Object
show all
Defined in:
lib/kleene/naive_online_regex.rb

Instance Method Summary collapse

Constructor Details

#initialize(regexen, window_size = 100) ⇒ NaiveOnlineRegex

Returns a new instance of NaiveOnlineRegex.



6
7
8
9
10
11
 
# File 'lib/kleene/naive_online_regex.rb', line 6

def initialize(regexen, window_size = 100)
  @regexen = regexen
  @window_size = window_size

  reset
end

Instance Method Details

#drop_matches_that_have_rolled_off(number_of_chars_at_front_of_buffer_that_rolled_off) ⇒ Object 



51
52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/kleene/naive_online_regex.rb', line 51

def drop_matches_that_have_rolled_off(number_of_chars_at_front_of_buffer_that_rolled_off)
  @matches_per_regex.transform_values! do |match_set|
    new_set = Set.new
    match_set.each do |online_match|
      online_match_clone = online_match.clone
      online_match_clone.decrement_offsets(number_of_chars_at_front_of_buffer_that_rolled_off)
      new_set << online_match_clone if online_match_clone.offsets.first > 0
    end
    new_set
  end

end

#ingest(input, _debug = false) ⇒ Object

#ingest(input) is the online-style matching interface



19
20
21
22
23
24
25
26
27
28
29
30
31
32
 
# File 'lib/kleene/naive_online_regex.rb', line 19

def ingest(input, _debug = false) # : Set(OnlineMatch)
  @buffer << input
  new_online_matches = Set.new
  @regexen.each do |regex|
    existing_matches_for_regex = (@matches_per_regex[regex] ||= Set.new)
    scan_matches = @buffer.scan_matches(regex)
    scan_online_matches = scan_matches.map {|match_data| OnlineMatch.new(regex, match_data) }.to_set
    new_matches = scan_online_matches - existing_matches_for_regex # new_matches : Set(OnlineMatch)
    existing_matches_for_regex.merge(new_matches)
    new_online_matches.merge(new_matches)
  end
  resize_buffer!
  new_online_matches
end

#matches ⇒ Object

Hash(Regexp, Set(OnlineMatch))



34
35
36
 
# File 'lib/kleene/naive_online_regex.rb', line 34

def matches # Hash(Regexp, Set(OnlineMatch))
  @matches_per_regex
end

#matches_for(regex) ⇒ Object

Set(OnlineMatch) | Nil



38
39
40
 
# File 'lib/kleene/naive_online_regex.rb', line 38

def matches_for(regex) # Set(OnlineMatch) | Nil
  @matches_per_regex[regex]
end

#reset ⇒ Object 



13
14
15
16
 
# File 'lib/kleene/naive_online_regex.rb', line 13

def reset
  @buffer = ''
  @matches_per_regex = {} # Hash(Regexp, Set(OnlineMatch))
end

#resize_buffer! ⇒ Object 



42
43
44
45
46
47
48
49
 
# File 'lib/kleene/naive_online_regex.rb', line 42

def resize_buffer!
  return unless @buffer.size > @window_size

  number_of_chars_at_front_of_buffer_that_should_roll_off = @buffer.size - @window_size

  @buffer = @buffer[-@window_size..-1]
  drop_matches_that_have_rolled_off(number_of_chars_at_front_of_buffer_that_should_roll_off)
end