Class: Appstats::Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/appstats/parser.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(data = {}) ⇒ Parser

Returns a new instance of Parser.



9
10
11
12
13
14
15
16
17
 
# File 'lib/appstats/parser.rb', line 9

def initialize(data = {})
  @raw_rules = data[:rules]
  @raw_tokenize = data[:tokenize]
  @repeating = data[:repeating] == true
  @results = {}
  @raw_results = []
  update_tokens
  update_rules
end

Instance Attribute Details

#constants ⇒ Object (readonly)

Returns the value of attribute constants.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def constants
  @constants
end

#constants_no_spaces ⇒ Object (readonly)

Returns the value of attribute constants_no_spaces.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def constants_no_spaces
  @constants_no_spaces
end

#raw_results ⇒ Object (readonly)

Returns the value of attribute raw_results.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def raw_results
  @raw_results
end

#raw_rules ⇒ Object (readonly)

Returns the value of attribute raw_rules.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def raw_rules
  @raw_rules
end

#raw_tokenize ⇒ Object (readonly)

Returns the value of attribute raw_tokenize.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def raw_tokenize
  @raw_tokenize
end

#repeating ⇒ Object (readonly)

Returns the value of attribute repeating.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def repeating
  @repeating
end

#results ⇒ Object (readonly)

Returns the value of attribute results.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def results
  @results
end

#rules ⇒ Object (readonly)

Returns the value of attribute rules.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def rules
  @rules
end

#tokenize ⇒ Object (readonly)

Returns the value of attribute tokenize.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def tokenize
  @tokenize
end

#tokenize_no_spaces ⇒ Object (readonly)

Returns the value of attribute tokenize_no_spaces.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def tokenize_no_spaces
  @tokenize_no_spaces
end

#tokenize_regex ⇒ Object (readonly)

Returns the value of attribute tokenize_regex.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def tokenize_regex
  @tokenize_regex
end

#tokenize_regex_no_spaces ⇒ Object (readonly)

Returns the value of attribute tokenize_regex_no_spaces.



5
6
7
 
# File 'lib/appstats/parser.rb', line 5

def tokenize_regex_no_spaces
  @tokenize_regex_no_spaces
end

Class Method Details

.alpha?(raw_input) ⇒ Boolean

Returns:

  • (Boolean) 


76
77
78
79
 
# File 'lib/appstats/parser.rb', line 76

def self.alpha?(raw_input)
  return false if raw_input.nil?
  !raw_input.match(/^[A-Za-z]+$/i).nil?
end

.merge_regex_filter(inputs = []) ⇒ Object 



100
101
102
103
104
 
# File 'lib/appstats/parser.rb', line 100

def self.merge_regex_filter(inputs = [])
  inputs.collect! { |x| x unless x.blank? }.compact!
  return "" if inputs.empty?
  "(#{inputs.join('|')})"
end

.parse_constant(current_text, constant) ⇒ Object 



81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/appstats/parser.rb', line 81

def self.parse_constant(current_text,constant)
  answer = [nil,nil]
  return answer if current_text.blank? || constant.nil?
  current_text.strip!
  
  remaining_text_index = -1
  if alpha?(constant)
    m = current_text.match(/^(#{constant})(\s|$)(.*)$/im)  
    remaining_text_index = 3
  else
    m = current_text.match(/^(#{constant})(.*)$/im)  
    remaining_text_index = 2
  end
  
  answer[0] = m[1] unless m.nil?
  answer[1] = m.nil? ? current_text : m[remaining_text_index]
  clean_parsed_word(answer)
end

Instance Method Details

#parse(input) ⇒ Object 



19
20
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
 
# File 'lib/appstats/parser.rb', line 19

def parse(input)
  @results = {}
  @raw_results = []
  return false if input.nil?
  return false if @rules.size == 0

  @rule_index = 0
  @max_rule_index = @rules.size - 1
  @previous_text_so_far = input.strip
  @text_so_far = @previous_text_so_far
  @remaining_constants = @constants.dup
  @remaining_constants_no_spaces = @constants_no_spaces.dup
  
  while !@text_so_far.blank?
    process_constant_if_present
    break if @rule_index > @max_rule_index && !@repeating
    @rule_index = 0 if @rule_index > @max_rule_index

    rule = @rules[@rule_index]
    @rule_index += 1
    
    if rule.kind_of?(Hash)
      if rule[:stop] == :constant
        was_found = false
        @remaining_constants.each_with_index do |k,index|
          p = parse_word(@text_so_far,k,true)
          if p[0].nil?
            unset_rules_until(k)
          else
            (index-1).downto(0) do |i|
              @remaining_constants_no_spaces.delete_at(i)
              @remaining_constants.delete_at(i)
            end
            add_results(rule[:rule],p[0])
            @text_so_far = p[1]
            was_found = true
            break
          end
        end
        unless was_found
          add_results(rule[:rule],@text_so_far)
          @text_so_far = nil
        end
      else
        p = parse_word(@text_so_far,rule[:stop],false)
        add_results(rule[:rule],p[0]) unless p[0].nil?
        @text_so_far = p[1]
      end
    end
    break if @previous_text_so_far == @text_so_far
    @previous_text_so_far = @text_so_far
  end
  remove_tokens_at_start(@text_so_far)
  unset_rules_until(nil)
  true
end

#parse_word(current_text, stop_on, strict = false) ⇒ Object 



106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
 
# File 'lib/appstats/parser.rb', line 106

def parse_word(current_text,stop_on,strict = false)
  answer = [nil,nil]
  return answer if current_text.blank? || stop_on.nil?
  current_text.strip!

  current_text = remove_tokens_at_start(current_text)
  
  if stop_on == :end
    filter = Parser.merge_regex_filter([nil,@tokenize_regex])
    m = current_text.match(/^(.*?)(#{filter}.*)$/im)
    if m.nil? || m[1].blank?
      answer[0] = current_text
    else
      answer[0] = m[1]
      answer[1] = m[2]
    end
  elsif stop_on == :space
    filter = Parser.merge_regex_filter(['\s',@tokenize_regex,remaining_constants_regex])
    m = current_text.match(/^(.*?)(#{filter}.*)$/im)
    if m.nil?
      answer[0] = current_text
    else
      answer[0] = m[1]
      answer[1] = m[2]
    end
  else
    filter = Parser.merge_regex_filter([stop_on,@tokenize_regex,remaining_constants_regex])
    m = current_text.match(/^(.*?)(#{filter}.*)$/im)
    if strict
      answer[0] = m[1] unless m.nil?
      answer[1] = m.nil? ? current_text : m[2]
    else
      answer[0] = m.nil? ? current_text : m[1]
      answer[1] = m[2] unless m.nil?
    end
  end
  answer = Parser.clean_parsed_word(answer)
  answer
end