Module: ChemScanner::Interpreter::BoldGroup

Included in:
MoleculeTextGroup, ReactionTextGroup
Defined in:
lib/chem_scanner/interpreter/text_group/bold_groups.rb

Instance Method Summary collapse

Instance Method Details

#extract_alphabet_number(text) ⇒ Object 



128
129
130
131
132
133
134
135
136
137
138
139
140
141
 
# File 'lib/chem_scanner/interpreter/text_group/bold_groups.rb', line 128

def extract_alphabet_number(text)
  # 3a,b -> 3a, 3b
  regex = /(\d+)( *[a-z],*)+/
  res = regex =~ text
  return [] if res.nil?

  els = text.split(",")
  anchor = els.first.strip.scan(/\d+/).first
  els[0] = els[0].gsub(anchor, "")

  els.reduce([]) do |arr, char|
    arr.push(anchor + char.strip)
  end
end

#extract_range_number(text) ⇒ Object 



116
117
118
119
120
121
122
123
124
125
126
 
# File 'lib/chem_scanner/interpreter/text_group/bold_groups.rb', line 116

def extract_range_number(text)
  # 3-6 -> 3,4,5,6
  regex = /(\d+)-(\d+)/
  res = text.scan(regex)
  return [] if res.empty?

  bnum, enum = res.first
  return [] if bnum >= enum

  (bnum..enum).to_a
end

#group_combinations(rgroup) ⇒ Object 



143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
 
# File 'lib/chem_scanner/interpreter/text_group/bold_groups.rb', line 143

def group_combinations(rgroup)
  return [] if rgroup.empty?

  combis = []

  key_arr = rgroup.keys
  group_num = key_arr.size

  # keep track of next element in each of the R-groups substitutions
  indices = Array.new(group_num, 0)

  loop do
    combi = {}
    indices.each_with_index.each do |val, idx|
      group = key_arr[idx]
      substitute = rgroup[group][val]

      combi[group] = substitute
    end
    combis.push(combi)

    group_max_idx = group_num - 1

    # rightmost array, has more elements left after the current element
    next_group_idx = group_max_idx
    next_group_size = rgroup[key_arr[next_group_idx]].size
    while next_group_idx >= 0 &&
        (indices[next_group_idx] + 1 >= next_group_size)
      next_group_idx -= 1
      next_group_size = rgroup[key_arr[next_group_idx]].size
    end

    return combis if next_group_idx < 0

    indices[next_group_idx] += 1
    (next_group_idx + 1..group_max_idx).each { |x| indices[x] = 0 }
  end
end

#line_bold_groups(line, target_groups) ⇒ Object 



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
77
78
79
80
81
 
# File 'lib/chem_scanner/interpreter/text_group/bold_groups.rb', line 43

def line_bold_groups(line, target_groups)
  bold_regex = /\*\*([^\*\*]*)\*\*/
  bold = line.scan(bold_regex).map(&:first).map(&:strip)
  bold.reject! do |x|
    bold.select { |y| (y.size > x.size) && y.include?(x) }.count > 0
  end

  group_or = "(" + target_groups.join("|") + ")"
  group_regex = /#{group_or} *=/
  res = line.enum_for(:scan, group_regex)
  positions = res.map { Regexp.last_match.begin(0) }

  text_arr = positions.map.with_index do |pos, idx|
    end_pos = idx == (positions.size - 1) ? line.size : positions[idx + 1]
    rtext = line[pos, end_pos - pos]
    regex = /#{group_or} *= *([^\*\*])*(?=$|\n|\.|\z|\Z|\*\*)/
    rtext[regex].strip
  end

  groups = text_arr.reduce({}) do |acc, gtext|
    group_val = gtext.scan(/#{group_or}? ?(?==)/)
    temp = gtext.split("=", 2).last.split(",").map do |t|
      t.strip.gsub(/^-/, "")
    end
    substitutes = temp.compact.uniq.select do |text|
      is_superatom = !ChemScanner.get_superatom(text).empty?
      is_abb = !ChemScanner.get_abbreviation(text).empty?
      is_n_atom = /^\d+$/.match?(text)

      is_superatom || is_abb || is_n_atom
    end
    next acc if group_val.empty? || substitutes.empty?

    info = { group_val.first.first.strip => substitutes }
    acc.merge(info) { |_, cur, new| cur.concat(new).compact.uniq }
  end

  [bold, groups]
end

#normalize_bold(bold) ⇒ Object 



102
103
104
105
106
107
108
109
110
111
112
113
114
 
# File 'lib/chem_scanner/interpreter/text_group/bold_groups.rb', line 102

def normalize_bold(bold)
  arr = []

  # 1-3 or 5-10 ... => [1,2,3] or [5,6,7,8,9,10]
  range = extract_range_number(bold)
  return arr.concat(range) unless range.empty?

  # 1a,b or 8a,b,c ... => [1a, 1b] or [8a,8b,8c]
  range = extract_alphabet_number(bold)
  return arr.concat(range) unless range.empty?

  [bold]
end

#normalize_bold_groups(bolds, groups) ⇒ Object 



83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'lib/chem_scanner/interpreter/text_group/bold_groups.rb', line 83

def normalize_bold_groups(bolds, groups)
  normalized = []

  bolds.each_with_index do |bold, idx|
    bgroup = {}
    groups.each { |k, v| bgroup[k] = v[idx] unless v[idx].nil? }
    norm_bolds = bold.split(",").reduce([]) do |arr, b|
      nbold = normalize_bold(b.strip)
      arr.concat(nbold)
    end

    norm_bolds.each do |b|
      normalized.push(bold: b, group: bgroup)
    end
  end

  normalized
end

#text_bold_groups(tid) ⇒ Object 



8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
 
# File 'lib/chem_scanner/interpreter/text_group/bold_groups.rb', line 8

def text_bold_groups(tid)
  all_groups = @alias_info.values.reduce([]) do |arr, infos|
    groups = infos.map { |info| info[:group] }
    arr.concat(groups).uniq
  end

  # In case "** \n", splitting results
  # "[...**], [bold text** ...]"
  # The bold part will be missed for next line
  text = @text_map[tid].markdown.gsub(/ *\*\* *\n/, "\n**")
  lines = text.split("\n")

  bold_arr = []
  group_info = {}

  lines.each do |line|
    bold_info, groups = line_bold_groups(line, all_groups)
    next if bold_info.empty? && groups.empty?

    list_bold = bold_info.reduce([]) do |arr, bold|
      # Remove ":" from "1:", or "2a,b:"
      bold.gsub!(":", "")
      norm = normalize_bold(bold)
      barr = norm.empty? ? bold : norm
      arr.push(barr)
    end

    bold_list = list_bold.flatten.reject { |b| /^[a-z]+$/.match?(b) }
    bold_arr.concat(bold_list)
    group_info.merge!(groups) { |_, old, new| old.concat(new) }
  end

  [bold_arr, group_info]
end