Class: Regexp

Inherits:
Object
  • Object
show all
Defined in:
lib/string/pattern/add_to_ruby.rb

Instance Method Summary collapse

Instance Method Details

#generate(expected_errors: [], **synonyms) ⇒ Object Also known as: gen

it will generate an string following the pattern specified



54
55
56
# File 'lib/string/pattern/add_to_ruby.rb', line 54

def generate(expected_errors: [], **synonyms)
  StringPattern.generate(self, expected_errors: expected_errors, **synonyms)
end

#to_spObject

adds method to convert a Regexp to StringPattern returns an array of string patterns or just one string pattern



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
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
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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
# File 'lib/string/pattern/add_to_ruby.rb', line 62

def to_sp
  regexp_s = self.to_s 
  return StringPattern.cache[regexp_s] unless StringPattern.cache[regexp_s].nil?
  regexp = Regexp.new regexp_s
  require 'regexp_parser'
  default_infinite = StringPattern.default_infinite
  pata = []
  pats = ''
  patg = [] # for (aa|bb|cc) group
  set = false
  capture = false

  range = ''
  fixed_text=false
  last_char = (regexp.to_s.gsub("?-mix:",'').length)-2
  Regexp::Scanner.scan regexp do |type, token, text, ts, te|
    if type == :escape
      if token == :dot
        token = :literal
        text = '.'
      elsif token == :literal and text.size == 2
        text = text[1]
      else 
        puts "Report token not controlled: type: #{type}, token: #{token}, text: '#{text}' [#{ts}..#{te}]"
      end
    end


    unless set || (token == :interval) || (token == :zero_or_one) ||
           (token == :zero_or_more) || (token == :one_or_more) || (pats == '')
      if (pats[0] == '[') && (pats[-1] == ']')
        pats[0] = ''
        if (token == :alternation) || !patg.empty?
          if fixed_text 
            if patg.size==0
              patg << (pata.pop + pats.chop)
            else
              patg[-1] += pats.chop
            end
          else
            patg << pats.chop
          end
        else
          if fixed_text 
            pata[-1]+=pats.chop
          else
            if pats.size==2
              pata << pats.chop #jal
            else
              pata << "1:[#{pats}" #jal
            end
            if last_char==te and type==:literal and token==:literal
              pata << text
              pats = ""
              next
            end
          end
        end
      else
        if (token == :alternation) || !patg.empty?
          patg << "1:#{pats}"
        else
          pata << "1:#{pats}"
        end
      end
      pats = ''
    end
    fixed_text=false

    case token
    when :open
      set = true
      pats += '['
    when :close
      if type == :set
        set = false
        if pats[-1] == '['
          pats.chop!
        else
          pats += ']'
        end
      elsif type == :group
        capture = false
        unless patg.empty?
          patg << pats if pats.to_s != ''
          pata << patg
          patg = []
          pats = ''
        end
      end
    when :capture
      capture = true if type == :group
    when :alternation
      if type == :meta
        if pats != ''
          patg << pats
          pats = ''
        elsif patg.empty?
          # for the case the first element was not added to patg and was on pata fex: (a+|b|c)
          patg << pata.pop
          end
      end
    when :range
      range = pats[-1]
      pats.chop!
    when :digit
      pats += 'n'
    when :nondigit
      pats += '*[%0123456789%]'
    when :space
      pats += '_'
    when :nonspace
      pats += '*[% %]'
    when :word
      pats += 'Ln_'
    when :nonword
      pats += '$'
    when :word_boundary
      pats += '$'
    when :dot
      pats += '*'
    when :literal
      if range == ''
        if text.size > 1
          fixed_text=true
          if !patg.empty?
            patg << text.chop
          else
            pata << text.chop
          end
          pats = text[-1]
        else
          pats += text
        end
      else
        range = range + '-' + text
        if range == 'a-z'
          pats = 'x' + pats
        elsif range == 'A-Z'
          pats = 'X' + pats
        elsif range == '0-9'
          pats = 'n' + pats
        else
          pats += if set
                    (range[0]..range[2]).to_a.join
                  else
                    '[' + (range[0]..range[2]).to_a.join + ']'
                    end

        end
        range = ''
      end
      pats = '[' + pats + ']' unless set
    when :interval
      size = text.sub(',', '-').sub('{', '').sub('}', '')
      size.chop! if size[-1] == '-'
      pats = size + ':' + pats
      if !patg.empty?
        patg << pats
      else
        pata << pats
      end
      pats = ''
    when :zero_or_one
      pats = '0-1:' + pats
      if !patg.empty?
        patg << pats
      else
        pata << pats
      end
      pats = ''
    when :zero_or_more
      pats = "0-#{default_infinite}:" + pats
      if !patg.empty?
        patg << pats
      else
        pata << pats
      end
      pats = ''
    when :one_or_more
      pats = "1-#{default_infinite}:" + pats
      if !patg.empty?
        patg << pats
      else
        pata << pats
      end
      pats = ''
    end
  end
  if pats!=""
    if pata.empty? 
      if pats[0]=="[" and pats[-1]=="]" #fex: /[12ab]/
        pata = ["1:#{pats}"]
      end
    else
      pata[-1]+=pats[1] #fex: /allo/
    end
  end
  if pata.size==1 and pata[0].kind_of?(String)
    res = pata[0]
  else
    res = pata
  end
  StringPattern.cache[regexp_s] = res
  return res
end