Class: RubyLexUtils

Inherits:
Object show all
Defined in:
lib/openc3/utilities/ruby_lex_utils.rb,
lib/openc3/utilities/ruby_lex_utils.rb

Constant Summary collapse

BLANK_LINE_REGEX =

Regular expression to detect blank lines

/^\s*$/
LONELY_ELSE_REGEX =

Regular expression to detect lines containing only ‘else’

/^\s*else\s*$/
KEY_KEYWORDS = 
[
  'class'.freeze,
  'module'.freeze,
  'def'.freeze,
  'undef'.freeze,
  'begin'.freeze,
  'rescue'.freeze,
  'ensure'.freeze,
  'end'.freeze,
  'if'.freeze,
  'unless'.freeze,
  'then'.freeze,
  'elsif'.freeze,
  'else'.freeze,
  'case'.freeze,
  'when'.freeze,
  'while'.freeze,
  'until'.freeze,
  'for'.freeze,
  'break'.freeze,
  'next'.freeze,
  'redo'.freeze,
  'retry'.freeze,
  'in'.freeze,
  'do'.freeze,
  'return'.freeze,
  'alias'.freeze
]
KEYWORD_TOKENS =

Ruby keywords

[RubyToken::TkCLASS,
RubyToken::TkMODULE,
RubyToken::TkDEF,
RubyToken::TkUNDEF,
RubyToken::TkBEGIN,
RubyToken::TkRESCUE,
RubyToken::TkENSURE,
RubyToken::TkEND,
RubyToken::TkIF,
RubyToken::TkUNLESS,
RubyToken::TkTHEN,
RubyToken::TkELSIF,
RubyToken::TkELSE,
RubyToken::TkCASE,
RubyToken::TkWHEN,
RubyToken::TkWHILE,
RubyToken::TkUNTIL,
RubyToken::TkFOR,
RubyToken::TkBREAK,
RubyToken::TkNEXT,
RubyToken::TkREDO,
RubyToken::TkRETRY,
RubyToken::TkIN,
RubyToken::TkDO,
RubyToken::TkRETURN,
RubyToken::TkIF_MOD,
RubyToken::TkUNLESS_MOD,
RubyToken::TkWHILE_MOD,
RubyToken::TkUNTIL_MOD,
RubyToken::TkALIAS,
RubyToken::TklBEGIN,
RubyToken::TklEND,
RubyToken::TkfLBRACE]
BLOCK_BEGINNING_TOKENS =

Ruby keywords which define the beginning of a block: do, {, begin

[RubyToken::TkDO,
RubyToken::TkfLBRACE,
RubyToken::TkBEGIN]

Instance Method Summary collapse

Constructor Details

#initialize ⇒ RubyLexUtils

Create a new RubyLex and StringIO to hold the text to operate on



84
85
86
87
 
# File 'lib/openc3/utilities/ruby_lex_utils.rb', line 84

def initialize
  @lex    = RubyLex.new
  @lex_io = StringIO.new('')
end

Instance Method Details

#contains_begin?(text) ⇒ Boolean

Returns Whether the text contains the ‘begin’ keyword.

Parameters:

Returns:

  • (Boolean) —

    Whether the text contains the 'begin' keyword



101
102
103
104
105
106
107
108
109
110
111
112
 
# File 'lib/openc3/utilities/ruby_lex_utils.rb', line 101

def contains_begin?(text)
  @lex.reinitialize
  @lex_io.string = text
  @lex.set_input(@lex_io)
  tokens = ripper_lex_without_warning(text)
  tokens.each do |token|
    if token[1] == :on_kw and token[2] == 'begin'
      return true
    end
  end
  return false
end

#contains_block_beginning?(text) ⇒ Boolean

Returns Whether the text contains a keyword which starts a block. i.e. ‘do’, ‘{’, or ‘begin’.

Parameters:

Returns:

  • (Boolean) —

    Whether the text contains a keyword which starts a block. i.e. 'do', '{', or 'begin'



136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
 
# File 'lib/openc3/utilities/ruby_lex_utils.rb', line 136

def contains_block_beginning?(text)
  @lex.reinitialize
  @lex_io.string = text
  @lex.set_input(@lex_io)
  tokens = ripper_lex_without_warning(text)
  tokens.each do |token|
    if token[1] == :on_kw
      if token[2] == 'begin' || token[2] == 'do'
        return true
      end
    elsif token[1] == :on_lbrace
      return true
    end
  end
  return false
end

#contains_keyword?(text) ⇒ Boolean

Returns Whether the text contains a Ruby keyword.

Parameters:

Returns:

  • (Boolean) —

    Whether the text contains a Ruby keyword



116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
 
# File 'lib/openc3/utilities/ruby_lex_utils.rb', line 116

def contains_keyword?(text)
  @lex.reinitialize
  @lex_io.string = text
  @lex.set_input(@lex_io)
  tokens = ripper_lex_without_warning(text)
  tokens.each do |token|
    if token[1] == :on_kw
      if KEY_KEYWORDS.include?(token[2])
        return true
      end
    elsif token[1] == :on_lbrace and !token[3].allbits?(Ripper::EXPR_BEG | Ripper::EXPR_LABEL)
      return true
    end
  end
  return false
end

#each_lexed_segment(text) {|line, instrumentable, inside_begin, line_no| ... } ⇒ Object

Yields each lexed segment and if the segment is instrumentable

Parameters:

Yield Parameters:

  • line (String) —

    The entire line

  • instrumentable (Boolean) —

    Whether the line is instrumentable

  • inside_begin (Integer) —

    The level of indentation

  • line_no (Integer) —

    The current line number



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
 
# File 'lib/openc3/utilities/ruby_lex_utils.rb', line 190

def each_lexed_segment(text)
  inside_begin = false
  indent = 0
  lex = RubyLex.new
  lex_io = StringIO.new(text)
  lex.set_input(lex_io)
  lex.line = ''
  while lexed = lex.lex
    lex.line_no += lexed.count("\n")
    lex.line.concat lexed
    next if lex.ltype or lex.continue

    # Detect the beginning and end of begin blocks so we can not catch exceptions there
    if indent == 0 and contains_begin?(lex.line)
      inside_begin = true
      indent = lex.indent
    else
      indent += lex.indent if indent > 0
    end

    if inside_begin and indent <= 0
      indent = 0
      inside_begin = false
    end

    loop do # loop to allow restarting for nested conditions
      # Yield blank lines and lonely else lines before the actual line
      while (index = lex.line.index("\n"))
        line = lex.line[0..index]
        if BLANK_LINE_REGEX.match?(line)
          yield line, true, inside_begin, lex.exp_line_no
          lex.exp_line_no += 1
          lex.line = lex.line[(index + 1)..-1]
        elsif LONELY_ELSE_REGEX.match?(line)
          yield line, false, inside_begin, lex.exp_line_no
          lex.exp_line_no += 1
          lex.line = lex.line[(index + 1)..-1]
        else
          break
        end
      end

      if contains_keyword?(lex.line)
        if contains_block_beginning?(lex.line)
          section = ''
          lex.line.each_line do |lexed_part|
            section << lexed_part
            if contains_block_beginning?(section)
              yield section, false, inside_begin, lex.exp_line_no
              break
            end
            lex.exp_line_no += 1
          end
          lex.exp_line_no += 1
          remainder = lex.line[(section.length)..-1]
          lex.line = remainder
          next unless remainder.empty?
        else
          yield lex.line, false, inside_begin, lex.exp_line_no
        end
      elsif !lex.line.empty?
        num_left_brackets  = lex.line.count('{')
        num_right_brackets = lex.line.count('}')
        if num_left_brackets != num_right_brackets
          # Don't instrument lines with unequal numbers of { and } brackets
          yield lex.line, false, inside_begin, lex.exp_line_no
        else
          yield lex.line, true, inside_begin, lex.exp_line_no
        end
      end
      lex.line = ''
      lex.exp_line_no = lex.line_no
      lex.indent = 0
      break
    end # loop do
  end # while lexed
end

#remove_comments(text, progress_dialog = nil) ⇒ String

Returns The text with all comments removed.

Parameters:

  • text (String)
  • progress_dialog (OpenC3::ProgressDialog) (defaults to: nil) —

    If this is set, the overall progress will be set as the processing progresses

Returns:

  • (String) —

    The text with all comments removed



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
 
# File 'lib/openc3/utilities/ruby_lex_utils.rb', line 157

def remove_comments(text, progress_dialog = nil)
  @lex.reinitialize
  @lex_io.string = text
  @lex.set_input(@lex_io)
  comments_removed = ""
  token_count = 0
  progress = 0.0
  tokens = ripper_lex_without_warning(text)
  tokens.each do |token|
    token_count += 1
    if token[1] != :on_comment
      comments_removed << token[2]
    else
      newline_count = token[2].count("\n")
      comments_removed << ("\n" * newline_count)
    end
    if progress_dialog and token_count % 10000 == 0
      progress += 0.01
      progress = 0.0 if progress >= 0.99
      progress_dialog.set_overall_progress(progress)
    end
  end

  return comments_removed
end

#ripper_lex_without_warning(code) ⇒ Object 



90
91
92
 
# File 'lib/openc3/utilities/ruby_lex_utils.rb', line 90

def ripper_lex_without_warning(code)
  RubyLex.ripper_lex_without_warning(code)
end