Class: RubyLex

Inherits:
Object show all
Defined in:
lib/irb/ruby-lex.rb

Overview

:stopdoc:

Defined Under Namespace

Classes: TerminateLineInput

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ RubyLex

Returns a new instance of RubyLex.



25
26
27
28
29
30
31
 
# File 'lib/irb/ruby-lex.rb', line 25

def initialize
  @exp_line_no = @line_no = 1
  @indent = 0
  @continue = false
  @line = ""
  @prompt = nil
end

Class Method Details

.compile_with_errors_suppressed(code) ⇒ Object 



33
34
35
36
37
38
39
40
41
42
43
 
# File 'lib/irb/ruby-lex.rb', line 33

def self.compile_with_errors_suppressed(code)
  line_no = 1
  begin
    result = yield code, line_no
  rescue ArgumentError
    code = ";\n#{code}"
    line_no = 0
    result = yield code, line_no
  end
  result
end

Instance Method Details

#check_code_block(code, tokens = @tokens) ⇒ Object 



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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
 
# File 'lib/irb/ruby-lex.rb', line 236

def check_code_block(code, tokens = @tokens)
  return true if tokens.empty?
  if tokens.last[1] == :on_heredoc_beg
    return true
  end

  begin # check if parser error are available
    verbose, $VERBOSE = $VERBOSE, nil
    case RUBY_ENGINE
    when 'ruby'
      self.class.compile_with_errors_suppressed(code) do |inner_code, line_no|
        RubyVM::InstructionSequence.compile(inner_code, nil, nil, line_no)
      end
    when 'jruby'
      JRuby.compile_ir(code)
    else
      catch(:valid) do
        eval("BEGIN { throw :valid, true }\n#{code}")
        false
      end
    end
  rescue EncodingError
    # This is for a hash with invalid encoding symbol, {"\xAE": 1}
  rescue SyntaxError => e
    case e.message
    when /unterminated (?:string|regexp) meets end of file/
      # "unterminated regexp meets end of file"
      #
      #   example:
      #     /
      #
      # "unterminated string meets end of file"
      #
      #   example:
      #     '
      return true
    when /syntax error, unexpected end-of-input/
      # "syntax error, unexpected end-of-input, expecting keyword_end"
      #
      #   example:
      #     if ture
      #       hoge
      #       if false
      #         fuga
      #       end
      return true
    when /syntax error, unexpected keyword_end/
      # "syntax error, unexpected keyword_end"
      #
      #   example:
      #     if (
      #     end
      #
      #   example:
      #     end
      return false
    when /syntax error, unexpected '\.'/
      # "syntax error, unexpected '.'"
      #
      #   example:
      #     .
      return false
    when /unexpected tREGEXP_BEG/
      # "syntax error, unexpected tREGEXP_BEG, expecting keyword_do or '{' or '('"
      #
      #   example:
      #     method / f /
      return false
    end
  ensure
    $VERBOSE = verbose
  end

  if defined?(Ripper::EXPR_BEG)
    last_lex_state = tokens.last[3]
    if last_lex_state.allbits?(Ripper::EXPR_BEG)
      return false
    elsif last_lex_state.allbits?(Ripper::EXPR_DOT)
      return true
    elsif last_lex_state.allbits?(Ripper::EXPR_CLASS)
      return true
    elsif last_lex_state.allbits?(Ripper::EXPR_FNAME)
      return true
    elsif last_lex_state.allbits?(Ripper::EXPR_VALUE)
      return true
    elsif last_lex_state.allbits?(Ripper::EXPR_ARG)
      return false
    end
  end

  false
end

#check_corresponding_token_depth ⇒ Object 



454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
 
# File 'lib/irb/ruby-lex.rb', line 454

def check_corresponding_token_depth
  corresponding_token_depth = nil
  is_first_spaces_of_line = true
  is_first_printable_of_line = true
  spaces_of_nest = []
  spaces_at_line_head = 0
  open_brace_on_line = 0
  in_oneliner_def = nil
  @tokens.each_with_index do |t, index|
    # detecting one-liner method definition
    if in_oneliner_def.nil?
      if t[3].allbits?(Ripper::EXPR_ENDFN)
        in_oneliner_def = :ENDFN
      end
    else
      if t[3].allbits?(Ripper::EXPR_ENDFN)
        # continuing
      elsif t[3].allbits?(Ripper::EXPR_BEG)
        if t[2] == '='
          in_oneliner_def = :BODY
        end
      else
        if in_oneliner_def == :BODY
          # one-liner method definition
          if is_first_printable_of_line
            corresponding_token_depth = spaces_of_nest.pop
          else
            spaces_of_nest.pop
            corresponding_token_depth = nil
          end
        end
        in_oneliner_def = nil
      end
    end

    case t[1]
    when :on_ignored_nl, :on_nl, :on_comment
      corresponding_token_depth = nil
      spaces_at_line_head = 0
      is_first_spaces_of_line = true
      is_first_printable_of_line = true
      open_brace_on_line = 0
      next
    when :on_sp
      spaces_at_line_head = t[2].count(' ') if is_first_spaces_of_line
      is_first_spaces_of_line = false
      next
    end
    case t[1]
    when :on_lbracket, :on_lbrace, :on_lparen, :on_tlambeg
      spaces_of_nest.push(spaces_at_line_head + open_brace_on_line * 2)
      open_brace_on_line += 1
    when :on_rbracket, :on_rbrace, :on_rparen
      if is_first_printable_of_line
        corresponding_token_depth = spaces_of_nest.pop
      else
        spaces_of_nest.pop
        corresponding_token_depth = nil
      end
      open_brace_on_line -= 1
    when :on_kw
      next if index > 0 and @tokens[index - 1][3].allbits?(Ripper::EXPR_FNAME)
      case t[2]
      when 'def', 'do', 'case', 'for', 'begin', 'class', 'module'
        spaces_of_nest.push(spaces_at_line_head)
      when 'rescue'
        unless t[3].allbits?(Ripper::EXPR_LABEL)
          corresponding_token_depth = spaces_of_nest.last
        end
      when 'if', 'unless', 'while', 'until'
        # postfix if/unless/while/until must be Ripper::EXPR_LABEL
        unless t[3].allbits?(Ripper::EXPR_LABEL)
          spaces_of_nest.push(spaces_at_line_head)
        end
      when 'else', 'elsif', 'ensure', 'when', 'in'
        corresponding_token_depth = spaces_of_nest.last
      when 'end'
        if is_first_printable_of_line
          corresponding_token_depth = spaces_of_nest.pop
        else
          spaces_of_nest.pop
          corresponding_token_depth = nil
        end
      end
    end
    is_first_spaces_of_line = false
    is_first_printable_of_line = false
  end
  corresponding_token_depth
end

#check_newline_depth_difference ⇒ Object 



385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
 
# File 'lib/irb/ruby-lex.rb', line 385

def check_newline_depth_difference
  depth_difference = 0
  open_brace_on_line = 0
  in_oneliner_def = nil
  @tokens.each_with_index do |t, index|
    # detecting one-liner method definition
    if in_oneliner_def.nil?
      if t[3].allbits?(Ripper::EXPR_ENDFN)
        in_oneliner_def = :ENDFN
      end
    else
      if t[3].allbits?(Ripper::EXPR_ENDFN)
        # continuing
      elsif t[3].allbits?(Ripper::EXPR_BEG)
        if t[2] == '='
          in_oneliner_def = :BODY
        end
      else
        if in_oneliner_def == :BODY
          # one-liner method definition
          depth_difference -= 1
        end
        in_oneliner_def = nil
      end
    end

    case t[1]
    when :on_ignored_nl, :on_nl, :on_comment
      if index != (@tokens.size - 1)
        depth_difference = 0
        open_brace_on_line = 0
      end
      next
    when :on_sp
      next
    end
    case t[1]
    when :on_lbracket, :on_lbrace, :on_lparen, :on_tlambeg
      depth_difference += 1
      open_brace_on_line += 1
    when :on_rbracket, :on_rbrace, :on_rparen
      depth_difference -= 1 if open_brace_on_line > 0
    when :on_kw
      next if index > 0 and @tokens[index - 1][3].allbits?(Ripper::EXPR_FNAME)
      case t[2]
      when 'do'
        if index > 0 and @tokens[index - 1][3].anybits?(Ripper::EXPR_CMDARG | Ripper::EXPR_ENDFN | Ripper::EXPR_ARG)
          # method_with_block do; end
          depth_difference += 1
        else
          # while cond do; end # also "until" or "for"
          # This "do" doesn't increment indent because "while" already
          # incremented.
        end
      when 'def', 'case', 'for', 'begin', 'class', 'module'
        depth_difference += 1
      when 'if', 'unless', 'while', 'until', 'rescue'
        # postfix if/unless/while/until/rescue must be Ripper::EXPR_LABEL
        unless t[3].allbits?(Ripper::EXPR_LABEL)
          depth_difference += 1
        end
      when 'else', 'elsif', 'ensure', 'when', 'in'
        depth_difference += 1
      end
    end
  end
  depth_difference
end

#check_state(code, tokens = nil) ⇒ Object 



144
145
146
147
148
149
150
151
 
# File 'lib/irb/ruby-lex.rb', line 144

def check_state(code, tokens = nil)
  tokens = ripper_lex_without_warning(code) unless tokens
  ltype = process_literal_type(tokens)
  indent = process_nesting_level(tokens)
  continue = process_continue(tokens)
  code_block_open = check_code_block(code, tokens)
  [ltype, indent, continue, code_block_open]
end

#check_string_literal(tokens) ⇒ Object 



545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
 
# File 'lib/irb/ruby-lex.rb', line 545

def check_string_literal(tokens)
  i = 0
  start_token = []
  end_type = []
  while i < tokens.size
    t = tokens[i]
    case t[1]
    when :on_tstring_beg
      start_token << t
      end_type << [:on_tstring_end, :on_label_end]
    when :on_regexp_beg
      start_token << t
      end_type << :on_regexp_end
    when :on_symbeg
      acceptable_single_tokens = %i{on_ident on_const on_op on_cvar on_ivar on_gvar on_kw}
      if (i + 1) < tokens.size and acceptable_single_tokens.all?{ |st| tokens[i + 1][1] != st }
        start_token << t
        end_type << :on_tstring_end
      end
    when :on_backtick
      start_token << t
      end_type << :on_tstring_end
    when :on_qwords_beg, :on_words_beg, :on_qsymbols_beg, :on_symbols_beg
      start_token << t
      end_type << :on_tstring_end
    when :on_heredoc_beg
      start_token << t
      end_type << :on_heredoc_end
    when *end_type.last
      start_token.pop
      end_type.pop
    end
    i += 1
  end
  start_token.last.nil? ? '' : start_token.last
end

#each_top_level_statement ⇒ Object 



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
 
# File 'lib/irb/ruby-lex.rb', line 168

def each_top_level_statement
  initialize_input
  catch(:TERM_INPUT) do
    loop do
      begin
        prompt
        unless l = lex
          throw :TERM_INPUT if @line == ''
        else
          @line_no += l.count("\n")
          next if l == "\n"
          @line.concat l
          if @code_block_open or @ltype or @continue or @indent > 0
            next
          end
        end
        if @line != "\n"
          @line.force_encoding(@io.encoding)
          yield @line, @exp_line_no
        end
        break if @io.eof?
        @line = ''
        @exp_line_no = @line_no

        @indent = 0
      rescue TerminateLineInput
        initialize_input
        prompt
      end
    end
  end
end

#initialize_input ⇒ Object 



159
160
161
162
163
164
165
166
 
# File 'lib/irb/ruby-lex.rb', line 159

def initialize_input
  @ltype = nil
  @indent = 0
  @continue = false
  @line = ""
  @exp_line_no = @line_no
  @code_block_open = false
end

#lex ⇒ Object 



201
202
203
204
205
206
207
208
209
210
211
212
213
214
 
# File 'lib/irb/ruby-lex.rb', line 201

def lex
  line = @input.call
  if @io.respond_to?(:check_termination)
    return line # multiline
  end
  code = @line + (line.nil? ? '' : line)
  code.gsub!(/\s*\z/, '').concat("\n")
  @tokens = ripper_lex_without_warning(code)
  @continue = process_continue
  @code_block_open = check_code_block(code)
  @indent = process_nesting_level
  @ltype = process_literal_type
  line
end

#process_continue(tokens = @tokens) ⇒ Object 



216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
 
# File 'lib/irb/ruby-lex.rb', line 216

def process_continue(tokens = @tokens)
  # last token is always newline
  if tokens.size >= 2 and tokens[-2][1] == :on_regexp_end
    # end of regexp literal
    return false
  elsif tokens.size >= 2 and tokens[-2][1] == :on_semicolon
    return false
  elsif tokens.size >= 2 and tokens[-2][1] == :on_kw and ['begin', 'else', 'ensure'].include?(tokens[-2][2])
    return false
  elsif !tokens.empty? and tokens.last[2] == "\\\n"
    return true
  elsif tokens.size >= 1 and tokens[-1][1] == :on_heredoc_end # "EOH\n"
    return false
  elsif tokens.size >= 2 and defined?(Ripper::EXPR_BEG) and tokens[-2][3].anybits?(Ripper::EXPR_BEG | Ripper::EXPR_FNAME)
    # end of literal except for regexp
    return true
  end
  false
end

#process_literal_type(tokens = @tokens) ⇒ Object 



582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
 
# File 'lib/irb/ruby-lex.rb', line 582

def process_literal_type(tokens = @tokens)
  start_token = check_string_literal(tokens)
  case start_token[1]
  when :on_tstring_beg
    case start_token[2]
    when ?"      then ?"
    when /^%.$/  then ?"
    when /^%Q.$/ then ?"
    when ?'      then ?'
    when /^%q.$/ then ?'
    end
  when :on_regexp_beg   then ?/
  when :on_symbeg       then ?:
  when :on_backtick     then ?`
  when :on_qwords_beg   then ?]
  when :on_words_beg    then ?]
  when :on_qsymbols_beg then ?]
  when :on_symbols_beg  then ?]
  when :on_heredoc_beg
    start_token[2] =~ /<<[-~]?(['"`])[_a-zA-Z0-9]+\1/
    case $1
    when ?" then ?"
    when ?' then ?'
    when ?` then ?`
    else         ?"
    end
  else
    nil
  end
end

#process_nesting_level(tokens = @tokens) ⇒ Object 



329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
 
# File 'lib/irb/ruby-lex.rb', line 329

def process_nesting_level(tokens = @tokens)
  indent = 0
  in_oneliner_def = nil
  tokens.each_with_index { |t, index|
    # detecting one-liner method definition
    if in_oneliner_def.nil?
      if t[3].allbits?(Ripper::EXPR_ENDFN)
        in_oneliner_def = :ENDFN
      end
    else
      if t[3].allbits?(Ripper::EXPR_ENDFN)
        # continuing
      elsif t[3].allbits?(Ripper::EXPR_BEG)
        if t[2] == '='
          in_oneliner_def = :BODY
        end
      else
        if in_oneliner_def == :BODY
          # one-liner method definition
          indent -= 1
        end
        in_oneliner_def = nil
      end
    end

    case t[1]
    when :on_lbracket, :on_lbrace, :on_lparen, :on_tlambeg
      indent += 1
    when :on_rbracket, :on_rbrace, :on_rparen
      indent -= 1
    when :on_kw
      next if index > 0 and tokens[index - 1][3].allbits?(Ripper::EXPR_FNAME)
      case t[2]
      when 'do'
        if index > 0 and tokens[index - 1][3].anybits?(Ripper::EXPR_CMDARG | Ripper::EXPR_ENDFN | Ripper::EXPR_ARG)
          # method_with_block do; end
          indent += 1
        else
          # while cond do; end # also "until" or "for"
          # This "do" doesn't increment indent because "while" already
          # incremented.
        end
      when 'def', 'case', 'for', 'begin', 'class', 'module'
        indent += 1
      when 'if', 'unless', 'while', 'until'
        # postfix if/unless/while/until must be Ripper::EXPR_LABEL
        indent += 1 unless t[3].allbits?(Ripper::EXPR_LABEL)
      when 'end'
        indent -= 1
      end
    end
    # percent literals are not indented
  }
  indent
end

#prompt ⇒ Object 



153
154
155
156
157
 
# File 'lib/irb/ruby-lex.rb', line 153

def prompt
  if @prompt
    @prompt.call(@ltype, @indent, @continue, @line_no)
  end
end

#ripper_lex_without_warning(code) ⇒ Object 



109
110
111
112
113
114
115
116
117
 
# File 'lib/irb/ruby-lex.rb', line 109

def ripper_lex_without_warning(code)
  verbose, $VERBOSE = $VERBOSE, nil
  tokens = nil
  self.class.compile_with_errors_suppressed(code) do |inner_code, line_no|
    tokens = Ripper.lex(inner_code, '-', line_no)
  end
  $VERBOSE = verbose
  tokens
end

#set_auto_indent(context) ⇒ Object 



119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
 
# File 'lib/irb/ruby-lex.rb', line 119

def set_auto_indent(context)
  if @io.respond_to?(:auto_indent) and context.auto_indent_mode
    @io.auto_indent do |lines, line_index, byte_pointer, is_newline|
      if is_newline
        md = lines[line_index - 1].match(/(\A +)/)
        prev_spaces = md.nil? ? 0 : md[1].count(' ')
        @tokens = ripper_lex_without_warning(lines[0..line_index].join("\n"))
        depth_difference = check_newline_depth_difference
        prev_spaces + depth_difference * 2
      else
        code = line_index.zero? ? '' : lines[0..(line_index - 1)].map{ |l| l + "\n" }.join
        last_line = lines[line_index]&.byteslice(0, byte_pointer)
        code += last_line if last_line
        @tokens = ripper_lex_without_warning(code)
        corresponding_token_depth = check_corresponding_token_depth
        if corresponding_token_depth
          corresponding_token_depth
        else
          nil
        end
      end
    end
  end
end

#set_input(io, p = nil, &block) ⇒ Object

io functions



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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/irb/ruby-lex.rb', line 46

def set_input(io, p = nil, &block)
  @io = io
  if @io.respond_to?(:check_termination)
    @io.check_termination do |code|
      code.gsub!(/\s*\z/, '').concat("\n")
      ltype, indent, continue, code_block_open = check_state(code)
      if ltype or indent > 0 or continue or code_block_open
        false
      else
        true
      end
    end
  end
  if @io.respond_to?(:dynamic_prompt)
    @io.dynamic_prompt do |lines|
      lines << '' if lines.empty?
      result = []
      tokens = ripper_lex_without_warning(lines.map{ |l| l + "\n" }.join)
      code = String.new
      partial_tokens = []
      unprocessed_tokens = []
      line_num_offset = 0
      tokens.each do |t|
        partial_tokens << t
        unprocessed_tokens << t
        if t[2].include?("\n")
          t_str = t[2]
          t_str.each_line("\n") do |s|
            code << s << "\n"
            ltype, indent, continue, code_block_open = check_state(code, partial_tokens)
            result << @prompt.call(ltype, indent, continue || code_block_open, @line_no + line_num_offset)
            line_num_offset += 1
          end
          unprocessed_tokens = []
        else
          code << t[2]
        end
      end
      unless unprocessed_tokens.empty?
        ltype, indent, continue, code_block_open = check_state(code, unprocessed_tokens)
        result << @prompt.call(ltype, indent, continue || code_block_open, @line_no + line_num_offset)
      end
      result
    end
  end
  if p.respond_to?(:call)
    @input = p
  elsif block_given?
    @input = block
  else
    @input = Proc.new{@io.gets}
  end
end

#set_prompt(p = nil, &block) ⇒ Object 



100
101
102
103
104
105
106
107
 
# File 'lib/irb/ruby-lex.rb', line 100

def set_prompt(p = nil, &block)
  p = block if block_given?
  if p.respond_to?(:call)
    @prompt = p
  else
    @prompt = Proc.new{print p}
  end
end