Class: Opal::Lexer

Inherits:
Object show all
Defined in:
opal/lib/opal/parser/lexer.rb

Overview

Lexer is used by Parser to step through ruby code, and returning tokens representing each chunk of ruby code.

Tokens are in the form:

[token, [value, location]]

where location is in the form [line_number, column_number]. The location data can be used to produce source maps in the compiler. Tokens are generally ruby symbols, and the value will always be a string value.

The main method used by the parser is #next_token, which is called repeatedly until a token of value false is returned, which indicated the EOF has been reached.

Generally this class is only used by Parser directly.

Constant Summary

STR_FUNC_ESCAPE = 
0x01
STR_FUNC_EXPAND = 
0x02
STR_FUNC_REGEXP = 
0x04
STR_FUNC_QWORDS = 
0x08
STR_FUNC_SYMBOL = 
0x10
STR_FUNC_INDENT = 
0x20
STR_FUNC_XQUOTE = 
0x40
STR_SQUOTE = 
0x00
STR_DQUOTE = 
STR_FUNC_EXPAND
STR_XQUOTE = 
STR_FUNC_EXPAND | STR_FUNC_XQUOTE
STR_REGEXP = 
STR_FUNC_REGEXP | STR_FUNC_ESCAPE | STR_FUNC_EXPAND
STR_SWORD = 
STR_FUNC_QWORDS
STR_DWORD = 
STR_FUNC_QWORDS | STR_FUNC_EXPAND
STR_SSYM = 
STR_FUNC_SYMBOL
STR_DSYM = 
STR_FUNC_SYMBOL | STR_FUNC_EXPAND

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(source, file) ⇒ Lexer

Create a new instance using the given ruby code and filename for reference.

Opal::Lexer.new("ruby code", "my_file.rb")

Parameters:

  • source (String) —

    ruby code to lex

  • file (String) —

    filename of given ruby code



59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'opal/lib/opal/parser/lexer.rb', line 59

def initialize(source, file)
  @lex_state  = :expr_beg
  @cond       = 0
  @cmdarg     = 0
  @line       = 1
  @tok_line   = 1
  @column     = 0
  @tok_column = 0
  @file       = file

  @scanner = StringScanner.new(source)
  @scanner_stack = [@scanner]

  @case_stmt = nil
  @start_of_lambda = nil
end

Instance Attribute Details

#column ⇒ Object (readonly)

Returns the value of attribute column



42
43
44
 
# File 'opal/lib/opal/parser/lexer.rb', line 42

def column
  @column
end

#eof_content ⇒ Object (readonly)

Returns the value of attribute eof_content



44
45
46
 
# File 'opal/lib/opal/parser/lexer.rb', line 44

def eof_content
  @eof_content
end

#lex_state ⇒ Object

Returns the value of attribute lex_state



46
47
48
 
# File 'opal/lib/opal/parser/lexer.rb', line 46

def lex_state
  @lex_state
end

#line ⇒ Object

Returns the value of attribute line



42
43
44
 
# File 'opal/lib/opal/parser/lexer.rb', line 42

def line
  @line
end

#parser ⇒ Object

Returns the value of attribute parser



50
51
52
 
# File 'opal/lib/opal/parser/lexer.rb', line 50

def parser
  @parser
end

#scanner ⇒ Object

Returns the value of attribute scanner



48
49
50
 
# File 'opal/lib/opal/parser/lexer.rb', line 48

def scanner
  @scanner
end

#scope ⇒ Object (readonly)

Returns the value of attribute scope



43
44
45
 
# File 'opal/lib/opal/parser/lexer.rb', line 43

def scope
  @scope
end

#strterm ⇒ Object

Returns the value of attribute strterm



47
48
49
 
# File 'opal/lib/opal/parser/lexer.rb', line 47

def strterm
  @strterm
end

#yylval ⇒ Object

Returns the value of attribute yylval



49
50
51
 
# File 'opal/lib/opal/parser/lexer.rb', line 49

def yylval
  @yylval
end

Instance Method Details

#add_string_content(str_buffer, str_parse) ⇒ Object 



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
453
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
 
# File 'opal/lib/opal/parser/lexer.rb', line 420

def add_string_content(str_buffer, str_parse)
  func = str_parse[:func]

  end_str_re = Regexp.new(Regexp.escape(str_parse[:term]))

  qwords = (func & STR_FUNC_QWORDS) != 0
  expand = (func & STR_FUNC_EXPAND) != 0
  regexp = (func & STR_FUNC_REGEXP) != 0
  escape = (func & STR_FUNC_ESCAPE) != 0
  xquote = (func == STR_XQUOTE)

  until scanner.eos?
    c = nil
    handled = true

    if check end_str_re
      # eos
      # if its just balancing, add it ass normal content..
      if str_parse[:balance] && (str_parse[:nesting] != 0)
        # we only checked above, so actually scan it
        scan end_str_re
        c = scanner.matched
        str_parse[:nesting] -= 1
      else
        # not balancing, so break (eos!)
        break
      end

    elsif str_parse[:balance] and scan Regexp.new(Regexp.escape(str_parse[:paren]))
      str_parse[:nesting] += 1
      c = scanner.matched

    elsif qwords && scan(/\s/)
      pushback(1)
      break
    elsif expand && check(/#(?=[\$\@\{])/)
      break
    elsif qwords and scan(/\s/)
      pushback(1)
      break
    elsif scan(/\\/)
      if xquote # opal - treat xstrings as dquotes? forces us to double escape
        c = "\\" + scan(/./)
      elsif qwords and scan(/\n/)
        str_buffer << "\n"
        next
      elsif expand and scan(/\n/)
        next
      elsif qwords and scan(/\s/)
        c = ' '
      elsif regexp
        if scan(/(.)/)
          c = "\\" + scanner.matched
        end
      elsif expand
        c = self.read_escape
      elsif scan(/\n/)
        # nothing..
      elsif scan(/\\/)
        if escape
          c = "\\\\"
        else
          c = scanner.matched
        end
      else # \\
        unless scan(end_str_re)
          str_buffer << "\\"
        else
          #c = scanner.matched
        end
      end
    else
      handled = false
    end

    unless handled
      reg = if qwords
              Regexp.new("[^#{Regexp.escape str_parse[:term]}\#\0\n\ \\\\]+|.")
            elsif str_parse[:balance]
              Regexp.new("[^#{Regexp.escape str_parse[:term]}#{Regexp.escape str_parse[:paren]}\#\0\\\\]+|.")
            else
              Regexp.new("[^#{Regexp.escape str_parse[:term]}\#\0\\\\]+|.")
            end

      scan reg
      c = scanner.matched
    end

    c ||= scanner.matched
    str_buffer << c
  end

  raise "reached EOF while in string" if scanner.eos?
end

#after_operator? ⇒ Boolean

Returns:

  • (Boolean) 


143
144
145
 
# File 'opal/lib/opal/parser/lexer.rb', line 143

def after_operator?
  [:expr_fname, :expr_dot].include? @lex_state
end

#arg? ⇒ Boolean

Returns:

  • (Boolean) 


131
132
133
 
# File 'opal/lib/opal/parser/lexer.rb', line 131

def arg?
  [:expr_arg, :expr_cmdarg].include? @lex_state
end

#beg? ⇒ Boolean

Returns:

  • (Boolean) 


139
140
141
 
# File 'opal/lib/opal/parser/lexer.rb', line 139

def beg?
  [:expr_beg, :expr_value, :expr_mid, :expr_class].include? @lex_state
end

#check(regexp) ⇒ Object 



181
182
183
 
# File 'opal/lib/opal/parser/lexer.rb', line 181

def check(regexp)
  @scanner.check regexp
end

#cmdarg? ⇒ Boolean

Returns:

  • (Boolean) 


127
128
129
 
# File 'opal/lib/opal/parser/lexer.rb', line 127

def cmdarg?
  (@cmdarg & 1) != 0
end

#cmdarg_lexpop ⇒ Object 



123
124
125
 
# File 'opal/lib/opal/parser/lexer.rb', line 123

def cmdarg_lexpop
  @cmdarg = (@cmdarg >> 1) | (@cmdarg & 1)
end

#cmdarg_pop ⇒ Object 



119
120
121
 
# File 'opal/lib/opal/parser/lexer.rb', line 119

def cmdarg_pop
  @cmdarg = @cmdarg >> 1
end

#cmdarg_push(n) ⇒ Object 



115
116
117
 
# File 'opal/lib/opal/parser/lexer.rb', line 115

def cmdarg_push(n)
  @cmdarg = (@cmdarg << 1) | (n & 1)
end

#cond? ⇒ Boolean

Returns:

  • (Boolean) 


111
112
113
 
# File 'opal/lib/opal/parser/lexer.rb', line 111

def cond?
  (@cond & 1) != 0
end

#cond_lexpop ⇒ Object 



107
108
109
 
# File 'opal/lib/opal/parser/lexer.rb', line 107

def cond_lexpop
  @cond = (@cond >> 1) | (@cond & 1)
end

#cond_pop ⇒ Object 



103
104
105
 
# File 'opal/lib/opal/parser/lexer.rb', line 103

def cond_pop
  @cond = @cond >> 1
end

#cond_push(n) ⇒ Object 



99
100
101
 
# File 'opal/lib/opal/parser/lexer.rb', line 99

def cond_push(n)
  @cond = (@cond << 1) | (n & 1)
end

#end? ⇒ Boolean

Returns:

  • (Boolean) 


135
136
137
 
# File 'opal/lib/opal/parser/lexer.rb', line 135

def end?
  [:expr_end, :expr_endarg, :expr_endfn].include? @lex_state
end

#has_local?(local) ⇒ Boolean

Returns:

  • (Boolean) 


95
96
97
 
# File 'opal/lib/opal/parser/lexer.rb', line 95

def has_local?(local)
  parser.scope.has_local?(local.to_sym)
end

#here_document(str_parse) ⇒ Object 



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
328
329
330
331
 
# File 'opal/lib/opal/parser/lexer.rb', line 279

def here_document(str_parse)
  eos_regx = /[ \t]*#{Regexp.escape(str_parse[:term])}(\r*\n|$)/
  expand = true

  # Don't escape single-quoted heredoc identifiers
  escape = str_parse[:func] != STR_SQUOTE

  if check(eos_regx)
    scan(/[ \t]*#{Regexp.escape(str_parse[:term])}/)

    if str_parse[:scanner]
      @scanner_stack << str_parse[:scanner]
      @scanner = str_parse[:scanner]
    end

    return :tSTRING_END
  end

  str_buffer = []

  if scan(/#/)
    if tok = peek_variable_name
      return tok
    end

    str_buffer << '#'
  end

  until check(eos_regx) && scanner.bol?
    if scanner.eos?
      raise "reached EOF while in heredoc"
    end

    if scan(/\n/)
      str_buffer << scanner.matched
    elsif expand && check(/#(?=[\$\@\{])/)
      break
    elsif scan(/\\/)
      str_buffer << (escape ? self.read_escape : scanner.matched)
    else
      reg = Regexp.new("[^\#\0\\\\\n]+|.")

      scan reg
      str_buffer << scanner.matched
    end
  end

  complete_str = str_buffer.join ''
  @line += complete_str.count("\n")

  self.yylval = complete_str
  return :tSTRING_CONTENT
end

#heredoc_identifier ⇒ Object 



515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
 
# File 'opal/lib/opal/parser/lexer.rb', line 515

def heredoc_identifier
  if scan(/(-?)(['"])?(\w+)\2?/)
    escape_method = (@scanner[2] == "'") ? STR_SQUOTE : STR_DQUOTE
    heredoc = @scanner[3]

    self.strterm = new_strterm(escape_method, heredoc, heredoc)
    self.strterm[:type] = :heredoc

    # if ruby code at end of line after heredoc, we have to store it to
    # parse after heredoc is finished parsing
    end_of_line = scan(/.*\n/)
    self.strterm[:scanner] = StringScanner.new(end_of_line) if end_of_line != "\n"

    self.line += 1
    self.yylval = heredoc
    return :tSTRING_BEG
  end
end

#label_state? ⇒ Boolean

Returns:

  • (Boolean) 


147
148
149
 
# File 'opal/lib/opal/parser/lexer.rb', line 147

def label_state?
  [:expr_beg, :expr_endfn].include?(@lex_state) or arg?
end

#matched ⇒ Object 



189
190
191
 
# File 'opal/lib/opal/parser/lexer.rb', line 189

def matched
  @scanner.matched
end

#new_op_asgn(value) ⇒ Object 



207
208
209
210
 
# File 'opal/lib/opal/parser/lexer.rb', line 207

def new_op_asgn(value)
  self.yylval = value
  :tOP_ASGN
end

#new_strterm(func, term, paren) ⇒ Object 



198
199
200
 
# File 'opal/lib/opal/parser/lexer.rb', line 198

def new_strterm(func, term, paren)
  { :type => :string, :func => func, :term => term, :paren => paren }
end

#new_strterm2(func, term, paren) ⇒ Object 



202
203
204
205
 
# File 'opal/lib/opal/parser/lexer.rb', line 202

def new_strterm2(func, term, paren)
  term = new_strterm(func, term, paren)
  term.merge({ :balance => true, :nesting => 0 })
end

#next_token ⇒ Array

Returns next token from source input stream.

Token in form:

[token, [value, [source_line, source_column]]]

Returns:

  • (Array) 


83
84
85
86
87
88
89
90
91
92
93
 
# File 'opal/lib/opal/parser/lexer.rb', line 83

def next_token
  token     = self.yylex
  value     = self.yylval
  location  = [@tok_line, @tok_column]

  # once location is stored, ensure next token starts in correct place
  @tok_column = @column
  @tok_line = @line

  [token, [value, location]]
end

#parse_string ⇒ Object 



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
384
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
 
# File 'opal/lib/opal/parser/lexer.rb', line 333

def parse_string
  str_parse = self.strterm
  func = str_parse[:func]

  space = false

  qwords = (func & STR_FUNC_QWORDS) != 0
  expand = (func & STR_FUNC_EXPAND) != 0
  regexp = (func & STR_FUNC_REGEXP) != 0

  space = true if qwords and scan(/\s+/)

  # if not end of string, so we must be parsing contents
  str_buffer = []

  if scan Regexp.new(Regexp.escape(str_parse[:term]))
    if qwords && !str_parse[:done_last_space]#&& space
      str_parse[:done_last_space] = true
      pushback(1)
      self.yylval = ' '
      return :tSPACE
    end

    if str_parse[:balance]
      if str_parse[:nesting] == 0

        if regexp
          self.yylval = scan(/\w+/)
          return :tREGEXP_END
        end
        return :tSTRING_END
      else
        str_buffer << scanner.matched
        str_parse[:nesting] -= 1
        self.strterm = str_parse
      end
    elsif regexp
      @lex_state = :expr_end
      self.yylval = scan(/\w+/)
      return :tREGEXP_END
    else
      if str_parse[:scanner]
        @scanner_stack << str_parse[:scanner]
        @scanner = str_parse[:scanner]
      end

      return :tSTRING_END
    end
  end

  if space
    self.yylval = ' '
    return :tSPACE
  end

  if str_parse[:balance] and scan Regexp.new(Regexp.escape(str_parse[:paren]))
    str_buffer << scanner.matched
    str_parse[:nesting] += 1
  elsif check(/#[@$]/)
    scan(/#/)
    if expand
      return :tSTRING_DVAR
    else
      str_buffer << scanner.matched
    end

  elsif scan(/#\{/)
    if expand
      return :tSTRING_DBEG
    else
      str_buffer << scanner.matched
    end

  # causes error, so we will just collect it later on with other text
  elsif scan(/\#/)
    str_buffer << '#'
  end

  add_string_content str_buffer, str_parse

  complete_str = str_buffer.join ''
  @line += complete_str.count("\n")

  self.yylval = complete_str
  return :tSTRING_CONTENT
end

#peek_variable_name ⇒ Object 



271
272
273
274
275
276
277
 
# File 'opal/lib/opal/parser/lexer.rb', line 271

def peek_variable_name
  if check(/[@$]/)
    :tSTRING_DVAR
  elsif scan(/\{/)
    :tSTRING_DBEG
  end
end

#process_identifier(matched, cmd_start) ⇒ Object 



534
535
536
537
538
539
540
541
542
543
544
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
581
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
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
 
# File 'opal/lib/opal/parser/lexer.rb', line 534

def process_identifier(matched, cmd_start)
  last_state = @lex_state

  if label_state? and !check(/::/) and scan(/:/)
    @lex_state = :expr_beg
    self.yylval = matched
    return :tLABEL
  end

  if matched == 'defined?'
    if after_operator?
      @lex_state = :expr_end
      return :tIDENTIFIER
    end

    @lex_state = :expr_arg
    return :kDEFINED
  end

  if matched.end_with? '?', '!'
    result = :tIDENTIFIER
  else
    if @lex_state == :expr_fname
      if !check(/\=\>/) and scan(/\=/)
        result = :tIDENTIFIER
        matched += scanner.matched
      end

    elsif matched =~ /#{REGEXP_START}[A-Z]/
      result = :tCONSTANT
    else
      result = :tIDENTIFIER
    end
  end

  if @lex_state != :expr_dot and kw = Keywords.keyword(matched)
    old_state = @lex_state
    @lex_state = kw.state

    if old_state == :expr_fname
      self.yylval = kw.name
      return kw.id[0]
    end

    if @lex_state == :expr_beg
      cmd_start = true
    end

    if matched == "do"
      if after_operator?
        @lex_state = :expr_end
        return :tIDENTIFIER
      end

      if @start_of_lambda
        @start_of_lambda = false
        @lex_state = :expr_beg
        return :kDO_LAMBDA
      elsif cond?
        @lex_state = :expr_beg
        return :kDO_COND
      elsif cmdarg? && @lex_state != :expr_cmdarg
        @lex_state = :expr_beg
        return :kDO_BLOCK
      elsif @lex_state == :expr_endarg
        return :kDO_BLOCK
      else
        @lex_state = :expr_beg
        return :kDO
      end
    else
      if old_state == :expr_beg or old_state == :expr_value
        self.yylval = matched
        return kw.id[0]
      else
        if kw.id[0] != kw.id[1]
          @lex_state = :expr_beg
        end

        self.yylval = matched
        return kw.id[1]
      end
    end
  end

  if [:expr_beg, :expr_dot, :expr_mid, :expr_arg, :expr_cmdarg].include? @lex_state
    @lex_state = cmd_start ? :expr_cmdarg : :expr_arg
  elsif @lex_state == :expr_fname
    @lex_state = :expr_endfn
  else
    @lex_state = :expr_end
  end

  if ![:expr_dot, :expr_fname].include?(last_state) and has_local?(matched)
    @lex_state = :expr_end
  end

  return matched =~ /#{REGEXP_START}[A-Z]/ ? :tCONSTANT : :tIDENTIFIER
end

#process_numeric ⇒ Object 



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
 
# File 'opal/lib/opal/parser/lexer.rb', line 212

def process_numeric
  @lex_state = :expr_end

  if scan(/[\d_]+\.[\d_]+\b|[\d_]+(\.[\d_]+)?[eE][-+]?[\d_]+\b/) # FLOATS
    self.yylval = scanner.matched.gsub(/_/, '').to_f
    return :tFLOAT
  elsif scan(/([^0][\d_]*|0)\b/)                                 # BASE 10
    self.yylval = scanner.matched.gsub(/_/, '').to_i
    return :tINTEGER
  elsif scan(/0[bB](0|1|_)+/)                                    # BASE 2
    self.yylval = scanner.matched.to_i(2)
    return :tINTEGER
  elsif scan(/0[xX](\d|[a-f]|[A-F]|_)+/)                         # BASE 16
    self.yylval = scanner.matched.to_i(16)
    return :tINTEGER
  elsif scan(/0[oO]?([0-7]|_)+/)                                 # BASE 8
    self.yylval = scanner.matched.to_i(8)
    return :tINTEGER
  elsif scan(/0[dD]([0-9]|_)+/)                                  # BASE 10
    self.yylval = scanner.matched.gsub(/_/, '').to_i
    return :tINTEGER
  else
    raise "Lexing error on numeric type: `#{scanner.peek 5}`"
  end
end

#pushback(n) ⇒ Object 



185
186
187
 
# File 'opal/lib/opal/parser/lexer.rb', line 185

def pushback(n)
  @scanner.pos -= n
end

#read_escape ⇒ Object 



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
 
# File 'opal/lib/opal/parser/lexer.rb', line 238

def read_escape
  if scan(/\\/)
    "\\"
  elsif scan(/n/)
    "\n"
  elsif scan(/t/)
    "\t"
  elsif scan(/r/)
    "\r"
  elsif scan(/f/)
    "\f"
  elsif scan(/v/)
    "\v"
  elsif scan(/a/)
    "\a"
  elsif scan(/b/)
    "\b"
  elsif scan(/e/)
    "\e"
  elsif scan(/s/)
    " "
  elsif scan(/[0-7]{1,3}/)
    (matched.to_i(8) % 0x100).chr
  elsif scan(/x([0-9a-fA-F]{1,2})/)
    scanner[1].to_i(16).chr
  elsif scan(/u([0-9a-zA-Z]{1,4})/)
    scanner[1].to_i(16).chr(Encoding::UTF_8)
  else
    # escaped char doesnt need escaping, so just return it
    scan(/./)
  end
end

#scan(regexp) ⇒ Object 



163
164
165
166
167
168
169
170
 
# File 'opal/lib/opal/parser/lexer.rb', line 163

def scan(regexp)
  if result = @scanner.scan(regexp)
    @column += result.length
    @yylval += @scanner.matched
  end

  result
end

#set_arg_state ⇒ Object 



159
160
161
 
# File 'opal/lib/opal/parser/lexer.rb', line 159

def set_arg_state
  @lex_state = after_operator? ? :expr_arg : :expr_beg
end

#skip(regexp) ⇒ Object 



172
173
174
175
176
177
178
179
 
# File 'opal/lib/opal/parser/lexer.rb', line 172

def skip(regexp)
  if result = @scanner.scan(regexp)
    @column += result.length
    @tok_column = @column
  end

  result
end

#space? ⇒ Boolean

Returns:

  • (Boolean) 


155
156
157
 
# File 'opal/lib/opal/parser/lexer.rb', line 155

def space?
  @scanner.check(/\s/)
end

#spcarg? ⇒ Boolean

Returns:

  • (Boolean) 


151
152
153
 
# File 'opal/lib/opal/parser/lexer.rb', line 151

def spcarg?
  arg? and @space_seen and !space?
end

#yylex ⇒ Object

Does the heavy lifting for next_token.



635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
 
# File 'opal/lib/opal/parser/lexer.rb', line 635

def yylex
  @yylval = ''
  @space_seen = false
  cmd_start = false
  c = ''

  if self.strterm
    if self.strterm[:type] == :heredoc
      token = here_document(self.strterm)
    else
      token = parse_string
    end

    if token == :tSTRING_END or token == :tREGEXP_END
      self.strterm = nil
      @lex_state = :expr_end
    end

    return token
  end

  while true
    if skip(/\ |\t|\r/)
      @space_seen = true
      next

    elsif skip(/(\n|#)/)
      c = scanner.matched
      if c == '#'
        skip(/(.*)/)
      else
        self.line += 1
      end

      skip(/(\n+)/)

      if scanner.matched
        self.line += scanner.matched.length
      end

      next if [:expr_beg, :expr_dot].include? @lex_state

      if skip(/([\ \t\r\f\v]*)\./)
        @space_seen = true unless scanner[1].empty?
        pushback(1)

        next unless check(/\.\./)
      end

      cmd_start = true
      @lex_state = :expr_beg
      self.yylval = '\\n'
      return :tNL

    elsif scan(/\;/)
      @lex_state = :expr_beg
      return :tSEMI

    elsif check(/\*/)
      if scan(/\*\*\=/)
        @lex_state = :expr_beg
        return new_op_asgn('**')
      elsif scan(/\*\*/)
        self.set_arg_state
        return :tPOW
      elsif scan(/\*\=/)
        @lex_state = :expr_beg
        return new_op_asgn('*')
      else
        scan(/\*/)

        if after_operator?
          @lex_state = :expr_arg
          return :tSTAR2
        elsif @space_seen && check(/\S/)
          @lex_state = :expr_beg
          return :tSTAR
        elsif [:expr_beg, :expr_mid].include? @lex_state
          @lex_state = :expr_beg
          return :tSTAR
        else
          @lex_state = :expr_beg
          return :tSTAR2
        end
      end

    elsif scan(/\!/)
      if after_operator?
        @lex_state = :expr_arg
        if scan(/@/)
          return :tBANG, '!'
        end
      else
        @lex_state = :expr_beg
      end

      if scan(/\=/)
        return :tNEQ
      elsif scan(/\~/)
        return :tNMATCH
      end

      return :tBANG

    elsif scan(/\=/)
      if @lex_state == :expr_beg and !@space_seen
        if scan(/begin/) and space?
          scan(/(.*)/) # end of line
          line_count = 0

          while true
            if scanner.eos?
              raise "embedded document meets end of file"
            end

            if scan(/\=end/) and space?
              @line += line_count
              return yylex
            end

            if scan(/\n/)
              line_count += 1
              next
            end

            scan(/(.*)/)
          end
        end
      end

      self.set_arg_state

      if scan(/\=/)
        if scan(/\=/)
          return :tEQQ
        end

        return :tEQ
      end

      if scan(/\~/)
        return :tMATCH
      elsif scan(/\>/)
        return :tASSOC
      end

      return :tEQL

    elsif scan(/\"/)
      self.strterm = new_strterm(STR_DQUOTE, '"', "\0")
      return :tSTRING_BEG

    elsif scan(/\'/)
      self.strterm = new_strterm(STR_SQUOTE, "'", "\0")
      return :tSTRING_BEG

    elsif scan(/\`/)
      self.strterm = new_strterm(STR_XQUOTE, "`", "\0")
      return :tXSTRING_BEG

    elsif scan(/\&/)
      if scan(/\&/)
        @lex_state = :expr_beg

        if scan(/\=/)
          return new_op_asgn('&&')
        end

        return :tANDOP

      elsif scan(/\=/)
        @lex_state = :expr_beg
        return new_op_asgn('&')
      end

      if spcarg?
        #puts "warning: `&' interpreted as argument prefix"
        result = :tAMPER
      elsif beg?
        result = :tAMPER
      else
        #puts "warn_balanced: & argument prefix"
        result = :tAMPER2
      end

      self.set_arg_state
      return result

    elsif scan(/\|/)
      if scan(/\|/)
        @lex_state = :expr_beg
        if scan(/\=/)
          return new_op_asgn('||')
        end

        return :tOROP

      elsif scan(/\=/)
        return new_op_asgn('|')
      end

      self.set_arg_state
      return :tPIPE

    elsif scan(/\%[QqWwixrs]/)
      str_type = scanner.matched[1, 1]
      paren = term = scan(/./)

      case term
      when '(' then term = ')'
      when '[' then term = ']'
      when '{' then term = '}'
      when '<' then term = '>'
      else paren = "\0"
      end

      token, func = case str_type
                    when 'Q'
                      [:tSTRING_BEG, STR_DQUOTE]
                    when 'q'
                      [:tSTRING_BEG, STR_SQUOTE]
                    when 'W'
                      skip(/\s*/)
                      [:tWORDS_BEG, STR_DWORD]
                    when 'w', 'i'
                      skip(/\s*/)
                      [:tAWORDS_BEG, STR_SWORD]
                    when 'x'
                      [:tXSTRING_BEG, STR_XQUOTE]
                    when 'r'
                      [:tREGEXP_BEG, STR_REGEXP]
                    when 's'
                      [:tSTRING_BEG, STR_SQUOTE]
                    end

      self.strterm = new_strterm2(func, term, paren)
      return token

    elsif scan(/\//)
      if beg?
        self.strterm = new_strterm(STR_REGEXP, '/', '/')
        return :tREGEXP_BEG
      elsif scan(/\=/)
        @lex_state = :expr_beg
        return new_op_asgn('/')
      end

      if arg?
        if !check(/\s/) && @space_seen
          self.strterm = new_strterm(STR_REGEXP, '/', '/')
          return :tREGEXP_BEG
        end
      end

      if after_operator?
        @lex_state = :expr_arg
      else
        @lex_state = :expr_beg
      end

      return :tDIVIDE

    elsif scan(/\%/)
      if scan(/\=/)
        @lex_state = :expr_beg
        return new_op_asgn('%')
      elsif check(/[^\s]/)
        if @lex_state == :expr_beg or (@lex_state == :expr_arg && @space_seen)
          start_word  = scan(/./)
          end_word    = { '(' => ')', '[' => ']', '{' => '}' }[start_word] || start_word
          self.strterm = new_strterm2(STR_DQUOTE, end_word, start_word)
          return :tSTRING_BEG
        end
      end

      self.set_arg_state

      return :tPERCENT

    elsif scan(/\\/)
      if scan(/\r?\n/)
        @space_seen = true
        next
      end

      raise SyntaxError, "backslash must appear before newline :#{@file}:#{@line}"

    elsif scan(/\(/)
      result = scanner.matched
      if beg?
        result = :tLPAREN
      elsif @space_seen && arg?
        result = :tLPAREN_ARG
      else
        result = :tLPAREN2
      end

      @lex_state = :expr_beg
      cond_push 0
      cmdarg_push 0

      return result

    elsif scan(/\)/)
      cond_lexpop
      cmdarg_lexpop
      @lex_state = :expr_end
      return :tRPAREN

    elsif scan(/\[/)
      result = scanner.matched

      if after_operator?
        @lex_state = :expr_arg
        if scan(/\]=/)
          return :tASET
        elsif scan(/\]/)
          return :tAREF
        else
          raise "Unexpected '[' token"
        end
      elsif beg?
        result = :tLBRACK
      elsif arg? && @space_seen
        result =  :tLBRACK
      else
        result = :tLBRACK2
      end

      @lex_state = :expr_beg
      cond_push 0
      cmdarg_push 0
      return result

    elsif scan(/\]/)
      cond_lexpop
      cmdarg_lexpop
      @lex_state = :expr_end
      return :tRBRACK

    elsif scan(/\}/)
      cond_lexpop
      cmdarg_lexpop
      @lex_state = :expr_end

      return :tRCURLY

    elsif scan(/\.\.\./)
      @lex_state = :expr_beg
      return :tDOT3

    elsif scan(/\.\./)
      @lex_state = :expr_beg
      return :tDOT2

    elsif scan(/\./)
      @lex_state = :expr_dot unless @lex_state == :expr_fname
      return :tDOT

    elsif scan(/\:\:/)
      if beg?
        @lex_state = :expr_beg
        return :tCOLON3
      elsif spcarg?
        @lex_state = :expr_beg
        return :tCOLON3
      end

      @lex_state = :expr_dot
      return :tCOLON2

    elsif scan(/\:/)
      if end? || check(/\s/)
        unless check(/\w/)
          @lex_state = :expr_beg
          return :tCOLON
        end

        @lex_state = :expr_fname
        return :tSYMBEG
      end

      if scan(/\'/)
        self.strterm = new_strterm(STR_SSYM, "'", "\0")
      elsif scan(/\"/)
        self.strterm = new_strterm(STR_DSYM, '"', "\0")
      end

      @lex_state = :expr_fname
      return :tSYMBEG

    elsif scan(/\^\=/)
      @lex_state = :expr_beg
      return new_op_asgn('^')

    elsif scan(/\^/)
      self.set_arg_state
      return :tCARET

    elsif check(/\</)
      if scan(/\<\<\=/)
        @lex_state = :expr_beg
        return new_op_asgn('<<')

      elsif scan(/\<\</)
        if after_operator?
          @lex_state = :expr_arg
          return :tLSHFT
        elsif !after_operator? && !end? && (!arg? || @space_seen)
          if token = heredoc_identifier
            return token
          end

          @lex_state = :expr_beg
          return :tLSHFT
        end
        @lex_state = :expr_beg
        return :tLSHFT
      elsif scan(/\<\=\>/)
        if after_operator?
          @lex_state = :expr_arg
        else
          if @lex_state == :expr_class
            cmd_start = true
          end

          @lex_state = :expr_beg
        end

        return :tCMP
      elsif scan(/\<\=/)
        self.set_arg_state
        return :tLEQ

      elsif scan(/\</)
        self.set_arg_state
        return :tLT
      end

    elsif check(/\>/)
      if scan(/\>\>\=/)
        return new_op_asgn('>>')

      elsif scan(/\>\>/)
        self.set_arg_state
        return :tRSHFT

      elsif scan(/\>\=/)
        self.set_arg_state
        return :tGEQ

      elsif scan(/\>/)
        self.set_arg_state
        return :tGT
      end

    elsif scan(/->/)
      # FIXME: # should be :expr_arg, but '(' breaks it...
      @lex_state = :expr_end
      @start_of_lambda = true
      return :tLAMBDA

    elsif scan(/[+-]/)
      matched = scanner.matched
      sign, utype = if matched == '+'
                      [:tPLUS, :tUPLUS]
                    else
                      [:tMINUS, :tUMINUS]
                    end

      if beg?
        @lex_state = :expr_mid
        self.yylval = matched
        if scanner.peek(1) =~ /\d/ and
          return utype == :tUMINUS ? '-@NUM' : '+@NUM'
        else
          return utype
        end
      elsif after_operator?
        @lex_state = :expr_arg
        if scan(/@/)
          self.yylval = matched + '@'
          return :tIDENTIFIER
        end

        self.yylval = matched
        return sign
      end

      if scan(/\=/)
        @lex_state = :expr_beg
        return new_op_asgn(matched)
      end

      if spcarg?
        @lex_state = :expr_mid
        self.yylval = matched
        return utype
      end

      @lex_state = :expr_beg
      self.yylval = matched
      return sign

    elsif scan(/\?/)
      if end?
        @lex_state = :expr_beg
        return :tEH
      end

      if check(/\ |\t|\r|\s/)
        @lex_state = :expr_beg
        return :tEH
      elsif scan(/\\/)
        @lex_state = :expr_end
        self.yylval = self.read_escape
        return :tSTRING
      end

      @lex_state = :expr_end
      self.yylval = scan(/./)
      return :tSTRING

    elsif scan(/\~/)
      self.set_arg_state
      return :tTILDE

    elsif check(/\$/)
      if scan(/\$([1-9]\d*)/)
        @lex_state = :expr_end
        self.yylval = scanner.matched.sub('$', '')
        return :tNTH_REF

      elsif scan(/(\$_)(\w+)/)
        @lex_state = :expr_end
        return :tGVAR

      elsif scan(/\$[\+\'\`\&!@\"~*$?\/\\:;=.,<>_]/)
        @lex_state = :expr_end
        return :tGVAR
      elsif scan(/\$\w+/)
        @lex_state = :expr_end
        return :tGVAR
      else
        raise "Bad gvar name: #{scanner.peek(5).inspect}"
      end

    elsif scan(/\$\w+/)
      @lex_state = :expr_end
      return :tGVAR

    elsif scan(/\@\@\w*/)
      @lex_state = :expr_end
      return :tCVAR

    elsif scan(/\@\w*/)
      @lex_state = :expr_end
      return :tIVAR

    elsif scan(/\,/)
      @lex_state = :expr_beg
      return :tCOMMA

    elsif scan(/\{/)
      if @start_of_lambda
        @start_of_lambda = false
        @lex_state = :expr_beg
        return :tLAMBEG

      elsif arg? or @lex_state == :expr_end
        result = :tLCURLY
      elsif @lex_state == :expr_endarg
        result = :LBRACE_ARG
      else
        result = :tLBRACE
      end

      @lex_state = :expr_beg
      cond_push 0
      cmdarg_push 0
      return result

    elsif scanner.bol? and skip(/\__END__(\n|$)/)
      while true
        if scanner.eos?
          @eof_content = self.yylval
          return false
        end

        scan(/(.*)/)
        scan(/\n/)
      end

    elsif check(/[0-9]/)
      return process_numeric

    elsif scan(/(\w)+[\?\!]?/)
      return process_identifier scanner.matched, cmd_start
    end

    if scanner.eos?
      if @scanner_stack.size == 1 # our main scanner, we cant pop this
        self.yylval = false
        return false
      else # we were probably parsing a heredoc, so pop that parser and continue
        @scanner_stack.pop
        @scanner = @scanner_stack.last
        return yylex
      end
    end

    raise "Unexpected content in parsing stream `#{scanner.peek 5}` :#{@file}:#{@line}"
  end
end