Class: LL::Lexer

Inherits:
Object
  • Object
show all
Defined in:
lib/ll/lexer.rb

Overview

Ragel lexer for LL grammar files.

Class Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(data, file = SourceLine::DEFAULT_FILE) ⇒ Lexer

Returns a new instance of Lexer.

Parameters:

  • data (String) —

    The data to lex.

  • file (String) (defaults to: SourceLine::DEFAULT_FILE) —

    The name of the input file.



202
203
204
205
206
207
 
# File 'lib/ll/lexer.rb', line 202

def initialize(data, file = SourceLine::DEFAULT_FILE)
  @data = data
  @file = file

  reset
end

Class Attribute Details

._ll_lexer_eof_trans ⇒ Object

Returns the value of attribute _ll_lexer_eof_trans.



161
162
163
 
# File 'lib/ll/lexer.rb', line 161

def _ll_lexer_eof_trans
  @_ll_lexer_eof_trans
end

._ll_lexer_from_state_actions ⇒ Object

Returns the value of attribute _ll_lexer_from_state_actions.



150
151
152
 
# File 'lib/ll/lexer.rb', line 150

def _ll_lexer_from_state_actions
  @_ll_lexer_from_state_actions
end

._ll_lexer_index_offsets ⇒ Object

Returns the value of attribute _ll_lexer_index_offsets.



41
42
43
 
# File 'lib/ll/lexer.rb', line 41

def _ll_lexer_index_offsets
  @_ll_lexer_index_offsets
end

._ll_lexer_indicies ⇒ Object

Returns the value of attribute _ll_lexer_indicies.



52
53
54
 
# File 'lib/ll/lexer.rb', line 52

def _ll_lexer_indicies
  @_ll_lexer_indicies
end

._ll_lexer_key_spans ⇒ Object

Returns the value of attribute _ll_lexer_key_spans.



30
31
32
 
# File 'lib/ll/lexer.rb', line 30

def _ll_lexer_key_spans
  @_ll_lexer_key_spans
end

._ll_lexer_to_state_actions ⇒ Object

Returns the value of attribute _ll_lexer_to_state_actions.



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

def _ll_lexer_to_state_actions
  @_ll_lexer_to_state_actions
end

._ll_lexer_trans_actions ⇒ Object

Returns the value of attribute _ll_lexer_trans_actions.



126
127
128
 
# File 'lib/ll/lexer.rb', line 126

def _ll_lexer_trans_actions
  @_ll_lexer_trans_actions
end

._ll_lexer_trans_keys ⇒ Object

Returns the value of attribute _ll_lexer_trans_keys.



13
14
15
 
# File 'lib/ll/lexer.rb', line 13

def _ll_lexer_trans_keys
  @_ll_lexer_trans_keys
end

._ll_lexer_trans_targs ⇒ Object

Returns the value of attribute _ll_lexer_trans_targs.



113
114
115
 
# File 'lib/ll/lexer.rb', line 113

def _ll_lexer_trans_targs
  @_ll_lexer_trans_targs
end

.ll_lexer_en_main ⇒ Object

Returns the value of attribute ll_lexer_en_main.



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

def ll_lexer_en_main
  @ll_lexer_en_main
end

.ll_lexer_en_ruby_body ⇒ Object

Returns the value of attribute ll_lexer_en_ruby_body.



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

def ll_lexer_en_ruby_body
  @ll_lexer_en_ruby_body
end

.ll_lexer_error ⇒ Object

Returns the value of attribute ll_lexer_error.



180
181
182
 
# File 'lib/ll/lexer.rb', line 180

def ll_lexer_error
  @ll_lexer_error
end

.ll_lexer_first_final ⇒ Object

Returns the value of attribute ll_lexer_first_final.



176
177
178
 
# File 'lib/ll/lexer.rb', line 176

def ll_lexer_first_final
  @ll_lexer_first_final
end

.ll_lexer_start ⇒ Object

Returns the value of attribute ll_lexer_start.



172
173
174
 
# File 'lib/ll/lexer.rb', line 172

def ll_lexer_start
  @ll_lexer_start
end

Instance Method Details

#add_token(type, value, line = @line) {|token| ... } ⇒ Object (private)

Yields a new token to the supplied block.

Parameters:

  • type (Symbol) —

    The token type.

  • value (String) —

    The token value.

  • line (Fixnum) (defaults to: @line)

Yield Parameters:



592
593
594
595
596
597
 
# File 'lib/ll/lexer.rb', line 592

def add_token(type, value, line = @line)
  source_line = SourceLine.new(@data, line, @column, @file)
  @column    += value.length

  @block.call(Token.new(type, value, source_line))
end

#advance(&block) ⇒ Object

Advances through the input and generates the corresponding tokens. Each token is yielded to the supplied block.

See Also:

  • LL::Lexer.[[#add_token]


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
328
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
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
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
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
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
544
545
546
547
548
549
550
 
# File 'lib/ll/lexer.rb', line 240

def advance(&block)
  @block = block

  data = @data # saves ivar lookups while lexing.
  ts   = nil
  te   = nil
  cs   = self.class.ll_lexer_start
  act  = 0
  eof  = @data.bytesize
  p    = 0
  pe   = eof

  mark        = 0
  brace_count = 0
  start_line  = 0

  _ll_lexer_eof_trans          = self.class.send(:_ll_lexer_eof_trans)
  _ll_lexer_from_state_actions = self.class.send(:_ll_lexer_from_state_actions)
  _ll_lexer_index_offsets      = self.class.send(:_ll_lexer_index_offsets)
  _ll_lexer_indicies           = self.class.send(:_ll_lexer_indicies)
  _ll_lexer_key_spans          = self.class.send(:_ll_lexer_key_spans)
  _ll_lexer_to_state_actions   = self.class.send(:_ll_lexer_to_state_actions)
  _ll_lexer_trans_actions      = self.class.send(:_ll_lexer_trans_actions)
  _ll_lexer_trans_keys         = self.class.send(:_ll_lexer_trans_keys)
  _ll_lexer_trans_targs        = self.class.send(:_ll_lexer_trans_targs)

  
# line 263 "lib/ll/lexer.rb"
begin
  testEof = false
  _slen, _trans, _keys, _inds, _acts, _nacts = nil
  _goto_level = 0
  _resume = 10
  _eof_trans = 15
  _again = 20
  _test_eof = 30
  _out = 40
  while true
  if _goto_level <= 0
  if p == pe
    _goto_level = _test_eof
    next
  end
  if cs == 0
    _goto_level = _out
    next
  end
  end
  if _goto_level <= _resume
  case _ll_lexer_from_state_actions[cs] 
  when 6 then
# line 1 "NONE"
    begin
ts = p
    end
# line 291 "lib/ll/lexer.rb"
  end
  _keys = cs << 1
  _inds = _ll_lexer_index_offsets[cs]
  _slen = _ll_lexer_key_spans[cs]
  _wide = ( (data.getbyte(p) || 0))
  _trans = if (   _slen > 0 && 
      _ll_lexer_trans_keys[_keys] <= _wide && 
      _wide <= _ll_lexer_trans_keys[_keys + 1] 
  ) then
      _ll_lexer_indicies[ _inds + _wide - _ll_lexer_trans_keys[_keys] ] 
     else 
      _ll_lexer_indicies[ _inds + _slen ]
     end
  end
  if _goto_level <= _eof_trans
  cs = _ll_lexer_trans_targs[_trans]
  if _ll_lexer_trans_actions[_trans] != 0
  case _ll_lexer_trans_actions[_trans]
  when 25 then
# line 188 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  brace_count += 1  end
    end
  when 26 then
# line 190 "lib/ll/lexer.rl"
    begin
te = p+1
 begin 
      if brace_count == 1
        emit(:T_RUBY, mark, ts, start_line)

        mark        = 0
        brace_count = 0
        start_line  = 0

        advance_column

        cs = 22;
      else
        brace_count -= 1
      end
     end
    end
  when 23 then
# line 206 "lib/ll/lexer.rl"
    begin
te = p+1
    end
  when 3 then
# line 215 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_NAME, ts, te)  end
    end
  when 4 then
# line 216 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_TERMINALS, ts, te)  end
    end
  when 2 then
# line 217 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_INNER, ts, te)  end
    end
  when 1 then
# line 218 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_HEADER, ts, te)  end
    end
  when 16 then
# line 220 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_EQUALS, ts, te)  end
    end
  when 14 then
# line 221 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_COLON, ts, te)  end
    end
  when 15 then
# line 222 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_SEMICOLON, ts, te)  end
    end
  when 20 then
# line 223 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_PIPE, ts, te)  end
    end
  when 13 then
# line 225 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_PLUS, ts, te)  end
    end
  when 12 then
# line 226 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_STAR, ts, te)  end
    end
  when 17 then
# line 227 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_QUESTION, ts, te)  end
    end
  when 10 then
# line 228 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_LPAREN, ts, te)  end
    end
  when 11 then
# line 229 "lib/ll/lexer.rl"
    begin
te = p+1
 begin  emit(:T_RPAREN, ts, te)  end
    end
  when 19 then
# line 231 "lib/ll/lexer.rl"
    begin
te = p+1
 begin 
      mark        = ts + 1
      brace_count = 1
      start_line  = @line

      advance_column

      cs = 25;
     end
    end
  when 22 then
# line 213 "lib/ll/lexer.rl"
    begin
te = p
p = p - 1;    end
  when 21 then
# line 1 "NONE"
    begin
  case act
  when 16 then
  begin begin p = ((te))-1; end
 emit(:T_EPSILON, ts, te) end
  when 23 then
  begin begin p = ((te))-1; end

    emit(:T_IDENT, ts, te)
  end
end 
      end
  when 24 then
# line 148 "lib/ll/lexer.rl"
    begin

    advance_line

    @column = 1
      end
# line 186 "lib/ll/lexer.rl"
    begin
te = p+1
    end
  when 9 then
# line 148 "lib/ll/lexer.rl"
    begin

    advance_line

    @column = 1
      end
# line 210 "lib/ll/lexer.rl"
    begin
te = p+1
    end
  when 8 then
# line 154 "lib/ll/lexer.rl"
    begin

    advance_column
      end
# line 211 "lib/ll/lexer.rl"
    begin
te = p+1
    end
  when 18 then
# line 1 "NONE"
    begin
te = p+1
    end
# line 224 "lib/ll/lexer.rl"
    begin
act = 16;   end
  when 7 then
# line 1 "NONE"
    begin
te = p+1
    end
# line 168 "lib/ll/lexer.rl"
    begin
act = 23;   end
# line 502 "lib/ll/lexer.rb"
  end
  end
  end
  if _goto_level <= _again
  case _ll_lexer_to_state_actions[cs] 
  when 5 then
# line 1 "NONE"
    begin
ts = nil;   end
# line 512 "lib/ll/lexer.rb"
  end

  if cs == 0
    _goto_level = _out
    next
  end
  p += 1
  if p != pe
    _goto_level = _resume
    next
  end
  end
  if _goto_level <= _test_eof
  if p == eof
  if _ll_lexer_eof_trans[cs] > 0
    _trans = _ll_lexer_eof_trans[cs] - 1;
    _goto_level = _eof_trans
    next;
  end
  end

  end
  if _goto_level <= _out
    break
  end
end
  end

# line 81 "lib/ll/lexer.rl"

  # % fix highlight
ensure
  reset
end

#advance_column ⇒ Object (private) 



603
604
605
 
# File 'lib/ll/lexer.rb', line 603

def advance_column
  @column += 1
end

#advance_line ⇒ Object (private) 



599
600
601
 
# File 'lib/ll/lexer.rb', line 599

def advance_line
  @line += 1
end

#emit(type, start, stop, line = @line) ⇒ Object (private)

Emits a token of which the value is based on the supplied start/stop position.

Parameters:

  • type (Symbol) —

    The token type.

  • start (Fixnum)
  • stop (Fixnum)
  • line (Fixnum) (defaults to: @line)

See Also:

  • LL::Lexer.[[#text]
  • LL::Lexer.[[#add_token]


566
567
568
569
570
 
# File 'lib/ll/lexer.rb', line 566

def emit(type, start, stop, line = @line)
  value = slice_input(start, stop)

  add_token(type, value, line)
end

#lex ⇒ Array

Gathers all the tokens for the input and returns them as an Array.

Returns:

  • (Array)

See Also:

  • LL::Lexer.[[#advance]


215
216
217
218
219
220
221
222
223
 
# File 'lib/ll/lexer.rb', line 215

def lex
  tokens = []

  advance do |token|
    tokens << token
  end

  return tokens
end

#reset ⇒ Object

Resets the internal state of the lexer.



228
229
230
231
232
 
# File 'lib/ll/lexer.rb', line 228

def reset
  @block  = nil
  @line   = 1
  @column = 1
end

#slice_input(start, stop) ⇒ String (private)

Returns the text between the specified start and stop position.

Parameters:

  • start (Fixnum)
  • stop (Fixnum)

Returns:

  • (String) 


579
580
581
 
# File 'lib/ll/lexer.rb', line 579

def slice_input(start, stop)
  return @data.byteslice(start, stop - start)
end