Class: RubyLexer

Inherits:
Object show all
Defined in:
lib/ruby_parser/ruby_lexer.rb

Constant Summary collapse

ESC_RE =
/\\([0-7]{1,3}|x[0-9a-fA-F]{1,2}|M-[^\\]|(C-|c)[^\\]|[^0-7xMCc])/
EOF =
:eof_haha!
STR_FUNC_BORING =

ruby constants for strings (should this be moved somewhere else?)

0x00
STR_FUNC_ESCAPE =

TODO: remove and replace with REGEXP

0x01
STR_FUNC_EXPAND =
0x02
STR_FUNC_REGEXP =
0x04
STR_FUNC_AWORDS =
0x08
STR_FUNC_SYMBOL =
0x10
STR_FUNC_INDENT =

<<-HEREDOC

0x20
STR_SQUOTE =
STR_FUNC_BORING
STR_DQUOTE =
STR_FUNC_BORING | STR_FUNC_EXPAND
STR_XQUOTE =
STR_FUNC_BORING | STR_FUNC_EXPAND
STR_REGEXP =
STR_FUNC_REGEXP | STR_FUNC_ESCAPE | STR_FUNC_EXPAND
STR_SSYM =
STR_FUNC_SYMBOL
STR_DSYM =
STR_FUNC_SYMBOL | STR_FUNC_EXPAND
TOKENS =
{
  "!"   => :tBANG,
  "!="  => :tNEQ,
  "!~"  => :tNMATCH,
  ","   => :tCOMMA,
  ".."  => :tDOT2,
  "..." => :tDOT3,
  "="   => :tEQL,
  "=="  => :tEQ,
  "===" => :tEQQ,
  "=>"  => :tASSOC,
  "=~"  => :tMATCH,
  "->"  => :tLAMBDA,
}

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(v = 18) ⇒ RubyLexer

Returns a new instance of RubyLexer.



221
222
223
224
225
226
227
228
229
# File 'lib/ruby_parser/ruby_lexer.rb', line 221

def initialize v = 18
  self.version = v
  self.cond = RubyParser::StackState.new(:cond)
  self.cmdarg = RubyParser::StackState.new(:cmdarg)
  self.nest = 0
  @comments = []

  reset
end

Instance Attribute Details

#cmdargObject

Returns the value of attribute cmdarg.



3
4
5
# File 'lib/ruby_parser/ruby_lexer.rb', line 3

def cmdarg
  @cmdarg
end

#command_startObject

Returns the value of attribute command_start.



2
3
4
# File 'lib/ruby_parser/ruby_lexer.rb', line 2

def command_start
  @command_start
end

#condObject

Returns the value of attribute cond.



4
5
6
# File 'lib/ruby_parser/ruby_lexer.rb', line 4

def cond
  @cond
end

#lex_stateObject

Additional context surrounding tokens that both the lexer and grammar use.



17
18
19
# File 'lib/ruby_parser/ruby_lexer.rb', line 17

def lex_state
  @lex_state
end

#lex_strtermObject

Returns the value of attribute lex_strterm.



19
20
21
# File 'lib/ruby_parser/ruby_lexer.rb', line 19

def lex_strterm
  @lex_strterm
end

#linenoObject



243
244
245
# File 'lib/ruby_parser/ruby_lexer.rb', line 243

def lineno
  @lineno ||= src.lineno
end

#nestObject

Returns the value of attribute nest.



5
6
7
# File 'lib/ruby_parser/ruby_lexer.rb', line 5

def nest
  @nest
end

#parserObject

HACK for very end of lexer… sigh



21
22
23
# File 'lib/ruby_parser/ruby_lexer.rb', line 21

def parser
  @parser
end

#srcObject

Stream of data that yylex examines.



24
25
26
# File 'lib/ruby_parser/ruby_lexer.rb', line 24

def src
  @src
end

#string_bufferObject

Returns the value of attribute string_buffer.



29
30
31
# File 'lib/ruby_parser/ruby_lexer.rb', line 29

def string_buffer
  @string_buffer
end

#tokenObject

Last token read via yylex.



27
28
29
# File 'lib/ruby_parser/ruby_lexer.rb', line 27

def token
  @token
end

#versionObject

What version of ruby to parse. 18 and 19 are the only valid values currently supported.



13
14
15
# File 'lib/ruby_parser/ruby_lexer.rb', line 13

def version
  @version
end

#warningsObject

What handles warnings



35
36
37
# File 'lib/ruby_parser/ruby_lexer.rb', line 35

def warnings
  @warnings
end

#yacc_valueObject

Value of last token which had a value associated with it.



32
33
34
# File 'lib/ruby_parser/ruby_lexer.rb', line 32

def yacc_value
  @yacc_value
end

Instance Method Details

#advanceObject

How the parser advances to the next token.

Returns:

  • true if not at end of file (EOF).



74
75
76
77
78
79
80
81
# File 'lib/ruby_parser/ruby_lexer.rb', line 74

def advance
  r = yylex
  self.token = r

  raise "yylex returned nil" unless r

  return RubyLexer::EOF != r
end

#arg_ambiguousObject



83
84
85
# File 'lib/ruby_parser/ruby_lexer.rb', line 83

def arg_ambiguous
  self.warning("Ambiguous first argument. make sure.")
end

#commentsObject



87
88
89
90
91
# File 'lib/ruby_parser/ruby_lexer.rb', line 87

def comments
  c = @comments.join
  @comments.clear
  c
end

#expr_beg_push(val) ⇒ Object



93
94
95
96
97
98
# File 'lib/ruby_parser/ruby_lexer.rb', line 93

def expr_beg_push val
  cond.push false
  cmdarg.push false
  self.lex_state = :expr_beg
  self.yacc_value = val
end

#fix_arg_lex_stateObject



100
101
102
103
104
105
106
# File 'lib/ruby_parser/ruby_lexer.rb', line 100

def fix_arg_lex_state
  self.lex_state = if lex_state == :expr_fname || lex_state == :expr_dot
                     :expr_arg
                   else
                     :expr_beg
                   end
end

#heredoc(here) ⇒ Object

63 lines



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
# File 'lib/ruby_parser/ruby_lexer.rb', line 108

def heredoc here # 63 lines
  _, eos, func, last_line = here

  indent  = (func & STR_FUNC_INDENT) != 0
  expand  = (func & STR_FUNC_EXPAND) != 0
  eos_re  = indent ? /[ \t]*#{eos}(\r?\n|\z)/ : /#{eos}(\r?\n|\z)/
  err_msg = "can't match #{eos_re.inspect} anywhere in "

  rb_compile_error err_msg if
    src.eos?

  if src.beginning_of_line? && src.scan(eos_re) then
    src.unread_many last_line # TODO: figure out how to remove this
    self.yacc_value = eos
    return :tSTRING_END
  end

  self.string_buffer = []

  if expand then
    case
    when src.scan(/#[$@]/) then
      src.pos -= 1 # FIX omg stupid
      self.yacc_value = src.matched
      return :tSTRING_DVAR
    when src.scan(/#[{]/) then
      self.yacc_value = src.matched
      return :tSTRING_DBEG
    when src.scan(/#/) then
      string_buffer << '#'
    end

    until src.check(eos_re) do
      c = tokadd_string func, "\n", nil

      rb_compile_error err_msg if
        c == RubyLexer::EOF

      if c != "\n" then
        self.yacc_value = string_buffer.join.delete("\r")
        return :tSTRING_CONTENT
      else
        string_buffer << src.scan(/\n/)
      end

      rb_compile_error err_msg if
        src.eos?
    end
  else
    until src.check(eos_re) do
      string_buffer << src.scan(/.*(\n|\z)/)
      rb_compile_error err_msg if
        src.eos?
    end
  end

  self.lex_strterm = [:heredoc, eos, func, last_line]
  self.yacc_value = string_buffer.join.delete("\r")

  return :tSTRING_CONTENT
end

#heredoc_identifierObject

51 lines



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
# File 'lib/ruby_parser/ruby_lexer.rb', line 170

def heredoc_identifier # 51 lines
  term, func = nil, STR_FUNC_BORING
  self.string_buffer = []

  case
  when src.scan(/(-?)(['"`])(.*?)\2/) then
    term = src[2]
    unless src[1].empty? then
      func |= STR_FUNC_INDENT
    end
    func |= case term
            when "\'" then
              STR_SQUOTE
            when '"' then
              STR_DQUOTE
            else
              STR_XQUOTE
            end
    string_buffer << src[3]
  when src.scan(/-?(['"`])(?!\1*\Z)/) then
    rb_compile_error "unterminated here document identifier"
  when src.scan(/(-?)(\w+)/) then
    term = '"'
    func |= STR_DQUOTE
    unless src[1].empty? then
      func |= STR_FUNC_INDENT
    end
    string_buffer << src[2]
  else
    return nil
  end

  if src.scan(/.*\n/) then
    # TODO: think about storing off the char range instead
    line = src.matched
    src.extra_lines_added += 1
  else
    line = nil
  end

  self.lex_strterm = [:heredoc, string_buffer.join, func, line]

  if term == '`' then
    self.yacc_value = "`"
    return :tXSTRING_BEG
  else
    self.yacc_value = "\""
    return :tSTRING_BEG
  end
end

#int_with_base(base) ⇒ Object



231
232
233
234
235
# File 'lib/ruby_parser/ruby_lexer.rb', line 231

def int_with_base base
  rb_compile_error "Invalid numeric format" if src.matched =~ /__/
  self.yacc_value = src.matched.to_i(base)
  return :tINTEGER
end

#parse_numberObject

Parse a number from the input stream.

Parameters:

  • c

    The first character of the number.

Returns:

  • A int constant wich represents a token.



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
# File 'lib/ruby_parser/ruby_lexer.rb', line 253

def parse_number
  self.lex_state = :expr_end

  case
  when src.scan(/[+-]?0[xbd]\b/) then
    rb_compile_error "Invalid numeric format"
  when src.scan(/[+-]?0x[a-f0-9_]+/i) then
    int_with_base(16)
  when src.scan(/[+-]?0b[01_]+/) then
    int_with_base(2)
  when src.scan(/[+-]?0d[0-9_]+/) then
    int_with_base(10)
  when src.scan(/[+-]?0[Oo]?[0-7_]*[89]/) then
    rb_compile_error "Illegal octal digit."
  when src.scan(/[+-]?0[Oo]?[0-7_]+|0[Oo]/) then
    int_with_base(8)
  when src.scan(/[+-]?[\d_]+_(e|\.)/) then
    rb_compile_error "Trailing '_' in number."
  when src.scan(/[+-]?[\d_]+\.[\d_]+(e[+-]?[\d_]+)?\b|[+-]?[\d_]+e[+-]?[\d_]+\b/i) then
    number = src.matched
    if number =~ /__/ then
      rb_compile_error "Invalid numeric format"
    end
    self.yacc_value = number.to_f
    :tFLOAT
  when src.scan(/[+-]?0\b/) then
    int_with_base(10)
  when src.scan(/[+-]?[\d_]+\b/) then
    int_with_base(10)
  else
    rb_compile_error "Bad number format"
  end
end

#parse_quoteObject

58 lines



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
# File 'lib/ruby_parser/ruby_lexer.rb', line 287

def parse_quote # 58 lines
  beg, nnd, short_hand, c = nil, nil, false, nil

  if src.scan(/[a-z0-9]{1,2}/i) then # Long-hand (e.g. %Q{}).
    rb_compile_error "unknown type of %string" if src.matched_size == 2
    c, beg, short_hand = src.matched, src.getch, false
  else                               # Short-hand (e.g. %{, %., %!, etc)
    c, beg, short_hand = 'Q', src.getch, true
  end

  if src.eos? or c == RubyLexer::EOF or beg == RubyLexer::EOF then
    rb_compile_error "unterminated quoted string meets end of file"
  end

  # Figure nnd-char.  "\0" is special to indicate beg=nnd and that no nesting?
  nnd = { "(" => ")", "[" => "]", "{" => "}", "<" => ">" }[beg]
  nnd, beg = beg, "\0" if nnd.nil?

  token_type, self.yacc_value = nil, "%#{c}#{beg}"
  token_type, string_type = case c
                            when 'Q' then
                              ch = short_hand ? nnd : c + beg
                              self.yacc_value = "%#{ch}"
                              [:tSTRING_BEG,   STR_DQUOTE]
                            when 'q' then
                              [:tSTRING_BEG,   STR_SQUOTE]
                            when 'W' then
                              src.scan(/\s*/)
                              [:tWORDS_BEG,    STR_DQUOTE | STR_FUNC_AWORDS]
                            when 'w' then
                              src.scan(/\s*/)
                              [:tAWORDS_BEG,   STR_SQUOTE | STR_FUNC_AWORDS]
                            when 'x' then
                              [:tXSTRING_BEG,  STR_XQUOTE]
                            when 'r' then
                              [:tREGEXP_BEG,   STR_REGEXP]
                            when 's' then
                              self.lex_state  = :expr_fname
                              [:tSYMBEG,       STR_SSYM]
                            end

  rb_compile_error "Bad %string type. Expected [Qqwxr\W], found '#{c}'." if
    token_type.nil?

  self.lex_strterm = [:strterm, string_type, nnd, beg]

  return token_type
end

#parse_string(quote) ⇒ Object

65 lines



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
# File 'lib/ruby_parser/ruby_lexer.rb', line 336

def parse_string(quote) # 65 lines
  _, string_type, term, open = quote

  space = false # FIX: remove these
  func = string_type
  paren = open
  term_re = Regexp.escape term

  awords = (func & STR_FUNC_AWORDS) != 0
  regexp = (func & STR_FUNC_REGEXP) != 0
  expand = (func & STR_FUNC_EXPAND) != 0

  unless func then # FIX: impossible, prolly needs == 0
    self.lineno = nil
    return :tSTRING_END
  end

  space = true if awords and src.scan(/\s+/)

  if self.nest == 0 && src.scan(/#{term_re}/) then
    if awords then
      quote[1] = nil
      return :tSPACE
    elsif regexp then
      self.yacc_value = self.regx_options
      self.lineno = nil
      return :tREGEXP_END
    else
      self.yacc_value = term
      self.lineno = nil
      return :tSTRING_END
    end
  end

  if space then
    return :tSPACE
  end

  self.string_buffer = []

  if expand
    case
    when src.scan(/#(?=[$@])/) then
      return :tSTRING_DVAR
    when src.scan(/#[{]/) then
      return :tSTRING_DBEG
    when src.scan(/#/) then
      string_buffer << '#'
    end
  end

  if tokadd_string(func, term, paren) == RubyLexer::EOF then
    rb_compile_error "unterminated string meets end of file"
  end

  self.yacc_value = string_buffer.join

  return :tSTRING_CONTENT
end

#process_token(command_state) ⇒ Object



1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
# File 'lib/ruby_parser/ruby_lexer.rb', line 1229

def process_token(command_state)

  token << src.matched if token =~ /^\w/ && src.scan(/[\!\?](?!=)/)

  result = nil
  last_state = lex_state


  case token
  when /^\$/ then
    self.lex_state, result = :expr_end, :tGVAR
  when /^@@/ then
    self.lex_state, result = :expr_end, :tCVAR
  when /^@/ then
    self.lex_state, result = :expr_end, :tIVAR
  else
    if token =~ /[!?]$/ then
      result = :tFID
    else
      if lex_state == :expr_fname then
        # ident=, not =~ => == or followed by =>
        # TODO test lexing of a=>b vs a==>b
        if src.scan(/=(?:(?![~>=])|(?==>))/) then
          result = :tIDENTIFIER
          token << src.matched
        end
      end

      result ||= if token =~ /^[A-Z]/ then
                   :tCONSTANT
                 else
                   :tIDENTIFIER
                 end
    end

    if (lex_state == :expr_beg && !command_state) || lex_state == :expr_arg || lex_state == :expr_cmdarg
      colon = src.scan(/:/)

      if colon && src.peek(1) != ":"
        src.unscan
        self.lex_state = :expr_beg
        src.scan(/:/)
        self.yacc_value = [token, src.lineno]
        return :tLABEL
      end

      src.unscan if colon
    end

    unless lex_state == :expr_dot then
      # See if it is a reserved word.
      keyword = RubyParser::Keyword.keyword token

      if keyword then
        state           = lex_state
        self.lex_state  = keyword.state
        self.yacc_value = [token, src.lineno]

        if state == :expr_fname then
          self.yacc_value = keyword.name
          return keyword.id0
        end

        if keyword.id0 == :kDO then
          self.command_start = true
          return :kDO_COND  if cond.is_in_state
          return :kDO_BLOCK if cmdarg.is_in_state && state != :expr_cmdarg
          return :kDO_BLOCK if state == :expr_endarg
          if defined?(@hack_expects_lambda) && @hack_expects_lambda
            @hack_expects_lambda = false
            return :kDO_LAMBDA
          end
          return :kDO
        end

        return keyword.id0 if state == :expr_beg or state == :expr_value

        self.lex_state = :expr_beg if keyword.id0 != keyword.id1

        return keyword.id1
      end
    end

    if (lex_state == :expr_beg || lex_state == :expr_mid ||
        lex_state == :expr_dot || lex_state == :expr_arg ||
        lex_state == :expr_cmdarg) then
      if command_state then
        self.lex_state = :expr_cmdarg
      else
        self.lex_state = :expr_arg
      end
    else
      self.lex_state = :expr_end
    end
  end

  self.yacc_value = token


  self.lex_state = :expr_end if
    last_state != :expr_dot && self.parser.env[token.to_sym] == :lvar

  return result
end

#rb_compile_error(msg) ⇒ Object

Raises:

  • (SyntaxError)


396
397
398
399
# File 'lib/ruby_parser/ruby_lexer.rb', line 396

def rb_compile_error msg
  msg += ". near line #{self.lineno}: #{src.rest[/^.*/].inspect}"
  raise SyntaxError, msg
end

#read_escapeObject

51 lines



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/ruby_parser/ruby_lexer.rb', line 401

def read_escape # 51 lines
  case
  when src.scan(/\\/) then                  # Backslash
    '\\'
  when src.scan(/n/) then                   # newline
    "\n"
  when src.scan(/t/) then                   # horizontal tab
    "\t"
  when src.scan(/r/) then                   # carriage-return
    "\r"
  when src.scan(/f/) then                   # form-feed
    "\f"
  when src.scan(/v/) then                   # vertical tab
    "\13"
  when src.scan(/a/) then                   # alarm(bell)
    "\007"
  when src.scan(/e/) then                   # escape
    "\033"
  when src.scan(/b/) then                   # backspace
    "\010"
  when src.scan(/s/) then                   # space
    " "
  when src.scan(/[0-7]{1,3}/) then          # octal constant
    src.matched.to_i(8).chr
  when src.scan(/x([0-9a-fA-F]{1,2})/) then # hex constant
    src[1].to_i(16).chr
  when src.check(/M-\\[\\MCc]/) then
    src.scan(/M-\\/) # eat it
    c = self.read_escape
    c[0] = (c[0].ord | 0x80).chr
    c
  when src.scan(/M-(.)/) then
    c = src[1]
    c[0] = (c[0].ord | 0x80).chr
    c
  when src.check(/(C-|c)\\[\\MCc]/) then
    src.scan(/(C-|c)\\/) # eat it
    c = self.read_escape
    c[0] = (c[0].ord & 0x9f).chr
    c
  when src.scan(/C-\?|c\?/) then
    127.chr
  when src.scan(/(C-|c)(.)/) then
    c = src[2]
    c[0] = (c[0].ord & 0x9f).chr
    c
  when src.scan(/[McCx0-9]/) || src.eos? then
    rb_compile_error("Invalid escape character syntax")
  else
    src.getch
  end
end

#regx_optionsObject

15 lines



454
455
456
457
458
459
460
461
462
463
464
465
466
467
# File 'lib/ruby_parser/ruby_lexer.rb', line 454

def regx_options # 15 lines
  good, bad = [], []

  if src.scan(/[a-z]+/) then
    good, bad = src.matched.split(//).partition { |s| s =~ /^[ixmonesu]$/ }
  end

  unless bad.empty? then
    rb_compile_error("unknown regexp option%s - %s" %
                     [(bad.size > 1 ? "s" : ""), bad.join.inspect])
  end

  return good.join
end

#resetObject



469
470
471
472
473
474
475
476
477
# File 'lib/ruby_parser/ruby_lexer.rb', line 469

def reset
  self.command_start = true
  self.lex_strterm   = nil
  self.token         = nil
  self.yacc_value    = nil

  @src       = nil
  @lex_state = nil
end

#tokadd_escape(term) ⇒ Object

20 lines



484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
# File 'lib/ruby_parser/ruby_lexer.rb', line 484

def tokadd_escape term # 20 lines
  case
  when src.scan(/\\\n/) then
    # just ignore
  when src.scan(/\\([0-7]{1,3}|x[0-9a-fA-F]{1,2})/) then
    self.string_buffer << src.matched
  when src.scan(/\\([MC]-|c)(?=\\)/) then
    self.string_buffer << src.matched
    self.tokadd_escape term
  when src.scan(/\\([MC]-|c)(.)/) then
    self.string_buffer << src.matched
  when src.scan(/\\[McCx]/) then
    rb_compile_error "Invalid escape character syntax"
  when src.scan(/\\(.)/m) then
    self.string_buffer << src.matched
  else
    rb_compile_error "Invalid escape character syntax"
  end
end

#tokadd_string(func, term, paren) ⇒ Object

105 lines



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
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
# File 'lib/ruby_parser/ruby_lexer.rb', line 504

def tokadd_string(func, term, paren) # 105 lines
  awords = (func & STR_FUNC_AWORDS) != 0
  escape = (func & STR_FUNC_ESCAPE) != 0
  expand = (func & STR_FUNC_EXPAND) != 0
  regexp = (func & STR_FUNC_REGEXP) != 0
  symbol = (func & STR_FUNC_SYMBOL) != 0

  paren_re = paren.nil? ? nil : Regexp.new(Regexp.escape(paren))
  term_re  = Regexp.new(Regexp.escape(term))

  until src.eos? do
    c = nil
    handled = true
    case
    when self.nest == 0 && src.scan(term_re) then
      src.pos -= 1
      break
    when paren_re && src.scan(paren_re) then
      self.nest += 1
    when src.scan(term_re) then
      self.nest -= 1
    when awords && src.scan(/\s/) then
      src.pos -= 1
      break
    when expand && src.scan(/#(?=[\$\@\{])/) then
      src.pos -= 1
      break
    when expand && src.scan(/#(?!\n)/) then
      # do nothing
    when src.check(/\\/) then
      case
      when awords && src.scan(/\\\n/) then
        string_buffer << "\n"
        next
      when awords && src.scan(/\\\s/) then
        c = ' '
      when expand && src.scan(/\\\n/) then
        next
      when regexp && src.check(/\\/) then
        self.tokadd_escape term
        next
      when expand && src.scan(/\\/) then
        c = self.read_escape
      when src.scan(/\\\n/) then
        # do nothing
      when src.scan(/\\\\/) then
        string_buffer << '\\' if escape
        c = '\\'
      when src.scan(/\\/) then
        unless src.scan(term_re) || paren.nil? || src.scan(paren_re) then
          string_buffer << "\\"
        end
      else
        handled = false
      end
    else
      handled = false
    end # case

    unless handled then

      t = Regexp.escape term
      x = Regexp.escape(paren) if paren && paren != "\000"
      re = if awords then
             /[^#{t}#{x}\#\0\\\n\ ]+|./ # |. to pick up whatever
           else
             /[^#{t}#{x}\#\0\\]+|./
           end

      src.scan re
      c = src.matched

      rb_compile_error "symbol cannot contain '\\0'" if symbol && c =~ /\0/
    end # unless handled

    c ||= src.matched
    string_buffer << c
  end # until

  c ||= src.matched
  c = RubyLexer::EOF if src.eos?


  return c
end

#unescape(s) ⇒ Object



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
# File 'lib/ruby_parser/ruby_lexer.rb', line 590

def unescape s

  r = {
    "a"    => "\007",
    "b"    => "\010",
    "e"    => "\033",
    "f"    => "\f",
    "n"    => "\n",
    "r"    => "\r",
    "s"    => " ",
    "t"    => "\t",
    "v"    => "\13",
    "\\"   => '\\',
    "\n"   => "",
    "C-\?" => 127.chr,
    "c\?"  => 127.chr,
  }[s]

  return r if r

  case s
  when /^[0-7]{1,3}/ then
    $&.to_i(8).chr
  when /^x([0-9a-fA-F]{1,2})/ then
    $1.to_i(16).chr
  when /^M-(.)/ then
    ($1[0].ord | 0x80).chr
  when /^(C-|c)(.)/ then
    ($2[0].ord & 0x9f).chr
  when /^[McCx0-9]/ then
    rb_compile_error("Invalid escape character syntax")
  else
    s
  end
end

#warning(s) ⇒ Object



626
627
628
# File 'lib/ruby_parser/ruby_lexer.rb', line 626

def warning s
  # do nothing for now
end

#yylexObject

Returns the next token. Also sets yy_val is needed.

Returns:

  • Description of the Returned Value



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
# File 'lib/ruby_parser/ruby_lexer.rb', line 635

def yylex # 826 lines

  c = ''
  space_seen = false
  command_state = false
  src = self.src

  self.token = nil
  self.yacc_value = nil

  return yylex_string if lex_strterm

  command_state = self.command_start
  self.command_start = false

  last_state = lex_state

  loop do # START OF CASE
    if src.scan(/[\ \t\r\f\v]/) then # \s - \n + \v
      space_seen = true
      next
    elsif src.check(/[^a-zA-Z]/) then
      if src.scan(/\n|#/) then
        self.lineno = nil
        c = src.matched
        if c == '#' then
          src.pos -= 1

          while src.scan(/\s*#.*(\n+|\z)/) do
            @comments << src.matched.gsub(/^ +#/, '#').gsub(/^ +$/, '')
          end

          if src.eos? then
            return RubyLexer::EOF
          end
        end

        # Replace a string of newlines with a single one
        src.scan(/\n+/)

        if [:expr_beg, :expr_fname,
            :expr_dot, :expr_class].include? lex_state then
          next
        end

        self.command_start = true
        self.lex_state = :expr_beg
        return :tNL
      elsif src.scan(/[\]\)\}]/) then
        cond.lexpop
        cmdarg.lexpop
        self.lex_state = :expr_end
        self.yacc_value = src.matched
        result = {
          ")" => :tRPAREN,
          "]" => :tRBRACK,
          "}" => :tRCURLY
        }[src.matched]
        return result
      elsif src.scan(/\.\.\.?|,|![=~]?/) then
        self.lex_state = :expr_beg
        tok = self.yacc_value = src.matched
        return TOKENS[tok]
      elsif src.check(/\./) then
        if src.scan(/\.\d/) then
          rb_compile_error "no .<digit> floating literal anymore put 0 before dot"
        elsif src.scan(/\./) then
          self.lex_state = :expr_dot
          self.yacc_value = "."
          return :tDOT
        end
      elsif src.scan(/\(/) then
        result = :tLPAREN2

        if lex_state == :expr_beg || lex_state == :expr_mid then
          result = :tLPAREN
        elsif space_seen then
          if lex_state == :expr_cmdarg then
            result = :tLPAREN_ARG
          elsif lex_state == :expr_arg then
            warning("don't put space before argument parentheses")
            result = :tLPAREN2
          end
        end

        self.expr_beg_push "("

        return result
      elsif src.check(/\=/) then
        if src.scan(/\=\=\=|\=\=|\=~|\=>|\=(?!begin\b)/) then
          self.fix_arg_lex_state
          tok = self.yacc_value = src.matched
          return TOKENS[tok]
        elsif src.scan(/\=begin(?=\s)/) then
          # @comments << '=' << src.matched
          @comments << src.matched

          unless src.scan(/.*?\n=end( |\t|\f)*[^\n]*(\n|\z)/m) then
            @comments.clear
            rb_compile_error("embedded document meets end of file")
          end

          @comments << src.matched

          next
        else
          raise "you shouldn't be able to get here"
        end
      elsif src.scan(/\"(#{ESC_RE}|#(#{ESC_RE}|[^\{\#\@\$\"\\])|[^\"\\\#])*\"/o) then
        self.yacc_value = src.matched[1..-2].gsub(ESC_RE) { unescape $1 }
        self.lex_state = :expr_end
        return :tSTRING
      elsif src.scan(/\"/) then # FALLBACK
        self.lex_strterm = [:strterm, STR_DQUOTE, '"', "\0"] # TODO: question this
        self.yacc_value = "\""
        return :tSTRING_BEG
      elsif src.scan(/\@\@?\w*/) then
        self.token = src.matched

        rb_compile_error "`#{token}` is not allowed as a variable name" if
          token =~ /\@\d/

        return process_token(command_state)
      elsif src.scan(/\:\:/) then
        if (lex_state == :expr_beg ||
            lex_state == :expr_mid ||
            lex_state == :expr_class ||
            (lex_state.is_argument && space_seen)) then
          self.lex_state = :expr_beg
          self.yacc_value = "::"
          return :tCOLON3
        end

        self.lex_state = :expr_dot
        self.yacc_value = "::"
        return :tCOLON2
      elsif lex_state != :expr_end && lex_state != :expr_endarg && src.scan(/:([a-zA-Z_]\w*(?:[?!]|=(?!>))?)/) then
        self.yacc_value = src[1]
        self.lex_state = :expr_end
        return :tSYMBOL
      elsif src.scan(/\:/) then
        # ?: / then / when
        if (lex_state == :expr_end || lex_state == :expr_endarg||
            src.check(/\s/)) then
          self.lex_state = :expr_beg
          self.yacc_value = ":"
          return :tCOLON
        end

        case
        when src.scan(/\'/) then
          self.lex_strterm = [:strterm, STR_SSYM, src.matched, "\0"]
        when src.scan(/\"/) then
          self.lex_strterm = [:strterm, STR_DSYM, src.matched, "\0"]
        end

        self.lex_state = :expr_fname
        self.yacc_value = ":"
        return :tSYMBEG
      elsif src.check(/[0-9]/) then
        return parse_number
      elsif src.scan(/\[/) then
        result = src.matched

        if lex_state == :expr_fname || lex_state == :expr_dot then
          self.lex_state = :expr_arg
          case
          when src.scan(/\]\=/) then
            self.yacc_value = "[]="
            return :tASET
          when src.scan(/\]/) then
            self.yacc_value = "[]"
            return :tAREF
          else
            rb_compile_error "unexpected '['"
          end
        elsif lex_state == :expr_beg || lex_state == :expr_mid then
          result = :tLBRACK
        elsif lex_state.is_argument && space_seen then
          result = :tLBRACK
        end

        self.expr_beg_push "["

        return result
      elsif src.scan(/\'(\\.|[^\'])*\'/) then
        self.yacc_value = src.matched[1..-2].gsub(/\\\\/, "\\").gsub(/\\'/, "'")
        self.lex_state = :expr_end
        return :tSTRING
      elsif src.check(/\|/) then
        if src.scan(/\|\|\=/) then
          self.lex_state = :expr_beg
          self.yacc_value = "||"
          return :tOP_ASGN
        elsif src.scan(/\|\|/) then
          self.lex_state = :expr_beg
          self.yacc_value = "||"
          return :tOROP
        elsif src.scan(/\|\=/) then
          self.lex_state = :expr_beg
          self.yacc_value = "|"
          return :tOP_ASGN
        elsif src.scan(/\|/) then
          self.fix_arg_lex_state
          self.yacc_value = "|"
          return :tPIPE
        end
      elsif src.scan(/\{/) then
        if defined?(@hack_expects_lambda) && @hack_expects_lambda
          @hack_expects_lambda = false
          self.lex_state = :expr_beg
          return :tLAMBEG
        end

        result = if lex_state.is_argument || lex_state == :expr_end then
                   :tLCURLY      #  block (primary)
                 elsif lex_state == :expr_endarg then
                   :tLBRACE_ARG  #  block (expr)
                 else
                   :tLBRACE      #  hash
                 end

        self.expr_beg_push "{"
        self.command_start = true unless result == :tLBRACE

        return result
      elsif src.scan(/->/) then
        @hack_expects_lambda = true
        self.lex_state = :expr_arg
        return :tLAMBDA
      elsif src.scan(/[+-]/) then
        sign = src.matched
        utype, type = if sign == "+" then
                        [:tUPLUS, :tPLUS]
                      else
                        [:tUMINUS, :tMINUS]
                      end

        if lex_state == :expr_fname || lex_state == :expr_dot then
          self.lex_state = :expr_arg
          if src.scan(/@/) then
            self.yacc_value = "#{sign}@"
            return utype
          else
            self.yacc_value = sign
            return type
          end
        end

        if src.scan(/\=/) then
          self.lex_state = :expr_beg
          self.yacc_value = sign
          return :tOP_ASGN
        end

        if (lex_state == :expr_beg || lex_state == :expr_mid ||
            (lex_state.is_argument && space_seen && !src.check(/\s/))) then
          if lex_state.is_argument then
            arg_ambiguous
          end

          self.lex_state = :expr_beg
          self.yacc_value = sign

          if src.check(/\d/) then
            if utype == :tUPLUS then
              return self.parse_number
            else
              return :tUMINUS_NUM
            end
          end

          return utype
        end

        self.lex_state = :expr_beg
        self.yacc_value = sign
        return type
      elsif src.check(/\*/) then
        if src.scan(/\*\*=/) then
          self.lex_state = :expr_beg
          self.yacc_value = "**"
          return :tOP_ASGN
        elsif src.scan(/\*\*/) then
          self.yacc_value = "**"
          self.fix_arg_lex_state
          return :tPOW
        elsif src.scan(/\*\=/) then
          self.lex_state = :expr_beg
          self.yacc_value = "*"
          return :tOP_ASGN
        elsif src.scan(/\*/) then
          result = if lex_state.is_argument && space_seen && src.check(/\S/) then
                     warning("`*' interpreted as argument prefix")
                     :tSTAR
                   elsif lex_state == :expr_beg || lex_state == :expr_mid then
                     :tSTAR
                   else
                     :tSTAR2
                   end
          self.yacc_value = "*"
          self.fix_arg_lex_state

          return result
        end
      elsif src.check(/\</) then
        if src.scan(/\<\=\>/) then
          self.fix_arg_lex_state
          self.yacc_value = "<=>"
          return :tCMP
        elsif src.scan(/\<\=/) then
          self.fix_arg_lex_state
          self.yacc_value = "<="
          return :tLEQ
        elsif src.scan(/\<\<\=/) then
          self.fix_arg_lex_state
          self.lex_state = :expr_beg
          self.yacc_value = "\<\<"
          return :tOP_ASGN
        elsif src.scan(/\<\</) then
          if (! [:expr_end,    :expr_dot,
                 :expr_endarg, :expr_class].include?(lex_state) &&
              (!lex_state.is_argument || space_seen)) then
            tok = self.heredoc_identifier
            if tok then
              return tok
            end
          end

          self.fix_arg_lex_state
          self.yacc_value = "\<\<"
          return :tLSHFT
        elsif src.scan(/\</) then
          self.fix_arg_lex_state
          self.yacc_value = "<"
          return :tLT
        end
      elsif src.check(/\>/) then
        if src.scan(/\>\=/) then
          self.fix_arg_lex_state
          self.yacc_value = ">="
          return :tGEQ
        elsif src.scan(/\>\>=/) then
          self.fix_arg_lex_state
          self.lex_state = :expr_beg
          self.yacc_value = ">>"
          return :tOP_ASGN
        elsif src.scan(/\>\>/) then
          self.fix_arg_lex_state
          self.yacc_value = ">>"
          return :tRSHFT
        elsif src.scan(/\>/) then
          self.fix_arg_lex_state
          self.yacc_value = ">"
          return :tGT
        end
      elsif src.scan(/\`/) then
        self.yacc_value = "`"
        case lex_state
        when :expr_fname then
          self.lex_state = :expr_end
          return :tBACK_REF2
        when :expr_dot then
          self.lex_state = if command_state then
                             :expr_cmdarg
                           else
                             :expr_arg
                           end
          return :tBACK_REF2
        end
        self.lex_strterm = [:strterm, STR_XQUOTE, '`', "\0"]
        return :tXSTRING_BEG
      elsif src.scan(/\?/) then
        if lex_state == :expr_end || lex_state == :expr_endarg then
          self.lex_state = :expr_beg
          self.yacc_value = "?"
          return :tEH
        end

        if src.eos? then
          rb_compile_error "incomplete character syntax"
        end

        if src.check(/\s|\v/) then
          unless lex_state.is_argument then
            c2 = { " " => 's',
                  "\n" => 'n',
                  "\t" => 't',
                  "\v" => 'v',
                  "\r" => 'r',
                  "\f" => 'f' }[src.matched]

            if c2 then
              warning("invalid character syntax; use ?\\" + c2)
            end
          end

          # ternary
          self.lex_state = :expr_beg
          self.yacc_value = "?"
          return :tEH
        elsif src.check(/\w(?=\w)/) then # ternary, also
          self.lex_state = :expr_beg
          self.yacc_value = "?"
          return :tEH
        end

        c = if src.scan(/\\/) then
              self.read_escape
            else
              src.getch
            end
        self.lex_state = :expr_end

        if version == 18 then
          self.yacc_value = c[0].ord & 0xff
          return :tINTEGER
        else
          self.yacc_value = c
          return :tSTRING
        end
      elsif src.check(/\&/) then
        if src.scan(/\&\&\=/) then
          self.yacc_value = "&&"
          self.lex_state = :expr_beg
          return :tOP_ASGN
        elsif src.scan(/\&\&/) then
          self.lex_state = :expr_beg
          self.yacc_value = "&&"
          return :tANDOP
        elsif src.scan(/\&\=/) then
          self.yacc_value = "&"
          self.lex_state = :expr_beg
          return :tOP_ASGN
        elsif src.scan(/&/) then
          result = if lex_state.is_argument && space_seen &&
                       !src.check(/\s/) then
                     warning("`&' interpreted as argument prefix")
                     :tAMPER
                   elsif lex_state == :expr_beg || lex_state == :expr_mid then
                     :tAMPER
                   else
                     :tAMPER2
                   end

          self.fix_arg_lex_state
          self.yacc_value = "&"
          return result
        end
      elsif src.scan(/\//) then
        if lex_state == :expr_beg || lex_state == :expr_mid then
          self.lex_strterm = [:strterm, STR_REGEXP, '/', "\0"]
          self.yacc_value = "/"
          return :tREGEXP_BEG
        end

        if src.scan(/\=/) then
          self.yacc_value = "/"
          self.lex_state = :expr_beg
          return :tOP_ASGN
        end

        if lex_state.is_argument && space_seen then
          unless src.scan(/\s/) then
            arg_ambiguous
            self.lex_strterm = [:strterm, STR_REGEXP, '/', "\0"]
            self.yacc_value = "/"
            return :tREGEXP_BEG
          end
        end

        self.fix_arg_lex_state
        self.yacc_value = "/"

        return :tDIVIDE
      elsif src.scan(/\^=/) then
        self.lex_state = :expr_beg
        self.yacc_value = "^"
        return :tOP_ASGN
      elsif src.scan(/\^/) then
        self.fix_arg_lex_state
        self.yacc_value = "^"
        return :tCARET
      elsif src.scan(/\;/) then
        self.command_start = true
        self.lex_state = :expr_beg
        self.yacc_value = ";"
        return :tSEMI
      elsif src.scan(/\~/) then
        if lex_state == :expr_fname || lex_state == :expr_dot then
          src.scan(/@/)
        end

        self.fix_arg_lex_state
        self.yacc_value = "~"

        return :tTILDE
      elsif src.scan(/\\/) then
        if src.scan(/\n/) then
          self.lineno = nil
          space_seen = true
          next
        end
        rb_compile_error "bare backslash only allowed before newline"
      elsif src.scan(/\%/) then
        if lex_state == :expr_beg || lex_state == :expr_mid then
          return parse_quote
        end

        if src.scan(/\=/) then
          self.lex_state = :expr_beg
          self.yacc_value = "%"
          return :tOP_ASGN
        end

        if lex_state.is_argument && space_seen && ! src.check(/\s/) then
          return parse_quote
        end

        self.fix_arg_lex_state
        self.yacc_value = "%"

        return :tPERCENT
      elsif src.check(/\$/) then
        if src.scan(/(\$_)(\w+)/) then
          self.lex_state = :expr_end
          self.token = src.matched
          return process_token(command_state)
        elsif src.scan(/\$_/) then
          self.lex_state = :expr_end
          self.token = src.matched
          self.yacc_value = src.matched
          return :tGVAR
        elsif src.scan(/\$[~*$?!@\/\\;,.=:<>\"]|\$-\w?/) then
          self.lex_state = :expr_end
          self.yacc_value = src.matched
          return :tGVAR
        elsif src.scan(/\$([\&\`\'\+])/) then
          self.lex_state = :expr_end
          # Explicit reference to these vars as symbols...
          if last_state == :expr_fname then
            self.yacc_value = src.matched
            return :tGVAR
          else
            self.yacc_value = src[1].to_sym
            return :tBACK_REF
          end
        elsif src.scan(/\$([1-9]\d*)/) then
          self.lex_state = :expr_end
          if last_state == :expr_fname then
            self.yacc_value = src.matched
            return :tGVAR
          else
            self.yacc_value = src[1].to_i
            return :tNTH_REF
          end
        elsif src.scan(/\$0/) then
          self.lex_state = :expr_end
          self.token = src.matched
          return process_token(command_state)
        elsif src.scan(/\$\W|\$\z/) then # TODO: remove?
          self.lex_state = :expr_end
          self.yacc_value = "$"
          return "$"
        elsif src.scan(/\$\w+/)
          self.lex_state = :expr_end
          self.token = src.matched
          return process_token(command_state)
        end
      elsif src.check(/\_/) then
        if src.beginning_of_line? && src.scan(/\__END__(\n|\Z)/) then
          self.lineno = nil
          return RubyLexer::EOF
        elsif src.scan(/\_\w*/) then
          self.token = src.matched
          return process_token(command_state)
        end
      end
    end # END OF CASE

    if src.scan(/\004|\032|\000/) || src.eos? then # ^D, ^Z, EOF
      return RubyLexer::EOF
    else # alpha check
      if src.scan(/\W/) then
        rb_compile_error "Invalid char #{src.matched.inspect} in expression"
      end
    end

    self.token = src.matched if self.src.scan(/\w+/)

    return process_token(command_state)
  end
end

#yylex_stringObject

23 lines



1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
# File 'lib/ruby_parser/ruby_lexer.rb', line 1334

def yylex_string # 23 lines
  token = if lex_strterm[0] == :heredoc then
            self.heredoc lex_strterm
          else
            self.parse_string lex_strterm
          end

  if token == :tSTRING_END || token == :tREGEXP_END then
    self.lineno      = nil
    self.lex_strterm = nil
    self.lex_state   = :expr_end
  end

  return token
end