Class: PuppetLint::Lexer

Inherits:
Object
  • Object
show all
Defined in:
lib/puppet-lint/lexer.rb,
lib/puppet-lint/lexer/token.rb

Overview

Internal: The puppet-lint lexer. Converts your manifest into its tokenised form.

Defined Under Namespace

Classes: Token

Constant Summary collapse

KEYWORDS =

Internal: A Hash whose keys are Strings representing reserved keywords in the Puppet DSL. From github.com/puppetlabs/puppet/blob/master/lib/puppet/pops/parser/lexer2.rb#L116-L137 or thereabouts

{
  'case'     => true,
  'class'    => true,
  'default'  => true,
  'define'   => true,
  'import'   => true,
  'if'       => true,
  'elsif'    => true,
  'else'     => true,
  'inherits' => true,
  'node'     => true,
  'and'      => true,
  'or'       => true,
  'undef'    => true,
  'false'    => true,
  'true'     => true,
  'in'       => true,
  'unless'   => true,
  'function' => true,
  'type'     => true,
  'attr'     => true,
  'private'  => true,
}.freeze
APP_MANAGEMENT_TOKENS =

Internal: A Hash whose keys are Strings representing reserved keywords in the Puppet DSL when Application Management is enabled From github.com/puppetlabs/puppet/blob/master/lib/puppet/pops/parser/lexer2.rb#L142-L159 or therabouts Currently unused

{
  'application' => true,
  'consumes'    => true,
  'produces'    => true,
  'site'        => true,
}.freeze
REGEX_PREV_TOKENS =

Internal: A Hash whose keys are Symbols representing token types which a regular expression can follow.

{
  :NODE    => true,
  :LBRACE  => true,
  :RBRACE  => true,
  :MATCH   => true,
  :NOMATCH => true,
  :COMMA   => true,
  :LBRACK  => true,
  :IF      => true,
  :ELSIF   => true,
  :LPAREN  => true,
}.freeze
NAME_RE =

Internal: An Array of Arrays containing tokens that can be described by a single regular expression. Each sub-Array contains 2 elements, the name of the token as a Symbol and a regular expression describing the value of the token.

%r{\A(((::)?[_a-z0-9][-\w]*)(::[a-z0-9][-\w]*)*)}
KNOWN_TOKENS = 
[
  [:TYPE, %r{\A(Integer|Float|Boolean|Regexp|String|Array|Hash|Resource|Class|Collection|Scalar|Numeric|CatalogEntry|Data|Tuple|Struct|Optional|NotUndef|Variant|Enum|Pattern|Any|Callable|Type|Runtime|Undef|Default)\b}],
  [:CLASSREF, %r{\A(((::){0,1}[A-Z][-\w]*)+)}],
  [:NUMBER, %r{\A\b((?:0[xX][0-9A-Fa-f]+|0?\d+(?:\.\d+)?(?:[eE]-?\d+)?))\b}],
  [:FUNCTION_NAME, %r{#{NAME_RE}\(}],
  [:NAME, NAME_RE],
  [:LBRACK, %r{\A(\[)}],
  [:RBRACK, %r{\A(\])}],
  [:LBRACE, %r{\A(\{)}],
  [:RBRACE, %r{\A(\})}],
  [:LPAREN, %r{\A(\()}],
  [:RPAREN, %r{\A(\))}],
  [:ISEQUAL, %r{\A(==)}],
  [:MATCH, %r{\A(=~)}],
  [:FARROW, %r{\A(=>)}],
  [:EQUALS, %r{\A(=)}],
  [:APPENDS, %r{\A(\+=)}],
  [:PARROW, %r{\A(\+>)}],
  [:PLUS, %r{\A(\+)}],
  [:GREATEREQUAL, %r{\A(>=)}],
  [:RSHIFT, %r{\A(>>)}],
  [:GREATERTHAN, %r{\A(>)}],
  [:LESSEQUAL, %r{\A(<=)}],
  [:LLCOLLECT, %r{\A(<<\|)}],
  [:OUT_EDGE, %r{\A(<-)}],
  [:OUT_EDGE_SUB, %r{\A(<~)}],
  [:LCOLLECT, %r{\A(<\|)}],
  [:LSHIFT, %r{\A(<<)}],
  [:LESSTHAN, %r{\A(<)}],
  [:NOMATCH, %r{\A(!~)}],
  [:NOTEQUAL, %r{\A(!=)}],
  [:NOT, %r{\A(!)}],
  [:RRCOLLECT, %r{\A(\|>>)}],
  [:RCOLLECT, %r{\A(\|>)}],
  [:IN_EDGE, %r{\A(->)}],
  [:IN_EDGE_SUB, %r{\A(~>)}],
  [:MINUS, %r{\A(-)}],
  [:COMMA, %r{\A(,)}],
  [:DOT, %r{\A(\.)}],
  [:COLON, %r{\A(:)}],
  [:SEMIC, %r{\A(;)}],
  [:QMARK, %r{\A(\?)}],
  [:BACKSLASH, %r{\A(\\)}],
  [:TIMES, %r{\A(\*)}],
  [:MODULO, %r{\A(%)}],
  [:PIPE, %r{\A(\|)}],
].freeze
FORMATTING_TOKENS =

Internal: A Hash whose keys are Symbols representing token types which are considered to be formatting tokens (i.e. tokens that don’t contain code).

{
  :WHITESPACE    => true,
  :NEWLINE       => true,
  :COMMENT       => true,
  :MLCOMMENT     => true,
  :SLASH_COMMENT => true,
  :INDENT        => true,
}.freeze
WHITESPACE_RE =

t == tab v == vertical tab f == form feed pZs == ASCII + Unicode non-linebreaking whitespace

RUBY_VERSION == '1.8.7' ? %r{[\t\v\f ]} : %r{[\t\v\f\p{Zs}]}
LINE_END_RE = 
%r{(?:\r\n|\r|\n)}

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Lexer

rubocop:disable Metrics/ClassLength



36
37
38
39
 
# File 'lib/puppet-lint/lexer.rb', line 36

def initialize
  @line_no = 1
  @column = 1
end

Class Method Details

.heredoc_queue ⇒ Object 



41
42
43
 
# File 'lib/puppet-lint/lexer.rb', line 41

def self.heredoc_queue
  @heredoc_queue ||= []
end

Instance Method Details

#get_heredoc_segment(string, eos_text, interpolate = true) ⇒ Object

Internal: Splits a heredoc String into segments if it is to be interpolated.

string - The String heredoc. eos_text - The String endtext for the heredoc. interpolate - A Boolean that specifies whether this heredoc can contain

interpolated values (defaults to True).

Returns an Array consisting of two Strings, the String up to the first terminator and the terminator that was found.



553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
 
# File 'lib/puppet-lint/lexer.rb', line 553

def get_heredoc_segment(string, eos_text, interpolate = true)
  regexp = if interpolate
             %r{(([^\\]|^|[^\\])([\\]{2})*[$]+|\|?\s*-?#{Regexp.escape(eos_text)})}
           else
             %r{\|?\s*-?#{Regexp.escape(eos_text)}}
           end

  str = string.scan_until(regexp)
  begin
    str =~ %r{\A(.*?)([$]+|\|?\s*-?#{Regexp.escape(eos_text)})\Z}m
    [Regexp.last_match(1), Regexp.last_match(2)]
  rescue
    [nil, nil]
  end
end

#get_string_segment(string, terminators) ⇒ Object

Internal: Split a string on multiple terminators, excluding escaped terminators.

string - The String to be split. terminators - The String of terminators that the String should be split

on.

Returns an Array consisting of two Strings, the String up to the first terminator and the terminator that was found.



415
416
417
418
419
420
421
422
 
# File 'lib/puppet-lint/lexer.rb', line 415

def get_string_segment(string, terminators)
  str = string.scan_until(%r{([^\\]|^|[^\\])([\\]{2})*[#{terminators}]+})
  begin
    [str[0..-2], str[-1, 1]]
  rescue
    [nil, nil]
  end
end

#heredoc_queue ⇒ Object 



45
46
47
 
# File 'lib/puppet-lint/lexer.rb', line 45

def heredoc_queue
  self.class.heredoc_queue
end

#interpolate_heredoc(string, name) ⇒ Object

Internal: Tokenise the contents of a heredoc.

string - The String to be tokenised. name - The String name/endtext of the heredoc.

Returns nothing.



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
 
# File 'lib/puppet-lint/lexer.rb', line 494

def interpolate_heredoc(string, name)
  ss = StringScanner.new(string)
  eos_text = name[%r{\A"?(.+?)"?(:.+?)?(/.*)?\Z}, 1]
  first = true
  interpolate = name.start_with?('"')
  value, terminator = get_heredoc_segment(ss, eos_text, interpolate)
  until value.nil?
    if terminator =~ %r{\A\|?\s*-?\s*#{Regexp.escape(eos_text)}}
      if first
        tokens << new_token(:HEREDOC, value, :raw => "#{value}#{terminator}")
        first = false
      else
        tokens << new_token(:HEREDOC_POST, value, :raw => "#{value}#{terminator}")
      end
    else
      if first
        tokens << new_token(:HEREDOC_PRE, value)
        first = false
      else
        tokens << new_token(:HEREDOC_MID, value)
      end
      if ss.scan(%r{\{}).nil?
        var_name = ss.scan(%r{(::)?(\w+(-\w+)*::)*\w+(-\w+)*})
        tokens << if var_name.nil?
                    new_token(:HEREDOC_MID, '$')
                  else
                    new_token(:UNENC_VARIABLE, var_name)
                  end
      else
        contents = ss.scan_until(%r{\}})[0..-2]
        raw = contents.dup
        if contents.match(%r{\A(::)?([\w-]+::)*[\w-]|(\[.+?\])*}) && !contents.match(%r{\A\w+\(})
          contents = "$#{contents}" unless contents.start_with?('$')
        end

        lexer = PuppetLint::Lexer.new
        lexer.tokenise(contents)
        lexer.tokens.each do |token|
          tokens << new_token(token.type, token.value)
        end
        if lexer.tokens.length == 1 && lexer.tokens[0].type == :VARIABLE
          tokens.last.raw = raw
        end
      end
    end
    value, terminator = get_heredoc_segment(ss, eos_text, interpolate)
  end
end

#interpolate_string(string, line, column) ⇒ Object

Internal: Tokenise the contents of a double quoted string.

string - The String to be tokenised. line - The Integer line number of the start of the passed string. column - The Integer column number of the start of the passed string.

Returns nothing.



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
 
# File 'lib/puppet-lint/lexer.rb', line 431

def interpolate_string(string, line, column)
  ss = StringScanner.new(string)
  first = true
  value, terminator = get_string_segment(ss, '"$')
  until value.nil?
    if terminator == '"'
      if first
        tokens << new_token(:STRING, value, :line => line, :column => column)
        first = false
      else
        token_column = column + (ss.pos - value.size)
        tokens << new_token(:DQPOST, value, :line => line, :column => token_column)
        line += value.scan(LINE_END_RE).size
        @column = column + ss.pos + 1
        @line_no = line
      end
    else
      if first
        tokens << new_token(:DQPRE, value, :line => line, :column => column)
        first = false
      else
        token_column = column + (ss.pos - value.size)
        tokens << new_token(:DQMID, value, :line => line, :column => token_column)
        line += value.scan(LINE_END_RE).size
      end
      if ss.scan(%r{\{}).nil?
        var_name = ss.scan(%r{(::)?(\w+(-\w+)*::)*\w+(-\w+)*})
        if var_name.nil?
          token_column = column + ss.pos - 1
          tokens << new_token(:DQMID, '$', :line => line, :column => token_column)
        else
          token_column = column + (ss.pos - var_name.size)
          tokens << new_token(:UNENC_VARIABLE, var_name, :line => line, :column => token_column)
        end
      else
        line += value.scan(LINE_END_RE).size
        contents = ss.scan_until(%r{\}})[0..-2]
        raw = contents.dup
        if contents.match(%r{\A(::)?([\w-]+::)*[\w-]+(\[.+?\])*}) && !contents.match(%r{\A\w+\(})
          contents = "$#{contents}"
        end
        lexer = PuppetLint::Lexer.new
        lexer.tokenise(contents)
        lexer.tokens.each do |token|
          tok_col = column + token.column + (ss.pos - contents.size - 1)
          tok_line = token.line + line - 1
          tokens << new_token(token.type, token.value, :line => tok_line, :column => tok_col)
        end
        if lexer.tokens.length == 1 && lexer.tokens[0].type == :VARIABLE
          tokens.last.raw = raw
        end
      end
    end
    value, terminator = get_string_segment(ss, '"$')
  end
end

#new_token(type, value, *args) ⇒ Object

Internal: Create a new PuppetLint::Lexer::Token object, calculate its line number and column and then add it to the Linked List of tokens.

type - The Symbol token type. value - The token value. opts - A Hash of additional values required to determine line number and

      column:
:line   - The Integer line number if calculated externally.
:column - The Integer column number if calculated externally.
:raw    - The String raw value of the token (if necessary).

Returns the instantiated PuppetLint::Lexer::Token object.



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
 
# File 'lib/puppet-lint/lexer.rb', line 353

def new_token(type, value, *args)
  # This bit of magic is used instead of an "opts = {}" argument so that we
  # can safely deprecate the old "length" parameter that might still be
  # passed by 3rd party plugins that haven't updated yet.
  opts = args.last.is_a?(Hash) ? args.last : {}

  # column number is calculated at the end of this method by calling
  # to_manifest on the token. Because the string tokens (DQPRE, DQMID etc)
  # are parsed before the variable token, they default to assuming that
  # they are followed by an enclosed variable and we need to remove 2 from
  # the column number if we encounter an unenclosed variable because of the
  # missing ${ at the end of the token value.
  @column -= 2 if type == :UNENC_VARIABLE

  column = opts[:column] || @column
  line_no = opts[:line] || @line_no

  token = Token.new(type, value, line_no, column)
  unless tokens.last.nil?
    token.prev_token = tokens.last
    tokens.last.next_token = token

    unless FORMATTING_TOKENS.include?(token.type)
      prev_nf_idx = tokens.rindex { |r| !FORMATTING_TOKENS.include?(r.type) }
      unless prev_nf_idx.nil?
        prev_nf_token = tokens[prev_nf_idx]
        prev_nf_token.next_code_token = token
        token.prev_code_token = prev_nf_token
      end
    end
  end

  token.raw = opts[:raw] if opts[:raw]

  if type == :NEWLINE
    @line_no += 1
    @column = 1
  else
    lines = token.to_manifest.split(LINE_END_RE, -1)
    @line_no += lines.length - 1
    if lines.length > 1
      # if the token renders to multiple lines, set the column state to the
      # length of the last line plus 1 (because column numbers are
      # 1 indexed)
      @column = lines.last.size + 1
    else
      @column += (lines.last || '').size
    end
  end

  token
end

#possible_regex? ⇒ Boolean

Internal: Given the tokens already processed, determine if the next token could be a regular expression.

Returns true if the next token could be a regex, otherwise return false.

Returns:

  • (Boolean) 


331
332
333
334
335
336
337
338
339
 
# File 'lib/puppet-lint/lexer.rb', line 331

def possible_regex?
  prev_token = tokens.reject { |r|
    FORMATTING_TOKENS.include?(r.type)
  }.last

  return true if prev_token.nil?

  REGEX_PREV_TOKENS.include?(prev_token.type)
end

#slurp_string(string) ⇒ Object 



311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
 
# File 'lib/puppet-lint/lexer.rb', line 311

def slurp_string(string)
  dq_str_regexp = %r{(\$\{|(\A|[^\\])(\\\\)*")}m
  scanner = StringScanner.new(string)
  contents = scanner.scan_until(dq_str_regexp)

  if scanner.matched.nil?
    raise LexerError.new(@line_no, @column, 'Double quoted string missing closing quote')
  end

  until scanner.matched.end_with?('"')
    contents += scanner.scan_until(%r{\}}m)
    contents += scanner.scan_until(dq_str_regexp)
  end
  contents
end

#tokenise(code) ⇒ Object

Internal: Convert a Puppet manifest into tokens.

code - The Puppet manifest to be tokenised as a String.

Returns an Array of PuppetLint::Lexer::Token objects. Raises PuppetLint::LexerError if it encounters unexpected characters (usually the result of syntax errors).



191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
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
 
# File 'lib/puppet-lint/lexer.rb', line 191

def tokenise(code)
  i = 0

  while i < code.size
    chunk = code[i..-1]

    found = false

    KNOWN_TOKENS.each do |type, regex|
      value = chunk[regex, 1]
      next if value.nil?

      length = value.size
      tokens << if type == :NAME && KEYWORDS.include?(value)
                  new_token(value.upcase.to_sym, value)
                else
                  new_token(type, value)
                end
      i += length
      found = true
      break
    end

    next if found

    if var_name = chunk[%r{\A\$((::)?(\w+(-\w+)*::)*\w+(-\w+)*(\[.+?\])*)}, 1]
      length = var_name.size + 1
      tokens << new_token(:VARIABLE, var_name)

    elsif chunk =~ %r{\A'.*?'}m
      str_content = StringScanner.new(code[i + 1..-1]).scan_until(%r{(\A|[^\\])(\\\\)*'}m)
      length = str_content.size + 1
      tokens << new_token(:SSTRING, str_content[0..-2])

    elsif chunk.start_with?('"')
      str_contents = slurp_string(code[i + 1..-1])
      lines_parsed = code[0..i].split(LINE_END_RE)
      interpolate_string(str_contents, lines_parsed.count, lines_parsed.last.length)
      length = str_contents.size + 1

    elsif heredoc_name = chunk[%r{\A@\(("?.+?"?(:.+?)?(/.*?)?)\)}, 1]
      heredoc_queue << heredoc_name
      tokens << new_token(:HEREDOC_OPEN, heredoc_name)
      length = heredoc_name.size + 3

    elsif comment = chunk[%r{\A(#[^\r\n]*)#{LINE_END_RE}?}, 1]
      length = comment.size
      comment.sub!(%r{#}, '')
      tokens << new_token(:COMMENT, comment)

    elsif slash_comment = chunk[%r{\A(//[^\r\n]*)#{LINE_END_RE}?}, 1]
      length = slash_comment.size
      slash_comment.sub!(%r{//}, '')
      tokens << new_token(:SLASH_COMMENT, slash_comment)

    elsif mlcomment = chunk[%r{\A(/\*.*?\*/)}m, 1]
      length = mlcomment.size
      mlcomment_raw = mlcomment.dup
      mlcomment.sub!(%r{\A/\* ?}, '')
      mlcomment.sub!(%r{ ?\*/\Z}, '')
      mlcomment.gsub!(%r{^ *\*}, '')
      tokens << new_token(:MLCOMMENT, mlcomment, :raw => mlcomment_raw)

    elsif chunk.match(%r{\A/.*?/}) && possible_regex?
      str_content = StringScanner.new(code[i + 1..-1]).scan_until(%r{(\A|[^\\])(\\\\)*/}m)
      length = str_content.size + 1
      tokens << new_token(:REGEX, str_content[0..-2])

    elsif eolindent = chunk[%r{\A(#{LINE_END_RE}#{WHITESPACE_RE}+)}m, 1]
      eol = eolindent[%r{\A(#{LINE_END_RE})}m, 1]
      tokens << new_token(:NEWLINE, eol)
      length = eol.size

      if heredoc_queue.empty?
        indent = eolindent[%r{\A#{LINE_END_RE}+(#{WHITESPACE_RE}+)}m, 1]
        tokens << new_token(:INDENT, indent)
        length += indent.size
      else
        heredoc_tag = heredoc_queue.shift
        heredoc_name = heredoc_tag[%r{\A"?(.+?)"?(:.+?)?(/.*)?\Z}, 1]
        str_contents = StringScanner.new(code[(i + length)..-1]).scan_until(%r{\|?\s*-?\s*#{heredoc_name}})
        interpolate_heredoc(str_contents, heredoc_tag)
        length += str_contents.size
      end

    elsif whitespace = chunk[%r{\A(#{WHITESPACE_RE}+)}, 1]
      length = whitespace.size
      tokens << new_token(:WHITESPACE, whitespace)

    elsif eol = chunk[%r{\A(#{LINE_END_RE})}, 1]
      length = eol.size
      tokens << new_token(:NEWLINE, eol)

      unless heredoc_queue.empty?
        heredoc_tag = heredoc_queue.shift
        heredoc_name = heredoc_tag[%r{\A"?(.+?)"?(:.+?)?(/.*)?\Z}, 1]
        str_contents = StringScanner.new(code[(i + length)..-1]).scan_until(%r{\|?\s*-?\s*#{heredoc_name}})
        _ = code[0..(i + length)].split(LINE_END_RE)
        interpolate_heredoc(str_contents, heredoc_tag)
        length += str_contents.size
      end

    elsif chunk.start_with?('/')
      length = 1
      tokens << new_token(:DIV, '/')

    elsif chunk.start_with?('@')
      length = 1
      tokens << new_token(:AT, '@')

    else
      raise PuppetLint::LexerError.new(@line_no, @column)
    end

    i += length
  end

  tokens
end

#tokens ⇒ Object

Internal: Access the internal token storage.

Returns an Array of PuppetLint::Lexer::Toxen objects.



180
181
182
 
# File 'lib/puppet-lint/lexer.rb', line 180

def tokens
  @tokens ||= []
end