Class: Regexp::Lexer

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

Overview

A very thin wrapper around the scanner that breaks quantified literal runs, collects emitted tokens into an array, calculates their nesting depth, and normalizes tokens for the parser, and checks if they are implemented by the given syntax flavor.

Constant Summary collapse

OPENING_TOKENS = 
%i[
  capture passive lookahead nlookahead lookbehind nlookbehind
  atomic options options_switch named absence
].freeze
CLOSING_TOKENS = 
%i[close].freeze
CONDITION_TOKENS = 
%i[condition condition_close].freeze

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.lex(input, syntax = "ruby/#{RUBY_VERSION}", options: nil, &block) ⇒ Object Also known as: scan 



16
17
18
 
# File 'lib/regexp_parser/lexer.rb', line 16

def self.lex(input, syntax = "ruby/#{RUBY_VERSION}", options: nil, &block)
  new.lex(input, syntax, options: options, &block)
end

Instance Method Details

#lex(input, syntax = "ruby/#{RUBY_VERSION}", options: nil, &block) ⇒ Object 



20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
 
# File 'lib/regexp_parser/lexer.rb', line 20

def lex(input, syntax = "ruby/#{RUBY_VERSION}", options: nil, &block)
  syntax = Regexp::Syntax.for(syntax)

  self.tokens = []
  self.nesting = 0
  self.set_nesting = 0
  self.conditional_nesting = 0
  self.shift = 0

  last = nil
  Regexp::Scanner.scan(input, options: options) do |type, token, text, ts, te|
    type, token = *syntax.normalize(type, token)
    syntax.check! type, token

    ascend(type, token)

    if type == :quantifier and last
      break_literal(last)        if last.type == :literal
      break_codepoint_list(last) if last.token == :codepoint_list
    end

    current = Regexp::Token.new(type, token, text, ts + shift, te + shift,
                                nesting, set_nesting, conditional_nesting)

    current = merge_condition(current) if type == :conditional and
      CONDITION_TOKENS.include?(token)

    last.next = current if last
    current.previous = last if last

    tokens << current
    last = current

    descend(type, token)
  end

  if block_given?
    tokens.map { |t| block.call(t) }
  else
    tokens
  end
end