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 open
].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 = nil, options: nil, collect_tokens: true, &block) ⇒ Object Also known as: scan 



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

def self.lex(input, syntax = nil, options: nil, collect_tokens: true, &block)
  new.lex(input, syntax, options: options, collect_tokens: collect_tokens, &block)
end

Instance Method Details

#emit(token) ⇒ Object 



71
72
73
74
75
76
77
78
79
 
# File 'lib/regexp_parser/lexer.rb', line 71

def emit(token)
  if block
    # TODO: in v3.0.0, remove `collect_tokens:` kwarg and only collect w/o block
    res = block.call(token)
    tokens << res if collect_tokens
  else
    tokens << token
  end
end

#lex(input, syntax = nil, options: nil, collect_tokens: true, &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
62
63
64
65
66
67
68
69
 
# File 'lib/regexp_parser/lexer.rb', line 20

def lex(input, syntax = nil, options: nil, collect_tokens: true, &block)
  syntax = syntax ? Regexp::Syntax.for(syntax) : Regexp::Syntax::CURRENT

  self.block = block
  self.collect_tokens = collect_tokens
  self.tokens = []
  self.prev_token = nil
  self.preprev_token = nil
  self.nesting = 0
  self.set_nesting = 0
  self.conditional_nesting = 0
  self.shift = 0

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

    ascend(type, token)

    if (last = prev_token) &&
       type == :quantifier &&
       (
         (last.type == :literal         && (parts = break_literal(last))) ||
         (last.token == :codepoint_list && (parts = break_codepoint_list(last)))
       )
      emit(parts[0])
      last = parts[1]
    end

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

    if type == :conditional && CONDITION_TOKENS.include?(token)
      current = merge_condition(current, last)
    elsif last
      last.next = current
      current.previous = last
      emit(last)
    end

    self.preprev_token = last
    self.prev_token = current

    descend(type, token)
  end

  emit(prev_token) if prev_token

  collect_tokens ? tokens : nil
end