Class: Regexp::Expression::Base

Inherits:
Object
  • Object
show all
Includes:
Shared
Defined in:
lib/regexp_parser/expression/base.rb,
lib/regexp_parser/expression/methods/match.rb,
lib/regexp_parser/expression/methods/options.rb,
lib/regexp_parser/expression/methods/strfregexp.rb

Instance Method Summary collapse

Methods included from Shared

#==, #base_length, #coded_offset, #full_length, #human_name, included, #is?, #nesting_level=, #offset, #one_of?, #optional?, #parts, #quantified?, #quantifier=, #quantifier_affix, #referential?, #starts_at, #terminal?, #to_s, #token_class, #type?

Constructor Details

#initialize(token, options = {}) ⇒ Base

Returns a new instance of Base.



5
6
7
 
# File 'lib/regexp_parser/expression/base.rb', line 5

def initialize(token, options = {})
  init_from_token_and_options(token, options)
end

Instance Method Details

#ascii_classes? ⇒ Boolean Also known as: a?

Returns:

  • (Boolean) 


25
26
27
 
# File 'lib/regexp_parser/expression/methods/options.rb', line 25

def ascii_classes?
  options[:a] == true
end

#case_insensitive? ⇒ Boolean Also known as: i?, ignore_case?

Returns:

  • (Boolean) 


8
9
10
 
# File 'lib/regexp_parser/expression/methods/options.rb', line 8

def case_insensitive?
  options[:i] == true
end

#default_classes? ⇒ Boolean Also known as: d?

Returns:

  • (Boolean) 


20
21
22
 
# File 'lib/regexp_parser/expression/methods/options.rb', line 20

def default_classes?
  options[:d] == true
end

#free_spacing? ⇒ Boolean Also known as: x?, extended?

Returns:

  • (Boolean) 


14
15
16
 
# File 'lib/regexp_parser/expression/methods/options.rb', line 14

def free_spacing?
  options[:x] == true
end

#greedy? ⇒ Boolean

Returns:

  • (Boolean) 


54
55
56
 
# File 'lib/regexp_parser/expression/base.rb', line 54

def greedy?
  quantified? and quantifier.greedy?
end

#initialize_copy(orig) ⇒ Object 



9
10
11
12
13
14
 
# File 'lib/regexp_parser/expression/base.rb', line 9

def initialize_copy(orig)
  self.text       = orig.text.dup         if orig.text
  self.options    = orig.options.dup      if orig.options
  self.quantifier = orig.quantifier.clone if orig.quantifier
  super
end

#match(string, offset = 0) ⇒ Object Also known as: =~ 



8
9
10
 
# File 'lib/regexp_parser/expression/methods/match.rb', line 8

def match(string, offset = 0)
  Regexp.new(to_s).match(string, offset)
end

#match?(string) ⇒ Boolean Also known as: matches?

Returns:

  • (Boolean) 


3
4
5
 
# File 'lib/regexp_parser/expression/methods/match.rb', line 3

def match?(string)
  !!match(string)
end

#multiline? ⇒ Boolean Also known as: m?

Returns:

  • (Boolean) 


3
4
5
 
# File 'lib/regexp_parser/expression/methods/options.rb', line 3

def multiline?
  options[:m] == true
end

#possessive? ⇒ Boolean

Returns:

  • (Boolean) 


63
64
65
 
# File 'lib/regexp_parser/expression/base.rb', line 63

def possessive?
  quantified? and quantifier.possessive?
end

#quantify(*args) ⇒ Object 



24
25
26
 
# File 'lib/regexp_parser/expression/base.rb', line 24

def quantify(*args)
  self.quantifier = Quantifier.new(*args)
end

#quantity ⇒ Object

Deprecated. Prefer ‘#repetitions` which has a more uniform interface.



33
34
35
36
 
# File 'lib/regexp_parser/expression/base.rb', line 33

def quantity
  return [nil,nil] unless quantified?
  [quantifier.min, quantifier.max]
end

#reluctant? ⇒ Boolean Also known as: lazy?

Returns:

  • (Boolean) 


58
59
60
 
# File 'lib/regexp_parser/expression/base.rb', line 58

def reluctant?
  quantified? and quantifier.reluctant?
end

#repetitions ⇒ Object 



38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
 
# File 'lib/regexp_parser/expression/base.rb', line 38

def repetitions
  @repetitions ||=
    if quantified?
      min = quantifier.min
      max = quantifier.max < 0 ? Float::INFINITY : quantifier.max
      range = min..max
      # fix Range#minmax on old Rubies - https://bugs.ruby-lang.org/issues/15807
      if RUBY_VERSION.to_f < 2.7
        range.define_singleton_method(:minmax) { [min, max] }
      end
      range
    else
      1..1
    end
end

#strfregexp(format = '%a', indent_offset = 0, index = nil) ⇒ Object Also known as: strfre

%l Level (depth) of the expression. Returns ‘root’ for the root

    expression, returns zero or higher for all others.

%>  Indentation at expression's level.

%x  Index of the expression at its depth. Available when using
    the sprintf_tree method only.

%s  Start offset within the whole expression.
%e  End offset within the whole expression.
%S  Length of expression.

%o  Coded offset and length, same as '@%s+%S'

%y  Type of expression.
%k  Token of expression.
%i  ID, same as '%y:%k'
%c  Class name

%q  Quantifier info, as {m[,M]}
%Q  Quantifier text

%z  Quantifier min
%Z  Quantifier max

%t  Base text of the expression (excludes quantifier, if any)
%~t Full text if the expression is terminal, otherwise %i
%T  Full text of the expression (includes quantifier, if any)

%b  Basic info, same as '%o %i'
%m  Most info, same as '%b %q'
%a  All info, same as '%m %t'



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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
 
# File 'lib/regexp_parser/expression/methods/strfregexp.rb', line 37

def strfregexp(format = '%a', indent_offset = 0, index = nil)
  have_index    = index ? true : false

  part = {}

  print_level = nesting_level > 0 ? nesting_level - 1 : nil

  # Order is important! Fields that use other fields in their
  # definition must appear before the fields they use.
  part_keys = %w[a m b o i l x s e S y k c q Q z Z t ~t T >]
  part.keys.each {|k| part[k] = "<?#{k}?>"}

  part['>'] = print_level ? ('  ' * (print_level + indent_offset)) : ''

  part['l'] = print_level ? "#{'%d' % print_level}" : 'root'
  part['x'] = "#{'%d' % index}" if have_index

  part['s'] = starts_at
  part['S'] = full_length
  part['e'] = starts_at + full_length
  part['o'] = coded_offset

  part['k'] = token
  part['y'] = type
  part['i'] = '%y:%k'
  part['c'] = self.class.name

  if quantified?
    if quantifier.max == -1
      part['q'] = "{#{quantifier.min}, or-more}"
    else
      part['q'] = "{#{quantifier.min}, #{quantifier.max}}"
    end

    part['Q'] = quantifier.text
    part['z'] = quantifier.min
    part['Z'] = quantifier.max
  else
    part['q'] = '{1}'
    part['Q'] = ''
    part['z'] = '1'
    part['Z'] = '1'
  end

  part['t'] = to_s(:base)
  part['~t'] = terminal? ? to_s : "#{type}:#{token}"
  part['T'] = to_s(:full)

  part['b'] = '%o %i'
  part['m'] = '%b %q'
  part['a'] = '%m %t'

  out = format.dup

  part_keys.each do |k|
    out.gsub!(/%#{k}/, part[k].to_s)
  end

  out
end

#to_h ⇒ Object Also known as: attributes 



67
68
69
70
71
72
73
74
75
76
77
78
79
80
 
# File 'lib/regexp_parser/expression/base.rb', line 67

def to_h
  {
    type:              type,
    token:             token,
    text:              to_s(:base),
    starts_at:         ts,
    length:            full_length,
    level:             level,
    set_level:         set_level,
    conditional_level: conditional_level,
    options:           options,
    quantifier:        quantified? ? quantifier.to_h : nil,
  }
end

#to_re(format = :full) ⇒ Object 



16
17
18
19
20
21
22
 
# File 'lib/regexp_parser/expression/base.rb', line 16

def to_re(format = :full)
  if set_level > 0
    warn "Calling #to_re on character set members is deprecated - "\
         "their behavior might not be equivalent outside of the set."
  end
  ::Regexp.new(to_s(format))
end

#unicode_classes? ⇒ Boolean Also known as: u?

Returns:

  • (Boolean) 


30
31
32
 
# File 'lib/regexp_parser/expression/methods/options.rb', line 30

def unicode_classes?
  options[:u] == true
end

#unquantified_clone ⇒ Object 



28
29
30
 
# File 'lib/regexp_parser/expression/base.rb', line 28

def unquantified_clone
  clone.tap { |exp| exp.quantifier = nil }
end