1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
|
require 'spec_helper'
RSpec.describe('CharacterSet::Range parsing') do
include_examples 'parse', '[a-z]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Range, count: 2],
[0, 0, 0] => [:literal, text: 'a'],
[0, 0, 1] => [:literal, text: 'z']
include_examples 'parse', '[\x00-\x22]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Range, count: 2],
[0, 0, 0] => [:hex, text: '\x00'],
[0, 0, 1] => [:hex, text: '\x22']
include_examples 'parse', '[\u{40 42}-\u1234]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Range, count: 2],
[0, 0, 0] => [:codepoint_list, text: '\u{40 42}'],
[0, 0, 1] => [:codepoint, text: '\u1234']
include_examples 'parse', '[--z]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Range, count: 2],
[0, 0, 0] => [:literal, text: '-'],
[0, 0, 1] => [:literal, text: 'z']
include_examples 'parse', '[!--]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Range, count: 2],
[0, 0, 0] => [:literal, text: '!'],
[0, 0, 1] => [:literal, text: '-']
include_examples 'parse', '[!-^]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Range, count: 2],
[0, 0, 0] => [:literal, text: '!'],
[0, 0, 1] => [:literal, text: '^']
# edge cases that are NOT treated as range
include_examples 'parse', '[^-z]',
[0] => [CharacterSet, count: 2],
[0, 0] => [:literal, text: '-'],
[0, 1] => [:literal, text: 'z']
include_examples 'parse', '[[\-ab]&&-bc]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Intersection, count: 2],
[0, 0, 0] => [CharacterSet::IntersectedSequence, count: 1],
[0, 0, 0, 0] => [CharacterSet, count: 3],
[0, 0, 1] => [CharacterSet::IntersectedSequence, count: 3],
[0, 0, 1, 0] => [:literal, text: '-']
include_examples 'parse', '[bc-&&[\-ab]]',
[0] => [CharacterSet, count: 1],
[0, 0] => [CharacterSet::Intersection, count: 2],
[0, 0, 0] => [CharacterSet::IntersectedSequence, count: 3],
[0, 0, 0, 2] => [:literal, text: '-'],
[0, 0, 1] => [CharacterSet::IntersectedSequence, count: 1],
[0, 0, 1, 0] => [CharacterSet, count: 3]
# Some edge-case patterns are evaluated with #match to make sure that
# their matching behavior still reflects the way they are parsed.
# #capturing_stderr is used to skip any warnings generated by this.
specify('ranges behavior remains unchanged') do
capturing_stderr do
expect(Regexp.new('[\x00-\x22]')).to match "\x11"
expect(Regexp.new('[\u{40 42}-\u1234]')).to match "\u0600"
expect(Regexp.new('[--z]')).to match 'a'
expect(Regexp.new('[!--]')).to match '$'
expect(Regexp.new('[!-^]')).to match '$'
# edge cases that are NOT treated as ranges
expect(Regexp.new('[^-z]')).to match 'a'
expect(Regexp.new('[^-z]')).not_to match 'z'
expect(Regexp.new('[[\-ab]&&-bc]')).to match '-'
expect(Regexp.new('[[\-ab]&&-bc]')).to match 'b'
expect(Regexp.new('[[\-ab]&&-bc]')).not_to match 'a'
expect(Regexp.new('[[\-ab]&&-bc]')).not_to match 'c'
expect(Regexp.new('[bc-&&[\-ab]]')).to match '-'
expect(Regexp.new('[bc-&&[\-ab]]')).to match 'b'
expect(Regexp.new('[bc-&&[\-ab]]')).not_to match 'a'
expect(Regexp.new('[bc-&&[\-ab]]')).not_to match 'c'
end
end
end
|
