regular_expression 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.github/dependabot.yml +6 -0
- data/.github/workflows/main.yml +36 -0
- data/.gitignore +1 -0
- data/.rubocop.yml +42 -0
- data/CODE_OF_CONDUCT.md +76 -0
- data/CONTRIBUTING.md +76 -0
- data/Gemfile +13 -0
- data/Gemfile.lock +69 -0
- data/LICENSE +21 -0
- data/README.md +51 -0
- data/Rakefile +18 -0
- data/bin/console +8 -0
- data/bin/parse +50 -0
- data/build/.gitignore +1 -0
- data/lib/regular_expression.rb +19 -0
- data/lib/regular_expression/ast.rb +364 -0
- data/lib/regular_expression/bytecode.rb +189 -0
- data/lib/regular_expression/cfg.rb +154 -0
- data/lib/regular_expression/compiler/ruby.rb +104 -0
- data/lib/regular_expression/compiler/x86.rb +281 -0
- data/lib/regular_expression/interpreter.rb +92 -0
- data/lib/regular_expression/lexer.rb +53 -0
- data/lib/regular_expression/nfa.rb +118 -0
- data/lib/regular_expression/parser.rb +399 -0
- data/lib/regular_expression/parser.y +96 -0
- data/lib/regular_expression/pattern.rb +23 -0
- data/lib/regular_expression/version.rb +5 -0
- data/regular_expression.gemspec +25 -0
- metadata +99 -0
@@ -0,0 +1,96 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class RegularExpression::Parser
|
4
|
+
rule
|
5
|
+
target:
|
6
|
+
root
|
7
|
+
{ result = val[0] }
|
8
|
+
| /* none */
|
9
|
+
{ result = nil }
|
10
|
+
|
11
|
+
root:
|
12
|
+
CARET expression
|
13
|
+
{ result = RegularExpression::AST::Root.new(val[1], at_start: true) }
|
14
|
+
| expression
|
15
|
+
{ result = RegularExpression::AST::Root.new(val[0]) }
|
16
|
+
|
17
|
+
expression:
|
18
|
+
subexpression PIPE expression
|
19
|
+
{ result = [RegularExpression::AST::Expression.new(val[0])] + val[2] }
|
20
|
+
| subexpression
|
21
|
+
{ result = [RegularExpression::AST::Expression.new(val[0])] }
|
22
|
+
|
23
|
+
subexpression:
|
24
|
+
item subexpression
|
25
|
+
{ result = [val[0]] + val[1] }
|
26
|
+
| item
|
27
|
+
{ result = [val[0]] }
|
28
|
+
|
29
|
+
item:
|
30
|
+
group
|
31
|
+
| match
|
32
|
+
| ANCHOR
|
33
|
+
{ result = RegularExpression::AST::Anchor.new(val[0]) }
|
34
|
+
|
35
|
+
group:
|
36
|
+
LPAREN expression RPAREN quantifier
|
37
|
+
{ result = RegularExpression::AST::Group.new(val[1], quantifier: val[3]) }
|
38
|
+
| LPAREN expression RPAREN
|
39
|
+
{ result = RegularExpression::AST::Group.new(val[1]) }
|
40
|
+
|
41
|
+
match:
|
42
|
+
match_item quantifier
|
43
|
+
{ result = RegularExpression::AST::Match.new(val[0], quantifier: val[1]) }
|
44
|
+
| match_item
|
45
|
+
{ result = RegularExpression::AST::Match.new(val[0]) }
|
46
|
+
|
47
|
+
match_item:
|
48
|
+
LBRACKET CARET character_group_items RBRACKET
|
49
|
+
{ result = RegularExpression::AST::CharacterGroup.new(val[2], invert: true) }
|
50
|
+
| LBRACKET character_group_items RBRACKET
|
51
|
+
{ result = RegularExpression::AST::CharacterGroup.new(val[1]) }
|
52
|
+
| CHAR_CLASS
|
53
|
+
{ result = RegularExpression::AST::CharacterClass.new(val[0]) }
|
54
|
+
| CHAR
|
55
|
+
{ result = RegularExpression::AST::Character.new(val[0]) }
|
56
|
+
| PERIOD
|
57
|
+
{ result = RegularExpression::AST::Period.new }
|
58
|
+
|
59
|
+
character_group_items:
|
60
|
+
character_group_item character_group_items
|
61
|
+
{ result = [val[0]] + val[1] }
|
62
|
+
| character_group_item
|
63
|
+
{ result = [val[0]] }
|
64
|
+
|
65
|
+
character_group_item:
|
66
|
+
CHAR_CLASS
|
67
|
+
| CHAR DASH CHAR
|
68
|
+
{ result = RegularExpression::AST::CharacterRange.new(val[0], val[2]) }
|
69
|
+
| CHAR
|
70
|
+
{ result = RegularExpression::AST::Character.new(val[0]) }
|
71
|
+
|
72
|
+
quantifier:
|
73
|
+
LBRACE INTEGER COMMA INTEGER RBRACE
|
74
|
+
{ result = RegularExpression::AST::Quantifier::Range.new(val[1], val[3]) }
|
75
|
+
| LBRACE INTEGER COMMA RBRACE
|
76
|
+
{ result = RegularExpression::AST::Quantifier::AtLeast.new(val[1]) }
|
77
|
+
| LBRACE INTEGER RBRACE
|
78
|
+
{ result = RegularExpression::AST::Quantifier::Exact.new(val[1]) }
|
79
|
+
| STAR
|
80
|
+
{ result = RegularExpression::AST::Quantifier::ZeroOrMore.new }
|
81
|
+
| PLUS
|
82
|
+
{ result = RegularExpression::AST::Quantifier::OneOrMore.new }
|
83
|
+
| QMARK
|
84
|
+
{ result = RegularExpression::AST::Quantifier::Optional.new }
|
85
|
+
end
|
86
|
+
|
87
|
+
---- inner
|
88
|
+
|
89
|
+
def parse(str)
|
90
|
+
@tokens = RegularExpression::Lexer.new(str).tokens
|
91
|
+
do_parse
|
92
|
+
end
|
93
|
+
|
94
|
+
def next_token
|
95
|
+
@tokens.shift
|
96
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module RegularExpression
|
4
|
+
class Pattern
|
5
|
+
attr_reader :bytecode
|
6
|
+
|
7
|
+
def initialize(source)
|
8
|
+
ast = Parser.new.parse(source)
|
9
|
+
@bytecode = Bytecode.compile(ast.to_nfa)
|
10
|
+
end
|
11
|
+
|
12
|
+
def compile(compiler: Generator::X86)
|
13
|
+
cfg = CFG.build(bytecode)
|
14
|
+
|
15
|
+
singleton_class.undef_method(:match?)
|
16
|
+
define_singleton_method(:match?, &compiler.compile(cfg))
|
17
|
+
end
|
18
|
+
|
19
|
+
def match?(string)
|
20
|
+
Interpreter.new(bytecode).match?(string)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative "lib/regular_expression/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "regular_expression"
|
7
|
+
spec.version = RegularExpression::VERSION
|
8
|
+
spec.authors = ["Kevin Newton"]
|
9
|
+
spec.email = ["kddnewton@gmail.com"]
|
10
|
+
|
11
|
+
spec.summary = "Regular expressions in Ruby"
|
12
|
+
spec.homepage = "https://github.com/kddeisz/regular_expression"
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = Dir.chdir(__dir__) do
|
16
|
+
`git ls-files -z`.split("\x0").reject do |f|
|
17
|
+
f.match(%r{^(test|spec|features)/})
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
spec.require_paths = ["lib"]
|
22
|
+
|
23
|
+
spec.add_dependency "fisk"
|
24
|
+
spec.add_dependency "racc"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,99 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: regular_expression
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Kevin Newton
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2021-07-13 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: fisk
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: racc
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description:
|
42
|
+
email:
|
43
|
+
- kddnewton@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- ".github/dependabot.yml"
|
49
|
+
- ".github/workflows/main.yml"
|
50
|
+
- ".gitignore"
|
51
|
+
- ".rubocop.yml"
|
52
|
+
- CODE_OF_CONDUCT.md
|
53
|
+
- CONTRIBUTING.md
|
54
|
+
- Gemfile
|
55
|
+
- Gemfile.lock
|
56
|
+
- LICENSE
|
57
|
+
- README.md
|
58
|
+
- Rakefile
|
59
|
+
- bin/console
|
60
|
+
- bin/parse
|
61
|
+
- build/.gitignore
|
62
|
+
- lib/regular_expression.rb
|
63
|
+
- lib/regular_expression/ast.rb
|
64
|
+
- lib/regular_expression/bytecode.rb
|
65
|
+
- lib/regular_expression/cfg.rb
|
66
|
+
- lib/regular_expression/compiler/ruby.rb
|
67
|
+
- lib/regular_expression/compiler/x86.rb
|
68
|
+
- lib/regular_expression/interpreter.rb
|
69
|
+
- lib/regular_expression/lexer.rb
|
70
|
+
- lib/regular_expression/nfa.rb
|
71
|
+
- lib/regular_expression/parser.rb
|
72
|
+
- lib/regular_expression/parser.y
|
73
|
+
- lib/regular_expression/pattern.rb
|
74
|
+
- lib/regular_expression/version.rb
|
75
|
+
- regular_expression.gemspec
|
76
|
+
homepage: https://github.com/kddeisz/regular_expression
|
77
|
+
licenses:
|
78
|
+
- MIT
|
79
|
+
metadata: {}
|
80
|
+
post_install_message:
|
81
|
+
rdoc_options: []
|
82
|
+
require_paths:
|
83
|
+
- lib
|
84
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - ">="
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '0'
|
89
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
90
|
+
requirements:
|
91
|
+
- - ">="
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
requirements: []
|
95
|
+
rubygems_version: 3.2.3
|
96
|
+
signing_key:
|
97
|
+
specification_version: 4
|
98
|
+
summary: Regular expressions in Ruby
|
99
|
+
test_files: []
|