kleene 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.rspec +3 -0
- data/Gemfile +12 -0
- data/Gemfile.lock +117 -0
- data/LICENSE +21 -0
- data/README.md +21 -0
- data/Rakefile +8 -0
- data/build.ops +63 -0
- data/kleene.gemspec +39 -0
- data/lib/kleene/dfa.rb +258 -0
- data/lib/kleene/dsl.rb +263 -0
- data/lib/kleene/kleene.rb +88 -0
- data/lib/kleene/multi_match_dfa.rb +308 -0
- data/lib/kleene/nfa.rb +304 -0
- data/lib/kleene/patches.rb +23 -0
- data/lib/kleene/version.rb +3 -0
- data/lib/kleene.rb +17 -0
- metadata +76 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 0c062445eeb37aa9a123c09e8d682b3c6514be3842a4f63b821ab320daee958b
|
4
|
+
data.tar.gz: 902a5fcc8d767bbb0c3b97e931dba5b72e07f9ef0ec8540c2420675ecd7bc0f7
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 54b677033bbae4ced31b75bf3b3130a123017982fb9959a957360a9d8a10a4b50d03533bf27e3fbfafc7052574388e2adba0eeae63beee9dc5c7c6cabed429c0
|
7
|
+
data.tar.gz: 9d0b6d4715254e3f544e4f2ed220103f9d092063ab58a7781688ce035810662f6a441a899660ff9496776a5052548251174aeab3107515530dbe106486d27175
|
data/.rspec
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,117 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
kleene (0.1.0)
|
5
|
+
activesupport (~> 7.1)
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: https://rubygems.org/
|
9
|
+
specs:
|
10
|
+
activesupport (7.1.1)
|
11
|
+
base64
|
12
|
+
bigdecimal
|
13
|
+
concurrent-ruby (~> 1.0, >= 1.0.2)
|
14
|
+
connection_pool (>= 2.2.5)
|
15
|
+
drb
|
16
|
+
i18n (>= 1.6, < 2)
|
17
|
+
minitest (>= 5.1)
|
18
|
+
mutex_m
|
19
|
+
tzinfo (~> 2.0)
|
20
|
+
ast (2.4.2)
|
21
|
+
backport (1.2.0)
|
22
|
+
base64 (0.1.1)
|
23
|
+
benchmark (0.2.1)
|
24
|
+
bigdecimal (3.1.4)
|
25
|
+
concurrent-ruby (1.2.2)
|
26
|
+
connection_pool (2.4.1)
|
27
|
+
diff-lcs (1.5.0)
|
28
|
+
drb (2.1.1)
|
29
|
+
ruby2_keywords
|
30
|
+
e2mmap (0.1.0)
|
31
|
+
i18n (1.14.1)
|
32
|
+
concurrent-ruby (~> 1.0)
|
33
|
+
jaro_winkler (1.5.6)
|
34
|
+
json (2.6.3)
|
35
|
+
kramdown (2.4.0)
|
36
|
+
rexml
|
37
|
+
kramdown-parser-gfm (1.1.0)
|
38
|
+
kramdown (~> 2.0)
|
39
|
+
language_server-protocol (3.17.0.3)
|
40
|
+
minitest (5.20.0)
|
41
|
+
mutex_m (0.1.2)
|
42
|
+
nokogiri (1.15.4-x86_64-linux)
|
43
|
+
racc (~> 1.4)
|
44
|
+
parallel (1.23.0)
|
45
|
+
parser (3.2.2.4)
|
46
|
+
ast (~> 2.4.1)
|
47
|
+
racc
|
48
|
+
racc (1.7.2)
|
49
|
+
rainbow (3.1.1)
|
50
|
+
rake (13.1.0)
|
51
|
+
rbs (2.8.4)
|
52
|
+
regexp_parser (2.8.2)
|
53
|
+
reverse_markdown (2.1.1)
|
54
|
+
nokogiri
|
55
|
+
rexml (3.2.6)
|
56
|
+
rspec (3.12.0)
|
57
|
+
rspec-core (~> 3.12.0)
|
58
|
+
rspec-expectations (~> 3.12.0)
|
59
|
+
rspec-mocks (~> 3.12.0)
|
60
|
+
rspec-core (3.12.2)
|
61
|
+
rspec-support (~> 3.12.0)
|
62
|
+
rspec-expectations (3.12.3)
|
63
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
64
|
+
rspec-support (~> 3.12.0)
|
65
|
+
rspec-mocks (3.12.6)
|
66
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
67
|
+
rspec-support (~> 3.12.0)
|
68
|
+
rspec-support (3.12.1)
|
69
|
+
rubocop (1.57.2)
|
70
|
+
json (~> 2.3)
|
71
|
+
language_server-protocol (>= 3.17.0)
|
72
|
+
parallel (~> 1.10)
|
73
|
+
parser (>= 3.2.2.4)
|
74
|
+
rainbow (>= 2.2.2, < 4.0)
|
75
|
+
regexp_parser (>= 1.8, < 3.0)
|
76
|
+
rexml (>= 3.2.5, < 4.0)
|
77
|
+
rubocop-ast (>= 1.28.1, < 2.0)
|
78
|
+
ruby-progressbar (~> 1.7)
|
79
|
+
unicode-display_width (>= 2.4.0, < 3.0)
|
80
|
+
rubocop-ast (1.30.0)
|
81
|
+
parser (>= 3.2.1.0)
|
82
|
+
ruby-progressbar (1.13.0)
|
83
|
+
ruby2_keywords (0.0.5)
|
84
|
+
solargraph (0.49.0)
|
85
|
+
backport (~> 1.2)
|
86
|
+
benchmark
|
87
|
+
bundler (~> 2.0)
|
88
|
+
diff-lcs (~> 1.4)
|
89
|
+
e2mmap
|
90
|
+
jaro_winkler (~> 1.5)
|
91
|
+
kramdown (~> 2.3)
|
92
|
+
kramdown-parser-gfm (~> 1.1)
|
93
|
+
parser (~> 3.0)
|
94
|
+
rbs (~> 2.0)
|
95
|
+
reverse_markdown (~> 2.0)
|
96
|
+
rubocop (~> 1.38)
|
97
|
+
thor (~> 1.0)
|
98
|
+
tilt (~> 2.0)
|
99
|
+
yard (~> 0.9, >= 0.9.24)
|
100
|
+
thor (1.3.0)
|
101
|
+
tilt (2.3.0)
|
102
|
+
tzinfo (2.0.6)
|
103
|
+
concurrent-ruby (~> 1.0)
|
104
|
+
unicode-display_width (2.5.0)
|
105
|
+
yard (0.9.34)
|
106
|
+
|
107
|
+
PLATFORMS
|
108
|
+
x86_64-linux
|
109
|
+
|
110
|
+
DEPENDENCIES
|
111
|
+
kleene!
|
112
|
+
rake (~> 13.0)
|
113
|
+
rspec (~> 3.0)
|
114
|
+
solargraph
|
115
|
+
|
116
|
+
BUNDLED WITH
|
117
|
+
2.4.10
|
data/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2023 David Ellis
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# kleene
|
2
|
+
|
3
|
+
kleene is a library for building regular expression recognition automata - nfas, dfas, and some specialty structures.
|
4
|
+
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
Install the gem and add to the application's Gemfile by executing:
|
9
|
+
|
10
|
+
$ bundle add kleene
|
11
|
+
|
12
|
+
If bundler is not being used to manage dependencies, install the gem by executing:
|
13
|
+
|
14
|
+
$ gem install kleene
|
15
|
+
|
16
|
+
|
17
|
+
## Usage
|
18
|
+
|
19
|
+
```ruby
|
20
|
+
require "kleene"
|
21
|
+
```
|
data/Rakefile
ADDED
data/build.ops
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
params:
|
2
|
+
version: string
|
3
|
+
|
4
|
+
imports:
|
5
|
+
core: "opswalrus/core"
|
6
|
+
|
7
|
+
...
|
8
|
+
|
9
|
+
# when you run this script, it should do something like:
|
10
|
+
# ~/sync/projects/kleene-rb
|
11
|
+
# ❯ ops run build.ops version:1.0.0
|
12
|
+
# Write version.rb for version 1.0.0
|
13
|
+
# [localhost] Build gem: gem build opswalrus.gemspec
|
14
|
+
# [localhost] Check whether Bitwarden is locked or not: bw status
|
15
|
+
# [localhost] Get Rubygems OTP: bw get totp Rubygems
|
16
|
+
# [localhost] Push gem: gem push opswalrus-1.0.0.gem
|
17
|
+
# [localhost] Build docker image: docker build -t opswalrus/ops:1.0.0 .
|
18
|
+
|
19
|
+
# ~/sync/projects/ops/opswalrus on main via 💎 v3.2.2 took 44s
|
20
|
+
|
21
|
+
|
22
|
+
version = params.version
|
23
|
+
|
24
|
+
exit 1, "version parameter must be specified" unless version
|
25
|
+
|
26
|
+
template = <<TEMPLATE
|
27
|
+
module Kleene
|
28
|
+
VERSION = "{{ version }}"
|
29
|
+
end
|
30
|
+
TEMPLATE
|
31
|
+
|
32
|
+
puts "Write version.rb for version #{version}"
|
33
|
+
core.template.write template: template,
|
34
|
+
variables: {version: version},
|
35
|
+
to: "./lib/kleene/version.rb"
|
36
|
+
|
37
|
+
sh("Build gem") { 'gem build kleene.gemspec' }
|
38
|
+
|
39
|
+
sh("Commit Gemfile.lock and version.rb and git push changes") { 'git commit -am "gem {{ version }}" && git push' }
|
40
|
+
|
41
|
+
# bw_status_output = sh("Check whether Bitwarden is locked or not") { 'bw status' }
|
42
|
+
is_unlocked = sh? "Check whether Bitwarden is locked or not",
|
43
|
+
'rbw unlocked'
|
44
|
+
# the `bw status`` command currently exhibits an error in which it emits 'mac failed.' some number of times, so we need to filter that out
|
45
|
+
# see:
|
46
|
+
# - https://community.bitwarden.com/t/what-does-mac-failed-mean-exactly/29208
|
47
|
+
# - https://github.com/bitwarden/cli/issues/88
|
48
|
+
# - https://github.com/vwxyzjn/portwarden/issues/22
|
49
|
+
# ❯ bw status
|
50
|
+
# mac failed.
|
51
|
+
# {"serverUrl":"...","lastSync":"2023-08-17T19:14:09.384Z","userEmail":"...","userId":"...","status":"locked"}
|
52
|
+
# bw_status_output = bw_status_output.gsub('mac failed.', '').strip
|
53
|
+
# bw_status_json = bw_status_output.parse_json
|
54
|
+
|
55
|
+
# if bw_status_json['status'] != 'unlocked'
|
56
|
+
# exit 1, "Bitwarden is not unlocked. Please unlock bitwarden with: bw unlock"
|
57
|
+
# end
|
58
|
+
exit 1, "Bitwarden is not unlocked. Please unlock bitwarden with: rbw unlock" unless is_unlocked
|
59
|
+
|
60
|
+
# totp = sh("Get Rubygems OTP") { 'bw get totp Rubygems' }
|
61
|
+
totp = sh "Get Rubygems OTP",
|
62
|
+
'rbw get -f totp Rubygems'
|
63
|
+
sh("Push gem", input: {/You have enabled multi-factor authentication. Please enter OTP code./ => "#{totp}\n"}) { 'gem push kleene-{{ version }}.gem' }
|
data/kleene.gemspec
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative "lib/kleene/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "kleene"
|
7
|
+
spec.version = Kleene::VERSION
|
8
|
+
spec.authors = ["David Ellis"]
|
9
|
+
spec.email = ["david@conquerthelawn.com"]
|
10
|
+
|
11
|
+
spec.summary = "kleene is a library for building regular expression recognition automata"
|
12
|
+
spec.description = "kleene is a library for building regular expression recognition automata - nfas, dfas, and some specialty structures."
|
13
|
+
spec.homepage = "https://github.com/davidkellis/kleene-rb"
|
14
|
+
spec.license = "MIT"
|
15
|
+
spec.required_ruby_version = ">= 3.0.0"
|
16
|
+
|
17
|
+
# spec.metadata["allowed_push_host"] = "TODO: Set to your gem server 'https://example.com'"
|
18
|
+
|
19
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
20
|
+
spec.metadata["source_code_uri"] = "https://github.com/davidkellis/kleene-rb"
|
21
|
+
# spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
|
22
|
+
|
23
|
+
# Specify which files should be added to the gem when it is released.
|
24
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
25
|
+
spec.files = Dir.chdir(__dir__) do
|
26
|
+
`git ls-files -z`.split("\x0").reject do |f|
|
27
|
+
(File.expand_path(f) == __FILE__) || f.start_with?(*%w[bin/ test/ spec/ features/ .git .circleci appveyor])
|
28
|
+
end
|
29
|
+
end
|
30
|
+
spec.bindir = "exe"
|
31
|
+
spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
|
32
|
+
spec.require_paths = ["lib"]
|
33
|
+
|
34
|
+
# Uncomment to register a new dependency of your gem
|
35
|
+
spec.add_dependency "activesupport", "~> 7.1"
|
36
|
+
|
37
|
+
# For more information and examples about making a new gem, check out our
|
38
|
+
# guide at: https://bundler.io/guides/creating_gem.html
|
39
|
+
end
|
data/lib/kleene/dfa.rb
ADDED
@@ -0,0 +1,258 @@
|
|
1
|
+
module Kleene
|
2
|
+
class DFATransition
|
3
|
+
attr_accessor :token # : Char
|
4
|
+
attr_accessor :from # : State
|
5
|
+
attr_accessor :to # : State
|
6
|
+
|
7
|
+
def initialize(token, from_state, to_state)
|
8
|
+
@token = token
|
9
|
+
@from = from_state
|
10
|
+
@to = to_state
|
11
|
+
end
|
12
|
+
|
13
|
+
def accept?(input)
|
14
|
+
@token == input
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
# ->(transition : DFATransition, token : Char, token_index : Int32) : Nil { ... }
|
19
|
+
# alias DFATransitionCallback = Proc(DFATransition, Char, Int32, Nil)
|
20
|
+
|
21
|
+
class DFA
|
22
|
+
attr_accessor :alphabet # : Set(Char)
|
23
|
+
attr_accessor :states # : Set(State)
|
24
|
+
attr_accessor :start_state # : State
|
25
|
+
attr_accessor :current_state # : State
|
26
|
+
attr_accessor :transitions # : Hash(State, Hash(Char, DFATransition))
|
27
|
+
attr_accessor :final_states # : Set(State)
|
28
|
+
attr_accessor :dfa_state_to_nfa_state_sets # : Hash(State, Set(State)) # this map contains (dfa_state => nfa_state_set) pairs
|
29
|
+
attr_accessor :nfa_state_to_dfa_state_sets # : Hash(State, Set(State)) # this map contains (nfa_state => dfa_state_set) pairs
|
30
|
+
attr_accessor :transition_callbacks # : Hash(DFATransition, DFATransitionCallback)
|
31
|
+
attr_accessor :transition_callbacks_per_destination_state # : Hash(State, DFATransitionCallback)
|
32
|
+
# @origin_nfa : NFA?
|
33
|
+
# @error_states : Set(State)?
|
34
|
+
# @regex_pattern : String?
|
35
|
+
|
36
|
+
def initialize(start_state, alphabet = DEFAULT_ALPHABET, transitions = Hash.new, dfa_state_to_nfa_state_sets = Hash.new, transition_callbacks = nil, origin_nfa: nil)
|
37
|
+
@start_state = start_state
|
38
|
+
@current_state = start_state
|
39
|
+
@transitions = transitions
|
40
|
+
@dfa_state_to_nfa_state_sets = dfa_state_to_nfa_state_sets
|
41
|
+
|
42
|
+
@alphabet = alphabet + all_transitions.map(&:token)
|
43
|
+
|
44
|
+
@states = reachable_states(@start_state)
|
45
|
+
@final_states = Set.new
|
46
|
+
|
47
|
+
@nfa_state_to_dfa_state_sets = Hash.new
|
48
|
+
@dfa_state_to_nfa_state_sets.each do |dfa_state, nfa_state_set|
|
49
|
+
nfa_state_set.each do |nfa_state|
|
50
|
+
dfa_state_set = @nfa_state_to_dfa_state_sets[nfa_state] ||= Set.new
|
51
|
+
dfa_state_set << dfa_state
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
@transition_callbacks = transition_callbacks || Hash.new
|
56
|
+
@transition_callbacks_per_destination_state = Hash.new
|
57
|
+
|
58
|
+
@origin_nfa = origin_nfa
|
59
|
+
|
60
|
+
update_final_states
|
61
|
+
reset_current_state
|
62
|
+
end
|
63
|
+
|
64
|
+
def origin_nfa
|
65
|
+
@origin_nfa || raise("This DFA was not created from an NFA, therefore it has no origin_nfa.")
|
66
|
+
end
|
67
|
+
|
68
|
+
def error_states
|
69
|
+
@error_states ||= @states.select {|s| s.error? }.to_set
|
70
|
+
end
|
71
|
+
|
72
|
+
def clear_error_states
|
73
|
+
@error_states = nil
|
74
|
+
end
|
75
|
+
|
76
|
+
def all_transitions() # : Array(DFATransition)
|
77
|
+
transitions.flat_map {|state, char_transition_map| char_transition_map.values }
|
78
|
+
end
|
79
|
+
|
80
|
+
def on_transition(transition, &blk)
|
81
|
+
@transition_callbacks[transition] = blk
|
82
|
+
end
|
83
|
+
|
84
|
+
def on_transition_to(state, &blk)
|
85
|
+
@transition_callbacks_per_destination_state[state] = blk
|
86
|
+
end
|
87
|
+
|
88
|
+
def shallow_clone
|
89
|
+
DFA.new(start_state, alphabet, transitions, dfa_state_to_nfa_state_sets, transition_callbacks, origin_nfa: origin_nfa).set_regex_pattern(regex_pattern)
|
90
|
+
end
|
91
|
+
|
92
|
+
# transition callbacks are not copied beacuse it is assumed that the state transition callbacks may be stateful and reference structures or states that only exist in `self`, but not the cloned copy.
|
93
|
+
def deep_clone
|
94
|
+
old_states = @states.to_a
|
95
|
+
new_states = old_states.map(&:dup)
|
96
|
+
state_mapping = old_states.zip(new_states).to_h
|
97
|
+
transition_mapping = Hash.new
|
98
|
+
new_transitions = transitions.map do |state, char_transition_map|
|
99
|
+
[
|
100
|
+
state_mapping[state],
|
101
|
+
char_transition_map.map do |char, old_transition|
|
102
|
+
new_transition = DFATransition.new(old_transition.token, state_mapping[old_transition.from], state_mapping[old_transition.to])
|
103
|
+
transition_mapping[old_transition] = new_transition
|
104
|
+
[char, new_transition]
|
105
|
+
end.to_h
|
106
|
+
]
|
107
|
+
end.to_h
|
108
|
+
# new_transition_callbacks = transition_callbacks.map do |transition, callback|
|
109
|
+
# {
|
110
|
+
# transition_mapping[transition],
|
111
|
+
# callback
|
112
|
+
# }
|
113
|
+
# end.to_h
|
114
|
+
|
115
|
+
new_dfa_state_to_nfa_state_sets = dfa_state_to_nfa_state_sets.map {|dfa_state, nfa_state_set| [state_mapping[dfa_state], nfa_state_set] }.to_h
|
116
|
+
|
117
|
+
DFA.new(state_mapping[@start_state], @alphabet.clone, new_transitions, new_dfa_state_to_nfa_state_sets, origin_nfa: origin_nfa).set_regex_pattern(regex_pattern)
|
118
|
+
end
|
119
|
+
|
120
|
+
def update_final_states
|
121
|
+
@final_states = @states.select {|s| s.final? }.to_set
|
122
|
+
end
|
123
|
+
|
124
|
+
def reset_current_state
|
125
|
+
@current_state = @start_state
|
126
|
+
end
|
127
|
+
|
128
|
+
def add_transition(token, from_state, to_state)
|
129
|
+
@alphabet << token # alphabet is a set, so there will be no duplications
|
130
|
+
@states << to_state # states is a set, so there will be no duplications (to_state should be the only new state)
|
131
|
+
new_transition = DFATransition.new(token, from_state, to_state)
|
132
|
+
@transitions[from_state][token] = new_transition
|
133
|
+
new_transition
|
134
|
+
end
|
135
|
+
|
136
|
+
def match?(input)
|
137
|
+
reset_current_state
|
138
|
+
|
139
|
+
input.each_char.with_index do |char, index|
|
140
|
+
handle_token!(char, index)
|
141
|
+
end
|
142
|
+
|
143
|
+
if accept?
|
144
|
+
MatchRef.new(input, 0...input.size)
|
145
|
+
end
|
146
|
+
end
|
147
|
+
|
148
|
+
# Returns an array of matches found in the input string, each of which begins at the offset input_start_offset
|
149
|
+
def matches_at_offset(input, input_start_offset)
|
150
|
+
reset_current_state
|
151
|
+
|
152
|
+
matches = []
|
153
|
+
(input_start_offset...input.size).each do |offset|
|
154
|
+
token = input[offset]
|
155
|
+
handle_token!(token, offset)
|
156
|
+
if accept?
|
157
|
+
matches << MatchRef.new(input, input_start_offset..offset)
|
158
|
+
end
|
159
|
+
end
|
160
|
+
matches
|
161
|
+
end
|
162
|
+
|
163
|
+
# Returns an array of matches found anywhere in the input string
|
164
|
+
def matches(input)
|
165
|
+
(0...input.size).reduce([]) do |memo, offset|
|
166
|
+
memo + matches_at_offset(input, offset)
|
167
|
+
end
|
168
|
+
end
|
169
|
+
|
170
|
+
# accept an input token and transition to the next state in the state machine
|
171
|
+
def handle_token!(input_token, token_index)
|
172
|
+
@current_state = next_state(@current_state, input_token, token_index)
|
173
|
+
end
|
174
|
+
|
175
|
+
def accept?
|
176
|
+
@current_state.final?
|
177
|
+
end
|
178
|
+
|
179
|
+
def error?
|
180
|
+
@current_state.error?
|
181
|
+
end
|
182
|
+
|
183
|
+
# def terminal?
|
184
|
+
# accept? || error?
|
185
|
+
# end
|
186
|
+
|
187
|
+
# if the DFA is currently in a final state, then we look up the associated NFA states that were also final, and return them
|
188
|
+
# def accepting_nfa_states : Set(State)
|
189
|
+
# if accept?
|
190
|
+
# dfa_state_to_nfa_state_sets[@current_state].select(&:final?).to_set
|
191
|
+
# else
|
192
|
+
# Set.new
|
193
|
+
# end
|
194
|
+
# end
|
195
|
+
|
196
|
+
# this function transitions from state to state on an input token
|
197
|
+
def next_state(from_state, input_token, token_index)
|
198
|
+
transition = @transitions[from_state][input_token] || raise("No DFA transition found. Input token #{input_token} not in DFA alphabet.")
|
199
|
+
|
200
|
+
# invoke the relevant transition callback function
|
201
|
+
transition_callbacks[transition].try {|callback_fn| callback_fn.call(transition, input_token, token_index) }
|
202
|
+
transition_callbacks_per_destination_state[transition.to].try {|callback_fn| callback_fn.call(transition, input_token, token_index) }
|
203
|
+
|
204
|
+
transition.to
|
205
|
+
end
|
206
|
+
|
207
|
+
# Returns a set of State objects which are reachable through any transition path from the DFA's start_state.
|
208
|
+
def reachable_states(start_state)
|
209
|
+
visited_states = Set.new()
|
210
|
+
unvisited_states = Set[start_state]
|
211
|
+
while !unvisited_states.empty?
|
212
|
+
outbound_transitions = unvisited_states.flat_map {|state| @transitions[state].try(&:values) || Array.new }
|
213
|
+
destination_states = outbound_transitions.map(&:to).to_set
|
214
|
+
visited_states.merge(unvisited_states) # add the unvisited states to the visited_states
|
215
|
+
unvisited_states = destination_states - visited_states
|
216
|
+
end
|
217
|
+
visited_states
|
218
|
+
end
|
219
|
+
|
220
|
+
# this is currently broken
|
221
|
+
# def to_nfa
|
222
|
+
# dfa = self.deep_clone
|
223
|
+
# NFA.new(dfa.start_state, dfa.alphabet.clone, dfa.transitions)
|
224
|
+
# # todo: add all of this machine's transitions to the new machine
|
225
|
+
# # @transitions.each {|t| nfa.add_transition(t.token, t.from, t.to) }
|
226
|
+
# # nfa
|
227
|
+
# end
|
228
|
+
|
229
|
+
def to_s(verbose = false)
|
230
|
+
if verbose
|
231
|
+
retval = states.map(&:to_s).join("\n")
|
232
|
+
retval += "\n"
|
233
|
+
all_transitions.each do |t|
|
234
|
+
retval += "#{t.from.id} -> #{t.token} -> #{t.to.id}\n"
|
235
|
+
end
|
236
|
+
retval
|
237
|
+
else
|
238
|
+
regex_pattern
|
239
|
+
end
|
240
|
+
end
|
241
|
+
|
242
|
+
# This is an implementation of the "Reducing a DFA to a Minimal DFA" algorithm presented here: http://web.cecs.pdx.edu/~harry/compilers/slides/LexicalPart4.pdf
|
243
|
+
# This implements Hopcroft's algorithm as presented on page 142 of the first edition of the dragon book.
|
244
|
+
def minimize!
|
245
|
+
# todo: I'll implement this when I need it
|
246
|
+
end
|
247
|
+
|
248
|
+
def set_regex_pattern(pattern)
|
249
|
+
@regex_pattern = pattern
|
250
|
+
self
|
251
|
+
end
|
252
|
+
|
253
|
+
def regex_pattern
|
254
|
+
@regex_pattern || "<<empty>>"
|
255
|
+
end
|
256
|
+
end
|
257
|
+
|
258
|
+
end
|