rambling-trie 1.0.1 → 2.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/Gemfile +6 -3
- data/Guardfile +3 -1
- data/README.md +30 -12
- data/Rakefile +8 -0
- data/lib/rambling-trie.rb +2 -0
- data/lib/rambling/trie.rb +48 -26
- data/lib/rambling/trie/comparable.rb +6 -3
- data/lib/rambling/trie/compressible.rb +16 -0
- data/lib/rambling/trie/compressor.rb +39 -24
- data/lib/rambling/trie/configuration.rb +3 -1
- data/lib/rambling/trie/configuration/properties.rb +18 -9
- data/lib/rambling/trie/configuration/provider_collection.rb +38 -17
- data/lib/rambling/trie/container.rb +123 -36
- data/lib/rambling/trie/enumerable.rb +6 -4
- data/lib/rambling/trie/inspectable.rb +2 -0
- data/lib/rambling/trie/invalid_operation.rb +3 -1
- data/lib/rambling/trie/nodes.rb +13 -0
- data/lib/rambling/trie/nodes/compressed.rb +98 -0
- data/lib/rambling/trie/nodes/missing.rb +12 -0
- data/lib/rambling/trie/nodes/node.rb +183 -0
- data/lib/rambling/trie/nodes/raw.rb +82 -0
- data/lib/rambling/trie/readers.rb +3 -1
- data/lib/rambling/trie/readers/plain_text.rb +3 -11
- data/lib/rambling/trie/serializers.rb +3 -1
- data/lib/rambling/trie/serializers/file.rb +2 -0
- data/lib/rambling/trie/serializers/marshal.rb +15 -5
- data/lib/rambling/trie/serializers/yaml.rb +21 -5
- data/lib/rambling/trie/serializers/zip.rb +15 -8
- data/lib/rambling/trie/stringifyable.rb +8 -2
- data/lib/rambling/trie/version.rb +3 -1
- data/rambling-trie.gemspec +21 -10
- data/spec/assets/test_words.es_DO.txt +1 -0
- data/spec/integration/rambling/trie_spec.rb +44 -35
- data/spec/lib/rambling/trie/comparable_spec.rb +8 -15
- data/spec/lib/rambling/trie/compressor_spec.rb +90 -13
- data/spec/lib/rambling/trie/configuration/properties_spec.rb +21 -13
- data/spec/lib/rambling/trie/configuration/provider_collection_spec.rb +18 -34
- data/spec/lib/rambling/trie/container_spec.rb +183 -217
- data/spec/lib/rambling/trie/enumerable_spec.rb +14 -9
- data/spec/lib/rambling/trie/inspectable_spec.rb +36 -11
- data/spec/lib/rambling/trie/nodes/compressed_spec.rb +37 -0
- data/spec/lib/rambling/trie/nodes/node_spec.rb +9 -0
- data/spec/lib/rambling/trie/nodes/raw_spec.rb +179 -0
- data/spec/lib/rambling/trie/readers/plain_text_spec.rb +3 -1
- data/spec/lib/rambling/trie/serializers/file_spec.rb +6 -4
- data/spec/lib/rambling/trie/serializers/marshal_spec.rb +5 -7
- data/spec/lib/rambling/trie/serializers/yaml_spec.rb +5 -7
- data/spec/lib/rambling/trie/serializers/zip_spec.rb +18 -20
- data/spec/lib/rambling/trie/stringifyable_spec.rb +14 -11
- data/spec/lib/rambling/trie_spec.rb +18 -11
- data/spec/spec_helper.rb +10 -5
- data/spec/support/config.rb +10 -0
- data/spec/support/helpers/add_word.rb +20 -0
- data/spec/support/helpers/one_line_heredoc.rb +11 -0
- data/spec/support/shared_examples/a_compressible_trie.rb +40 -0
- data/spec/support/shared_examples/a_serializable_trie.rb +10 -6
- data/spec/support/shared_examples/a_serializer.rb +9 -1
- data/spec/support/shared_examples/a_trie_data_structure.rb +2 -0
- data/spec/support/shared_examples/a_trie_node.rb +127 -0
- data/spec/{lib/rambling/trie/compressed_node_spec.rb → support/shared_examples/a_trie_node_implementation.rb} +25 -72
- metadata +40 -33
- data/lib/rambling/trie/compressable.rb +0 -14
- data/lib/rambling/trie/compressed_node.rb +0 -120
- data/lib/rambling/trie/forwardable.rb +0 -21
- data/lib/rambling/trie/missing_node.rb +0 -8
- data/lib/rambling/trie/node.rb +0 -97
- data/lib/rambling/trie/raw_node.rb +0 -96
- data/spec/lib/rambling/trie/node_spec.rb +0 -86
- data/spec/lib/rambling/trie/raw_node_spec.rb +0 -389
- data/spec/support/shared_examples/a_compressable_trie.rb +0 -26
@@ -1,3 +1,5 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
module Rambling
|
2
4
|
module Trie
|
3
5
|
# Provides the String representation behavior for the trie data structure.
|
@@ -6,14 +8,18 @@ module Rambling
|
|
6
8
|
# @return [String] the string representation of the current node.
|
7
9
|
# @raise [InvalidOperation] if node is not terminal or is root.
|
8
10
|
def as_word
|
9
|
-
|
11
|
+
if letter && !terminal?
|
12
|
+
raise Rambling::Trie::InvalidOperation,
|
13
|
+
'Cannot represent branch as a word'
|
14
|
+
end
|
15
|
+
|
10
16
|
to_s
|
11
17
|
end
|
12
18
|
|
13
19
|
# String representation of the current node.
|
14
20
|
# @return [String] the string representation of the current node.
|
15
21
|
def to_s
|
16
|
-
parent.to_s
|
22
|
+
parent.to_s + letter.to_s
|
17
23
|
end
|
18
24
|
end
|
19
25
|
end
|
data/rambling-trie.gemspec
CHANGED
@@ -1,26 +1,37 @@
|
|
1
|
-
#
|
2
|
-
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
$LOAD_PATH.push File.expand_path('../lib', __FILE__)
|
3
4
|
require 'rambling/trie/version'
|
4
5
|
|
5
6
|
Gem::Specification.new do |gem|
|
6
7
|
gem.authors = ['Edgar Gonzalez', 'Lilibeth De La Cruz']
|
7
8
|
gem.email = ['edggonzalezg@gmail.com', 'lilibethdlc@gmail.com']
|
8
|
-
|
9
|
+
|
10
|
+
gem.description = <<~DESCRIPTION.gsub(%r{\s+}, ' ')
|
11
|
+
The Rambling Trie is a Ruby implementation of the trie data structure, which
|
12
|
+
includes compression abilities and is designed to be very fast to traverse.
|
13
|
+
DESCRIPTION
|
14
|
+
|
9
15
|
gem.summary = 'A Ruby implementation of the trie data structure.'
|
10
16
|
gem.homepage = 'http://github.com/gonzedge/rambling-trie'
|
11
17
|
gem.date = Time.now.strftime '%Y-%m-%d'
|
12
18
|
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
19
|
+
executables = `git ls-files -- bin/*`.split "\n"
|
20
|
+
files = `git ls-files -- {lib,*file,*.gemspec,LICENSE*,README*}`.split "\n"
|
21
|
+
test_files = `git ls-files -- {test,spec,features}/*`.split "\n"
|
22
|
+
|
23
|
+
gem.executables = executables.map { |f| File.basename f }
|
24
|
+
gem.files = files
|
25
|
+
gem.test_files = test_files
|
26
|
+
gem.require_paths = %w(lib)
|
17
27
|
|
18
28
|
gem.name = 'rambling-trie'
|
19
29
|
gem.license = 'MIT'
|
20
30
|
gem.version = Rambling::Trie::VERSION
|
21
31
|
gem.platform = Gem::Platform::RUBY
|
32
|
+
gem.required_ruby_version = '~> 2.4'
|
22
33
|
|
23
|
-
gem.add_development_dependency '
|
24
|
-
gem.add_development_dependency '
|
25
|
-
gem.add_development_dependency 'yard', '~> 0.9.
|
34
|
+
gem.add_development_dependency 'rake', '~> 13.0'
|
35
|
+
gem.add_development_dependency 'rspec', '~> 3.9'
|
36
|
+
gem.add_development_dependency 'yard', '~> 0.9.25'
|
26
37
|
end
|
@@ -1,61 +1,72 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require 'spec_helper'
|
4
|
+
require 'zip'
|
2
5
|
|
3
6
|
describe Rambling::Trie do
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
7
|
+
let(:assets_path) { File.join ::SPEC_ROOT, 'assets' }
|
8
|
+
|
9
|
+
context 'when providing words directly' do
|
10
|
+
it_behaves_like 'a compressible trie' do
|
11
|
+
let(:trie) { Rambling::Trie.create }
|
12
|
+
let(:words) { %w(a couple of words for our full trie integration test) }
|
13
|
+
|
14
|
+
before do
|
15
|
+
trie.concat words
|
16
|
+
end
|
8
17
|
end
|
9
18
|
end
|
10
19
|
|
11
|
-
|
12
|
-
it_behaves_like 'a
|
13
|
-
let(:
|
14
|
-
let(:words)
|
15
|
-
|
20
|
+
context 'when provided with words with unicode characters' do
|
21
|
+
it_behaves_like 'a compressible trie' do
|
22
|
+
let(:trie) { Rambling::Trie.create }
|
23
|
+
let(:words) do
|
24
|
+
%w(poquísimas palabras para nuestra prueba de integración completa 🙃)
|
25
|
+
end
|
26
|
+
|
27
|
+
before do
|
28
|
+
trie.concat words
|
29
|
+
end
|
16
30
|
end
|
17
31
|
end
|
18
32
|
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
33
|
+
context 'when provided with a filepath' do
|
34
|
+
let(:trie) { Rambling::Trie.create filepath }
|
35
|
+
let(:words) { File.readlines(filepath).map(&:chomp) }
|
36
|
+
|
37
|
+
context 'with english words' do
|
38
|
+
it_behaves_like 'a compressible trie' do
|
39
|
+
let(:filepath) { File.join assets_path, 'test_words.en_US.txt' }
|
40
|
+
end
|
23
41
|
end
|
24
|
-
end
|
25
42
|
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
let(:trie) { Rambling::Trie.create filepath }
|
43
|
+
context 'with unicode characters' do
|
44
|
+
it_behaves_like 'a compressible trie' do
|
45
|
+
let(:filepath) { File.join assets_path, 'test_words.es_DO.txt' }
|
46
|
+
end
|
31
47
|
end
|
32
48
|
end
|
33
49
|
|
34
|
-
describe '
|
35
|
-
let(:words_filepath) { File.join
|
36
|
-
let(:words) { File.readlines(words_filepath).map
|
37
|
-
let(:trie_to_serialize) { Rambling::Trie.create words_filepath }
|
38
|
-
let(:trie_filename) { File.join ::SPEC_ROOT, '..', 'tmp', 'trie-root' }
|
50
|
+
describe 'dump and load' do
|
51
|
+
let(:words_filepath) { File.join assets_path, 'test_words.en_US.txt' }
|
52
|
+
let(:words) { File.readlines(words_filepath).map(&:chomp) }
|
39
53
|
|
40
54
|
context 'when serialized with Ruby marshal format (default)' do
|
41
55
|
it_behaves_like 'a serializable trie' do
|
42
|
-
let(:
|
43
|
-
let(:
|
44
|
-
let(:serializer) { nil }
|
56
|
+
let(:trie_to_serialize) { Rambling::Trie.create words_filepath }
|
57
|
+
let(:format) { :marshal }
|
45
58
|
end
|
46
59
|
end
|
47
60
|
|
48
61
|
context 'when serialized with YAML' do
|
49
62
|
it_behaves_like 'a serializable trie' do
|
50
|
-
let(:
|
51
|
-
let(:
|
52
|
-
let(:serializer) { nil }
|
63
|
+
let(:trie_to_serialize) { Rambling::Trie.create words_filepath }
|
64
|
+
let(:format) { :yml }
|
53
65
|
end
|
54
66
|
end
|
55
67
|
|
56
68
|
context 'when serialized with zipped Ruby marshal format' do
|
57
69
|
before do
|
58
|
-
require 'zip'
|
59
70
|
@original_on_exists_proc = ::Zip.on_exists_proc
|
60
71
|
@original_continue_on_exists_proc = ::Zip.continue_on_exists_proc
|
61
72
|
::Zip.on_exists_proc = true
|
@@ -63,15 +74,13 @@ describe Rambling::Trie do
|
|
63
74
|
end
|
64
75
|
|
65
76
|
after do
|
66
|
-
require 'zip'
|
67
77
|
::Zip.on_exists_proc = @original_on_exists_proc
|
68
78
|
::Zip.continue_on_exists_proc = @original_continue_on_exists_proc
|
69
79
|
end
|
70
80
|
|
71
81
|
it_behaves_like 'a serializable trie' do
|
72
|
-
let(:
|
73
|
-
let(:
|
74
|
-
let(:serializer) { nil }
|
82
|
+
let(:trie_to_serialize) { Rambling::Trie.create words_filepath }
|
83
|
+
let(:format) { 'marshal.zip' }
|
75
84
|
end
|
76
85
|
end
|
77
86
|
end
|
@@ -1,9 +1,11 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require 'spec_helper'
|
2
4
|
|
3
5
|
describe Rambling::Trie::Comparable do
|
4
6
|
describe '#==' do
|
5
|
-
let(:node_1) { Rambling::Trie::
|
6
|
-
let(:node_2) { Rambling::Trie::
|
7
|
+
let(:node_1) { Rambling::Trie::Nodes::Raw.new }
|
8
|
+
let(:node_2) { Rambling::Trie::Nodes::Raw.new }
|
7
9
|
|
8
10
|
context 'when the nodes do not have the same letter' do
|
9
11
|
before do
|
@@ -67,37 +69,28 @@ describe Rambling::Trie::Comparable do
|
|
67
69
|
context 'when the nodes have the same letter and the same children' do
|
68
70
|
before do
|
69
71
|
node_1.letter = :t
|
70
|
-
node_1
|
71
|
-
node_1.add 'hree'
|
72
|
-
node_1.add 'hings'
|
72
|
+
add_words node_1, %w(hese hree hings)
|
73
73
|
|
74
74
|
node_2.letter = :t
|
75
|
-
node_2
|
76
|
-
node_2.add 'hree'
|
77
|
-
node_2.add 'hings'
|
75
|
+
add_words node_2, %w(hese hree hings)
|
78
76
|
end
|
79
77
|
|
80
78
|
it 'returns true' do
|
81
79
|
expect(node_1).to eq node_2
|
82
|
-
expect(node_1[:h][:e][:s][:e]).to eq node_2[:h][:e][:s][:e]
|
83
80
|
end
|
84
81
|
end
|
85
82
|
|
86
83
|
context 'when the nodes have the same letter but different children' do
|
87
84
|
before do
|
88
85
|
node_1.letter = :t
|
89
|
-
node_1
|
90
|
-
node_1.add 'wo'
|
86
|
+
add_words node_1, %w(hese wo)
|
91
87
|
|
92
88
|
node_2.letter = :t
|
93
|
-
node_2
|
94
|
-
node_2.add 'hree'
|
95
|
-
node_2.add 'hings'
|
89
|
+
add_words node_2, %w(hese hree hings)
|
96
90
|
end
|
97
91
|
|
98
92
|
it 'returns false' do
|
99
93
|
expect(node_1).not_to eq node_2
|
100
|
-
expect(node_1[:h][:e][:s][:e]).to eq node_2[:h][:e][:s][:e]
|
101
94
|
end
|
102
95
|
end
|
103
96
|
end
|
@@ -1,31 +1,108 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require 'spec_helper'
|
2
4
|
|
3
5
|
describe Rambling::Trie::Compressor do
|
4
6
|
let(:compressor) { Rambling::Trie::Compressor.new }
|
5
7
|
|
6
8
|
describe '#compress' do
|
7
|
-
let(:
|
8
|
-
|
9
|
-
|
9
|
+
let(:node) { Rambling::Trie::Nodes::Raw.new }
|
10
|
+
|
11
|
+
it 'compresses the node' do
|
12
|
+
add_words node, %w(a few words hello hell)
|
13
|
+
compressed = compressor.compress node
|
14
|
+
|
15
|
+
expect(compressed.children_tree.keys).to eq %i(a f w h)
|
16
|
+
end
|
17
|
+
|
18
|
+
context 'with at least one word' do
|
19
|
+
before do
|
20
|
+
add_words node, %w(all the words)
|
21
|
+
end
|
22
|
+
|
23
|
+
it 'keeps the node letter nil' do
|
24
|
+
compressed = compressor.compress node
|
25
|
+
|
26
|
+
expect(compressed.letter).to be_nil
|
27
|
+
end
|
10
28
|
end
|
11
29
|
|
12
|
-
|
13
|
-
|
30
|
+
context 'with a single word' do
|
31
|
+
before do
|
32
|
+
add_word node, 'all'
|
33
|
+
end
|
34
|
+
|
35
|
+
it 'compresses into a single node without children' do
|
36
|
+
compressed = compressor.compress node
|
37
|
+
|
38
|
+
expect(compressed[:a].letter).to eq :all
|
39
|
+
expect(compressed[:a].children.size).to eq 0
|
40
|
+
expect(compressed[:a]).to be_terminal
|
41
|
+
expect(compressed[:a]).to be_compressed
|
42
|
+
end
|
14
43
|
end
|
15
44
|
|
16
|
-
|
17
|
-
|
45
|
+
context 'with two words' do
|
46
|
+
before do
|
47
|
+
add_words node, %w(all ask)
|
48
|
+
end
|
49
|
+
|
50
|
+
it 'compresses into corresponding three nodes' do
|
51
|
+
compressed = compressor.compress node
|
52
|
+
|
53
|
+
expect(compressed[:a].letter).to eq :a
|
54
|
+
expect(compressed[:a].children.size).to eq 2
|
55
|
+
|
56
|
+
expect(compressed[:a][:l].letter).to eq :ll
|
57
|
+
expect(compressed[:a][:s].letter).to eq :sk
|
58
|
+
|
59
|
+
expect(compressed[:a][:l].children.size).to eq 0
|
60
|
+
expect(compressed[:a][:s].children.size).to eq 0
|
18
61
|
|
19
|
-
|
20
|
-
|
21
|
-
|
62
|
+
expect(compressed[:a][:l]).to be_terminal
|
63
|
+
expect(compressed[:a][:s]).to be_terminal
|
64
|
+
|
65
|
+
expect(compressed[:a][:l]).to be_compressed
|
66
|
+
expect(compressed[:a][:s]).to be_compressed
|
22
67
|
end
|
23
68
|
end
|
24
69
|
|
25
|
-
it '
|
26
|
-
|
70
|
+
it 'reassigns the parent nodes correctly' do
|
71
|
+
add_words node, %w(repay rest repaint)
|
72
|
+
compressed = compressor.compress node
|
73
|
+
|
74
|
+
expect(compressed[:r].letter).to eq :re
|
75
|
+
expect(compressed[:r].parent).to eq compressed
|
76
|
+
expect(compressed[:r].children.size).to eq 2
|
77
|
+
|
78
|
+
expect(compressed[:r][:p].letter).to eq :pa
|
79
|
+
expect(compressed[:r][:p].parent).to eq compressed[:r]
|
80
|
+
expect(compressed[:r][:p].children.size).to eq 2
|
81
|
+
|
82
|
+
expect(compressed[:r][:s].letter).to eq :st
|
83
|
+
expect(compressed[:r][:s].parent).to eq compressed[:r]
|
84
|
+
expect(compressed[:r][:s].children.size).to eq 0
|
85
|
+
|
86
|
+
expect(compressed[:r][:p][:y].letter).to eq :y
|
87
|
+
expect(compressed[:r][:p][:y].parent).to eq compressed[:r][:p]
|
88
|
+
expect(compressed[:r][:p][:y].children.size).to eq 0
|
89
|
+
|
90
|
+
expect(compressed[:r][:p][:i].letter).to eq :int
|
91
|
+
expect(compressed[:r][:p][:i].parent).to eq compressed[:r][:p]
|
92
|
+
expect(compressed[:r][:p][:i].children.size).to eq 0
|
93
|
+
end
|
94
|
+
|
95
|
+
it 'does not compress terminal nodes' do
|
96
|
+
add_words node, %w(you your yours)
|
97
|
+
compressed = compressor.compress node
|
98
|
+
|
99
|
+
expect(compressed[:y].letter).to eq :you
|
100
|
+
|
101
|
+
expect(compressed[:y][:r].letter).to eq :r
|
102
|
+
expect(compressed[:y][:r]).to be_compressed
|
27
103
|
|
28
|
-
expect(
|
104
|
+
expect(compressed[:y][:r][:s].letter).to eq :s
|
105
|
+
expect(compressed[:y][:r][:s]).to be_compressed
|
29
106
|
end
|
30
107
|
end
|
31
108
|
end
|
@@ -1,3 +1,5 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require 'spec_helper'
|
2
4
|
|
3
5
|
describe Rambling::Trie::Configuration::Properties do
|
@@ -6,27 +8,33 @@ describe Rambling::Trie::Configuration::Properties do
|
|
6
8
|
describe '.new' do
|
7
9
|
it 'configures the serializers' do
|
8
10
|
serializers = properties.serializers
|
9
|
-
expect(serializers.keys).to match_array %i(marshal yaml yml zip)
|
10
11
|
|
11
|
-
expect(serializers
|
12
|
-
expect(serializers
|
13
|
-
|
14
|
-
|
12
|
+
expect(serializers.formats).to match_array %i(marshal yaml yml zip)
|
13
|
+
expect(serializers.providers.to_a).to match_array [
|
14
|
+
[:marshal, Rambling::Trie::Serializers::Marshal],
|
15
|
+
[:yaml, Rambling::Trie::Serializers::Yaml],
|
16
|
+
[:yml, Rambling::Trie::Serializers::Yaml],
|
17
|
+
[:zip, Rambling::Trie::Serializers::Zip],
|
18
|
+
]
|
15
19
|
end
|
16
20
|
|
17
21
|
it 'configures the readers' do
|
18
22
|
readers = properties.readers
|
19
|
-
expect(readers.keys).to match_array %i(txt)
|
20
23
|
|
21
|
-
expect(readers
|
24
|
+
expect(readers.formats).to match_array %i(txt)
|
25
|
+
expect(readers.providers.to_a).to match_array [
|
26
|
+
[:txt, Rambling::Trie::Readers::PlainText],
|
27
|
+
]
|
22
28
|
end
|
23
29
|
|
24
30
|
it 'configures the compressor' do
|
25
|
-
|
31
|
+
compressor = properties.compressor
|
32
|
+
expect(compressor).to be_instance_of Rambling::Trie::Compressor
|
26
33
|
end
|
27
34
|
|
28
35
|
it 'configures the root_builder' do
|
29
|
-
|
36
|
+
root = properties.root_builder.call
|
37
|
+
expect(root).to be_instance_of Rambling::Trie::Nodes::Raw
|
30
38
|
end
|
31
39
|
end
|
32
40
|
|
@@ -37,13 +45,13 @@ describe Rambling::Trie::Configuration::Properties do
|
|
37
45
|
end
|
38
46
|
|
39
47
|
it 'resets the serializers and readers to initial values' do
|
40
|
-
expect(properties.serializers.
|
41
|
-
expect(properties.readers.
|
48
|
+
expect(properties.serializers.formats).to include :test
|
49
|
+
expect(properties.readers.formats).to include :test
|
42
50
|
|
43
51
|
properties.reset
|
44
52
|
|
45
|
-
expect(properties.serializers.
|
46
|
-
expect(properties.readers.
|
53
|
+
expect(properties.serializers.formats).not_to include :test
|
54
|
+
expect(properties.readers.formats).not_to include :test
|
47
55
|
end
|
48
56
|
end
|
49
57
|
end
|