suffix_tree 0.0.1
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/lib/data/base_data_source.rb +44 -0
- data/lib/data/data_source_factory.rb +16 -0
- data/lib/data/file_data_source.rb +29 -0
- data/lib/data/line_state_machine.rb +86 -0
- data/lib/data/string_data_source.rb +31 -0
- data/lib/data/word_data_source.rb +229 -0
- data/lib/location.rb +165 -0
- data/lib/node.rb +63 -0
- data/lib/node_factory.rb +169 -0
- data/lib/persist/suffix_tree_db.rb +148 -0
- data/lib/search/searcher.rb +68 -0
- data/lib/suffix_linker.rb +16 -0
- data/lib/suffix_tree.rb +122 -0
- data/lib/visitor/base_visitor.rb +17 -0
- data/lib/visitor/bfs.rb +22 -0
- data/lib/visitor/data_source_visitor.rb +15 -0
- data/lib/visitor/dfs.rb +34 -0
- data/lib/visitor/k_common_visitor.rb +71 -0
- data/lib/visitor/leaf_count_visitor.rb +15 -0
- data/lib/visitor/node_count_visitor.rb +16 -0
- data/lib/visitor/numbering_visitor.rb +230 -0
- data/lib/visitor/suffix_offset_visitor.rb +23 -0
- data/lib/visitor/tree_print_visitor.rb +44 -0
- data/lib/visitor/value_depth_visitor.rb +34 -0
- data/spec/constant_lca_spec.rb +27 -0
- data/spec/data_source_spec.rb +51 -0
- data/spec/fixtures/arizona.txt +1 -0
- data/spec/fixtures/chapter1.txt +371 -0
- data/spec/fixtures/chapter1.txt.summary +3 -0
- data/spec/fixtures/chapter1.txt.values +0 -0
- data/spec/fixtures/chapter1.txt.words +1329 -0
- data/spec/fixtures/mississippi.txt +1 -0
- data/spec/fixtures/singlePara.txt +41 -0
- data/spec/fixtures/smallFile.txt +3 -0
- data/spec/fixtures/smallFile.txt.summary +2 -0
- data/spec/fixtures/smallFile.txt.values +0 -0
- data/spec/fixtures/smallFile.txt.words +14 -0
- data/spec/fixtures/testbook.txt +5414 -0
- data/spec/location_spec.rb +149 -0
- data/spec/node_factory_spec.rb +199 -0
- data/spec/search_spec.rb +182 -0
- data/spec/suffix_tree_spec.rb +270 -0
- data/spec/util_spec.rb +47 -0
- data/spec/visitor_spec.rb +310 -0
- metadata +87 -0
@@ -0,0 +1,270 @@
|
|
1
|
+
require 'rspec'
|
2
|
+
|
3
|
+
require_relative '../lib/data/string_data_source'
|
4
|
+
require_relative '../lib/data/word_data_source'
|
5
|
+
require_relative '../lib/suffix_tree'
|
6
|
+
require_relative '../lib/visitor/data_source_visitor'
|
7
|
+
require_relative '../lib/visitor/dfs'
|
8
|
+
require_relative '../lib/visitor/leaf_count_visitor'
|
9
|
+
require_relative '../lib/visitor/tree_print_visitor'
|
10
|
+
require_relative '../lib/visitor/value_depth_visitor'
|
11
|
+
|
12
|
+
|
13
|
+
describe 'suffix tree' do
|
14
|
+
|
15
|
+
it 'should create suffix tree' do
|
16
|
+
|
17
|
+
st = SuffixTree.new('$')
|
18
|
+
stringData = StringDataSource.new("mississippi")
|
19
|
+
st.addDataSource(stringData)
|
20
|
+
expect(st.root).to_not eq(nil)
|
21
|
+
expect(st.root.children.length).to eq(5)
|
22
|
+
mChild = st.root.children['m']
|
23
|
+
expect(mChild).to_not eq(nil)
|
24
|
+
expect(mChild.isLeaf).to eq(true)
|
25
|
+
expect(mChild.suffixOffset).to eq(0)
|
26
|
+
iChild = st.root.children['i']
|
27
|
+
expect(iChild).to_not eq(nil)
|
28
|
+
expect(iChild.isInternal).to eq(true)
|
29
|
+
expect(iChild.children.length).to eq(3)
|
30
|
+
expect(iChild.suffixOffset).to eq(1)
|
31
|
+
sChild = st.root.children['s']
|
32
|
+
expect(sChild.isInternal).to eq(true)
|
33
|
+
expect(sChild.children.length).to eq(2)
|
34
|
+
pChild = st.root.children['p']
|
35
|
+
expect(pChild.isInternal).to eq(true)
|
36
|
+
expect(pChild.children.length).to eq(2)
|
37
|
+
end
|
38
|
+
|
39
|
+
it "builds tree with one leaf" do
|
40
|
+
dataSource = StringDataSource.new("a")
|
41
|
+
st = SuffixTree.new
|
42
|
+
st.addDataSource(dataSource)
|
43
|
+
expect(st.root.children.length).to eq (1)
|
44
|
+
location = st.location
|
45
|
+
expect(location.onNode).to eq (true)
|
46
|
+
expect(location.node).to eq(st.root)
|
47
|
+
end
|
48
|
+
|
49
|
+
it "builds tree with two leaf" do
|
50
|
+
dataSource = StringDataSource.new("ab")
|
51
|
+
st = SuffixTree.new
|
52
|
+
st.addDataSource(dataSource)
|
53
|
+
expect(st.root.children.length).to eq (2)
|
54
|
+
child1 = st.root.children['a']
|
55
|
+
expect(child1.suffixOffset).to eq(0)
|
56
|
+
child2 = st.root.children['b']
|
57
|
+
expect(child2.suffixOffset).to eq(1)
|
58
|
+
location = st.location
|
59
|
+
expect(location.onNode).to eq (true)
|
60
|
+
expect(location.node).to eq(st.root)
|
61
|
+
end
|
62
|
+
|
63
|
+
it "builds mississippi tree" do
|
64
|
+
dataSource = StringDataSource.new("mississippi")
|
65
|
+
st = SuffixTree.new
|
66
|
+
st.setDataSource(dataSource)
|
67
|
+
|
68
|
+
sio = StringIO.new()
|
69
|
+
tpv = TreePrintVisitor.new(dataSource, sio)
|
70
|
+
dfs = DFS.new(tpv)
|
71
|
+
|
72
|
+
st.addValue('m', 0)
|
73
|
+
|
74
|
+
expect(st.root.children['m'].nodeId).to eq(2)
|
75
|
+
location = st.location
|
76
|
+
expect(location.onNode).to eq (true)
|
77
|
+
expect(location.node.nodeId).to eq (1)
|
78
|
+
|
79
|
+
st.addValue('i', 1)
|
80
|
+
|
81
|
+
expect(st.root.children['i'].nodeId).to eq(3)
|
82
|
+
expect(location.onNode).to eq (true)
|
83
|
+
expect(location.node.nodeId).to eq (st.root.nodeId)
|
84
|
+
|
85
|
+
st.addValue('s', 2)
|
86
|
+
|
87
|
+
expect(st.root.children['s'].nodeId).to eq(4)
|
88
|
+
expect(location.onNode).to eq (true)
|
89
|
+
expect(location.node.nodeId).to eq (st.root.nodeId)
|
90
|
+
|
91
|
+
st.addValue('s', 3)
|
92
|
+
|
93
|
+
rootSchild = st.root.children['s']
|
94
|
+
expect(rootSchild.nodeId).to eq (4)
|
95
|
+
expect(rootSchild.incomingEdgeStartOffset).to eq(2)
|
96
|
+
expect(rootSchild.incomingEdgeEndOffset).to eq(Node::CURRENT_ENDING_OFFSET)
|
97
|
+
expect(location.onNode).to eq (false)
|
98
|
+
expect(location.incomingEdgeOffset).to eq (3)
|
99
|
+
|
100
|
+
st.addValue('i', 4)
|
101
|
+
|
102
|
+
# should have added an internal node and a leaf node
|
103
|
+
# internal node should be the 's' child of root, with a suffix link pointing to root
|
104
|
+
rootSchild = st.root.children['s']
|
105
|
+
expect(rootSchild.suffixLink).not_to eq (nil)
|
106
|
+
expect(rootSchild.suffixLink).to eq(st.root)
|
107
|
+
expect(location.onNode).to eq (false)
|
108
|
+
expect(location.incomingEdgeOffset).to eq (2)
|
109
|
+
rootSchild = st.root.children['s']
|
110
|
+
suffix3_nodeId = rootSchild.children['s'].nodeId
|
111
|
+
expect(rootSchild.incomingEdgeStartOffset).to eq(2)
|
112
|
+
expect(rootSchild.incomingEdgeEndOffset).to eq(2)
|
113
|
+
|
114
|
+
# these next 3 should not should only update the location incomingEdgeOffset
|
115
|
+
st.addValue('s', 5)
|
116
|
+
|
117
|
+
expect(location.incomingEdgeOffset).to eq (3)
|
118
|
+
expect(location.onNode).to eq (false)
|
119
|
+
|
120
|
+
st.addValue('s', 6)
|
121
|
+
|
122
|
+
expect(location.incomingEdgeOffset).to eq (4)
|
123
|
+
expect(location.onNode).to eq (false)
|
124
|
+
|
125
|
+
st.addValue('i', 7)
|
126
|
+
|
127
|
+
expect(location.incomingEdgeOffset).to eq (5)
|
128
|
+
expect(location.onNode).to eq (false)
|
129
|
+
|
130
|
+
result = st.extend('p', 8)
|
131
|
+
|
132
|
+
expect(result).to eq (true)
|
133
|
+
expect(location.onNode).to eq(true)
|
134
|
+
slNode = location.node
|
135
|
+
expect(slNode.suffixLink).to eq(nil)
|
136
|
+
result = st.extend('p', 8)
|
137
|
+
|
138
|
+
expect(result).to eq (true)
|
139
|
+
expect(location.onNode).to eq(false)
|
140
|
+
result = st.extend('p', 8)
|
141
|
+
|
142
|
+
expect(result).to eq (true)
|
143
|
+
expect(location.onNode).to eq(true)
|
144
|
+
expect(slNode.suffixLink).not_to eq(nil)
|
145
|
+
result = st.extend('p', 8)
|
146
|
+
|
147
|
+
expect(result).to eq (true)
|
148
|
+
expect(location.onNode).to eq(false)
|
149
|
+
result = st.extend('p', 8)
|
150
|
+
|
151
|
+
expect(result).to eq (true)
|
152
|
+
expect(location.onNode).to eq(true)
|
153
|
+
result = st.extend('p', 8)
|
154
|
+
|
155
|
+
expect(result).to eq (true)
|
156
|
+
expect(location.onNode).to eq(false)
|
157
|
+
result = st.extend('p', 8)
|
158
|
+
|
159
|
+
expect(result).to eq (true)
|
160
|
+
expect(location.onNode).to eq(true)
|
161
|
+
result = st.extend('p', 8)
|
162
|
+
|
163
|
+
expect(result).to eq (true)
|
164
|
+
expect(location.onNode).to eq(true)
|
165
|
+
result = st.extend('p', 8)
|
166
|
+
|
167
|
+
expect(result).to eq (false)
|
168
|
+
expect(location.onNode).to eq(true)
|
169
|
+
|
170
|
+
st.addValue('p', 9)
|
171
|
+
|
172
|
+
expect(location.onNode).to eq (false)
|
173
|
+
expect(location.incomingEdgeOffset).to eq(9)
|
174
|
+
|
175
|
+
st.addValue('i', 10)
|
176
|
+
|
177
|
+
dfs.traverse(st.root)
|
178
|
+
expected_tree = <<-TREESTR
|
179
|
+
ROOT
|
180
|
+
mississippi
|
181
|
+
i
|
182
|
+
ssi
|
183
|
+
ssippi
|
184
|
+
ppi
|
185
|
+
ppi
|
186
|
+
s
|
187
|
+
si
|
188
|
+
ssippi
|
189
|
+
ppi
|
190
|
+
i
|
191
|
+
ssippi
|
192
|
+
ppi
|
193
|
+
p
|
194
|
+
pi
|
195
|
+
i
|
196
|
+
TREESTR
|
197
|
+
expect(sio.string).to eq (expected_tree)
|
198
|
+
|
199
|
+
expect(location.onNode).to eq (true)
|
200
|
+
expect(location.node.nodeId).to eq (13)
|
201
|
+
end
|
202
|
+
|
203
|
+
it "builds suffix tree of words" do
|
204
|
+
wordDataSource = WordDataSource.new File.join('spec', 'fixtures', "chapter1.txt")
|
205
|
+
st = SuffixTree.new(nil, { :leafCount => true, :valueDepth => true })
|
206
|
+
st.addDataSource(wordDataSource)
|
207
|
+
|
208
|
+
root = st.root
|
209
|
+
expect(root.nodeId).to eq 1
|
210
|
+
lcv = DFS.new(LeafCountVisitor.new)
|
211
|
+
lcv.traverse(st.root)
|
212
|
+
deepVal = DeepestValueDepthVisitor.new
|
213
|
+
dfs = DFS.new(deepVal)
|
214
|
+
dfs.traverse(st.root)
|
215
|
+
expect(st.nodeFactory.valuePath(deepVal.deepestValueDepthNode)).to eq "in spite of his"
|
216
|
+
end
|
217
|
+
|
218
|
+
it "converts tree to suffix array" do
|
219
|
+
dataSource = StringDataSource.new "mississippi"
|
220
|
+
st = SuffixTree.new('$')
|
221
|
+
st.addDataSource dataSource
|
222
|
+
|
223
|
+
suffix_array = []
|
224
|
+
st.root.each_suffix do |suffixOffset|
|
225
|
+
suffix_array << suffixOffset
|
226
|
+
end
|
227
|
+
expect(suffix_array).to eq [11, 10, 7, 4, 1, 0, 9, 8, 6, 3, 5, 2]
|
228
|
+
end
|
229
|
+
|
230
|
+
describe "builds generalized suffix trees" do
|
231
|
+
let(:alphaDataSource) { StringDataSource.new "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqr" }
|
232
|
+
let(:alphaNodeFactory) { NodeFactory.new alphaDataSource }
|
233
|
+
let(:secondDataSource) { StringDataSource.new "asjdfkjaskdjfkajlxxxxxxxjklmnopqrstuvwxyzabcsdf;laksjdf aksjd"}
|
234
|
+
|
235
|
+
it "builds generalized suffix tree" do
|
236
|
+
st = SuffixTree.new('$', {:valueDepth => true})
|
237
|
+
st.addDataSource alphaDataSource
|
238
|
+
st.addDataSource secondDataSource
|
239
|
+
|
240
|
+
deepVal = DeepestValueDepthVisitor.new
|
241
|
+
dfs = DFS.new(deepVal)
|
242
|
+
dfs.traverse(st.root)
|
243
|
+
expect(st.nodeFactory.valuePath(deepVal.deepestValueDepthNode,'')).to eq "jklmnopqrstuvwxyzabc"
|
244
|
+
end
|
245
|
+
|
246
|
+
let(:src1) { StringDataSource.new "abcd" }
|
247
|
+
let(:src2) { StringDataSource.new "cxyz" }
|
248
|
+
|
249
|
+
it "uses multiple data sources" do
|
250
|
+
st = SuffixTree.new(nil, {:valueDepth => true, :dataSourceBit => true})
|
251
|
+
st.addDataSource src1
|
252
|
+
st.addDataSource src2
|
253
|
+
|
254
|
+
deepVal = DeepestValueDepthVisitor.new
|
255
|
+
dfs = DFS.new(deepVal)
|
256
|
+
dfs.traverse(st.root)
|
257
|
+
expect(st.nodeFactory.valuePath(deepVal.deepestValueDepthNode,'')).to eq "c"
|
258
|
+
dataSourceVisitor = DataSourceVisitor.new
|
259
|
+
dfs = DFS.new(dataSourceVisitor)
|
260
|
+
dfs.traverse(st.root)
|
261
|
+
expect(deepVal.deepestValueDepthNode.dataSourceBit).to eq 3
|
262
|
+
expect(st.root.dataSourceBit).to eq 3
|
263
|
+
expect(st.root.children['a'].dataSourceBit).to eq 1
|
264
|
+
expect(st.root.children['x'].dataSourceBit).to eq 2
|
265
|
+
expect(deepVal.deepestValueDepthNode.children['d'].dataSourceBit).to eq 1
|
266
|
+
expect(deepVal.deepestValueDepthNode.children['x'].dataSourceBit).to eq 2
|
267
|
+
end
|
268
|
+
end
|
269
|
+
|
270
|
+
end
|
data/spec/util_spec.rb
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
require 'rspec'
|
2
|
+
require_relative '../lib/visitor/numbering_visitor'
|
3
|
+
|
4
|
+
|
5
|
+
describe 'utility' do
|
6
|
+
it 'should find right-most 1-bit' do
|
7
|
+
bu = BitUtil.new
|
8
|
+
(0..63).each do |n|
|
9
|
+
expect(bu.rightBit(2**n)).to eq (n+1)
|
10
|
+
end
|
11
|
+
expect(bu.rightBit(65)).to eq (1)
|
12
|
+
expect(bu.rightBit(66)).to eq (2)
|
13
|
+
end
|
14
|
+
|
15
|
+
it 'should find left-most 1-bit' do
|
16
|
+
bu = BitUtil.new
|
17
|
+
(0..63).each do |n|
|
18
|
+
expect(bu.leftBit(2**n)).to eq (n+1)
|
19
|
+
end
|
20
|
+
expect(bu.leftBit(65)).to eq (7)
|
21
|
+
expect(bu.leftBit(66)).to eq (7)
|
22
|
+
expect(bu.leftBit(129)).to eq (8)
|
23
|
+
expect(bu.leftBit(280)).to eq (9)
|
24
|
+
end
|
25
|
+
|
26
|
+
it 'finds bit common to two values greater than or equal to a given value' do
|
27
|
+
bu = BitUtil.new
|
28
|
+
expect(bu.bitGreaterThanOrEqualTo(1, 1, 1)).to eq 1
|
29
|
+
expect(bu.bitGreaterThanOrEqualTo(1, 2, 2)).to eq 2
|
30
|
+
expect(bu.bitGreaterThanOrEqualTo(1, 3, 3)).to eq 1
|
31
|
+
expect(bu.bitGreaterThanOrEqualTo(1, 4, 4)).to eq 3
|
32
|
+
expect(bu.bitGreaterThanOrEqualTo(1, 8, 8)).to eq 4
|
33
|
+
expect(bu.bitGreaterThanOrEqualTo(1, 7, 6)).to eq 2
|
34
|
+
expect(bu.bitGreaterThanOrEqualTo(2, 5, 6)).to eq 3
|
35
|
+
expect(bu.bitGreaterThanOrEqualTo(10, 1024+2048, 2049)).to eq 12
|
36
|
+
end
|
37
|
+
|
38
|
+
it 'finds left most bit to right of a given bit' do
|
39
|
+
bu = BitUtil.new
|
40
|
+
expect(bu.leftMostBitToRightOf(2, 1)).to eq 1
|
41
|
+
expect(bu.leftMostBitToRightOf(4, 1)).to eq 1
|
42
|
+
expect(bu.leftMostBitToRightOf(8, 3)).to eq 2
|
43
|
+
expect(bu.leftMostBitToRightOf(8, 15)).to eq 4
|
44
|
+
expect(bu.leftMostBitToRightOf(8, 22)).to eq 5
|
45
|
+
expect(bu.leftMostBitToRightOf(8, 33)).to eq 6
|
46
|
+
end
|
47
|
+
end
|
@@ -0,0 +1,310 @@
|
|
1
|
+
require 'rspec'
|
2
|
+
require_relative '../lib/location'
|
3
|
+
require_relative '../lib/node'
|
4
|
+
require_relative '../lib/node_factory'
|
5
|
+
require_relative '../lib/data/string_data_source'
|
6
|
+
require_relative '../lib/data/file_data_source'
|
7
|
+
require_relative '../lib/suffix_tree'
|
8
|
+
require_relative '../lib/visitor/bfs'
|
9
|
+
require_relative '../lib/visitor/data_source_visitor'
|
10
|
+
require_relative '../lib/visitor/k_common_visitor'
|
11
|
+
require_relative '../lib/visitor/leaf_count_visitor'
|
12
|
+
require_relative '../lib/visitor/value_depth_visitor'
|
13
|
+
require_relative '../lib/visitor/dfs'
|
14
|
+
require_relative '../lib/visitor/node_count_visitor'
|
15
|
+
require_relative '../lib/visitor/suffix_offset_visitor'
|
16
|
+
require_relative '../lib/visitor/numbering_visitor'
|
17
|
+
require_relative '../lib/visitor/tree_print_visitor'
|
18
|
+
|
19
|
+
describe 'character depth visitor' do
|
20
|
+
|
21
|
+
let (:dataSource) { StringDataSource.new("mississippi") }
|
22
|
+
let (:stringNodeFactory) { NodeFactory.new dataSource }
|
23
|
+
let (:stringRootNodeId) { stringNodeFactory.nextNodeId }
|
24
|
+
let (:fileDataSource) { FileDataSource.new(File.join('spec', 'fixtures', "mississippi.txt")) }
|
25
|
+
let (:fileNodeFactory) { NodeFactory.new fileDataSource }
|
26
|
+
|
27
|
+
def verifyValueDepth(root)
|
28
|
+
expect(root.valueDepth).to eq (0)
|
29
|
+
mChild = root.children['m']
|
30
|
+
iChild = root.children['i']
|
31
|
+
sChild = root.children['s']
|
32
|
+
pChild = root.children['p']
|
33
|
+
expect(pChild.valueDepth).to eq (1)
|
34
|
+
expect(pChild.children['p'].valueDepth).to eq (Node::LEAF_DEPTH)
|
35
|
+
expect(pChild.children['i'].valueDepth).to eq (Node::LEAF_DEPTH)
|
36
|
+
expect(mChild.valueDepth).to eq (Node::LEAF_DEPTH)
|
37
|
+
expect(iChild.valueDepth).to eq (1)
|
38
|
+
expect(iChild.children['p'].valueDepth).to eq (Node::LEAF_DEPTH)
|
39
|
+
isChild = iChild.children['s']
|
40
|
+
expect(isChild.valueDepth).to eq (4)
|
41
|
+
expect(isChild.children['s'].valueDepth).to eq(Node::LEAF_DEPTH)
|
42
|
+
expect(isChild.children['p'].valueDepth).to eq(Node::LEAF_DEPTH)
|
43
|
+
expect(sChild.valueDepth).to eq (1)
|
44
|
+
siChild = sChild.children['i']
|
45
|
+
ssChild = sChild.children['s']
|
46
|
+
expect(siChild.valueDepth).to eq (2)
|
47
|
+
expect(ssChild.valueDepth).to eq (3)
|
48
|
+
expect(siChild.children['p'].valueDepth).to eq(Node::LEAF_DEPTH)
|
49
|
+
expect(siChild.children['s'].valueDepth).to eq(Node::LEAF_DEPTH)
|
50
|
+
expect(ssChild.children['s'].valueDepth).to eq(Node::LEAF_DEPTH)
|
51
|
+
expect(ssChild.children['p'].valueDepth).to eq(Node::LEAF_DEPTH)
|
52
|
+
end
|
53
|
+
|
54
|
+
context "DFS traversal" do
|
55
|
+
it "sets character depth using depth first traversal" do
|
56
|
+
|
57
|
+
hash = {
|
58
|
+
:valueDepth => true
|
59
|
+
}
|
60
|
+
st = SuffixTree.new(nil, hash)
|
61
|
+
st.addDataSource(dataSource)
|
62
|
+
|
63
|
+
cdv = DFS.new(ValueDepthVisitor.new)
|
64
|
+
cdv.traverse(st.root)
|
65
|
+
self.verifyValueDepth(st.root)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
context "BFS traversal" do
|
70
|
+
it "sets character depth using breadth first traversal" do
|
71
|
+
st = SuffixTree.new(nil, { :valueDepth => true })
|
72
|
+
st.addDataSource(dataSource)
|
73
|
+
cdv = BFS.new(ValueDepthVisitor.new)
|
74
|
+
cdv.traverse(st.root)
|
75
|
+
self.verifyValueDepth(st.root)
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
def verifyLeafCount(root)
|
80
|
+
lcv = DFS.new(LeafCountVisitor.new)
|
81
|
+
lcv.traverse(root)
|
82
|
+
expect(root.leafCount).to eq (10) # final 'i' is implicit
|
83
|
+
mChild = root.children['m']
|
84
|
+
iChild = root.children['i']
|
85
|
+
sChild = root.children['s']
|
86
|
+
pChild = root.children['p']
|
87
|
+
expect(mChild.leafCount).to eq (1)
|
88
|
+
expect(iChild.leafCount).to eq (3)
|
89
|
+
expect(sChild.leafCount).to eq (4)
|
90
|
+
expect(pChild.leafCount).to eq (2)
|
91
|
+
end
|
92
|
+
|
93
|
+
context "DFS traversal" do
|
94
|
+
it "sets leaf count for suffix tree created from string" do
|
95
|
+
hash = {
|
96
|
+
:leafCount => true
|
97
|
+
}
|
98
|
+
st = SuffixTree.new(nil, hash)
|
99
|
+
st.addDataSource(dataSource)
|
100
|
+
self.verifyLeafCount(st.root)
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
context "DFS traversal" do
|
105
|
+
it "sets leaf count for suffix tree loaded from file" do
|
106
|
+
hash = {
|
107
|
+
:leafCount => true
|
108
|
+
}
|
109
|
+
st = SuffixTree.new(nil, hash)
|
110
|
+
st.addDataSource(fileDataSource)
|
111
|
+
self.verifyLeafCount(st.root)
|
112
|
+
end
|
113
|
+
end
|
114
|
+
|
115
|
+
def verifyNodeCount(dataSource)
|
116
|
+
st = SuffixTree.new(nil, nil)
|
117
|
+
st.addDataSource(fileDataSource)
|
118
|
+
ncv = NodeCountVisitor.new
|
119
|
+
bt = DFS.new(ncv)
|
120
|
+
bt.traverse(st.root)
|
121
|
+
expect(ncv.count).to eq (17)
|
122
|
+
bncv = NodeCountVisitor.new
|
123
|
+
bfst = BFS.new(bncv)
|
124
|
+
bfst.traverse(st.root)
|
125
|
+
expect(bncv.count).to eq (17)
|
126
|
+
end
|
127
|
+
|
128
|
+
context "Count nodes" do
|
129
|
+
it "counts nodes with DFS traversal of file data source" do
|
130
|
+
verifyNodeCount(fileDataSource)
|
131
|
+
end
|
132
|
+
end
|
133
|
+
|
134
|
+
context "Count nodes" do
|
135
|
+
it "counts nodes with DFS traversal of string data source" do
|
136
|
+
verifyNodeCount(dataSource)
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
context "collect suffix offsets" do
|
141
|
+
it "traverses suffix tree and collects suffix offsets" do
|
142
|
+
soCollector = SuffixOffsetVisitor.new
|
143
|
+
so = BFS.new(soCollector)
|
144
|
+
st = SuffixTree.new(nil, nil)
|
145
|
+
st.addDataSource(dataSource)
|
146
|
+
so.traverse(st.root)
|
147
|
+
expect(soCollector.result.sort).to eq ([ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 ])
|
148
|
+
end
|
149
|
+
end
|
150
|
+
|
151
|
+
describe "generalized suffix tree" do
|
152
|
+
let(:s1) { StringDataSource.new "sandollar" }
|
153
|
+
let(:s2) { StringDataSource.new "sandlot" }
|
154
|
+
let(:s3) { StringDataSource.new "handler" }
|
155
|
+
let(:s4) { StringDataSource.new "grand" }
|
156
|
+
let(:s5) { StringDataSource.new "pantry" }
|
157
|
+
|
158
|
+
it "KCommonVisitor finds longest substring common to k strings" do
|
159
|
+
# make the generalized suffix tree
|
160
|
+
st = SuffixTree.new("$", {:valueDepth => true, :dataSourceBit => true})
|
161
|
+
st.addDataSource(s1)
|
162
|
+
st.addDataSource(s2)
|
163
|
+
st.addDataSource(s3)
|
164
|
+
st.addDataSource(s4)
|
165
|
+
st.addDataSource(s5)
|
166
|
+
|
167
|
+
dataSourceVisitor = DataSourceVisitor.new
|
168
|
+
dfs = DFS.new(dataSourceVisitor)
|
169
|
+
dfs.traverse(st.root)
|
170
|
+
kCommonVisitor = KCommonVisitor.new(s1)
|
171
|
+
dfs = DFS.new(kCommonVisitor)
|
172
|
+
dfs.traverse(st.root)
|
173
|
+
longestLength,sample = kCommonVisitor.longestStringCommonTo(2)
|
174
|
+
expect(longestLength).to eq 4
|
175
|
+
expect(sample).to eq "sand"
|
176
|
+
longestLength,sample = kCommonVisitor.longestStringCommonTo(3)
|
177
|
+
expect(longestLength).to eq 3
|
178
|
+
expect(sample).to eq "and"
|
179
|
+
longestLength,sample = kCommonVisitor.longestStringCommonTo(4)
|
180
|
+
expect(longestLength).to eq 3
|
181
|
+
expect(sample).to eq "and"
|
182
|
+
longestLength,sample = kCommonVisitor.longestStringCommonTo(5)
|
183
|
+
expect(longestLength).to eq 2
|
184
|
+
expect(sample).to eq "an"
|
185
|
+
end
|
186
|
+
end
|
187
|
+
|
188
|
+
describe "DFS depth number" do
|
189
|
+
it "sets sets depth numbers and count of nodes in subtree for nodes" do
|
190
|
+
st = SuffixTree.new
|
191
|
+
st.addDataSource(dataSource)
|
192
|
+
dfs = OrderedDFS.new(NumberingVisitor.new)
|
193
|
+
dfs.traverse(st.root)
|
194
|
+
expect(st.root.dfsNumber).to eq 1
|
195
|
+
expect(st.root.numberNodesInSubtree).to eq 17
|
196
|
+
|
197
|
+
iChild = st.root.children['i']
|
198
|
+
expect(iChild.dfsNumber).to eq 2
|
199
|
+
expect(iChild.numberNodesInSubtree).to eq 5
|
200
|
+
expect(iChild.children['p'].dfsNumber).to eq 3
|
201
|
+
expect(iChild.children['p'].numberNodesInSubtree).to eq 1
|
202
|
+
expect(iChild.children['s'].dfsNumber).to eq 4
|
203
|
+
expect(iChild.children['s'].numberNodesInSubtree).to eq 3
|
204
|
+
expect(iChild.children['s'].children['p'].dfsNumber).to eq 5
|
205
|
+
expect(iChild.children['s'].children['p'].numberNodesInSubtree).to eq 1
|
206
|
+
expect(iChild.children['s'].children['s'].dfsNumber).to eq 6
|
207
|
+
expect(iChild.children['s'].children['s'].numberNodesInSubtree).to eq 1
|
208
|
+
|
209
|
+
mChild = st.root.children['m']
|
210
|
+
expect(mChild.dfsNumber).to eq 7
|
211
|
+
expect(mChild.numberNodesInSubtree).to eq 1
|
212
|
+
|
213
|
+
pChild = st.root.children['p']
|
214
|
+
expect(pChild.dfsNumber).to eq 8
|
215
|
+
expect(pChild.numberNodesInSubtree).to eq 3
|
216
|
+
expect(pChild.children['i'].dfsNumber).to eq 9
|
217
|
+
expect(pChild.children['p'].dfsNumber).to eq 10
|
218
|
+
|
219
|
+
sChild = st.root.children['s']
|
220
|
+
expect(sChild.dfsNumber).to eq 11
|
221
|
+
expect(sChild.numberNodesInSubtree).to eq 7
|
222
|
+
expect(sChild.children['i'].dfsNumber).to eq 12
|
223
|
+
expect(sChild.children['i'].numberNodesInSubtree).to eq 3
|
224
|
+
expect(sChild.children['i'].children['p'].dfsNumber).to eq 13
|
225
|
+
expect(sChild.children['i'].children['p'].numberNodesInSubtree).to eq 1
|
226
|
+
expect(sChild.children['i'].children['s'].dfsNumber).to eq 14
|
227
|
+
expect(sChild.children['i'].children['s'].numberNodesInSubtree).to eq 1
|
228
|
+
expect(sChild.children['s'].dfsNumber).to eq 15
|
229
|
+
expect(sChild.children['s'].numberNodesInSubtree).to eq 3
|
230
|
+
expect(sChild.children['s'].children['p'].dfsNumber).to eq 16
|
231
|
+
expect(sChild.children['s'].children['p'].numberNodesInSubtree).to eq 1
|
232
|
+
expect(sChild.children['s'].children['s'].dfsNumber).to eq 17
|
233
|
+
expect(sChild.children['s'].children['s'].numberNodesInSubtree).to eq 1
|
234
|
+
end
|
235
|
+
end
|
236
|
+
|
237
|
+
describe "DFS node path numbers number" do
|
238
|
+
it "sets sets node depth numbers then path numbers" do
|
239
|
+
st = SuffixTree.new
|
240
|
+
st.addDataSource(dataSource)
|
241
|
+
dfs = OrderedDFS.new(NumberingVisitor.new)
|
242
|
+
dfs.traverse(st.root)
|
243
|
+
dfs = OrderedDFS.new(RunDefiningVisitor.new)
|
244
|
+
dfs.traverse(st.root)
|
245
|
+
dfs = DFS.new(RunBitVisitor.new(st.root))
|
246
|
+
dfs.traverse(st.root)
|
247
|
+
|
248
|
+
expect(st.root.runTail.binaryTreeHeight).to eq 5
|
249
|
+
expect(st.root.runTail.dfsNumber).to eq 16
|
250
|
+
expect(st.root.runBits).to eq 16
|
251
|
+
|
252
|
+
iChild = st.root.children['i']
|
253
|
+
expect(iChild.runTail.binaryTreeHeight).to eq 3
|
254
|
+
expect(iChild.runTail.dfsNumber).to eq 4
|
255
|
+
expect(iChild.runBits).to eq 20 # 16 (binaryTreeHeight 5) + 4 (binaryTreeHeight 3)
|
256
|
+
|
257
|
+
expect(iChild.children['p'].runTail.binaryTreeHeight).to eq 1
|
258
|
+
expect(iChild.children['p'].runTail.dfsNumber).to eq 3
|
259
|
+
expect(iChild.children['p'].runBits).to eq 21
|
260
|
+
expect(iChild.children['s'].runTail.binaryTreeHeight).to eq 3
|
261
|
+
expect(iChild.children['s'].runTail.dfsNumber).to eq 4
|
262
|
+
expect(iChild.children['s'].runBits).to eq 20
|
263
|
+
expect(iChild.children['s'].children['p'].runTail.binaryTreeHeight).to eq 1
|
264
|
+
expect(iChild.children['s'].children['p'].runTail.dfsNumber).to eq 5
|
265
|
+
expect(iChild.children['s'].children['p'].runBits).to eq 21
|
266
|
+
expect(iChild.children['s'].children['s'].runTail.binaryTreeHeight).to eq 2
|
267
|
+
expect(iChild.children['s'].children['s'].runTail.dfsNumber).to eq 6
|
268
|
+
expect(iChild.children['s'].children['s'].runBits).to eq 22
|
269
|
+
|
270
|
+
mChild = st.root.children['m']
|
271
|
+
expect(mChild.runTail.binaryTreeHeight).to eq 1
|
272
|
+
expect(mChild.runTail.dfsNumber).to eq 7
|
273
|
+
expect(mChild.runBits).to eq 17
|
274
|
+
|
275
|
+
pChild = st.root.children['p']
|
276
|
+
expect(pChild.runTail.binaryTreeHeight).to eq 4
|
277
|
+
expect(pChild.runTail.dfsNumber).to eq 8
|
278
|
+
expect(pChild.runBits).to eq 24
|
279
|
+
expect(pChild.children['i'].runTail.binaryTreeHeight).to eq 1
|
280
|
+
expect(pChild.children['i'].runTail.dfsNumber).to eq 9
|
281
|
+
expect(pChild.children['i'].runBits).to eq 25
|
282
|
+
expect(pChild.children['p'].runTail.binaryTreeHeight).to eq 2
|
283
|
+
expect(pChild.children['p'].runTail.dfsNumber).to eq 10
|
284
|
+
expect(pChild.children['p'].runBits).to eq 26
|
285
|
+
|
286
|
+
sChild = st.root.children['s']
|
287
|
+
expect(sChild.runTail.binaryTreeHeight).to eq 5
|
288
|
+
expect(sChild.runTail.dfsNumber).to eq 16
|
289
|
+
expect(sChild.runBits).to eq 16
|
290
|
+
expect(sChild.children['i'].runTail.binaryTreeHeight).to eq 3
|
291
|
+
expect(sChild.children['i'].runTail.dfsNumber).to eq 12
|
292
|
+
expect(sChild.children['i'].runBits).to eq 20
|
293
|
+
expect(sChild.children['i'].children['p'].runTail.binaryTreeHeight).to eq 1
|
294
|
+
expect(sChild.children['i'].children['p'].runTail.dfsNumber).to eq 13
|
295
|
+
expect(sChild.children['i'].children['p'].runBits).to eq 21
|
296
|
+
expect(sChild.children['i'].children['s'].runTail.binaryTreeHeight).to eq 2
|
297
|
+
expect(sChild.children['i'].children['s'].runTail.dfsNumber).to eq 14
|
298
|
+
expect(sChild.children['i'].children['s'].runBits).to eq 22
|
299
|
+
expect(sChild.children['s'].runTail.binaryTreeHeight).to eq 5
|
300
|
+
expect(sChild.children['s'].runTail.dfsNumber).to eq 16
|
301
|
+
expect(sChild.children['s'].runBits).to eq 16
|
302
|
+
expect(sChild.children['s'].children['p'].runTail.binaryTreeHeight).to eq 5
|
303
|
+
expect(sChild.children['s'].children['p'].runTail.dfsNumber).to eq 16
|
304
|
+
expect(sChild.children['s'].children['p'].runBits).to eq 16
|
305
|
+
expect(sChild.children['s'].children['s'].runTail.binaryTreeHeight).to eq 1
|
306
|
+
expect(sChild.children['s'].children['s'].runTail.dfsNumber).to eq 17
|
307
|
+
expect(sChild.children['s'].children['s'].runBits).to eq 17
|
308
|
+
end
|
309
|
+
end
|
310
|
+
end
|