boyer_moore 0.2.1 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/boyer_moore.gemspec +2 -2
- data/lib/boyer_moore.rb +76 -84
- data/lib/boyer_moore/version.rb +1 -1
- data/test_file +1 -0
- metadata +12 -11
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 7de6b2a49229c15b9f3ab4a7311bcbd77789d02b
|
4
|
+
data.tar.gz: 21c26b9a7476405f08eaef5fc76f614496664850
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6199a53c8228caded86afe336064ee3f0ae98008fba3786861f38b021f184c369efcd0bb9528fe86b26c1f03790599806483be4c89129258d845ec269193da86
|
7
|
+
data.tar.gz: acadd4c9f7de76fdc4e25e3208403eba5704949d177eccb41ee7f02eda772421851f13b010192b44388b2486d6728b2036f982d3dfa608ea44f11d9f154978e4
|
data/boyer_moore.gemspec
CHANGED
@@ -26,6 +26,6 @@ Gem::Specification.new do |spec|
|
|
26
26
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
27
27
|
spec.require_paths = ["lib"]
|
28
28
|
|
29
|
-
spec.add_development_dependency "bundler"
|
30
|
-
spec.add_development_dependency "rake"
|
29
|
+
spec.add_development_dependency "bundler"
|
30
|
+
spec.add_development_dependency "rake"
|
31
31
|
end
|
data/lib/boyer_moore.rb
CHANGED
@@ -1,108 +1,100 @@
|
|
1
|
-
|
1
|
+
require_relative "./boyer_moore/version"
|
2
2
|
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
@regexps = {}
|
7
|
-
@regular = {}
|
8
|
-
end
|
3
|
+
module BoyerMoore
|
4
|
+
def self.search(haystack, needle_string)
|
5
|
+
needle = Needle.new(needle_string)
|
9
6
|
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
7
|
+
haystack_index = 0
|
8
|
+
while haystack_index <= haystack.size - needle.size
|
9
|
+
if skip_by = needle.match_or_skip_by(haystack, haystack_index)
|
10
|
+
haystack_index += skip_by
|
11
|
+
else
|
12
|
+
break haystack_index # Found a match at haystack_index!
|
16
13
|
end
|
17
14
|
end
|
18
|
-
nil
|
19
15
|
end
|
20
16
|
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
@regular[k] = v
|
17
|
+
class Needle
|
18
|
+
def initialize(needle)
|
19
|
+
needle.size > 0 or raise "Must pass needle with size > 0"
|
20
|
+
@needle = needle
|
26
21
|
end
|
27
|
-
end
|
28
|
-
|
29
|
-
end
|
30
22
|
|
31
|
-
|
23
|
+
def size
|
24
|
+
@needle.size
|
25
|
+
end
|
32
26
|
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
return haystack if needle_len == 0
|
38
|
-
badcharacter = self.prepare_badcharacter_heuristic(needle)
|
39
|
-
goodsuffix = self.prepare_goodsuffix_heuristic(needle)
|
40
|
-
s = 0
|
41
|
-
while s <= haystack_len - needle_len
|
42
|
-
j = needle_len
|
43
|
-
while (j > 0) && self.needle_matches?(needle[j-1], haystack[s+j-1])
|
44
|
-
j -= 1
|
27
|
+
def match_or_skip_by(haystack, haystack_index)
|
28
|
+
if mismatch_idx = mismatch_index(haystack, haystack_index)
|
29
|
+
mismatch_char_index = character_index(haystack[haystack_index + mismatch_idx])
|
30
|
+
skip_by(mismatch_char_index, mismatch_idx)
|
45
31
|
end
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
return s
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
|
36
|
+
def mismatch_index(haystack, haystack_index)
|
37
|
+
compare_index = size - 1
|
38
|
+
while @needle[compare_index] == haystack[haystack_index + compare_index]
|
39
|
+
compare_index -= 1
|
40
|
+
compare_index < 0 and return nil
|
56
41
|
end
|
42
|
+
compare_index
|
57
43
|
end
|
58
|
-
return nil
|
59
|
-
end
|
60
44
|
|
61
|
-
|
62
|
-
|
63
|
-
0.upto(str.length - 1) do |i|
|
64
|
-
result[str[i]] = i
|
45
|
+
def character_index(char)
|
46
|
+
character_indexes[char] || -1
|
65
47
|
end
|
66
|
-
result
|
67
|
-
end
|
68
48
|
|
69
|
-
|
70
|
-
|
71
|
-
result = []
|
72
|
-
reversed = normal.dup.reverse
|
73
|
-
prefix_normal = compute_prefix(normal)
|
74
|
-
prefix_reversed = compute_prefix(reversed)
|
75
|
-
0.upto(size) do |i|
|
76
|
-
result[i] = size - prefix_normal[size-1]
|
49
|
+
def good_suffix(compare_index)
|
50
|
+
good_suffixes[compare_index]
|
77
51
|
end
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
52
|
+
|
53
|
+
def skip_by(mismatch_char_index, compare_index)
|
54
|
+
suffix_index = good_suffix(compare_index + 1)
|
55
|
+
if mismatch_char_index <= compare_index && (m = compare_index - mismatch_char_index) > suffix_index
|
56
|
+
m
|
57
|
+
else
|
58
|
+
suffix_index
|
59
|
+
end
|
82
60
|
end
|
83
|
-
result
|
84
|
-
end
|
85
61
|
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
62
|
+
def character_indexes
|
63
|
+
@char_indexes ||=
|
64
|
+
(0...@needle.length).reduce({}) do |hash, i|
|
65
|
+
hash[@needle[i]] = i
|
66
|
+
hash
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
def good_suffixes
|
71
|
+
@good_suffixes ||=
|
72
|
+
begin
|
73
|
+
prefix_normal = self.class.prefix(@needle)
|
74
|
+
prefix_reversed = self.class.prefix(@needle.reverse)
|
75
|
+
result = []
|
76
|
+
(0..@needle.size).each do |i|
|
77
|
+
result[i] = @needle.size - prefix_normal[@needle.size-1]
|
78
|
+
end
|
79
|
+
(0...@needle.size).each do |i|
|
80
|
+
j = @needle.size - prefix_reversed[i]
|
81
|
+
k = i - prefix_reversed[i] + 1
|
82
|
+
result[j] > k and result[j] = k
|
83
|
+
end
|
84
|
+
result
|
85
|
+
end
|
91
86
|
end
|
92
|
-
end
|
93
87
|
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
k
|
88
|
+
def self.prefix(string)
|
89
|
+
k = 0
|
90
|
+
(1...string.length).reduce([0]) do |prefix, q|
|
91
|
+
while k > 0 && string[k] != string[q]
|
92
|
+
k = prefix[k - 1]
|
93
|
+
end
|
94
|
+
string[k] == string[q] and k += 1
|
95
|
+
prefix[q] = k
|
96
|
+
prefix
|
101
97
|
end
|
102
|
-
k += 1 if(str[k] == str[q])
|
103
|
-
result[q] = k
|
104
98
|
end
|
105
|
-
result
|
106
99
|
end
|
107
|
-
|
108
100
|
end
|
data/lib/boyer_moore/version.rb
CHANGED
data/test_file
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
123456
|
metadata
CHANGED
@@ -1,43 +1,43 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: boyer_moore
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Sri Harsha Kappala
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2016-06-23 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - "
|
17
|
+
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '0'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - "
|
24
|
+
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: rake
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - "
|
31
|
+
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '0'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - "
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '0'
|
41
41
|
description: Ruby wrapper for Boyer-Moore - The fastest search strategy, ever!
|
42
42
|
email:
|
43
43
|
- sriharsha.kappala@hotmail.com
|
@@ -55,6 +55,7 @@ files:
|
|
55
55
|
- boyer_moore.gemspec
|
56
56
|
- lib/boyer_moore.rb
|
57
57
|
- lib/boyer_moore/version.rb
|
58
|
+
- test_file
|
58
59
|
homepage: https://github.com/sriharshakappala/boyer_moore
|
59
60
|
licenses:
|
60
61
|
- MIT
|
@@ -76,7 +77,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
76
77
|
version: '0'
|
77
78
|
requirements: []
|
78
79
|
rubyforge_project:
|
79
|
-
rubygems_version: 2.4
|
80
|
+
rubygems_version: 2.6.4
|
80
81
|
signing_key:
|
81
82
|
specification_version: 4
|
82
83
|
summary: Ruby wrapper for BoyerMoore algorithm - The fastest search strategy, ever!
|