kmp 0.1.0 → 0.2.0

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.
Files changed (11) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +5 -0
  3. data/Gemfile.lock +1 -1
  4. data/README.md +78 -0
  5. data/benchmark.rb +60 -0
  6. data/benchmark.txt +70 -0
  7. data/ext/kmp/kmp_string.c +10 -10
  8. data/lib/kmp/kmp.so +0 -0
  9. data/lib/kmp/version.rb +1 -1
  10. metadata +4 -3
  11. data/banch_mark.rb +0 -19
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: e04c7a5db40803de18e97fc8a9344333a24564c7
4
- data.tar.gz: 3e84aa406dde540db0777c52ac910937f392c150
3
+ metadata.gz: f7d9ef58fc7947f5b3f2901cf4c52e7ad3e5ad99
4
+ data.tar.gz: 68909c1f9efaeef13ef684828c13b7e4c01b29aa
5
5
  SHA512:
6
- metadata.gz: 8378a07e3ef333d753997415784b82839bcf33a6792d9ed2aba9299fbd63c23ca2559d62e326282589a852caefec5752615068928ac147065ae25d8179193317
7
- data.tar.gz: 3f012d995f4e9d71bf4be6a01490ce075e52505a8cfa5e474169d4d2965406b01158992fca3b7635e3657f6d938a21bd8271dd239595bcd7056d7c44f5a9f15a
6
+ metadata.gz: 8cf863aaf38f13b29b0a8b1a5ddb2da28457e31d8064e2f0265614d3457ce653da7221984e58e0d424409c4a97018ffc3bbebaef4c8cd4a282a0752564c59deb
7
+ data.tar.gz: 378da39201d4cc1f38dfc6d99b249731fcfaf5ca91c3c3fe665a33627d7716dd64e8af00f0ce9fd6d5d78be45b645b2f7acf67354affdb9b3c5961f6180537b5
data/CHANGELOG.md CHANGED
@@ -1,3 +1,8 @@
1
1
  ## v0.1.0
2
2
  * initial release
3
3
  * implement kmp algorithm
4
+
5
+ ## v0.2.0
6
+ * memory allocation bug fix
7
+ * make function pointer constant
8
+ * improve code standard
data/Gemfile.lock CHANGED
@@ -1,7 +1,7 @@
1
1
  PATH
2
2
  remote: .
3
3
  specs:
4
- kmp (0.1.0)
4
+ kmp (0.2.0)
5
5
 
6
6
  GEM
7
7
  remote: https://rubygems.org/
data/README.md CHANGED
@@ -2,6 +2,8 @@
2
2
  [![Build Status](https://travis-ci.org/tanvir002700/kmp.svg?branch=master)](https://travis-ci.org/tanvir002700/kmp)
3
3
  [![Maintainability](https://api.codeclimate.com/v1/badges/69f40101eeb294c05163/maintainability)](https://codeclimate.com/github/tanvir002700/kmp/maintainability)
4
4
  [![Coverage Status](https://coveralls.io/repos/github/tanvir002700/kmp/badge.svg?branch=master)](https://coveralls.io/github/tanvir002700/kmp?branch=master)
5
+ [![Gem Version](https://badge.fury.io/rb/kmp.svg)](https://badge.fury.io/rb/kmp)
6
+ [![Downloads](https://img.shields.io/gem/dt/kmp.svg)](https://rubygems.org/gems/kmp)
5
7
  [![GitHub last commit (branch)](https://img.shields.io/github/last-commit/tanvir002700/kmp/master.svg)](https://github.com/tanvir002700/kmp)
6
8
  [![license](https://img.shields.io/github/license/tanvir002700/kmp.svg)](https://github.com/tanvir002700/kmp/blob/master/LICENSE)
7
9
 
@@ -39,6 +41,82 @@ k.length #=> 7
39
41
  - match function complexity O(N+M), N original text string length, M match string length
40
42
  - length complexity O(1)
41
43
 
44
+ ## Benchmark
45
+ This benchmark between kmp implementation in c-extenstion vs pure ruby. [Benchmark](http://ruby-doc.org/stdlib-2.0.0/libdoc/benchmark/rdoc/Benchmark.html) module use for comparison.
46
+
47
+ ```
48
+ lenght of string: 500
49
+ Rehearsal -----------------------------------------------
50
+ c-extension 0.000000 0.000000 0.000000 ( 0.000028)
51
+ ruby 0.000000 0.000000 0.000000 ( 0.001067)
52
+ -------------------------------------- total: 0.000000sec
53
+
54
+ user system total real
55
+ c-extension 0.000000 0.000000 0.000000 ( 0.000019)
56
+ ruby 0.000000 0.000000 0.000000 ( 0.000731)
57
+
58
+ lenght of string: 5000
59
+ Rehearsal -----------------------------------------------
60
+ c-extension 0.000000 0.000000 0.000000 ( 0.000074)
61
+ ruby 0.000000 0.000000 0.000000 ( 0.006990)
62
+ -------------------------------------- total: 0.000000sec
63
+
64
+ user system total real
65
+ c-extension 0.000000 0.000000 0.000000 ( 0.000059)
66
+ ruby 0.000000 0.000000 0.000000 ( 0.003058)
67
+
68
+ lenght of string: 50000
69
+ Rehearsal -----------------------------------------------
70
+ c-extension 0.000000 0.000000 0.000000 ( 0.000276)
71
+ ruby 0.030000 0.000000 0.030000 ( 0.022061)
72
+ -------------------------------------- total: 0.030000sec
73
+
74
+ user system total real
75
+ c-extension 0.000000 0.000000 0.000000 ( 0.000117)
76
+ ruby 0.010000 0.000000 0.010000 ( 0.014624)
77
+
78
+ lenght of string: 500000
79
+ Rehearsal -----------------------------------------------
80
+ c-extension 0.000000 0.000000 0.000000 ( 0.001346)
81
+ ruby 0.140000 0.000000 0.140000 ( 0.147500)
82
+ -------------------------------------- total: 0.140000sec
83
+
84
+ user system total real
85
+ c-extension 0.000000 0.000000 0.000000 ( 0.001188)
86
+ ruby 0.140000 0.000000 0.140000 ( 0.146642)
87
+
88
+ lenght of string: 5000000
89
+ Rehearsal -----------------------------------------------
90
+ c-extension 0.010000 0.000000 0.010000 ( 0.013171)
91
+ ruby 1.480000 0.010000 1.490000 ( 1.482893)
92
+ -------------------------------------- total: 1.500000sec
93
+
94
+ user system total real
95
+ c-extension 0.010000 0.000000 0.010000 ( 0.013098)
96
+ ruby 1.510000 0.000000 1.510000 ( 1.508361)
97
+
98
+ lenght of string: 50000000
99
+ Rehearsal -----------------------------------------------
100
+ c-extension 0.120000 0.020000 0.140000 ( 0.143160)
101
+ ruby 16.320000 0.020000 16.340000 ( 16.356332)
102
+ ------------------------------------- total: 16.480000sec
103
+
104
+ user system total real
105
+ c-extension 0.120000 0.010000 0.130000 ( 0.143203)
106
+ ruby 15.130000 0.050000 15.180000 ( 15.191924)
107
+
108
+ lenght of string: 500000000
109
+ Rehearsal -----------------------------------------------
110
+ c-extension 1.190000 0.200000 1.390000 ( 1.491211)
111
+ ruby 159.510000 0.210000 159.720000 (159.723059)
112
+ ------------------------------------ total: 161.110000sec
113
+
114
+ user system total real
115
+ c-extension 1.270000 0.200000 1.470000 ( 1.568321)
116
+ ruby 161.190000 0.250000 161.440000 (161.449839)
117
+
118
+ ```
119
+
42
120
  ## Development
43
121
 
44
122
  After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment. For compile c extension run `rake compile`.
data/benchmark.rb ADDED
@@ -0,0 +1,60 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "bundler/setup"
4
+ require "kmp"
5
+
6
+ def compute_prefix(ptrn)
7
+ m = ptrn.size
8
+ prefix = Array.new m, 0
9
+ k = -1
10
+ prefix[0] = -1
11
+ (m-1).times do |i|
12
+ i = i + 1
13
+ while k>-1 && ptrn[k+1] != ptrn[i] do
14
+ k = prefix[k];
15
+ end
16
+ if ptrn[k+1] == ptrn[i]
17
+ k = k + 1
18
+ end
19
+ prefix[i] = k
20
+ end
21
+ prefix
22
+ end
23
+
24
+ def kmp_ruby(txt, ptrn)
25
+ prefix = compute_prefix(ptrn)
26
+ n = txt.size
27
+ m = ptrn.size
28
+ pos = []
29
+
30
+ q = -1
31
+ (n).times do |i|
32
+ while(q>-1 && ptrn[q+1]!=txt[i]) do
33
+ q = prefix[q]
34
+ end
35
+ if ptrn[q+1] == txt[i]
36
+ q = q + 1
37
+ end
38
+ if q == (m-1)
39
+ pos << (i-m+1)
40
+ q = prefix[q]
41
+ end
42
+ end
43
+ return pos
44
+ end
45
+
46
+ require 'benchmark'
47
+
48
+ n = 1
49
+ 7.times do |t|
50
+ n = n * 10;
51
+ txt = ''
52
+ (n).times{txt << 'xpyyubzabcabcabcabcabcabcabcabcabcabcxyzabukxpyksl'}
53
+ puts "lenght of string: #{txt.size}"
54
+ a = Kmp::String.new(txt);
55
+ Benchmark.bmbm do |x|
56
+ x.report("c-extension") { a.match 'abcabcabcabcabcabc' }
57
+ x.report("ruby") { kmp_ruby(txt, 'abcabcabcabcabcabc') }
58
+ end
59
+ puts ""
60
+ end
data/benchmark.txt ADDED
@@ -0,0 +1,70 @@
1
+ lenght of string: 500
2
+ Rehearsal -----------------------------------------------
3
+ c-extension 0.000000 0.000000 0.000000 ( 0.000028)
4
+ ruby 0.000000 0.000000 0.000000 ( 0.001067)
5
+ -------------------------------------- total: 0.000000sec
6
+
7
+ user system total real
8
+ c-extension 0.000000 0.000000 0.000000 ( 0.000019)
9
+ ruby 0.000000 0.000000 0.000000 ( 0.000731)
10
+
11
+ lenght of string: 5000
12
+ Rehearsal -----------------------------------------------
13
+ c-extension 0.000000 0.000000 0.000000 ( 0.000074)
14
+ ruby 0.000000 0.000000 0.000000 ( 0.006990)
15
+ -------------------------------------- total: 0.000000sec
16
+
17
+ user system total real
18
+ c-extension 0.000000 0.000000 0.000000 ( 0.000059)
19
+ ruby 0.000000 0.000000 0.000000 ( 0.003058)
20
+
21
+ lenght of string: 50000
22
+ Rehearsal -----------------------------------------------
23
+ c-extension 0.000000 0.000000 0.000000 ( 0.000276)
24
+ ruby 0.030000 0.000000 0.030000 ( 0.022061)
25
+ -------------------------------------- total: 0.030000sec
26
+
27
+ user system total real
28
+ c-extension 0.000000 0.000000 0.000000 ( 0.000117)
29
+ ruby 0.010000 0.000000 0.010000 ( 0.014624)
30
+
31
+ lenght of string: 500000
32
+ Rehearsal -----------------------------------------------
33
+ c-extension 0.000000 0.000000 0.000000 ( 0.001346)
34
+ ruby 0.140000 0.000000 0.140000 ( 0.147500)
35
+ -------------------------------------- total: 0.140000sec
36
+
37
+ user system total real
38
+ c-extension 0.000000 0.000000 0.000000 ( 0.001188)
39
+ ruby 0.140000 0.000000 0.140000 ( 0.146642)
40
+
41
+ lenght of string: 5000000
42
+ Rehearsal -----------------------------------------------
43
+ c-extension 0.010000 0.000000 0.010000 ( 0.013171)
44
+ ruby 1.480000 0.010000 1.490000 ( 1.482893)
45
+ -------------------------------------- total: 1.500000sec
46
+
47
+ user system total real
48
+ c-extension 0.010000 0.000000 0.010000 ( 0.013098)
49
+ ruby 1.510000 0.000000 1.510000 ( 1.508361)
50
+
51
+ lenght of string: 50000000
52
+ Rehearsal -----------------------------------------------
53
+ c-extension 0.120000 0.020000 0.140000 ( 0.143160)
54
+ ruby 16.320000 0.020000 16.340000 ( 16.356332)
55
+ ------------------------------------- total: 16.480000sec
56
+
57
+ user system total real
58
+ c-extension 0.120000 0.010000 0.130000 ( 0.143203)
59
+ ruby 15.130000 0.050000 15.180000 ( 15.191924)
60
+
61
+ lenght of string: 500000000
62
+ Rehearsal -----------------------------------------------
63
+ c-extension 1.190000 0.200000 1.390000 ( 1.491211)
64
+ ruby 159.510000 0.210000 159.720000 (159.723059)
65
+ ------------------------------------ total: 161.110000sec
66
+
67
+ user system total real
68
+ c-extension 1.270000 0.200000 1.470000 ( 1.568321)
69
+ ruby 161.190000 0.250000 161.440000 (161.449839)
70
+
data/ext/kmp/kmp_string.c CHANGED
@@ -27,7 +27,7 @@ static VALUE initialize(VALUE self, VALUE rb_string)
27
27
  Check_Type(rb_string, T_STRING);
28
28
  Data_Get_Struct(self, struct Str, str);
29
29
 
30
- str->ptr = calloc(RSTRING_LEN(rb_string) , sizeof(char));
30
+ str->ptr = calloc(RSTRING_LEN(rb_string) + 1 , sizeof(char));
31
31
  memcpy(str->ptr, StringValuePtr(rb_string), RSTRING_LEN(rb_string));
32
32
 
33
33
  rb_iv_set(self, "@str", rb_string);
@@ -36,15 +36,14 @@ static VALUE initialize(VALUE self, VALUE rb_string)
36
36
  return self;
37
37
  }
38
38
 
39
- static int* compute_prefix(char *str)
39
+ static int* compute_prefix(const char *str)
40
40
  {
41
41
  int len = strlen(str);
42
-
42
+ int k = -1;
43
43
  int * prefix;
44
- prefix = calloc(len+1, sizeof(int));
45
44
 
45
+ prefix = (int *) calloc(len+1, sizeof(int));
46
46
  prefix[0] = -1;
47
- int k = -1;
48
47
 
49
48
  for(int i=1; i<len; i++)
50
49
  {
@@ -62,20 +61,21 @@ static VALUE match(VALUE self, VALUE rb_str)
62
61
  char * str;
63
62
  char * ptrn;
64
63
  int * prefix;
64
+ int n,m,q;
65
65
 
66
66
  Data_Get_Struct(self, struct Str, obj);
67
- str = calloc(strlen(obj->ptr), sizeof(char));
67
+ str = calloc(strlen(obj->ptr) + 1, sizeof(char));
68
68
  strcpy(str, obj->ptr);
69
69
 
70
- ptrn = calloc(RSTRING_LEN(rb_str), sizeof(char));
70
+ ptrn = (char *) calloc(RSTRING_LEN(rb_str) + 1, sizeof(char));
71
71
  memcpy(ptrn, StringValuePtr(rb_str), RSTRING_LEN(rb_str));
72
72
 
73
73
  prefix = compute_prefix(ptrn);
74
74
 
75
- int n = strlen(str);
76
- int m = strlen(ptrn);
75
+ n = strlen(str);
76
+ m = strlen(ptrn);
77
77
 
78
- int q = -1;
78
+ q = -1;
79
79
  for(int i=0; i<n; i++)
80
80
  {
81
81
  while( q>-1 && ptrn[q+1]!=str[i] ) q = prefix[q];
data/lib/kmp/kmp.so CHANGED
Binary file
data/lib/kmp/version.rb CHANGED
@@ -1,3 +1,3 @@
1
1
  module Kmp
2
- VERSION = "0.1.0"
2
+ VERSION = "0.2.0"
3
3
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: kmp
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.0
4
+ version: 0.2.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - tanvir hasan
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2018-02-02 00:00:00.000000000 Z
11
+ date: 2018-02-04 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: bundler
@@ -108,7 +108,8 @@ files:
108
108
  - LICENSE.txt
109
109
  - README.md
110
110
  - Rakefile
111
- - banch_mark.rb
111
+ - benchmark.rb
112
+ - benchmark.txt
112
113
  - bin/console
113
114
  - bin/setup
114
115
  - ext/kmp/extconf.rb
data/banch_mark.rb DELETED
@@ -1,19 +0,0 @@
1
- #!/usr/bin/env ruby
2
-
3
- require "bundler/setup"
4
- require "kmp"
5
-
6
- #(0...50).map { ('a'..'z').to_a[rand(26)] }.join
7
- txt = ''
8
- 10000.times{txt << 'abc'}
9
-
10
- t1 = Time.now
11
- a = Kmp::String.new txt
12
- b = a.match 'abcabcabcabcabcabc'
13
- puts Time.now - t1
14
- puts b.length
15
-
16
- t1 = Time.now
17
- b = txt.enum_for(:scan, /(?=abcabcabcabcabcabc)/).map { Regexp.last_match.offset(0).first }
18
- puts Time.now - t1
19
- puts b.size