bise 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +5 -0
- data/Gemfile +9 -0
- data/LICENSE +21 -0
- data/README.rdoc +25 -0
- data/Rakefile +1 -0
- data/bise.gemspec +22 -0
- data/gem +84 -0
- data/lib/bise/version.rb +3 -0
- data/lib/bise.rb +41 -0
- data/spec/bise_spec.rb +34 -0
- data/spec/dict +5 -0
- data/spec/spec_helper.rb +7 -0
- metadata +68 -0
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
Copyright (c) 2011 Eugene Kalenkovich
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
21
|
+
|
data/README.rdoc
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
= Bise
|
2
|
+
Binary search for presorted text files. Finds the first occurance of a string
|
3
|
+
with value >= provided term.
|
4
|
+
|
5
|
+
Finds the first string in the oredered file that satisfies term <= str.
|
6
|
+
|
7
|
+
Takes optional comparison block accepting term and str.
|
8
|
+
|
9
|
+
Default - { |term, str| term <=> str }
|
10
|
+
|
11
|
+
== Installation
|
12
|
+
|
13
|
+
gem install rhymes
|
14
|
+
|
15
|
+
|
16
|
+
== Usage
|
17
|
+
require 'bise'
|
18
|
+
# find word in dictionary
|
19
|
+
File.open('/usr/share/dict/words'){|f| f.bin_find('bo')}
|
20
|
+
|
21
|
+
# find ip-to-country record
|
22
|
+
`wget "http://software77.net/geo-ip/?DL=1" -O IpToCountry.csv.gz && gunzip IpToCountry.csv.gz`
|
23
|
+
require 'ipaddr'
|
24
|
+
File.open('../../files/IpToCountry.csv'){|f| f.bin_find(IPAddr.new('72.4.120.124').to_i){|num,str|
|
25
|
+
l,r = str.gsub('"','').split(',').first(2).map(&:to_i); r ||= 0; (l..r) === num ? 0 : num < l ? -1 : 1}}
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/bise.gemspec
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "bise/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "bise"
|
7
|
+
s.version = Bise::VERSION
|
8
|
+
s.authors = ["Eugene Kalenkovich"]
|
9
|
+
s.email = ["rubify@softover.com"]
|
10
|
+
s.homepage = ""
|
11
|
+
s.summary = %q{Binary search in text files}
|
12
|
+
s.description = %q{Binary search in ordered text files}
|
13
|
+
|
14
|
+
s.rubyforge_project = "bise"
|
15
|
+
|
16
|
+
s.files = `git ls-files`.split("\n")
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
19
|
+
s.require_paths = ["lib"]
|
20
|
+
|
21
|
+
s.add_development_dependency "rspec"
|
22
|
+
end
|
data/gem
ADDED
@@ -0,0 +1,84 @@
|
|
1
|
+
module BinarySearch
|
2
|
+
def bin_find(term)
|
3
|
+
if block_given?
|
4
|
+
compare = lambda { |a, b| yield(a, b) }
|
5
|
+
else
|
6
|
+
compare = lambda { |a, b| a <=> b }
|
7
|
+
end
|
8
|
+
bin_search(term, 0, stat.size, &compare)
|
9
|
+
end
|
10
|
+
|
11
|
+
private
|
12
|
+
|
13
|
+
def bin_search(term, start, finish, &block)
|
14
|
+
pos = (start + finish + 1) / 2
|
15
|
+
seek pos
|
16
|
+
gets unless pos == 0
|
17
|
+
str = gets
|
18
|
+
return str if start >= finish
|
19
|
+
return nil unless str
|
20
|
+
comp = yield(term, str)
|
21
|
+
case comp
|
22
|
+
when 1
|
23
|
+
bin_search(term, pos, finish, &block)
|
24
|
+
when -1
|
25
|
+
pos == finish ? str : bin_search(term, start, pos, &block)
|
26
|
+
else
|
27
|
+
str
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
class File < IO
|
33
|
+
include BinarySearch
|
34
|
+
end
|
35
|
+
|
36
|
+
|
37
|
+
#nums=[]
|
38
|
+
#out=true
|
39
|
+
#max = (4294967295 - 50331648) + 50331647
|
40
|
+
#if ARGV[0] == '-test'
|
41
|
+
# n=ARGV[1].to_i
|
42
|
+
# n.times{ nums << rand( max + 1 )}
|
43
|
+
# out=false
|
44
|
+
#else
|
45
|
+
# ARGV.each do |argv|
|
46
|
+
# nums << argv.to_i #((($1.to_i*256)+$2.to_i)*256+$3.to_i)*256+$4.to_i if argv=~/(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})/
|
47
|
+
# end
|
48
|
+
#end
|
49
|
+
#if nums.empty?
|
50
|
+
# puts "Please enter valid ip(s)"
|
51
|
+
# exit
|
52
|
+
#end
|
53
|
+
#
|
54
|
+
#nums.each do |num|
|
55
|
+
# ctry='Unknown'
|
56
|
+
# res=bin_find('../files/IpToCountry.csv',num) { |search, str|
|
57
|
+
# res = nil
|
58
|
+
# if str.empty? || str[0,1]!='"'
|
59
|
+
# res = 1
|
60
|
+
# else
|
61
|
+
# l, r = str.gsub('"','').split(',')[0,2].map(&:to_i)
|
62
|
+
# if (l..r) === search
|
63
|
+
# res = 0
|
64
|
+
# else
|
65
|
+
# res = search > r ? 1 : -1
|
66
|
+
# end
|
67
|
+
# res
|
68
|
+
# end
|
69
|
+
# }.gsub('"','').split(',')
|
70
|
+
# ctry=res[4] if (res[0].to_i..res[1].to_i)===num
|
71
|
+
# puts ctry if out
|
72
|
+
#end
|
73
|
+
|
74
|
+
itc_compare = lambda do |num, str|
|
75
|
+
return 1 if str.empty? || str[0] != '"'
|
76
|
+
l, r = str.gsub('"','').split(',')[0,2].map(&:to_i)
|
77
|
+
return 0 if (l..r) === num
|
78
|
+
num > r ? 1 : -1
|
79
|
+
end
|
80
|
+
|
81
|
+
num = (($1.to_i << 8 | $2.to_i) << 8 | $3.to_i ) << 8 | $4.to_i if ARGV[0]=~/(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})/
|
82
|
+
puts File.open('/usr/share/dict/words'){|f| f.bin_find(ARGV[0])}
|
83
|
+
puts File.open('../files/IpToCountry.csv'){|f| f.bin_find(num, &itc_compare}
|
84
|
+
|
data/lib/bise/version.rb
ADDED
data/lib/bise.rb
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
require "bise/version"
|
2
|
+
|
3
|
+
module Bise
|
4
|
+
##
|
5
|
+
# Finds the first string in the presorted text file that satisfies term <= str.
|
6
|
+
# Takes optional comparison block accepting term and str.
|
7
|
+
# Default - { |term, str| term <=> str }
|
8
|
+
|
9
|
+
def bin_find(term, &comp)
|
10
|
+
comp ||= lambda{|term, str| term <=> str}
|
11
|
+
bin_search(term, 0, stat.size, &comp)
|
12
|
+
end
|
13
|
+
|
14
|
+
|
15
|
+
private
|
16
|
+
|
17
|
+
def bin_search(term, start, finish, &comp)
|
18
|
+
pos = (start + finish) / 2
|
19
|
+
seek pos
|
20
|
+
gets unless pos == 0
|
21
|
+
str = gets
|
22
|
+
return str && str.chomp if start >= finish
|
23
|
+
return nil unless str
|
24
|
+
case yield(term, str.chomp!)
|
25
|
+
when 1
|
26
|
+
next_str = gets
|
27
|
+
return nil unless next_str
|
28
|
+
return next_str if yield(term, next_str.chomp!) != 1
|
29
|
+
return bin_search(term, pos, finish, &comp) if start < pos
|
30
|
+
start == 0 ? str : next_str
|
31
|
+
when -1
|
32
|
+
bin_search(term, start, pos, &comp)
|
33
|
+
else
|
34
|
+
str
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
class File
|
40
|
+
include Bise
|
41
|
+
end
|
data/spec/bise_spec.rb
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
#rubs
|
3
|
+
#ruby
|
4
|
+
#ruby's
|
5
|
+
#rubying
|
6
|
+
#rucksack
|
7
|
+
|
8
|
+
describe Bise do
|
9
|
+
before(:all) do
|
10
|
+
@dict = File.join(File.dirname(__FILE__), 'dict')
|
11
|
+
end
|
12
|
+
|
13
|
+
it 'should find first line for "small" term' do
|
14
|
+
File.open(@dict){|f| f.bin_find('a')}.should == 'rubs'
|
15
|
+
File.open(@dict){|f| f.bin_find('A'){|t,s| t.downcase <=> s}}.should == 'rubs'
|
16
|
+
end
|
17
|
+
|
18
|
+
it 'should find full word for starting part' do
|
19
|
+
File.open(@dict){|f| f.bin_find('rubyi')}.should == 'rubying'
|
20
|
+
File.open(@dict){|f| f.bin_find('RuByI'){|t,s| t.downcase <=> s}}.should == 'rubying'
|
21
|
+
end
|
22
|
+
|
23
|
+
it 'should find exact word' do
|
24
|
+
File.open(@dict){|f| f.bin_find('ruby')}.should == 'ruby'
|
25
|
+
File.open(@dict){|f| f.bin_find('rUbY'){|t,s| t.downcase <=> s}}.should == 'ruby'
|
26
|
+
end
|
27
|
+
|
28
|
+
it 'should find nothing for "big" term' do
|
29
|
+
File.open(@dict){|f| f.bin_find('z')}.should == nil
|
30
|
+
File.open(@dict){|f| f.bin_find('Z'){|t,s| t.downcase <=> s}}.should == nil
|
31
|
+
end
|
32
|
+
|
33
|
+
|
34
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,68 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: bise
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Eugene Kalenkovich
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2011-10-28 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: &70027100 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70027100
|
25
|
+
description: Binary search in ordered text files
|
26
|
+
email:
|
27
|
+
- rubify@softover.com
|
28
|
+
executables: []
|
29
|
+
extensions: []
|
30
|
+
extra_rdoc_files: []
|
31
|
+
files:
|
32
|
+
- .gitignore
|
33
|
+
- Gemfile
|
34
|
+
- LICENSE
|
35
|
+
- README.rdoc
|
36
|
+
- Rakefile
|
37
|
+
- bise.gemspec
|
38
|
+
- gem
|
39
|
+
- lib/bise.rb
|
40
|
+
- lib/bise/version.rb
|
41
|
+
- spec/bise_spec.rb
|
42
|
+
- spec/dict
|
43
|
+
- spec/spec_helper.rb
|
44
|
+
homepage: ''
|
45
|
+
licenses: []
|
46
|
+
post_install_message:
|
47
|
+
rdoc_options: []
|
48
|
+
require_paths:
|
49
|
+
- lib
|
50
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
51
|
+
none: false
|
52
|
+
requirements:
|
53
|
+
- - ! '>='
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: '0'
|
56
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
requirements: []
|
63
|
+
rubyforge_project: bise
|
64
|
+
rubygems_version: 1.8.11
|
65
|
+
signing_key:
|
66
|
+
specification_version: 3
|
67
|
+
summary: Binary search in text files
|
68
|
+
test_files: []
|