sort_index 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/.travis.yml +4 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +75 -0
- data/Rakefile +6 -0
- data/bin/console +10 -0
- data/bin/setup +7 -0
- data/lib/sort_index/file.rb +104 -0
- data/lib/sort_index/version.rb +3 -0
- data/lib/sort_index.rb +5 -0
- data/sort_index.gemspec +32 -0
- metadata +121 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 44dd87ebf9e2728f47050cfa271ed013f7af834d
|
4
|
+
data.tar.gz: cf3f99237d86fa6caed70a84ab57b5df06eb23c5
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 867b0ba9295f54cedcb616da6101e7aeac773c9688a42255d5ee4d3feab137767c767c7d7ba42ce87ed16e7302e8b66b0601eaee8b04b6df15162f771222d26e
|
7
|
+
data.tar.gz: 0bfdeed7a173e601e4d036586000bf66175a9bb7bcc72fa1e5971f5b750aa21d7351dfeebda4bdeec4b897dc6a52389522b4b390795d8c464cfa72d87dcb182d
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 Scott Pierce
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
# SortIndex
|
2
|
+
Proof of concept to maintain a file with sorted and unique values.
|
3
|
+
This could be helpful for building building indexes.
|
4
|
+
|
5
|
+
`Range#bsearch` is used to determine if a line is already in the file and
|
6
|
+
to determine where a line should be inserted. This means Ruby 2.0 is required.
|
7
|
+
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
```ruby
|
13
|
+
gem 'sort_index'
|
14
|
+
```
|
15
|
+
|
16
|
+
And then execute:
|
17
|
+
|
18
|
+
$ bundle
|
19
|
+
|
20
|
+
Or install it yourself as:
|
21
|
+
|
22
|
+
$ gem install sort_index
|
23
|
+
|
24
|
+
## Usage
|
25
|
+
|
26
|
+
Use `sorted_puts` on the File instance instead of `write`, `<<`, etc.
|
27
|
+
|
28
|
+
```ruby
|
29
|
+
SortIndex::File.open('animals', 'w+') do |f|
|
30
|
+
f.sorted_puts 'cat' # add stuff out of order
|
31
|
+
f.sorted_puts 'bat'
|
32
|
+
f.sorted_puts 'dog'
|
33
|
+
f.sorted_puts 'ant'
|
34
|
+
f.sorted_puts 'cat' # duplicate on purpose
|
35
|
+
end
|
36
|
+
|
37
|
+
IO.read('animals')
|
38
|
+
=> "ant\nbat\ncat\ndog\n"
|
39
|
+
```
|
40
|
+
|
41
|
+
## Gotchas
|
42
|
+
Performance of writes is probably the biggest problem. There really isn't a
|
43
|
+
great way to insert lines in the middle of a file. So we do it the naive way.
|
44
|
+
|
45
|
+
1. save current position `IO#tell`
|
46
|
+
2. read the remaining bytes of the file using `IO#read`
|
47
|
+
3. write the line at the current position
|
48
|
+
4. write the rest of the contents from step 2.
|
49
|
+
|
50
|
+
Common sense would say don't create gigabyte files this way. Use unix calls
|
51
|
+
instead:
|
52
|
+
|
53
|
+
```sh
|
54
|
+
echo 'cat' >> animals
|
55
|
+
echo 'bat' >> animals
|
56
|
+
echo 'dog' >> animals
|
57
|
+
echo 'ant' >> animals
|
58
|
+
sort -u animals
|
59
|
+
```
|
60
|
+
|
61
|
+
## Development
|
62
|
+
|
63
|
+
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.
|
64
|
+
|
65
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
66
|
+
|
67
|
+
## Contributing
|
68
|
+
|
69
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/ddrscott/sort_index.
|
70
|
+
|
71
|
+
|
72
|
+
## License
|
73
|
+
|
74
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
75
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
data/bin/setup
ADDED
@@ -0,0 +1,104 @@
|
|
1
|
+
module SortIndex
|
2
|
+
class File < ::File
|
3
|
+
|
4
|
+
# adds the line to the while maintaining the data's sort order
|
5
|
+
#
|
6
|
+
# @param [String] line to add to the file, it should not have it's own line ending.
|
7
|
+
# @return [Nil] always returns nil to match standard #puts method
|
8
|
+
def sorted_puts(line)
|
9
|
+
if line == nil || line.size == 0
|
10
|
+
raise ArgumentError, 'Line cannot be blank!'
|
11
|
+
end
|
12
|
+
if line.index($/)
|
13
|
+
raise ArgumentError, "Cannot `puts` a line with extra line endings. Make sure the line does not contain `#{$/.inspect}`"
|
14
|
+
end
|
15
|
+
|
16
|
+
matched, idx = binary_seek(line)
|
17
|
+
|
18
|
+
if matched
|
19
|
+
# an exact match was found, nothing to do
|
20
|
+
else
|
21
|
+
if idx == nil
|
22
|
+
# append to end of file
|
23
|
+
self.seek(0, IO::SEEK_END)
|
24
|
+
puts(line)
|
25
|
+
else
|
26
|
+
self.seek(cached_positions[idx][0], IO::SEEK_SET)
|
27
|
+
do_at_current_position{puts(line)}
|
28
|
+
end
|
29
|
+
update_cached_position(idx, line)
|
30
|
+
end
|
31
|
+
nil
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
|
36
|
+
# Builds an Array of position and length of the current file.
|
37
|
+
# @return [Array[Array[Fixnum,Fixnum]]] array of position, line length pairs
|
38
|
+
def index_each_line
|
39
|
+
positions = []
|
40
|
+
size = 0
|
41
|
+
each_line do |line|
|
42
|
+
positions << [size, line.size]
|
43
|
+
size += line.size
|
44
|
+
end
|
45
|
+
rewind
|
46
|
+
positions
|
47
|
+
end
|
48
|
+
|
49
|
+
# remembers current file position, reads everything at the position
|
50
|
+
# execute the block, and put everything back.
|
51
|
+
# This routine is really bad for huge files since it could run out of
|
52
|
+
# memory.
|
53
|
+
def do_at_current_position(&block)
|
54
|
+
current_position = self.tell
|
55
|
+
huge_buffer = self.read
|
56
|
+
self.seek(current_position, IO::SEEK_SET)
|
57
|
+
block.call
|
58
|
+
ensure
|
59
|
+
self.write huge_buffer
|
60
|
+
end
|
61
|
+
|
62
|
+
def update_cached_position(idx, line)
|
63
|
+
line_size_with_ending = line.size + $/.size
|
64
|
+
if idx
|
65
|
+
# add an entry to the positions
|
66
|
+
prev_pos = cached_positions[idx][0]
|
67
|
+
cached_positions.insert(idx, [prev_pos, line_size_with_ending])
|
68
|
+
|
69
|
+
# move all other entries ahead by the new entries length
|
70
|
+
(idx+1).upto(cached_positions.size-1).each do |i|
|
71
|
+
prev_pos = cached_positions[i][0]
|
72
|
+
cached_positions[i][0] = prev_pos + line_size_with_ending
|
73
|
+
end
|
74
|
+
elsif cached_positions.empty?
|
75
|
+
cached_positions << [0, line_size_with_ending]
|
76
|
+
else
|
77
|
+
last_pos, last_size = *cached_positions.last
|
78
|
+
cached_positions << [last_pos + last_size, line_size_with_ending]
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
def cached_positions
|
83
|
+
@cached_positions ||= index_each_line
|
84
|
+
end
|
85
|
+
|
86
|
+
# @return [Boolean, Fixnum] true if exact match, the minimum position index
|
87
|
+
def binary_seek(val)
|
88
|
+
return nil if cached_positions.empty?
|
89
|
+
|
90
|
+
last_line = nil
|
91
|
+
idx = (0...@cached_positions.size).bsearch do |i|
|
92
|
+
last_pair = @cached_positions[i]
|
93
|
+
pos, len = *last_pair
|
94
|
+
self.seek(pos, IO::SEEK_SET)
|
95
|
+
|
96
|
+
# we don't want to compare the line ending
|
97
|
+
last_line = self.read(len).strip
|
98
|
+
last_line >= val
|
99
|
+
end
|
100
|
+
return last_line == val, idx
|
101
|
+
end
|
102
|
+
# END private
|
103
|
+
end
|
104
|
+
end
|
data/lib/sort_index.rb
ADDED
data/sort_index.gemspec
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'sort_index/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.required_ruby_version = '>= 2.0.0'
|
8
|
+
spec.name = 'sort_index'
|
9
|
+
spec.version = SortIndex::VERSION
|
10
|
+
spec.authors = ['Scott Pierce']
|
11
|
+
spec.email = ['ddrscott@gmail.com']
|
12
|
+
|
13
|
+
spec.summary = %q{Simple File wrapper to keep file contents unique and sorted as lines are added.}
|
14
|
+
spec.description = <<-RDOC
|
15
|
+
== Description ==
|
16
|
+
Proof of concept to maintain a file with sorted and unique values.
|
17
|
+
This could be helpful for building building indexes.
|
18
|
+
|
19
|
+
Range#bsearch is used to determine if a line is already in the file and
|
20
|
+
to determine where a line should be inserted. This means Ruby 2.0 is required.
|
21
|
+
RDOC
|
22
|
+
spec.homepage = 'https://github.com/ddrscott/sort_index'
|
23
|
+
spec.license = 'MIT'
|
24
|
+
|
25
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
26
|
+
spec.require_paths = ['lib']
|
27
|
+
|
28
|
+
spec.add_development_dependency 'bundler', '~> 1.10'
|
29
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
30
|
+
spec.add_development_dependency 'rspec', '~> 3.2.0'
|
31
|
+
spec.add_development_dependency 'pry', '~> 0.10.3'
|
32
|
+
end
|
metadata
ADDED
@@ -0,0 +1,121 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: sort_index
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Scott Pierce
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-12-26 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.10'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.10'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 3.2.0
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 3.2.0
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 0.10.3
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 0.10.3
|
69
|
+
description: |
|
70
|
+
== Description ==
|
71
|
+
Proof of concept to maintain a file with sorted and unique values.
|
72
|
+
This could be helpful for building building indexes.
|
73
|
+
|
74
|
+
Range#bsearch is used to determine if a line is already in the file and
|
75
|
+
to determine where a line should be inserted. This means Ruby 2.0 is required.
|
76
|
+
email:
|
77
|
+
- ddrscott@gmail.com
|
78
|
+
executables: []
|
79
|
+
extensions: []
|
80
|
+
extra_rdoc_files: []
|
81
|
+
files:
|
82
|
+
- ".gitignore"
|
83
|
+
- ".rspec"
|
84
|
+
- ".travis.yml"
|
85
|
+
- Gemfile
|
86
|
+
- LICENSE.txt
|
87
|
+
- README.md
|
88
|
+
- Rakefile
|
89
|
+
- bin/console
|
90
|
+
- bin/setup
|
91
|
+
- lib/sort_index.rb
|
92
|
+
- lib/sort_index/file.rb
|
93
|
+
- lib/sort_index/version.rb
|
94
|
+
- sort_index.gemspec
|
95
|
+
homepage: https://github.com/ddrscott/sort_index
|
96
|
+
licenses:
|
97
|
+
- MIT
|
98
|
+
metadata: {}
|
99
|
+
post_install_message:
|
100
|
+
rdoc_options: []
|
101
|
+
require_paths:
|
102
|
+
- lib
|
103
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
104
|
+
requirements:
|
105
|
+
- - ">="
|
106
|
+
- !ruby/object:Gem::Version
|
107
|
+
version: 2.0.0
|
108
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
109
|
+
requirements:
|
110
|
+
- - ">="
|
111
|
+
- !ruby/object:Gem::Version
|
112
|
+
version: '0'
|
113
|
+
requirements: []
|
114
|
+
rubyforge_project:
|
115
|
+
rubygems_version: 2.4.5.1
|
116
|
+
signing_key:
|
117
|
+
specification_version: 4
|
118
|
+
summary: Simple File wrapper to keep file contents unique and sorted as lines are
|
119
|
+
added.
|
120
|
+
test_files: []
|
121
|
+
has_rdoc:
|