masticate 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +18 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +29 -0
- data/Rakefile +8 -0
- data/lib/masticate/sniffer.rb +40 -0
- data/lib/masticate/version.rb +3 -0
- data/lib/masticate.rb +8 -0
- data/masticate.gemspec +20 -0
- data/spec/data/pipe_data.txt +5 -0
- data/spec/data/tabbed_data.txt +5 -0
- data/spec/spec/sniffer_spec.rb +21 -0
- data/spec/spec_helper.rb +34 -0
- metadata +74 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Jason May
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# Masticate
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'masticate'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install masticate
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,40 @@
|
|
1
|
+
class Masticate::Sniffer
|
2
|
+
attr_reader :file
|
3
|
+
attr_reader :col_sep
|
4
|
+
|
5
|
+
CandidateDelimiters = [',', '|', "\t"]
|
6
|
+
|
7
|
+
def initialize(file)
|
8
|
+
@file = file
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.sniff(file)
|
12
|
+
sniffer = new(file)
|
13
|
+
sniffer.sniff
|
14
|
+
end
|
15
|
+
|
16
|
+
def sniff
|
17
|
+
@col_sep = find_col_sep
|
18
|
+
{
|
19
|
+
:col_sep => col_sep,
|
20
|
+
:field_counts => stats
|
21
|
+
}
|
22
|
+
end
|
23
|
+
|
24
|
+
def find_col_sep
|
25
|
+
line1 = file.lines.first
|
26
|
+
delimcounts = CandidateDelimiters.each_with_object({}) do |delim,h|
|
27
|
+
h[delim] = consider_delim(line1, delim)
|
28
|
+
end
|
29
|
+
file.seek(0) # reset file pointer
|
30
|
+
delimcounts.sort_by{|h,v| -v}.first.first
|
31
|
+
end
|
32
|
+
|
33
|
+
def consider_delim(line, delim)
|
34
|
+
line.count(delim)
|
35
|
+
end
|
36
|
+
|
37
|
+
def stats
|
38
|
+
file.lines.map {|line| line.split(col_sep).count}.uniq
|
39
|
+
end
|
40
|
+
end
|
data/lib/masticate.rb
ADDED
data/masticate.gemspec
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/masticate/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Jason May"]
|
6
|
+
gem.email = ["jmay@pobox.com"]
|
7
|
+
gem.description = %q{Data file crunching}
|
8
|
+
gem.summary = %q{Utility functions for parsing incoming text data files.}
|
9
|
+
gem.homepage = ""
|
10
|
+
gem.rubyforge_project = "masticate"
|
11
|
+
|
12
|
+
gem.files = `git ls-files`.split($\)
|
13
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
14
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
15
|
+
gem.name = "masticate"
|
16
|
+
gem.require_paths = ["lib"]
|
17
|
+
gem.version = Masticate::VERSION
|
18
|
+
|
19
|
+
gem.add_development_dependency "rspec"
|
20
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
# spec for file-sniffing functions
|
2
|
+
|
3
|
+
require "spec_helper"
|
4
|
+
|
5
|
+
describe "delimiter sniffing" do
|
6
|
+
it "should find tab delimiter" do
|
7
|
+
filename = File.dirname(__FILE__) + "/../data/tabbed_data.txt"
|
8
|
+
file = File.open(filename)
|
9
|
+
results = Masticate.sniff(file)
|
10
|
+
results[:col_sep].should == "\t"
|
11
|
+
results[:field_counts].should == [6]
|
12
|
+
end
|
13
|
+
|
14
|
+
it "should find pipe delimiter" do
|
15
|
+
filename = File.dirname(__FILE__) + "/../data/pipe_data.txt"
|
16
|
+
file = File.open(filename)
|
17
|
+
results = Masticate.sniff(file)
|
18
|
+
results[:col_sep].should == '|'
|
19
|
+
results[:field_counts].should == [6]
|
20
|
+
end
|
21
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
# require File.expand_path("../../config/environment", __FILE__)
|
2
|
+
# require 'rspec/rails'
|
3
|
+
require 'rspec/autorun'
|
4
|
+
# require 'capybara/rspec'
|
5
|
+
|
6
|
+
# Requires supporting ruby files with custom matchers and macros, etc,
|
7
|
+
# in spec/support/ and its subdirectories.
|
8
|
+
# Dir[Rails.root.join("spec/support/**/*.rb")].each {|f| require f}
|
9
|
+
|
10
|
+
require File.expand_path('../../lib/masticate', __FILE__)
|
11
|
+
|
12
|
+
RSpec.configure do |config|
|
13
|
+
# ## Mock Framework
|
14
|
+
#
|
15
|
+
# If you prefer to use mocha, flexmock or RR, uncomment the appropriate line:
|
16
|
+
#
|
17
|
+
# config.mock_with :mocha
|
18
|
+
# config.mock_with :flexmock
|
19
|
+
# config.mock_with :rr
|
20
|
+
|
21
|
+
# Remove this line if you're not using ActiveRecord or ActiveRecord fixtures
|
22
|
+
# config.fixture_path = "#{::Rails.root}/spec/fixtures"
|
23
|
+
|
24
|
+
# If you're not using ActiveRecord, or you'd prefer not to run each of your
|
25
|
+
# examples within a transaction, remove the following line or assign false
|
26
|
+
# instead of true.
|
27
|
+
# config.use_transactional_fixtures = true
|
28
|
+
# config.use_instantiated_fixtures = false
|
29
|
+
|
30
|
+
# If true, the base class of anonymous controllers will be inferred
|
31
|
+
# automatically. This will be the default behavior in future versions of
|
32
|
+
# rspec-rails.
|
33
|
+
# config.infer_base_class_for_anonymous_controllers = false
|
34
|
+
end
|
metadata
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: masticate
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Jason May
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-04-03 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: &2153533260 !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: *2153533260
|
25
|
+
description: Data file crunching
|
26
|
+
email:
|
27
|
+
- jmay@pobox.com
|
28
|
+
executables: []
|
29
|
+
extensions: []
|
30
|
+
extra_rdoc_files: []
|
31
|
+
files:
|
32
|
+
- .gitignore
|
33
|
+
- Gemfile
|
34
|
+
- LICENSE
|
35
|
+
- README.md
|
36
|
+
- Rakefile
|
37
|
+
- lib/masticate.rb
|
38
|
+
- lib/masticate/sniffer.rb
|
39
|
+
- lib/masticate/version.rb
|
40
|
+
- masticate.gemspec
|
41
|
+
- spec/data/pipe_data.txt
|
42
|
+
- spec/data/tabbed_data.txt
|
43
|
+
- spec/spec/sniffer_spec.rb
|
44
|
+
- spec/spec_helper.rb
|
45
|
+
homepage: ''
|
46
|
+
licenses: []
|
47
|
+
post_install_message:
|
48
|
+
rdoc_options: []
|
49
|
+
require_paths:
|
50
|
+
- lib
|
51
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '0'
|
57
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
58
|
+
none: false
|
59
|
+
requirements:
|
60
|
+
- - ! '>='
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: '0'
|
63
|
+
requirements: []
|
64
|
+
rubyforge_project: masticate
|
65
|
+
rubygems_version: 1.8.10
|
66
|
+
signing_key:
|
67
|
+
specification_version: 3
|
68
|
+
summary: Utility functions for parsing incoming text data files.
|
69
|
+
test_files:
|
70
|
+
- spec/data/pipe_data.txt
|
71
|
+
- spec/data/tabbed_data.txt
|
72
|
+
- spec/spec/sniffer_spec.rb
|
73
|
+
- spec/spec_helper.rb
|
74
|
+
has_rdoc:
|