tabular_data 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +93 -0
- data/Rakefile +2 -0
- data/lib/tabular_data/version.rb +3 -0
- data/lib/tabular_data.rb +88 -0
- data/tabular_data.gemspec +17 -0
- data/test/integration/test_reader.rb +80 -0
- metadata +55 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 mrodrigues
|
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 +1,93 @@
|
|
1
|
+
# TabularData
|
2
|
+
|
3
|
+
A library for parsing tabular data.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'tabular_data'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install tabular_data
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
|
22
|
+
```ruby
|
23
|
+
class Person
|
24
|
+
attr_accessor :name, :age
|
25
|
+
|
26
|
+
ATTRIBUTES = [:name, :age]
|
27
|
+
end
|
28
|
+
|
29
|
+
reader = TabularData::Reader.new(Person::ATTRIBUTES)
|
30
|
+
person = reader.read(Person.new, "Marcos;23")
|
31
|
+
|
32
|
+
person.name
|
33
|
+
=> "Marcos"
|
34
|
+
|
35
|
+
person.age
|
36
|
+
=> "23"
|
37
|
+
```
|
38
|
+
|
39
|
+
### Changing strategies
|
40
|
+
|
41
|
+
```ruby
|
42
|
+
reader.strategy = :array
|
43
|
+
person = reader.read(Person.new, ["Marcos", 23])
|
44
|
+
|
45
|
+
person.name
|
46
|
+
=> "Marcos"
|
47
|
+
|
48
|
+
person.age
|
49
|
+
=> 23
|
50
|
+
|
51
|
+
custom_csv = TabularData::Strategies::CSVStrategy.new
|
52
|
+
custom_csv.column_delimiter = "|"
|
53
|
+
reader.strategy = custom_csv
|
54
|
+
|
55
|
+
person = reader.read(Person.new, "Marcos|23")
|
56
|
+
|
57
|
+
person.name
|
58
|
+
=> "Marcos"
|
59
|
+
|
60
|
+
person.age
|
61
|
+
=> "23"
|
62
|
+
|
63
|
+
reader.strategy = lambda do |context, attributes_to_parse, attributes|
|
64
|
+
attributes_to_parse = [attributes[0..3], attributes_to_parse[4..5]]
|
65
|
+
attributes.each_with_index do |attribute, i|
|
66
|
+
context.send "#{attribute}=", attributes_to_parse[i]
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
person = reader.read(Person.new, "Marc23")
|
71
|
+
|
72
|
+
person.name
|
73
|
+
=> "Marc"
|
74
|
+
|
75
|
+
person.age
|
76
|
+
=> "23"
|
77
|
+
```
|
78
|
+
|
79
|
+
### Useful methods
|
80
|
+
|
81
|
+
```ruby
|
82
|
+
people = TabularData.parse_csv("people_data.csv", Person::ATTRIBUTES, lambda{ Person.new })
|
83
|
+
|
84
|
+
people = TabularData.parse_lines("Marcos;23\nFelipe;25", Person::ATTRIBUTES, lambda{ Person.new })
|
85
|
+
```
|
86
|
+
|
87
|
+
## Contributing
|
88
|
+
|
89
|
+
1. Fork it
|
90
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
91
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
92
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
93
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/lib/tabular_data.rb
ADDED
@@ -0,0 +1,88 @@
|
|
1
|
+
module TabularData
|
2
|
+
|
3
|
+
def self.parse_lines(lines, attributes, factory, column_delimiter = ";")
|
4
|
+
lines = lines.split("\n") if lines.is_a? String
|
5
|
+
|
6
|
+
reader = TabularData::Reader.new(attributes)
|
7
|
+
reader.strategy = TabularData::Strategies::CSVStrategy.new(column_delimiter)
|
8
|
+
|
9
|
+
entries = []
|
10
|
+
lines.each do |line|
|
11
|
+
entries << reader.read(factory.call, line.strip)
|
12
|
+
end
|
13
|
+
entries
|
14
|
+
end
|
15
|
+
|
16
|
+
def self.parse_csv(path, attributes, factory, column_delimiter = ";")
|
17
|
+
parse_lines File.open(path, "r").readlines, attributes, factory, column_delimiter
|
18
|
+
end
|
19
|
+
|
20
|
+
module Strategies
|
21
|
+
class ReaderStrategy
|
22
|
+
|
23
|
+
def call(context, attributes_to_parse, attributes)
|
24
|
+
attributes_to_parse = parse_attributes(attributes_to_parse)
|
25
|
+
attributes.each_with_index do |attribute, i|
|
26
|
+
context.send "#{attribute}=", attributes_to_parse[i]
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def parse_attributes(attributes)
|
31
|
+
raise NotImplementedError.new("Not implemented yet.")
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
class CSVStrategy < ReaderStrategy
|
36
|
+
|
37
|
+
attr_accessor :column_delimiter
|
38
|
+
|
39
|
+
def initialize(column_delimiter = ";")
|
40
|
+
@column_delimiter = column_delimiter
|
41
|
+
end
|
42
|
+
|
43
|
+
def column_delimiter
|
44
|
+
@column_delimiter
|
45
|
+
end
|
46
|
+
|
47
|
+
def parse_attributes(line)
|
48
|
+
line.split(column_delimiter)
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
class ArrayStrategy < ReaderStrategy
|
53
|
+
|
54
|
+
def parse_attributes(attributes)
|
55
|
+
attributes
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
end
|
60
|
+
|
61
|
+
class Reader
|
62
|
+
|
63
|
+
def strategy
|
64
|
+
@strategy ||= TabularData::Strategies::CSVStrategy.new
|
65
|
+
end
|
66
|
+
|
67
|
+
def strategy=(str)
|
68
|
+
if str.is_a? Symbol
|
69
|
+
case str
|
70
|
+
when :csv then @strategy = TabularData::Strategies::CSVStrategy.new
|
71
|
+
when :array then @strategy = TabularData::Strategies::ArrayStrategy.new
|
72
|
+
end
|
73
|
+
else
|
74
|
+
@strategy = str
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
def initialize(attributes)
|
79
|
+
@attributes = attributes
|
80
|
+
end
|
81
|
+
|
82
|
+
def read(entry, attributes_to_parse)
|
83
|
+
@strategy.call(entry, attributes_to_parse, @attributes)
|
84
|
+
entry
|
85
|
+
end
|
86
|
+
|
87
|
+
end
|
88
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/tabular_data/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["mrodrigues"]
|
6
|
+
gem.email = ["mrodrigues.uff@gmail.com"]
|
7
|
+
gem.description = %q{A library for parsing tabular data.}
|
8
|
+
gem.summary = %q{A library for parsing tabular data.}
|
9
|
+
gem.homepage = "https://github.com/mrodrigues/TabularData"
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "tabular_data"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = TabularData::VERSION
|
17
|
+
end
|
@@ -0,0 +1,80 @@
|
|
1
|
+
$:.unshift File.expand_path("../../lib")
|
2
|
+
require 'tabular_data'
|
3
|
+
require 'test/unit'
|
4
|
+
|
5
|
+
class Entry
|
6
|
+
attr_accessor :a, :b
|
7
|
+
ATTRIBUTES = [:a, :b]
|
8
|
+
end
|
9
|
+
|
10
|
+
class TestEntry < Test::Unit::TestCase
|
11
|
+
|
12
|
+
def setup
|
13
|
+
@reader = TabularData::Reader.new(Entry::ATTRIBUTES)
|
14
|
+
@entry = Entry.new
|
15
|
+
end
|
16
|
+
|
17
|
+
def test_csv_strategy
|
18
|
+
@reader.strategy = :csv
|
19
|
+
@reader.read(@entry, "first;second")
|
20
|
+
assert_equal "first", @entry.a
|
21
|
+
assert_equal "second", @entry.b
|
22
|
+
end
|
23
|
+
|
24
|
+
def test_csv_strategy_setting_delimiter
|
25
|
+
strategy = TabularData::Strategies::CSVStrategy.new
|
26
|
+
strategy.column_delimiter = "|"
|
27
|
+
@reader.strategy = strategy
|
28
|
+
|
29
|
+
@reader.read(@entry, "first|second")
|
30
|
+
assert_equal "first", @entry.a
|
31
|
+
assert_equal "second", @entry.b
|
32
|
+
end
|
33
|
+
|
34
|
+
def test_array_strategy
|
35
|
+
@reader.strategy = :array
|
36
|
+
@reader.read(@entry, ["first","second"])
|
37
|
+
assert_equal "first", @entry.a
|
38
|
+
assert_equal "second", @entry.b
|
39
|
+
end
|
40
|
+
|
41
|
+
def test_anonymous_strategy
|
42
|
+
@reader.strategy = lambda do |context, attributes_to_parse, attributes|
|
43
|
+
attributes_to_parse = [attributes_to_parse[0..2], attributes_to_parse[3..5]]
|
44
|
+
attributes.each_with_index do |attribute, i|
|
45
|
+
context.send "#{attribute}=", attributes_to_parse[i]
|
46
|
+
end
|
47
|
+
end
|
48
|
+
@reader.read(@entry, "1st2nd")
|
49
|
+
assert_equal "1st", @entry.a
|
50
|
+
assert_equal "2nd", @entry.b
|
51
|
+
end
|
52
|
+
|
53
|
+
def test_parse_lines
|
54
|
+
entries = TabularData.parse_lines("first;second\n1st;2nd",
|
55
|
+
Entry::ATTRIBUTES,
|
56
|
+
lambda{ Entry.new })
|
57
|
+
assert_equal "first", entries[0].a
|
58
|
+
assert_equal "second", entries[0].b
|
59
|
+
assert_equal "1st", entries[1].a
|
60
|
+
assert_equal "2nd", entries[1].b
|
61
|
+
end
|
62
|
+
|
63
|
+
def test_parse_csv
|
64
|
+
require 'fileutils'
|
65
|
+
FileUtils.mkdir("temp") unless File.exists?("temp")
|
66
|
+
File.open("temp/entries.csv", "w") do |f|
|
67
|
+
f << "first;second\n1st;2nd"
|
68
|
+
end
|
69
|
+
|
70
|
+
entries = TabularData.parse_csv("temp/entries.csv",
|
71
|
+
Entry::ATTRIBUTES,
|
72
|
+
lambda { Entry.new })
|
73
|
+
assert_equal "first", entries[0].a
|
74
|
+
assert_equal "second", entries[0].b
|
75
|
+
assert_equal "1st", entries[1].a
|
76
|
+
assert_equal "2nd", entries[1].b
|
77
|
+
|
78
|
+
FileUtils.rm_rf("temp")
|
79
|
+
end
|
80
|
+
end
|
metadata
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: tabular_data
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- mrodrigues
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-06-30 00:00:00.000000000Z
|
13
|
+
dependencies: []
|
14
|
+
description: A library for parsing tabular data.
|
15
|
+
email:
|
16
|
+
- mrodrigues.uff@gmail.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- .gitignore
|
22
|
+
- Gemfile
|
23
|
+
- LICENSE
|
24
|
+
- README.md
|
25
|
+
- Rakefile
|
26
|
+
- lib/tabular_data.rb
|
27
|
+
- lib/tabular_data/version.rb
|
28
|
+
- tabular_data.gemspec
|
29
|
+
- test/integration/test_reader.rb
|
30
|
+
homepage: https://github.com/mrodrigues/TabularData
|
31
|
+
licenses: []
|
32
|
+
post_install_message:
|
33
|
+
rdoc_options: []
|
34
|
+
require_paths:
|
35
|
+
- lib
|
36
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
37
|
+
none: false
|
38
|
+
requirements:
|
39
|
+
- - ! '>='
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '0'
|
42
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
43
|
+
none: false
|
44
|
+
requirements:
|
45
|
+
- - ! '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
requirements: []
|
49
|
+
rubyforge_project:
|
50
|
+
rubygems_version: 1.8.17
|
51
|
+
signing_key:
|
52
|
+
specification_version: 3
|
53
|
+
summary: A library for parsing tabular data.
|
54
|
+
test_files:
|
55
|
+
- test/integration/test_reader.rb
|