relational_exporter 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +93 -0
- data/Rakefile +1 -0
- data/lib/relational_exporter/active_record_extension.rb +38 -0
- data/lib/relational_exporter/version.rb +3 -0
- data/lib/relational_exporter.rb +147 -0
- data/relational_exporter.gemspec +27 -0
- metadata +124 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 812375c407e516d9335f9de5ef56b1472bd67e2a
|
4
|
+
data.tar.gz: 05079ba3387f1a94910da2d2e9338883156e3bbf
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: bec4595a08715fb900cf95e6c3b7b647b8b5a3e996068e75aa9f19d39d06c00857a1af22480c45f230e103e892efadaba06349d8147872b2b5af7fe43a0cbdba
|
7
|
+
data.tar.gz: 70b0fe2eebfc33cfef4d5ceb2096a20a0dd7f03af68e9f51a117228a886940d05bd27ff5f536c1e2971f9337d2d5e3e072e46cb52ffcf5fbb86bcd67b3d57940
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Andrew Hammond
|
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
|
+
# relational_exporter
|
2
|
+
|
3
|
+
A gem to make it easy to export data from relational databases. RelationalExporter shines when your intended output is a "flat" CSV file, but your data is relational (each record can have multiple associated sub-records). Define your schema (once) in a familiar ActiveRecord-y way and leverage the robust model featureset. Once your schema is defined, define one or more output configurations which can be re-used to generate an export file.
|
4
|
+
|
5
|
+
## TODO
|
6
|
+
|
7
|
+
* Support multiple formats (currently only CSV)
|
8
|
+
* Integrate serializers of some sort
|
9
|
+
* Improve DSL
|
10
|
+
* Clean up the code
|
11
|
+
|
12
|
+
## Installation
|
13
|
+
|
14
|
+
Add this line to your application's Gemfile:
|
15
|
+
|
16
|
+
gem 'relational_exporter'
|
17
|
+
|
18
|
+
And then execute:
|
19
|
+
|
20
|
+
$ bundle
|
21
|
+
|
22
|
+
Or install it yourself as:
|
23
|
+
|
24
|
+
$ gem install relational_exporter
|
25
|
+
|
26
|
+
## Usage
|
27
|
+
|
28
|
+
```ruby
|
29
|
+
# Define schemas
|
30
|
+
my_schema = {
|
31
|
+
person: {
|
32
|
+
table_name: :person,
|
33
|
+
primary_key: :id,
|
34
|
+
has_many: {
|
35
|
+
addresses: nil,
|
36
|
+
emails: nil
|
37
|
+
},
|
38
|
+
has_one: {
|
39
|
+
avatar: [{ foreign_key: :ref_id }]
|
40
|
+
}
|
41
|
+
},
|
42
|
+
avatar: {
|
43
|
+
table_name: :avatar,
|
44
|
+
belongs_to: {
|
45
|
+
person: [{ foreign_key: :ref_id }]
|
46
|
+
}
|
47
|
+
}
|
48
|
+
}
|
49
|
+
|
50
|
+
# Define output
|
51
|
+
my_output_config = {
|
52
|
+
format: :csv,
|
53
|
+
output: {
|
54
|
+
model: :person,
|
55
|
+
scope: {
|
56
|
+
where: "person.status = 'active'"
|
57
|
+
},
|
58
|
+
associations: {
|
59
|
+
emails: {},
|
60
|
+
avatar: {
|
61
|
+
scope: {
|
62
|
+
where: "ref_type like 'person'",
|
63
|
+
limit: 1,
|
64
|
+
order: "id desc"
|
65
|
+
}
|
66
|
+
}
|
67
|
+
}
|
68
|
+
}
|
69
|
+
}
|
70
|
+
|
71
|
+
# Define DB connection info
|
72
|
+
my_conn = {
|
73
|
+
adapter: 'mysql2',
|
74
|
+
host: ENV['DB_HOST'],
|
75
|
+
username: ENV['DB_USER'],
|
76
|
+
password: ENV['DB_PASS'],
|
77
|
+
database: 'my_database'
|
78
|
+
}
|
79
|
+
|
80
|
+
# Run the export!
|
81
|
+
r = RelationalExporter::Runner.new schema: my_schema, connection_config: my_conn
|
82
|
+
r.export(my_output_config) do |record|
|
83
|
+
# modify the record and it's models/associations
|
84
|
+
end
|
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 'Add some feature'`)
|
92
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
93
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,38 @@
|
|
1
|
+
module ActiveRecordExtension
|
2
|
+
extend ActiveSupport::Concern
|
3
|
+
|
4
|
+
def find_all_by_scope(scope_hash={})
|
5
|
+
scope_hash = { where: {} } if scope_hash.nil?
|
6
|
+
the_scope = nil
|
7
|
+
scope_hash.each do |method, scoping|
|
8
|
+
if the_scope.nil?
|
9
|
+
the_scope = send method.to_sym, scoping
|
10
|
+
else
|
11
|
+
the_scope.send method.to_sym, scoping
|
12
|
+
end
|
13
|
+
end
|
14
|
+
the_scope
|
15
|
+
end
|
16
|
+
|
17
|
+
def set_scope_from_hash(scope_hash={}, clear_default_scope=false)
|
18
|
+
scope_hash = {} if scope_hash.nil?
|
19
|
+
clear_default_scopes if clear_default_scope
|
20
|
+
|
21
|
+
result = nil
|
22
|
+
scope_hash.each do |method, scoping|
|
23
|
+
if result.nil?
|
24
|
+
result = send method.to_sym, scoping
|
25
|
+
else
|
26
|
+
result.send method.to_sym, scoping
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
default_scope { result }
|
31
|
+
end
|
32
|
+
|
33
|
+
def clear_default_scopes
|
34
|
+
self.default_scopes = []
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
ActiveRecord::Base.send(:extend, ActiveRecordExtension)
|
@@ -0,0 +1,147 @@
|
|
1
|
+
require 'byebug'
|
2
|
+
require 'csv'
|
3
|
+
require 'hashie'
|
4
|
+
require 'relational_exporter/version'
|
5
|
+
require 'relational_exporter/active_record_extension'
|
6
|
+
|
7
|
+
module RelationalExporter
|
8
|
+
class Runner
|
9
|
+
attr_accessor :schema
|
10
|
+
|
11
|
+
def initialize(options={})
|
12
|
+
# TODO - disable when not byebugging!!!
|
13
|
+
ActiveRecord::Base.logger = Logger.new(STDOUT)
|
14
|
+
|
15
|
+
@connection_config = options[:connection_config]
|
16
|
+
begin
|
17
|
+
ActiveRecord::Base.establish_connection @connection_config
|
18
|
+
ActiveRecord::Base.connection.active?
|
19
|
+
rescue Exception => e
|
20
|
+
raise "Database connection failed: #{e.message}"
|
21
|
+
end
|
22
|
+
|
23
|
+
@schema = Hashie::Mash.new(options[:schema] || YAML.load_file(options[:schema_file]))
|
24
|
+
|
25
|
+
load_models
|
26
|
+
end
|
27
|
+
|
28
|
+
def export(output_config, &block)
|
29
|
+
output_config = Hashie::Mash.new output_config
|
30
|
+
|
31
|
+
main_klass = output_config.output.model.to_s.classify.constantize
|
32
|
+
|
33
|
+
main_klass.set_scope_from_hash output_config.output.scope.as_json
|
34
|
+
|
35
|
+
header_row = []
|
36
|
+
max_associations = {}
|
37
|
+
|
38
|
+
::CSV.open('/tmp/test.csv', 'wb', headers: true) do |csv|
|
39
|
+
main_klass.all.find_in_batches do |batch|
|
40
|
+
batch.each do |single|
|
41
|
+
if block_given?
|
42
|
+
yield single
|
43
|
+
end
|
44
|
+
|
45
|
+
row = []
|
46
|
+
|
47
|
+
# Add main record headers
|
48
|
+
single.attributes.each do |field, value|
|
49
|
+
header_row << [main_klass.to_s.underscore, field].join('_').classify if csv.header_row?
|
50
|
+
row << value
|
51
|
+
end
|
52
|
+
|
53
|
+
output_config.output.associations.each do |association_accessor, association_options|
|
54
|
+
association_accessor = association_accessor.to_s.to_sym
|
55
|
+
association_klass = association_accessor.to_s.classify.constantize
|
56
|
+
scope = symbolize_options association_options.scope
|
57
|
+
|
58
|
+
associated = single.send association_accessor
|
59
|
+
# TODO - this might suck for single associations (has_one) because they don't return an ar::associations::collectionproxy
|
60
|
+
associated = associated.find_all_by_scope(scope) unless scope.blank? || !associated.respond_to?(:find_all_by_scope)
|
61
|
+
|
62
|
+
if associated.is_a? Hash
|
63
|
+
associated = [ associated ]
|
64
|
+
elsif associated.blank?
|
65
|
+
associated = []
|
66
|
+
end
|
67
|
+
|
68
|
+
foreign_key = main_klass.reflections[association_accessor].foreign_key rescue nil
|
69
|
+
|
70
|
+
fields = association_klass.first.attributes.keys
|
71
|
+
|
72
|
+
fields.reject! {|v| v == foreign_key } if foreign_key
|
73
|
+
|
74
|
+
if csv.header_row?
|
75
|
+
case main_klass.reflections[association_accessor].macro
|
76
|
+
when :has_many
|
77
|
+
max_associated = association_klass.find_all_by_scope(scope)
|
78
|
+
.joins(main_klass.table_name.to_sym)
|
79
|
+
.order('count_all desc')
|
80
|
+
.group(foreign_key)
|
81
|
+
.limit(1).count.flatten[1]
|
82
|
+
when :has_one
|
83
|
+
max_associated = 1
|
84
|
+
end
|
85
|
+
|
86
|
+
max_associations[association_accessor] = max_associated
|
87
|
+
|
88
|
+
max_associated.times do |i|
|
89
|
+
fields.each do |field|
|
90
|
+
header_row << [association_klass.to_s.underscore, i+1, field].join('_').classify
|
91
|
+
end
|
92
|
+
end
|
93
|
+
end
|
94
|
+
|
95
|
+
get_row_arr(associated, fields, max_associations[association_accessor]) {|field| row << field}
|
96
|
+
end
|
97
|
+
|
98
|
+
csv << header_row if csv.header_row?
|
99
|
+
if row.count != header_row.count
|
100
|
+
puts "OH SHIT, this row is not right!"
|
101
|
+
byebug
|
102
|
+
end
|
103
|
+
csv << row
|
104
|
+
end
|
105
|
+
end
|
106
|
+
end
|
107
|
+
end
|
108
|
+
|
109
|
+
private
|
110
|
+
|
111
|
+
def get_row_arr(records, fields, max_count=1, &block)
|
112
|
+
max_count.times do |i|
|
113
|
+
fields.each do |field|
|
114
|
+
val = records[i][field] rescue nil
|
115
|
+
yield val
|
116
|
+
end
|
117
|
+
end
|
118
|
+
end
|
119
|
+
|
120
|
+
def symbolize_options(options)
|
121
|
+
options = options.as_json
|
122
|
+
if options.is_a? Hash
|
123
|
+
options.deep_symbolize_keys!
|
124
|
+
elsif options.is_a? Array
|
125
|
+
options.map { |val| symbolize_options val }
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
def load_models
|
130
|
+
@schema.each do |model, options|
|
131
|
+
klass = Object.const_set model.to_s.classify, Class.new(ActiveRecord::Base)
|
132
|
+
# klass.extend ActiveRecordExtension
|
133
|
+
options.each do |method, calls|
|
134
|
+
method = "#{method}=".to_sym if klass.respond_to?("#{method}=")
|
135
|
+
if calls.respond_to? :each_pair
|
136
|
+
calls.each do |association, association_options|
|
137
|
+
association_options = symbolize_options association_options
|
138
|
+
klass.send method, association.to_sym, *association_options
|
139
|
+
end
|
140
|
+
else
|
141
|
+
klass.send method, *calls
|
142
|
+
end
|
143
|
+
end
|
144
|
+
end
|
145
|
+
end
|
146
|
+
end
|
147
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'relational_exporter/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'relational_exporter'
|
8
|
+
spec.version = RelationalExporter::VERSION
|
9
|
+
spec.authors = ['Andrew Hammond']
|
10
|
+
spec.email = ['andrew@tremorlab.com']
|
11
|
+
spec.description = %q{Export relational databases as flat files}
|
12
|
+
spec.summary = %q{Export relational databases as flat files}
|
13
|
+
spec.homepage = 'http://github.com/andrhamm'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ['lib']
|
20
|
+
|
21
|
+
spec.add_dependency 'hashie'
|
22
|
+
spec.add_dependency 'activesupport'
|
23
|
+
|
24
|
+
spec.add_development_dependency 'bundler', '~> 1.3'
|
25
|
+
spec.add_development_dependency 'rake'
|
26
|
+
spec.add_development_dependency 'byebug'
|
27
|
+
end
|
metadata
ADDED
@@ -0,0 +1,124 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: relational_exporter
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Andrew Hammond
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-01-31 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: hashie
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: activesupport
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.3'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.3'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: byebug
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
description: Export relational databases as flat files
|
84
|
+
email:
|
85
|
+
- andrew@tremorlab.com
|
86
|
+
executables: []
|
87
|
+
extensions: []
|
88
|
+
extra_rdoc_files: []
|
89
|
+
files:
|
90
|
+
- .gitignore
|
91
|
+
- Gemfile
|
92
|
+
- LICENSE.txt
|
93
|
+
- README.md
|
94
|
+
- Rakefile
|
95
|
+
- lib/relational_exporter.rb
|
96
|
+
- lib/relational_exporter/active_record_extension.rb
|
97
|
+
- lib/relational_exporter/version.rb
|
98
|
+
- relational_exporter.gemspec
|
99
|
+
homepage: http://github.com/andrhamm
|
100
|
+
licenses:
|
101
|
+
- MIT
|
102
|
+
metadata: {}
|
103
|
+
post_install_message:
|
104
|
+
rdoc_options: []
|
105
|
+
require_paths:
|
106
|
+
- lib
|
107
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
108
|
+
requirements:
|
109
|
+
- - '>='
|
110
|
+
- !ruby/object:Gem::Version
|
111
|
+
version: '0'
|
112
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
113
|
+
requirements:
|
114
|
+
- - '>='
|
115
|
+
- !ruby/object:Gem::Version
|
116
|
+
version: '0'
|
117
|
+
requirements: []
|
118
|
+
rubyforge_project:
|
119
|
+
rubygems_version: 2.0.0
|
120
|
+
signing_key:
|
121
|
+
specification_version: 4
|
122
|
+
summary: Export relational databases as flat files
|
123
|
+
test_files: []
|
124
|
+
has_rdoc:
|