data_imp 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 +14 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +21 -0
- data/README.md +90 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/data/hero.json +1 -0
- data/data/hero.yaml +4 -0
- data/data/heros.csv +2 -0
- data/data/heros.json +1 -0
- data/data/heros.ods +0 -0
- data/data/heros.xls +0 -0
- data/data/heros.xlsx +0 -0
- data/data/heros.yaml +4 -0
- data/data_imp.gemspec +30 -0
- data/lib/data_imp.rb +70 -0
- data/lib/data_imp/class_methods.rb +63 -0
- data/lib/data_imp/no_importer.rb +11 -0
- data/lib/data_imp/no_parser.rb +11 -0
- data/lib/data_imp/parser.rb +41 -0
- data/lib/data_imp/parser/csv.rb +16 -0
- data/lib/data_imp/parser/json.rb +7 -0
- data/lib/data_imp/parser/ods.rb +7 -0
- data/lib/data_imp/parser/spreadsheet.rb +20 -0
- data/lib/data_imp/parser/stream.rb +16 -0
- data/lib/data_imp/parser/xls.rb +7 -0
- data/lib/data_imp/parser/xlsx.rb +6 -0
- data/lib/data_imp/parser/yaml.rb +7 -0
- data/lib/data_imp/porter.rb +63 -0
- data/lib/data_imp/porter/sample.rb +2 -0
- data/lib/data_imp/version.rb +3 -0
- metadata +163 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 86e11f4b6817ad75532ca9af858c261295516645
|
4
|
+
data.tar.gz: 7cdd8b503afa39ce898eaf8a77a5034f86af448e
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 84f36d210ff7c43709501f10eed5289e2f7d4d965c2cb1fcfb0edca5134e2af08e5a0821b307ef22ee20c414e43e73398e26879b773ab2cbef33d9f7af7dba91
|
7
|
+
data.tar.gz: 9735f74a69ccee71adb71b3b4bb28273525cbad80eb7158f337f7357a38bd83d413cc920b95ceea2fb2adf9157ee3d06f3af7a6e6aad98229b89cccc40fbbac0
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at robert.w.ferney@uscis.dhs.gov. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2017 Robert W. Ferney
|
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 +1,90 @@
|
|
1
|
+
# Data Imp Porter
|
2
|
+
|
3
|
+
## Installation
|
4
|
+
|
5
|
+
Add this line to your application's Gemfile:
|
6
|
+
|
7
|
+
```ruby
|
8
|
+
gem 'data_imp'
|
9
|
+
```
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install data_imp
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
The use of this gem requires that you define an 'importer' for your files.
|
22
|
+
|
23
|
+
the fields from your data will be available to the importer as if they were local variables.
|
24
|
+
```ruby
|
25
|
+
class SampleImporter < DataImp::Porter
|
26
|
+
def import
|
27
|
+
User.create_with(
|
28
|
+
name: name,
|
29
|
+
).find_or_create_by(
|
30
|
+
email: email
|
31
|
+
)
|
32
|
+
end
|
33
|
+
end
|
34
|
+
```
|
35
|
+
|
36
|
+
If you had your users in a csv file like
|
37
|
+
|
38
|
+
```csv
|
39
|
+
name,email
|
40
|
+
George,george@example.com
|
41
|
+
Fred,fred@example.net
|
42
|
+
```
|
43
|
+
|
44
|
+
You could then use
|
45
|
+
```ruby
|
46
|
+
DataImp.import 'user.csv'
|
47
|
+
```
|
48
|
+
|
49
|
+
If you had your users in a yaml file like
|
50
|
+
|
51
|
+
```yaml
|
52
|
+
---
|
53
|
+
- name: George
|
54
|
+
email: george@example.com
|
55
|
+
- name: Fred
|
56
|
+
email: fred@example.net
|
57
|
+
```
|
58
|
+
|
59
|
+
You could then use
|
60
|
+
```ruby
|
61
|
+
DataImp.import 'user.yaml'
|
62
|
+
```
|
63
|
+
|
64
|
+
The same importer would be used for either example.
|
65
|
+
|
66
|
+
The importer is looked up by the base name, or provided by the `importer:` parameter. . 'user' in this case.
|
67
|
+
|
68
|
+
Parsing of the file is done by a Parser class and is looked up by the file extension, or the `parser:` parameter.
|
69
|
+
|
70
|
+
Pre defined parsers are located in the lib/data_imp/parsers/ folder
|
71
|
+
|
72
|
+
If you need to write your own, define it as 'class ExtParser < DataImp::Parser' to create or override the 'ext' extension parser.
|
73
|
+
|
74
|
+
## Development
|
75
|
+
|
76
|
+
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.
|
77
|
+
|
78
|
+
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).
|
79
|
+
|
80
|
+
## Contributing
|
81
|
+
|
82
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/data-porter. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
83
|
+
|
84
|
+
## License
|
85
|
+
|
86
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
87
|
+
|
88
|
+
## Code of Conduct
|
89
|
+
|
90
|
+
Everyone interacting in the Data::Porter project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/data-porter/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "data/porter"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/data/hero.json
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
{"name":"George","rank":"Sargent","serial_number":9991212}
|
data/data/hero.yaml
ADDED
data/data/heros.csv
ADDED
data/data/heros.json
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
[{"name":"George","rank":"Sargent","serial_number":9991212}]
|
data/data/heros.ods
ADDED
Binary file
|
data/data/heros.xls
ADDED
Binary file
|
data/data/heros.xlsx
ADDED
Binary file
|
data/data/heros.yaml
ADDED
data/data_imp.gemspec
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "data_imp/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "data_imp"
|
8
|
+
spec.version = DataImp::VERSION
|
9
|
+
spec.authors = ["Robert W. Ferney"]
|
10
|
+
spec.email = ["rob@ferney.org"]
|
11
|
+
|
12
|
+
spec.summary = %q{Scaffolding to make importing data easy}
|
13
|
+
spec.homepage = "https://github.com/capnregex/data_imp"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
17
|
+
f.match(%r{^(test|spec|features)/})
|
18
|
+
end
|
19
|
+
spec.bindir = "exe"
|
20
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
21
|
+
spec.require_paths = ["lib"]
|
22
|
+
|
23
|
+
spec.add_runtime_dependency 'activesupport'
|
24
|
+
|
25
|
+
spec.add_development_dependency "bundler", "~> 1.14.6"
|
26
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
27
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
28
|
+
spec.add_development_dependency "roo" #, "~> 3.0"
|
29
|
+
spec.add_development_dependency "roo-xls" #, "~> 3.0"
|
30
|
+
end
|
data/lib/data_imp.rb
ADDED
@@ -0,0 +1,70 @@
|
|
1
|
+
|
2
|
+
require 'active_support/core_ext/string'
|
3
|
+
require_relative "data_imp/version"
|
4
|
+
require_relative "data_imp/class_methods"
|
5
|
+
|
6
|
+
# Dir[File.dirname(__FILE__) + '/data_imp/*.rb'].each {|file| require file }
|
7
|
+
class DataImp
|
8
|
+
extend DataImp::ClassMethods
|
9
|
+
attr_accessor :file, :parser, :importer, :extname, :basename
|
10
|
+
|
11
|
+
def initialize file = nil, parser: nil, importer: nil
|
12
|
+
self.file = data_dir.join(file)
|
13
|
+
extname = File.extname(file)
|
14
|
+
self.basename ||= File.basename(file, extname)
|
15
|
+
self.extname = extname = extname.downcase.sub('.','')
|
16
|
+
self.importer = find_importer(importer || basename) # returns class
|
17
|
+
self.parser = find_parser(parser || extname) # returns class
|
18
|
+
end
|
19
|
+
|
20
|
+
def import
|
21
|
+
puts "Importing #{basename} with #{importer}"
|
22
|
+
importer.before_all_imports
|
23
|
+
parser.new(file).process_file do |hash, index|
|
24
|
+
porter = importer.new(hash,index)
|
25
|
+
begin
|
26
|
+
porter.before_import
|
27
|
+
porter.import
|
28
|
+
porter.after_import
|
29
|
+
show_progress index
|
30
|
+
rescue StandardError => e
|
31
|
+
warn "#{basename}:#{index}:#{e.class.name}"
|
32
|
+
porter.on_error e
|
33
|
+
end
|
34
|
+
end
|
35
|
+
importer.after_all_imports
|
36
|
+
puts
|
37
|
+
end
|
38
|
+
|
39
|
+
def show_progress index
|
40
|
+
puts if index % 10_000 == 0
|
41
|
+
print '.' if index % 100 == 0
|
42
|
+
end
|
43
|
+
|
44
|
+
# def import_file file
|
45
|
+
#
|
46
|
+
# parser_class_name = ext.classify
|
47
|
+
# importer_class_name = base.concat('_importer').classify
|
48
|
+
# file = data_dir.join(file)
|
49
|
+
#
|
50
|
+
# begin
|
51
|
+
# parser = const_get(parser_class_name)
|
52
|
+
# importer = importer_class_name.constantize
|
53
|
+
# rescue NameError => e
|
54
|
+
# warn "No importer class: #{e}"
|
55
|
+
# return
|
56
|
+
# end
|
57
|
+
# parser.new(file, importer).import
|
58
|
+
# end
|
59
|
+
|
60
|
+
# def reader= reader
|
61
|
+
# return unless reader
|
62
|
+
# @reader =
|
63
|
+
# case reader
|
64
|
+
# when IO,DataImp::Reader then reader
|
65
|
+
# when String then open(reader)
|
66
|
+
# when Pathname then reader.open
|
67
|
+
# end
|
68
|
+
# end
|
69
|
+
end
|
70
|
+
|
@@ -0,0 +1,63 @@
|
|
1
|
+
require 'pathname'
|
2
|
+
|
3
|
+
require_relative "parser"
|
4
|
+
require_relative "porter"
|
5
|
+
|
6
|
+
module DataImp::ClassMethods
|
7
|
+
def self.extended(mod)
|
8
|
+
mod.delegate :data_dir, :find_parser, :find_importer, to: :class
|
9
|
+
end
|
10
|
+
|
11
|
+
def root= dir
|
12
|
+
@root = dir
|
13
|
+
end
|
14
|
+
|
15
|
+
def root
|
16
|
+
@root ||= Pathname.pwd
|
17
|
+
end
|
18
|
+
|
19
|
+
def data_dir= dir
|
20
|
+
path = Pathname.new(dir)
|
21
|
+
@data_dir =
|
22
|
+
if path.absolute?
|
23
|
+
path
|
24
|
+
else
|
25
|
+
root.join(path)
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
def data_dir
|
30
|
+
@data_dir ||= root.join('data')
|
31
|
+
end
|
32
|
+
|
33
|
+
def import(file=nil,*args,&block)
|
34
|
+
file.strip!
|
35
|
+
return if file =~ /^#/
|
36
|
+
new(file, *args,&block).import
|
37
|
+
end
|
38
|
+
|
39
|
+
def import_list *args
|
40
|
+
args.each do |arg|
|
41
|
+
arg.each_line do |file|
|
42
|
+
import file
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
def find_parser type
|
48
|
+
return type if type.kind_of? DataImp::Parser
|
49
|
+
type = type.to_s.camelize
|
50
|
+
const_get "#{type}Parser"
|
51
|
+
rescue NameError => e
|
52
|
+
DataImp::Parser.find_parser type
|
53
|
+
end
|
54
|
+
|
55
|
+
def find_importer type
|
56
|
+
return type if type.kind_of? DataImp::Porter
|
57
|
+
type = type.to_s.camelize
|
58
|
+
const_get "#{type}Importer"
|
59
|
+
rescue NameError => e
|
60
|
+
DataImp::Porter.find_importer type
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
@@ -0,0 +1,11 @@
|
|
1
|
+
class DataImp::NoImporter < StandardError
|
2
|
+
attr_accessor :porter_type
|
3
|
+
def initialize(porter_type)
|
4
|
+
@porter_type = porter_type
|
5
|
+
super <<-MSG.strip_heredoc
|
6
|
+
Unable to find Importer for #{porter_type.inspect}
|
7
|
+
Please define: class #{porter_type.classify}Importer < DataImp::Porter
|
8
|
+
MSG
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
@@ -0,0 +1,11 @@
|
|
1
|
+
class DataImp::NoParser < StandardError
|
2
|
+
attr_accessor :parser_type
|
3
|
+
def initialize(parser_type)
|
4
|
+
@parser_type = parser_type
|
5
|
+
super <<-MSG.strip_heredoc
|
6
|
+
Unable to find Parser for #{parser_type.inspect}
|
7
|
+
Please define: class #{parser_type.camelize}Parser < DataImp::Parser
|
8
|
+
MSG
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
@@ -0,0 +1,41 @@
|
|
1
|
+
require_relative 'no_parser'
|
2
|
+
class DataImp::Parser
|
3
|
+
attr_reader :filename
|
4
|
+
|
5
|
+
def initialize filename=nil
|
6
|
+
@filename = filename
|
7
|
+
end
|
8
|
+
|
9
|
+
def self.find_parser type
|
10
|
+
return self if type.blank?
|
11
|
+
begin
|
12
|
+
const_get type.camelize
|
13
|
+
rescue NameError => e
|
14
|
+
if require_relative "parser/#{type.underscore}"
|
15
|
+
retry
|
16
|
+
end
|
17
|
+
end
|
18
|
+
rescue LoadError => e
|
19
|
+
raise DataImp::NoParser.new(type)
|
20
|
+
end
|
21
|
+
|
22
|
+
def parse chunk
|
23
|
+
chunk # assume chunk is a hash
|
24
|
+
end
|
25
|
+
|
26
|
+
def process input, &block
|
27
|
+
index = 1
|
28
|
+
input.each do |chunk|
|
29
|
+
hash = parse(chunk)
|
30
|
+
yield hash, index
|
31
|
+
index += 1
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
def process_file &block
|
36
|
+
open(filename) do |file|
|
37
|
+
process file, &block
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require 'csv'
|
2
|
+
class DataImp::Parser::Csv < DataImp::Parser
|
3
|
+
def options
|
4
|
+
{ headers: true }
|
5
|
+
end
|
6
|
+
|
7
|
+
def parse chunk
|
8
|
+
chunk.to_h
|
9
|
+
end
|
10
|
+
|
11
|
+
def process_file &block
|
12
|
+
CSV.open(filename, options) do |csv|
|
13
|
+
process csv, &block
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
require 'roo'
|
2
|
+
class DataImp::Parser::Spreadsheet < DataImp::Parser
|
3
|
+
def options
|
4
|
+
{ }
|
5
|
+
end
|
6
|
+
|
7
|
+
def process_file &block
|
8
|
+
spreadsheet = Roo::Spreadsheet.open(filename, options)
|
9
|
+
header = spreadsheet.row(1)
|
10
|
+
(2..spreadsheet.last_row).each do |index|
|
11
|
+
row = spreadsheet.row(index)
|
12
|
+
hash = [header, row].transpose.to_h
|
13
|
+
yield hash, index
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
def process input, &block
|
18
|
+
raise "unable to process spreadsheet as a stream"
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
class DataImp::Parser::Stream < DataImp::Parser
|
2
|
+
def process input
|
3
|
+
if input.respond_to? :read
|
4
|
+
input = input.read
|
5
|
+
end
|
6
|
+
data = process_string(input)
|
7
|
+
case data
|
8
|
+
when Hash
|
9
|
+
yield data, 0
|
10
|
+
when Array
|
11
|
+
data.each_with_index do |node, index|
|
12
|
+
yield node, index
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
require 'active_support/hash_with_indifferent_access'
|
2
|
+
require_relative 'no_importer'
|
3
|
+
class DataImp::Porter
|
4
|
+
attr_reader :hash, :index
|
5
|
+
|
6
|
+
def self.find_importer type
|
7
|
+
return self if type.blank?
|
8
|
+
begin
|
9
|
+
const_get type.classify
|
10
|
+
rescue NameError => e
|
11
|
+
if require_relative "porter/#{type.underscore}"
|
12
|
+
retry
|
13
|
+
end
|
14
|
+
end
|
15
|
+
rescue LoadError => e
|
16
|
+
raise DataImp::NoImporter.new(type)
|
17
|
+
end
|
18
|
+
|
19
|
+
def initialize(hash, index = nil)
|
20
|
+
@hash = HashWithIndifferentAccess.new(hash)
|
21
|
+
@index = index
|
22
|
+
end
|
23
|
+
|
24
|
+
def respond_to_missing?(method, include_private = false)
|
25
|
+
hash.has_key?(method) || false # super
|
26
|
+
end
|
27
|
+
|
28
|
+
def method_missing(method, *_args)
|
29
|
+
return nil unless respond_to_missing?(method)
|
30
|
+
value = hash[method]
|
31
|
+
parse(method,value)
|
32
|
+
end
|
33
|
+
|
34
|
+
def parse method, value
|
35
|
+
value # override for special handling
|
36
|
+
end
|
37
|
+
|
38
|
+
def self.before_all_imports
|
39
|
+
# called before any data is processed
|
40
|
+
end
|
41
|
+
|
42
|
+
def before_import
|
43
|
+
# called for a record before import
|
44
|
+
end
|
45
|
+
|
46
|
+
def import
|
47
|
+
# called to import a record
|
48
|
+
warn "Import: #{self.class.name}:#{index}:#{hash.inspect}"
|
49
|
+
end
|
50
|
+
|
51
|
+
def after_import
|
52
|
+
# called after a record was imported
|
53
|
+
end
|
54
|
+
|
55
|
+
def self.after_all_imports
|
56
|
+
# called after all data is processed
|
57
|
+
end
|
58
|
+
|
59
|
+
def on_error e
|
60
|
+
warn "Error: #{self.class.name}:#{index}:#{hash.inspect}"
|
61
|
+
warn e
|
62
|
+
end
|
63
|
+
end
|
metadata
ADDED
@@ -0,0 +1,163 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: data_imp
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Robert W. Ferney
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-09-13 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: activesupport
|
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: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.14.6
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 1.14.6
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rspec
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '3.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '3.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: roo
|
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
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: roo-xls
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description:
|
98
|
+
email:
|
99
|
+
- rob@ferney.org
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- ".gitignore"
|
105
|
+
- ".rspec"
|
106
|
+
- ".travis.yml"
|
107
|
+
- CODE_OF_CONDUCT.md
|
108
|
+
- Gemfile
|
109
|
+
- LICENSE.txt
|
110
|
+
- README.md
|
111
|
+
- Rakefile
|
112
|
+
- bin/console
|
113
|
+
- bin/setup
|
114
|
+
- data/hero.json
|
115
|
+
- data/hero.yaml
|
116
|
+
- data/heros.csv
|
117
|
+
- data/heros.json
|
118
|
+
- data/heros.ods
|
119
|
+
- data/heros.xls
|
120
|
+
- data/heros.xlsx
|
121
|
+
- data/heros.yaml
|
122
|
+
- data_imp.gemspec
|
123
|
+
- lib/data_imp.rb
|
124
|
+
- lib/data_imp/class_methods.rb
|
125
|
+
- lib/data_imp/no_importer.rb
|
126
|
+
- lib/data_imp/no_parser.rb
|
127
|
+
- lib/data_imp/parser.rb
|
128
|
+
- lib/data_imp/parser/csv.rb
|
129
|
+
- lib/data_imp/parser/json.rb
|
130
|
+
- lib/data_imp/parser/ods.rb
|
131
|
+
- lib/data_imp/parser/spreadsheet.rb
|
132
|
+
- lib/data_imp/parser/stream.rb
|
133
|
+
- lib/data_imp/parser/xls.rb
|
134
|
+
- lib/data_imp/parser/xlsx.rb
|
135
|
+
- lib/data_imp/parser/yaml.rb
|
136
|
+
- lib/data_imp/porter.rb
|
137
|
+
- lib/data_imp/porter/sample.rb
|
138
|
+
- lib/data_imp/version.rb
|
139
|
+
homepage: https://github.com/capnregex/data_imp
|
140
|
+
licenses:
|
141
|
+
- MIT
|
142
|
+
metadata: {}
|
143
|
+
post_install_message:
|
144
|
+
rdoc_options: []
|
145
|
+
require_paths:
|
146
|
+
- lib
|
147
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
148
|
+
requirements:
|
149
|
+
- - ">="
|
150
|
+
- !ruby/object:Gem::Version
|
151
|
+
version: '0'
|
152
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
153
|
+
requirements:
|
154
|
+
- - ">="
|
155
|
+
- !ruby/object:Gem::Version
|
156
|
+
version: '0'
|
157
|
+
requirements: []
|
158
|
+
rubyforge_project:
|
159
|
+
rubygems_version: 2.5.1
|
160
|
+
signing_key:
|
161
|
+
specification_version: 4
|
162
|
+
summary: Scaffolding to make importing data easy
|
163
|
+
test_files: []
|