data_janitor 0.3.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.github/ISSUE_TEMPLATE +16 -0
- data/.github/PULL_REQUEST_TEMPLATE +19 -0
- data/.gitignore +11 -0
- data/.rspec +3 -0
- data/.travis.yml +11 -0
- data/Gemfile +4 -0
- data/LICENSE +201 -0
- data/README.md +86 -0
- data/Rakefile +7 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/contributing.md +13 -0
- data/data_janitor.gemspec +27 -0
- data/lib/data_janitor/audit_validatable.rb +15 -0
- data/lib/data_janitor/universal_validator.rb +50 -0
- data/lib/data_janitor/version.rb +3 -0
- data/lib/data_janitor.rb +14 -0
- data/lib/tasks/data_janitor.rake +100 -0
- metadata +121 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: f234ed8031caa839c30a2e485173c4166987bcac
|
4
|
+
data.tar.gz: f72579f69d10bb6c2a76e70c98ac37479066156d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b16d22613630c39960ca6a5e2ec84d8a42a1f618069981994fc345ab31c746981057b19913d137f16139bc04a98483d8c287b2e88a483890f19c4b4a09e878aa
|
7
|
+
data.tar.gz: 8e0768a057fb6d1093266d26d26b99efec8c0db594850e31b3dea6a44e236ea937f422e7a2b2b9bca3b2cd4065c3f0c51b79865b49ae75470fb4f33fb3963938
|
@@ -0,0 +1,16 @@
|
|
1
|
+
### Expected/Desired Behavior:
|
2
|
+
< Description of the expected or desired behavior including an example >
|
3
|
+
|
4
|
+
### Current Behavior:
|
5
|
+
< Description of the current behavior being encountered including an example >
|
6
|
+
|
7
|
+
### Impact:
|
8
|
+
- Will this introduce any externally facing changes(endpoint, fields, validation, query)?
|
9
|
+
- Was a regression introduced(if bug)?
|
10
|
+
- Urgency(low, medium, high)?
|
11
|
+
- Teams impacted?(web, ios, android, maps, etc)
|
12
|
+
|
13
|
+
### Requirements:
|
14
|
+
- Label as "Bug Fix", "Feature" or "Optimization"(Tech Debt)
|
15
|
+
|
16
|
+
cc: @two_ @team_members
|
@@ -0,0 +1,19 @@
|
|
1
|
+
### Issue:
|
2
|
+
[JIRA-0000](http://link_to_ticket.com)
|
3
|
+
|
4
|
+
### Proposed Changes:
|
5
|
+
< Description of the proposed change and its value. If possible also include a usage example and relative links to provide additional context for the reviewer>
|
6
|
+
|
7
|
+
### Impact:
|
8
|
+
- Will this introduce any externally facing changes(endpoint, fields, validation, query)?
|
9
|
+
- Any special deployment coordination needed(env changes, data/db migrations, etc.)?
|
10
|
+
- Urgency(low, medium, high)?
|
11
|
+
- Teams impacted(web, ios, android, maps, etc)?
|
12
|
+
|
13
|
+
### Requirements:
|
14
|
+
- Add Tests to cover changes
|
15
|
+
- Update Swagger documentation if applicable
|
16
|
+
- Update repo documentation if applicable(readme, wiki)
|
17
|
+
- Label as "Bug Fix", "Feature" or "Optimization"(Tech Debt)
|
18
|
+
|
19
|
+
cc: @two_ @team_members
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,201 @@
|
|
1
|
+
Apache License
|
2
|
+
Version 2.0, January 2004
|
3
|
+
http://www.apache.org/licenses/
|
4
|
+
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6
|
+
|
7
|
+
1. Definitions.
|
8
|
+
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
11
|
+
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13
|
+
the copyright owner that is granting the License.
|
14
|
+
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
16
|
+
other entities that control, are controlled by, or are under common
|
17
|
+
control with that entity. For the purposes of this definition,
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
19
|
+
direction or management of such entity, whether by contract or
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22
|
+
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24
|
+
exercising permissions granted by this License.
|
25
|
+
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
27
|
+
including but not limited to software source code, documentation
|
28
|
+
source, and configuration files.
|
29
|
+
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
31
|
+
transformation or translation of a Source form, including but
|
32
|
+
not limited to compiled object code, generated documentation,
|
33
|
+
and conversions to other media types.
|
34
|
+
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
36
|
+
Object form, made available under the License, as indicated by a
|
37
|
+
copyright notice that is included in or attached to the work
|
38
|
+
(an example is provided in the Appendix below).
|
39
|
+
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46
|
+
the Work and Derivative Works thereof.
|
47
|
+
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
49
|
+
the original version of the Work and any modifications or additions
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
61
|
+
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
64
|
+
subsequently incorporated within the Work.
|
65
|
+
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
72
|
+
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78
|
+
where such license applies only to those patent claims licensable
|
79
|
+
by such Contributor that are necessarily infringed by their
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
82
|
+
institute patent litigation against any entity (including a
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
85
|
+
or contributory patent infringement, then any patent licenses
|
86
|
+
granted to You under this License for that Work shall terminate
|
87
|
+
as of the date such litigation is filed.
|
88
|
+
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
91
|
+
modifications, and in Source or Object form, provided that You
|
92
|
+
meet the following conditions:
|
93
|
+
|
94
|
+
(a) You must give any other recipients of the Work or
|
95
|
+
Derivative Works a copy of this License; and
|
96
|
+
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
98
|
+
stating that You changed the files; and
|
99
|
+
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
102
|
+
attribution notices from the Source form of the Work,
|
103
|
+
excluding those notices that do not pertain to any part of
|
104
|
+
the Derivative Works; and
|
105
|
+
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
108
|
+
include a readable copy of the attribution notices contained
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
111
|
+
of the following places: within a NOTICE text file distributed
|
112
|
+
as part of the Derivative Works; within the Source form or
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
114
|
+
within a display generated by the Derivative Works, if and
|
115
|
+
wherever such third-party notices normally appear. The contents
|
116
|
+
of the NOTICE file are for informational purposes only and
|
117
|
+
do not modify the License. You may add Your own attribution
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
120
|
+
that such additional attribution notices cannot be construed
|
121
|
+
as modifying the License.
|
122
|
+
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
124
|
+
may provide additional or different license terms and conditions
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
128
|
+
the conditions stated in this License.
|
129
|
+
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
133
|
+
this License, without any additional terms or conditions.
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135
|
+
the terms of any separate license agreement you may have executed
|
136
|
+
with Licensor regarding such Contributions.
|
137
|
+
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
140
|
+
except as required for reasonable and customary use in describing the
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
142
|
+
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
152
|
+
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
158
|
+
incidental, or consequential damages of any character arising as a
|
159
|
+
result of this License or out of the use or inability to use the
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
162
|
+
other commercial damages or losses), even if such Contributor
|
163
|
+
has been advised of the possibility of such damages.
|
164
|
+
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168
|
+
or other liability obligations and/or rights consistent with this
|
169
|
+
License. However, in accepting such obligations, You may act only
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
174
|
+
of your accepting any such warranty or additional liability.
|
175
|
+
|
176
|
+
END OF TERMS AND CONDITIONS
|
177
|
+
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
179
|
+
|
180
|
+
To apply the Apache License to your work, attach the following
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "{}"
|
182
|
+
replaced with your own identifying information. (Don't include
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
184
|
+
comment syntax for the file format. We also recommend that a
|
185
|
+
file or class name and description of purpose be included on the
|
186
|
+
same "printed page" as the copyright notice for easier
|
187
|
+
identification within third-party archives.
|
188
|
+
|
189
|
+
Copyright {yyyy} {name of copyright owner}
|
190
|
+
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192
|
+
you may not use this file except in compliance with the License.
|
193
|
+
You may obtain a copy of the License at
|
194
|
+
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
196
|
+
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200
|
+
See the License for the specific language governing permissions and
|
201
|
+
limitations under the License.
|
data/README.md
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
[![Build Status](https://travis-ci.org/westfieldlabs/data_janitor.svg?branch=master)](https://travis-ci.org/westfieldlabs/data_janitor)
|
2
|
+
|
3
|
+
# DataJanitor
|
4
|
+
|
5
|
+
DataJanitor allows you to run your in-application Active Record validations as well as additional data audit validations across all records in a table or database at will. This is particular helpful in evolving validations and finding which records will no longer pass validation, as well as periodically performing more extensive audit validations without the real-time cost. Additional validations can be written to run only during the audit, or can be also be run during create. This allows time to migrate existing data to the new validation requirements while ensuring new data meets the current validation standards.
|
6
|
+
|
7
|
+
DataJanitor also augments your ActiveRecord models (at rake-task runtime) to allow for running project-wide common validations on the data. Thus, it will look at all models in your repository and tell you whether any data was stored that potentially violates the common project data formats. This can happen if a model does not have enough validations of its own or if its validations are not strict enough.
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
```ruby
|
13
|
+
gem 'data_janitor'
|
14
|
+
```
|
15
|
+
|
16
|
+
And then execute:
|
17
|
+
|
18
|
+
$ bundle
|
19
|
+
|
20
|
+
Or install it yourself as:
|
21
|
+
|
22
|
+
$ gem install data_janitor
|
23
|
+
|
24
|
+
## Usage
|
25
|
+
|
26
|
+
### Custom Model Level Validations
|
27
|
+
|
28
|
+
ActiveRecord validations for **Audit Only**
|
29
|
+
|
30
|
+
```ruby
|
31
|
+
class SomeModel < ActiveRecord::Base
|
32
|
+
extend DataJanitor::AuditValidatable
|
33
|
+
|
34
|
+
dj_audit_validations do
|
35
|
+
# Desired validations
|
36
|
+
validates :country, inclusion: { in: ['US', 'AU', 'NZ'] }
|
37
|
+
end
|
38
|
+
end
|
39
|
+
```
|
40
|
+
These validations only run when validating with an the ActiveRecord context `:dj_audit` is included, as in `rec.invalid?(:dj_audit)`, so they normally will only be run by the DJ rake tasks.
|
41
|
+
|
42
|
+
ActiveRecord validations for **Audit** and **Newly Created Records**
|
43
|
+
|
44
|
+
```ruby
|
45
|
+
class SomeModel < ActiveRecord::Base
|
46
|
+
extend DataJanitor::AuditValidatable
|
47
|
+
|
48
|
+
dj_validations do
|
49
|
+
validates :name, length: { maximum: 25 }
|
50
|
+
end
|
51
|
+
end
|
52
|
+
```
|
53
|
+
These validations are run when validating during create and with an the ActiveRecord context `:dj_audit` is included, as in `rec.invalid?(:dj_audit)`, so they are run by the application as well as by the DJ rake tasks.
|
54
|
+
|
55
|
+
### Rake Tasks
|
56
|
+
|
57
|
+
To audit the data defined by the ActiveRecord models in your repository:
|
58
|
+
```
|
59
|
+
rake data_janitor:audit
|
60
|
+
rake data_janitor:audit['some/file/path.json']
|
61
|
+
rake data_janitor:audit['some/file/path.json',true]
|
62
|
+
```
|
63
|
+
|
64
|
+
This will audit your DB for errors and output them to `tmp/data_janitor_results.json` (by default), or a specified path. The report will contain a list of errors with IDs of invalid records for each model. Including `true` will also display the output at the console.
|
65
|
+
|
66
|
+
You can also audit a specific model rather than all models found in the repository:
|
67
|
+
|
68
|
+
```
|
69
|
+
rake data_janitor:audit_model[SomeModel]
|
70
|
+
```
|
71
|
+
|
72
|
+
To apply common fixes to all models in your repository:
|
73
|
+
```
|
74
|
+
rake data_janitor:cleanse
|
75
|
+
```
|
76
|
+
|
77
|
+
To apply common fixes to just one model:
|
78
|
+
```
|
79
|
+
rake data_janitor:cleanse[SomeModel]
|
80
|
+
```
|
81
|
+
|
82
|
+
This will apply all the fixes that do not require semantic analysis of the data (e.g. replace `nil` values with `""` for strings)
|
83
|
+
|
84
|
+
## Contributing
|
85
|
+
|
86
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/westfield/data_janitor.
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "data_janitor"
|
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
|
data/bin/setup
ADDED
data/contributing.md
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
## Contributing
|
2
|
+
|
3
|
+
0. Raise an issue in this project outlining the change you'd like to make. You'll need the `issue_number`
|
4
|
+
1. Fork this project into your own Github account
|
5
|
+
2. Create your feature branch (`git checkout -b {issue_number}_my-new-feature`)
|
6
|
+
4. Push to the branch (`git push -u origin {issue_number}_my-new-feature`)
|
7
|
+
5. Write RSpec tests to formalise the outcomes of your change
|
8
|
+
6. Write the code to implement the changes, ensuring that the tests eventually pass
|
9
|
+
7. Commit your changes (`git commit -am '{issue_number} Added some feature'`)
|
10
|
+
8. Push to the branch (`git push -u origin my-new-feature`)
|
11
|
+
9. Create a new Pull Request using Github's built-in mechanisms.
|
12
|
+
10. Wait for a code review to come back, or an approval.
|
13
|
+
11. Either go back and fix whatever the reviewers recommend, or watch and smile as your PR gets merged in and you become part of software development history.
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require_relative 'lib/data_janitor/version'
|
3
|
+
|
4
|
+
Gem::Specification.new do |spec|
|
5
|
+
spec.name = 'data_janitor'
|
6
|
+
spec.version = DataJanitor::VERSION
|
7
|
+
spec.authors = ['Louis Tran', 'Zhenya Mirkin']
|
8
|
+
spec.email = ['tran.louis@gmail.com']
|
9
|
+
|
10
|
+
spec.summary = %q{Rake task to check validity of column types and values.}
|
11
|
+
spec.description = %q{Rake task to check validity of column types and values.}
|
12
|
+
spec.homepage = 'https://github.com/westfieldlabs/data_janitor'
|
13
|
+
spec.license = 'Apache-2.0'
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
16
|
+
spec.bindir = 'bin'
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.require_paths = ['lib']
|
19
|
+
|
20
|
+
spec.required_ruby_version = '>= 2.2.2'
|
21
|
+
|
22
|
+
spec.add_dependency 'rails', '~> 4.2'
|
23
|
+
|
24
|
+
spec.add_development_dependency 'bundler', '~> 1.10'
|
25
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
26
|
+
spec.add_development_dependency 'rspec', '~> 3.3'
|
27
|
+
end
|
@@ -0,0 +1,15 @@
|
|
1
|
+
module DataJanitor
|
2
|
+
module AuditValidatable
|
3
|
+
# extended data janitor model validations that apply
|
4
|
+
# to new records and data_janitor audit purposes
|
5
|
+
def dj_validations(&block)
|
6
|
+
with_options(on: [:dj_audit, :create], &block)
|
7
|
+
end
|
8
|
+
|
9
|
+
# extended data janitor model validations that apply
|
10
|
+
# data_janitor audit purposes
|
11
|
+
def dj_audit_validations(&block)
|
12
|
+
with_options(on: [:dj_audit], &block)
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
module DataJanitor
|
2
|
+
module UniversalValidator
|
3
|
+
# TODO: Disabled until we decide to apply this condition as a standard validation
|
4
|
+
# TODO: Run standard validators instead of home-brewed
|
5
|
+
# validate :validate_field_values
|
6
|
+
# ACCEPTABLE_BOOLEAN_VALUES = %w(t true y yes on 1 f false n no off 0) # this list was taken from Postgres spec. TRUE FALSE, that are also there, are not listed because they are DB-native literals and have no representation in Ruby code
|
7
|
+
def validate_field_values
|
8
|
+
# selected_attributes = self.changed? ? self.changed_attributes : self.attributes
|
9
|
+
selected_attributes = self.attributes
|
10
|
+
|
11
|
+
selected_attributes.each do |field_name, field_val|
|
12
|
+
column = self.column_for_attribute field_name
|
13
|
+
report_error = lambda {|msg| errors[column.name] << msg}
|
14
|
+
|
15
|
+
if column.array
|
16
|
+
report_error.call "cannot be nil" if field_val.nil?
|
17
|
+
next
|
18
|
+
end
|
19
|
+
|
20
|
+
case column.type
|
21
|
+
when :boolean
|
22
|
+
report_error.call "cannot be nil" if field_val.nil?
|
23
|
+
# report_error.call("must be a valid boolean") unless ACCEPTABLE_BOOLEAN_VALUES.include? field_val
|
24
|
+
when :date
|
25
|
+
# Date.iso8601(field_val) rescue report_error.call("must be a date in ISO-8601")
|
26
|
+
when :time
|
27
|
+
# Time.iso8601(field_val) rescue report_error.call("must be a datetime in ISO-8601")
|
28
|
+
when :datetime
|
29
|
+
# Time.iso8601(field_val) rescue report_error.call("must be a datetime in ISO-8601")
|
30
|
+
when :decimal
|
31
|
+
report_error.call "cannot be nil" if field_val.nil?
|
32
|
+
# TODO: run numericality test
|
33
|
+
when :float
|
34
|
+
report_error.call "cannot be nil" if field_val.nil?
|
35
|
+
# TODO: run numericality test
|
36
|
+
when :integer
|
37
|
+
report_error.call "cannot be nil" if field_val.nil?
|
38
|
+
# TODO: run numericality test
|
39
|
+
when :string, :text
|
40
|
+
if field_val.nil?
|
41
|
+
report_error.call "cannot be nil. Use an empty string instead if that's what you wanted."
|
42
|
+
else
|
43
|
+
report_error.call "cannot have leading/trailing whitespaces" if field_val =~ /^\s/ || field_val =~ /\s$/
|
44
|
+
# TODO: Should we constrain to certain encoding types?
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
data/lib/data_janitor.rb
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
require "data_janitor/version"
|
2
|
+
require 'rails'
|
3
|
+
require "data_janitor/universal_validator"
|
4
|
+
require "data_janitor/audit_validatable"
|
5
|
+
|
6
|
+
module DataJanitor
|
7
|
+
|
8
|
+
class MyRailtie < Rails::Railtie
|
9
|
+
rake_tasks do
|
10
|
+
Dir[File.join(File.dirname(__FILE__),'tasks/*.rake')].each { |f| load f }
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
end
|
@@ -0,0 +1,100 @@
|
|
1
|
+
namespace :data_janitor do
|
2
|
+
desc 'Summarize invalid database records'
|
3
|
+
task :audit, [:output_file, :verbose, :unscoped] => [:environment] do |_t, args|
|
4
|
+
args.with_defaults(
|
5
|
+
output_file: Rails.root.join('tmp', 'data_janitor_results.json'),
|
6
|
+
verbose: false,
|
7
|
+
unscoped: false
|
8
|
+
)
|
9
|
+
|
10
|
+
output = {}
|
11
|
+
all_models.each do |ar_model|
|
12
|
+
begin
|
13
|
+
audit ar_model, output, args[:verbose], args[:unscoped]
|
14
|
+
rescue ActiveRecord::StatementInvalid # used to catch HABTM and schema migration. Only care about real Models
|
15
|
+
puts "skipping #{ar_model}"
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
File.write(args[:output_file], output.to_json)
|
20
|
+
|
21
|
+
puts "Wrote results to #{args[:output_file]}"
|
22
|
+
end
|
23
|
+
|
24
|
+
desc 'Audit one model for data issues'
|
25
|
+
task :audit_model, [:model] => [:environment] do |_t, args|
|
26
|
+
Rails.application.eager_load!
|
27
|
+
audit args[:model].constantize, {}, true
|
28
|
+
end
|
29
|
+
|
30
|
+
# For each model, apply trivial data corrections (those that do not require looking at data semantics).
|
31
|
+
# This includes:
|
32
|
+
# - replace all null strings with empty strings
|
33
|
+
# - replace all null booleans with false
|
34
|
+
# - replace all null arrays with []
|
35
|
+
desc 'Apply common and safe data corrections'
|
36
|
+
task cleanse: :environment do
|
37
|
+
all_models.each do |ar_model|
|
38
|
+
cleanse_model! ar_model
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
desc 'Apply fixes to one model only'
|
43
|
+
task :cleanse_model, [:model] => [:environment] do |_t, args|
|
44
|
+
Rails.application.eager_load!
|
45
|
+
|
46
|
+
cleanse_model! args[:model].constantize
|
47
|
+
end
|
48
|
+
|
49
|
+
private
|
50
|
+
|
51
|
+
def all_models
|
52
|
+
Rails.application.eager_load!
|
53
|
+
ActiveRecord::Base.descendants
|
54
|
+
end
|
55
|
+
|
56
|
+
def audit(model, output = {}, verbose = false, unscoped = false)
|
57
|
+
total = 0
|
58
|
+
failed = 0
|
59
|
+
puts "Validating: #{model.name}"
|
60
|
+
output[model.to_s] = {}
|
61
|
+
model = model.unscoped if unscoped
|
62
|
+
|
63
|
+
model.include(DataJanitor::UniversalValidator)
|
64
|
+
model.validate :validate_field_values
|
65
|
+
|
66
|
+
model.find_each do |rec|
|
67
|
+
if rec.invalid?(:dj_audit)
|
68
|
+
rec.errors.to_h.each_pair do |attribute, error_message|
|
69
|
+
output[model.to_s][attribute] ||= {}
|
70
|
+
output[model.to_s][attribute][error_message] ||= []
|
71
|
+
output[model.to_s][attribute][error_message] << rec.id
|
72
|
+
end
|
73
|
+
|
74
|
+
failed += 1
|
75
|
+
end
|
76
|
+
|
77
|
+
total += 1
|
78
|
+
end
|
79
|
+
|
80
|
+
puts output.to_json if verbose
|
81
|
+
puts "Completed #{total} records with #{failed} failures"
|
82
|
+
end
|
83
|
+
|
84
|
+
def cleanse_model!(model)
|
85
|
+
string_columns = model.columns.select{|c| (c.type == :string || c.type == :text) && c.array == false}
|
86
|
+
boolean_columns = model.columns.select{|c| c.type == :boolean && c.array == false}
|
87
|
+
array_columns = model.columns.select{|c| c.array == true}
|
88
|
+
|
89
|
+
clean_nils_from! model, string_columns, ""
|
90
|
+
clean_nils_from! model, boolean_columns, false
|
91
|
+
clean_nils_from! model, array_columns, []
|
92
|
+
end
|
93
|
+
|
94
|
+
def clean_nils_from!(model, columns, default)
|
95
|
+
columns.each do |column|
|
96
|
+
count = model.where(column.name => nil).update_all(column.name => default)
|
97
|
+
puts "Fixed #{count} #{model} records where #{column.name} was nil" if count > 0
|
98
|
+
end
|
99
|
+
end
|
100
|
+
end
|
metadata
ADDED
@@ -0,0 +1,121 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: data_janitor
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.3.4
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Louis Tran
|
8
|
+
- Zhenya Mirkin
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2017-06-09 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rails
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
requirements:
|
18
|
+
- - "~>"
|
19
|
+
- !ruby/object:Gem::Version
|
20
|
+
version: '4.2'
|
21
|
+
type: :runtime
|
22
|
+
prerelease: false
|
23
|
+
version_requirements: !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - "~>"
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
version: '4.2'
|
28
|
+
- !ruby/object:Gem::Dependency
|
29
|
+
name: bundler
|
30
|
+
requirement: !ruby/object:Gem::Requirement
|
31
|
+
requirements:
|
32
|
+
- - "~>"
|
33
|
+
- !ruby/object:Gem::Version
|
34
|
+
version: '1.10'
|
35
|
+
type: :development
|
36
|
+
prerelease: false
|
37
|
+
version_requirements: !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - "~>"
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '1.10'
|
42
|
+
- !ruby/object:Gem::Dependency
|
43
|
+
name: rake
|
44
|
+
requirement: !ruby/object:Gem::Requirement
|
45
|
+
requirements:
|
46
|
+
- - "~>"
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
version: '10.0'
|
49
|
+
type: :development
|
50
|
+
prerelease: false
|
51
|
+
version_requirements: !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - "~>"
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: '10.0'
|
56
|
+
- !ruby/object:Gem::Dependency
|
57
|
+
name: rspec
|
58
|
+
requirement: !ruby/object:Gem::Requirement
|
59
|
+
requirements:
|
60
|
+
- - "~>"
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: '3.3'
|
63
|
+
type: :development
|
64
|
+
prerelease: false
|
65
|
+
version_requirements: !ruby/object:Gem::Requirement
|
66
|
+
requirements:
|
67
|
+
- - "~>"
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '3.3'
|
70
|
+
description: Rake task to check validity of column types and values.
|
71
|
+
email:
|
72
|
+
- tran.louis@gmail.com
|
73
|
+
executables:
|
74
|
+
- console
|
75
|
+
- setup
|
76
|
+
extensions: []
|
77
|
+
extra_rdoc_files: []
|
78
|
+
files:
|
79
|
+
- ".github/ISSUE_TEMPLATE"
|
80
|
+
- ".github/PULL_REQUEST_TEMPLATE"
|
81
|
+
- ".gitignore"
|
82
|
+
- ".rspec"
|
83
|
+
- ".travis.yml"
|
84
|
+
- Gemfile
|
85
|
+
- LICENSE
|
86
|
+
- README.md
|
87
|
+
- Rakefile
|
88
|
+
- bin/console
|
89
|
+
- bin/setup
|
90
|
+
- contributing.md
|
91
|
+
- data_janitor.gemspec
|
92
|
+
- lib/data_janitor.rb
|
93
|
+
- lib/data_janitor/audit_validatable.rb
|
94
|
+
- lib/data_janitor/universal_validator.rb
|
95
|
+
- lib/data_janitor/version.rb
|
96
|
+
- lib/tasks/data_janitor.rake
|
97
|
+
homepage: https://github.com/westfieldlabs/data_janitor
|
98
|
+
licenses:
|
99
|
+
- Apache-2.0
|
100
|
+
metadata: {}
|
101
|
+
post_install_message:
|
102
|
+
rdoc_options: []
|
103
|
+
require_paths:
|
104
|
+
- lib
|
105
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
106
|
+
requirements:
|
107
|
+
- - ">="
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: 2.2.2
|
110
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
111
|
+
requirements:
|
112
|
+
- - ">="
|
113
|
+
- !ruby/object:Gem::Version
|
114
|
+
version: '0'
|
115
|
+
requirements: []
|
116
|
+
rubyforge_project:
|
117
|
+
rubygems_version: 2.4.8
|
118
|
+
signing_key:
|
119
|
+
specification_version: 4
|
120
|
+
summary: Rake task to check validity of column types and values.
|
121
|
+
test_files: []
|