schema-inference 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +49 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +97 -0
- data/Rakefile +6 -0
- data/bin/console +11 -0
- data/bin/setup +8 -0
- data/lib/extensions/boolean.rb +3 -0
- data/lib/schema/inference.rb +21 -0
- data/lib/schema/inference/schema_inferrer.rb +251 -0
- data/lib/schema/inference/version.rb +5 -0
- data/schema-inference.gemspec +29 -0
- metadata +157 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: e9966b0286d35c69194293d9895fe6e7198c893d
|
4
|
+
data.tar.gz: d15a656c7a2c654a618b29f976f27926de913180
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 7d33da3b607dba3848fc05d8a19d5c24554e39809302146b7581749923afa34fe980caa4cf18cf32d2ca2d40f885fedc0c4f273f7a25661f1baa878bde4d2bf4
|
7
|
+
data.tar.gz: 2fa3693d384696779211b7f5706a80453e473d2d986579293d0ee7ceb8a4de3b3a1774aff80b1e041437539317cdf749fe56956e809d98c2cee00043c3cc487d
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
# Contributor Code of Conduct
|
2
|
+
|
3
|
+
As contributors and maintainers of this project, and in the interest of
|
4
|
+
fostering an open and welcoming community, we pledge to respect all people who
|
5
|
+
contribute through reporting issues, posting feature requests, updating
|
6
|
+
documentation, submitting pull requests or patches, and other activities.
|
7
|
+
|
8
|
+
We are committed to making participation in this project a harassment-free
|
9
|
+
experience for everyone, regardless of level of experience, gender, gender
|
10
|
+
identity and expression, sexual orientation, disability, personal appearance,
|
11
|
+
body size, race, ethnicity, age, religion, or nationality.
|
12
|
+
|
13
|
+
Examples of unacceptable behavior by participants include:
|
14
|
+
|
15
|
+
* The use of sexualized language or imagery
|
16
|
+
* Personal attacks
|
17
|
+
* Trolling or insulting/derogatory comments
|
18
|
+
* Public or private harassment
|
19
|
+
* Publishing other's private information, such as physical or electronic
|
20
|
+
addresses, without explicit permission
|
21
|
+
* Other unethical or unprofessional conduct
|
22
|
+
|
23
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
24
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
25
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
26
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
27
|
+
threatening, offensive, or harmful.
|
28
|
+
|
29
|
+
By adopting this Code of Conduct, project maintainers commit themselves to
|
30
|
+
fairly and consistently applying these principles to every aspect of managing
|
31
|
+
this project. Project maintainers who do not follow or enforce the Code of
|
32
|
+
Conduct may be permanently removed from the project team.
|
33
|
+
|
34
|
+
This code of conduct applies both within project spaces and in public spaces
|
35
|
+
when an individual is representing the project or its community.
|
36
|
+
|
37
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
38
|
+
reported by contacting a project maintainer at eurico@phybbit.com. All
|
39
|
+
complaints will be reviewed and investigated and will result in a response that
|
40
|
+
is deemed necessary and appropriate to the circumstances. Maintainers are
|
41
|
+
obligated to maintain confidentiality with regard to the reporter of an
|
42
|
+
incident.
|
43
|
+
|
44
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
45
|
+
version 1.3.0, available at
|
46
|
+
[http://contributor-covenant.org/version/1/3/0/][version]
|
47
|
+
|
48
|
+
[homepage]: http://contributor-covenant.org
|
49
|
+
[version]: http://contributor-covenant.org/version/1/3/0/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 株式会社Phybbit
|
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 +1,97 @@
|
|
1
|
+
# Schema::Inference
|
2
|
+
|
3
|
+
Supports inferring tabular schemas from deep nested data structures.
|
4
|
+
There 2 main uses for this gem:
|
5
|
+
- gives schema information on a nested data structure (useful when converting to a tabular format)
|
6
|
+
- recover types from data that has been serialized to string (e.g. JSON or CSV)
|
7
|
+
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
```ruby
|
13
|
+
gem 'schema-inference'
|
14
|
+
```
|
15
|
+
|
16
|
+
And then execute:
|
17
|
+
|
18
|
+
$ bundle
|
19
|
+
|
20
|
+
Or install it yourself as:
|
21
|
+
|
22
|
+
$ gem install schema-inference
|
23
|
+
|
24
|
+
## Usage
|
25
|
+
|
26
|
+
1. Report information on nested data structure
|
27
|
+
|
28
|
+
```
|
29
|
+
schema = Schema::Inference.schema(dataset: [
|
30
|
+
{
|
31
|
+
'person' => {
|
32
|
+
'name' => 'Bob',
|
33
|
+
'age' => 30,
|
34
|
+
'weight' => 60
|
35
|
+
},
|
36
|
+
'updated_at' => '2016-01-01T00:00:00Z'
|
37
|
+
},
|
38
|
+
{
|
39
|
+
'person' => {
|
40
|
+
'name' => 'Alice',
|
41
|
+
# Alice does not want to show her age
|
42
|
+
'weight' => 50.5
|
43
|
+
},
|
44
|
+
'updated_at' => '2016-01-01T00:00:00Z'
|
45
|
+
},
|
46
|
+
])
|
47
|
+
|
48
|
+
schema['person.name'][:type] # String
|
49
|
+
schema['person.name'][:usage] # 1.0 (100% of the entries have a name)
|
50
|
+
|
51
|
+
schema['person.age'][:type] # Integer
|
52
|
+
schema['person.age'][:usage] # 0.5 (50% of the entries have an age)
|
53
|
+
|
54
|
+
schema['person.weight'][:type] # Numeric (inferred to be numeric, even though an integer was present)
|
55
|
+
schema['updated_at'][:type] # Time
|
56
|
+
```
|
57
|
+
|
58
|
+
2. Recover types from string serialization
|
59
|
+
|
60
|
+
```
|
61
|
+
schema = Schema::Inference.schema(dataset: {
|
62
|
+
'serialized_time' => '2016-01-01T00:00:00Z',
|
63
|
+
'serialized_integer' => '100',
|
64
|
+
'serialized_numeric' => '0.5',
|
65
|
+
'serialized_boolean' => 'true',
|
66
|
+
})
|
67
|
+
schema['serialized_time'][:type] # Time
|
68
|
+
schema['serialized_integer'][:type] # Integer
|
69
|
+
schema['serialized_numeric'][:type] # Numeric
|
70
|
+
schema['serialized_boolean'][:type] # Boolean
|
71
|
+
```
|
72
|
+
|
73
|
+
3. If you need to load a lot of data consider using the following pattern:
|
74
|
+
```
|
75
|
+
schema = Schema::Inference.schema(batch_count: 10) do |idx\
|
76
|
+
# Pull and return some large amount of data.
|
77
|
+
# Fetching/accessing the data here would avoid the IPC cost of
|
78
|
+
# sending the data to the child process for parallel processing.
|
79
|
+
# e.g.:
|
80
|
+
MongoClient.find.limit(1000).offset(1000 * idx)
|
81
|
+
end
|
82
|
+
```
|
83
|
+
|
84
|
+
## Development
|
85
|
+
|
86
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. In certain cases, you maybe want to use the debug flag e.g. `DEBUG=true rake spec` to disable parallel schema processing. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
87
|
+
|
88
|
+
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).
|
89
|
+
|
90
|
+
## Contributing
|
91
|
+
|
92
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/phybbit/schema-inference. 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.
|
93
|
+
|
94
|
+
|
95
|
+
## License
|
96
|
+
|
97
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'bundler/setup'
|
4
|
+
require 'schema/inference'
|
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
|
data/bin/setup
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'active_support'
|
2
|
+
require 'active_support/core_ext/object/blank'
|
3
|
+
require 'active_support/core_ext/hash/reverse_merge'
|
4
|
+
|
5
|
+
require 'parallel'
|
6
|
+
require 'timeliness'
|
7
|
+
|
8
|
+
require 'extensions/boolean'
|
9
|
+
require 'schema/inference/version'
|
10
|
+
require 'schema/inference/schema_inferrer'
|
11
|
+
|
12
|
+
|
13
|
+
module Schema
|
14
|
+
module Inference
|
15
|
+
|
16
|
+
def Inference.schema(*args)
|
17
|
+
SchemaInferrer.new.infer_schema(*args)
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,251 @@
|
|
1
|
+
module Schema
|
2
|
+
module Inference
|
3
|
+
class SchemaInferrer
|
4
|
+
attr_accessor :separator
|
5
|
+
|
6
|
+
def initialize(separator: '.')
|
7
|
+
@separator = separator
|
8
|
+
end
|
9
|
+
|
10
|
+
# Generate a schema based on this collection's records.
|
11
|
+
# We evaluate the schema of each record and then merge all
|
12
|
+
# the information together.
|
13
|
+
# @param dataset [Array] of samples on which we will
|
14
|
+
# perform the schema analysis.
|
15
|
+
# @param extended [Boolean] Set to true to keep each field as a basic type.
|
16
|
+
# Set to false to reduce the terminal arrays to a single key (under the type array).
|
17
|
+
# @return [Hash] with one entry per 'column'/'field'. The values
|
18
|
+
# contains information about the type and usage.
|
19
|
+
def infer_schema(dataset: [], batch_count: 0, extended: false)
|
20
|
+
# support detecting schemas of single objects
|
21
|
+
dataset = [dataset] if dataset.is_a?(Hash)
|
22
|
+
validate_dataset(dataset)
|
23
|
+
|
24
|
+
has_dataset = dataset.count > 0 || (block_given? && batch_count > 0)
|
25
|
+
raise ArgumentError, 'a dataset or a block with a batch count must be passed' unless has_dataset
|
26
|
+
|
27
|
+
if dataset.is_a?(Array) && dataset.count > 0
|
28
|
+
# divide in batches to process in parallel
|
29
|
+
per_process = (dataset.count / Parallel.processor_count.to_f).ceil
|
30
|
+
batch_count = (dataset.count / per_process.to_f).ceil
|
31
|
+
end
|
32
|
+
|
33
|
+
results = parallel_map(batch_count.times) { |i|
|
34
|
+
batch = block_given? ? yield(i) : dataset[i*per_process...(i+1)*per_process]
|
35
|
+
{ partial_schema: data_schema(batch), count: batch.count }
|
36
|
+
}
|
37
|
+
|
38
|
+
partial_schemas = results.map { |r| r[:partial_schema] }
|
39
|
+
total_count = results.map { |r| r[:count] }.reduce(:+)
|
40
|
+
|
41
|
+
table_schema = process_schema_results(partial_schemas, total_count, extended)
|
42
|
+
table_schema.sort_by { |k, v| -v[:usage] }.to_h
|
43
|
+
end
|
44
|
+
|
45
|
+
private
|
46
|
+
|
47
|
+
def validate_dataset(dataset)
|
48
|
+
return if dataset.is_a?(Array)
|
49
|
+
raise ArgumentError, 'dataset must be an array or a hash'
|
50
|
+
end
|
51
|
+
|
52
|
+
def data_schema(data)
|
53
|
+
table_schema = {}
|
54
|
+
data.each do |record|
|
55
|
+
# fetch the record schema & update the general schema
|
56
|
+
rec_schema = record_schema(record)
|
57
|
+
rec_schema.each do |field_schema|
|
58
|
+
table_schema[field_schema[:field]] ||= {type: field_schema[:type], usage_count: 0}
|
59
|
+
if table_schema[field_schema[:field]][:type] != field_schema[:type]
|
60
|
+
if table_schema[field_schema[:field]][:type] == NilClass
|
61
|
+
table_schema[field_schema[:field]][:type] = field_schema[:type]
|
62
|
+
elsif field_schema[:type] != nil
|
63
|
+
table_schema[field_schema[:field]][:type] = lowest_common_type(field_schema[:type], table_schema[field_schema[:field]][:type])
|
64
|
+
end
|
65
|
+
end
|
66
|
+
table_schema[field_schema[:field]][:usage_count] += 1
|
67
|
+
table_schema[field_schema[:field]][:types] ||= {}
|
68
|
+
table_schema[field_schema[:field]][:types][field_schema[:type]] ||= 0
|
69
|
+
table_schema[field_schema[:field]][:types][field_schema[:type]] += 1
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
table_schema
|
74
|
+
end
|
75
|
+
|
76
|
+
def process_schema_results(results, total_count, extended)
|
77
|
+
# aggregate the results
|
78
|
+
table_schema = results[0]
|
79
|
+
results[1..-1].each { |res|
|
80
|
+
table_schema.each { |k, v|
|
81
|
+
next if res[k].blank?
|
82
|
+
|
83
|
+
# aggregate types count
|
84
|
+
res[k][:types].each { |type, count|
|
85
|
+
table_schema[k][:types][type] ||= 0
|
86
|
+
table_schema[k][:types][type] += count
|
87
|
+
}
|
88
|
+
|
89
|
+
# aggregate other informations
|
90
|
+
table_schema[k][:usage_count] += res[k][:usage_count].to_i
|
91
|
+
if (table_schema[k][:type] != res[k][:type])
|
92
|
+
if table_schema[k][:type] == NilClass
|
93
|
+
table_schema[k][:type] = res[k][:type]
|
94
|
+
elsif res[k][:type] != NilClass
|
95
|
+
table_schema[k][:type] = lowest_common_type(res[k][:type], table_schema[k][:type])
|
96
|
+
end
|
97
|
+
end
|
98
|
+
}
|
99
|
+
|
100
|
+
# make sure keys that were not in table_schema are now added.
|
101
|
+
table_schema.reverse_merge!(res)
|
102
|
+
}
|
103
|
+
|
104
|
+
# detect and remove nulls that are part of other schemas
|
105
|
+
# e.g. { 'some_data': null } and { 'some_data': { 'hash': 1 } }
|
106
|
+
# shouldn't be reported as different keys
|
107
|
+
table_schema.each { |k, v|
|
108
|
+
next unless v[:type] == NilClass
|
109
|
+
# check if there is any key that match this one plus an hash/array extension
|
110
|
+
full_key_exists = table_schema.find {|full_key, _| full_key =~ /^#{k}#{Regexp.quote(separator)}.*/}.present?
|
111
|
+
table_schema.delete(k) if full_key_exists
|
112
|
+
}
|
113
|
+
|
114
|
+
# detect and process array information
|
115
|
+
unless extended
|
116
|
+
terminal_array_keys = {}
|
117
|
+
table_schema.keys.each { |key|
|
118
|
+
is_terminal_array = /.*#{Regexp.quote(separator)}[0-9]+$/ =~ key
|
119
|
+
next unless is_terminal_array
|
120
|
+
key_prefix = key.split(separator)[0...-1].join(separator)
|
121
|
+
terminal_array_keys[key_prefix] ||= []
|
122
|
+
terminal_array_keys[key_prefix] << key
|
123
|
+
}
|
124
|
+
|
125
|
+
terminal_array_keys.each do |key_prefix, keys|
|
126
|
+
keys_usage_count = keys.map{ |x| table_schema[x][:usage_count] }
|
127
|
+
usage_count = keys_usage_count.max
|
128
|
+
# min size = how many keys have "always" been used
|
129
|
+
# As the keys may not have been used at the same time,
|
130
|
+
# this may not be valid depending on the array usage.
|
131
|
+
min_size = keys_usage_count.count { |x| x == usage_count }
|
132
|
+
max_size = keys.map { |x| x.split(separator)[-1].to_i }.max + 1
|
133
|
+
|
134
|
+
# delete keys that are part of they array
|
135
|
+
keys.each { |key, _| table_schema.delete(key) }
|
136
|
+
|
137
|
+
table_schema[key_prefix] = {
|
138
|
+
type: Array,
|
139
|
+
usage_count: usage_count,
|
140
|
+
min_size: min_size,
|
141
|
+
max_size: max_size
|
142
|
+
}
|
143
|
+
end
|
144
|
+
end
|
145
|
+
|
146
|
+
# add a percentage in terms of usage
|
147
|
+
table_schema.each { |k, v|
|
148
|
+
table_schema[k][:usage] = table_schema[k][:usage_count] / total_count.to_f
|
149
|
+
}
|
150
|
+
|
151
|
+
table_schema
|
152
|
+
end
|
153
|
+
|
154
|
+
NumericTypes = [Numeric, Integer].freeze
|
155
|
+
def lowest_common_type(type1, type2)
|
156
|
+
return type1 if type1 == type2
|
157
|
+
return Numeric if NumericTypes.include?(type1) && NumericTypes.include?(type2)
|
158
|
+
Object
|
159
|
+
end
|
160
|
+
|
161
|
+
# Recursively explore a record and return its schema
|
162
|
+
def record_schema(record, name = "")
|
163
|
+
if record.is_a? Hash
|
164
|
+
record.flat_map { |k, v|
|
165
|
+
field_name = "#{name}#{separator}#{k}" if name.present?
|
166
|
+
field_name ||= k
|
167
|
+
record_schema(v, field_name)
|
168
|
+
}
|
169
|
+
elsif record.is_a? Array
|
170
|
+
record.each_with_index.flat_map { |x, index|
|
171
|
+
field_name = "#{name}#{separator}#{index}" if name.present?
|
172
|
+
field_name ||= k
|
173
|
+
record_schema(x, field_name)
|
174
|
+
}
|
175
|
+
else
|
176
|
+
{ field: name, type: detect_type_of(record) }
|
177
|
+
end
|
178
|
+
end
|
179
|
+
|
180
|
+
def detect_type_of(value)
|
181
|
+
return Boolean if value.is_a?(TrueClass) || value.is_a?(FalseClass)
|
182
|
+
return Integer if value.is_a? Integer
|
183
|
+
return Numeric if value.is_a? Numeric
|
184
|
+
return Time if value.is_a? Time
|
185
|
+
return NilClass if value.is_a? NilClass
|
186
|
+
|
187
|
+
if value.is_a? String
|
188
|
+
return Integer if value =~ /^[-+]?[0-9]+$/
|
189
|
+
return Numeric if value =~ /^[-+]?[0-9]*\.?[0-9]+$/
|
190
|
+
return Boolean if %w(false true).include?(value.downcase)
|
191
|
+
return Time if Timeliness.parse(value) != nil
|
192
|
+
return String
|
193
|
+
end
|
194
|
+
|
195
|
+
Object
|
196
|
+
end
|
197
|
+
|
198
|
+
def key_access_tokens(key:)
|
199
|
+
key.split(separator).map { |token|
|
200
|
+
# only parse integers for array indexing
|
201
|
+
next token unless is_integer?(token)
|
202
|
+
token.to_i
|
203
|
+
}
|
204
|
+
end
|
205
|
+
|
206
|
+
def record_value(record:, key:)
|
207
|
+
tokens = key_access_tokens(key: key)
|
208
|
+
record.dig(*tokens)
|
209
|
+
end
|
210
|
+
|
211
|
+
def add_value_to_record(record:, key:, value:)
|
212
|
+
tokens = key.split(separator)
|
213
|
+
current_ref = record
|
214
|
+
previous_token = tokens[0]
|
215
|
+
|
216
|
+
tokens[1..-1].each_with_index { |token|
|
217
|
+
if is_integer?(token)
|
218
|
+
current_ref[previous_token] ||= []
|
219
|
+
current_ref = current_ref[previous_token]
|
220
|
+
previous_token = token.to_i
|
221
|
+
else
|
222
|
+
current_ref[previous_token] ||= {}
|
223
|
+
current_ref = current_ref[previous_token]
|
224
|
+
previous_token = token
|
225
|
+
end
|
226
|
+
}
|
227
|
+
|
228
|
+
current_ref[previous_token] = value
|
229
|
+
end
|
230
|
+
|
231
|
+
def is_integer?(value)
|
232
|
+
(/^[+-]?[0-9]+$/ =~ value).present?
|
233
|
+
end
|
234
|
+
|
235
|
+
def parallel_map(itr, &block)
|
236
|
+
# set to true to debug code in the iteration
|
237
|
+
is_debugging_impl = ENV['DEBUG']
|
238
|
+
if is_debugging_impl
|
239
|
+
itr.map do |arg|
|
240
|
+
block.call(arg)
|
241
|
+
end
|
242
|
+
else
|
243
|
+
Parallel.map(itr) do |arg|
|
244
|
+
block.call(arg)
|
245
|
+
end
|
246
|
+
end
|
247
|
+
end
|
248
|
+
|
249
|
+
end
|
250
|
+
end
|
251
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'schema/inference/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'schema-inference'
|
8
|
+
spec.version = Schema::Inference::VERSION
|
9
|
+
spec.authors = ['Eurico Doirado']
|
10
|
+
spec.email = ['eurico@phybbit.com']
|
11
|
+
|
12
|
+
spec.summary = %q{Supports inferring tabular schemas from deep nested structures.}
|
13
|
+
spec.homepage = 'https://github.com/Phybbit/schema-inference'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ['lib']
|
20
|
+
|
21
|
+
spec.add_development_dependency 'bundler', '~> 1.12'
|
22
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
23
|
+
spec.add_development_dependency 'rspec', '~> 3.0'
|
24
|
+
spec.add_development_dependency 'pry-byebug'
|
25
|
+
|
26
|
+
spec.add_dependency 'activesupport', '>= 4.0.0'
|
27
|
+
spec.add_dependency 'parallel', '~>1.8'
|
28
|
+
spec.add_dependency 'timeliness', '~>0.3'
|
29
|
+
end
|
metadata
ADDED
@@ -0,0 +1,157 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: schema-inference
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Eurico Doirado
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-09-03 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.12'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.12'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry-byebug
|
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: activesupport
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 4.0.0
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 4.0.0
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: parallel
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '1.8'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.8'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: timeliness
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0.3'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0.3'
|
111
|
+
description:
|
112
|
+
email:
|
113
|
+
- eurico@phybbit.com
|
114
|
+
executables: []
|
115
|
+
extensions: []
|
116
|
+
extra_rdoc_files: []
|
117
|
+
files:
|
118
|
+
- ".gitignore"
|
119
|
+
- ".rspec"
|
120
|
+
- ".travis.yml"
|
121
|
+
- CODE_OF_CONDUCT.md
|
122
|
+
- Gemfile
|
123
|
+
- LICENSE.txt
|
124
|
+
- README.md
|
125
|
+
- Rakefile
|
126
|
+
- bin/console
|
127
|
+
- bin/setup
|
128
|
+
- lib/extensions/boolean.rb
|
129
|
+
- lib/schema/inference.rb
|
130
|
+
- lib/schema/inference/schema_inferrer.rb
|
131
|
+
- lib/schema/inference/version.rb
|
132
|
+
- schema-inference.gemspec
|
133
|
+
homepage: https://github.com/Phybbit/schema-inference
|
134
|
+
licenses:
|
135
|
+
- MIT
|
136
|
+
metadata: {}
|
137
|
+
post_install_message:
|
138
|
+
rdoc_options: []
|
139
|
+
require_paths:
|
140
|
+
- lib
|
141
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - ">="
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
147
|
+
requirements:
|
148
|
+
- - ">="
|
149
|
+
- !ruby/object:Gem::Version
|
150
|
+
version: '0'
|
151
|
+
requirements: []
|
152
|
+
rubyforge_project:
|
153
|
+
rubygems_version: 2.5.1
|
154
|
+
signing_key:
|
155
|
+
specification_version: 4
|
156
|
+
summary: Supports inferring tabular schemas from deep nested structures.
|
157
|
+
test_files: []
|