yancya-big_query 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 +37 -0
- data/CHANGELOG.md +8 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +80 -0
- data/LICENSE +21 -0
- data/README.md +54 -0
- data/Rakefile +10 -0
- data/big_query.gemspec +26 -0
- data/bin/big_query +3 -0
- data/lib/yancya/big_query/dataset.rb +31 -0
- data/lib/yancya/big_query/datasets.rb +63 -0
- data/lib/yancya/big_query/initializer.rb +9 -0
- data/lib/yancya/big_query/job.rb +53 -0
- data/lib/yancya/big_query/jobs.rb +61 -0
- data/lib/yancya/big_query/project.rb +33 -0
- data/lib/yancya/big_query/projects.rb +21 -0
- data/lib/yancya/big_query/request_executor.rb +23 -0
- data/lib/yancya/big_query/table.rb +68 -0
- data/lib/yancya/big_query/tabledata.rb +37 -0
- data/lib/yancya/big_query/tables.rb +90 -0
- data/lib/yancya/big_query/version.rb +5 -0
- data/lib/yancya/big_query.rb +68 -0
- data/test/test_big_query.rb +176 -0
- metadata +125 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 6d5bd68e33c49a23f96f348b24d41aa9e2140af2
|
4
|
+
data.tar.gz: a4ae4adae7acf4754728e94ca31a9726239aa1ad
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: dcae7d1b73287106727ac1ebbf5a4e0f344ad6f981c78686f4ae47de33cda2b93fbf36a0e108a6052b56ad763f1e1eed93bf9af891589aafa94cf8f37a653025
|
7
|
+
data.tar.gz: aa6af3940f7b669a3b00a727cc75638f550f1fa4690bbfffb83fee0d145fb7c95142963d74865dfe84f4f5dda11c229ebcf4ea238f6b3fe593593422ad203ba4
|
data/.gitignore
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
*.gem
|
2
|
+
*.rbc
|
3
|
+
/.config
|
4
|
+
/coverage/
|
5
|
+
/InstalledFiles
|
6
|
+
/pkg/
|
7
|
+
/spec/reports/
|
8
|
+
/test/tmp/
|
9
|
+
/test/version_tmp/
|
10
|
+
/tmp/
|
11
|
+
|
12
|
+
## Specific to RubyMotion:
|
13
|
+
.dat*
|
14
|
+
.repl_history
|
15
|
+
build/
|
16
|
+
|
17
|
+
## Documentation cache and generated files:
|
18
|
+
/.yardoc/
|
19
|
+
/_yardoc/
|
20
|
+
/doc/
|
21
|
+
/rdoc/
|
22
|
+
|
23
|
+
## Environment normalisation:
|
24
|
+
/.bundle/
|
25
|
+
/lib/bundler/man/
|
26
|
+
|
27
|
+
# for a library or gem, you might want to ignore these files since the code is
|
28
|
+
# intended to run in multiple environments; otherwise, check them in:
|
29
|
+
# Gemfile.lock
|
30
|
+
# .ruby-version
|
31
|
+
# .ruby-gemset
|
32
|
+
|
33
|
+
# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
|
34
|
+
.rvmrc
|
35
|
+
|
36
|
+
# IDEA config file
|
37
|
+
.idea
|
data/CHANGELOG.md
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
big_query (0.0.2)
|
5
|
+
google-api-client
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: https://rubygems.org/
|
9
|
+
specs:
|
10
|
+
activesupport (4.2.1)
|
11
|
+
i18n (~> 0.7)
|
12
|
+
json (~> 1.7, >= 1.7.7)
|
13
|
+
minitest (~> 5.1)
|
14
|
+
thread_safe (~> 0.3, >= 0.3.4)
|
15
|
+
tzinfo (~> 1.1)
|
16
|
+
addressable (2.3.8)
|
17
|
+
autoparse (0.3.3)
|
18
|
+
addressable (>= 2.3.1)
|
19
|
+
extlib (>= 0.9.15)
|
20
|
+
multi_json (>= 1.0.0)
|
21
|
+
extlib (0.9.16)
|
22
|
+
faraday (0.9.1)
|
23
|
+
multipart-post (>= 1.2, < 3)
|
24
|
+
google-api-client (0.8.6)
|
25
|
+
activesupport (>= 3.2)
|
26
|
+
addressable (~> 2.3)
|
27
|
+
autoparse (~> 0.3)
|
28
|
+
extlib (~> 0.9)
|
29
|
+
faraday (~> 0.9)
|
30
|
+
googleauth (~> 0.3)
|
31
|
+
launchy (~> 2.4)
|
32
|
+
multi_json (~> 1.10)
|
33
|
+
retriable (~> 1.4)
|
34
|
+
signet (~> 0.6)
|
35
|
+
googleauth (0.4.1)
|
36
|
+
faraday (~> 0.9)
|
37
|
+
jwt (~> 1.4)
|
38
|
+
logging (~> 2.0)
|
39
|
+
memoist (~> 0.12)
|
40
|
+
multi_json (= 1.11)
|
41
|
+
signet (~> 0.6)
|
42
|
+
i18n (0.7.0)
|
43
|
+
json (1.8.3)
|
44
|
+
jwt (1.5.0)
|
45
|
+
launchy (2.4.3)
|
46
|
+
addressable (~> 2.3)
|
47
|
+
little-plugger (1.1.3)
|
48
|
+
logging (2.0.0)
|
49
|
+
little-plugger (~> 1.1)
|
50
|
+
multi_json (~> 1.10)
|
51
|
+
memoist (0.12.0)
|
52
|
+
minitest (5.7.0)
|
53
|
+
multi_json (1.11.0)
|
54
|
+
multipart-post (2.0.0)
|
55
|
+
power_assert (0.2.3)
|
56
|
+
rake (10.4.2)
|
57
|
+
retriable (1.4.1)
|
58
|
+
signet (0.6.1)
|
59
|
+
addressable (~> 2.3)
|
60
|
+
extlib (~> 0.9)
|
61
|
+
faraday (~> 0.9)
|
62
|
+
jwt (~> 1.5)
|
63
|
+
multi_json (~> 1.10)
|
64
|
+
test-unit (3.1.1)
|
65
|
+
power_assert
|
66
|
+
thread_safe (0.3.5)
|
67
|
+
tzinfo (1.2.2)
|
68
|
+
thread_safe (~> 0.1)
|
69
|
+
|
70
|
+
PLATFORMS
|
71
|
+
ruby
|
72
|
+
|
73
|
+
DEPENDENCIES
|
74
|
+
big_query!
|
75
|
+
bundler (~> 1.6)
|
76
|
+
rake
|
77
|
+
test-unit
|
78
|
+
|
79
|
+
BUNDLED WITH
|
80
|
+
1.10.3
|
data/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2014 Shinta Koyanagi
|
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 all
|
13
|
+
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 THE
|
21
|
+
SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
# BigQuery
|
2
|
+
|
3
|
+
[![Gitter](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/yancya/big_query?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
|
4
|
+
|
5
|
+
Google BigQuery API client library
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
gem 'big_query', github: "yancya/big_query"
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or build and install it yourself as:
|
18
|
+
|
19
|
+
$ git clone git@github.com:yancya/big_query.git
|
20
|
+
$ cd big_query
|
21
|
+
$ rake install
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
```rb
|
26
|
+
bq = BigQuery.new(
|
27
|
+
key_path: "path_to_secret_key"
|
28
|
+
issuer: "mail@address"
|
29
|
+
)
|
30
|
+
|
31
|
+
job = bq.jobs.query(
|
32
|
+
project_id: "name_of_project",
|
33
|
+
sql: "select 1 as a, 2 as b, 3 as c"
|
34
|
+
)
|
35
|
+
|
36
|
+
begin
|
37
|
+
result = job.query_results
|
38
|
+
end until result["jobComplete"]
|
39
|
+
|
40
|
+
result["schema"]["fields"].map{|f| f["name"]}.join(",") #=> "a,b,c"
|
41
|
+
result["rows"].map{|row| row["f"].map{|col| col["v"]}.join(",")} #=> ["1,2,3"]
|
42
|
+
```
|
43
|
+
|
44
|
+
## Google BigQuery API Reference
|
45
|
+
|
46
|
+
https://developers.google.com/bigquery/docs/reference/v2/
|
47
|
+
|
48
|
+
## Contributing
|
49
|
+
|
50
|
+
1. Fork it ( https://github.com/yancya/big_query/fork )
|
51
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
52
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
53
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
54
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/big_query.gemspec
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'yancya/big_query/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "yancya-big_query"
|
8
|
+
spec.version = Yancya::BigQuery::VERSION
|
9
|
+
spec.authors = ["yancya"]
|
10
|
+
spec.email = ["yancya@upec.jp"]
|
11
|
+
spec.summary = %q{Google BigQuery API client library.}
|
12
|
+
spec.description = %q{Google BigQuery API client library. This is simple wrapper.}
|
13
|
+
spec.homepage = "https://github.com/yancya/big_query"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
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_runtime_dependency "google-api-client", "~> 0"
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
24
|
+
spec.add_development_dependency "rake", "~> 0"
|
25
|
+
spec.add_development_dependency "test-unit", "~> 0"
|
26
|
+
end
|
data/bin/big_query
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
require_relative 'tables'
|
2
|
+
|
3
|
+
module Yancya
|
4
|
+
class BigQuery::Dataset
|
5
|
+
def initialize(resource:, bq:)
|
6
|
+
@resource = resource
|
7
|
+
@tables = BigQuery::Tables.new(bq: bq)
|
8
|
+
end
|
9
|
+
|
10
|
+
def tables
|
11
|
+
@tables.list(
|
12
|
+
project_id: project_id,
|
13
|
+
dataset_id: dataset_id
|
14
|
+
)
|
15
|
+
end
|
16
|
+
|
17
|
+
def project_id
|
18
|
+
dataset_reference["projectId"]
|
19
|
+
end
|
20
|
+
|
21
|
+
def dataset_id
|
22
|
+
dataset_reference["datasetId"]
|
23
|
+
end
|
24
|
+
|
25
|
+
private
|
26
|
+
|
27
|
+
def dataset_reference
|
28
|
+
@resource["datasetReference"]
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
require_relative 'initializer'
|
2
|
+
require_relative 'request_executor'
|
3
|
+
|
4
|
+
require_relative 'dataset'
|
5
|
+
|
6
|
+
module Yancya
|
7
|
+
class BigQuery::Datasets
|
8
|
+
include Initializer
|
9
|
+
include RequestExecutor
|
10
|
+
|
11
|
+
def delete(project_id:, dataset_id:)
|
12
|
+
execute(
|
13
|
+
api_method: @bq.api.datasets.delete,
|
14
|
+
parameters: {projectId: project_id, datasetId: dataset_id, deleteContents: true}
|
15
|
+
)
|
16
|
+
end
|
17
|
+
|
18
|
+
def get(project_id:, dataset_id:)
|
19
|
+
execute(
|
20
|
+
api_method: @bq.api.datasets.get,
|
21
|
+
parameters: {projectId: project_id, datasetId: dataset_id}
|
22
|
+
)
|
23
|
+
end
|
24
|
+
|
25
|
+
def insert(project_id:, dataset:)
|
26
|
+
execute(
|
27
|
+
api_method: @bq.api.datasets.insert,
|
28
|
+
parameters: {projectId: project_id},
|
29
|
+
body_object: dataset
|
30
|
+
)
|
31
|
+
end
|
32
|
+
|
33
|
+
def list(project_id:)
|
34
|
+
resources = execute(
|
35
|
+
api_method: @bq.api.datasets.list,
|
36
|
+
parameters: {projectId: project_id}
|
37
|
+
)
|
38
|
+
|
39
|
+
resources["datasets"].map{ |resource|
|
40
|
+
Yancya::BigQuery::Dataset.new(
|
41
|
+
resource: resource,
|
42
|
+
bq: @bq
|
43
|
+
)
|
44
|
+
}
|
45
|
+
end
|
46
|
+
|
47
|
+
def patch(project_id:, dataset_id:, dataset:)
|
48
|
+
execute(
|
49
|
+
api_method: @bq.api.datasets.patch,
|
50
|
+
parameters: {projectId: project_id, datasetId: dataset_id},
|
51
|
+
body_object: dataset
|
52
|
+
)
|
53
|
+
end
|
54
|
+
|
55
|
+
def update(project_id:, dataset_id:, dataset:)
|
56
|
+
execute(
|
57
|
+
api_method: @bq.api.datasets.update,
|
58
|
+
parameters: {projectId: project_id, datasetId: dataset_id},
|
59
|
+
body_object: dataset
|
60
|
+
)
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
@@ -0,0 +1,53 @@
|
|
1
|
+
module Yancya
|
2
|
+
class BigQuery::Job
|
3
|
+
def initialize(resource:, bq:)
|
4
|
+
@resource = resource
|
5
|
+
@jobs = BigQuery::Jobs.new(bq: bq)
|
6
|
+
end
|
7
|
+
|
8
|
+
def query_results
|
9
|
+
@jobs.get_query_results(
|
10
|
+
project_id: project_id,
|
11
|
+
job_id: job_id
|
12
|
+
)
|
13
|
+
end
|
14
|
+
|
15
|
+
def reload
|
16
|
+
@jobs.get(project_id: project_id, job_id: job_id)
|
17
|
+
end
|
18
|
+
|
19
|
+
def project_id
|
20
|
+
job_reference["projectId"]
|
21
|
+
end
|
22
|
+
|
23
|
+
def job_id
|
24
|
+
job_reference["jobId"]
|
25
|
+
end
|
26
|
+
|
27
|
+
def query
|
28
|
+
(configuration["query"]||{})["query"]
|
29
|
+
end
|
30
|
+
|
31
|
+
def state
|
32
|
+
status["state"]
|
33
|
+
end
|
34
|
+
|
35
|
+
def errors
|
36
|
+
status["errors"]
|
37
|
+
end
|
38
|
+
|
39
|
+
private
|
40
|
+
|
41
|
+
def configuration
|
42
|
+
@resource["configuration"]
|
43
|
+
end
|
44
|
+
|
45
|
+
def status
|
46
|
+
@resource["status"]
|
47
|
+
end
|
48
|
+
|
49
|
+
def job_reference
|
50
|
+
@resource["jobReference"]
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
@@ -0,0 +1,61 @@
|
|
1
|
+
require 'json'
|
2
|
+
|
3
|
+
require_relative 'initializer'
|
4
|
+
require_relative 'request_executor'
|
5
|
+
require_relative 'job'
|
6
|
+
|
7
|
+
module Yancya
|
8
|
+
class BigQuery::Jobs
|
9
|
+
include Initializer
|
10
|
+
include RequestExecutor
|
11
|
+
|
12
|
+
def cancel(project_id:, job_id:)
|
13
|
+
execute(
|
14
|
+
api_method: @bq.api.jobs.cancel,
|
15
|
+
parameters: { projectId: project_id, jobId: job_id }
|
16
|
+
)
|
17
|
+
end
|
18
|
+
|
19
|
+
def get(project_id:, job_id:)
|
20
|
+
resource = execute(
|
21
|
+
api_method: @bq.api.jobs.get,
|
22
|
+
parameters: { projectId: project_id, jobId: job_id }
|
23
|
+
)
|
24
|
+
|
25
|
+
BigQuery::Job.new(resource: resource, bq: @bq)
|
26
|
+
end
|
27
|
+
|
28
|
+
def get_query_results(project_id:, job_id:)
|
29
|
+
execute(
|
30
|
+
api_method: @bq.api.jobs.get_query_results,
|
31
|
+
parameters: { projectId: project_id, jobId: job_id }
|
32
|
+
)
|
33
|
+
end
|
34
|
+
|
35
|
+
def insert(project_id:)
|
36
|
+
# TODO: https://developers.google.com/bigquery/docs/reference/v2/jobs/insert
|
37
|
+
raise "This method is not yet working"
|
38
|
+
end
|
39
|
+
|
40
|
+
def list(project_id:)
|
41
|
+
resources = execute(
|
42
|
+
api_method: @bq.api.jobs.list,
|
43
|
+
parameters: { projectId: project_id, projection: "full" }
|
44
|
+
)
|
45
|
+
|
46
|
+
resources["jobs"].map{|job|
|
47
|
+
BigQuery::Job.new(resource: job, bq: @bq)
|
48
|
+
}
|
49
|
+
end
|
50
|
+
|
51
|
+
def query(project_id:, sql:)
|
52
|
+
resource = execute(
|
53
|
+
api_method: @bq.api.jobs.query,
|
54
|
+
body_object: { query: sql },
|
55
|
+
parameters: { projectId: project_id }
|
56
|
+
)
|
57
|
+
|
58
|
+
BigQuery::Job.new(resource: resource, bq: @bq)
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
@@ -0,0 +1,33 @@
|
|
1
|
+
require_relative 'jobs'
|
2
|
+
require_relative 'datasets'
|
3
|
+
require_relative 'request_executor'
|
4
|
+
|
5
|
+
module Yancya
|
6
|
+
class BigQuery::Project
|
7
|
+
include RequestExecutor
|
8
|
+
|
9
|
+
def initialize(resource:, bq:)
|
10
|
+
@resource = resource
|
11
|
+
@jobs = BigQuery::Jobs.new(bq: bq)
|
12
|
+
@datasets = BigQuery::Datasets.new(bq: bq)
|
13
|
+
@bq = bq
|
14
|
+
end
|
15
|
+
|
16
|
+
def query(sql)
|
17
|
+
@jobs.query(project_id: project_id, sql: sql)
|
18
|
+
end
|
19
|
+
|
20
|
+
def jobs
|
21
|
+
@jobs.list(project_id: project_id)
|
22
|
+
end
|
23
|
+
|
24
|
+
def datasets
|
25
|
+
@datasets.list(project_id: project_id)
|
26
|
+
end
|
27
|
+
|
28
|
+
def project_id
|
29
|
+
@resource["projectReference"]["projectId"]
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require_relative 'request_executor'
|
2
|
+
require_relative 'initializer'
|
3
|
+
|
4
|
+
require_relative 'project'
|
5
|
+
|
6
|
+
module Yancya
|
7
|
+
class BigQuery::Projects
|
8
|
+
include Initializer
|
9
|
+
include RequestExecutor
|
10
|
+
|
11
|
+
def list
|
12
|
+
resources = execute(
|
13
|
+
api_method: @bq.api.projects.list
|
14
|
+
)
|
15
|
+
|
16
|
+
resources["projects"].map do |resource|
|
17
|
+
BigQuery::Project.new(resource: resource, bq: @bq)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
module Yancya
|
2
|
+
module RequestExecutor
|
3
|
+
private
|
4
|
+
|
5
|
+
def response_to_json(obj)
|
6
|
+
return {} if obj.response.body.empty?
|
7
|
+
JSON.parse(obj.response.body).tap do |resource|
|
8
|
+
raise resource["error"].to_s if resource["error"]
|
9
|
+
break resource
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
def execute(api_method:, body_object: nil, parameters: nil)
|
14
|
+
response_to_json(
|
15
|
+
@bq.client.execute(
|
16
|
+
api_method: api_method,
|
17
|
+
body_object: body_object,
|
18
|
+
parameters: parameters
|
19
|
+
)
|
20
|
+
)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,68 @@
|
|
1
|
+
module Yancya
|
2
|
+
class BigQuery::Table
|
3
|
+
def initialize(resource:, tables:)
|
4
|
+
@resource = resource
|
5
|
+
@tables = tables
|
6
|
+
end
|
7
|
+
|
8
|
+
def project_id
|
9
|
+
table_reference["projectId"]
|
10
|
+
end
|
11
|
+
|
12
|
+
def dataset_id
|
13
|
+
table_reference["datasetId"]
|
14
|
+
end
|
15
|
+
|
16
|
+
def table_id
|
17
|
+
table_reference["tableId"]
|
18
|
+
end
|
19
|
+
|
20
|
+
def description
|
21
|
+
@resource["description"]
|
22
|
+
end
|
23
|
+
|
24
|
+
def schema
|
25
|
+
@resource["schema"]
|
26
|
+
end
|
27
|
+
|
28
|
+
def reload
|
29
|
+
@tables.get(
|
30
|
+
project_id: project_id,
|
31
|
+
dataset_id: dataset_id,
|
32
|
+
table_id: table_id
|
33
|
+
)
|
34
|
+
end
|
35
|
+
|
36
|
+
def delete
|
37
|
+
@tables.delete(
|
38
|
+
project_id: project_id,
|
39
|
+
dataset_id: dataset_id,
|
40
|
+
table_id: table_id
|
41
|
+
)
|
42
|
+
end
|
43
|
+
|
44
|
+
def patch(table_reference:)
|
45
|
+
@tables.patch(
|
46
|
+
project_id: project_id,
|
47
|
+
dataset_id: dataset_id,
|
48
|
+
table_id: table_id,
|
49
|
+
table: table_reference
|
50
|
+
)
|
51
|
+
end
|
52
|
+
|
53
|
+
def update(table_reference:)
|
54
|
+
@tables.update(
|
55
|
+
project_id: project_id,
|
56
|
+
dataset_id: dataset_id,
|
57
|
+
table_id: table_id,
|
58
|
+
table: table_reference
|
59
|
+
)
|
60
|
+
end
|
61
|
+
|
62
|
+
private
|
63
|
+
def table_reference
|
64
|
+
@resource["tableReference"]
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
@@ -0,0 +1,37 @@
|
|
1
|
+
require_relative 'request_executor'
|
2
|
+
|
3
|
+
module Yancya
|
4
|
+
class BigQuery::Tabledata
|
5
|
+
include RequestExecutor
|
6
|
+
|
7
|
+
def initialize(project_id:, dataset_id:, table_id:, bq:)
|
8
|
+
@project_id = project_id
|
9
|
+
@dataset_id = dataset_id
|
10
|
+
@table_id = table_id
|
11
|
+
@bq = bq
|
12
|
+
end
|
13
|
+
|
14
|
+
def insert_all(rows)
|
15
|
+
execute(
|
16
|
+
api_method: @bq.api.tabledata.insert_all,
|
17
|
+
body_object: {rows: rows},
|
18
|
+
parameters: {
|
19
|
+
datasetId: @dataset_id,
|
20
|
+
projectId: @project_id,
|
21
|
+
tableId: @table_id
|
22
|
+
}
|
23
|
+
)
|
24
|
+
end
|
25
|
+
|
26
|
+
def list
|
27
|
+
execute(
|
28
|
+
api_method: @bq.api.tabledata.list,
|
29
|
+
parameters: {
|
30
|
+
datasetId: @dataset_id,
|
31
|
+
projectId: @project_id,
|
32
|
+
tableId: @table_id
|
33
|
+
}
|
34
|
+
)
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,90 @@
|
|
1
|
+
require_relative 'initializer'
|
2
|
+
require_relative 'request_executor'
|
3
|
+
|
4
|
+
require_relative 'table'
|
5
|
+
|
6
|
+
module Yancya
|
7
|
+
class BigQuery::Tables
|
8
|
+
include Initializer
|
9
|
+
include RequestExecutor
|
10
|
+
|
11
|
+
def delete(project_id:, dataset_id:, table_id:)
|
12
|
+
execute(
|
13
|
+
api_method: @bq.api.tables.delete,
|
14
|
+
parameters: {
|
15
|
+
datasetId: dataset_id,
|
16
|
+
projectId: project_id,
|
17
|
+
tableId: table_id,
|
18
|
+
}
|
19
|
+
)
|
20
|
+
end
|
21
|
+
|
22
|
+
def get(project_id:, dataset_id:, table_id:)
|
23
|
+
resource = execute(
|
24
|
+
api_method: @bq.api.tables.get,
|
25
|
+
parameters: {
|
26
|
+
datasetId: dataset_id,
|
27
|
+
projectId: project_id,
|
28
|
+
tableId: table_id,
|
29
|
+
}
|
30
|
+
)
|
31
|
+
|
32
|
+
BigQuery::Table.new(resource: resource, tables: self)
|
33
|
+
end
|
34
|
+
|
35
|
+
def insert(project_id:, dataset_id:, table:)
|
36
|
+
resource = execute(
|
37
|
+
api_method: @bq.api.tables.insert,
|
38
|
+
parameters: {
|
39
|
+
datasetId: dataset_id,
|
40
|
+
projectId: project_id,
|
41
|
+
},
|
42
|
+
body_object: table
|
43
|
+
)
|
44
|
+
|
45
|
+
BigQuery::Table.new(resource: resource, tables: self)
|
46
|
+
end
|
47
|
+
|
48
|
+
def list(project_id:, dataset_id:)
|
49
|
+
resources = execute(
|
50
|
+
api_method: @bq.api.tables.list,
|
51
|
+
parameters: {
|
52
|
+
datasetId: dataset_id,
|
53
|
+
projectId: project_id,
|
54
|
+
}
|
55
|
+
)
|
56
|
+
|
57
|
+
(resources["tables"]||[]).map do |resource|
|
58
|
+
BigQuery::Table.new(resource: resource, tables: self)
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
def patch(project_id:, dataset_id:, table_id:, table:)
|
63
|
+
resource = execute(
|
64
|
+
api_method: @bq.api.tables.patch,
|
65
|
+
parameters: {
|
66
|
+
datasetId: dataset_id,
|
67
|
+
projectId: project_id,
|
68
|
+
tableId: table_id,
|
69
|
+
},
|
70
|
+
body_object: table
|
71
|
+
)
|
72
|
+
|
73
|
+
BigQuery::Table.new(resource: resource, tables: self)
|
74
|
+
end
|
75
|
+
|
76
|
+
def update(project_id:, dataset_id:, table_id:, table:)
|
77
|
+
resource = execute(
|
78
|
+
api_method: @bq.api.tables.update,
|
79
|
+
parameters: {
|
80
|
+
datasetId: dataset_id,
|
81
|
+
projectId: project_id,
|
82
|
+
tableId: table_id,
|
83
|
+
},
|
84
|
+
body_object: table
|
85
|
+
)
|
86
|
+
|
87
|
+
BigQuery::Table.new(resource: resource, tables: self)
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|
@@ -0,0 +1,68 @@
|
|
1
|
+
require_relative "big_query/version"
|
2
|
+
require_relative "big_query/datasets"
|
3
|
+
require_relative "big_query/jobs"
|
4
|
+
require_relative "big_query/projects"
|
5
|
+
require_relative "big_query/tabledata"
|
6
|
+
require_relative "big_query/tables"
|
7
|
+
|
8
|
+
require 'google/api_client'
|
9
|
+
|
10
|
+
module Yancya
|
11
|
+
class BigQuery
|
12
|
+
attr_reader :client
|
13
|
+
|
14
|
+
BQ = Struct.new(:client) do
|
15
|
+
def api
|
16
|
+
client.discovered_api("bigquery", "v2")
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def initialize(key_path:,
|
21
|
+
issuer:,
|
22
|
+
application_name: "github.com/yancya/big_query",
|
23
|
+
application_version: BigQuery::VERSION)
|
24
|
+
|
25
|
+
app_info = {
|
26
|
+
application_name: application_name,
|
27
|
+
application_version: application_version
|
28
|
+
}
|
29
|
+
|
30
|
+
client = Google::APIClient.new(app_info)
|
31
|
+
|
32
|
+
asserter = Google::APIClient::JWTAsserter.new(
|
33
|
+
issuer,
|
34
|
+
"https://www.googleapis.com/auth/bigquery",
|
35
|
+
Google::APIClient::PKCS12.load_key(File.open(key_path), "notasecret")
|
36
|
+
)
|
37
|
+
|
38
|
+
client.authorization = asserter.authorize
|
39
|
+
|
40
|
+
@bq = BQ.new(client)
|
41
|
+
end
|
42
|
+
|
43
|
+
def datasets
|
44
|
+
Datasets.new(bq: @bq)
|
45
|
+
end
|
46
|
+
|
47
|
+
def jobs
|
48
|
+
Jobs.new(bq: @bq)
|
49
|
+
end
|
50
|
+
|
51
|
+
def projects
|
52
|
+
Projects.new(bq: @bq)
|
53
|
+
end
|
54
|
+
|
55
|
+
def tabledata(project_id:, dataset_id:, table_id:)
|
56
|
+
Tabledata.new(
|
57
|
+
project_id: project_id,
|
58
|
+
dataset_id: dataset_id,
|
59
|
+
table_id: table_id,
|
60
|
+
bq: @bq
|
61
|
+
)
|
62
|
+
end
|
63
|
+
|
64
|
+
def tables
|
65
|
+
Tables.new(bq: @bq)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
end
|
@@ -0,0 +1,176 @@
|
|
1
|
+
require 'test-unit'
|
2
|
+
require 'pp'
|
3
|
+
require_relative '../lib/yancya/big_query'
|
4
|
+
|
5
|
+
class TestBigQuery < Test::Unit::TestCase
|
6
|
+
TEST_DATASET_ID = "test_dataset_for_yancya_big_query_gem"
|
7
|
+
TEST_DATASET_ID_MODIFIED = "test_dataset_for_yancya_big_query_gem_"
|
8
|
+
TEST_TABLE_ID = "test_table"
|
9
|
+
TEST_TABLE_INFO = {
|
10
|
+
schema: {
|
11
|
+
fields: [
|
12
|
+
{name: "column_s", type: "STRING"},
|
13
|
+
{name: "column_i", type: "INTEGER"},
|
14
|
+
{name: "column_f", type: "FLOAT"},
|
15
|
+
{name: "column_b", type: "BOOLEAN"}
|
16
|
+
]
|
17
|
+
},
|
18
|
+
tableReference: {
|
19
|
+
tableId: TEST_TABLE_ID
|
20
|
+
}
|
21
|
+
}
|
22
|
+
|
23
|
+
setup do
|
24
|
+
@bq = Yancya::BigQuery.new(
|
25
|
+
key_path: ENV["GCP_KEY_PATH"],
|
26
|
+
issuer: ENV["GCP_ISSUER"]
|
27
|
+
)
|
28
|
+
|
29
|
+
@project_id = ENV["BQ_PROJECT_ID"]
|
30
|
+
|
31
|
+
if @bq.datasets.list(project_id: @project_id).map{ |ds| ds.dataset_id }.include? TEST_DATASET_ID
|
32
|
+
@bq.datasets.delete(project_id: @project_id, dataset_id: TEST_DATASET_ID)
|
33
|
+
end
|
34
|
+
|
35
|
+
dataset = {
|
36
|
+
datasetReference: {
|
37
|
+
datasetId: TEST_DATASET_ID
|
38
|
+
}
|
39
|
+
}
|
40
|
+
|
41
|
+
@bq.datasets.insert(project_id: @project_id, dataset: dataset)
|
42
|
+
end
|
43
|
+
|
44
|
+
teardown do
|
45
|
+
@bq.datasets.delete(project_id: @project_id, dataset_id: TEST_DATASET_ID)
|
46
|
+
end
|
47
|
+
|
48
|
+
test "get dataset" do
|
49
|
+
dataset = @bq.
|
50
|
+
datasets.
|
51
|
+
get(
|
52
|
+
project_id: @project_id,
|
53
|
+
dataset_id: TEST_DATASET_ID
|
54
|
+
)["datasetReference"]
|
55
|
+
|
56
|
+
assert { TEST_DATASET_ID == dataset["datasetId"] }
|
57
|
+
end
|
58
|
+
|
59
|
+
test "jobs list" do
|
60
|
+
job_list = @bq.jobs.list(project_id: @project_id)
|
61
|
+
assert { job_list.is_a? Array }
|
62
|
+
end
|
63
|
+
|
64
|
+
test "get job" do
|
65
|
+
job_id = @bq.jobs.list(project_id: @project_id).last.job_id
|
66
|
+
assert do
|
67
|
+
job_id == @bq.jobs.get(project_id: @project_id, job_id: job_id).job_id
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
test "project list" do
|
72
|
+
assert do
|
73
|
+
@bq.projects.list.map{ |project| project.project_id }.include? @project_id
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
test "select without table" do
|
78
|
+
result = execute_query("select 1 as a, 2 as b, 3 as c")
|
79
|
+
|
80
|
+
assert do
|
81
|
+
"1,2,3" == result["rows"].map{|row| row["f"].map{|col| col["v"]}.join(",")}.first
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
test "create table" do
|
86
|
+
result = create_table
|
87
|
+
|
88
|
+
assert { TEST_TABLE_ID == result.table_id }
|
89
|
+
end
|
90
|
+
|
91
|
+
test "insert_all data" do
|
92
|
+
create_table
|
93
|
+
|
94
|
+
table_data = @bq.tabledata(
|
95
|
+
project_id: @project_id,
|
96
|
+
dataset_id: TEST_DATASET_ID,
|
97
|
+
table_id: TEST_TABLE_ID
|
98
|
+
)
|
99
|
+
|
100
|
+
rows = [{ json: { column_s: "hoge", column_i: 1, column_f: 0.1, column_b: false } }]
|
101
|
+
|
102
|
+
assert { table_data.insert_all(rows)["insertErrors"].nil? }
|
103
|
+
assert { table_data.list["totalRows"] }
|
104
|
+
end
|
105
|
+
|
106
|
+
test "table list" do
|
107
|
+
create_table
|
108
|
+
|
109
|
+
assert { 1 == @bq.tables.list(project_id: @project_id, dataset_id: TEST_DATASET_ID).size }
|
110
|
+
end
|
111
|
+
|
112
|
+
test "get table"do
|
113
|
+
create_table
|
114
|
+
|
115
|
+
table = @bq.tables.get(project_id: @project_id, dataset_id: TEST_DATASET_ID, table_id: TEST_TABLE_ID)
|
116
|
+
|
117
|
+
assert { TEST_TABLE_ID == table.table_id }
|
118
|
+
end
|
119
|
+
|
120
|
+
test "delete table" do
|
121
|
+
table = create_table
|
122
|
+
@bq.tables.delete(project_id: @project_id, dataset_id: TEST_DATASET_ID, table_id: table.table_id)
|
123
|
+
|
124
|
+
assert { @bq.tables.list(project_id: @project_id, dataset_id: TEST_DATASET_ID).empty? }
|
125
|
+
end
|
126
|
+
|
127
|
+
test "patch table" do
|
128
|
+
create_table
|
129
|
+
|
130
|
+
table = @bq.tables.patch(
|
131
|
+
project_id: @project_id,
|
132
|
+
dataset_id: TEST_DATASET_ID,
|
133
|
+
table_id: TEST_TABLE_ID,
|
134
|
+
table: {
|
135
|
+
description: "hello world"
|
136
|
+
}
|
137
|
+
)
|
138
|
+
|
139
|
+
assert { "hello world" == table.description }
|
140
|
+
end
|
141
|
+
|
142
|
+
test "update table" do
|
143
|
+
schema = create_table.schema
|
144
|
+
|
145
|
+
table = @bq.tables.update(
|
146
|
+
project_id: @project_id,
|
147
|
+
dataset_id: TEST_DATASET_ID,
|
148
|
+
table_id: TEST_TABLE_ID,
|
149
|
+
table: {
|
150
|
+
schema: schema.tap { |hash| hash["fields"] << { name: "hoge", type: "STRING" }; break hash }
|
151
|
+
}
|
152
|
+
)
|
153
|
+
|
154
|
+
assert { table.schema["fields"].map { |field| field["name"] }.include? "hoge" }
|
155
|
+
end
|
156
|
+
|
157
|
+
private
|
158
|
+
|
159
|
+
def create_table
|
160
|
+
@bq.tables.insert(
|
161
|
+
project_id: @project_id,
|
162
|
+
dataset_id: TEST_DATASET_ID,
|
163
|
+
table: TEST_TABLE_INFO
|
164
|
+
)
|
165
|
+
end
|
166
|
+
|
167
|
+
def execute_query(sql)
|
168
|
+
job = @bq.jobs.query(project_id: @project_id, sql: sql)
|
169
|
+
|
170
|
+
begin
|
171
|
+
result = job.query_results
|
172
|
+
end until result["jobComplete"]
|
173
|
+
|
174
|
+
result
|
175
|
+
end
|
176
|
+
end
|
metadata
ADDED
@@ -0,0 +1,125 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: yancya-big_query
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- yancya
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-06-11 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: google-api-client
|
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: '1.6'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.6'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: test-unit
|
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
|
+
description: Google BigQuery API client library. This is simple wrapper.
|
70
|
+
email:
|
71
|
+
- yancya@upec.jp
|
72
|
+
executables:
|
73
|
+
- big_query
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- ".gitignore"
|
78
|
+
- CHANGELOG.md
|
79
|
+
- Gemfile
|
80
|
+
- Gemfile.lock
|
81
|
+
- LICENSE
|
82
|
+
- README.md
|
83
|
+
- Rakefile
|
84
|
+
- big_query.gemspec
|
85
|
+
- bin/big_query
|
86
|
+
- lib/yancya/big_query.rb
|
87
|
+
- lib/yancya/big_query/dataset.rb
|
88
|
+
- lib/yancya/big_query/datasets.rb
|
89
|
+
- lib/yancya/big_query/initializer.rb
|
90
|
+
- lib/yancya/big_query/job.rb
|
91
|
+
- lib/yancya/big_query/jobs.rb
|
92
|
+
- lib/yancya/big_query/project.rb
|
93
|
+
- lib/yancya/big_query/projects.rb
|
94
|
+
- lib/yancya/big_query/request_executor.rb
|
95
|
+
- lib/yancya/big_query/table.rb
|
96
|
+
- lib/yancya/big_query/tabledata.rb
|
97
|
+
- lib/yancya/big_query/tables.rb
|
98
|
+
- lib/yancya/big_query/version.rb
|
99
|
+
- test/test_big_query.rb
|
100
|
+
homepage: https://github.com/yancya/big_query
|
101
|
+
licenses:
|
102
|
+
- MIT
|
103
|
+
metadata: {}
|
104
|
+
post_install_message:
|
105
|
+
rdoc_options: []
|
106
|
+
require_paths:
|
107
|
+
- lib
|
108
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
109
|
+
requirements:
|
110
|
+
- - ">="
|
111
|
+
- !ruby/object:Gem::Version
|
112
|
+
version: '0'
|
113
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ">="
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
requirements: []
|
119
|
+
rubyforge_project:
|
120
|
+
rubygems_version: 2.4.5
|
121
|
+
signing_key:
|
122
|
+
specification_version: 4
|
123
|
+
summary: Google BigQuery API client library.
|
124
|
+
test_files:
|
125
|
+
- test/test_big_query.rb
|