avro_utils 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/avro_utils.gemspec +20 -0
- data/lib/avro_utils.rb +29 -0
- data/lib/exceptions/invalid_data_exception.rb +2 -0
- data/lib/utils/avro_utils.rb +54 -0
- metadata +131 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 138c585168f97b5d9786dfcfda80f7b5f25caa61
|
4
|
+
data.tar.gz: 1011ffd72b61545233da0a573608a2692d8d194c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: ccd802a2f71f5a48a723dd457ed210662e6dae1a80a44d1500593cb909e5481981f2b40a6da95707f528fbadb24c4e668e80e4d0e753a5e2292da7424db30989
|
7
|
+
data.tar.gz: a5c4af7e7f56a3694fce9f78b0cdbd8780b726ce81f837ad0d6c3b256c6bd6a5d355f8c36c48786fab532ad0819b82850a84cf17a39ec1eadf3c5410571c59a3
|
data/avro_utils.gemspec
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Gem::Specification.new do |s|
|
2
|
+
s.name = 'avro_utils'
|
3
|
+
s.version = '0.1.0'
|
4
|
+
s.summary = "A gem to convert different data format to avro"
|
5
|
+
s.description = "A gem to convert different data format to avro"
|
6
|
+
s.authors = ['Linh Chau']
|
7
|
+
s.email = 'chauhonglinh@gmail.com'
|
8
|
+
s.files = [
|
9
|
+
'./avro_utils.gemspec', 'lib/avro_utils.rb',
|
10
|
+
'lib/utils/avro_utils.rb', 'lib/exceptions/invalid_data_exception.rb'
|
11
|
+
]
|
12
|
+
s.homepage = 'https://github.com/linhchauatl/avro_utils'
|
13
|
+
s.license = 'MIT'
|
14
|
+
s.add_runtime_dependency 'json'
|
15
|
+
s.add_runtime_dependency 'json-schema'
|
16
|
+
s.add_runtime_dependency 'avro'
|
17
|
+
s.add_runtime_dependency 'logging'
|
18
|
+
s.add_runtime_dependency 'activesupport'
|
19
|
+
s.add_development_dependency 'rspec', '~> 3.3'
|
20
|
+
end
|
data/lib/avro_utils.rb
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'active_support/all'
|
2
|
+
require 'json'
|
3
|
+
require 'json-schema'
|
4
|
+
require 'avro'
|
5
|
+
|
6
|
+
# avro types
|
7
|
+
# string: unicode character sequence
|
8
|
+
# bytes: sequence of 8-bit unsigned bytes
|
9
|
+
# int: 32-bit signed integer
|
10
|
+
# long: 64-bit signed integer
|
11
|
+
# float: single precision (32-bit) IEEE 754 floating-point number
|
12
|
+
# double: double precision (64-bit) IEEE 754 floating-point number
|
13
|
+
# boolean: a binary value
|
14
|
+
# null: no value
|
15
|
+
|
16
|
+
RUBY_AVRO_TYPE_MAPPING = {
|
17
|
+
String: :string,
|
18
|
+
Symbol: :string,
|
19
|
+
Fixnum: :int,
|
20
|
+
Bignum: :long,
|
21
|
+
Float: :double,
|
22
|
+
TrueClass: :boolean,
|
23
|
+
FalseClass: :boolean,
|
24
|
+
NilClass: :null
|
25
|
+
|
26
|
+
}
|
27
|
+
|
28
|
+
Dir.glob('./lib/exceptions/*.rb').sort.each { |file| puts file; require file }
|
29
|
+
Dir.glob('./lib/utils/*.rb').sort.each { |file| puts file; require file }
|
@@ -0,0 +1,54 @@
|
|
1
|
+
class AvroUtils
|
2
|
+
|
3
|
+
class << self
|
4
|
+
def avro_schema_hash(hash_data, record_type_name)
|
5
|
+
result = {
|
6
|
+
type: 'record',
|
7
|
+
name: record_type_name,
|
8
|
+
fields: []
|
9
|
+
}
|
10
|
+
|
11
|
+
hash_data.each do |key, value|
|
12
|
+
if value.is_a? Hash
|
13
|
+
result[:fields] << { name: key, type: avro_schema_hash(value, key.to_s.singularize.camelize) }
|
14
|
+
elsif value.is_a? Array
|
15
|
+
result[:fields] << { name: key, type: { type: 'array', items: RUBY_AVRO_TYPE_MAPPING[value[0].class.name.to_sym] } }
|
16
|
+
else
|
17
|
+
result[:fields] << { name: key, type: RUBY_AVRO_TYPE_MAPPING[value.class.name.to_sym] }
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
result
|
22
|
+
rescue StandardError => error
|
23
|
+
puts("Error: #{error.message}\n#{error.backtrace.join("\n")}")
|
24
|
+
raise InvalidDataException.new(error.message)
|
25
|
+
end
|
26
|
+
|
27
|
+
def avro_schema(hash_data, record_type_name)
|
28
|
+
Avro::Schema.parse(avro_schema_hash(hash_data, record_type_name).to_json)
|
29
|
+
end
|
30
|
+
|
31
|
+
def json_to_avro(json_data, record_type_name)
|
32
|
+
buffer = StringIO.new
|
33
|
+
|
34
|
+
# Avro assumes that all the hashes use strings for keys. It does not accept Indifferent Hash.
|
35
|
+
# So the conversion bellow ensures that the hash data uses strings for keys.
|
36
|
+
json_data = json_data.to_json if json_data.is_a? Hash
|
37
|
+
hash_data = JSON.parse(json_data)
|
38
|
+
|
39
|
+
schema = avro_schema(hash_data, record_type_name)
|
40
|
+
|
41
|
+
datum_writer = Avro::IO::DatumWriter.new(schema)
|
42
|
+
file_writer = Avro::DataFile::Writer.new(buffer, datum_writer, schema)
|
43
|
+
file_writer << hash_data
|
44
|
+
file_writer.flush
|
45
|
+
|
46
|
+
buffer.rewind
|
47
|
+
buffer
|
48
|
+
rescue StandardError => error
|
49
|
+
puts("Error: #{error.message}\n#{error.backtrace.join("\n")}")
|
50
|
+
raise InvalidDataException.new(error.message)
|
51
|
+
end
|
52
|
+
|
53
|
+
end
|
54
|
+
end
|
metadata
ADDED
@@ -0,0 +1,131 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: avro_utils
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Linh Chau
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-09-24 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: json
|
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: json-schema
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: avro
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
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: logging
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
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: '0'
|
76
|
+
type: :runtime
|
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: rspec
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '3.3'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '3.3'
|
97
|
+
description: A gem to convert different data format to avro
|
98
|
+
email: chauhonglinh@gmail.com
|
99
|
+
executables: []
|
100
|
+
extensions: []
|
101
|
+
extra_rdoc_files: []
|
102
|
+
files:
|
103
|
+
- "./avro_utils.gemspec"
|
104
|
+
- lib/avro_utils.rb
|
105
|
+
- lib/exceptions/invalid_data_exception.rb
|
106
|
+
- lib/utils/avro_utils.rb
|
107
|
+
homepage: https://github.com/linhchauatl/avro_utils
|
108
|
+
licenses:
|
109
|
+
- MIT
|
110
|
+
metadata: {}
|
111
|
+
post_install_message:
|
112
|
+
rdoc_options: []
|
113
|
+
require_paths:
|
114
|
+
- lib
|
115
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
116
|
+
requirements:
|
117
|
+
- - ">="
|
118
|
+
- !ruby/object:Gem::Version
|
119
|
+
version: '0'
|
120
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
125
|
+
requirements: []
|
126
|
+
rubyforge_project:
|
127
|
+
rubygems_version: 2.4.8
|
128
|
+
signing_key:
|
129
|
+
specification_version: 4
|
130
|
+
summary: A gem to convert different data format to avro
|
131
|
+
test_files: []
|