avro_turf 1.7.0 → 1.9.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/ruby.yml +4 -4
- data/CHANGELOG.md +11 -2
- data/avro_turf.gemspec +1 -1
- data/lib/avro_turf/cached_confluent_schema_registry.rb +2 -2
- data/lib/avro_turf/confluent_schema_registry.rb +2 -2
- data/lib/avro_turf/core_ext/date.rb +1 -1
- data/lib/avro_turf/disk_cache.rb +25 -15
- data/lib/avro_turf/in_memory_cache.rb +2 -2
- data/lib/avro_turf/messaging.rb +16 -4
- data/lib/avro_turf/version.rb +1 -1
- data/lib/avro_turf.rb +2 -3
- data/spec/avro_turf_spec.rb +70 -2
- data/spec/core_ext/date_spec.rb +2 -2
- data/spec/spec_helper.rb +10 -0
- data/spec/support/confluent_schema_registry_context.rb +12 -1
- metadata +10 -10
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3cb36f9b1395a1a6210d1178ca0823636f30ad194caf57663e8fb5cc13273d68
|
4
|
+
data.tar.gz: 2fb489fe330b39b88ed585d6b622936e573b525c1f4c5c4fe50704b16b11fd39
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: be796c4b42daf30a79dd699d23842e61c61e8f8c70b1645f269ec25e4a4f4fb1e87148b0ffd69a68b24382e9abc01048cb3ba082bd3a3dd2162be714ecdcd57b
|
7
|
+
data.tar.gz: 332486d45cd611da3906247f4fb55386c7e1617043070dd44fff06b05c50c44237af6dad62f1fd087ca9c67580aadd53fc342f76509b69b67375532b60637bf9
|
data/.github/workflows/ruby.yml
CHANGED
@@ -7,17 +7,17 @@ jobs:
|
|
7
7
|
|
8
8
|
runs-on: ubuntu-latest
|
9
9
|
strategy:
|
10
|
+
fail-fast: false
|
10
11
|
matrix:
|
11
|
-
ruby: [2.
|
12
|
+
ruby: [2.6, 2.7, "3.0", 3.1, 3.2]
|
12
13
|
|
13
14
|
steps:
|
14
|
-
- uses: actions/checkout@
|
15
|
+
- uses: actions/checkout@v3
|
15
16
|
- name: Set up Ruby ${{ matrix.ruby }}
|
16
17
|
uses: ruby/setup-ruby@v1
|
17
18
|
with:
|
18
19
|
ruby-version: ${{ matrix.ruby }}
|
20
|
+
bundler-cache: true
|
19
21
|
- name: Build and test with RSpec
|
20
22
|
run: |
|
21
|
-
gem install bundler
|
22
|
-
bundle install --jobs 4 --retry 3
|
23
23
|
bundle exec rspec
|
data/CHANGELOG.md
CHANGED
@@ -2,9 +2,18 @@
|
|
2
2
|
|
3
3
|
## Unreleased
|
4
4
|
|
5
|
+
## v1.9.0
|
6
|
+
|
7
|
+
- Send Accept and User-Agent headers on every request (#184)
|
8
|
+
|
9
|
+
## v1.8.0
|
10
|
+
|
11
|
+
- Add support for `Date` via appropriate logicalType defintion. This is a backwards incompatible change (#177)
|
12
|
+
- Fixed schema file cache truncation on multiple running instances and parallel access to the cache files.
|
13
|
+
|
5
14
|
## v1.7.0
|
6
15
|
|
7
|
-
- Added extra params for the validation message
|
16
|
+
- Added extra params for the validation message schema before encode (#169)
|
8
17
|
- Fix infinite retry when loading schema with nested primary type in separate file (#165)
|
9
18
|
|
10
19
|
## v1.6.0
|
@@ -60,7 +69,7 @@
|
|
60
69
|
## v0.9.0
|
61
70
|
|
62
71
|
- Compatibility with Avro v1.9.0 (#94)
|
63
|
-
- Disable the auto
|
72
|
+
- Disable the auto registration of schema (#95)
|
64
73
|
- abstracted caching from CachedConfluentSchemaRegistry (#74)
|
65
74
|
- Load avro-patches if installed to silence deprecation errors (#85)
|
66
75
|
- Make schema store to be thread safe (#92)
|
data/avro_turf.gemspec
CHANGED
@@ -25,7 +25,7 @@ Gem::Specification.new do |spec|
|
|
25
25
|
spec.add_development_dependency "bundler", "~> 2.0"
|
26
26
|
spec.add_development_dependency "rake", "~> 13.0"
|
27
27
|
spec.add_development_dependency "rspec", "~> 3.2"
|
28
|
-
spec.add_development_dependency "fakefs", "
|
28
|
+
spec.add_development_dependency "fakefs", "< 3"
|
29
29
|
spec.add_development_dependency "webmock"
|
30
30
|
spec.add_development_dependency "sinatra"
|
31
31
|
spec.add_development_dependency "json_spec"
|
@@ -13,7 +13,7 @@ class AvroTurf::CachedConfluentSchemaRegistry
|
|
13
13
|
# cache - Optional user provided Cache object that responds to all methods in the AvroTurf::InMemoryCache interface.
|
14
14
|
def initialize(upstream, cache: nil)
|
15
15
|
@upstream = upstream
|
16
|
-
@cache = cache || AvroTurf::InMemoryCache.new
|
16
|
+
@cache = cache || AvroTurf::InMemoryCache.new
|
17
17
|
end
|
18
18
|
|
19
19
|
# Delegate the following methods to the upstream
|
@@ -34,7 +34,7 @@ class AvroTurf::CachedConfluentSchemaRegistry
|
|
34
34
|
|
35
35
|
def subject_version(subject, version = 'latest')
|
36
36
|
return @upstream.subject_version(subject, version) if version == 'latest'
|
37
|
-
|
37
|
+
|
38
38
|
@cache.lookup_by_version(subject, version) ||
|
39
39
|
@cache.store_by_version(subject, version, @upstream.subject_version(subject, version))
|
40
40
|
end
|
@@ -19,9 +19,9 @@ class AvroTurf::ConfluentSchemaRegistry
|
|
19
19
|
)
|
20
20
|
@path_prefix = path_prefix
|
21
21
|
@logger = logger
|
22
|
-
headers =
|
22
|
+
headers = Excon.defaults[:headers].merge(
|
23
23
|
"Content-Type" => CONTENT_TYPE
|
24
|
-
|
24
|
+
)
|
25
25
|
headers[:proxy] = proxy unless proxy.nil?
|
26
26
|
@connection = Excon.new(
|
27
27
|
url,
|
data/lib/avro_turf/disk_cache.rb
CHANGED
@@ -1,20 +1,18 @@
|
|
1
1
|
# A cache for the CachedConfluentSchemaRegistry.
|
2
2
|
# Extends the InMemoryCache to provide a write-thru to disk for persistent cache.
|
3
|
-
class AvroTurf::DiskCache
|
3
|
+
class AvroTurf::DiskCache
|
4
4
|
|
5
5
|
def initialize(disk_path, logger: Logger.new($stdout))
|
6
|
-
super()
|
7
|
-
|
8
6
|
@logger = logger
|
9
7
|
|
10
8
|
# load the write-thru cache on startup, if it exists
|
11
9
|
@schemas_by_id_path = File.join(disk_path, 'schemas_by_id.json')
|
12
10
|
hash = read_from_disk_cache(@schemas_by_id_path)
|
13
|
-
@schemas_by_id = hash
|
11
|
+
@schemas_by_id = hash || {}
|
14
12
|
|
15
13
|
@ids_by_schema_path = File.join(disk_path, 'ids_by_schema.json')
|
16
14
|
hash = read_from_disk_cache(@ids_by_schema_path)
|
17
|
-
@ids_by_schema = hash
|
15
|
+
@ids_by_schema = hash || {}
|
18
16
|
|
19
17
|
@schemas_by_subject_version_path = File.join(disk_path, 'schemas_by_subject_version.json')
|
20
18
|
@schemas_by_subject_version = {}
|
@@ -24,15 +22,16 @@ class AvroTurf::DiskCache < AvroTurf::InMemoryCache
|
|
24
22
|
# the write-thru cache (json) does not store keys in numeric format
|
25
23
|
# so, convert id to a string for caching purposes
|
26
24
|
def lookup_by_id(id)
|
27
|
-
|
25
|
+
@schemas_by_id[id.to_s]
|
28
26
|
end
|
29
27
|
|
30
28
|
# override to include write-thru cache after storing result from upstream
|
31
29
|
def store_by_id(id, schema)
|
32
30
|
# must return the value from storing the result (i.e. do not return result from file write)
|
33
|
-
|
34
|
-
|
35
|
-
|
31
|
+
@schemas_by_id[id.to_s] = schema
|
32
|
+
write_to_disk_cache(@schemas_by_id_path, @schemas_by_id)
|
33
|
+
|
34
|
+
schema
|
36
35
|
end
|
37
36
|
|
38
37
|
# override to use a json serializable cache key
|
@@ -45,7 +44,8 @@ class AvroTurf::DiskCache < AvroTurf::InMemoryCache
|
|
45
44
|
def store_by_schema(subject, schema, id)
|
46
45
|
key = "#{subject}#{schema}"
|
47
46
|
@ids_by_schema[key] = id
|
48
|
-
|
47
|
+
|
48
|
+
write_to_disk_cache(@ids_by_schema_path, @ids_by_schema)
|
49
49
|
id
|
50
50
|
end
|
51
51
|
|
@@ -78,7 +78,7 @@ class AvroTurf::DiskCache < AvroTurf::InMemoryCache
|
|
78
78
|
hash[key] = schema
|
79
79
|
hash
|
80
80
|
else
|
81
|
-
{key => schema}
|
81
|
+
{ key => schema }
|
82
82
|
end
|
83
83
|
|
84
84
|
write_to_disk_cache(@schemas_by_subject_version_path, hash)
|
@@ -90,17 +90,27 @@ class AvroTurf::DiskCache < AvroTurf::InMemoryCache
|
|
90
90
|
# Parse the file from disk, if it exists and is not zero length
|
91
91
|
private def read_from_disk_cache(path)
|
92
92
|
if File.exist?(path)
|
93
|
-
if File.size(path)!=0
|
94
|
-
|
93
|
+
if File.size(path) != 0
|
94
|
+
json_data = File.open(path, 'r') do |file|
|
95
|
+
file.flock(File::LOCK_SH)
|
96
|
+
file.read
|
97
|
+
end
|
98
|
+
|
99
|
+
return JSON.parse(json_data)
|
95
100
|
else
|
96
101
|
# just log a message if skipping zero length file
|
97
102
|
@logger.warn "skipping JSON.parse of zero length file at #{path}"
|
98
103
|
end
|
99
104
|
end
|
100
|
-
|
105
|
+
|
106
|
+
nil
|
101
107
|
end
|
102
108
|
|
103
109
|
private def write_to_disk_cache(path, hash)
|
104
|
-
|
110
|
+
# don't use "w" because it truncates the file before lock
|
111
|
+
File.open(path, File::RDWR | File::CREAT, 0644) do |file|
|
112
|
+
file.flock(File::LOCK_EX)
|
113
|
+
file.write(JSON.pretty_generate(hash))
|
114
|
+
end
|
105
115
|
end
|
106
116
|
end
|
@@ -17,12 +17,12 @@ class AvroTurf::InMemoryCache
|
|
17
17
|
end
|
18
18
|
|
19
19
|
def lookup_by_schema(subject, schema)
|
20
|
-
key = [subject, schema
|
20
|
+
key = [subject, schema]
|
21
21
|
@ids_by_schema[key]
|
22
22
|
end
|
23
23
|
|
24
24
|
def store_by_schema(subject, schema, id)
|
25
|
-
key = [subject, schema
|
25
|
+
key = [subject, schema]
|
26
26
|
@ids_by_schema[key] = id
|
27
27
|
end
|
28
28
|
|
data/lib/avro_turf/messaging.rb
CHANGED
@@ -21,8 +21,20 @@ class AvroTurf
|
|
21
21
|
# 1: https://github.com/confluentinc/schema-registry
|
22
22
|
class Messaging
|
23
23
|
MAGIC_BYTE = [0].pack("C").freeze
|
24
|
-
|
25
|
-
|
24
|
+
|
25
|
+
class DecodedMessage
|
26
|
+
attr_reader :schema_id
|
27
|
+
attr_reader :writer_schema
|
28
|
+
attr_reader :reader_schema
|
29
|
+
attr_reader :message
|
30
|
+
|
31
|
+
def initialize(schema_id, writer_schema, reader_schema, message)
|
32
|
+
@schema_id = schema_id
|
33
|
+
@writer_schema = writer_schema
|
34
|
+
@reader_schema = reader_schema
|
35
|
+
@message = message
|
36
|
+
end
|
37
|
+
end
|
26
38
|
|
27
39
|
# Instantiate a new Messaging instance with the given configuration.
|
28
40
|
#
|
@@ -34,7 +46,7 @@ class AvroTurf
|
|
34
46
|
# namespace - The String default schema namespace.
|
35
47
|
# registry_path_prefix - The String URL path prefix used to namespace schema registry requests (optional).
|
36
48
|
# logger - The Logger that should be used to log information (optional).
|
37
|
-
#
|
49
|
+
# proxy - Forward the request via proxy (optional).
|
38
50
|
# user - User for basic auth (optional).
|
39
51
|
# password - Password for basic auth (optional).
|
40
52
|
# ssl_ca_file - Name of file containing CA certificate (optional).
|
@@ -130,7 +142,7 @@ class AvroTurf
|
|
130
142
|
writer.write(message, encoder)
|
131
143
|
|
132
144
|
stream.string
|
133
|
-
rescue Excon::
|
145
|
+
rescue Excon::Error::NotFound
|
134
146
|
if schema_id
|
135
147
|
raise SchemaNotFoundError.new("Schema with id: #{schema_id} is not found on registry")
|
136
148
|
else
|
data/lib/avro_turf/version.rb
CHANGED
data/lib/avro_turf.rb
CHANGED
@@ -121,10 +121,9 @@ class AvroTurf
|
|
121
121
|
# namespace - The namespace of the Avro schema (optional).
|
122
122
|
#
|
123
123
|
# Returns true if the data is valid, false otherwise.
|
124
|
-
def valid?(data, schema_name: nil, namespace: @namespace)
|
124
|
+
def valid?(data, schema_name: nil, namespace: @namespace, validate_options: {})
|
125
125
|
schema = schema_name && @schema_store.find(schema_name, namespace)
|
126
|
-
|
127
|
-
Avro::Schema.validate(schema, data.as_avro)
|
126
|
+
Avro::Schema.validate(schema, data.as_avro, **validate_options)
|
128
127
|
end
|
129
128
|
|
130
129
|
# Loads all schema definition files in the `schemas_dir`.
|
data/spec/avro_turf_spec.rb
CHANGED
@@ -16,6 +16,13 @@ describe AvroTurf do
|
|
16
16
|
{
|
17
17
|
"type": "string",
|
18
18
|
"name": "full_name"
|
19
|
+
},
|
20
|
+
{
|
21
|
+
"name": "birth_date",
|
22
|
+
"type": {
|
23
|
+
"type": "int",
|
24
|
+
"logicalType": "date"
|
25
|
+
}
|
19
26
|
}
|
20
27
|
]
|
21
28
|
}
|
@@ -24,7 +31,8 @@ describe AvroTurf do
|
|
24
31
|
|
25
32
|
it "encodes data with Avro" do
|
26
33
|
data = {
|
27
|
-
"full_name" => "John Doe"
|
34
|
+
"full_name" => "John Doe",
|
35
|
+
"birth_date" => Date.new(1934, 1, 2)
|
28
36
|
}
|
29
37
|
|
30
38
|
encoded_data = avro.encode(data, schema_name: "person")
|
@@ -36,7 +44,8 @@ describe AvroTurf do
|
|
36
44
|
compressed_avro = AvroTurf.new(schemas_path: "spec/schemas/", codec: "deflate")
|
37
45
|
|
38
46
|
data = {
|
39
|
-
"full_name" => "John Doe" * 100
|
47
|
+
"full_name" => "John Doe" * 100,
|
48
|
+
"birth_date" => Date.new(1934, 1, 2)
|
40
49
|
}
|
41
50
|
|
42
51
|
uncompressed_data = avro.encode(data, schema_name: "person")
|
@@ -329,5 +338,64 @@ describe AvroTurf do
|
|
329
338
|
datum = { message: "hello" }
|
330
339
|
expect(avro.valid?(datum, schema_name: "postcard")).to eq true
|
331
340
|
end
|
341
|
+
|
342
|
+
it "handles logicalType of date in schema" do
|
343
|
+
define_schema "postcard.avsc", <<-AVSC
|
344
|
+
{
|
345
|
+
"name": "postcard",
|
346
|
+
"type": "record",
|
347
|
+
"fields": [
|
348
|
+
{
|
349
|
+
"name": "message",
|
350
|
+
"type": "string"
|
351
|
+
},
|
352
|
+
{
|
353
|
+
"name": "sent_date",
|
354
|
+
"type": {
|
355
|
+
"type": "int",
|
356
|
+
"logicalType": "date"
|
357
|
+
}
|
358
|
+
}
|
359
|
+
]
|
360
|
+
}
|
361
|
+
AVSC
|
362
|
+
|
363
|
+
datum = {
|
364
|
+
message: "hello",
|
365
|
+
sent_date: Date.new(2022, 9, 11)
|
366
|
+
}
|
367
|
+
expect(avro.valid?(datum, schema_name: "postcard")).to eq true
|
368
|
+
end
|
369
|
+
|
370
|
+
context "when message contains extra fields (typo in key)" do
|
371
|
+
let(:message) { { "fulll_name" => "John Doe" } }
|
372
|
+
|
373
|
+
before do
|
374
|
+
define_schema "message.avsc", <<-AVSC
|
375
|
+
{
|
376
|
+
"name": "message",
|
377
|
+
"type": "record",
|
378
|
+
"fields": [
|
379
|
+
{ "name": "full_name", "type": "string" }
|
380
|
+
]
|
381
|
+
}
|
382
|
+
AVSC
|
383
|
+
end
|
384
|
+
|
385
|
+
it "is valid" do
|
386
|
+
datum = { "full_name" => "John Doe", "extra" => "extra" }
|
387
|
+
expect(avro.valid?(datum, schema_name: "message")).to eq true
|
388
|
+
end
|
389
|
+
|
390
|
+
it "is invalid when passing fail_on_extra_fields" do
|
391
|
+
datum = { "full_name" => "John Doe", "extra" => "extra" }
|
392
|
+
validate_options = {
|
393
|
+
recursive: true,
|
394
|
+
encoded: false,
|
395
|
+
fail_on_extra_fields: true }
|
396
|
+
valid = avro.valid?(datum, schema_name: "message", validate_options: validate_options)
|
397
|
+
expect(valid).to eq false
|
398
|
+
end
|
399
|
+
end
|
332
400
|
end
|
333
401
|
end
|
data/spec/core_ext/date_spec.rb
CHANGED
data/spec/spec_helper.rb
CHANGED
@@ -22,6 +22,16 @@ module Helpers
|
|
22
22
|
end
|
23
23
|
end
|
24
24
|
|
25
|
+
# gem `fakefs` does not support flock for the file, and require patch
|
26
|
+
# https://github.com/fakefs/fakefs/issues/433
|
27
|
+
module FakeFS
|
28
|
+
class File < StringIO
|
29
|
+
def flock(*)
|
30
|
+
true
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
25
35
|
RSpec.configure do |config|
|
26
36
|
config.include FakeFS::SpecHelpers
|
27
37
|
config.include Helpers
|
@@ -13,9 +13,20 @@ shared_examples_for "a confluent schema registry client" do
|
|
13
13
|
]
|
14
14
|
}.to_json
|
15
15
|
end
|
16
|
+
let(:headers) do
|
17
|
+
{
|
18
|
+
'Accept'=>'*/*',
|
19
|
+
'Content-Type'=> AvroTurf::ConfluentSchemaRegistry::CONTENT_TYPE,
|
20
|
+
'Host'=> "#{URI.parse(registry_url).host}:80",
|
21
|
+
'User-Agent'=> "excon/#{Excon::VERSION}"
|
22
|
+
}
|
23
|
+
end
|
16
24
|
|
17
25
|
before do
|
18
|
-
stub_request(:any, /^#{registry_url}/)
|
26
|
+
stub_request(:any, /^#{registry_url}/)
|
27
|
+
.with(headers: headers)
|
28
|
+
.to_rack(FakeConfluentSchemaRegistryServer)
|
29
|
+
|
19
30
|
FakeConfluentSchemaRegistryServer.clear
|
20
31
|
end
|
21
32
|
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: avro_turf
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.9.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Daniel Schierbeck
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2023-06-06 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: avro
|
@@ -90,16 +90,16 @@ dependencies:
|
|
90
90
|
name: fakefs
|
91
91
|
requirement: !ruby/object:Gem::Requirement
|
92
92
|
requirements:
|
93
|
-
- - "
|
93
|
+
- - "<"
|
94
94
|
- !ruby/object:Gem::Version
|
95
|
-
version:
|
95
|
+
version: '3'
|
96
96
|
type: :development
|
97
97
|
prerelease: false
|
98
98
|
version_requirements: !ruby/object:Gem::Requirement
|
99
99
|
requirements:
|
100
|
-
- - "
|
100
|
+
- - "<"
|
101
101
|
- !ruby/object:Gem::Version
|
102
|
-
version:
|
102
|
+
version: '3'
|
103
103
|
- !ruby/object:Gem::Dependency
|
104
104
|
name: webmock
|
105
105
|
requirement: !ruby/object:Gem::Requirement
|
@@ -156,7 +156,7 @@ dependencies:
|
|
156
156
|
- - ">="
|
157
157
|
- !ruby/object:Gem::Version
|
158
158
|
version: '0'
|
159
|
-
description:
|
159
|
+
description:
|
160
160
|
email:
|
161
161
|
- dasch@zendesk.com
|
162
162
|
executables: []
|
@@ -251,8 +251,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
251
251
|
- !ruby/object:Gem::Version
|
252
252
|
version: '0'
|
253
253
|
requirements: []
|
254
|
-
rubygems_version: 3.3.
|
255
|
-
signing_key:
|
254
|
+
rubygems_version: 3.0.3.1
|
255
|
+
signing_key:
|
256
256
|
specification_version: 4
|
257
257
|
summary: A library that makes it easier to use the Avro serialization format from
|
258
258
|
Ruby
|