avro_turf 0.9.0 → 0.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 01a2bdf42a996a7a89bab1769672adc11888d973e5c0c70df42d07b63e87e2bf
-  data.tar.gz: c80b96eace3ae4fdb254f046335e7aaf21939cde9da86b671d7450e3d1d2ceb4
+  metadata.gz: 622818bec3f2c9af6a801fe428b373c96ad38596bef90e6f24d86c855084a1a9
+  data.tar.gz: 386053febb649eb457fd0fca3685556e074bee28994be511944da5d7b75b594b
 SHA512:
-  metadata.gz: 978d5323dd68d2a1518dadcaa90c1871b065e184ffd06ca7a9a86ad1402c16a46f557ba5847e0a841a269b38bfdcb0769a66ec961eddd6b40dd4f025c6eb2c9e
-  data.tar.gz: c2abf819298e5c925f60e7d5e6536aced127e1bee0ef4a66893ea25c16f1e8ea9905de9e142e3f7e0a5989901e7708a9ce000cd85384ef2a703d6e77eb27ce7d
+  metadata.gz: 35663cd1404da25e60c03bdfcca2dc20fd1af8fb5eb046bad57fb079f4e50901120e15ae3e6f9d275b068202fd113613b49b9e9237ca2705de3f1fd0e34c304a
+  data.tar.gz: a37f52541946c02c4858c73e974f78e3e88702fe31292807dd46760e9e2a4dabad8287b136df0ff95ba6912cbb15760881e9574f2837a3124242a00e9d6fac75

data/.circleci/config.yml

@@ -17,6 +17,7 @@ jobs:
         - v1-dep-master-
         # Any branch if there are none on the default branch - this should be unnecessary if you have your default branch configured correctly
         - v1-dep-
+    - run: gem install bundler --no-document
     - run: 'bundle check --path=vendor/bundle || bundle install --path=vendor/bundle --jobs=4 --retry=3'
     # Save dependency cache
     - save_cache:
@@ -26,7 +27,7 @@ jobs:
         - ~/.bundle
     - run: mkdir -p $CIRCLE_TEST_REPORTS/rspec
     - run:
-        command: bundle exec rspec --color --require spec_helper --format RspecJunitFormatter --out $CIRCLE_TEST_REPORTS/rspec/rspec.xml --format progress spec
+        command: bundle exec rspec --color --require spec_helper --format progress
     - store_test_results:
         path: /tmp/circleci-test-results
     - store_artifacts:

data/.github/workflows/ruby.yml

@@ -0,0 +1,20 @@
+name: Ruby
+
+on: [push]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Ruby 2.6
+      uses: actions/setup-ruby@v1
+      with:
+        ruby-version: 2.6.x
+    - name: Build and test with RSpec
+      run: |
+        gem install bundler
+        bundle install --jobs 4 --retry 3
+        bundle exec rspec

data/CHANGELOG.md

@@ -2,6 +2,11 @@
 
 ## Unreleased
 
+## v0.10.0
+
+- Add more disk caching (#103)
+- Include schema information when decoding (#100, #101, #104)
+
 ## v0.9.0
 
 - Compatibility with Avro v1.9.0 (#94)

data/Gemfile

@@ -2,6 +2,3 @@ source 'https://rubygems.org'
 
 # Specify your gem's dependencies in avro_turf.gemspec
 gemspec
-
-# Used by CircleCI to format RSpec results.
-gem 'rspec_junit_formatter', :git => 'git@github.com:circleci/rspec_junit_formatter.git'

data/README.md

@@ -126,13 +126,27 @@ data = avro.encode({ "title" => "hello, world" }, schema_name: "greeting")
 
 # If you don't want to automatically register new schemas, you can pass explicitly
 # subject and version to specify which schema should be used for encoding.
-# It will fetch that schema from the registry and cache it. Subsequent instances 
+# It will fetch that schema from the registry and cache it. Subsequent instances
 # of the same schema version will be served by the cache.
 data = avro.encode({ "title" => "hello, world" }, subject: 'greeting', version: 1)
 
+# You can also pass explicitly schema_id to specify which schema
+# should be used for encoding.
+# It will fetch that schema from the registry and cache it. Subsequent instances
+# of the same schema version will be served by the cache.
+data = avro.encode({ "title" => "hello, world" }, schema_id: 2)
+
 # When decoding, the schema will be fetched from the registry and cached. Subsequent
 # instances of the same schema id will be served by the cache.
 avro.decode(data) #=> { "title" => "hello, world" }
+
+# If you want to get decoded message as well as the schema used to encode the message,
+# you can use `#decode_message` method.
+result = avro.decode_message(data)
+result.message       #=> { "title" => "hello, world" }
+result.schema_id     #=> 3
+result.writer_schema #=> #<Avro::Schema: ...>
+result.reader_schema #=> nil
 ```
 
 ### Confluent Schema Registry Client

data/avro_turf.gemspec

@@ -20,7 +20,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "avro", ">= 1.7.7", "< 1.10"
   spec.add_dependency "excon", "~> 0.45"
 
-  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "bundler", "~> 2.0"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3.2.0"
   spec.add_development_dependency "fakefs", "~> 0.6.7"

data/lib/avro_turf/disk_cache.rb

@@ -11,6 +11,9 @@ class AvroTurf::DiskCache < AvroTurf::InMemoryCache
 
     @ids_by_schema_path = File.join(disk_path, 'ids_by_schema.json')
     @ids_by_schema = JSON.parse(File.read(@ids_by_schema_path)) if File.exist?(@ids_by_schema_path)
+
+    @schemas_by_subject_version_path = File.join(disk_path, 'schemas_by_subject_version.json')
+    @schemas_by_subject_version = {}
   end
 
   # override
@@ -35,4 +38,46 @@ class AvroTurf::DiskCache < AvroTurf::InMemoryCache
     File.write(@ids_by_schema_path, JSON.pretty_generate(@ids_by_schema))
     return value
   end
+
+  # checks instance var (in-memory cache) for schema
+  # checks disk cache if in-memory cache doesn't exists
+  # if file exists but no in-memory cache, read from file and sync in-memory cache
+  # finally, if file doesn't exist return nil
+  def lookup_by_version(subject, version)
+    key = "#{subject}#{version}"
+    schema = @schemas_by_subject_version[key]
+
+    return schema unless schema.nil?
+
+    hash = JSON.parse(File.read(@schemas_by_subject_version_path)) if File.exist?(@schemas_by_subject_version_path)
+    if hash
+      @schemas_by_subject_version = hash
+      @schemas_by_subject_version[key]
+    end
+  end
+
+  # check if file exists and parse json into a hash
+  # if file exists take json and overwite/insert schema at key
+  # if file doesn't exist create new hash
+  # write the new/updated hash to file
+  # update instance var (in memory-cache) to match
+  def store_by_version(subject, version, schema)
+    key = "#{subject}#{version}"
+    hash = JSON.parse(File.read(@schemas_by_subject_version_path)) if File.exist?(@schemas_by_subject_version_path)
+    hash = if hash
+             hash[key] = schema
+             hash
+           else
+             {key => schema}
+           end
+
+    write_to_disk_cache(@schemas_by_subject_version_path, hash)
+
+    @schemas_by_subject_version = hash
+    @schemas_by_subject_version[key]
+  end
+
+  private def write_to_disk_cache(path, hash)
+    File.write(path, JSON.pretty_generate(hash))
+  end
 end

data/lib/avro_turf/messaging.rb

@@ -21,6 +21,8 @@ class AvroTurf
   # 1: https://github.com/confluentinc/schema-registry
   class Messaging
     MAGIC_BYTE = [0].pack("C").freeze
+    DecodedMessage = Struct.new(:schema_id, :writer_schema, :reader_schema, :message)
+    private_constant(:DecodedMessage)
 
     # Instantiate a new Messaging instance with the given configuration.
     #
@@ -50,15 +52,19 @@ class AvroTurf
     #               the schema registry (optional).
     # version     - The integer version of the schema that should be used to decode
     #               the data. Must match the schema used when encoding (optional).
+    # schema_id   - The integer id of the schema that should be used to encode
+    #               the data.
     #
     # Returns the encoded data as a String.
-    def encode(message, schema_name: nil, namespace: @namespace, subject: nil, version: nil)
-      schema_id, schema = if subject && version
+    def encode(message, schema_name: nil, namespace: @namespace, subject: nil, version: nil, schema_id: nil)
+      schema_id, schema = if schema_id
+        fetch_schema_by_id(schema_id)
+      elsif subject && version
         fetch_schema(subject, version)
       elsif schema_name
         register_schema(subject, schema_name, namespace)
       else
-        raise ArgumentError.new('Neither schema_name nor subject + version provided to determine the schema.')
+        raise ArgumentError.new('Neither schema_name nor schema_id nor subject + version provided to determine the schema.')
       end
 
       stream = StringIO.new
@@ -76,7 +82,11 @@ class AvroTurf
 
       stream.string
     rescue Excon::Error::NotFound
-      raise SchemaNotFoundError.new("Schema with subject: `#{subject}` version: `#{version}` is not found on registry")
+      if schema_id
+        raise SchemaNotFoundError.new("Schema with id: #{schema_id} is not found on registry")
+      else
+        raise SchemaNotFoundError.new("Schema with subject: `#{subject}` version: `#{version}` is not found on registry")
+      end
     end
 
     # Decodes data into the original message.
@@ -88,6 +98,20 @@ class AvroTurf
     #
     # Returns the decoded message.
     def decode(data, schema_name: nil, namespace: @namespace)
+      decode_message(data, schema_name: schema_name, namespace: namespace).message
+    end
+
+    # Decodes data into the original message.
+    #
+    # data        - A String containing encoded data.
+    # schema_name - The String name of the schema that should be used to decode
+    #               the data. Must match the schema used when encoding (optional).
+    # namespace   - The namespace of the schema (optional).
+    #
+    # Returns Struct with the next attributes:
+    #   schema_id  - The integer id of schema used to encode the message
+    #   message    - The decoded message
+    def decode_message(data, schema_name: nil, namespace: @namespace)
       readers_schema = schema_name && @schema_store.find(schema_name, namespace)
       stream = StringIO.new(data)
       decoder = Avro::IO::BinaryDecoder.new(stream)
@@ -108,7 +132,9 @@ class AvroTurf
       end
 
       reader = Avro::IO::DatumReader.new(writers_schema, readers_schema)
-      reader.read(decoder)
+      message = reader.read(decoder)
+
+      DecodedMessage.new(schema_id, writers_schema, readers_schema, message)
     rescue Excon::Error::NotFound
       raise SchemaNotFoundError.new("Schema with id: #{schema_id} is not found on registry")
     end
@@ -125,6 +151,13 @@ class AvroTurf
       [schema_id, schema]
     end
 
+    # Fetch the schema from registry with the provided schema_id.
+    def fetch_schema_by_id(schema_id)
+      schema_json = @registry.fetch(schema_id)
+      schema = Avro::Schema.parse(schema_json)
+      [schema_id, schema]
+    end
+
     # Schemas are registered under the full name of the top level Avro record
     # type, or `subject` if it's provided.
     def register_schema(subject, schema_name, namespace)

data/lib/avro_turf/version.rb

@@ -1,3 +1,3 @@
 class AvroTurf
-  VERSION = "0.9.0"
+  VERSION = "0.10.0"
 end

data/spec/disk_cached_confluent_schema_registry_spec.rb

@@ -24,6 +24,21 @@ describe AvroTurf::CachedConfluentSchemaRegistry do
     }.to_json
   end
 
+  let(:subject) { 'subject' }
+  let(:version) { rand(999) }
+  let(:subject_version_schema) do
+    {
+      subject: subject,
+      version: version,
+      id: id,
+      schema:  {
+        type: "record",
+        name: "city",
+        fields: { name: "name", type: "string" }
+      }
+    }.to_json
+  end
+
   before do
     FileUtils.mkdir_p("spec/cache")
   end
@@ -105,6 +120,38 @@ describe AvroTurf::CachedConfluentSchemaRegistry do
     end
   end
 
+  describe "#subject_version" do
+    it "writes thru to disk cache" do
+      # multiple calls return same result, with zero upstream calls
+      allow(upstream).to receive(:subject_version).with(subject, version).and_return(subject_version_schema)
+      expect(File).not_to exist("./spec/cache/schemas_by_subject_version.json")
+
+      expect(registry.subject_version(subject, version)).to eq(subject_version_schema)
+
+      json = JSON.parse(File.read("./spec/cache/schemas_by_subject_version.json"))["#{subject}#{version}"]
+      expect(json).to eq(subject_version_schema)
+
+      expect(registry.subject_version(subject, version)).to eq(subject_version_schema)
+      expect(upstream).to have_received(:subject_version).exactly(1).times
+    end
+
+    it "reads from disk cache and populates mem cache" do
+      allow(upstream).to receive(:subject_version).with(subject, version).and_return(subject_version_schema)
+      key = "#{subject}#{version}"
+      hash = {key => subject_version_schema}
+      cache.send(:write_to_disk_cache, "./spec/cache/schemas_by_subject_version.json", hash)
+
+      cached_schema = cache.instance_variable_get(:@schemas_by_subject_version)
+      expect(cached_schema).to eq({})
+
+      expect(registry.subject_version(subject, version)).to eq(subject_version_schema)
+      expect(upstream).to have_received(:subject_version).exactly(0).times
+
+      cached_schema = cache.instance_variable_get(:@schemas_by_subject_version)
+      expect(cached_schema).to eq({key => subject_version_schema})
+    end
+  end
+
   it_behaves_like "a confluent schema registry client" do
     let(:upstream) { AvroTurf::ConfluentSchemaRegistry.new(registry_url, logger: logger) }
     let(:registry) { described_class.new(upstream) }

data/spec/messaging_spec.rb

@@ -29,6 +29,7 @@ describe AvroTurf::Messaging do
       }
     AVSC
   end
+  let(:schema) { Avro::Schema.parse(schema_json) }
 
   before do
     FileUtils.mkdir_p("spec/schemas")
@@ -66,8 +67,8 @@ describe AvroTurf::Messaging do
   shared_examples_for 'encoding and decoding with the schema from registry' do
     before do
       registry = AvroTurf::ConfluentSchemaRegistry.new(registry_url, logger: logger)
-      registry.register('person', Avro::Schema.parse(schema_json))
-      registry.register('people', Avro::Schema.parse(schema_json))
+      registry.register('person', schema)
+      registry.register('people', schema)
     end
 
     it 'encodes and decodes messages' do
@@ -93,10 +94,37 @@ describe AvroTurf::Messaging do
     end
   end
 
+  shared_examples_for 'encoding and decoding with the schema_id from registry' do
+    before do
+      registry = AvroTurf::ConfluentSchemaRegistry.new(registry_url, logger: logger)
+      registry.register('person', schema)
+      registry.register('people', schema)
+    end
+
+    it 'encodes and decodes messages' do
+      data = avro.encode(message, schema_id: 1)
+      expect(avro.decode(data)).to eq message
+    end
+
+    it 'raises AvroTurf::SchemaNotFoundError when the schema does not exist on registry' do
+      expect { avro.encode(message, schema_id: 5) }.to raise_error(AvroTurf::SchemaNotFoundError)
+    end
+
+    it 'caches parsed schemas for decoding' do
+      data = avro.encode(message, schema_id: 1)
+      avro.decode(data)
+      allow(Avro::Schema).to receive(:parse).and_call_original
+      expect(avro.decode(data)).to eq message
+      expect(Avro::Schema).not_to have_received(:parse)
+    end
+  end
+
   it_behaves_like "encoding and decoding with the schema from schema store"
 
   it_behaves_like 'encoding and decoding with the schema from registry'
 
+  it_behaves_like 'encoding and decoding with the schema_id from registry'
+
   context "with a provided registry" do
     let(:registry) { AvroTurf::ConfluentSchemaRegistry.new(registry_url, logger: logger) }
 
@@ -112,6 +140,8 @@ describe AvroTurf::Messaging do
 
     it_behaves_like 'encoding and decoding with the schema from registry'
 
+    it_behaves_like 'encoding and decoding with the schema_id from registry'
+
     it "uses the provided registry" do
       allow(registry).to receive(:register).and_call_original
       message = { "full_name" => "John Doe" }
@@ -146,4 +176,119 @@ describe AvroTurf::Messaging do
       expect(schema_store).to have_received(:find).with("person", nil)
     end
   end
+
+  describe 'decoding with #decode_message' do
+    shared_examples_for "encoding and decoding with the schema from schema store" do
+      it "encodes and decodes messages" do
+        data = avro.encode(message, schema_name: "person")
+        result = avro.decode_message(data)
+        expect(result.message).to eq message
+        expect(result.schema_id).to eq 0
+        expect(result.writer_schema).to eq schema
+        expect(result.reader_schema).to eq nil
+      end
+
+      it "allows specifying a reader's schema" do
+        data = avro.encode(message, schema_name: "person")
+        result = avro.decode_message(data, schema_name: "person")
+        expect(result.message).to eq message
+        expect(result.writer_schema).to eq schema
+        expect(result.reader_schema).to eq schema
+      end
+
+      it "caches parsed schemas for decoding" do
+        data = avro.encode(message, schema_name: "person")
+        avro.decode_message(data)
+        allow(Avro::Schema).to receive(:parse).and_call_original
+        expect(avro.decode_message(data).message).to eq message
+        expect(Avro::Schema).not_to have_received(:parse)
+      end
+    end
+
+    shared_examples_for 'encoding and decoding with the schema from registry' do
+      before do
+        registry = AvroTurf::ConfluentSchemaRegistry.new(registry_url, logger: logger)
+        registry.register('person', schema)
+        registry.register('people', schema)
+      end
+
+      it 'encodes and decodes messages' do
+        data = avro.encode(message, subject: 'person', version: 1)
+        result = avro.decode_message(data)
+        expect(result.message).to eq message
+        expect(result.schema_id).to eq 0
+      end
+
+      it "allows specifying a reader's schema by subject and version" do
+        data = avro.encode(message, subject: 'person', version: 1)
+        expect(avro.decode_message(data, schema_name: 'person').message).to eq message
+      end
+
+      it 'raises AvroTurf::SchemaNotFoundError when the schema does not exist on registry' do
+        expect { avro.encode(message, subject: 'missing', version: 1) }.to raise_error(AvroTurf::SchemaNotFoundError)
+      end
+
+      it 'caches parsed schemas for decoding' do
+        data = avro.encode(message, subject: 'person', version: 1)
+        avro.decode_message(data)
+        allow(Avro::Schema).to receive(:parse).and_call_original
+        expect(avro.decode_message(data).message).to eq message
+        expect(Avro::Schema).not_to have_received(:parse)
+      end
+    end
+
+    it_behaves_like "encoding and decoding with the schema from schema store"
+
+    it_behaves_like 'encoding and decoding with the schema from registry'
+
+    context "with a provided registry" do
+      let(:registry) { AvroTurf::ConfluentSchemaRegistry.new(registry_url, logger: logger) }
+
+      let(:avro) do
+        AvroTurf::Messaging.new(
+          registry: registry,
+          schemas_path: "spec/schemas",
+          logger: logger
+        )
+      end
+
+      it_behaves_like "encoding and decoding with the schema from schema store"
+
+      it_behaves_like 'encoding and decoding with the schema from registry'
+
+      it "uses the provided registry" do
+        allow(registry).to receive(:register).and_call_original
+        message = { "full_name" => "John Doe" }
+        avro.encode(message, schema_name: "person")
+        expect(registry).to have_received(:register).with("person", anything)
+      end
+
+      it "allows specifying a schema registry subject" do
+        allow(registry).to receive(:register).and_call_original
+        message = { "full_name" => "John Doe" }
+        avro.encode(message, schema_name: "person", subject: "people")
+        expect(registry).to have_received(:register).with("people", anything)
+      end
+    end
+
+    context "with a provided schema store" do
+      let(:schema_store) { AvroTurf::SchemaStore.new(path: "spec/schemas") }
+
+      let(:avro) do
+        AvroTurf::Messaging.new(
+          registry_url: registry_url,
+          schema_store: schema_store,
+          logger: logger
+        )
+      end
+
+      it_behaves_like "encoding and decoding with the schema from schema store"
+
+      it "uses the provided schema store" do
+        allow(schema_store).to receive(:find).and_call_original
+        avro.encode(message, schema_name: "person")
+        expect(schema_store).to have_received(:find).with("person", nil)
+      end
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: avro_turf
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.10.0
 platform: ruby
 authors:
 - Daniel Schierbeck
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-07-15 00:00:00.000000000 Z
+date: 2019-09-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: avro
@@ -50,14 +50,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '2.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -164,6 +164,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".circleci/config.yml"
+- ".github/workflows/ruby.yml"
 - ".gitignore"
 - ".rspec"
 - CHANGELOG.md
@@ -248,7 +249,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubyforge_project: 
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: A library that makes it easier to use the Avro serialization format from