logstash-codec-protobuf 1.2.0 → 1.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 4812c43d851064eacffc5c6fba4719eed4691702
-  data.tar.gz: 88436b13daa031ffb714a0f3b1c9611e4130133a
+SHA256:
+  metadata.gz: 48d78608a993ce87e16cefbf92995c27ea0f95b3a9af82f030d3bd7fc22a1e6d
+  data.tar.gz: 5f1e2aab280322aab0878eae12ee51f98f30257025ce8d50b0bac39a4edd793e
 SHA512:
-  metadata.gz: b9e6b75105a06e434fdf6f968e80842ac874bbeb7cf1bd72b7339ce3434e43dd4cdc20e992add4b24e811302f2d4366ee8548426b8813042649ea73617cd14ca
-  data.tar.gz: 53d72f5bdb6b5eac6fb88b4d092dba366c820043a709a0d433cf0ef30e7a52f468a48e46cd8a9e728a2fb9c2775c31fee305fb11e5e4f1d7ac0f7d491389a4dc
+  metadata.gz: 932aaff952bf4982d5192701eb3a3997416d76dc750516d53e48f08689f16f93bef0c734a2813f9d71f36ac8a3566fc8916af0c3e3b33b58714b33f40848b1f0
+  data.tar.gz: 76562195f5f05b10dc34695447ace2bd74081e1fdee281c4f5b28e04722f518f6fff0fac789b462c7a7be2877c03236922063d7bb86d16676c853bf1506cac26

data/CHANGELOG.md

@@ -1,3 +1,10 @@
+## 1.2.1
+  - Keep original data in case of parsing errors
+
+## 1.2.0
+  - Autoload all referenced protobuf classes
+  - Fix concurrency issue when using multiple pipelines
+
 ## 1.1.0
   - Add support for protobuf3
 

data/README.md

@@ -4,58 +4,62 @@ This is a codec plugin for [Logstash](https://github.com/elastic/logstash) to pa
 
 # Prerequisites and Installation
  
-* prepare your ruby versions of the protobuf definitions
-** For protobuf 2 use the [ruby-protoc compiler](https://github.com/codekitchen/ruby-protocol-buffers).
-** For protobuf 3 use the [official google protobuf compiler](https://developers.google.com/protocol-buffers/docs/reference/ruby-generated).
+* prepare your Ruby versions of the Protobuf definitions:
+  * For protobuf 2 use the [ruby-protoc compiler](https://github.com/codekitchen/ruby-protocol-buffers).  
+  * For protobuf 3 use the [official google protobuf compiler](https://developers.google.com/protocol-buffers/docs/reference/ruby-generated).
 * install the codec: `bin/logstash-plugin install logstash-codec-protobuf`
-* use the codec in your logstash config file. See details below.
+* use the codec in your Logstash config file. See details below.
 
 ## Configuration
 
-include_path  (required): an array of strings with filenames where logstash can find your protobuf definitions. Please provide absolute paths. For directories it will only try to import files ending on .rb
+`include_path`  (required): an array of strings with filenames where logstash can find your protobuf definitions. Requires absolute paths. Please note that protobuf v2 files have the ending `.pb.rb` whereas files compiled for protobuf v3 end in `_pb.rb`.
 
-class_name    (required): the name of the protobuf class that is to be decoded or encoded. For protobuf 2 separate the modules with ::. For protobuf 3 use single dots. See examples below.
+`class_name`    (required): the name of the protobuf class that is to be decoded or encoded. For protobuf 2 separate the modules with ::. For protobuf 3 use single dots. 
 
-protobuf_version (optional): set this to 3 if you want to use protobuf 3 definitions. Defaults to 2.
+`protobuf_version` (optional): set this to 3 if you want to use protobuf 3 definitions. Defaults to 2.
 
 ## Usage example: decoder
 
 Use this as a codec in any logstash input. Just provide the name of the class that your incoming objects will be encoded in, and specify the path to the compiled definition.
 Here's an example for a kafka input with protobuf 2:
 
-	kafka 
-	{
-	  zk_connect => "127.0.0.1"
-	  topic_id => "unicorns_protobuffed"
-	  key_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
-	  value_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
-
-	  codec => protobuf 
-	  {
-	    class_name => "Animals::Unicorn"
-	    include_path => ['/path/to/pb_definitions/Animal.pb.rb', '/path/to/pb_definitions/Unicorn.pb.rb']
-	  }
-	}
+```ruby
+kafka 
+{
+  topic_id => "..."
+  key_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
+  value_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
+
+  codec => protobuf 
+  {
+    class_name => "Animals::Mammals::Unicorn"
+    include_path => ['/path/to/pb_definitions/Animal.pb.rb', '/path/to/pb_definitions/Unicorn.pb.rb']
+  }
+}
+```
 
 Example for protobuf 3:
 
-	kafka 
-	{
-	  zk_connect => "127.0.0.1"
-	  topic_id => "unicorns_protobuffed"
-	  key_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
-	  value_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
-	  codec => protobuf 
-	  {
-	    class_name => "Animals.Unicorn"
-	    include_path => ['/path/to/pb_definitions/Animal_pb.rb', '/path/to/pb_definitions/Unicorn_pb.rb']
-	    protobuf_version => 3
-	  }
-	}
+```ruby
+kafka 
+{
+  topic_id => "..."
+  key_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
+  value_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
+  codec => protobuf 
+  {
+    class_name => "Animals.Mammals.Unicorn"
+    include_path => ['/path/to/pb_definitions/Animal_pb.rb', '/path/to/pb_definitions/Unicorn_pb.rb']
+    protobuf_version => 3
+  }
+}
+```
 
 For version 3 class names check the bottom of the generated protobuf ruby file. It contains lines like this:
 
-    Animals.Unicorn = Google::Protobuf::DescriptorPool.generated_pool.lookup("Animals.Unicorn").msgclass
+```ruby
+Animals.Unicorn = Google::Protobuf::DescriptorPool.generated_pool.lookup("Animals.Unicorn").msgclass
+```
 
 Use the parameter for the lookup call as the class_name for the codec config.
 
@@ -65,32 +69,39 @@ If you're using a kafka input please also set the deserializer classes as shown
 
 Imagine you have the following protobuf version 2 relationship: class Unicorn lives in namespace Animal::Horse and uses another class Wings. 
 
-	module Animal
-	  module Horse
-	    class Unicorn
-	      set_fully_qualified_name "Animal.Horse.Unicorn"
-	      optional ::Animal::Bodypart::Wings, :wings, 1
-	      optional :string, :name, 2
-	      # here be more field definitions
+```ruby
+module Animal
+  module Mammal
+    class Unicorn
+      set_fully_qualified_name "Animal.Mammal.Unicorn"
+      optional ::Bodypart::Wings, :wings, 1
+      optional :string, :name, 2
+      ...
+```
 
 Make sure to put the referenced wings class first in the include_path:
 
-	include_path => ['/path/to/pb_definitions/wings.pb.rb','/path/to/pb_definitions/unicorn.pb.rb']
+```ruby
+include_path => ['/path/to/pb_definitions/wings.pb.rb','/path/to/pb_definitions/unicorn.pb.rb']
+```
 
 Set the class name to the parent class:
-	
-	class_name => "Animal::Horse::Unicorn"
 
-for protobuf 2. For protobuf 3 use 
+```ruby
+class_name => "Animal::Mammal::Unicorn"
+```
 
-	class_name => "Animal.Horse.Unicorn"
+for protobuf 2. For protobuf 3 use 
 
+```ruby
+class_name => "Animal.Mammal.Unicorn"
+```
 
 ## Usage example: encoder
 
 The configuration of the codec for encoding logstash events for a protobuf output is pretty much the same as for the decoder input usage as demonstrated above. There are some constraints though that you need to be aware of:
-* the protobuf definition needs to contain all the fields that logstash typically adds to an event, in the corrent data type. Examples for this are @timestamp (string), @version (string), host, path, all of which depend on your input sources and filters aswell. If you do not want to add those fields to your protobuf definition then please use a [modify filter](https://www.elastic.co/guide/en/logstash/current/plugins-filters-mutate.html) to [remove](https://www.elastic.co/guide/en/logstash/current/plugins-filters-mutate.html#plugins-filters-mutate-remove_field) the undesired fields.
-* object members starting with @ are somewhat problematic in protobuf definitions. Therefore those fields will automatically be renamed to remove the at character. This also effects the important @timestamp field. Please name it just "timestamp" in your definition.
+* the protobuf definition needs to contain all the fields that logstash typically adds to an event, in the corrent data type. Examples for this are `@timestamp` (string), `@version` (string), `host`, `path`, all of which depend on your input sources and filters aswell. If you do not want to add those fields to your protobuf definition then please use a [modify filter](https://www.elastic.co/guide/en/logstash/current/plugins-filters-mutate.html) to [remove](https://www.elastic.co/guide/en/logstash/current/plugins-filters-mutate.html#plugins-filters-mutate-remove_field) the undesired fields.
+* object members starting with `@` are somewhat problematic in protobuf definitions. Therefore those fields will automatically be renamed to remove the at character. This also effects the important `@timestamp` field. Please name it just "timestamp" in your definition.
 
 
 ## Troubleshooting
@@ -98,11 +109,11 @@ The configuration of the codec for encoding logstash events for a protobuf outpu
 ### Protobuf 2 
 #### "uninitialized constant SOME_CLASS_NAME"
 
-If you include more than one definition class, consider the order of inclusion. This is especially relevant if you include whole directories. A definition might refer to another definition that is not loaded yet. In this case, please specify the files in the include_path variable in reverse order of reference. See 'Example with referenced definitions' above.
+If you include more than one definition class, consider the order of inclusion. This is especially relevant if you include whole directories. A definition might refer to another definition that is not loaded yet. In this case, please specify the files in the `include_path` variable in reverse order of reference. See 'Example with referenced definitions' above.
 
 #### no protobuf output
 
-Maybe your protobuf definition does not fullfill the requirements and needs additional fields. Run logstash with the --debug flag and search for error messages.
+Maybe your protobuf definition does not fullfill the requirements and needs additional fields. Run logstash with the `--debug` flag and search for error messages.
 
 ### Protobuf 3
 

data/docs/index.asciidoc

@@ -20,26 +20,51 @@ include::{include_path}/plugin_header.asciidoc[]
 
 ==== Description
 
-This codec converts protobuf encoded messages into logstash events and vice versa. 
+This codec converts protobuf encoded messages into logstash events and vice versa. It supports the protobuf versions 2 and 3.
 
-Requires the protobuf definitions as ruby files. You can create those using the [ruby-protoc compiler](https://github.com/codekitchen/ruby-protocol-buffers).
+The plugin requires the protobuf definitions to be compiled to ruby files. +
+For protobuf 2 use the https://github.com/codekitchen/ruby-protocol-buffers[ruby-protoc compiler]. +
+For protobuf 3 use the https://developers.google.com/protocol-buffers/docs/reference/ruby-generated[official google protobuf compiler].
 
-The following shows a usage example for decoding events from a kafka stream:
+The following shows a usage example (protobuf v2) for decoding events from a kafka stream:
 [source,ruby]
 kafka 
 {
- zk_connect => "127.0.0.1"
- topic_id => "your_topic_goes_here"
+ topic_id => "..."
  key_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
  value_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
  codec => protobuf 
  {
-   class_name => "Animal::Unicorn"
+   class_name => "Animals::Mammals::Unicorn"
    include_path => ['/path/to/protobuf/definitions/UnicornProtobuf.pb.rb']
  }
 }
 
-Specifically for the kafka input: please set the deserializer classes as shown above.
+Usage example for protobuf v3:
+[source,ruby]
+kafka 
+{
+  topic_id => "..."
+  key_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
+  value_deserializer_class => "org.apache.kafka.common.serialization.ByteArrayDeserializer"
+  codec => protobuf 
+  {
+    class_name => "Animals.Mammals.Unicorn"
+    include_path => ['/path/to/pb_definitions/Animal_pb.rb', '/path/to/pb_definitions/Unicorn_pb.rb']
+    protobuf_version => 3
+  }
+}
+
+
+The codec can be used in input and output plugins. +
+When using the codec in the kafka input plugin please set the deserializer classes as shown above. +
+When using the codec in an output plugin:
+
+* make sure to include all the desired fields in the protobuf definition, including timestamp. 
+  Remove fields that are not part of the protobuf definition from the event by using the mutate filter.
+* the `@` symbol is currently not supported in field names when loading the protobuf definitions for encoding. Make sure to call the timestamp field `timestamp`
+  instead of `@timestamp` in the protobuf file. Logstash event fields will be stripped of the leading `@` before conversion.
+
 
 [id="plugins-{type}s-{plugin}-options"]
 ==== Protobuf Codec Configuration Options
@@ -49,6 +74,7 @@ Specifically for the kafka input: please set the deserializer classes as shown a
 |Setting |Input type|Required
 | <<plugins-{type}s-{plugin}-class_name>> |<<string,string>>|Yes
 | <<plugins-{type}s-{plugin}-include_path>> |<<array,array>>|Yes
+| <<plugins-{type}s-{plugin}-protobuf_version>> |<<number,number>>|Yes
 |=======================================================================
 
 &nbsp;
@@ -60,24 +86,21 @@ Specifically for the kafka input: please set the deserializer classes as shown a
   * Value type is <<string,string>>
   * There is no default value for this setting.
 
-Name of the class to decode.
-If your protobuf definition contains modules, prepend them to the class name with double colons like so:
+Fully qualified name of the class to decode.
+Please note that the module delimiter is different depending on the protobuf version. For protobuf v2, use double colons:
 [source,ruby]
-class_name => "Foods::Dairy::Cheese"
+class_name => "Animals::Mammals::Unicorn"
 
-This corresponds to a protobuf definition starting as follows:
+For protobuf v3, use single dots:
 [source,ruby]
-module Foods
-   module Dairy
-       class Cheese
-           # here are your field definitions.
+class_name => "Animals.Mammals.Unicorn"
 
-If your class references other definitions: you only have to add the main class here.
-For version 3 class names check the bottom of the generated protobuf ruby file. It contains lines like this:
+For protobuf v3, you can copy the class name from the Descriptorpool registrations at the bottom of the generated protobuf ruby file. It contains lines like this:
+[source,ruby]
+Animals.Mammals.Unicorn = Google::Protobuf::DescriptorPool.generated_pool.lookup("Animals.Mammals.Unicorn").msgclass
 
-    Animals.Unicorn = Google::Protobuf::DescriptorPool.generated_pool.lookup("Animals.Unicorn").msgclass
 
-Use the parameter for the lookup call as the class_name for the codec config.
+If your class references other definitions: you only have to add the name of the main class here.
 
 [id="plugins-{type}s-{plugin}-include_path"]
 ===== `include_path` 
@@ -90,25 +113,29 @@ List of absolute pathes to files with protobuf definitions.
 When using more than one file, make sure to arrange the files in reverse order of dependency so that each class is loaded before it is 
 refered to by another.
 
-Example: a class _Cheese_ referencing another protobuf class _Milk_
+Example: a class _Unicorn_ referencing another protobuf class _Wings_
 [source,ruby]
-module Foods
-  module Dairy
-        class Cheese
-           set_fully_qualified_name "Foods.Dairy.Cheese"
-           optional ::Foods::Cheese::Milk, :milk, 1
-           optional :int64, :unique_id, 2
-           # here be more field definitions
+module Animal
+  module Mammal
+    class Unicorn
+      set_fully_qualified_name "Animal.Mammal.Unicorn"
+      optional ::Bodypart::Wings, :wings, 1
+      optional :string, :name, 2
+      ...
 
 would be configured as
 [source,ruby]
-include_path => ['/path/to/protobuf/definitions/Milk.pb.rb','/path/to/protobuf/definitions/Cheese.pb.rb']
+include_path => ['/path/to/pb_definitions/wings.pb.rb','/path/to/pb_definitions/unicorn.pb.rb']
+
+Please note that protobuf v2 files have the ending `.pb.rb` whereas files compiled for protobuf v3 end in `_pb.rb`.
+
+[id="plugins-{type}s-{plugin}-protobuf_version"]
+===== `protobuf_version` 
+
+  * Value type is <<number,number>>
+  * Default value is 2
+
+Protocol buffers version. Valid settings are 2, 3.
 
-When using the codec in an output plugin: 
-* make sure to include all the desired fields in the protobuf definition, including timestamp. 
-  Remove fields that are not part of the protobuf definition from the event by using the mutate filter.
-* the @ symbol is currently not supported in field names when loading the protobuf definitions for encoding. Make sure to call the timestamp field "timestamp" 
-  instead of "@timestamp" in the protobuf file. Logstash event fields will be stripped of the leading @ before conversion.
- 
 
 

data/lib/logstash/codecs/protobuf.rb

@@ -214,6 +214,8 @@ class LogStash::Codecs::Protobuf < LogStash::Codecs::Base
     @logger.warn("Couldn't decode protobuf: #{e.inspect}.")
     if stop_on_error
       raise e
+    else # keep original message so that the user can debug it.
+      yield LogStash::Event.new("message" => data, "tags" => ["_protobufdecodefailure"])
     end
   end # def decode
 

data/logstash-codec-protobuf.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
 
   s.name            = 'logstash-codec-protobuf'
-  s.version         = '1.2.0'
+  s.version         = '1.2.1'
   s.licenses        = ['Apache License (2.0)']
   s.summary         = "Reads protobuf messages and converts to Logstash Events"
   s.description     = "This gem is a logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/plugin install gemname. This gem is not a stand-alone program"

data/spec/codecs/protobuf3_spec.rb

@@ -261,6 +261,7 @@ describe LogStash::Codecs::Protobuf do
 
   context "#test6_pb3" do
 
+
     let(:execution_context) { double("execution_context")}
     let(:pipeline_id) {rand(36**8).to_s(36)}
 
@@ -372,4 +373,36 @@ describe LogStash::Codecs::Protobuf do
 
   end # context #encodePB3
 
+
+
+  context "#test7_pb3" do
+
+    #### Test case 6: decode test case for github issue 17 ####################################################################################################################
+    let(:plugin_7) { LogStash::Codecs::Protobuf.new("class_name" => "RepeatedEvents", "include_path" => [pb_include_path + '/pb3/events_pb.rb'], "protobuf_version" => 3)  }
+    before do
+        plugin_7.register
+    end
+
+    it "should return an event from protobuf encoded data with repeated top level objects" do
+      event_class = Google::Protobuf::DescriptorPool.generated_pool.lookup("RepeatedEvent").msgclass # TODO this shouldnt be necessary because the classes are already
+      # specified at the end of the _pb.rb files
+      events_class = Google::Protobuf::DescriptorPool.generated_pool.lookup("RepeatedEvents").msgclass
+      test_a = event_class.new({:id => "1", :msg => "a"})
+      test_b = event_class.new({:id => "2", :msg => "b"})
+      test_c = event_class.new({:id => "3", :msg => "c"})
+      event_obj = events_class.new({:repeated_events=>[test_a, test_b, test_c]})
+      bin = events_class.encode(event_obj)
+      plugin_7.decode(bin) do |event|
+        expect(event.get("repeated_events").size ).to eq(3)
+        expect(event.get("repeated_events")[0]["id"] ).to eq("1")
+        expect(event.get("repeated_events")[2]["id"] ).to eq("3")
+        expect(event.get("repeated_events")[0]["msg"] ).to eq("a")
+        expect(event.get("repeated_events")[2]["msg"] ).to eq("c")
+      end
+    end # it
+
+
+  end # context test7_pb3
+
+
 end # describe

data/spec/helpers/pb3/events.proto3

@@ -0,0 +1,10 @@
+syntax = "proto3";
+
+message Event {
+   string id = 1;
+   string msg = 2;
+}
+
+message Events {
+    repeated Event events = 1;
+}

data/spec/helpers/pb3/events_pb.rb

@@ -0,0 +1,17 @@
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: events.proto3
+
+require 'google/protobuf'
+
+Google::Protobuf::DescriptorPool.generated_pool.build do
+  add_message "RepeatedEvent" do
+    optional :id, :string, 1
+    optional :msg, :string, 2
+  end
+  add_message "RepeatedEvents" do
+    repeated :repeated_events, :message, 1, "RepeatedEvent"
+  end
+end
+
+Event = Google::Protobuf::DescriptorPool.generated_pool.lookup("RepeatedEvent").msgclass
+Events = Google::Protobuf::DescriptorPool.generated_pool.lookup("RepeatedEvents").msgclass

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: logstash-codec-protobuf
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.2.1
 platform: ruby
 authors:
 - Inga Feick
@@ -103,6 +103,8 @@ files:
 - spec/helpers/pb2/unicorn_event.pb.rb
 - spec/helpers/pb3/ProbeResult_pb.rb
 - spec/helpers/pb3/dnsmessage_pb.rb
+- spec/helpers/pb3/events.proto3
+- spec/helpers/pb3/events_pb.rb
 - spec/helpers/pb3/header/header.proto3
 - spec/helpers/pb3/header/header_pb.rb
 - spec/helpers/pb3/integertest_pb.rb
@@ -134,7 +136,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.6.14.1
+rubygems_version: 2.7.6
 signing_key:
 specification_version: 4
 summary: Reads protobuf messages and converts to Logstash Events
@@ -152,6 +154,8 @@ test_files:
 - spec/helpers/pb2/unicorn_event.pb.rb
 - spec/helpers/pb3/ProbeResult_pb.rb
 - spec/helpers/pb3/dnsmessage_pb.rb
+- spec/helpers/pb3/events.proto3
+- spec/helpers/pb3/events_pb.rb
 - spec/helpers/pb3/header/header.proto3
 - spec/helpers/pb3/header/header_pb.rb
 - spec/helpers/pb3/integertest_pb.rb