waterdrop 2.6.4 → 2.6.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d70b143a525502bda5fd1ab9d391afa6e5434032179ad169b7a0cf9a1015be8d
-  data.tar.gz: c7fd47967967a0ca11e7f791f87eb9475f2d21bd3b3673a57a2c983e91244277
+  metadata.gz: b8230d88044bf8542a887da74a67273ac3599918e108b0c30694b8fe38910c4e
+  data.tar.gz: 39e1aff3939c76ca14cb967148fb8328af148098cd3215cd921190c40b95efdc
 SHA512:
-  metadata.gz: 8dcc38ac6a287417c2f4b0aa65c9f08146ff84d77264b2d12e56201ff1180c9c8f9c3eead2a508341189239d223e1fadb9c126f9e7c0a2b5ebb352ffffdd9dd5
-  data.tar.gz: 73deed1c8323285e497f98d6710ddd3e8b890641205556d04f5cf460859efc5a39803f58e4ff5d2a31a1387f6a75b66dc7ddc46573145a30360797ee49fe70fc
+  metadata.gz: 5018e5ede943b48093b871381757aeb2b6af92248181ff3a8dd954a2c40e3cc123515dbb71dd7b0f33e1107c500711be6dcb252552e0ecd348e0fad292c2700c
+  data.tar.gz: 06c00dfe2cd6d7b37455a8b8f5f6613e161620535138fe53dc304b5e7fc1cad835ed0b8f2a86e71ffbb840c39f85bf7897eab227b2ce2671995ef15e07f666a8

data/CHANGELOG.md

@@ -1,6 +1,12 @@
 # WaterDrop changelog
 
-### 2.6.4 (Unreleased)
+### 2.6.6 (2023-08-03)
+- [Improvement] Provide `log_messages` option to `LoggerListener` so the extensive messages data logging can disabled.
+
+### 2.6.5 (2023-07-22)
+- [Fix] Add cause to the errors that are passed into instrumentation (konalegi)
+
+### 2.6.4 (2023-07-11)
 - [Improvement] Use original error `#inspect` for `WaterDrop::Errors::ProduceError` and `WaterDrop::Errors::ProduceManyError` instead of the current empty string.
 
 ### 2.6.3 (2023-06-28)

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    waterdrop (2.6.4)
+    waterdrop (2.6.6)
       karafka-core (>= 2.1.1, < 3.0.0)
       zeitwerk (~> 2.3)
 

data/README.md

@@ -339,6 +339,35 @@ Karafka [Web UI](https://karafka.io/docs/Web-UI-Getting-Started/) is a user inte
 
 ![Example producer errors in Karafka Web-UI](https://raw.githubusercontent.com/karafka/misc/master/printscreens/web-ui/errors-producer.png)
 
+### Logger Listener
+
+WaterDrop comes equipped with a `LoggerListener`, a useful feature designed to facilitate the reporting of WaterDrop's operational details directly into the assigned logger. The `LoggerListener` provides a convenient way of tracking the events and operations that occur during the usage of WaterDrop, enhancing transparency and making debugging and issue tracking easier.
+
+However, it's important to note that this Logger Listener is not subscribed by default. This means that WaterDrop does not automatically send operation data to your logger out of the box. This design choice has been made to give users greater flexibility and control over their logging configuration.
+
+To use this functionality, you need to manually subscribe the `LoggerListener` to WaterDrop instrumentation. Below, you will find an example demonstrating how to perform this subscription.
+
+```ruby
+LOGGER = Logger.new($stdout)
+
+producer = WaterDrop::Producer.new do |config|
+  config.kafka = { 'bootstrap.servers': 'localhost:9092' }
+  config.logger = LOGGER
+end
+
+producer.monitor.subscribe(
+  WaterDrop::Instrumentation::LoggerListener.new(
+    # You can use a different logger than the one assigned to WaterDrop if you want
+    producer.config.logger,
+    # If this is set to false, the produced messages details will not be sent to logs
+    # You may set it to false if you find the level of reporting in the debug too extensive
+    log_messages: true
+  )
+)
+
+producer.produce_sync(topic: 'my.topic', payload: 'my.message')
+```
+
 ### Usage statistics
 
 WaterDrop is configured to emit internal `librdkafka` metrics every five seconds. You can change this by setting the `kafka` `statistics.interval.ms` configuration property to a value greater of equal `0`. Emitted statistics are available after subscribing to the `statistics.emitted` publisher event. If set to `0`, metrics will not be published.

data/lib/waterdrop/instrumentation/logger_listener.rb

@@ -9,8 +9,17 @@ module WaterDrop
     #   as well as we can use it standalone
     class LoggerListener
       # @param logger [Object] logger we want to use
-      def initialize(logger)
+      # @param log_messages [Boolean] Should we report the messages content (payload and metadata)
+      #   with each message operation.
+      #
+      #   This can be extensive, especially when producing a lot of messages. We provide this
+      #   despite the fact that we only report payloads in debug, because Rails by default operates
+      #   with debug level. This means, that when working with Rails in development, every single
+      #   payload dispatched will go to logs. In majority of the cases this is extensive and simply
+      #   floods the end user.
+      def initialize(logger, log_messages: true)
         @logger = logger
+        @log_messages = log_messages
       end
 
       # @param event [Dry::Events::Event] event that happened with the details
@@ -18,6 +27,9 @@ module WaterDrop
         message = event[:message]
 
         info(event, "Async producing of a message to '#{message[:topic]}' topic")
+
+        return unless log_messages?
+
         debug(event, message)
       end
 
@@ -26,6 +38,9 @@ module WaterDrop
         message = event[:message]
 
         info(event, "Sync producing of a message to '#{message[:topic]}' topic")
+
+        return unless log_messages?
+
         debug(event, message)
       end
 
@@ -35,6 +50,9 @@ module WaterDrop
         topics_count = messages.map { |message| "'#{message[:topic]}'" }.uniq.count
 
         info(event, "Async producing of #{messages.size} messages to #{topics_count} topics")
+
+        return unless log_messages?
+
         debug(event, messages)
       end
 
@@ -44,6 +62,9 @@ module WaterDrop
         topics_count = messages.map { |message| "'#{message[:topic]}'" }.uniq.count
 
         info(event, "Sync producing of #{messages.size} messages to #{topics_count} topics")
+
+        return unless log_messages?
+
         debug(event, messages)
       end
 
@@ -52,6 +73,9 @@ module WaterDrop
         message = event[:message]
 
         info(event, "Buffering of a message to '#{message[:topic]}' topic")
+
+        return unless log_messages?
+
         debug(event, [message])
       end
 
@@ -60,6 +84,9 @@ module WaterDrop
         messages = event[:messages]
 
         info(event, "Buffering of #{messages.size} messages")
+
+        return unless log_messages?
+
         debug(event, [messages, messages.size])
       end
 
@@ -68,6 +95,9 @@ module WaterDrop
         messages = event[:messages]
 
         info(event, "Async flushing of #{messages.size} messages from the buffer")
+
+        return unless log_messages?
+
         debug(event, messages)
       end
 
@@ -76,6 +106,9 @@ module WaterDrop
         messages = event[:messages]
 
         info(event, "Sync flushing of #{messages.size} messages from the buffer")
+
+        return unless log_messages?
+
         debug(event, messages)
       end
 
@@ -94,6 +127,11 @@ module WaterDrop
 
       private
 
+      # @return [Boolean] should we report the messages details in the debug mode.
+      def log_messages?
+        @log_messages
+      end
+
       # @param event [Dry::Events::Event] event that happened with the details
       # @param log_message [String] message we want to publish
       def debug(event, log_message)

data/lib/waterdrop/producer/async.rb

@@ -23,17 +23,21 @@ module WaterDrop
           message: message
         ) { produce(message) }
       rescue *SUPPORTED_FLOW_ERRORS => e
-        re_raised = Errors::ProduceError.new(e.inspect)
+        # We use this syntax here because we want to preserve the original `#cause` when we
+        # instrument the error and there is no way to manually assign `#cause` value
+        begin
+          raise Errors::ProduceError, e.inspect
+        rescue Errors::ProduceError => ex
+          @monitor.instrument(
+            'error.occurred',
+            producer_id: id,
+            message: message,
+            error: ex,
+            type: 'message.produce_async'
+          )
 
-        @monitor.instrument(
-          'error.occurred',
-          producer_id: id,
-          message: message,
-          error: re_raised,
-          type: 'message.produce_async'
-        )
-
-        raise re_raised
+          raise ex
+        end
       end
 
       # Produces many messages to Kafka and does not wait for them to be delivered

data/lib/waterdrop/producer/sync.rb

@@ -27,17 +27,21 @@ module WaterDrop
           wait(produce(message))
         end
       rescue *SUPPORTED_FLOW_ERRORS => e
-        re_raised = Errors::ProduceError.new(e.inspect)
+        # We use this syntax here because we want to preserve the original `#cause` when we
+        # instrument the error and there is no way to manually assign `#cause` value
+        begin
+          raise Errors::ProduceError, e.inspect
+        rescue Errors::ProduceError => ex
+          @monitor.instrument(
+            'error.occurred',
+            producer_id: id,
+            message: message,
+            error: ex,
+            type: 'message.produce_sync'
+          )
 
-        @monitor.instrument(
-          'error.occurred',
-          producer_id: id,
-          message: message,
-          error: re_raised,
-          type: 'message.produce_sync'
-        )
-
-        raise re_raised
+          raise ex
+        end
       end
 
       # Produces many messages to Kafka and waits for them to be delivered

data/lib/waterdrop/version.rb

@@ -3,5 +3,5 @@
 # WaterDrop library
 module WaterDrop
   # Current WaterDrop version
-  VERSION = '2.6.4'
+  VERSION = '2.6.6'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: waterdrop
 version: !ruby/object:Gem::Version
-  version: 2.6.4
+  version: 2.6.6
 platform: ruby
 authors:
 - Maciej Mensfeld
@@ -35,7 +35,7 @@ cert_chain:
   Qf04B9ceLUaC4fPVEz10FyobjaFoY4i32xRto3XnrzeAgfEe4swLq8bQsR3w/EF3
   MGU0FeSV2Yj7Xc2x/7BzLK8xQn5l7Yy75iPF+KP3vVmDHnNl
   -----END CERTIFICATE-----
-date: 2023-07-11 00:00:00.000000000 Z
+date: 2023-08-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: karafka-core