Merge branch 'master' into di-settings-internal

Matrixfile

@@ -285,7 +285,10 @@
     'graphql-2.1'  => '❌ 2.5 / ❌ 2.6 / ✅ 2.7 / ✅ 3.0 / ✅ 3.1 / ✅ 3.2 / ✅ 3.3 / ✅ 3.4 / ✅ jruby',
     'graphql-2.0'  => '✅ 2.5 / ✅ 2.6 / ✅ 2.7 / ✅ 3.0 / ✅ 3.1 / ✅ 3.2 / ✅ 3.3 / ✅ 3.4 / ✅ jruby',
     'graphql-1.13' => '❌ 2.5 / ✅ 2.6 / ✅ 2.7 / ✅ 3.0 / ✅ 3.1 / ✅ 3.2 / ✅ 3.3 / ✅ 3.4 / ✅ jruby',
-  }
+  },
+  'di:active_record' => {
+    'rails61-mysql2'  => '❌ 2.5 / ✅ 2.6 / ✅ 2.7 / ✅ 3.0 / ✅ 3.1 / ✅ 3.2 / ✅ 3.3 / ✅ 3.4 / ❌ jruby',
+  },
 }.each_with_object({}) do |(tasks, spec_metadata), hash|
   # Explode arrays of task names into individual tasks
   # e.g. ['rails', 'railsdisableenv'] => {'...'} becomes 'rails7' => {'...'}, 'railsdisableenv7' => {'...'}

Rakefile

@@ -314,6 +314,14 @@ namespace :spec do
 
   task appsec: [:'appsec:all']
 
+  namespace :di do
+    desc '' # "Explicitly hiding from `rake -T`"
+    RSpec::Core::RakeTask.new(:active_record) do |t, args|
+      t.pattern = 'spec/datadog/di/contrib/active_record/**/*_spec.rb'
+      t.rspec_opts = args.to_a.join(' ')
+    end
+  end
+
   namespace :profiling do
     task all: [:main, :ractors]
 

lib/datadog/di/contrib/active_record.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+Datadog::DI::Serializer.register(condition: lambda { |value| ActiveRecord::Base === value }) do |serializer, value, name:, depth:| # steep:ignore
+  # steep thinks all of the arguments are nil here
+  # steep:ignore:start
+  value_to_serialize = {
+    attributes: value.attributes,
+  }
+  serializer.serialize_value(value_to_serialize, depth: depth ? depth - 1 : nil, type: value.class)
+  # steep:ignore:end
+end

lib/datadog/di/serializer.rb

@@ -38,13 +38,42 @@ module DI
     #
     # @api private
     class Serializer
-      def initialize(settings, redactor)
+      # Third-party library integration / custom serializers.
+      #
+      # Dynamic instrumentation has limited payload sizes, and for efficiency
+      # reasons it is not desirable to transmit data to Datadog that will
+      # never contain useful information. Additionally, due to depth limits,
+      # desired data may not even be included in payloads when serialized
+      # with the default, naive serializer. Therefore, custom objects like
+      # ActiveRecord model instances may need custom serializers.
+      #
+      # CUSTOMER NOTE: The API for defining custom serializers is not yet
+      # finalized. Please create an issue at
+      # https://github.com/datadog/dd-trace-rb/issues describing the
+      # object(s) you wish to serialize so that we can ensure your use case
+      # will be supported as the library evolves.
+      #
+      # Note that the current implementation does not permit defining a
+      # serializer for a particular class, which is the simplest use case.
+      # This is because the library itself does not need this functionality
+      # yet, and it won't help for ActiveRecord models (that derive from
+      # a common base class but are all of different classes) or for Mongoid
+      # models (that do not have a common base class at all but include a
+      # standard Mongoid module).
+      @@flat_registry = []
+      def self.register(condition: nil, &block)
+        @@flat_registry << {condition: condition, proc: block}
+      end
+
+      def initialize(settings, redactor, telemetry: nil)
         @settings = settings
         @redactor = redactor
+        @telemetry = telemetry
       end
 
       attr_reader :settings
       attr_reader :redactor
+      attr_reader :telemetry
 
       # Serializes positional and keyword arguments to a method,
       # as obtained by a method probe.
@@ -86,116 +115,135 @@ def serialize_vars(vars)
       # (integers, strings, arrays, hashes).
       #
       # Respects string length, collection size and traversal depth limits.
-      def serialize_value(value, name: nil, depth: settings.dynamic_instrumentation.max_capture_depth)
-        if redactor.redact_type?(value)
-          return {type: class_name(value.class), notCapturedReason: "redactedType"}
-        end
+      def serialize_value(value, name: nil, depth: settings.dynamic_instrumentation.max_capture_depth, type: nil)
+        cls = type || value.class
+        begin
+          if redactor.redact_type?(value)
+            return {type: class_name(cls), notCapturedReason: "redactedType"}
+          end
 
-        if name && redactor.redact_identifier?(name)
-          return {type: class_name(value.class), notCapturedReason: "redactedIdent"}
-        end
+          if name && redactor.redact_identifier?(name)
+            return {type: class_name(cls), notCapturedReason: "redactedIdent"}
+          end
 
-        serialized = {type: class_name(value.class)}
-        case value
-        when NilClass
-          serialized.update(isNull: true)
-        when Integer, Float, TrueClass, FalseClass
-          serialized.update(value: value.to_s)
-        when String, Symbol
-          need_dup = false
-          value = if String === value
-            # This is the only place where we duplicate the value, currently.
-            # All other values are immutable primitives (e.g. numbers).
-            # However, do not duplicate if the string is frozen, or if
-            # it is later truncated.
-            need_dup = !value.frozen?
-            value
-          else
-            value.to_s
+          @@flat_registry.each do |entry|
+            if (condition = entry[:condition]) && condition.call(value)
+              serializer_proc = entry.fetch(:proc)
+              return serializer_proc.call(self, value, name: nil, depth: depth)
+            end
           end
-          max = settings.dynamic_instrumentation.max_capture_string_length
-          if value.length > max
-            serialized.update(truncated: true, size: value.length)
-            value = value[0...max]
+
+          serialized = {type: class_name(cls)}
+          case value
+          when NilClass
+            serialized.update(isNull: true)
+          when Integer, Float, TrueClass, FalseClass
+            serialized.update(value: value.to_s)
+          when Time
+            # This path also handles DateTime values although they do not need
+            # to be explicitly added to the case statement.
+            serialized.update(value: value.iso8601)
+          when Date
+            serialized.update(value: value.to_s)
+          when String, Symbol
             need_dup = false
-          end
-          value = value.dup if need_dup
-          serialized.update(value: value)
-        when Array
-          if depth < 0
-            serialized.update(notCapturedReason: "depth")
-          else
-            max = settings.dynamic_instrumentation.max_capture_collection_size
-            if max != 0 && value.length > max
-              serialized.update(notCapturedReason: "collectionSize", size: value.length)
-              # same steep failure with array slices.
-              # https://github.com/soutaro/steep/issues/1219
-              value = value[0...max] || []
+            value = if String === value
+              # This is the only place where we duplicate the value, currently.
+              # All other values are immutable primitives (e.g. numbers).
+              # However, do not duplicate if the string is frozen, or if
+              # it is later truncated.
+              need_dup = !value.frozen?
+              value
+            else
+              value.to_s
             end
-            entries = value.map do |elt|
-              serialize_value(elt, depth: depth - 1)
+            max = settings.dynamic_instrumentation.max_capture_string_length
+            if value.length > max
+              serialized.update(truncated: true, size: value.length)
+              value = value[0...max]
+              need_dup = false
             end
-            serialized.update(elements: entries)
-          end
-        when Hash
-          if depth < 0
-            serialized.update(notCapturedReason: "depth")
-          else
-            max = settings.dynamic_instrumentation.max_capture_collection_size
-            cur = 0
-            entries = []
-            value.each do |k, v|
-              if max != 0 && cur >= max
+            value = value.dup if need_dup
+            serialized.update(value: value)
+          when Array
+            if depth < 0
+              serialized.update(notCapturedReason: "depth")
+            else
+              max = settings.dynamic_instrumentation.max_capture_collection_size
+              if max != 0 && value.length > max
                 serialized.update(notCapturedReason: "collectionSize", size: value.length)
-                break
+                # same steep failure with array slices.
+                # https://github.com/soutaro/steep/issues/1219
+                value = value[0...max] || []
+              end
+              entries = value.map do |elt|
+                serialize_value(elt, depth: depth - 1)
               end
-              cur += 1
-              entries << [serialize_value(k, depth: depth - 1), serialize_value(v, name: k, depth: depth - 1)]
+              serialized.update(elements: entries)
+            end
+          when Hash
+            if depth < 0
+              serialized.update(notCapturedReason: "depth")
+            else
+              max = settings.dynamic_instrumentation.max_capture_collection_size
+              cur = 0
+              entries = []
+              value.each do |k, v|
+                if max != 0 && cur >= max
+                  serialized.update(notCapturedReason: "collectionSize", size: value.length)
+                  break
+                end
+                cur += 1
+                entries << [serialize_value(k, depth: depth - 1), serialize_value(v, name: k, depth: depth - 1)]
+              end
+              serialized.update(entries: entries)
             end
-            serialized.update(entries: entries)
-          end
-        else
-          if depth < 0
-            serialized.update(notCapturedReason: "depth")
           else
-            fields = {}
-            max = settings.dynamic_instrumentation.max_capture_attribute_count
-            cur = 0
+            if depth < 0
+              serialized.update(notCapturedReason: "depth")
+            else
+              fields = {}
+              max = settings.dynamic_instrumentation.max_capture_attribute_count
+              cur = 0
 
-            # MRI and JRuby 9.4.5+ preserve instance variable definition
-            # order when calling #instance_variables. Previous JRuby versions
-            # did not preserve order and returned the variables in arbitrary
-            # order.
-            #
-            # The arbitrary order is problematic because 1) when there are
-            # fewer instance variables than capture limit, the order in which
-            # the variables are shown in UI will change from one capture to
-            # the next and generally will be arbitrary to the user, and
-            # 2) when there are more instance variables than capture limit,
-            # *which* variables are captured will also change meaning user
-            # looking at the UI may have "new" instance variables appear and
-            # existing ones disappear as they are looking at multiple captures.
-            #
-            # For consistency, we should have some kind of stable order of
-            # instance variables on all supported Ruby runtimes, so that the UI
-            # stays consistent. Given that initial implementation of Ruby DI
-            # does not support JRuby, we don't handle JRuby's lack of ordering
-            # of #instance_variables here, but if JRuby is supported in the
-            # future this may need to be addressed.
-            ivars = value.instance_variables
+              # MRI and JRuby 9.4.5+ preserve instance variable definition
+              # order when calling #instance_variables. Previous JRuby versions
+              # did not preserve order and returned the variables in arbitrary
+              # order.
+              #
+              # The arbitrary order is problematic because 1) when there are
+              # fewer instance variables than capture limit, the order in which
+              # the variables are shown in UI will change from one capture to
+              # the next and generally will be arbitrary to the user, and
+              # 2) when there are more instance variables than capture limit,
+              # *which* variables are captured will also change meaning user
+              # looking at the UI may have "new" instance variables appear and
+              # existing ones disappear as they are looking at multiple captures.
+              #
+              # For consistency, we should have some kind of stable order of
+              # instance variables on all supported Ruby runtimes, so that the UI
+              # stays consistent. Given that initial implementation of Ruby DI
+              # does not support JRuby, we don't handle JRuby's lack of ordering
+              # of #instance_variables here, but if JRuby is supported in the
+              # future this may need to be addressed.
+              ivars = value.instance_variables
 
-            ivars.each do |ivar|
-              if cur >= max
-                serialized.update(notCapturedReason: "fieldCount", fields: fields)
-                break
+              ivars.each do |ivar|
+                if cur >= max
+                  serialized.update(notCapturedReason: "fieldCount", fields: fields)
+                  break
+                end
+                cur += 1
+                fields[ivar] = serialize_value(value.instance_variable_get(ivar), name: ivar, depth: depth - 1)
               end
-              cur += 1
-              fields[ivar] = serialize_value(value.instance_variable_get(ivar), name: ivar, depth: depth - 1)
+              serialized.update(fields: fields)
             end
-            serialized.update(fields: fields)
           end
+          serialized
+        rescue => exc
+          telemetry&.report(exc, description: "Error serializing")
+          {type: class_name(cls), notSerializedReason: exc.to_s}
         end
-        serialized
       end
 
       private

sig/datadog/di/serializer.rbs

@@ -4,16 +4,23 @@ module Datadog
       @settings: untyped
 
       @redactor: untyped
+
+      @telemetry: Core::Telemetry::Component
 
-      def initialize: (untyped settings, untyped redactor) -> void
+      def initialize: (untyped settings, untyped redactor, ?telemetry: Core::Telemetry::Component) -> void
 
       attr_reader settings: Datadog::Core::Configuration::Settings
 
       attr_reader redactor: Datadog::DI::Redactor
 
+      attr_reader telemetry: Core::Telemetry::Component
+
       def serialize_args: (untyped args, untyped kwargs) -> untyped
       def serialize_vars: (untyped vars) -> untyped
       def serialize_value: (untyped value, ?name: String, ?depth: Integer) -> untyped
+
+      def self.register: (?condition: Proc) { 
+        (serializer: Serializer, value: untyped, name: Symbol, depth: Integer) -> untyped } -> void
 
       private
       def class_name: (untyped cls) -> untyped