logstash-filter-fingerprint 3.2.3 → 3.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5985afeb097946794b24fa48da9e78f4a4146e39b7a39b4be98f11c2b74cd7f8
-  data.tar.gz: 1e6ba943dbae9448dacf4bcf8f4d268aa48381d816be73630f6594358090c8d4
+  metadata.gz: f6c1e99ae34e1681eba14af022fa9fc79909bfaf306542326f0ae88881810370
+  data.tar.gz: ffe46fdd11dc94d0fdcdb35d889ec41f3560f205c78e872985ea426fdd776cef
 SHA512:
-  metadata.gz: 63d38e83879e80b301af57fd82fbf60630ace866b6f102425e8d3ae97467b5384b17268215e52854c35bf1c24e7dfe8f6bd448fa9821f7289610c794232d7a48
-  data.tar.gz: 566ef91a8e6d67abf113bdd07621f65d47a290d0b12f7278d881d3eb13cdaf8c6346147eee3d4534a4184ec70544440177b9821b54e61f58ace71a84ae821669
+  metadata.gz: c343f48b3f479e5a38c4de0510fc9a51b6785c4437441206baf491c1373df9abae24d30b5efc4f761295857e7d376c7c276e69378ed305e53432fe55e6e5477a
+  data.tar.gz: 964ad01b6482e60069421ec1c26c1ad422c44e88372ff63305d752210fd31755752409af9dd2bee96adf8fafa9b9065ca1ce40b53f18da05b5a76b86a54fffb0

data/CHANGELOG.md

@@ -1,3 +1,15 @@
+## 3.3.2
+  - [DOC] Clarify behavior when key is set [#65](https://github.com/logstash-plugins/logstash-filter-fingerprint/pull/65). 
+
+## 3.3.1
+  - Force encoding to UTF-8 when concatenating sources to generate fingerprint [#64](https://github.com/logstash-plugins/logstash-filter-fingerprint/pull/64)
+
+## 3.3.0
+  - Add ECS compatibility [#62](https://github.com/logstash-plugins/logstash-filter-fingerprint/pull/62)
+
+## 3.2.4
+  - Fixed the error in Murmur3 with Integer [#61](https://github.com/logstash-plugins/logstash-filter-fingerprint/pull/61)
+
 ## 3.2.3
   - [DOC] Expanded description for concatenate_sources behavior and provided examples [#60](https://github.com/logstash-plugins/logstash-filter-fingerprint/pull/60)
 

data/docs/index.asciidoc

@@ -23,15 +23,30 @@ include::{include_path}/plugin_header.asciidoc[]
 Create consistent hashes (fingerprints) of one or more fields and store
 the result in a new field.
 
-You can use this plugin to create consistent document ids when  events are
+You can use this plugin to create consistent document ids when events are
 inserted into Elasticsearch. This approach means that existing documents can be
 updated instead of creating new documents.
 
-NOTE: When the `target` option is set to `UUID` the result won't be
+NOTE: When the `method` option is set to `UUID` the result won't be
 a consistent hash but a random
 https://en.wikipedia.org/wiki/Universally_unique_identifier[UUID].
 To generate UUIDs, prefer the {logstash-ref}/plugins-filters-uuid.html[uuid filter].
 
+[id="plugins-{type}s-{plugin}-ecs_metadata"]
+==== Event Metadata and the Elastic Common Schema (ECS)
+This plugin adds a hash value to event as an identifier. You can configure the `target` option to change the output field.
+
+When ECS compatibility is disabled, the hash value is stored in the `fingerprint` field.
+When ECS is enabled, the value is stored in the `[event][hash]` field.
+
+Here’s how ECS compatibility mode affects output.
+[cols="<l,<l,e,<e"]
+|=======================================================================
+| ECS disabled | ECS v1 | Availability | Description
+
+| fingerprint | [event][hash] | Always | a hash value of event
+|=======================================================================
+
 [id="plugins-{type}s-{plugin}-options"]
 ==== Fingerprint Filter Configuration Options
 
@@ -43,6 +58,7 @@ This plugin supports the following configuration options plus the <<plugins-{typ
 | <<plugins-{type}s-{plugin}-base64encode>> |<<boolean,boolean>>|No
 | <<plugins-{type}s-{plugin}-concatenate_sources>> |<<boolean,boolean>>|No
 | <<plugins-{type}s-{plugin}-concatenate_all_fields>> |<<boolean,boolean>>|No
+| <<plugins-{type}s-{plugin}-ecs_compatibility>> | <<string,string>>|No
 | <<plugins-{type}s-{plugin}-key>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-method>> |<<string,string>>, one of `["SHA1", "SHA256", "SHA384", "SHA512", "MD5", "MURMUR3", "IPV4_NETWORK", "UUID", "PUNCTUATION"]`|Yes
 | <<plugins-{type}s-{plugin}-source>> |<<array,array>>|No
@@ -133,6 +149,18 @@ fingerprint computation. If `false` and at least one source field is
 given, the target field will be an array with fingerprints of the 
 source fields given.
 
+[id="plugins-{type}s-{plugin}-ecs_compatibility"]
+===== `ecs_compatibility`
+
+* Value type is <<string,string>>
+* Supported values are:
+** `disabled`: unstructured data added at root level
+** `v1`: uses `[event][hash]` fields that are compatible with Elastic Common Schema
+
+Controls this plugin's compatibility with the
+{ecs-ref}[Elastic Common Schema (ECS)].
+See <<plugins-{type}s-{plugin}-ecs_metadata>> for detailed information.
+
 [id="plugins-{type}s-{plugin}-key"]
 ===== `key` 
 
@@ -151,12 +179,11 @@ With other methods, optionally fill in the HMAC key.
 
 The fingerprint method to use.
 
-If set to `SHA1`, `SHA256`, `SHA384`, `SHA512`, or `MD5` and a key is set,
-the cryptographic hash function with the same name will be used to generate
-the fingerprint. When a key set, the keyed-hash (HMAC) digest function will
-be used.
+If set to `SHA1`, `SHA256`, `SHA384`, `SHA512`, or `MD5` and a key is set, the
+corresponding cryptographic hash function and the keyed-hash (HMAC) digest function
+are used to generate the fingerprint.
 
-If set to `MURMUR3` the non-cryptographic MurmurHash function will be used.
+If set to `MURMUR3` the non-cryptographic 64 bit MurmurHash function will be used.
 
 If set to `IPV4_NETWORK` the input data needs to be a IPv4 address and
 the hash value will be the masked-out address using the number of bits
@@ -184,7 +211,8 @@ to create the fingerprint. If an array is given, see the
 ===== `target` 
 
   * Value type is <<string,string>>
-  * Default value is `"fingerprint"`
+  * Default value is `"fingerprint"` when ECS is disabled
+  * Default value is `"[event][hash]"` when ECS is enabled
 
 The name of the field where the generated fingerprint will be stored.
 Any current contents of that field will be overwritten.

data/lib/logstash/filters/fingerprint.rb

@@ -6,6 +6,7 @@ require "openssl"
 require "ipaddr"
 require "murmurhash3"
 require "securerandom"
+require "logstash/plugin_mixins/ecs_compatibility_support"
 
 # Create consistent hashes (fingerprints) of one or more fields and store
 # the result in a new field.
@@ -22,6 +23,8 @@ require "securerandom"
 # https://en.wikipedia.org/wiki/Universally_unique_identifier[UUID].
 # To generate UUIDs, prefer the <<plugins-filters-uuid,uuid filter>>.
 class LogStash::Filters::Fingerprint < LogStash::Filters::Base
+  include LogStash::PluginMixins::ECSCompatibilitySupport(:disabled, :v1, :v8 => :v1)
+
   config_name "fingerprint"
 
   # The name(s) of the source field(s) whose contents will be used
@@ -31,7 +34,7 @@ class LogStash::Filters::Fingerprint < LogStash::Filters::Base
 
   # The name of the field where the generated fingerprint will be stored.
   # Any current contents of that field will be overwritten.
-  config :target, :validate => :string, :default => 'fingerprint'
+  config :target, :validate => :string
 
   # When used with the `IPV4_NETWORK` method fill in the subnet prefix length.
   # With other methods, optionally fill in the HMAC key.
@@ -76,6 +79,11 @@ class LogStash::Filters::Fingerprint < LogStash::Filters::Base
   # without having to proide the field names in the `source` attribute
   config :concatenate_all_fields, :validate => :boolean, :default => false
 
+  def initialize(*params)
+    super
+    @target ||= ecs_select[disabled: 'fingerprint', v1: '[event][hash]']
+  end
+
   def register
     # convert to symbol for faster comparisons
     @method = @method.to_sym
@@ -120,11 +128,13 @@ class LogStash::Filters::Fingerprint < LogStash::Filters::Base
         to_string = ""
         if @concatenate_all_fields
           deep_sort_hashes(event.to_hash).each do |k,v|
-            to_string << "|#{k}|#{v}"
+            # Force encoding to UTF-8 to get around https://github.com/jruby/jruby/issues/6748
+            to_string << "|#{k}|#{v}".force_encoding("UTF-8")
           end
         else
           @source.sort.each do |k|
-            to_string << "|#{k}|#{deep_sort_hashes(event.get(k))}"
+            # Force encoding to UTF-8 to get around https://github.com/jruby/jruby/issues/6748
+            to_string << "|#{k}|#{deep_sort_hashes(event.get(k))}".force_encoding("UTF-8")
           end
         end
         to_string << "|"
@@ -193,8 +203,8 @@ class LogStash::Filters::Fingerprint < LogStash::Filters::Base
 
   def fingerprint_murmur3(value)
     case value
-    when Fixnum
-      MurmurHash3::V32.int_hash(value)
+    when Integer
+      MurmurHash3::V32.int64_hash(value)
     else
       MurmurHash3::V32.str_hash(value.to_s)
     end

data/logstash-filter-fingerprint.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
 
   s.name            = 'logstash-filter-fingerprint'
-  s.version         = '3.2.3'
+  s.version         = '3.3.2'
   s.licenses        = ['Apache-2.0']
   s.summary         = "Fingerprints fields by replacing values with a consistent hash"
   s.description     = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program"
@@ -23,5 +23,6 @@ Gem::Specification.new do |s|
   s.add_runtime_dependency "logstash-core-plugin-api", ">= 1.60", "<= 2.99"
   s.add_runtime_dependency "murmurhash3"                      #(MIT license)
   s.add_development_dependency 'logstash-devutils'
+  s.add_runtime_dependency 'logstash-mixin-ecs_compatibility_support', '~>1.2'
 end
 

data/spec/filters/fingerprint_spec.rb

@@ -1,287 +1,319 @@
 # encoding: utf-8
 require "logstash/devutils/rspec/spec_helper"
 require "logstash/filters/fingerprint"
+require 'logstash/plugin_mixins/ecs_compatibility_support/spec_helper'
 
-describe LogStash::Filters::Fingerprint do
+describe LogStash::Filters::Fingerprint, :ecs_compatibility_support, :aggregate_failures do
+  ecs_compatibility_matrix(:disabled, :v1, :v8 => :v1) do |ecs_select|
 
-  let(:plugin) { described_class.new(config) }
-  let(:config) { { "method" => fingerprint_method } }
-  let(:fingerprint_method) { "SHA1" } # default
-  let(:data) { {} }
-  let(:event) { LogStash::Event.new(data) }
-  let(:fingerprint) { event.get("fingerprint") }
+    let(:plugin) { described_class.new(config) }
+    let(:config) { { "method" => fingerprint_method } }
+    let(:fingerprint_method) { "SHA1" } # default
+    let(:data) { {} }
+    let(:event) { LogStash::Event.new(data) }
+    let(:fingerprint) { event.get(ecs_select[disabled: "fingerprint", v1: "[event][hash]"]) }
 
-  before(:each) do
-    plugin.register
-    plugin.filter(event)
-  end
+    before(:each) do
+      allow_any_instance_of(described_class).to receive(:ecs_compatibility).and_return(ecs_compatibility)
+      plugin.register
+      plugin.filter(event)
+    end
 
-  context "with a string field" do
-    let(:data) { {"clientip" => "123.123.123.123" } }
-    let(:config) { super().merge("source" => ["clientip" ]) }
+    context "with a string field" do
+      let(:data) { {"clientip" => "123.123.123.123" } }
+      let(:config) { super().merge("source" => ["clientip" ]) }
 
-    describe "the IPV4_NETWORK method" do
-      let(:fingerprint_method) { "IPV4_NETWORK" }
-      let(:config) { super().merge("key" => 24) }
+      describe "the IPV4_NETWORK method" do
+        let(:fingerprint_method) { "IPV4_NETWORK" }
+        let(:config) { super().merge("key" => 24) }
 
-      it "fingerprints the ip as the network" do
-        expect(fingerprint).to eq("123.123.123.0")
+        it "fingerprints the ip as the network" do
+          expect(fingerprint).to eq("123.123.123.0")
+        end
       end
-    end
 
-    describe "the MURMUR3 method" do
-      let(:fingerprint_method) { "MURMUR3" }
+      describe "the MURMUR3 method" do
+        let(:fingerprint_method) { "MURMUR3" }
 
-      it "fingerprints the value" do
-        expect(fingerprint).to eq(4013733395)
-      end
-    end
+        context "string" do
+          it "fingerprints the value" do
+            expect(fingerprint).to eq(4013733395)
+          end
+        end
 
-    describe "the SHA1 method" do
-      let(:fingerprint_method) { "SHA1" }
+        context "number" do
+          let(:data) { {"clientip" => 123 } }
 
-      it "fingerprints the value" do
-        expect(fingerprint).to eq("3a5076c520b4b463f43806896ea0b3978d09dcae")
+          it "fingerprints the value" do
+            expect(fingerprint).to eq(823512154)
+          end
+        end
       end
 
-      context "with HMAC" do
-        let(:config) { super().merge("key" => "longencryptionkey") }
+      describe "the SHA1 method" do
+        let(:fingerprint_method) { "SHA1" }
 
         it "fingerprints the value" do
-          expect(fingerprint).to eq("fdc60acc4773dc5ac569ffb78fcb93c9630797f4")
+          expect(fingerprint).to eq("3a5076c520b4b463f43806896ea0b3978d09dcae")
         end
-        context "with HMAC and base64 encoding" do
-          let(:config) { super().merge("base64encode" => true) }
+
+        context "with HMAC" do
+          let(:config) { super().merge("key" => "longencryptionkey") }
+
           it "fingerprints the value" do
-            expect(fingerprint).to eq("/cYKzEdz3FrFaf+3j8uTyWMHl/Q=")
+            expect(fingerprint).to eq("fdc60acc4773dc5ac569ffb78fcb93c9630797f4")
+          end
+          context "with HMAC and base64 encoding" do
+            let(:config) { super().merge("base64encode" => true) }
+            it "fingerprints the value" do
+              expect(fingerprint).to eq("/cYKzEdz3FrFaf+3j8uTyWMHl/Q=")
+            end
           end
         end
-      end
-      context "and base64 encoding" do
-        let(:config) { super().merge("base64encode" => true) }
-        it "fingerprints the value" do
-          expect(fingerprint).to eq("OlB2xSC0tGP0OAaJbqCzl40J3K4=")
+        context "and base64 encoding" do
+          let(:config) { super().merge("base64encode" => true) }
+          it "fingerprints the value" do
+            expect(fingerprint).to eq("OlB2xSC0tGP0OAaJbqCzl40J3K4=")
+          end
         end
       end
-    end
 
-    context "the SHA256 algorithm" do
-      let(:fingerprint_method) { "SHA256" }
-      it "fingerprints the value" do
-        expect(fingerprint).to eq("4dabcab210766e35f03e77120e6986d6e6d4752b2a9ff22980b9253d026080d8")
-      end
-      context "with HMAC" do
-        let(:config) { super().merge("key" => "longencryptionkey") }
+      context "the SHA256 algorithm" do
+        let(:fingerprint_method) { "SHA256" }
         it "fingerprints the value" do
-          expect(fingerprint).to eq("345bec3eff242d53b568916c2610b3e393d885d6b96d643f38494fd74bf4a9ca")
+          expect(fingerprint).to eq("4dabcab210766e35f03e77120e6986d6e6d4752b2a9ff22980b9253d026080d8")
         end
-        context "and base64 encoding" do
-          let(:config) { super().merge("base64encode" => true) }
+        context "with HMAC" do
+          let(:config) { super().merge("key" => "longencryptionkey") }
           it "fingerprints the value" do
-            expect(fingerprint).to eq("NFvsPv8kLVO1aJFsJhCz45PYhda5bWQ/OElP10v0qco=")
+            expect(fingerprint).to eq("345bec3eff242d53b568916c2610b3e393d885d6b96d643f38494fd74bf4a9ca")
+          end
+          context "and base64 encoding" do
+            let(:config) { super().merge("base64encode" => true) }
+            it "fingerprints the value" do
+              expect(fingerprint).to eq("NFvsPv8kLVO1aJFsJhCz45PYhda5bWQ/OElP10v0qco=")
+            end
           end
         end
       end
-    end
 
-    context "the SHA384 algorithm" do
-      let(:fingerprint_method) { "SHA384" }
-      it "fingerprints the value" do
-        expect(fingerprint).to eq("fd605b0a3af3e04ce0d7a0b0d9c48d67a12dab811f60072e6eae84e35d567793ffb68a1807536f11c90874065c2a4392")
-      end
-      context "with HMAC" do
-        let(:config) { super().merge("key" => "longencryptionkey") }
+      context "the SHA384 algorithm" do
+        let(:fingerprint_method) { "SHA384" }
         it "fingerprints the value" do
-          expect(fingerprint).to eq("22d4c0e8c4fbcdc4887d2038fca7650f0e2e0e2457ff41c06eb2a980dded6749561c814fe182aff93e2538d18593947a")
+          expect(fingerprint).to eq("fd605b0a3af3e04ce0d7a0b0d9c48d67a12dab811f60072e6eae84e35d567793ffb68a1807536f11c90874065c2a4392")
         end
-        context "and base64 encoding" do
-          let(:config) { super().merge("base64encode" => true) }
+        context "with HMAC" do
+          let(:config) { super().merge("key" => "longencryptionkey") }
           it "fingerprints the value" do
-            expect(fingerprint).to eq("ItTA6MT7zcSIfSA4/KdlDw4uDiRX/0HAbrKpgN3tZ0lWHIFP4YKv+T4lONGFk5R6")
+            expect(fingerprint).to eq("22d4c0e8c4fbcdc4887d2038fca7650f0e2e0e2457ff41c06eb2a980dded6749561c814fe182aff93e2538d18593947a")
+          end
+          context "and base64 encoding" do
+            let(:config) { super().merge("base64encode" => true) }
+            it "fingerprints the value" do
+              expect(fingerprint).to eq("ItTA6MT7zcSIfSA4/KdlDw4uDiRX/0HAbrKpgN3tZ0lWHIFP4YKv+T4lONGFk5R6")
+            end
           end
         end
       end
-    end
-    context "the SHA512 algorithm" do
-      let(:fingerprint_method) { "SHA512" }
-      it "fingerprints the value" do
-        expect(fingerprint).to eq("5468e2dc64ea92b617782aae884b35af60041ac9e168a283615b6a462c54c13d42fa9542cce9b7d76a8124ac6616818905e3e5dd35d6e519f77c3b517558639a")
-      end
-      context "with HMAC" do
-        let(:config) { super().merge("key" => "longencryptionkey") }
+      context "the SHA512 algorithm" do
+        let(:fingerprint_method) { "SHA512" }
         it "fingerprints the value" do
-          expect(fingerprint).to eq("11c19b326936c08d6c50a3c847d883e5a1362e6a64dd55201a25f2c1ac1b673f7d8bf15b8f112a4978276d573275e3b14166e17246f670c2a539401c5bfdace8")
+          expect(fingerprint).to eq("5468e2dc64ea92b617782aae884b35af60041ac9e168a283615b6a462c54c13d42fa9542cce9b7d76a8124ac6616818905e3e5dd35d6e519f77c3b517558639a")
         end
-        context "and base64 encoding" do
-          let(:config) { super().merge("base64encode" => true) }
+        context "with HMAC" do
+          let(:config) { super().merge("key" => "longencryptionkey") }
           it "fingerprints the value" do
-            expect(fingerprint).to eq("EcGbMmk2wI1sUKPIR9iD5aE2Lmpk3VUgGiXywawbZz99i/FbjxEqSXgnbVcydeOxQWbhckb2cMKlOUAcW/2s6A==")
+            expect(fingerprint).to eq("11c19b326936c08d6c50a3c847d883e5a1362e6a64dd55201a25f2c1ac1b673f7d8bf15b8f112a4978276d573275e3b14166e17246f670c2a539401c5bfdace8")
+          end
+          context "and base64 encoding" do
+            let(:config) { super().merge("base64encode" => true) }
+            it "fingerprints the value" do
+              expect(fingerprint).to eq("EcGbMmk2wI1sUKPIR9iD5aE2Lmpk3VUgGiXywawbZz99i/FbjxEqSXgnbVcydeOxQWbhckb2cMKlOUAcW/2s6A==")
+            end
           end
         end
       end
-    end
-    context "the MD5 algorithm" do
-      let(:fingerprint_method) { "MD5" }
-      it "fingerprints the value" do
-        expect(fingerprint).to eq("ccdd8d3d940a01b2fb3258c059924c0d")
-      end
-      context "with HMAC" do
-        let(:config) { super().merge("key" => "longencryptionkey") }
+      context "the MD5 algorithm" do
+        let(:fingerprint_method) { "MD5" }
         it "fingerprints the value" do
-          expect(fingerprint).to eq("9336c879e305c9604a3843fc3e75948f")
+          expect(fingerprint).to eq("ccdd8d3d940a01b2fb3258c059924c0d")
         end
-        context "and base64 encoding" do
-          let(:config) { super().merge("base64encode" => true) }
+        context "with HMAC" do
+          let(:config) { super().merge("key" => "longencryptionkey") }
           it "fingerprints the value" do
-            expect(fingerprint).to eq("kzbIeeMFyWBKOEP8PnWUjw==")
+            expect(fingerprint).to eq("9336c879e305c9604a3843fc3e75948f")
+          end
+          context "and base64 encoding" do
+            let(:config) { super().merge("base64encode" => true) }
+            it "fingerprints the value" do
+              expect(fingerprint).to eq("kzbIeeMFyWBKOEP8PnWUjw==")
+            end
           end
         end
       end
     end
-  end
 
-  context "multiple values in the source field" do
-    let(:config) { super().merge("source" => ["clientip" ]) }
-    let(:data) { { "clientip" => [ "123.123.123.123", "223.223.223.223" ] } }
+    context "multiple values in the source field" do
+      let(:config) { super().merge("source" => ["clientip" ]) }
+      let(:data) { { "clientip" => [ "123.123.123.123", "223.223.223.223" ] } }
 
-    it "produces a fingerprint array" do
-      expect(fingerprint).to eq(["3a5076c520b4b463f43806896ea0b3978d09dcae", "47bbc4e06edebbace047fed35abeceec64968b81"])
+      it "produces a fingerprint array" do
+        expect(fingerprint).to eq(["3a5076c520b4b463f43806896ea0b3978d09dcae", "47bbc4e06edebbace047fed35abeceec64968b81"])
+      end
     end
-  end
 
-  describe "concatenate_all_fields" do
-    let(:config) { { "concatenate_all_fields" => true } }
-    # The @timestamp field is specified in this sample event as we need the event contents to be constant for the tests
-    let(:data) do
-      { "@timestamp" => "2017-07-26T14:44:27.064Z", "clientip" => "123.123.123.123", "message" => "This is a test message", "log_level" => "INFO", "offset" => 123456789, "type" => "test" }
-    end
+    describe "concatenate_all_fields" do
+      let(:config) { { "concatenate_all_fields" => true } }
+      # The @timestamp field is specified in this sample event as we need the event contents to be constant for the tests
+      let(:data) do
+        { "@timestamp" => "2017-07-26T14:44:27.064Z", "clientip" => "123.123.123.123", "message" => "This is a test message", "log_level" => "INFO", "offset" => 123456789, "type" => "test" }
+      end
 
-    it "fingerprints the concatenated values" do
-      expect(fingerprint).to eq("cbf022518e97860403160ed8a41847c0db104e63")
+      it "fingerprints the concatenated values" do
+        expect(fingerprint).to eq("cbf022518e97860403160ed8a41847c0db104e63")
+      end
     end
-  end
 
-  context "when multiple fields are used" do
-    let(:config) { super().merge("source" => ['field1', 'field2']) }
-    let(:data) { { "field1" => "test1", "field2" => "test2" } }
+    context "when multiple fields are used" do
+      let(:config) { super().merge("source" => ['field1', 'field2']) }
+      let(:data) { { "field1" => "test1", "field2" => "test2" } }
 
-    it "fingerprints the value of the last value" do
-      # SHA1 of "test2"
-      expect(fingerprint).to eq("109f4b3c50d7b0df729d299bc6f8e9ef9066971f")
-    end
+      it "fingerprints the value of the last value" do
+        # SHA1 of "test2"
+        expect(fingerprint).to eq("109f4b3c50d7b0df729d299bc6f8e9ef9066971f")
+      end
 
-    describe "with concatenate_sources" do
-      let(:config) { super().merge("concatenate_sources" => true) }
-      it "fingerprints the value of concatenated key/pairs" do
-        # SHA1 of "|field1|test1|field2|test2|"
-        expect(fingerprint).to eq("e3b6b71eedc656f1d29408264e8a75535db985cb")
+      describe "with concatenate_sources" do
+        let(:config) { super().merge("concatenate_sources" => true) }
+        it "fingerprints the value of concatenated key/pairs" do
+          # SHA1 of "|field1|test1|field2|test2|"
+          expect(fingerprint).to eq("e3b6b71eedc656f1d29408264e8a75535db985cb")
+        end
       end
     end
-  end
 
-  describe "PUNCTUATION method" do
-    let(:fingerprint_method) { 'PUNCTUATION' }
-    let(:config) { super().merge("source" => 'field1') }
-    let(:data) { { "field1" =>  "PHP Warning:  json_encode() [<a href='function.json-encode'>function.json-encode</a>]: Invalid UTF-8 sequence in argument in /var/www/htdocs/test.php on line 233" } }
+    context "when utf-8 chars used" do
+      let(:config) { super().merge("source" => ['field1', 'field2']) }
+      let(:data) { {"field1"=>[{"inner_key"=>"🂡"}, {"1"=>"2"}], "field2"=>"🂡"} }
+      it "fingerprints the value of the last value" do
+        # SHA1 of "|field1|inner_key|🂡|1|2|field2|🂡|"
+        expect(fingerprint).to eq("58fa9e0e60c9f0d24b51d84cddb26732a39eeb3d")
+      end
 
-    it "extracts punctiation as the fingerprint" do
-      expect(fingerprint).to eq(":_()[<='.-'>.-</>]:-////.")
+      describe "with concatenate_sources" do
+        let(:config) { super().merge("concatenate_sources" => true) }
+        it "fingerprints the value of concatenated key/pairs" do
+          # SHA1 of "|field1|inner_key|🂡|1|2|field2|🂡|"
+          expect(fingerprint).to eq("d74f41841c7cdc793a97c218d2ff18064a5f1950")
+        end
+      end
     end
-  end
 
-  context 'Timestamps' do
-    epoch_time = Time.at(0).gmtime
-    let(:config) { super().merge("source" => ['@timestamp']) }
+    describe "PUNCTUATION method" do
+      let(:fingerprint_method) { 'PUNCTUATION' }
+      let(:config) { super().merge("source" => 'field1') }
+      let(:data) { { "field1" =>  "PHP Warning:  json_encode() [<a href='function.json-encode'>function.json-encode</a>]: Invalid UTF-8 sequence in argument in /var/www/htdocs/test.php on line 233" } }
 
-    describe 'OpenSSL Fingerprinting' do
-      let(:config) { super().merge("key" => '0123') }
-      let(:fingerprint_method) { "SHA1" }
-      let(:data) { { "@timestamp" => epoch_time } }
-      it "fingerprints the timestamp correctly" do
-        expect(fingerprint).to eq('1d5379ec92d86a67cfc642d55aa050ca312d3b9a')
+      it "extracts punctiation as the fingerprint" do
+        expect(fingerprint).to eq(":_()[<='.-'>.-</>]:-////.")
       end
     end
 
-    describe 'MURMUR3 Fingerprinting' do
-      let(:fingerprint_method) { "MURMUR3" }
-      let(:data) { { "@timestamp" => epoch_time } }
-      it "fingerprints the timestamp correctly" do
-        expect(fingerprint).to eq(743372282)
+    context 'Timestamps' do
+      epoch_time = Time.at(0).gmtime
+      let(:config) { super().merge("source" => ['@timestamp']) }
+
+      describe 'OpenSSL Fingerprinting' do
+        let(:config) { super().merge("key" => '0123') }
+        let(:fingerprint_method) { "SHA1" }
+        let(:data) { { "@timestamp" => epoch_time } }
+        it "fingerprints the timestamp correctly" do
+          expect(fingerprint).to eq('1d5379ec92d86a67cfc642d55aa050ca312d3b9a')
+        end
       end
-    end
-  end
 
-  describe "post fingerprint execution triggers" do
-    let(:fingerprint_method) { "PUNCTUATION" }
-    let(:config) do
-      {
-        "source" => 'field1',
-        "add_field" => { 'myfield' => 'myvalue' },
-        "add_tag" => ['mytag']
-      }
+      describe 'MURMUR3 Fingerprinting' do
+        let(:fingerprint_method) { "MURMUR3" }
+        let(:data) { { "@timestamp" => epoch_time } }
+        it "fingerprints the timestamp correctly" do
+          expect(fingerprint).to eq(743372282)
+        end
+      end
     end
-    let(:data) { { "field1" => "Hello, World!" } }
 
-    it "adds the new field" do
-      expect(event.get("myfield")).to eq("myvalue")
-    end
-    it "adds the new tag" do
-      expect(event.get("tags")).to include("mytag")
+    describe "post fingerprint execution triggers" do
+      let(:fingerprint_method) { "PUNCTUATION" }
+      let(:config) do
+        {
+          "source" => 'field1',
+          "add_field" => { 'myfield' => 'myvalue' },
+          "add_tag" => ['mytag']
+        }
+      end
+      let(:data) { { "field1" => "Hello, World!" } }
+
+      it "adds the new field" do
+        expect(event.get("myfield")).to eq("myvalue")
+      end
+      it "adds the new tag" do
+        expect(event.get("tags")).to include("mytag")
+      end
     end
-  end
 
-  describe "tolerance to hash order" do
-    # insertion order can influence the result of to_hash's keys
-    let(:data1) { {
+    describe "tolerance to hash order" do
+      # insertion order can influence the result of to_hash's keys
+      let(:data1) { {
         "a" => {"a0" => 0, "a1" => 1},
         "b" => {"b0" => 0, "b1" => 1},
-    } }
-    let(:event1) { LogStash::Event.new(data1) }
-    let(:data2) { {
+      } }
+      let(:event1) { LogStash::Event.new(data1) }
+      let(:data2) { {
         "b" => {"b1" => 1, "b0" => 0},
         "a" => {"a1" => 1, "a0" => 0},
-    } }
-    let(:event2) { LogStash::Event.new(data2) }
-    let(:config) { { "source" => [ "a" ] } }
+      } }
+      let(:event2) { LogStash::Event.new(data2) }
+      let(:config) { { "source" => [ "a" ] } }
 
-    before(:each) do
-      # for testing purposes we want to ensure the hash order is different.
-      # since we can't easily control the order on the underlying Map,
-      # we're mocking the order here:
-      allow(event1).to receive(:to_hash).and_return(data1)
-      allow(event2).to receive(:to_hash).and_return(data2)
-      # by default event.get(key) fetches data from the event.
-      # mocking the default value has to be done first, and only
-      # then we can mock the getting "a" and "b"
-      allow(event1).to receive(:get).and_call_original
-      allow(event2).to receive(:get).and_call_original
-      # mock event.get("a") and event.get("b") for both events
-      # so we can inject an inconsistent order for the tests
-      allow(event1).to receive(:get).with("a") {|arg| data1["a"] }
-      allow(event1).to receive(:get).with("b") {|arg| data1["b"] }
-      allow(event2).to receive(:get).with("a") {|arg| data2["a"] }
-      allow(event2).to receive(:get).with("b") {|arg| data2["b"] }
-      plugin.filter(event1)
-      plugin.filter(event2)
-    end
-    it "computes the same hash" do
-      # confirm the order of the keys in the nested hash is different
-      # (of course it is, we just mocked the to_hash return)
-      expect(event1.to_hash["a"].keys).to_not eq(event2.to_hash["a"].keys)
-      # let's check that the fingerprint doesn't care about the insertion order
-      expect(event1.get("fingerprint")).to eq(event2.get("fingerprint"))
-    end
-    context "concatenate_sources" do
-      let("config") { { "source" => [ "a", "b"], "concatenate_sources" => true } }
-      it "computes the same hash" do
-        expect(event1.get("fingerprint")).to eq(event2.get("fingerprint"))
+      before(:each) do
+        # for testing purposes we want to ensure the hash order is different.
+        # since we can't easily control the order on the underlying Map,
+        # we're mocking the order here:
+        allow(event1).to receive(:to_hash).and_return(data1)
+        allow(event2).to receive(:to_hash).and_return(data2)
+        # by default event.get(key) fetches data from the event.
+        # mocking the default value has to be done first, and only
+        # then we can mock the getting "a" and "b"
+        allow(event1).to receive(:get).and_call_original
+        allow(event2).to receive(:get).and_call_original
+        # mock event.get("a") and event.get("b") for both events
+        # so we can inject an inconsistent order for the tests
+        allow(event1).to receive(:get).with("a") {|arg| data1["a"] }
+        allow(event1).to receive(:get).with("b") {|arg| data1["b"] }
+        allow(event2).to receive(:get).with("a") {|arg| data2["a"] }
+        allow(event2).to receive(:get).with("b") {|arg| data2["b"] }
+        plugin.filter(event1)
+        plugin.filter(event2)
       end
-    end
-    context "concatenate_all_fields => true" do
-      let(:config) { { "concatenate_all_fields" => true } }
       it "computes the same hash" do
+        # confirm the order of the keys in the nested hash is different
+        # (of course it is, we just mocked the to_hash return)
+        expect(event1.to_hash["a"].keys).to_not eq(event2.to_hash["a"].keys)
+        # let's check that the fingerprint doesn't care about the insertion order
         expect(event1.get("fingerprint")).to eq(event2.get("fingerprint"))
       end
+      context "concatenate_sources" do
+        let("config") { { "source" => [ "a", "b"], "concatenate_sources" => true } }
+        it "computes the same hash" do
+          expect(event1.get("fingerprint")).to eq(event2.get("fingerprint"))
+        end
+      end
+      context "concatenate_all_fields => true" do
+        let(:config) { { "concatenate_all_fields" => true } }
+        it "computes the same hash" do
+          expect(event1.get("fingerprint")).to eq(event2.get("fingerprint"))
+        end
+      end
     end
+
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: logstash-filter-fingerprint
 version: !ruby/object:Gem::Version
-  version: 3.2.3
+  version: 3.3.2
 platform: ruby
 authors:
 - Elastic
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-03-11 00:00:00.000000000 Z
+date: 2021-07-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
@@ -58,6 +58,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+  name: logstash-mixin-ecs_compatibility_support
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
 description: This gem is a Logstash plugin required to be installed on top of the
   Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This
   gem is not a stand-alone program