[elastic_agent] - Cleanup fields.yml issues (#8079)

For fields that exist in ECS use 'external: ecs' in the field definition.

Remove attributes from field definitions that have no purpose (like footnote, level, title, etc).

Fix typo for description attribute in some field definitions.

Remove duplicate definitions of fields within the same data stream.

Fix dotted YAML key in manifest.yml.

[git-generate]
cd packages/elastic_agent
go run github.com/andrewkroh/fydler@90f7b627e -fix -a useecs,invalidattribute,unknownattribute **/fields/*.yml
perl -p -i -e 's/descripion:/description:/g' **/fields/*.yml
elastic-package format
elastic-package changelog add --link #8079 --type enhancement --next minor --description "Modified the field definitions to reference ECS where possible and remove invalid field attributes."

Author: andrewkroh

packages/elastic_agent/changelog.yml

@@ -1,4 +1,9 @@
 # newer versions go on top
+- version: "1.14.0"
+  changes:
+    - description: Modify field mappings to reference ECS fields where possible and remove duplicate field declarations.
+      type: enhancement
+      link: https://github.com/elastic/integrations/pull/8079
 - version: "1.13.1"
   changes:
     - description: Fix mapping and description for the `system.process.cpu.{system,user,total}.time.ms` fields.

packages/elastic_agent/data_stream/apm_server_logs/fields/agent.yml

@@ -1,166 +1,65 @@
 - name: cloud
-  title: Cloud
-  group: 2
-  description: Fields related to the cloud or infrastructure the events are coming from.
-  footnote: "Examples: If Metricbeat is running on an EC2 host and fetches data from its host, the cloud info contains the data about this machine. If Metricbeat runs on a remote machine outside the cloud and fetches data from a service running in the cloud, the field contains cloud data from the machine the service is running on."
   type: group
   fields:
     - name: account.id
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: "The cloud account or organization id used to identify different entities in a multi-tenant environment.\nExamples: AWS account id, Google Cloud ORG Id, or other unique identifier."
-      example: 666777888999
+      external: ecs
     - name: availability_zone
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Availability zone in which this host is running.
-      example: us-east-1c
+      external: ecs
     - name: instance.id
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Instance ID of the host machine.
-      example: i-1234567890abcdef0
+      external: ecs
     - name: instance.name
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Instance name of the host machine.
+      external: ecs
     - name: machine.type
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Machine type of the host machine.
-      example: t2.medium
+      external: ecs
     - name: provider
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Name of the cloud provider. Example values are aws, azure, gcp, or digitalocean.
-      example: aws
+      external: ecs
     - name: region
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Region in which this host is running.
-      example: us-east-1
+      external: ecs
     - name: project.id
-      type: keyword
-      description: Name of the project in Google Cloud.
+      external: ecs
     - name: image.id
       type: keyword
       description: Image ID for the cloud instance.
 - name: container
-  title: Container
-  group: 2
-  description: "Container fields are used for meta information about the specific container that is the source of information.\nThese fields help correlate data based containers from any runtime."
   type: group
   fields:
     - name: id
-      level: core
-      type: keyword
-      ignore_above: 1024
-      description: Unique container id.
+      external: ecs
     - name: image.name
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Name of the image the container was built on.
+      external: ecs
     - name: labels
-      level: extended
-      type: object
-      object_type: keyword
-      description: Image labels.
+      external: ecs
     - name: name
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Container name.
+      external: ecs
 - name: host
-  title: Host
-  group: 2
-  description: "A host is defined as a general computing instance.\nECS host.* fields should be populated with details about the host on which the event happened, or from which the measurement was taken. Host types include hardware, virtual machines, Docker containers, and Kubernetes nodes."
   type: group
   fields:
     - name: architecture
-      level: core
-      type: keyword
-      ignore_above: 1024
-      description: Operating system architecture.
-      example: x86_64
+      external: ecs
     - name: domain
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: "Name of the domain of which the host is a member.\nFor example, on Windows this could be the host's Active Directory domain or NetBIOS domain name. For Linux this could be the domain of the host's LDAP provider."
-      example: CONTOSO
-      default_field: false
+      external: ecs
     - name: hostname
-      level: core
-      type: keyword
-      ignore_above: 1024
-      description: "Hostname of the host.\nIt normally contains what the `hostname` command returns on the host machine."
+      external: ecs
     - name: id
-      level: core
-      type: keyword
-      ignore_above: 1024
-      description: "Unique host id.\nAs hostname is not always unique, use values that are meaningful in your environment.\nExample: The current usage of `beat.name`."
+      external: ecs
     - name: ip
-      level: core
-      type: ip
-      description: Host ip addresses.
+      external: ecs
     - name: mac
-      level: core
-      type: keyword
-      ignore_above: 1024
-      description: Host mac addresses.
+      external: ecs
     - name: name
-      level: core
-      type: keyword
-      ignore_above: 1024
-      description: "Name of the host.\nIt can contain what `hostname` returns on Unix systems, the fully qualified domain name, or a name specified by the user. The sender decides which value to use."
+      external: ecs
     - name: os.family
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: OS family (such as redhat, debian, freebsd, windows).
-      example: debian
+      external: ecs
     - name: os.kernel
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Operating system kernel version as a raw string.
-      example: 4.4.0-112-generic
+      external: ecs
     - name: os.name
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      multi_fields:
-        - name: text
-          type: text
-          norms: false
-          default_field: false
-      description: Operating system name, without the version.
-      example: Mac OS X
+      external: ecs
     - name: os.platform
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Operating system platform (such centos, ubuntu, windows).
-      example: darwin
+      external: ecs
     - name: os.version
-      level: extended
-      type: keyword
-      ignore_above: 1024
-      description: Operating system version as a raw string.
-      example: 10.14.1
+      external: ecs
     - name: type
-      level: core
-      type: keyword
-      ignore_above: 1024
-      description: "Type of host.\nFor Cloud providers this can be the machine type like `t2.medium`. If vm, this could be the container, for example, or other information meaningful in your environment."
+      external: ecs
     - name: containerized
       type: boolean
       description: >

packages/elastic_agent/data_stream/apm_server_logs/fields/base-fields.yml

@@ -1,15 +1,11 @@
 - name: data_stream.type
-  type: constant_keyword
-  description: Data stream type.
+  external: ecs
 - name: data_stream.dataset
-  type: constant_keyword
-  description: Data stream dataset.
+  external: ecs
 - name: data_stream.namespace
-  type: constant_keyword
-  description: Data stream namespace.
+  external: ecs
 - name: "@timestamp"
-  type: date
-  description: Event timestamp.
+  external: ecs
 - name: event.dataset
   type: constant_keyword
-  description: Event dataset
+  external: ecs

packages/elastic_agent/data_stream/apm_server_logs/fields/fields.yml

@@ -1,8 +1,6 @@
 - name: message
   external: ecs
 - name: elastic_agent
-  title: Elastic Agent
-  description: Fields related to the Elastic Agents
   type: group
   fields:
     - name: id