Fix asset test runner

internal/packages/assets.go

@@ -5,11 +5,11 @@
 package packages
 
 import (
+	"encoding/json"
 	"fmt"
 	"io/ioutil"
 	"os"
 	"path/filepath"
-	"strings"
 
 	"github.com/pkg/errors"
 
@@ -38,6 +38,11 @@ type Asset struct {
 	DataStream string
 }
 
+// String method returns a string representation of the asset
+func (asset Asset) String() string {
+	return fmt.Sprintf("%s (type: %s)", asset.ID, asset.Type)
+}
+
 // LoadPackageAssets parses the package contents and returns a list of assets defined by the package.
 func LoadPackageAssets(pkgRootPath string) ([]Asset, error) {
 	assets, err := loadKibanaAssets(pkgRootPath)
@@ -116,6 +121,12 @@ func loadElasticsearchAssets(pkgRootPath string) ([]Asset, error) {
 		assets = append(assets, asset)
 
 		if dsManifest.Type == dataStreamTypeLogs {
+			elasticsearchDirPath := filepath.Join(filepath.Dir(dsManifestPath), "elasticsearch", "ingest_pipeline")
+			pipelineFiles, _ := ioutil.ReadDir(elasticsearchDirPath)
+			if pipelineFiles == nil || len(pipelineFiles) == 0 {
+				continue // ingest pipeline is not defined
+			}
+
 			ingestPipelineName := dsManifest.GetPipelineNameOrDefault()
 			if ingestPipelineName == defaultPipelineName {
 				ingestPipelineName = fmt.Sprintf("%s-%s.%s-%s", dsManifest.Type, pkgManifest.Name, dsManifest.Name, pkgManifest.Version)
@@ -154,15 +165,39 @@ func loadFileBasedAssets(kibanaAssetsFolderPath string, assetType AssetType) ([]
 			continue
 		}
 
-		name := f.Name()
-		id := strings.TrimSuffix(name, ".json")
+		assetPath := filepath.Join(assetsFolderPath, f.Name())
+		assetID, err := readAssetID(assetPath)
+		if err != nil {
+			return nil, errors.Wrapf(err, "can't read asset ID (path: %s)", assetPath)
+		}
 
 		asset := Asset{
-			ID:   id,
+			ID:   assetID,
 			Type: assetType,
 		}
 		assets = append(assets, asset)
 	}
 
 	return assets, nil
 }
+
+func readAssetID(assetPath string) (string, error) {
+	content, err := ioutil.ReadFile(assetPath)
+	if err != nil {
+		return "", errors.Wrap(err, "can't read file body")
+	}
+
+	assetBody := struct {
+		ID string `json:"id"`
+	}{}
+
+	err = json.Unmarshal(content, &assetBody)
+	if err != nil {
+		return "", errors.Wrap(err, "can't unmarshal asset")
+	}
+
+	if assetBody.ID == "" {
+		return "", errors.New("empty asset ID")
+	}
+	return assetBody.ID, nil
+}

internal/testrunner/runners/asset/runner.go

@@ -7,6 +7,7 @@ package asset
 import (
 	"fmt"
 	"path/filepath"
+	"strings"
 	"time"
 
 	es "github.com/elastic/go-elasticsearch/v7"
@@ -125,7 +126,7 @@ func (r *runner) run() ([]testrunner.TestResult, error) {
 
 		if !findActualAsset(actualAssets, e) {
 			result.FailureMsg = "could not find expected asset"
-			result.FailureDetails = fmt.Sprintf("could not find expected asset with ID = %s and type = %s. Assets loaded = %v", e.ID, e.Type, actualAssets)
+			result.FailureDetails = fmt.Sprintf("could not find %s asset \"%s\". Assets loaded:\n%s", e.Type, e.ID, formatAssetsAsString(actualAssets))
 		}
 
 		results = append(results, result)
@@ -154,3 +155,11 @@ func findActualAsset(actualAssets []packages.Asset, expectedAsset packages.Asset
 
 	return false
 }
+
+func formatAssetsAsString(assets []packages.Asset) string {
+	var sb strings.Builder
+	for _, asset := range assets {
+		sb.WriteString(fmt.Sprintf("- %s\n", asset.String()))
+	}
+	return sb.String()
+}

test/packages/log/data_stream/log/agent/stream/stream.yml.hbs

@@ -0,0 +1,9 @@
+paths:
+{{#each paths}}
+  - {{this}}
+{{/each}}
+
+data_stream:
+  dataset: {{data_stream.dataset}}
+
+{{custom}}

test/packages/log/data_stream/log/fields/agent.yml

@@ -0,0 +1,198 @@
+- 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.
+
+        Examples: AWS account id, Google Cloud ORG Id, or other unique identifier.'
+      example: 666777888999
+    - name: availability_zone
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Availability zone in which this host is running.
+      example: us-east-1c
+    - name: instance.id
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Instance ID of the host machine.
+      example: i-1234567890abcdef0
+    - name: instance.name
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Instance name of the host machine.
+    - name: machine.type
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Machine type of the host machine.
+      example: t2.medium
+    - 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
+    - name: region
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Region in which this host is running.
+      example: us-east-1
+    - name: project.id
+      type: keyword
+      description: Name of the project in Google Cloud.
+    - 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.
+
+    These 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.
+    - name: image.name
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Name of the image the container was built on.
+    - name: labels
+      level: extended
+      type: object
+      object_type: keyword
+      description: Image labels.
+    - name: name
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Container name.
+- name: host
+  title: Host
+  group: 2
+  description: 'A host is defined as a general computing instance.
+
+    ECS 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
+    - name: domain
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: 'Name of the domain of which the host is a member.
+
+        For 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
+    - name: hostname
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Hostname of the host.
+
+        It normally contains what the `hostname` command returns on the host machine.'
+    - name: id
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Unique host id.
+
+        As hostname is not always unique, use values that are meaningful in your environment.
+
+        Example: The current usage of `beat.name`.'
+    - name: ip
+      level: core
+      type: ip
+      description: Host ip addresses.
+    - name: mac
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: Host mac addresses.
+    - name: name
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Name of the host.
+
+        It 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.'
+    - name: os.family
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: OS family (such as redhat, debian, freebsd, windows).
+      example: debian
+    - 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
+    - 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
+    - name: os.platform
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Operating system platform (such centos, ubuntu, windows).
+      example: darwin
+    - name: os.version
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Operating system version as a raw string.
+      example: 10.14.1
+    - name: type
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Type of host.
+
+        For 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.'
+    - name: containerized
+      type: boolean
+      description: >
+        If the host is a container.
+
+    - name: os.build
+      type: keyword
+      example: "18D109"
+      description: >
+        OS build information.
+
+    - name: os.codename
+      type: keyword
+      example: "stretch"
+      description: >
+        OS codename, if any.
+

test/packages/log/data_stream/log/fields/base-fields.yml

@@ -0,0 +1,12 @@
+- name: data_stream.type
+  type: constant_keyword
+  description: Data stream type.
+- name: data_stream.dataset
+  type: constant_keyword
+  description: Data stream dataset.
+- name: data_stream.namespace
+  type: constant_keyword
+  description: Data stream namespace.
+- name: '@timestamp'
+  type: date
+  description: Event timestamp.

test/packages/log/data_stream/log/manifest.yml

@@ -0,0 +1,28 @@
+title: Log Dataset
+type: logs
+streams:
+  - input: logfile
+    description: Collect your custom log files.
+    title: Collect log files
+    vars:
+      - name: paths
+        required: true
+        title: Log file path
+        description: Path to log files to be collected
+        type: text
+        multi: true
+      - name: data_stream.dataset
+        required: true
+        default: generic
+        title: Dataset name
+        description: >
+          Set the name for your dataset. Changing the dataset will send the data to a different index. You can't use `-` in the name of a dataset and only valid characters for [Elasticsearch index names](https://www.elastic.co/guide/en/elasticsearch/reference/current/docs-index_.html).
+
+        type: text
+      - name: custom
+        title: Custom configurations
+        description: >
+          Here YAML configuration options can be used to be added to your configuration. Be careful using this as it might break your configuration file.
+
+        type: yaml
+        default: ""

test/packages/log/docs/README.md

@@ -0,0 +1,3 @@
+# Log Package
+
+The log package is used as a generic package based on which any log file can be tailed by adjusting the ingest pipeline.

test/packages/log/manifest.yml

@@ -0,0 +1,25 @@
+format_version: 1.0.0
+name: log
+title: Custom logs
+description: >
+  Collect your custom logs.
+
+type: integration
+version: 0.4.6
+release: experimental
+license: basic
+categories:
+  - custom
+policy_templates:
+  - name: logs
+    title: Custom logs
+    description: Collect your custom log files.
+    inputs:
+      - type: logfile
+        title: Custom log file
+        description: Collect your custom log files.
+icons:
+  - src: "/img/icon.svg"
+    type: "image/svg+xml"
+owner:
+  github: elastic/integrations-services