[processor/k8sattributes] Support name:tag@digest image name format (open-telemetry#36145)

<!--Ex. Fixing a bug - Describe the bug and how this fixes the issue.
Ex. Adding a feature - Explain what this achieves.-->
#### Description
Fixed issue with `k8sattributesprocessor` where digest is not properly
separated from tag if both are present. used official docker library to
perform parsing.

<!-- Issue number (e.g. open-telemetry#1234) or full URL to issue, if applicable. -->
#### Link to tracking issue
Fixes
open-telemetry#36131

<!--Describe what testing was performed and which tests were added.-->
#### Testing
unit tests
integration/e2e tests

<!--Describe the documentation added.-->
#### Documentation
N/A. Fields are already described correctly, this is simply fixing
parsing logic

<!--Please delete paragraphs that you did not use before submitting.-->

Author: spiffyy99

.chloggen/fix-k8s-image-parsing.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: bug_fix
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: processor/k8sattribute
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: fixes parsing of k8s image names to support images with tags and digests.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [36131]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]

processor/k8sattributesprocessor/README.md

@@ -170,7 +170,7 @@ spec:
     - --duration=10s
     - --rate=1
     - --otlp-attributes=k8s.container.name="telemetrygen"
-    image: ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen:latest
+    image: ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen:0.112.0@sha256:b248ef911f93ae27cbbc85056d1ffacc87fd941bbdc2ffd951b6df8df72b8096
     name: telemetrygen
 status:
   podIP: 10.244.0.11
@@ -193,7 +193,8 @@ the processor associates the received trace to the pod, based on the connection
     "k8s.pod.name": "telemetrygen-pod",
     "k8s.pod.uid": "038e2267-b473-489b-b48c-46bafdb852eb",
     "container.image.name": "telemetrygen",
-    "container.image.tag": "latest"
+    "container.image.tag": "0.112.0", 
+    "container.image.repo_digests": ["ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen@sha256:b248ef911f93ae27cbbc85056d1ffacc87fd941bbdc2ffd951b6df8df72b8096"]
   }
 }
 ```

processor/k8sattributesprocessor/documentation.md

@@ -9,7 +9,7 @@
 | container.id | Container ID. Usually a UUID, as for example used to identify Docker containers. The UUID might be abbreviated. Requires k8s.container.restart_count. | Any Str | false |
 | container.image.name | Name of the image the container was built on. Requires container.id or k8s.container.name. | Any Str | true |
 | container.image.repo_digests | Repo digests of the container image as provided by the container runtime. | Any Slice | false |
-| container.image.tag | Container image tag. Requires container.id or k8s.container.name. | Any Str | true |
+| container.image.tag | Container image tag. Defaults to "latest" if not provided (unless digest also in image path) Requires container.id or k8s.container.name. | Any Str | true |
 | k8s.cluster.uid | Gives cluster uid identified with kube-system namespace | Any Str | false |
 | k8s.container.name | The name of the Container in a Pod template. Requires container.id. | Any Str | false |
 | k8s.cronjob.name | The name of the CronJob. | Any Str | false |

processor/k8sattributesprocessor/e2e_test.go

@@ -54,7 +54,7 @@ func newExpectedValue(mode int, value string) *expectedValue {
 
 // TestE2E_ClusterRBAC tests the k8s attributes processor in a k8s cluster with the collector's service account having
 // cluster-wide permissions to list/watch namespaces, nodes, pods and replicasets. The config in the test does not
-// set filter::namespace.
+// set filter::namespace, and the telemetrygen image has a latest tag but no digest.
 // The test requires a prebuilt otelcontribcol image uploaded to a kind k8s cluster defined in
 // `/tmp/kube-config-otelcol-e2e-testing`. Run the following command prior to running the test locally:
 //
@@ -540,7 +540,8 @@ func TestE2E_ClusterRBAC(t *testing.T) {
 	}
 }
 
-// Test with `filter::namespace` set and only role binding to collector's SA. We can't get node and namespace labels/annotations.
+// Test with `filter::namespace` set and only role binding to collector's SA. We can't get node and namespace labels/annotations,
+// and the telemetrygen image has a digest but no tag.
 func TestE2E_NamespacedRBAC(t *testing.T) {
 	testDir := filepath.Join("testdata", "e2e", "namespacedrbac")
 
@@ -615,7 +616,7 @@ func TestE2E_NamespacedRBAC(t *testing.T) {
 				"k8s.container.name":           newExpectedValue(equal, "telemetrygen"),
 				"container.image.name":         newExpectedValue(equal, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen"),
 				"container.image.repo_digests": newExpectedValue(regex, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen@sha256:[0-9a-fA-f]{64}"),
-				"container.image.tag":          newExpectedValue(equal, "latest"),
+				"container.image.tag":          newExpectedValue(shouldnotexist, ""),
 				"container.id":                 newExpectedValue(exist, ""),
 			},
 		},
@@ -639,7 +640,7 @@ func TestE2E_NamespacedRBAC(t *testing.T) {
 				"k8s.container.name":           newExpectedValue(equal, "telemetrygen"),
 				"container.image.name":         newExpectedValue(equal, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen"),
 				"container.image.repo_digests": newExpectedValue(regex, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen@sha256:[0-9a-fA-f]{64}"),
-				"container.image.tag":          newExpectedValue(equal, "latest"),
+				"container.image.tag":          newExpectedValue(shouldnotexist, ""),
 				"container.id":                 newExpectedValue(exist, ""),
 			},
 		},
@@ -663,7 +664,7 @@ func TestE2E_NamespacedRBAC(t *testing.T) {
 				"k8s.container.name":           newExpectedValue(equal, "telemetrygen"),
 				"container.image.name":         newExpectedValue(equal, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen"),
 				"container.image.repo_digests": newExpectedValue(regex, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen@sha256:[0-9a-fA-f]{64}"),
-				"container.image.tag":          newExpectedValue(equal, "latest"),
+				"container.image.tag":          newExpectedValue(shouldnotexist, ""),
 				"container.id":                 newExpectedValue(exist, ""),
 			},
 		},
@@ -712,7 +713,7 @@ func TestE2E_NamespacedRBAC(t *testing.T) {
 }
 
 // Test with `filter::namespace` set, role binding for namespace-scoped objects (pod, replicaset) and clusterrole
-// binding for node and namespace objects.
+// binding for node and namespace objects, and the telemetrygen image has a tag and digest.
 func TestE2E_MixRBAC(t *testing.T) {
 	testDir := filepath.Join("testdata", "e2e", "mixrbac")
 
@@ -802,7 +803,7 @@ func TestE2E_MixRBAC(t *testing.T) {
 				"k8s.container.name":           newExpectedValue(equal, "telemetrygen"),
 				"container.image.name":         newExpectedValue(equal, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen"),
 				"container.image.repo_digests": newExpectedValue(regex, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen@sha256:[0-9a-fA-f]{64}"),
-				"container.image.tag":          newExpectedValue(equal, "latest"),
+				"container.image.tag":          newExpectedValue(equal, "0.112.0"),
 				"container.id":                 newExpectedValue(exist, ""),
 				"k8s.namespace.labels.foons":   newExpectedValue(equal, "barns"),
 				"k8s.node.labels.foo":          newExpectedValue(equal, "too"),
@@ -829,7 +830,7 @@ func TestE2E_MixRBAC(t *testing.T) {
 				"k8s.container.name":           newExpectedValue(equal, "telemetrygen"),
 				"container.image.name":         newExpectedValue(equal, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen"),
 				"container.image.repo_digests": newExpectedValue(regex, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen@sha256:[0-9a-fA-f]{64}"),
-				"container.image.tag":          newExpectedValue(equal, "latest"),
+				"container.image.tag":          newExpectedValue(equal, "0.112.0"),
 				"container.id":                 newExpectedValue(exist, ""),
 				"k8s.namespace.labels.foons":   newExpectedValue(equal, "barns"),
 				"k8s.node.labels.foo":          newExpectedValue(equal, "too"),
@@ -856,7 +857,7 @@ func TestE2E_MixRBAC(t *testing.T) {
 				"k8s.container.name":           newExpectedValue(equal, "telemetrygen"),
 				"container.image.name":         newExpectedValue(equal, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen"),
 				"container.image.repo_digests": newExpectedValue(regex, "ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen@sha256:[0-9a-fA-f]{64}"),
-				"container.image.tag":          newExpectedValue(equal, "latest"),
+				"container.image.tag":          newExpectedValue(equal, "0.112.0"),
 				"container.id":                 newExpectedValue(exist, ""),
 				"k8s.namespace.labels.foons":   newExpectedValue(equal, "barns"),
 				"k8s.node.labels.foo":          newExpectedValue(equal, "too"),
@@ -914,7 +915,8 @@ func TestE2E_MixRBAC(t *testing.T) {
 // While `k8s.pod.ip` is not set in `k8sattributes:extract:metadata` and the `pod_association` is not `connection`
 // we expect that the `k8s.pod.ip` metadata is not added.
 // While `container.image.repo_digests` is not set in `k8sattributes::extract::metadata`, we expect
-// that the `container.image.repo_digests` metadata is not added
+// that the `container.image.repo_digests` metadata is not added.
+// The telemetrygen image has neither a tag nor digest (implicitly latest version)
 func TestE2E_NamespacedRBACNoPodIP(t *testing.T) {
 	testDir := filepath.Join("testdata", "e2e", "namespaced_rbac_no_pod_ip")
 

processor/k8sattributesprocessor/internal/kube/client.go

@@ -666,6 +666,30 @@ func removeUnnecessaryPodData(pod *api_v1.Pod, rules ExtractionRules) *api_v1.Po
 	return &transformedPod
 }
 
+// parseNameAndTagFromImage parses the image name and tag for differently-formatted image names.
+// returns "latest" as the default if tag not present. also checks if the image contains a digest.
+// if it does, no latest tag is assumed.
+func parseNameAndTagFromImage(image string) (name, tag string, err error) {
+	ref, err := reference.Parse(image)
+	if err != nil {
+		return
+	}
+	namedRef, ok := ref.(reference.Named)
+	if !ok {
+		return "", "", errors.New("cannot retrieve image name")
+	}
+	name = namedRef.Name()
+	if taggedRef, ok := namedRef.(reference.Tagged); ok {
+		tag = taggedRef.Tag()
+	}
+	if tag == "" {
+		if digestedRef, ok := namedRef.(reference.Digested); !ok || digestedRef.String() == "" {
+			tag = "latest"
+		}
+	}
+	return
+}
+
 func (c *WatchClient) extractPodContainersAttributes(pod *api_v1.Pod) PodContainers {
 	containers := PodContainers{
 		ByID:   map[string]*Container{},
@@ -677,16 +701,14 @@ func (c *WatchClient) extractPodContainersAttributes(pod *api_v1.Pod) PodContain
 	if c.Rules.ContainerImageName || c.Rules.ContainerImageTag {
 		for _, spec := range append(pod.Spec.Containers, pod.Spec.InitContainers...) {
 			container := &Container{}
-			nameTagSep := strings.LastIndex(spec.Image, ":")
-			if c.Rules.ContainerImageName {
-				if nameTagSep > 0 {
-					container.ImageName = spec.Image[:nameTagSep]
-				} else {
-					container.ImageName = spec.Image
+			name, tag, err := parseNameAndTagFromImage(spec.Image)
+			if err == nil {
+				if c.Rules.ContainerImageName {
+					container.ImageName = name
+				}
+				if c.Rules.ContainerImageTag {
+					container.ImageTag = tag
 				}
-			}
-			if c.Rules.ContainerImageTag && nameTagSep > 0 {
-				container.ImageTag = spec.Image[nameTagSep+1:]
 			}
 			containers.ByName[spec.Name] = container
 		}

processor/k8sattributesprocessor/internal/kube/client_test.go

@@ -1495,17 +1495,21 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 			Containers: []api_v1.Container{
 				{
 					Name:  "container1",
-					Image: "test/image1:0.1.0",
+					Image: "example.com:5000/test/image1:0.1.0",
 				},
 				{
 					Name:  "container2",
-					Image: "example.com:port1/image2:0.2.0",
+					Image: "example.com:81/image2@sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9",
+				},
+				{
+					Name:  "container3",
+					Image: "example-website.com/image3:1.0@sha256:4b0b1b6f6cdd3e5b9e55f74a1e8d19ed93a3f5a04c6b6c3c57c4e6d19f6b7c4d",
 				},
 			},
 			InitContainers: []api_v1.Container{
 				{
 					Name:  "init_container",
-					Image: "test/init-image:1.0.2",
+					Image: "test/init-image",
 				},
 			},
 		},
@@ -1520,7 +1524,13 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 				{
 					Name:         "container2",
 					ContainerID:  "docker://container2-id-456",
-					ImageID:      "sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9",
+					ImageID:      "sha256:4b0b1b6f6cdd3e5b9e55f74a1e8d19ed93a3f5a04c6b6c3c57c4e6d19f6b7c4d",
+					RestartCount: 2,
+				},
+				{
+					Name:         "container3",
+					ContainerID:  "docker://container3-id-abc",
+					ImageID:      "docker.io/otel/collector:2.0.0@sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9",
 					RestartCount: 2,
 				},
 			},
@@ -1564,13 +1574,15 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 			pod: &pod,
 			want: PodContainers{
 				ByID: map[string]*Container{
-					"container1-id-123":     {ImageName: "test/image1"},
-					"container2-id-456":     {ImageName: "example.com:port1/image2"},
+					"container1-id-123":     {ImageName: "example.com:5000/test/image1"},
+					"container2-id-456":     {ImageName: "example.com:81/image2"},
+					"container3-id-abc":     {ImageName: "example-website.com/image3"},
 					"init-container-id-789": {ImageName: "test/init-image"},
 				},
 				ByName: map[string]*Container{
-					"container1":     {ImageName: "test/image1"},
-					"container2":     {ImageName: "example.com:port1/image2"},
+					"container1":     {ImageName: "example.com:5000/test/image1"},
+					"container2":     {ImageName: "example.com:81/image2"},
+					"container3":     {ImageName: "example-website.com/image3"},
 					"init_container": {ImageName: "test/init-image"},
 				},
 			},
@@ -1615,6 +1627,11 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 							2: {ContainerID: "container2-id-456"},
 						},
 					},
+					"container3-id-abc": {
+						Statuses: map[int]ContainerStatus{
+							2: {ContainerID: "container3-id-abc"},
+						},
+					},
 					"init-container-id-789": {
 						Statuses: map[int]ContainerStatus{
 							0: {ContainerID: "init-container-id-789"},
@@ -1632,6 +1649,11 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 							2: {ContainerID: "container2-id-456"},
 						},
 					},
+					"container3": {
+						Statuses: map[int]ContainerStatus{
+							2: {ContainerID: "container3-id-abc"},
+						},
+					},
 					"init_container": {
 						Statuses: map[int]ContainerStatus{
 							0: {ContainerID: "init-container-id-789"},
@@ -1658,6 +1680,11 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 							2: {},
 						},
 					},
+					"container3-id-abc": {
+						Statuses: map[int]ContainerStatus{
+							2: {ImageRepoDigest: "docker.io/otel/collector:2.0.0@sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9"},
+						},
+					},
 					"init-container-id-789": {
 						Statuses: map[int]ContainerStatus{
 							0: {ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
@@ -1675,6 +1702,11 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 							2: {},
 						},
 					},
+					"container3": {
+						Statuses: map[int]ContainerStatus{
+							2: {ImageRepoDigest: "docker.io/otel/collector:2.0.0@sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9"},
+						},
+					},
 					"init_container": {
 						Statuses: map[int]ContainerStatus{
 							0: {ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
@@ -1695,45 +1727,57 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 			want: PodContainers{
 				ByID: map[string]*Container{
 					"container1-id-123": {
-						ImageName: "test/image1",
+						ImageName: "example.com:5000/test/image1",
 						ImageTag:  "0.1.0",
 						Statuses: map[int]ContainerStatus{
 							0: {ContainerID: "container1-id-123", ImageRepoDigest: "docker.io/otel/collector@sha256:55d008bc28344c3178645d40e7d07df30f9d90abe4b53c3fc4e5e9c0295533da"},
 						},
 					},
 					"container2-id-456": {
-						ImageName: "example.com:port1/image2",
-						ImageTag:  "0.2.0",
+						ImageName: "example.com:81/image2",
 						Statuses: map[int]ContainerStatus{
 							2: {ContainerID: "container2-id-456"},
 						},
 					},
+					"container3-id-abc": {
+						ImageName: "example-website.com/image3",
+						ImageTag:  "1.0",
+						Statuses: map[int]ContainerStatus{
+							2: {ContainerID: "container3-id-abc", ImageRepoDigest: "docker.io/otel/collector:2.0.0@sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9"},
+						},
+					},
 					"init-container-id-789": {
 						ImageName: "test/init-image",
-						ImageTag:  "1.0.2",
+						ImageTag:  "latest",
 						Statuses: map[int]ContainerStatus{
 							0: {ContainerID: "init-container-id-789", ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
 						},
 					},
 				},
 				ByName: map[string]*Container{
 					"container1": {
-						ImageName: "test/image1",
+						ImageName: "example.com:5000/test/image1",
 						ImageTag:  "0.1.0",
 						Statuses: map[int]ContainerStatus{
 							0: {ContainerID: "container1-id-123", ImageRepoDigest: "docker.io/otel/collector@sha256:55d008bc28344c3178645d40e7d07df30f9d90abe4b53c3fc4e5e9c0295533da"},
 						},
 					},
 					"container2": {
-						ImageName: "example.com:port1/image2",
-						ImageTag:  "0.2.0",
+						ImageName: "example.com:81/image2",
 						Statuses: map[int]ContainerStatus{
 							2: {ContainerID: "container2-id-456"},
 						},
 					},
+					"container3": {
+						ImageName: "example-website.com/image3",
+						ImageTag:  "1.0",
+						Statuses: map[int]ContainerStatus{
+							2: {ContainerID: "container3-id-abc", ImageRepoDigest: "docker.io/otel/collector:2.0.0@sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9"},
+						},
+					},
 					"init_container": {
 						ImageName: "test/init-image",
-						ImageTag:  "1.0.2",
+						ImageTag:  "latest",
 						Statuses: map[int]ContainerStatus{
 							0: {ContainerID: "init-container-id-789", ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
 						},

processor/k8sattributesprocessor/metadata.yaml

@@ -108,7 +108,7 @@ resource_attributes:
     type: slice
     enabled: false
   container.image.tag:
-    description: Container image tag. Requires container.id or k8s.container.name.
+    description: Container image tag. Defaults to "latest" if not provided (unless digest also in image path) Requires container.id or k8s.container.name.
     type: string
     enabled: true