[processor/k8sattributes] Deprecate FieldExtractConfig.Regex config option (#33411)

**Link to tracking Issue:** #25128

---------

Signed-off-by: odubajDT <[email protected]>
Co-authored-by: Curtis Robert <[email protected]>
Co-authored-by: Evan Bradley <[email protected]>
Co-authored-by: Tyler Helmuth <[email protected]>

Author: 4 people

.chloggen/chore_25128_regex.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: deprecation
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: k8sattributesprocessor
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Deprecate `extract.annotations.regex` and `extract.labels.regex` config fields in favor of the `ExtractPatterns` function in the transform processor. The `FieldExtractConfig.Regex` parameter will be removed in version v0.111.0.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [25128]
+
+# (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: Deprecating of FieldExtractConfig.Regex parameter means that it is recommended to use the `ExtractPatterns` function from the transform processor instead. To convert your current configuration please check the `ExtractPatterns` function [documentation](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/pkg/ottl/ottlfuncs#extractpatterns). You should use the `pattern` parameter of `ExtractPatterns` instead of using the `FieldExtractConfig.Regex` parameter.
+
+# 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

@@ -332,3 +332,51 @@ as tags.
 
 By default, the `k8s.pod.start_time` uses [Time.MarshalText()](https://pkg.go.dev/time#Time.MarshalText) to format the
 timestamp value as an RFC3339 compliant timestamp.
+
+## Feature Gate
+
+### `k8sattr.fieldExtractConfigRegex.disallow`
+
+The `k8sattr.fieldExtractConfigRegex.disallow` [feature gate](https://github.com/open-telemetry/opentelemetry-collector/blob/main/featuregate/README.md#collector-feature-gates) disallows the usage of the `extract.annotations.regex` and `extract.labels.regex` fields.
+The validation performed on the configuration will fail, if at least one of the parameters is set (non-empty) and `k8sattr.fieldExtractConfigRegex.disallow` is set to `true` (default `false`).
+
+#### Example Usage
+
+The following config with the feature gate set will lead to validation error:
+
+`config.yaml`:
+
+  ```yaml
+  extract:
+    labels:
+      regex: <my-regex1>
+    annotations:
+      regex: <my-regex2>
+  ```
+
+  Run collector: `./otelcol --config config.yaml --feature-gates=k8sattr.fieldExtractConfigRegex.disallow`
+
+#### Migration
+
+Deprecation of the `extract.annotations.regex` and `extract.labels.regex` fields means that it is recommended to use the `ExtractPatterns` function from the transform processor instead. To convert your current configuration please check the `ExtractPatterns` function [documentation](https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/pkg/ottl/ottlfuncs#extractpatterns). You should use the `pattern` parameter of `ExtractPatterns` instead of using the the `extract.annotations.regex` and `extract.labels.regex` fields.
+
+##### Example
+
+The following configuration of `k8sattributes processor`:
+
+`config.yaml`:
+
+  ```yaml
+  annotations:
+    - tag_name: a2 # extracts value of annotation with key `annotation2` with regexp and inserts it as a tag with key `a2`
+      key: annotation2
+      regex: field=(?P<value>.+)
+      from: pod
+  ```
+
+can be converted with the usage of `ExtractPatterns` function:
+
+```yaml
+  - set(cache["annotations"], ExtractPatterns(attributes["k8s.pod.annotations["annotation2"], "field=(?P<value>.+))")
+  - set(k8s.pod.annotations["a2"], cache["annotations"]["value"])
+```

processor/k8sattributesprocessor/config.go

@@ -7,12 +7,20 @@ import (
 	"fmt"
 	"regexp"
 
+	"go.opentelemetry.io/collector/featuregate"
 	conventions "go.opentelemetry.io/collector/semconv/v1.6.1"
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/internal/k8sconfig"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/processor/k8sattributesprocessor/internal/kube"
 )
 
+var disallowFieldExtractConfigRegex = featuregate.GlobalRegistry().MustRegister(
+	"k8sattr.fieldExtractConfigRegex.disallow",
+	featuregate.StageAlpha,
+	featuregate.WithRegisterDescription("When enabled, usage of the FieldExtractConfig.Regex field is disallowed"),
+	featuregate.WithRegisterFromVersion("v0.106.0"),
+)
+
 // Config defines configuration for k8s attributes processor.
 type Config struct {
 	k8sconfig.APIConfig `mapstructure:",squash"`
@@ -63,6 +71,9 @@ func (cfg *Config) Validate() error {
 		}
 
 		if f.Regex != "" {
+			if disallowFieldExtractConfigRegex.IsEnabled() {
+				return fmt.Errorf("the extract.annotations.regex and extract.labels.regex fields have been deprecated, please use the `ExtractPatterns` function in the transform processor instead")
+			}
 			r, err := regexp.Compile(f.Regex)
 			if err != nil {
 				return err
@@ -213,6 +224,8 @@ type FieldExtractConfig struct {
 	//       regex: JENKINS=(?P<value>[\w]+)
 	//
 	// this will add the `git.sha` and `ci.build` resource attributes.
+	// Deprecated: [v0.106.0] Use the `ExtractPatterns` function in the transform processor instead.
+	// More information about how to replace the regex field can be found in the k8sattributes processor readme.
 	Regex string `mapstructure:"regex"`
 
 	// From represents the source of the labels/annotations.

processor/k8sattributesprocessor/config_test.go

@@ -11,6 +11,7 @@ import (
 	"github.com/stretchr/testify/require"
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/confmap/confmaptest"
+	"go.opentelemetry.io/collector/featuregate"
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/internal/k8sconfig"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/processor/k8sattributesprocessor/internal/kube"
@@ -21,8 +22,9 @@ func TestLoadConfig(t *testing.T) {
 	t.Parallel()
 
 	tests := []struct {
-		id       component.ID
-		expected component.Config
+		id            component.ID
+		expected      component.Config
+		disallowRegex bool
 	}{
 		{
 			id: component.NewID(metadata.Type),
@@ -127,9 +129,35 @@ func TestLoadConfig(t *testing.T) {
 				},
 			},
 		},
+		{
+			id: component.NewIDWithName(metadata.Type, "deprecated-regex"),
+			expected: &Config{
+				APIConfig:   k8sconfig.APIConfig{AuthType: k8sconfig.AuthTypeKubeConfig},
+				Passthrough: false,
+				Extract: ExtractConfig{
+					Metadata: enabledAttributes(),
+					Annotations: []FieldExtractConfig{
+						{Regex: "field=(?P<value>.+)", From: "pod"},
+					},
+					Labels: []FieldExtractConfig{
+						{Regex: "field=(?P<value>.+)", From: "pod"},
+					},
+				},
+				Exclude: ExcludeConfig{
+					Pods: []ExcludePodConfig{
+						{Name: "jaeger-agent"},
+						{Name: "jaeger-collector"},
+					},
+				},
+			},
+		},
 		{
 			id: component.NewIDWithName(metadata.Type, "too_many_sources"),
 		},
+		{
+			id:            component.NewIDWithName(metadata.Type, "deprecated-regex"),
+			disallowRegex: true,
+		},
 		{
 			id: component.NewIDWithName(metadata.Type, "bad_keys_labels"),
 		},
@@ -176,6 +204,12 @@ func TestLoadConfig(t *testing.T) {
 
 	for _, tt := range tests {
 		t.Run(tt.id.String(), func(t *testing.T) {
+			if tt.disallowRegex {
+				require.Nil(t, featuregate.GlobalRegistry().Set(disallowFieldExtractConfigRegex.ID(), true))
+				t.Cleanup(func() {
+					require.Nil(t, featuregate.GlobalRegistry().Set(disallowFieldExtractConfigRegex.ID(), false))
+				})
+			}
 			cm, err := confmaptest.LoadConf(filepath.Join("testdata", "config.yaml"))
 			require.NoError(t, err)
 

processor/k8sattributesprocessor/testdata/config.yaml

@@ -106,6 +106,17 @@ k8sattributes/too_many_sources:
         - from: connection
           name: ip
 
+k8sattributes/deprecated-regex:
+  passthrough: false
+  auth_type: "kubeConfig"
+  extract:
+    labels:
+      - regex: field=(?P<value>.+)
+        from: pod
+    annotations:
+      - regex: field=(?P<value>.+)
+        from: pod
+
 k8sattributes/bad_keys_labels:
   extract:
     labels: