[pkg/ottl] Add new ExtractPatterns converter that extract regex patterns from string

.chloggen/ottl-func-extract-pattern.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: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: pkg/ottl
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add new `ExtractPattern` converter that extract regex pattern from string.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [25834, 25856]
+
+# (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]

pkg/ottl/ottlfuncs/README.md

@@ -277,6 +277,7 @@ Unlike functions, they do not modify any input telemetry and always return a val
 Available Converters:
 - [Concat](#concat)
 - [ConvertCase](#convertcase)
+- [ExtractPattern](#extractpattern)
 - [FNV](#fnv)
 - [Duration](#duration)
 - [Int](#int)
@@ -530,6 +531,21 @@ Examples:
 
 - `ParseJSON(body)`
 
+### ExtractPattern
+
+`ExtractPattern(target, pattern)`
+
+The `ExtractPattern` Converter returns a `pcommon.Map` struct that is a result of extracting named capture groups from the target string
+
+`target` is a Getter that returns a string. `pattern` is a regex string.
+If `target` is not a string, nil, or does not match the pattern, `ExtractPattern` will return an error.
+
+Examples:
+
+- `ExtractPattern(attributes["k8s.change_cause"], "GIT_SHA=(?P<git.sha>\w+)")`
+
+- `ExtractPattern(body, "^(?P<timestamp>\\w+ \\w+ [0-9]+:[0-9]+:[0-9]+) (?P<hostname>([A-Za-z0-9-_]+)) (?P<process>\\w+)(\\[(?P<pid>\\d+)\\])?: (?P<message>.*)$")`
+
 ### SHA1
 
 `SHA1(value)`

pkg/ottl/ottlfuncs/func_extract_pattern.go

@@ -0,0 +1,74 @@
+package ottlfuncs
+
+import (
+	"context"
+	"fmt"
+	"regexp"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
+	"go.opentelemetry.io/collector/pdata/pcommon"
+)
+
+type ExtractPatternArguments[K any] struct {
+	Target  ottl.StringGetter[K] `ottlarg:"0"`
+	Pattern string               `ottlarg:"1"`
+}
+
+func NewExtractPatternFactory[K any]() ottl.Factory[K] {
+	return ottl.NewFactory("ExtractPattern", &ExtractPatternArguments[K]{}, createExtractPatternFunction[K])
+}
+
+func createExtractPatternFunction[K any](_ ottl.FunctionContext, oArgs ottl.Arguments) (ottl.ExprFunc[K], error) {
+	args, ok := oArgs.(*ExtractPatternArguments[K])
+
+	if !ok {
+		return nil, fmt.Errorf("ExtractPatternFactory args must be of type *ExtractPatternArguments[K]")
+	}
+
+	return extractPattern(args.Target, args.Pattern)
+}
+
+func extractPattern[K any](target ottl.StringGetter[K], pattern string) (ottl.ExprFunc[K], error) {
+	r, err := regexp.Compile(pattern)
+	if err != nil {
+		return nil, fmt.Errorf("the pattern supplied to ExtractPattern is not a valid pattern: %w", err)
+	}
+
+	namedCaptureGroups := 0
+	for _, groupName := range r.SubexpNames() {
+		if groupName != "" {
+			namedCaptureGroups++
+		}
+	}
+
+	if namedCaptureGroups == 0 {
+		return nil, fmt.Errorf("no named capture groups in regex pattern")
+	}
+
+	return func(ctx context.Context, tCtx K) (interface{}, error) {
+		val, err := target.Get(ctx, tCtx)
+		if err != nil {
+			return nil, err
+		}
+
+		matches := r.FindStringSubmatch(val)
+		if matches == nil {
+			return nil, fmt.Errorf("regex pattern does not match")
+		}
+
+		parsedValues := map[string]interface{}{}
+		for i, subexp := range r.SubexpNames() {
+			if i == 0 {
+				// Skip whole match
+				continue
+			}
+			if subexp != "" {
+				parsedValues[subexp] = matches[i]
+			}
+		}
+
+		result := pcommon.NewMap()
+		err = result.FromRaw(parsedValues)
+		return result, err
+	}, nil
+}

pkg/ottl/ottlfuncs/func_extract_pattern_test.go

@@ -0,0 +1,130 @@
+package ottlfuncs
+
+import (
+	"context"
+	"testing"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.opentelemetry.io/collector/pdata/pcommon"
+)
+
+func Test_extractPattern(t *testing.T) {
+	target := &ottl.StandardStringGetter[any]{
+		Getter: func(ctx context.Context, tCtx any) (interface{}, error) {
+			return `a=b c=d`, nil
+		},
+	}
+	tests := []struct {
+		name    string
+		target  ottl.StringGetter[any]
+		pattern string
+		want    func(pcommon.Map)
+	}{
+		{
+			name:    "parse regex",
+			target:  target,
+			pattern: `^a=(?P<a>\w+)\s+c=(?P<c>\w+)$`,
+			want: func(expectedMap pcommon.Map) {
+				expectedMap.PutStr("a", "b")
+				expectedMap.PutStr("c", "d")
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			exprFunc, err := extractPattern(tt.target, tt.pattern)
+			assert.NoError(t, err)
+
+			result, err := exprFunc(context.Background(), nil)
+			assert.NoError(t, err)
+
+			resultMap, ok := result.(pcommon.Map)
+			require.True(t, ok)
+
+			expected := pcommon.NewMap()
+			tt.want(expected)
+
+			assert.Equal(t, expected.Len(), resultMap.Len())
+			expected.Range(func(k string, v pcommon.Value) bool {
+				ev, _ := expected.Get(k)
+				av, _ := resultMap.Get(k)
+				assert.Equal(t, ev, av)
+				return true
+			})
+		})
+	}
+}
+
+func Test_extractPattern_validation(t *testing.T) {
+	tests := []struct {
+		name    string
+		target  ottl.StringGetter[any]
+		pattern string
+	}{
+		{
+			name: "bad regex",
+			target: &ottl.StandardStringGetter[any]{
+				Getter: func(ctx context.Context, tCtx any) (interface{}, error) {
+					return "foobar", nil
+				},
+			},
+			pattern: "(",
+		},
+		{
+			name: "no named capture group",
+			target: &ottl.StandardStringGetter[any]{
+				Getter: func(ctx context.Context, tCtx any) (interface{}, error) {
+					return "foobar", nil
+				},
+			},
+			pattern: "(.*)",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			exprFunc, err := extractPattern[any](tt.target, tt.pattern)
+			assert.Error(t, err)
+			assert.Nil(t, exprFunc)
+		})
+	}
+}
+
+func Test_extractPattern_bad_input(t *testing.T) {
+	tests := []struct {
+		name    string
+		target  ottl.StringGetter[any]
+		pattern string
+	}{
+		{
+			name: "target is non-string",
+			target: &ottl.StandardStringGetter[any]{
+				Getter: func(ctx context.Context, tCtx any) (interface{}, error) {
+					return 123, nil
+				},
+			},
+			pattern: "(?P<line>.*)",
+		},
+		{
+			name: "target is nil",
+			target: &ottl.StandardStringGetter[any]{
+				Getter: func(ctx context.Context, tCtx any) (interface{}, error) {
+					return nil, nil
+				},
+			},
+			pattern: "(?P<line>.*)",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			exprFunc, err := extractPattern[any](tt.target, tt.pattern)
+			assert.NoError(t, err)
+
+			result, err := exprFunc(nil, nil)
+			assert.Error(t, err)
+			assert.Nil(t, result)
+		})
+	}
+}

pkg/ottl/ottlfuncs/functions.go

@@ -37,6 +37,7 @@ func converters[K any]() []ottl.Factory[K] {
 		NewConcatFactory[K](),
 		NewConvertCaseFactory[K](),
 		NewDurationFactory[K](),
+		NewExtractPatternFactory[K](),
 		NewFnvFactory[K](),
 		NewIntFactory[K](),
 		NewIsMapFactory[K](),