Add OTTL md5 function

Author: edmocosta

.chloggen/ottl_md5_function.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 the `MD5` function to convert the `value` into a MD5 hash/digest"
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [33792]
+
+# (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/e2e/e2e_test.go

@@ -465,6 +465,12 @@ func Test_e2e_converters(t *testing.T) {
 				tCtx.GetLogRecord().Attributes().PutDouble("test", 0)
 			},
 		},
+		{
+			statement: `set(attributes["test"], MD5("pass"))`,
+			want: func(tCtx ottllog.TransformContext) {
+				tCtx.GetLogRecord().Attributes().PutStr("test", "1a1dc91c907325c69271ddf0c944bc72")
+			},
+		},
 		{
 			statement: `set(attributes["test"], Microseconds(Duration("1ms")))`,
 			want: func(tCtx ottllog.TransformContext) {

pkg/ottl/ottlfuncs/README.md

@@ -429,6 +429,7 @@ Available Converters:
 - [IsString](#isstring)
 - [Len](#len)
 - [Log](#log)
+- [MD5](#md5)
 - [Microseconds](#microseconds)
 - [Milliseconds](#milliseconds)
 - [Minute](#minute)
@@ -831,6 +832,26 @@ Examples:
 
 - `Int(Log(attributes["duration_ms"])`
 
+### MD5
+
+`MD5(value)`
+
+The `MD5` Converter converts the `value` to a md5 hash/digest.
+
+The returned type is string.
+
+`value` is either a path expression to a string telemetry field or a literal string. If `value` is another type an error is returned.
+
+If an error occurs during hashing it will be returned.
+
+Examples:
+
+- `MD5(attributes["device.name"])`
+
+- `MD5("name")`
+
+**Note:** According to the National Institute of Standards and Technology (NIST), MD5 is no longer a recommended hash function. It should be avoided except when required for compatibility. New uses should prefer FNV whenever possible.
+
 ### Microseconds
 
 `Microseconds(value)`

pkg/ottl/ottlfuncs/func_md5.go

@@ -0,0 +1,47 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package ottlfuncs // import "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl/ottlfuncs"
+
+import (
+	"context"
+	"crypto/md5" // #nosec
+	"encoding/hex"
+	"fmt"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
+)
+
+type MD5Arguments[K any] struct {
+	Target ottl.StringGetter[K]
+}
+
+func NewMD5Factory[K any]() ottl.Factory[K] {
+	return ottl.NewFactory("MD5", &MD5Arguments[K]{}, createMD5Function[K])
+}
+
+func createMD5Function[K any](_ ottl.FunctionContext, oArgs ottl.Arguments) (ottl.ExprFunc[K], error) {
+	args, ok := oArgs.(*MD5Arguments[K])
+
+	if !ok {
+		return nil, fmt.Errorf("MD5Factory args must be of type *MD5Arguments[K]")
+	}
+
+	return MD5HashString(args.Target)
+}
+
+func MD5HashString[K any](target ottl.StringGetter[K]) (ottl.ExprFunc[K], error) {
+
+	return func(ctx context.Context, tCtx K) (any, error) {
+		val, err := target.Get(ctx, tCtx)
+		if err != nil {
+			return nil, err
+		}
+		hash := md5.New() // #nosec
+		_, err = hash.Write([]byte(val))
+		if err != nil {
+			return nil, err
+		}
+		return hex.EncodeToString(hash.Sum(nil)), nil
+	}, nil
+}

pkg/ottl/ottlfuncs/func_md5_test.go

@@ -0,0 +1,82 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package ottlfuncs
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
+)
+
+func Test_MD5(t *testing.T) {
+	tests := []struct {
+		name     string
+		value    any
+		expected any
+		err      bool
+	}{
+		{
+			name:     "string",
+			value:    "hello world",
+			expected: "5eb63bbbe01eeed093cb22bb8f5acdc3",
+		},
+		{
+			name:     "empty string",
+			value:    "",
+			expected: "d41d8cd98f00b204e9800998ecf8427e",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			exprFunc, err := MD5HashString[any](&ottl.StandardStringGetter[any]{
+				Getter: func(context.Context, any) (any, error) {
+					return tt.value, nil
+				},
+			})
+			assert.NoError(t, err)
+			result, err := exprFunc(nil, nil)
+			if tt.err {
+				assert.Error(t, err)
+			} else {
+				assert.NoError(t, err)
+			}
+			assert.Equal(t, tt.expected, result)
+		})
+	}
+}
+
+func Test_MD5Error(t *testing.T) {
+	tests := []struct {
+		name          string
+		value         any
+		err           bool
+		expectedError string
+	}{
+		{
+			name:          "non-string",
+			value:         10,
+			expectedError: "expected string but got int",
+		},
+		{
+			name:          "nil",
+			value:         nil,
+			expectedError: "expected string but got nil",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			exprFunc, err := MD5HashString[any](&ottl.StandardStringGetter[any]{
+				Getter: func(context.Context, any) (any, error) {
+					return tt.value, nil
+				},
+			})
+			assert.NoError(t, err)
+			_, err = exprFunc(nil, nil)
+			assert.ErrorContains(t, err, tt.expectedError)
+		})
+	}
+}

pkg/ottl/ottlfuncs/functions.go

@@ -56,6 +56,7 @@ func converters[K any]() []ottl.Factory[K] {
 		NewIsStringFactory[K](),
 		NewLenFactory[K](),
 		NewLogFactory[K](),
+		NewMD5Factory[K](),
 		NewMicrosecondsFactory[K](),
 		NewMillisecondsFactory[K](),
 		NewMinuteFactory[K](),