[pkg/stanza] Add 'strip_ansi_escape_codes' operator

.chloggen/strip-ansi-escape-codes.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/stanza
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add 'strip_ansi_escape_codes' operator
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [37443]
+
+# (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: []

pkg/stanza/adapter/register.go

@@ -29,5 +29,6 @@ import (
 	_ "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/remove"
 	_ "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/retain"
 	_ "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/router"
+	_ "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/stripansiescapecodes"
 	_ "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/unquote"
 )

pkg/stanza/docs/operators/README.md

@@ -44,5 +44,6 @@ General purpose:
 - [remove](./remove.md)
 - [retain](./retain.md)
 - [router](./router.md)
+- [strip_ansi_escape_codes](./strip_ansi_escape_codes.md)
 - [unquote](./unquote.md)
 - [assign_keys](./assign_keys.md)

pkg/stanza/docs/operators/strip_ansi_escape_codes.md

@@ -0,0 +1,53 @@
+## `strip_ansi_escape_codes` operator
+
+The `strip_ansi_escape_codes` operator removes ANSI escape sequences (such as color codes) from a string.
+
+### Configuration Fields
+
+| Field      | Default                   | Description |
+| ---        | ---                       | ---         |
+| `id`       | `strip_ansi_escape_codes` | A unique identifier for the operator. |
+| `output`   | Next in pipeline          | The connected operator(s) that will receive all outbound entries. |
+| `field`    | required                  | The [field](../types/field.md) to strip. Must be a string. |
+| `on_error` | `send`                    | The behavior of the operator if it encounters an error. See [on_error](../types/on_error.md). |
+| `if`       |                           | An [expression](../types/expression.md) that, when set, will be evaluated to determine whether this operator should be used for the given entry. This allows you to do easy conditional parsing without branching logic with routers. |
+
+Right now the operator only removes the ANSI "Control Sequence Introducer (CSI)" escape codes starting with `ESC [`.
+
+### Example Configurations:
+
+<hr>
+
+Remove all color escape codes from the body
+```yaml
+- type: strip_ansi_escape_codes
+  field: body
+```
+
+<table>
+<tr><td> Input Entry </td> <td> Output Entry </td></tr>
+<tr>
+<td>
+
+```json
+{
+  "resource": { },
+  "attributes": { },
+  "body": "\x1b[31mred\x1b[0m"
+}
+```
+
+</td>
+<td>
+
+```json
+{
+  "resource": { },
+  "attributes": { },
+  "body": "red"
+}
+```
+
+</td>
+</tr>
+</table>

pkg/stanza/operator/transformer/stripansiescapecodes/config.go

@@ -0,0 +1,49 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package stripansiescapecodes // import "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/stripansiescapecodes"
+
+import (
+	"go.opentelemetry.io/collector/component"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/entry"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/helper"
+)
+
+const operatorType = "strip_ansi_escape_codes"
+
+func init() {
+	operator.Register(operatorType, func() operator.Builder { return NewConfig() })
+}
+
+// NewConfig creates a new strip_ansi_escape_codes config with default values
+func NewConfig() *Config {
+	return NewConfigWithID(operatorType)
+}
+
+// NewConfigWithID creates a new strip_ansi_escape_codes config with default values
+func NewConfigWithID(operatorID string) *Config {
+	return &Config{
+		TransformerConfig: helper.NewTransformerConfig(operatorID, operatorType),
+	}
+}
+
+// Config is the configuration of an strip_ansi_escape_codes operator.
+type Config struct {
+	helper.TransformerConfig `mapstructure:",squash"`
+	Field                    entry.Field `mapstructure:"field"`
+}
+
+// Build will build an strip_ansi_escape_codes operator.
+func (c Config) Build(set component.TelemetrySettings) (operator.Operator, error) {
+	transformerOperator, err := c.TransformerConfig.Build(set)
+	if err != nil {
+		return nil, err
+	}
+
+	return &Transformer{
+		TransformerOperator: transformerOperator,
+		field:               c.Field,
+	}, nil
+}

pkg/stanza/operator/transformer/stripansiescapecodes/config_test.go

@@ -0,0 +1,69 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+package stripansiescapecodes
+
+import (
+	"path/filepath"
+	"testing"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/entry"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/operatortest"
+)
+
+// test unmarshalling of values into config struct
+func TestUnmarshal(t *testing.T) {
+	operatortest.ConfigUnmarshalTests{
+		DefaultConfig: NewConfig(),
+		TestsFile:     filepath.Join(".", "testdata", "config.yaml"),
+		Tests: []operatortest.ConfigUnmarshalTest{
+			{
+				Name: "strip_ansi_escape_codes_body",
+				Expect: func() *Config {
+					cfg := NewConfig()
+					cfg.Field = entry.NewBodyField("nested")
+					return cfg
+				}(),
+			},
+			{
+				Name: "strip_ansi_escape_codes_single_attribute",
+				Expect: func() *Config {
+					cfg := NewConfig()
+					cfg.Field = entry.NewAttributeField("key")
+					return cfg
+				}(),
+			},
+			{
+				Name: "strip_ansi_escape_codes_single_resource",
+				Expect: func() *Config {
+					cfg := NewConfig()
+					cfg.Field = entry.NewResourceField("key")
+					return cfg
+				}(),
+			},
+			{
+				Name: "strip_ansi_escape_codes_nested_body",
+				Expect: func() *Config {
+					cfg := NewConfig()
+					cfg.Field = entry.NewBodyField("one", "two")
+					return cfg
+				}(),
+			},
+			{
+				Name: "strip_ansi_escape_codes_nested_attribute",
+				Expect: func() *Config {
+					cfg := NewConfig()
+					cfg.Field = entry.NewAttributeField("one", "two")
+					return cfg
+				}(),
+			},
+			{
+				Name: "strip_ansi_escape_codes_nested_resource",
+				Expect: func() *Config {
+					cfg := NewConfig()
+					cfg.Field = entry.NewResourceField("one", "two")
+					return cfg
+				}(),
+			},
+		},
+	}.Run(t)
+}

pkg/stanza/operator/transformer/stripansiescapecodes/package_test.go

@@ -0,0 +1,14 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package stripansiescapecodes
+
+import (
+	"testing"
+
+	"go.uber.org/goleak"
+)
+
+func TestMain(m *testing.M) {
+	goleak.VerifyTestMain(m)
+}

pkg/stanza/operator/transformer/stripansiescapecodes/testdata/config.yaml

@@ -0,0 +1,18 @@
+strip_ansi_escape_codes_body:
+  type: strip_ansi_escape_codes
+  field: body.nested
+strip_ansi_escape_codes_nested_attribute:
+  type: strip_ansi_escape_codes
+  field: attributes.one.two
+strip_ansi_escape_codes_nested_body:
+  type: strip_ansi_escape_codes
+  field: body.one.two
+strip_ansi_escape_codes_nested_resource:
+  type: strip_ansi_escape_codes
+  field: resource.one.two
+strip_ansi_escape_codes_single_attribute:
+  type: strip_ansi_escape_codes
+  field: attributes.key
+strip_ansi_escape_codes_single_resource:
+  type: strip_ansi_escape_codes
+  field: resource.key

pkg/stanza/operator/transformer/stripansiescapecodes/transformer.go

@@ -0,0 +1,42 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package stripansiescapecodes // import "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/stripansiescapecodes"
+
+import (
+	"context"
+	"fmt"
+	"regexp"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/entry"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/helper"
+)
+
+var ansiCsiEscapeRegex = regexp.MustCompile(`\x1B\[[\x30-\x3F]*[\x20-\x2F]*[\x40-\x7E]`)
+
+// Transformer is an operator that will remove ANSI Escape Codes from a string.
+type Transformer struct {
+	helper.TransformerOperator
+	field entry.Field
+}
+
+// Process will remove ANSI Escape Codes from a string
+func (t *Transformer) Process(ctx context.Context, entry *entry.Entry) error {
+	return t.ProcessWith(ctx, entry, t.strip)
+}
+
+// strip will remove ANSI Escape Codes from a string
+func (t *Transformer) strip(e *entry.Entry) error {
+	value, ok := t.field.Get(e)
+	if !ok {
+		return nil
+	}
+
+	switch v := value.(type) {
+	case string:
+		s := ansiCsiEscapeRegex.ReplaceAllString(v, "")
+		return t.field.Set(e, s)
+	default:
+		return fmt.Errorf("type %T cannot be stripped", value)
+	}
+}