docs(codecs): fix wording in decoder and framing doc strings

lib/codecs/src/decoding/format/avro.rs

@@ -103,8 +103,7 @@ pub struct AvroDeserializerOptions {
     ))]
     pub schema: String,
 
-    /// For Avro datum encoded in Kafka messages, the bytes are prefixed with the schema ID.  Set this to `true` to strip the schema ID prefix.
-    /// According to [Confluent Kafka's document](https://docs.confluent.io/platform/current/schema-registry/fundamentals/serdes-develop/index.html#wire-format).
+    /// For Avro datum encoded in Kafka messages, the bytes are prefixed with the schema ID.  Set this to `true` to strip the schema ID prefix, as described in [Confluent Kafka's documentation](https://docs.confluent.io/platform/current/schema-registry/fundamentals/serdes-develop/index.html#wire-format).
     pub strip_schema_id_prefix: bool,
 }
 

lib/codecs/src/decoding/format/gelf.rs

@@ -47,7 +47,7 @@ pub enum ValidationMode {
 
     /// Uses more relaxed validation that skips strict GELF specification checks.
     ///
-    /// This mode will not treat specification violations as errors, allowing the decoder
+    /// This mode does not treat specification violations as errors, allowing the decoder
     /// to accept messages from sources that don't strictly follow the GELF spec.
     Relaxed,
 }

lib/codecs/src/decoding/format/otlp.rs

@@ -34,11 +34,11 @@ pub enum OtlpSignalType {
 pub struct OtlpDeserializerConfig {
     /// Signal types to attempt parsing, in priority order.
     ///
-    /// The deserializer will try parsing in the order specified. This allows you to optimize
+    /// The deserializer tries to parse signals in the specified order. This allows you to optimize
     /// performance when you know the expected signal types. For example, if you only receive
     /// traces, set this to `["traces"]` to avoid attempting to parse as logs or metrics first.
     ///
-    /// If not specified, defaults to trying all types in order: logs, metrics, traces.
+    /// If not specified, defaults to trying all types in this order: logs, metrics, traces.
     /// Duplicate signal types are automatically removed while preserving order.
     #[serde(default = "default_signal_types")]
     pub signal_types: IndexSet<OtlpSignalType>,

lib/codecs/src/decoding/format/protobuf.rs

@@ -75,7 +75,7 @@ pub struct ProtobufDeserializerOptions {
     ///
     /// This file is the output of `protoc -I <include path> -o <desc output path> <proto>`.
     ///
-    /// You can read more [here](https://buf.build/docs/reference/images/#how-buf-images-work).
+    /// For more information, see [How Buf images work](https://buf.build/docs/reference/images/#how-buf-images-work).
     pub desc_file: PathBuf,
 
     /// The name of the message type to use for serializing.
@@ -85,7 +85,7 @@ pub struct ProtobufDeserializerOptions {
     /// Use JSON field names (camelCase) instead of protobuf field names (snake_case).
     ///
     /// When enabled, the deserializer will output fields using their JSON names as defined
-    /// in the `.proto` file (e.g., `jobDescription` instead of `job_description`).
+    /// in the `.proto` file (for example, `jobDescription` instead of `job_description`).
     ///
     /// This is useful when working with data that needs to be converted to JSON or
     /// when interfacing with systems that use JSON naming conventions.

lib/codecs/src/decoding/format/vrl.rs

@@ -30,8 +30,8 @@ pub struct VrlDeserializerConfig {
 #[derive(Debug, Clone, PartialEq, Eq, Default)]
 pub struct VrlDeserializerOptions {
     /// The [Vector Remap Language][vrl] (VRL) program to execute for each event.
-    /// Note that the final contents of the `.` target will be used as the decoding result.
-    /// Compilation error or use of 'abort' in a program will result in a decoding error.
+    /// The final contents of the `.` target are used as the decoding result.
+    /// Compilation errors or use of `abort` in the program result in a decoding error.
     ///
     ///
     /// [vrl]: https://vector.dev/docs/reference/vrl

lib/codecs/src/decoding/framing/character_delimited.rs

@@ -47,13 +47,13 @@ pub struct CharacterDelimitedDecoderOptions {
     ///
     /// This length does *not* include the trailing delimiter.
     ///
-    /// By default, there is no maximum length enforced. If events are malformed, this can lead to
+    /// By default, no maximum length is enforced. If events are malformed, this can lead to
     /// additional resource usage as events continue to be buffered in memory, and can potentially
     /// lead to memory exhaustion in extreme cases.
     ///
     /// If there is a risk of processing malformed data, such as logs with user-controlled input,
     /// consider setting the maximum length to a reasonably large value as a safety net. This
-    /// ensures that processing is not actually unbounded.
+    /// prevents processing from being unbounded.
     #[serde(skip_serializing_if = "vector_core::serde::is_default")]
     pub max_length: Option<usize>,
 }

lib/codecs/src/decoding/framing/chunked_gelf.rs

@@ -54,7 +54,7 @@ impl ChunkedGelfDecoderConfig {
 #[derivative(Default)]
 pub struct ChunkedGelfDecoderOptions {
     /// The timeout, in seconds, for a message to be fully received. If the timeout is reached, the
-    /// decoder drops all the received chunks of the timed out message.
+    /// decoder drops all received chunks for the timed-out message.
     #[serde(default = "default_timeout_secs")]
     #[derivative(Default(value = "default_timeout_secs()"))]
     pub timeout_secs: f64,
@@ -66,15 +66,15 @@ pub struct ChunkedGelfDecoderOptions {
     #[serde(default, skip_serializing_if = "vector_core::serde::is_default")]
     pub pending_messages_limit: Option<usize>,
 
-    /// The maximum length of a single GELF message, in bytes. Messages longer than this length will
-    /// be dropped. If this option is not set, the decoder does not limit the length of messages and
+    /// The maximum length of a single GELF message, in bytes. Messages longer than this length are
+    /// dropped. If this option is not set, the decoder does not limit the length of messages and
     /// the per-message memory is unbounded.
     ///
-    /// **Note**: A message can be composed of multiple chunks and this limit is applied to the whole
+    /// **Note**: A message can be composed of multiple chunks, and this limit applies to the whole
     /// message, not to individual chunks.
     ///
-    /// This limit takes only into account the message's payload and the GELF header bytes are excluded from the calculation.
-    /// The message's payload is the concatenation of all the chunks' payloads.
+    /// This limit takes into account only the message payload. GELF header bytes are excluded from the calculation.
+    /// The message payload is the concatenation of all chunk payloads.
     #[serde(default, skip_serializing_if = "vector_core::serde::is_default")]
     pub max_length: Option<usize>,
 

lib/codecs/src/decoding/framing/newline_delimited.rs

@@ -21,13 +21,13 @@ pub struct NewlineDelimitedDecoderOptions {
     ///
     /// This length does *not* include the trailing delimiter.
     ///
-    /// By default, there is no maximum length enforced. If events are malformed, this can lead to
+    /// By default, no maximum length is enforced. If events are malformed, this can lead to
     /// additional resource usage as events continue to be buffered in memory, and can potentially
     /// lead to memory exhaustion in extreme cases.
     ///
     /// If there is a risk of processing malformed data, such as logs with user-controlled input,
     /// consider setting the maximum length to a reasonably large value as a safety net. This
-    /// ensures that processing is not actually unbounded.
+    /// prevents processing from being unbounded.
     #[serde(skip_serializing_if = "vector_core::serde::is_default")]
     pub max_length: Option<usize>,
 }

lib/codecs/src/decoding/mod.rs

@@ -270,7 +270,7 @@ pub enum DeserializerConfig {
 
     /// Decodes the raw bytes as [native Protocol Buffers format][vector_native_protobuf].
     ///
-    /// This decoder can output all types of events (logs, metrics, traces).
+    /// This decoder can output all types of events: logs, metrics, and traces.
     ///
     /// This codec is **[experimental][experimental]**.
     ///
@@ -280,7 +280,7 @@ pub enum DeserializerConfig {
 
     /// Decodes the raw bytes as [native JSON format][vector_native_json].
     ///
-    /// This decoder can output all types of events (logs, metrics, traces).
+    /// This decoder can output all types of events: logs, metrics, and traces.
     ///
     /// This codec is **[experimental][experimental]**.
     ///
@@ -294,13 +294,13 @@ pub enum DeserializerConfig {
     ///
     /// The GELF specification is more strict than the actual Graylog receiver.
     /// Vector's decoder adheres more strictly to the GELF spec, with
-    /// the exception that some characters such as `@`  are allowed in field names.
+    /// the exception that some characters such as `@` are allowed in field names.
     ///
-    /// Other GELF codecs such as Loki's, use a [Go SDK][implementation] that is maintained
-    /// by Graylog, and is much more relaxed than the GELF spec.
+    /// Other GELF codecs, such as Loki's, use a [Go SDK][implementation] that is maintained
+    /// by Graylog and is much more relaxed than the GELF spec.
     ///
-    /// Going forward, Vector will use that [Go SDK][implementation] as the reference implementation, which means
-    /// the codec may continue to relax the enforcement of specification.
+    /// Going forward, Vector will use the [Go SDK][implementation] as the reference implementation, which means
+    /// the codec may continue to relax the enforcement of the specification.
     ///
     /// [gelf]: https://docs.graylog.org/docs/gelf
     /// [implementation]: https://github.com/Graylog2/go-gelf/blob/v2/gelf/reader.go

website/cue/reference/components/sinks/generated/websocket_server.cue

@@ -604,11 +604,8 @@ generated: components: sinks: websocket_server: configuration: {
 										type: string: examples: ["{ \"type\": \"record\", \"name\": \"log\", \"fields\": [{ \"name\": \"message\", \"type\": \"string\" }] }"]
 									}
 									strip_schema_id_prefix: {
-										description: """
-																								For Avro datum encoded in Kafka messages, the bytes are prefixed with the schema ID.  Set this to `true` to strip the schema ID prefix.
-																								According to [Confluent Kafka's document](https://docs.confluent.io/platform/current/schema-registry/fundamentals/serdes-develop/index.html#wire-format).
-																								"""
-										required: true
+										description: "For Avro datum encoded in Kafka messages, the bytes are prefixed with the schema ID.  Set this to `true` to strip the schema ID prefix, as described in [Confluent Kafka's documentation](https://docs.confluent.io/platform/current/schema-registry/fundamentals/serdes-develop/index.html#wire-format)."
+										required:    true
 										type: bool: {}
 									}
 								}
@@ -632,13 +629,13 @@ generated: components: sinks: websocket_server: configuration: {
 
 																							The GELF specification is more strict than the actual Graylog receiver.
 																							Vector's decoder adheres more strictly to the GELF spec, with
-																							the exception that some characters such as `@`  are allowed in field names.
+																							the exception that some characters such as `@` are allowed in field names.
 
-																							Other GELF codecs such as Loki's, use a [Go SDK][implementation] that is maintained
-																							by Graylog, and is much more relaxed than the GELF spec.
+																							Other GELF codecs, such as Loki's, use a [Go SDK][implementation] that is maintained
+																							by Graylog and is much more relaxed than the GELF spec.
 
-																							Going forward, Vector will use that [Go SDK][implementation] as the reference implementation, which means
-																							the codec may continue to relax the enforcement of specification.
+																							Going forward, Vector will use the [Go SDK][implementation] as the reference implementation, which means
+																							the codec may continue to relax the enforcement of the specification.
 
 																							[gelf]: https://docs.graylog.org/docs/gelf
 																							[implementation]: https://github.com/Graylog2/go-gelf/blob/v2/gelf/reader.go
@@ -656,7 +653,7 @@ generated: components: sinks: websocket_server: configuration: {
 										native: """
 																							Decodes the raw bytes as [native Protocol Buffers format][vector_native_protobuf].
 
-																							This decoder can output all types of events (logs, metrics, traces).
+																							This decoder can output all types of events: logs, metrics, and traces.
 
 																							This codec is **[experimental][experimental]**.
 
@@ -666,7 +663,7 @@ generated: components: sinks: websocket_server: configuration: {
 										native_json: """
 																							Decodes the raw bytes as [native JSON format][vector_native_json].
 
-																							This decoder can output all types of events (logs, metrics, traces).
+																							This decoder can output all types of events: logs, metrics, and traces.
 
 																							This codec is **[experimental][experimental]**.
 
@@ -728,7 +725,7 @@ generated: components: sinks: websocket_server: configuration: {
 												relaxed: """
 																											Uses more relaxed validation that skips strict GELF specification checks.
 
-																											This mode will not treat specification violations as errors, allowing the decoder
+																											This mode does not treat specification violations as errors, allowing the decoder
 																											to accept messages from sources that don't strictly follow the GELF spec.
 																											"""
 												strict: "Uses strict validation that closely follows the GELF spec."
@@ -796,7 +793,7 @@ generated: components: sinks: websocket_server: configuration: {
 
 																								This file is the output of `protoc -I <include path> -o <desc output path> <proto>`.
 
-																								You can read more [here](https://buf.build/docs/reference/images/#how-buf-images-work).
+																								For more information, see [How Buf images work](https://buf.build/docs/reference/images/#how-buf-images-work).
 																								"""
 										required: false
 										type: string: default: ""
@@ -814,7 +811,7 @@ generated: components: sinks: websocket_server: configuration: {
 																								Use JSON field names (camelCase) instead of protobuf field names (snake_case).
 
 																								When enabled, the deserializer will output fields using their JSON names as defined
-																								in the `.proto` file (e.g., `jobDescription` instead of `job_description`).
+																								in the `.proto` file (for example, `jobDescription` instead of `job_description`).
 
 																								This is useful when working with data that needs to be converted to JSON or
 																								when interfacing with systems that use JSON naming conventions.
@@ -828,11 +825,11 @@ generated: components: sinks: websocket_server: configuration: {
 								description: """
 																				Signal types to attempt parsing, in priority order.
 
-																				The deserializer will try parsing in the order specified. This allows you to optimize
+																				The deserializer tries to parse signals in the specified order. This allows you to optimize
 																				performance when you know the expected signal types. For example, if you only receive
 																				traces, set this to `["traces"]` to avoid attempting to parse as logs or metrics first.
 
-																				If not specified, defaults to trying all types in order: logs, metrics, traces.
+																				If not specified, defaults to trying all types in this order: logs, metrics, traces.
 																				Duplicate signal types are automatically removed while preserving order.
 																				"""
 								relevant_when: "codec = \"otlp\""
@@ -870,8 +867,8 @@ generated: components: sinks: websocket_server: configuration: {
 									source: {
 										description: """
 																								The [Vector Remap Language][vrl] (VRL) program to execute for each event.
-																								Note that the final contents of the `.` target will be used as the decoding result.
-																								Compilation error or use of 'abort' in a program will result in a decoding error.
+																								The final contents of the `.` target are used as the decoding result.
+																								Compilation errors or use of `abort` in the program result in a decoding error.
 
 																								[vrl]: https://vector.dev/docs/reference/vrl
 																								"""