From 5f8c4cfa748e846cd20965d6ab04c3115ce41833 Mon Sep 17 00:00:00 2001
From: Amar3tto <actions@GitHub Actions 1025821803.local>
Date: Fri, 21 Aug 2026 13:12:53 +0000
Subject: [PATCH] Update managed-io.md for release 2.76.0-RC4.

---
 .../content/en/documentation/io/managed-io.md | 774 ++++++++----------
 1 file changed, 362 insertions(+), 412 deletions(-)

diff --git a/website/www/site/content/en/documentation/io/managed-io.md b/website/www/site/content/en/documentation/io/managed-io.md
index 70b5efe9ed17..38c73cbf45af 100644
--- a/website/www/site/content/en/documentation/io/managed-io.md
+++ b/website/www/site/content/en/documentation/io/managed-io.md
@@ -59,30 +59,31 @@ and Beam SQL is invoked via the Managed API under the hood.
       <th>Write Configuration</th>
     </tr>
     <tr>
-      <td><strong>DELTA</strong></td>
-      <td>
-        <strong>table</strong> (<code style="color: green">str</code>)<br>
-        hadoop_config (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
-        timestamp (<code style="color: green">str</code>)<br>
-        version (<code style="color: #f54251">int64</code>)<br>
-      </td>
-      <td>
-        Unavailable
-      </td>
-    </tr>
-    <tr>
-      <td><strong>DELTA_CDC</strong></td>
+      <td><strong>KAFKA</strong></td>
       <td>
-        <strong>table</strong> (<code style="color: green">str</code>)<br>
-        start_version (<code style="color: #f54251">int64</code>)<br>
-        start_timestamp (<code style="color: green">str</code>)<br>
-        end_version (<code style="color: #f54251">int64</code>)<br>
-        end_timestamp (<code style="color: green">str</code>)<br>
-        hadoop_config (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
-        include_metadata_columns (<code>list[<span style="color: green;">str</span>]</code>)<br>
+        <strong>bootstrap_servers</strong> (<code style="color: green">str</code>)<br>
+        <strong>topic</strong> (<code style="color: green">str</code>)<br>
+        allow_duplicates (<code style="color: orange">boolean</code>)<br>
+        confluent_schema_registry_subject (<code style="color: green">str</code>)<br>
+        confluent_schema_registry_url (<code style="color: green">str</code>)<br>
+        consumer_config_updates (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
+        file_descriptor_path (<code style="color: green">str</code>)<br>
+        format (<code style="color: green">str</code>)<br>
+        message_name (<code style="color: green">str</code>)<br>
+        offset_deduplication (<code style="color: orange">boolean</code>)<br>
+        redistribute_by_record_key (<code style="color: orange">boolean</code>)<br>
+        redistribute_num_keys (<code style="color: #f54251">int32</code>)<br>
+        redistributed (<code style="color: orange">boolean</code>)<br>
+        schema (<code style="color: green">str</code>)<br>
       </td>
       <td>
-        Unavailable
+        <strong>bootstrap_servers</strong> (<code style="color: green">str</code>)<br>
+        <strong>format</strong> (<code style="color: green">str</code>)<br>
+        <strong>topic</strong> (<code style="color: green">str</code>)<br>
+        file_descriptor_path (<code style="color: green">str</code>)<br>
+        message_name (<code style="color: green">str</code>)<br>
+        producer_config_updates (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
+        schema (<code style="color: green">str</code>)<br>
       </td>
     </tr>
     <tr>
@@ -111,34 +112,7 @@ and Beam SQL is invoked via the Managed API under the hood.
         sort_fields (<code>list[<span style="color: green;">str</span>]</code>)<br>
         table_properties (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
         triggering_frequency_seconds (<code style="color: #f54251">int32</code>)<br>
-      </td>
-    </tr>
-    <tr>
-      <td><strong>KAFKA</strong></td>
-      <td>
-        <strong>bootstrap_servers</strong> (<code style="color: green">str</code>)<br>
-        <strong>topic</strong> (<code style="color: green">str</code>)<br>
-        allow_duplicates (<code style="color: orange">boolean</code>)<br>
-        confluent_schema_registry_subject (<code style="color: green">str</code>)<br>
-        confluent_schema_registry_url (<code style="color: green">str</code>)<br>
-        consumer_config_updates (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
-        file_descriptor_path (<code style="color: green">str</code>)<br>
-        format (<code style="color: green">str</code>)<br>
-        message_name (<code style="color: green">str</code>)<br>
-        offset_deduplication (<code style="color: orange">boolean</code>)<br>
-        redistribute_by_record_key (<code style="color: orange">boolean</code>)<br>
-        redistribute_num_keys (<code style="color: #f54251">int32</code>)<br>
-        redistributed (<code style="color: orange">boolean</code>)<br>
-        schema (<code style="color: green">str</code>)<br>
-      </td>
-      <td>
-        <strong>bootstrap_servers</strong> (<code style="color: green">str</code>)<br>
-        <strong>format</strong> (<code style="color: green">str</code>)<br>
-        <strong>topic</strong> (<code style="color: green">str</code>)<br>
-        file_descriptor_path (<code style="color: green">str</code>)<br>
-        message_name (<code style="color: green">str</code>)<br>
-        producer_config_updates (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
-        schema (<code style="color: green">str</code>)<br>
+        write_properties (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
       </td>
     </tr>
     <tr>
@@ -152,22 +126,56 @@ and Beam SQL is invoked via the Managed API under the hood.
         filter (<code style="color: green">str</code>)<br>
         from_snapshot (<code style="color: #f54251">int64</code>)<br>
         from_timestamp (<code style="color: #f54251">int64</code>)<br>
+        include_metadata_columns (<code>list[<span style="color: green;">str</span>]</code>)<br>
         keep (<code>list[<span style="color: green;">str</span>]</code>)<br>
         poll_interval_seconds (<code style="color: #f54251">int32</code>)<br>
         starting_strategy (<code style="color: green">str</code>)<br>
         streaming (<code style="color: orange">boolean</code>)<br>
         to_snapshot (<code style="color: #f54251">int64</code>)<br>
         to_timestamp (<code style="color: #f54251">int64</code>)<br>
+        watermark_column (<code style="color: green">str</code>)<br>
+        watermark_column_time_unit (<code style="color: green">str</code>)<br>
       </td>
       <td>
         Unavailable
       </td>
     </tr>
     <tr>
-      <td><strong>POSTGRES</strong></td>
+      <td><strong>DELTA</strong></td>
+      <td>
+        <strong>table</strong> (<code style="color: green">str</code>)<br>
+        hadoop_config (<code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>)<br>
+        timestamp (<code style="color: green">str</code>)<br>
+        version (<code style="color: #f54251">int64</code>)<br>
+      </td>
+      <td>
+        Unavailable
+      </td>
+    </tr>
+    <tr>
+      <td><strong>BIGQUERY</strong></td>
+      <td>
+        kms_key (<code style="color: green">str</code>)<br>
+        query (<code style="color: green">str</code>)<br>
+        row_restriction (<code style="color: green">str</code>)<br>
+        fields (<code>list[<span style="color: green;">str</span>]</code>)<br>
+        table (<code style="color: green">str</code>)<br>
+      </td>
+      <td>
+        <strong>table</strong> (<code style="color: green">str</code>)<br>
+        drop (<code>list[<span style="color: green;">str</span>]</code>)<br>
+        keep (<code>list[<span style="color: green;">str</span>]</code>)<br>
+        kms_key (<code style="color: green">str</code>)<br>
+        only (<code style="color: green">str</code>)<br>
+        triggering_frequency_seconds (<code style="color: #f54251">int64</code>)<br>
+      </td>
+    </tr>
+    <tr>
+      <td><strong>SQLSERVER</strong></td>
       <td>
         <strong>jdbc_url</strong> (<code style="color: green">str</code>)<br>
         connection_properties (<code style="color: green">str</code>)<br>
+        disable_auto_commit (<code style="color: orange">boolean</code>)<br>
         fetch_size (<code style="color: #f54251">int32</code>)<br>
         location (<code style="color: green">str</code>)<br>
         num_partitions (<code style="color: #f54251">int32</code>)<br>
@@ -189,11 +197,10 @@ and Beam SQL is invoked via the Managed API under the hood.
       </td>
     </tr>
     <tr>
-      <td><strong>SQLSERVER</strong></td>
+      <td><strong>POSTGRES</strong></td>
       <td>
         <strong>jdbc_url</strong> (<code style="color: green">str</code>)<br>
         connection_properties (<code style="color: green">str</code>)<br>
-        disable_auto_commit (<code style="color: orange">boolean</code>)<br>
         fetch_size (<code style="color: #f54251">int32</code>)<br>
         location (<code style="color: green">str</code>)<br>
         num_partitions (<code style="color: #f54251">int32</code>)<br>
@@ -214,24 +221,6 @@ and Beam SQL is invoked via the Managed API under the hood.
         write_statement (<code style="color: green">str</code>)<br>
       </td>
     </tr>
-    <tr>
-      <td><strong>BIGQUERY</strong></td>
-      <td>
-        kms_key (<code style="color: green">str</code>)<br>
-        query (<code style="color: green">str</code>)<br>
-        row_restriction (<code style="color: green">str</code>)<br>
-        fields (<code>list[<span style="color: green;">str</span>]</code>)<br>
-        table (<code style="color: green">str</code>)<br>
-      </td>
-      <td>
-        <strong>table</strong> (<code style="color: green">str</code>)<br>
-        drop (<code>list[<span style="color: green;">str</span>]</code>)<br>
-        keep (<code>list[<span style="color: green;">str</span>]</code>)<br>
-        kms_key (<code style="color: green">str</code>)<br>
-        only (<code style="color: green">str</code>)<br>
-        triggering_frequency_seconds (<code style="color: #f54251">int64</code>)<br>
-      </td>
-    </tr>
     <tr>
       <td><strong>MYSQL</strong></td>
       <td>
@@ -265,7 +254,7 @@ and Beam SQL is invoked via the Managed API under the hood.
 
 ## Configuration Details
 
-### `DELTA` Read
+### `KAFKA` Write
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -276,52 +265,85 @@ and Beam SQL is invoked via the Managed API under the hood.
     </tr>
     <tr>
       <td>
-        <strong>table</strong>
+        <strong>bootstrap_servers</strong>
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        Identifier of the Delta Lake table.
+        A list of host/port pairs to use for establishing the initial connection to the Kafka cluster. The client will make use of all servers irrespective of which servers are specified here for bootstrapping—this list only impacts the initial hosts used to discover the full set of servers. | Format: host1:port1,host2:port2,...
       </td>
     </tr>
     <tr>
       <td>
-        hadoop_config
+        <strong>format</strong>
       </td>
       <td>
-        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        Properties passed to the Hadoop Configuration.
+        The encoding format for the data stored in Kafka. Valid options are: RAW,JSON,AVRO,PROTO
       </td>
     </tr>
     <tr>
       <td>
-        timestamp
+        <strong>topic</strong>
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        Timestamp of the Delta Lake table to read.
+        n/a
       </td>
     </tr>
     <tr>
       <td>
-        version
+        file_descriptor_path
       </td>
       <td>
-        <code style="color: #f54251">int64</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        Version of the Delta Lake table to read.
+        The path to the Protocol Buffer File Descriptor Set file. This file is used for schema definition and message serialization.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        message_name
+      </td>
+      <td>
+        <code style="color: green">str</code>
+      </td>
+      <td>
+        The name of the Protocol Buffer message to be used for schema extraction and data conversion.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        producer_config_updates
+      </td>
+      <td>
+        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
+      </td>
+      <td>
+        A list of key-value pairs that act as configuration parameters for Kafka producers. Most of these configurations will not be needed, but if you need to customize your Kafka producer, you may use this. See a detailed list: https://docs.confluent.io/platform/current/installation/configuration/producer-configs.html
+      </td>
+    </tr>
+    <tr>
+      <td>
+        schema
+      </td>
+      <td>
+        <code style="color: green">str</code>
+      </td>
+      <td>
+        n/a
       </td>
     </tr>
   </table>
 </div>
 
-### `DELTA_CDC` Read
+### `KAFKA` Read
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -332,79 +354,156 @@ and Beam SQL is invoked via the Managed API under the hood.
     </tr>
     <tr>
       <td>
-        <strong>table</strong>
+        <strong>bootstrap_servers</strong>
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        Identifier of the Delta Lake table.
+        A list of host/port pairs to use for establishing the initial connection to the Kafka cluster. The client will make use of all servers irrespective of which servers are specified here for bootstrapping—this list only impacts the initial hosts used to discover the full set of servers. This list should be in the form `host1:port1,host2:port2,...`
       </td>
     </tr>
     <tr>
       <td>
-        start_version
+        <strong>topic</strong>
       </td>
       <td>
-        <code style="color: #f54251">int64</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        Start version of the Delta Lake table to read changes from. Either start_version or start_timestamp must be set.
+        n/a
       </td>
     </tr>
     <tr>
       <td>
-        start_timestamp
+        allow_duplicates
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: orange">boolean</code>
       </td>
       <td>
-        Start timestamp of the Delta Lake table to read changes from. Either start_version or start_timestamp must be set.
+        If the Kafka read allows duplicates.
       </td>
     </tr>
     <tr>
       <td>
-        end_version
+        confluent_schema_registry_subject
       </td>
       <td>
-        <code style="color: #f54251">int64</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        End version of the Delta Lake table to read changes up to.
+        n/a
       </td>
     </tr>
     <tr>
       <td>
-        end_timestamp
+        confluent_schema_registry_url
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        End timestamp of the Delta Lake table to read changes up to.
+        n/a
       </td>
     </tr>
     <tr>
       <td>
-        hadoop_config
+        consumer_config_updates
       </td>
       <td>
         <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
       </td>
       <td>
-        Properties passed to the Hadoop Configuration.
+        A list of key-value pairs that act as configuration parameters for Kafka consumers. Most of these configurations will not be needed, but if you need to customize your Kafka consumer, you may use this. See a detailed list: https://docs.confluent.io/platform/current/installation/configuration/consumer-configs.html
       </td>
     </tr>
     <tr>
       <td>
-        include_metadata_columns
+        file_descriptor_path
       </td>
       <td>
-        <code>list[<span style="color: green;">str</span>]</code>
+        <code style="color: green">str</code>
+      </td>
+      <td>
+        The path to the Protocol Buffer File Descriptor Set file. This file is used for schema definition and message serialization.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        format
+      </td>
+      <td>
+        <code style="color: green">str</code>
+      </td>
+      <td>
+        The encoding format for the data stored in Kafka. Valid options are: RAW,STRING,AVRO,JSON,PROTO
+      </td>
+    </tr>
+    <tr>
+      <td>
+        message_name
+      </td>
+      <td>
+        <code style="color: green">str</code>
+      </td>
+      <td>
+        The name of the Protocol Buffer message to be used for schema extraction and data conversion.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        offset_deduplication
+      </td>
+      <td>
+        <code style="color: orange">boolean</code>
+      </td>
+      <td>
+        If the redistribute is using offset deduplication mode.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        redistribute_by_record_key
       </td>
       <td>
-        Metadata columns to include in the output rows. Supported columns are: _change_type, _commit_version, and _commit_timestamp.
+        <code style="color: orange">boolean</code>
+      </td>
+      <td>
+        If the redistribute keys by the Kafka record key.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        redistribute_num_keys
+      </td>
+      <td>
+        <code style="color: #f54251">int32</code>
+      </td>
+      <td>
+        The number of keys for redistributing Kafka inputs.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        redistributed
+      </td>
+      <td>
+        <code style="color: orange">boolean</code>
+      </td>
+      <td>
+        If the Kafka read should be redistributed.
+      </td>
+    </tr>
+    <tr>
+      <td>
+        schema
+      </td>
+      <td>
+        <code style="color: green">str</code>
+      </td>
+      <td>
+        The schema in which the data is encoded in the Kafka topic. For AVRO data, this is a schema defined with AVRO schema syntax (https://avro.apache.org/docs/1.10.2/spec.html#schemas). For JSON data, this is a schema defined with JSON-schema syntax (https://json-schema.org/). If a URL to Confluent Schema Registry is provided, then this field is ignored, and the schema is fetched from Confluent Schema Registry.
       </td>
     </tr>
   </table>
@@ -677,10 +776,21 @@ For more information on table properties, please visit https://iceberg.apache.or
         For a streaming pipeline, sets the frequency at which snapshots are produced.
       </td>
     </tr>
+    <tr>
+      <td>
+        write_properties
+      </td>
+      <td>
+        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
+      </td>
+      <td>
+        Properties applied to the underlying file writer (e.g. Parquet write properties like 'write.parquet.bloom-filter-enabled.column.<col>').
+      </td>
+    </tr>
   </table>
 </div>
 
-### `KAFKA` Read
+### `ICEBERG_CDC` Read
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -691,251 +801,257 @@ For more information on table properties, please visit https://iceberg.apache.or
     </tr>
     <tr>
       <td>
-        <strong>bootstrap_servers</strong>
+        <strong>table</strong>
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        A list of host/port pairs to use for establishing the initial connection to the Kafka cluster. The client will make use of all servers irrespective of which servers are specified here for bootstrapping—this list only impacts the initial hosts used to discover the full set of servers. This list should be in the form `host1:port1,host2:port2,...`
+        Identifier of the Iceberg table.
       </td>
     </tr>
     <tr>
       <td>
-        <strong>topic</strong>
+        catalog_name
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        n/a
+        Name of the catalog containing the table.
       </td>
     </tr>
     <tr>
       <td>
-        allow_duplicates
+        catalog_properties
       </td>
       <td>
-        <code style="color: orange">boolean</code>
+        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
       </td>
       <td>
-        If the Kafka read allows duplicates.
+        Properties used to set up the Iceberg catalog.
       </td>
     </tr>
     <tr>
       <td>
-        confluent_schema_registry_subject
+        config_properties
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
       </td>
       <td>
-        n/a
+        Properties passed to the Hadoop Configuration.
       </td>
     </tr>
     <tr>
       <td>
-        confluent_schema_registry_url
+        drop
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code>list[<span style="color: green;">str</span>]</code>
       </td>
       <td>
-        n/a
+        A subset of column names to exclude from reading. If null or empty, all columns will be read.
       </td>
     </tr>
     <tr>
       <td>
-        consumer_config_updates
+        filter
       </td>
       <td>
-        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        A list of key-value pairs that act as configuration parameters for Kafka consumers. Most of these configurations will not be needed, but if you need to customize your Kafka consumer, you may use this. See a detailed list: https://docs.confluent.io/platform/current/installation/configuration/consumer-configs.html
+        SQL-like predicate to filter data at scan time. Example: "id > 5 AND status = 'ACTIVE'". Uses Apache Calcite syntax: https://calcite.apache.org/docs/reference.html
       </td>
     </tr>
     <tr>
       <td>
-        file_descriptor_path
+        from_snapshot
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: #f54251">int64</code>
       </td>
       <td>
-        The path to the Protocol Buffer File Descriptor Set file. This file is used for schema definition and message serialization.
+        Starts reading from this snapshot ID (inclusive).
       </td>
     </tr>
     <tr>
       <td>
-        format
+        from_timestamp
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: #f54251">int64</code>
       </td>
       <td>
-        The encoding format for the data stored in Kafka. Valid options are: RAW,STRING,AVRO,JSON,PROTO
+        Starts reading from the first snapshot (inclusive) that was created after this timestamp (in milliseconds).
       </td>
     </tr>
     <tr>
       <td>
-        message_name
+        include_metadata_columns
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code>list[<span style="color: green;">str</span>]</code>
       </td>
       <td>
-        The name of the Protocol Buffer message to be used for schema extraction and data conversion.
+        List of top-level metadata columns to include with CDC output rows. Supported columns: 
+- `_change_type`
+- `_row_id`
+- `_last_updated_sequence_number`
+- `_commit_snapshot_id`
+- `_commit_snapshot_sequence_number`
+
       </td>
     </tr>
     <tr>
       <td>
-        offset_deduplication
+        keep
       </td>
       <td>
-        <code style="color: orange">boolean</code>
+        <code>list[<span style="color: green;">str</span>]</code>
       </td>
       <td>
-        If the redistribute is using offset deduplication mode.
+        A subset of column names to read exclusively. If null or empty, all columns will be read.
       </td>
     </tr>
     <tr>
       <td>
-        redistribute_by_record_key
+        poll_interval_seconds
       </td>
       <td>
-        <code style="color: orange">boolean</code>
+        <code style="color: #f54251">int32</code>
       </td>
       <td>
-        If the redistribute keys by the Kafka record key.
+        The interval at which to poll for new snapshots. Defaults to 60 seconds.
       </td>
     </tr>
     <tr>
       <td>
-        redistribute_num_keys
+        starting_strategy
       </td>
       <td>
-        <code style="color: #f54251">int32</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        The number of keys for redistributing Kafka inputs.
+        The source's starting strategy. Valid options are: "earliest" or "latest". Can be overriden by setting a starting snapshot or timestamp. Defaults to earliest for batch, and latest for streaming.
       </td>
     </tr>
     <tr>
       <td>
-        redistributed
+        streaming
       </td>
       <td>
         <code style="color: orange">boolean</code>
       </td>
       <td>
-        If the Kafka read should be redistributed.
+        Enables streaming reads, where source continuously polls for snapshots forever.
       </td>
     </tr>
     <tr>
       <td>
-        schema
+        to_snapshot
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: #f54251">int64</code>
       </td>
       <td>
-        The schema in which the data is encoded in the Kafka topic. For AVRO data, this is a schema defined with AVRO schema syntax (https://avro.apache.org/docs/1.10.2/spec.html#schemas). For JSON data, this is a schema defined with JSON-schema syntax (https://json-schema.org/). If a URL to Confluent Schema Registry is provided, then this field is ignored, and the schema is fetched from Confluent Schema Registry.
+        Reads up to this snapshot ID (inclusive).
       </td>
     </tr>
-  </table>
-</div>
-
-### `KAFKA` Write
-
-<div class="table-container-wrapper">
-  <table class="table table-bordered">
-    <tr>
-      <th>Configuration</th>
-      <th>Type</th>
-      <th>Description</th>
-    </tr>
     <tr>
       <td>
-        <strong>bootstrap_servers</strong>
+        to_timestamp
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: #f54251">int64</code>
       </td>
       <td>
-        A list of host/port pairs to use for establishing the initial connection to the Kafka cluster. The client will make use of all servers irrespective of which servers are specified here for bootstrapping—this list only impacts the initial hosts used to discover the full set of servers. | Format: host1:port1,host2:port2,...
+        Reads up to the latest snapshot (inclusive) created before this timestamp (in milliseconds).
       </td>
     </tr>
     <tr>
       <td>
-        <strong>format</strong>
+        watermark_column
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        The encoding format for the data stored in Kafka. Valid options are: RAW,JSON,AVRO,PROTO
+        Column used to derive the source's output watermark. Must be an existing, required, top-level column of type 'long' or 'timestamp'. If not set, the watermark advances according to snapshot commit timestamp.
       </td>
     </tr>
     <tr>
       <td>
-        <strong>topic</strong>
+        watermark_column_time_unit
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        n/a
+        Time unit used to interpret watermark column of type LONG. One of NANOSECONDS, MICROSECONDS, MILLISECONDS, SECONDS, MINUTES, HOURS, DAYS. Defaults to MICROSECONDS.
       </td>
     </tr>
+  </table>
+</div>
+
+### `DELTA` Read
+
+<div class="table-container-wrapper">
+  <table class="table table-bordered">
+    <tr>
+      <th>Configuration</th>
+      <th>Type</th>
+      <th>Description</th>
+    </tr>
     <tr>
       <td>
-        file_descriptor_path
+        <strong>table</strong>
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        The path to the Protocol Buffer File Descriptor Set file. This file is used for schema definition and message serialization.
+        Identifier of the Delta Lake table.
       </td>
     </tr>
     <tr>
       <td>
-        message_name
+        hadoop_config
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
       </td>
       <td>
-        The name of the Protocol Buffer message to be used for schema extraction and data conversion.
+        Properties passed to the Hadoop Configuration.
       </td>
     </tr>
     <tr>
       <td>
-        producer_config_updates
+        timestamp
       </td>
       <td>
-        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        A list of key-value pairs that act as configuration parameters for Kafka producers. Most of these configurations will not be needed, but if you need to customize your Kafka producer, you may use this. See a detailed list: https://docs.confluent.io/platform/current/installation/configuration/producer-configs.html
+        Timestamp of the Delta Lake table to read.
       </td>
     </tr>
     <tr>
       <td>
-        schema
+        version
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: #f54251">int64</code>
       </td>
       <td>
-        n/a
+        Version of the Delta Lake table to read.
       </td>
     </tr>
   </table>
 </div>
 
-### `ICEBERG_CDC` Read
+### `BIGQUERY` Read
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -946,162 +1062,141 @@ For more information on table properties, please visit https://iceberg.apache.or
     </tr>
     <tr>
       <td>
-        <strong>table</strong>
+        kms_key
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        Identifier of the Iceberg table.
+        Use this Cloud KMS key to encrypt your data
       </td>
     </tr>
     <tr>
       <td>
-        catalog_name
+        query
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        Name of the catalog containing the table.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        catalog_properties
-      </td>
-      <td>
-        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
-      </td>
-      <td>
-        Properties used to set up the Iceberg catalog.
+        The SQL query to be executed to read from the BigQuery table.
       </td>
     </tr>
     <tr>
       <td>
-        config_properties
+        row_restriction
       </td>
       <td>
-        <code>map[<span style="color: green;">str</span>, <span style="color: green;">str</span>]</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        Properties passed to the Hadoop Configuration.
+        Read only rows that match this filter, which must be compatible with Google standard SQL. This is not supported when reading via query.
       </td>
     </tr>
     <tr>
       <td>
-        drop
+        fields
       </td>
       <td>
         <code>list[<span style="color: green;">str</span>]</code>
       </td>
       <td>
-        A subset of column names to exclude from reading. If null or empty, all columns will be read.
+        Read only the specified fields (columns) from a BigQuery table. Fields may not be returned in the order specified. If no value is specified, then all fields are returned. Example: "col1, col2, col3"
       </td>
     </tr>
     <tr>
       <td>
-        filter
+        table
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        SQL-like predicate to filter data at scan time. Example: "id > 5 AND status = 'ACTIVE'". Uses Apache Calcite syntax: https://calcite.apache.org/docs/reference.html
-      </td>
-    </tr>
-    <tr>
-      <td>
-        from_snapshot
-      </td>
-      <td>
-        <code style="color: #f54251">int64</code>
-      </td>
-      <td>
-        Starts reading from this snapshot ID (inclusive).
+        The fully-qualified name of the BigQuery table to read from. Format: [${PROJECT}:]${DATASET}.${TABLE}
       </td>
     </tr>
+  </table>
+</div>
+
+### `BIGQUERY` Write
+
+<div class="table-container-wrapper">
+  <table class="table table-bordered">
     <tr>
-      <td>
-        from_timestamp
-      </td>
-      <td>
-        <code style="color: #f54251">int64</code>
-      </td>
-      <td>
-        Starts reading from the first snapshot (inclusive) that was created after this timestamp (in milliseconds).
-      </td>
+      <th>Configuration</th>
+      <th>Type</th>
+      <th>Description</th>
     </tr>
     <tr>
       <td>
-        keep
+        <strong>table</strong>
       </td>
       <td>
-        <code>list[<span style="color: green;">str</span>]</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        A subset of column names to read exclusively. If null or empty, all columns will be read.
+        The bigquery table to write to. Format: [${PROJECT}:]${DATASET}.${TABLE}
       </td>
     </tr>
     <tr>
       <td>
-        poll_interval_seconds
+        drop
       </td>
       <td>
-        <code style="color: #f54251">int32</code>
+        <code>list[<span style="color: green;">str</span>]</code>
       </td>
       <td>
-        The interval at which to poll for new snapshots. Defaults to 60 seconds.
+        A list of field names to drop from the input record before writing. Is mutually exclusive with 'keep' and 'only'.
       </td>
     </tr>
     <tr>
       <td>
-        starting_strategy
+        keep
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code>list[<span style="color: green;">str</span>]</code>
       </td>
       <td>
-        The source's starting strategy. Valid options are: "earliest" or "latest". Can be overriden by setting a starting snapshot or timestamp. Defaults to earliest for batch, and latest for streaming.
+        A list of field names to keep in the input record. All other fields are dropped before writing. Is mutually exclusive with 'drop' and 'only'.
       </td>
     </tr>
     <tr>
       <td>
-        streaming
+        kms_key
       </td>
       <td>
-        <code style="color: orange">boolean</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        Enables streaming reads, where source continuously polls for snapshots forever.
+        Use this Cloud KMS key to encrypt your data
       </td>
     </tr>
     <tr>
       <td>
-        to_snapshot
+        only
       </td>
       <td>
-        <code style="color: #f54251">int64</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        Reads up to this snapshot ID (inclusive).
+        The name of a single record field that should be written. Is mutually exclusive with 'keep' and 'drop'.
       </td>
     </tr>
     <tr>
       <td>
-        to_timestamp
+        triggering_frequency_seconds
       </td>
       <td>
         <code style="color: #f54251">int64</code>
       </td>
       <td>
-        Reads up to the latest snapshot (inclusive) created before this timestamp (in milliseconds).
+        Determines how often to 'commit' progress into BigQuery. Default is every 5 seconds.
       </td>
     </tr>
   </table>
 </div>
 
-### `POSTGRES` Read
+### `SQLSERVER` Read
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -1132,6 +1227,17 @@ For more information on table properties, please visit https://iceberg.apache.or
         Used to set connection properties passed to the JDBC driver not already defined as standalone parameter (e.g. username and password can be set using parameters above accordingly). Format of the string must be "key1=value1;key2=value2;".
       </td>
     </tr>
+    <tr>
+      <td>
+        disable_auto_commit
+      </td>
+      <td>
+        <code style="color: orange">boolean</code>
+      </td>
+      <td>
+        Whether to disable auto commit on read. Defaults to true if not provided. The need for this config varies depending on the database platform. Informix requires this to be set to false while Postgres requires this to be set to true.
+      </td>
+    </tr>
     <tr>
       <td>
         fetch_size
@@ -1223,7 +1329,7 @@ For more information on table properties, please visit https://iceberg.apache.or
   </table>
 </div>
 
-### `POSTGRES` Write
+### `SQLSERVER` Write
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -1323,7 +1429,7 @@ For more information on table properties, please visit https://iceberg.apache.or
   </table>
 </div>
 
-### `SQLSERVER` Write
+### `POSTGRES` Write
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -1423,7 +1529,7 @@ For more information on table properties, please visit https://iceberg.apache.or
   </table>
 </div>
 
-### `SQLSERVER` Read
+### `POSTGRES` Read
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -1454,17 +1560,6 @@ For more information on table properties, please visit https://iceberg.apache.or
         Used to set connection properties passed to the JDBC driver not already defined as standalone parameter (e.g. username and password can be set using parameters above accordingly). Format of the string must be "key1=value1;key2=value2;".
       </td>
     </tr>
-    <tr>
-      <td>
-        disable_auto_commit
-      </td>
-      <td>
-        <code style="color: orange">boolean</code>
-      </td>
-      <td>
-        Whether to disable auto commit on read. Defaults to true if not provided. The need for this config varies depending on the database platform. Informix requires this to be set to false while Postgres requires this to be set to true.
-      </td>
-    </tr>
     <tr>
       <td>
         fetch_size
@@ -1556,7 +1651,7 @@ For more information on table properties, please visit https://iceberg.apache.or
   </table>
 </div>
 
-### `BIGQUERY` Read
+### `MYSQL` Write
 
 <div class="table-container-wrapper">
   <table class="table table-bordered">
@@ -1567,135 +1662,101 @@ For more information on table properties, please visit https://iceberg.apache.or
     </tr>
     <tr>
       <td>
-        kms_key
+        <strong>jdbc_url</strong>
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        Use this Cloud KMS key to encrypt your data
+        Connection URL for the JDBC sink.
       </td>
     </tr>
     <tr>
       <td>
-        query
+        autosharding
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: orange">boolean</code>
       </td>
       <td>
-        The SQL query to be executed to read from the BigQuery table.
+        If true, enables using a dynamically determined number of shards to write.
       </td>
     </tr>
     <tr>
       <td>
-        row_restriction
+        batch_size
       </td>
       <td>
-        <code style="color: green">str</code>
+        <code style="color: #f54251">int64</code>
       </td>
       <td>
-        Read only rows that match this filter, which must be compatible with Google standard SQL. This is not supported when reading via query.
+        n/a
       </td>
     </tr>
     <tr>
       <td>
-        fields
+        connection_init_sql
       </td>
       <td>
         <code>list[<span style="color: green;">str</span>]</code>
       </td>
       <td>
-        Read only the specified fields (columns) from a BigQuery table. Fields may not be returned in the order specified. If no value is specified, then all fields are returned. Example: "col1, col2, col3"
+        Sets the connection init sql statements used by the Driver. Only MySQL and MariaDB support this.
       </td>
     </tr>
     <tr>
       <td>
-        table
+        connection_properties
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        The fully-qualified name of the BigQuery table to read from. Format: [${PROJECT}:]${DATASET}.${TABLE}
+        Used to set connection properties passed to the JDBC driver not already defined as standalone parameter (e.g. username and password can be set using parameters above accordingly). Format of the string must be "key1=value1;key2=value2;".
       </td>
     </tr>
-  </table>
-</div>
-
-### `BIGQUERY` Write
-
-<div class="table-container-wrapper">
-  <table class="table table-bordered">
-    <tr>
-      <th>Configuration</th>
-      <th>Type</th>
-      <th>Description</th>
-    </tr>
     <tr>
       <td>
-        <strong>table</strong>
+        location
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        The bigquery table to write to. Format: [${PROJECT}:]${DATASET}.${TABLE}
-      </td>
-    </tr>
-    <tr>
-      <td>
-        drop
-      </td>
-      <td>
-        <code>list[<span style="color: green;">str</span>]</code>
-      </td>
-      <td>
-        A list of field names to drop from the input record before writing. Is mutually exclusive with 'keep' and 'only'.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        keep
-      </td>
-      <td>
-        <code>list[<span style="color: green;">str</span>]</code>
-      </td>
-      <td>
-        A list of field names to keep in the input record. All other fields are dropped before writing. Is mutually exclusive with 'drop' and 'only'.
+        Name of the table to write to.
       </td>
     </tr>
     <tr>
       <td>
-        kms_key
+        password
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        Use this Cloud KMS key to encrypt your data
+        Password for the JDBC source.
       </td>
     </tr>
     <tr>
       <td>
-        only
+        username
       </td>
       <td>
         <code style="color: green">str</code>
       </td>
       <td>
-        The name of a single record field that should be written. Is mutually exclusive with 'keep' and 'drop'.
+        Username for the JDBC source.
       </td>
     </tr>
     <tr>
       <td>
-        triggering_frequency_seconds
+        write_statement
       </td>
       <td>
-        <code style="color: #f54251">int64</code>
+        <code style="color: green">str</code>
       </td>
       <td>
-        Determines how often to 'commit' progress into BigQuery. Default is every 5 seconds.
+        SQL query used to insert records into the JDBC sink.
       </td>
     </tr>
   </table>
@@ -1845,114 +1906,3 @@ For more information on table properties, please visit https://iceberg.apache.or
   </table>
 </div>
 
-### `MYSQL` Write
-
-<div class="table-container-wrapper">
-  <table class="table table-bordered">
-    <tr>
-      <th>Configuration</th>
-      <th>Type</th>
-      <th>Description</th>
-    </tr>
-    <tr>
-      <td>
-        <strong>jdbc_url</strong>
-      </td>
-      <td>
-        <code style="color: green">str</code>
-      </td>
-      <td>
-        Connection URL for the JDBC sink.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        autosharding
-      </td>
-      <td>
-        <code style="color: orange">boolean</code>
-      </td>
-      <td>
-        If true, enables using a dynamically determined number of shards to write.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        batch_size
-      </td>
-      <td>
-        <code style="color: #f54251">int64</code>
-      </td>
-      <td>
-        n/a
-      </td>
-    </tr>
-    <tr>
-      <td>
-        connection_init_sql
-      </td>
-      <td>
-        <code>list[<span style="color: green;">str</span>]</code>
-      </td>
-      <td>
-        Sets the connection init sql statements used by the Driver. Only MySQL and MariaDB support this.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        connection_properties
-      </td>
-      <td>
-        <code style="color: green">str</code>
-      </td>
-      <td>
-        Used to set connection properties passed to the JDBC driver not already defined as standalone parameter (e.g. username and password can be set using parameters above accordingly). Format of the string must be "key1=value1;key2=value2;".
-      </td>
-    </tr>
-    <tr>
-      <td>
-        location
-      </td>
-      <td>
-        <code style="color: green">str</code>
-      </td>
-      <td>
-        Name of the table to write to.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        password
-      </td>
-      <td>
-        <code style="color: green">str</code>
-      </td>
-      <td>
-        Password for the JDBC source.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        username
-      </td>
-      <td>
-        <code style="color: green">str</code>
-      </td>
-      <td>
-        Username for the JDBC source.
-      </td>
-    </tr>
-    <tr>
-      <td>
-        write_statement
-      </td>
-      <td>
-        <code style="color: green">str</code>
-      </td>
-      <td>
-        SQL query used to insert records into the JDBC sink.
-      </td>
-    </tr>
-  </table>
-</div>
-