Update READMEs via plugin

v1/README_Cloud_PubSub_to_Datadog.md

@@ -4,7 +4,7 @@ Pub/Sub to Datadog template
 The Pub/Sub to Datadog template is a streaming pipeline that reads messages from
 a Pub/Sub subscription and writes the message payload to Datadog by using a
 Datadog endpoint. The most common use case for this template is to export log
-files to Datadog. For more information check out <a href="https://docs.datadoghq.com/integrations/google_cloud_platform/?tab=project#log-collection">Datadog's log collection process</a>.
+files to Datadog.
 
 Before writing to Datadog, you can apply a JavaScript user-defined function to
 the message payload. Any messages that experience processing failures are
@@ -40,7 +40,7 @@ on [Metadata Annotations](https://github.com/GoogleCloudPlatform/DataflowTemplat
 * **apiKey** : The Datadog API key. You must provide this value if the `apiKeySource` is set to `PLAINTEXT` or `KMS`. For more information, see API and Application Keys (https://docs.datadoghq.com/account_management/api-app-keys/) in the Datadog documentation.
 * **batchCount** : The batch size for sending multiple events to Datadog. The default is `1` (no batching).
 * **parallelism** : The maximum number of parallel requests. The default is `1` (no parallelism).
-* **includePubsubMessage** : Whether to include the full Pub/Sub message in the payload. The default is `true` (all elements, including data element, are included in the payload).
+* **includePubsubMessage** : Whether to include the full Pub/Sub message in the payload. The default is `true` (all elements, including the data element, are included in the payload).
 * **apiKeyKMSEncryptionKey** : The Cloud KMS key to use to decrypt the API Key. You must provide this parameter if the `apiKeySource` is set to `KMS`. If the Cloud KMS key is provided, you must pass in an encrypted API Key. (Example: projects/your-project-id/locations/global/keyRings/your-keyring/cryptoKeys/your-key-name).
 * **apiKeySecretId** : The Secret Manager secret ID for the API Key. You must provide this parameter if the `apiKeySource` is set to `SECRET_MANAGER`. (Example: projects/your-project-id/secrets/your-secret/versions/your-secret-version).
 * **apiKeySource** : The source of the API key. The following values are supported: `PLAINTEXT`, `KMS`, and `SECRET_MANAGER`. You must provide this parameter if you're using Secret Manager. If `apiKeySource` is set to `KMS`, you must also provide `apiKeyKMSEncryptionKey` and encrypted `API Key`. If `apiKeySource` is set to `SECRET_MANAGER`, you must also provide `apiKeySecretId`. If `apiKeySource` is set to `PLAINTEXT`, you must also provide `apiKey`.
@@ -145,7 +145,7 @@ export OUTPUT_DEADLETTER_TOPIC=<outputDeadletterTopic>
 export API_KEY=<apiKey>
 export BATCH_COUNT=<batchCount>
 export PARALLELISM=<parallelism>
-export INCLUDE_PUBSUB_MESSAGE=<includePubsubMessage>
+export INCLUDE_PUBSUB_MESSAGE=true
 export API_KEY_KMSENCRYPTION_KEY=<apiKeyKMSEncryptionKey>
 export API_KEY_SECRET_ID=<apiKeySecretId>
 export API_KEY_SOURCE=<apiKeySource>
@@ -196,7 +196,7 @@ export OUTPUT_DEADLETTER_TOPIC=<outputDeadletterTopic>
 export API_KEY=<apiKey>
 export BATCH_COUNT=<batchCount>
 export PARALLELISM=<parallelism>
-export INCLUDE_PUBSUB_MESSAGE=<includePubsubMessage>
+export INCLUDE_PUBSUB_MESSAGE=true
 export API_KEY_KMSENCRYPTION_KEY=<apiKeyKMSEncryptionKey>
 export API_KEY_SECRET_ID=<apiKeySecretId>
 export API_KEY_SOURCE=<apiKeySource>
@@ -263,7 +263,7 @@ resource "google_dataflow_job" "cloud_pubsub_to_datadog" {
     # apiKey = "<apiKey>"
     # batchCount = "<batchCount>"
     # parallelism = "<parallelism>"
-    # includePubsubMessage = "<includePubsubMessage>"
+    # includePubsubMessage = "true"
     # apiKeyKMSEncryptionKey = "projects/your-project-id/locations/global/keyRings/your-keyring/cryptoKeys/your-key-name"
     # apiKeySecretId = "projects/your-project-id/secrets/your-secret/versions/your-secret-version"
     # apiKeySource = "<apiKeySource>"

v2/bigquery-to-bigtable/README_BigQuery_to_Bigtable.md

@@ -28,6 +28,7 @@ on [Metadata Annotations](https://github.com/GoogleCloudPlatform/DataflowTemplat
 * **query** : The SQL query to use to read data from BigQuery. If the BigQuery dataset is in a different project than the Dataflow job, specify the full dataset name in the SQL query, for example: <PROJECT_ID>.<DATASET_NAME>.<TABLE_NAME>. By default, the `query` parameter uses GoogleSQL (https://cloud.google.com/bigquery/docs/introduction-sql), unless `useLegacySql` is `true`. You must specify either `inputTableSpec` or `query`. If you set both parameters, the template uses the `query` parameter. (Example: select * from sampledb.sample_table).
 * **useLegacySql** : Set to true to use legacy SQL. This parameter only applies when using the `query` parameter. Defaults to: false.
 * **queryLocation** : Needed when reading from an authorized view without underlying table's permission. (Example: US).
+* **queryTempDataset** : With this option, you can set an existing dataset to create the temporary table to store the results of the query. (Example: temp_dataset).
 * **bigtableRpcAttemptTimeoutMs** : The timeout for each Bigtable RPC attempt in milliseconds.
 * **bigtableRpcTimeoutMs** : The total timeout for a Bigtable RPC operation in milliseconds.
 * **bigtableAdditionalRetryCodes** : The additional retry codes. (Example: RESOURCE_EXHAUSTED,DEADLINE_EXCEEDED).
@@ -125,6 +126,7 @@ export OUTPUT_DEADLETTER_TABLE=<outputDeadletterTable>
 export QUERY=<query>
 export USE_LEGACY_SQL=false
 export QUERY_LOCATION=<queryLocation>
+export QUERY_TEMP_DATASET=<queryTempDataset>
 export BIGTABLE_RPC_ATTEMPT_TIMEOUT_MS=<bigtableRpcAttemptTimeoutMs>
 export BIGTABLE_RPC_TIMEOUT_MS=<bigtableRpcTimeoutMs>
 export BIGTABLE_ADDITIONAL_RETRY_CODES=<bigtableAdditionalRetryCodes>
@@ -144,6 +146,7 @@ gcloud dataflow flex-template run "bigquery-to-bigtable-job" \
   --parameters "query=$QUERY" \
   --parameters "useLegacySql=$USE_LEGACY_SQL" \
   --parameters "queryLocation=$QUERY_LOCATION" \
+  --parameters "queryTempDataset=$QUERY_TEMP_DATASET" \
   --parameters "bigtableRpcAttemptTimeoutMs=$BIGTABLE_RPC_ATTEMPT_TIMEOUT_MS" \
   --parameters "bigtableRpcTimeoutMs=$BIGTABLE_RPC_TIMEOUT_MS" \
   --parameters "bigtableAdditionalRetryCodes=$BIGTABLE_ADDITIONAL_RETRY_CODES" \
@@ -184,6 +187,7 @@ export OUTPUT_DEADLETTER_TABLE=<outputDeadletterTable>
 export QUERY=<query>
 export USE_LEGACY_SQL=false
 export QUERY_LOCATION=<queryLocation>
+export QUERY_TEMP_DATASET=<queryTempDataset>
 export BIGTABLE_RPC_ATTEMPT_TIMEOUT_MS=<bigtableRpcAttemptTimeoutMs>
 export BIGTABLE_RPC_TIMEOUT_MS=<bigtableRpcTimeoutMs>
 export BIGTABLE_ADDITIONAL_RETRY_CODES=<bigtableAdditionalRetryCodes>
@@ -200,7 +204,7 @@ mvn clean package -PtemplatesRun \
 -Dregion="$REGION" \
 -DjobName="bigquery-to-bigtable-job" \
 -DtemplateName="BigQuery_to_Bigtable" \
--Dparameters="readIdColumn=$READ_ID_COLUMN,inputTableSpec=$INPUT_TABLE_SPEC,outputDeadletterTable=$OUTPUT_DEADLETTER_TABLE,query=$QUERY,useLegacySql=$USE_LEGACY_SQL,queryLocation=$QUERY_LOCATION,bigtableRpcAttemptTimeoutMs=$BIGTABLE_RPC_ATTEMPT_TIMEOUT_MS,bigtableRpcTimeoutMs=$BIGTABLE_RPC_TIMEOUT_MS,bigtableAdditionalRetryCodes=$BIGTABLE_ADDITIONAL_RETRY_CODES,bigtableWriteInstanceId=$BIGTABLE_WRITE_INSTANCE_ID,bigtableWriteTableId=$BIGTABLE_WRITE_TABLE_ID,bigtableWriteColumnFamily=$BIGTABLE_WRITE_COLUMN_FAMILY,bigtableWriteAppProfile=$BIGTABLE_WRITE_APP_PROFILE,bigtableWriteProjectId=$BIGTABLE_WRITE_PROJECT_ID,bigtableBulkWriteLatencyTargetMs=$BIGTABLE_BULK_WRITE_LATENCY_TARGET_MS,bigtableBulkWriteMaxRowKeyCount=$BIGTABLE_BULK_WRITE_MAX_ROW_KEY_COUNT,bigtableBulkWriteMaxRequestSizeBytes=$BIGTABLE_BULK_WRITE_MAX_REQUEST_SIZE_BYTES" \
+-Dparameters="readIdColumn=$READ_ID_COLUMN,inputTableSpec=$INPUT_TABLE_SPEC,outputDeadletterTable=$OUTPUT_DEADLETTER_TABLE,query=$QUERY,useLegacySql=$USE_LEGACY_SQL,queryLocation=$QUERY_LOCATION,queryTempDataset=$QUERY_TEMP_DATASET,bigtableRpcAttemptTimeoutMs=$BIGTABLE_RPC_ATTEMPT_TIMEOUT_MS,bigtableRpcTimeoutMs=$BIGTABLE_RPC_TIMEOUT_MS,bigtableAdditionalRetryCodes=$BIGTABLE_ADDITIONAL_RETRY_CODES,bigtableWriteInstanceId=$BIGTABLE_WRITE_INSTANCE_ID,bigtableWriteTableId=$BIGTABLE_WRITE_TABLE_ID,bigtableWriteColumnFamily=$BIGTABLE_WRITE_COLUMN_FAMILY,bigtableWriteAppProfile=$BIGTABLE_WRITE_APP_PROFILE,bigtableWriteProjectId=$BIGTABLE_WRITE_PROJECT_ID,bigtableBulkWriteLatencyTargetMs=$BIGTABLE_BULK_WRITE_LATENCY_TARGET_MS,bigtableBulkWriteMaxRowKeyCount=$BIGTABLE_BULK_WRITE_MAX_ROW_KEY_COUNT,bigtableBulkWriteMaxRequestSizeBytes=$BIGTABLE_BULK_WRITE_MAX_REQUEST_SIZE_BYTES" \
 -f v2/bigquery-to-bigtable
 ```
 
@@ -254,6 +258,7 @@ resource "google_dataflow_flex_template_job" "bigquery_to_bigtable" {
     # query = "select * from sampledb.sample_table"
     # useLegacySql = "false"
     # queryLocation = "US"
+    # queryTempDataset = "temp_dataset"
     # bigtableRpcAttemptTimeoutMs = "<bigtableRpcAttemptTimeoutMs>"
     # bigtableRpcTimeoutMs = "<bigtableRpcTimeoutMs>"
     # bigtableAdditionalRetryCodes = "RESOURCE_EXHAUSTED,DEADLINE_EXCEEDED"

v2/datastream-to-spanner/README_Cloud_Datastream_to_Spanner.md

@@ -42,18 +42,18 @@ on [Metadata Annotations](https://github.com/GoogleCloudPlatform/DataflowTemplat
 
 ### Required parameters
 
-* **inputFilePattern** : The Cloud Storage file location that contains the Datastream files to replicate. Typically, this is the root path for a stream.
 * **instanceId** : The Spanner instance where the changes are replicated.
 * **databaseId** : The Spanner database where the changes are replicated.
 
 ### Optional parameters
 
+* **inputFilePattern** : The Cloud Storage file location that contains the Datastream files to replicate. Typically, this is the root path for a stream. Support for this feature has been disabled.
 * **inputFileFormat** : The format of the output file produced by Datastream. For example `avro,json`. Default, `avro`.
 * **sessionFilePath** : Session file path in Cloud Storage that contains mapping information from HarbourBridge.
 * **projectId** : The Spanner project ID.
 * **spannerHost** : The Cloud Spanner endpoint to call in the template. (Example: https://batch-spanner.googleapis.com). Defaults to: https://batch-spanner.googleapis.com.
-* **streamName** : The name or template for the stream to poll for schema information and source type.
 * **gcsPubSubSubscription** : The Pub/Sub subscription being used in a Cloud Storage notification policy. The name should be in the format of projects/<project-id>/subscriptions/<subscription-name>.
+* **streamName** : The name or template for the stream to poll for schema information and source type.
 * **shadowTablePrefix** : The prefix used to name shadow tables. Default: `shadow_`.
 * **shouldCreateShadowTables** : This flag indicates whether shadow tables must be created in Cloud Spanner database. Defaults to: true.
 * **rfcStartDateTime** : The starting DateTime used to fetch from Cloud Storage (https://tools.ietf.org/html/rfc3339). Defaults to: 1970-01-01T00:00:00.00Z.
@@ -73,7 +73,10 @@ on [Metadata Annotations](https://github.com/GoogleCloudPlatform/DataflowTemplat
 * **transformationClassName** : Fully qualified class name having the custom transformation logic.  It is a mandatory field in case transformationJarPath is specified. Defaults to empty.
 * **transformationCustomParameters** : String containing any custom parameters to be passed to the custom transformation class. Defaults to empty.
 * **filteredEventsDirectory** : This is the file path to store the events filtered via custom transformation. Default is a directory under the Dataflow job's temp location. The default value is enough under most conditions.
-* **shardingContextFilePath** : Sharding context file path in cloud storage used to populate shard id during migrations. It is of the format Map<stream_name, Map<db_name, shard_id>>.
+* **shardingContextFilePath** : Sharding context file path in cloud storage is used to populate the shard id in spanner database for each source shard.It is of the format Map<stream_name, Map<db_name, shard_id>>.
+* **tableOverrides** : These are the table name overrides from source to spanner. They are written in thefollowing format: [{SourceTableName1, SpannerTableName1}, {SourceTableName2, SpannerTableName2}]This example shows mapping Singers table to Vocalists and Albums table to Records. (Example: [{Singers, Vocalists}, {Albums, Records}]). Defaults to empty.
+* **columnOverrides** : These are the column name overrides from source to spanner. They are written in thefollowing format: [{SourceTableName1.SourceColumnName1, SourceTableName1.SpannerColumnName1}, {SourceTableName2.SourceColumnName1, SourceTableName2.SpannerColumnName1}]Note that the SourceTableName should remain the same in both the source and spanner pair. To override table names, use tableOverrides.The example shows mapping SingerName to TalentName and AlbumName to RecordName in Singers and Albums table respectively. (Example: [{Singers.SingerName, Singers.TalentName}, {Albums.AlbumName, Albums.RecordName}]). Defaults to empty.
+* **schemaOverridesFilePath** : A file which specifies the table and the column name overrides from source to spanner. Defaults to empty.
 
 
 
@@ -152,17 +155,17 @@ export REGION=us-central1
 export TEMPLATE_SPEC_GCSPATH="gs://$BUCKET_NAME/templates/flex/Cloud_Datastream_to_Spanner"
 
 ### Required
-export INPUT_FILE_PATTERN=<inputFilePattern>
 export INSTANCE_ID=<instanceId>
 export DATABASE_ID=<databaseId>
-export STREAM_NAME=<streamName>
 
 ### Optional
+export INPUT_FILE_PATTERN=<inputFilePattern>
 export INPUT_FILE_FORMAT=avro
 export SESSION_FILE_PATH=<sessionFilePath>
 export PROJECT_ID=<projectId>
 export SPANNER_HOST=https://batch-spanner.googleapis.com
 export GCS_PUB_SUB_SUBSCRIPTION=<gcsPubSubSubscription>
+export STREAM_NAME=<streamName>
 export SHADOW_TABLE_PREFIX=shadow_
 export SHOULD_CREATE_SHADOW_TABLES=true
 export RFC_START_DATE_TIME=1970-01-01T00:00:00.00Z
@@ -175,14 +178,17 @@ export DATASTREAM_SOURCE_TYPE=<datastreamSourceType>
 export ROUND_JSON_DECIMALS=false
 export RUN_MODE=regular
 export TRANSFORMATION_CONTEXT_FILE_PATH=<transformationContextFilePath>
-export SHARDING_CONTEXT_FILE_PATH=<shardingContextFilePath>
 export DIRECTORY_WATCH_DURATION_IN_MINUTES=10
 export SPANNER_PRIORITY=HIGH
 export DLQ_GCS_PUB_SUB_SUBSCRIPTION=<dlqGcsPubSubSubscription>
 export TRANSFORMATION_JAR_PATH=""
 export TRANSFORMATION_CLASS_NAME=""
 export TRANSFORMATION_CUSTOM_PARAMETERS=""
 export FILTERED_EVENTS_DIRECTORY=""
+export SHARDING_CONTEXT_FILE_PATH=<shardingContextFilePath>
+export TABLE_OVERRIDES=""
+export COLUMN_OVERRIDES=""
+export SCHEMA_OVERRIDES_FILE_PATH=""
 
 gcloud dataflow flex-template run "cloud-datastream-to-spanner-job" \
   --project "$PROJECT" \
@@ -216,7 +222,10 @@ gcloud dataflow flex-template run "cloud-datastream-to-spanner-job" \
   --parameters "transformationClassName=$TRANSFORMATION_CLASS_NAME" \
   --parameters "transformationCustomParameters=$TRANSFORMATION_CUSTOM_PARAMETERS" \
   --parameters "filteredEventsDirectory=$FILTERED_EVENTS_DIRECTORY" \
-  --parameters "shardingContextFilePath=$SHARDING_CONTEXT_FILE_PATH"
+  --parameters "shardingContextFilePath=$SHARDING_CONTEXT_FILE_PATH" \
+  --parameters "tableOverrides=$TABLE_OVERRIDES" \
+  --parameters "columnOverrides=$COLUMN_OVERRIDES" \
+  --parameters "schemaOverridesFilePath=$SCHEMA_OVERRIDES_FILE_PATH"
 ```
 
 For more information about the command, please check:
@@ -235,17 +244,17 @@ export BUCKET_NAME=<bucket-name>
 export REGION=us-central1
 
 ### Required
-export INPUT_FILE_PATTERN=<inputFilePattern>
 export INSTANCE_ID=<instanceId>
 export DATABASE_ID=<databaseId>
-export STREAM_NAME=<streamName>
 
 ### Optional
+export INPUT_FILE_PATTERN=<inputFilePattern>
 export INPUT_FILE_FORMAT=avro
 export SESSION_FILE_PATH=<sessionFilePath>
 export PROJECT_ID=<projectId>
 export SPANNER_HOST=https://batch-spanner.googleapis.com
 export GCS_PUB_SUB_SUBSCRIPTION=<gcsPubSubSubscription>
+export STREAM_NAME=<streamName>
 export SHADOW_TABLE_PREFIX=shadow_
 export SHOULD_CREATE_SHADOW_TABLES=true
 export RFC_START_DATE_TIME=1970-01-01T00:00:00.00Z
@@ -266,6 +275,9 @@ export TRANSFORMATION_CLASS_NAME=""
 export TRANSFORMATION_CUSTOM_PARAMETERS=""
 export FILTERED_EVENTS_DIRECTORY=""
 export SHARDING_CONTEXT_FILE_PATH=<shardingContextFilePath>
+export TABLE_OVERRIDES=""
+export COLUMN_OVERRIDES=""
+export SCHEMA_OVERRIDES_FILE_PATH=""
 
 mvn clean package -PtemplatesRun \
 -DskipTests \
@@ -274,7 +286,7 @@ mvn clean package -PtemplatesRun \
 -Dregion="$REGION" \
 -DjobName="cloud-datastream-to-spanner-job" \
 -DtemplateName="Cloud_Datastream_to_Spanner" \
--Dparameters="inputFilePattern=$INPUT_FILE_PATTERN,inputFileFormat=$INPUT_FILE_FORMAT,sessionFilePath=$SESSION_FILE_PATH,instanceId=$INSTANCE_ID,databaseId=$DATABASE_ID,projectId=$PROJECT_ID,spannerHost=$SPANNER_HOST,gcsPubSubSubscription=$GCS_PUB_SUB_SUBSCRIPTION,streamName=$STREAM_NAME,shadowTablePrefix=$SHADOW_TABLE_PREFIX,shouldCreateShadowTables=$SHOULD_CREATE_SHADOW_TABLES,rfcStartDateTime=$RFC_START_DATE_TIME,fileReadConcurrency=$FILE_READ_CONCURRENCY,deadLetterQueueDirectory=$DEAD_LETTER_QUEUE_DIRECTORY,dlqRetryMinutes=$DLQ_RETRY_MINUTES,dlqMaxRetryCount=$DLQ_MAX_RETRY_COUNT,dataStreamRootUrl=$DATA_STREAM_ROOT_URL,datastreamSourceType=$DATASTREAM_SOURCE_TYPE,roundJsonDecimals=$ROUND_JSON_DECIMALS,runMode=$RUN_MODE,transformationContextFilePath=$TRANSFORMATION_CONTEXT_FILE_PATH,directoryWatchDurationInMinutes=$DIRECTORY_WATCH_DURATION_IN_MINUTES,spannerPriority=$SPANNER_PRIORITY,dlqGcsPubSubSubscription=$DLQ_GCS_PUB_SUB_SUBSCRIPTION,transformationJarPath=$TRANSFORMATION_JAR_PATH,transformationClassName=$TRANSFORMATION_CLASS_NAME,transformationCustomParameters=$TRANSFORMATION_CUSTOM_PARAMETERS,filteredEventsDirectory=$FILTERED_EVENTS_DIRECTORY",shardingContextFilePath=$SHARDING_CONTEXT_FILE_PATH \
+-Dparameters="inputFilePattern=$INPUT_FILE_PATTERN,inputFileFormat=$INPUT_FILE_FORMAT,sessionFilePath=$SESSION_FILE_PATH,instanceId=$INSTANCE_ID,databaseId=$DATABASE_ID,projectId=$PROJECT_ID,spannerHost=$SPANNER_HOST,gcsPubSubSubscription=$GCS_PUB_SUB_SUBSCRIPTION,streamName=$STREAM_NAME,shadowTablePrefix=$SHADOW_TABLE_PREFIX,shouldCreateShadowTables=$SHOULD_CREATE_SHADOW_TABLES,rfcStartDateTime=$RFC_START_DATE_TIME,fileReadConcurrency=$FILE_READ_CONCURRENCY,deadLetterQueueDirectory=$DEAD_LETTER_QUEUE_DIRECTORY,dlqRetryMinutes=$DLQ_RETRY_MINUTES,dlqMaxRetryCount=$DLQ_MAX_RETRY_COUNT,dataStreamRootUrl=$DATA_STREAM_ROOT_URL,datastreamSourceType=$DATASTREAM_SOURCE_TYPE,roundJsonDecimals=$ROUND_JSON_DECIMALS,runMode=$RUN_MODE,transformationContextFilePath=$TRANSFORMATION_CONTEXT_FILE_PATH,directoryWatchDurationInMinutes=$DIRECTORY_WATCH_DURATION_IN_MINUTES,spannerPriority=$SPANNER_PRIORITY,dlqGcsPubSubSubscription=$DLQ_GCS_PUB_SUB_SUBSCRIPTION,transformationJarPath=$TRANSFORMATION_JAR_PATH,transformationClassName=$TRANSFORMATION_CLASS_NAME,transformationCustomParameters=$TRANSFORMATION_CUSTOM_PARAMETERS,filteredEventsDirectory=$FILTERED_EVENTS_DIRECTORY,shardingContextFilePath=$SHARDING_CONTEXT_FILE_PATH,tableOverrides=$TABLE_OVERRIDES,columnOverrides=$COLUMN_OVERRIDES,schemaOverridesFilePath=$SCHEMA_OVERRIDES_FILE_PATH" \
 -f v2/datastream-to-spanner
 ```
 
@@ -319,15 +331,15 @@ resource "google_dataflow_flex_template_job" "cloud_datastream_to_spanner" {
   name              = "cloud-datastream-to-spanner"
   region            = var.region
   parameters        = {
-    inputFilePattern = "<inputFilePattern>"
     instanceId = "<instanceId>"
     databaseId = "<databaseId>"
-    streamName = "<streamName>"
+    # inputFilePattern = "<inputFilePattern>"
     # inputFileFormat = "avro"
     # sessionFilePath = "<sessionFilePath>"
     # projectId = "<projectId>"
     # spannerHost = "https://batch-spanner.googleapis.com"
     # gcsPubSubSubscription = "<gcsPubSubSubscription>"
+    # streamName = "<streamName>"
     # shadowTablePrefix = "shadow_"
     # shouldCreateShadowTables = "true"
     # rfcStartDateTime = "1970-01-01T00:00:00.00Z"
@@ -348,6 +360,9 @@ resource "google_dataflow_flex_template_job" "cloud_datastream_to_spanner" {
     # transformationCustomParameters = ""
     # filteredEventsDirectory = ""
     # shardingContextFilePath = "<shardingContextFilePath>"
+    # tableOverrides = "[{Singers, Vocalists}, {Albums, Records}]"
+    # columnOverrides = "[{Singers.SingerName, Singers.TalentName}, {Albums.AlbumName, Albums.RecordName}]"
+    # schemaOverridesFilePath = ""
   }
 }
 ```