Class: Aws::Glue::Types::UpdateJobRequest
- Inherits:
-
Struct
- Object
- Struct
- Aws::Glue::Types::UpdateJobRequest
- Includes:
- Structure
- Defined in:
- lib/aws-sdk-glue/types.rb
Overview
Note:
When making an API call, you may pass UpdateJobRequest data as a hash:
{
job_name: "NameString", # required
job_update: { # required
description: "DescriptionString",
log_uri: "UriString",
role: "RoleString",
execution_property: {
max_concurrent_runs: 1,
},
command: {
name: "GenericString",
script_location: "ScriptLocationString",
python_version: "PythonVersionString",
},
default_arguments: {
"GenericString" => "GenericString",
},
non_overridable_arguments: {
"GenericString" => "GenericString",
},
connections: {
connections: ["GenericString"],
},
max_retries: 1,
allocated_capacity: 1,
timeout: 1,
max_capacity: 1.0,
worker_type: "Standard", # accepts Standard, G.1X, G.2X, G.025X
number_of_workers: 1,
security_configuration: "NameString",
notification_property: {
notify_delay_after: 1,
},
glue_version: "GlueVersionString",
code_gen_configuration_nodes: {
"NodeId" => {
athena_connector_source: {
name: "NodeName", # required
connection_name: "EnclosedInStringProperty", # required
connector_name: "EnclosedInStringProperty", # required
connection_type: "EnclosedInStringProperty", # required
connection_table: "EnclosedInStringPropertyWithQuote",
schema_name: "EnclosedInStringProperty", # required
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
jdbc_connector_source: {
name: "NodeName", # required
connection_name: "EnclosedInStringProperty", # required
connector_name: "EnclosedInStringProperty", # required
connection_type: "EnclosedInStringProperty", # required
additional_options: {
filter_predicate: "EnclosedInStringProperty",
partition_column: "EnclosedInStringProperty",
lower_bound: 1,
upper_bound: 1,
num_partitions: 1,
job_bookmark_keys: ["EnclosedInStringProperty"],
job_bookmark_keys_sort_order: "EnclosedInStringProperty",
data_type_mapping: {
"ARRAY" => "DATE", # accepts DATE, STRING, TIMESTAMP, INT, FLOAT, LONG, BIGDECIMAL, BYTE, SHORT, DOUBLE
},
},
connection_table: "EnclosedInStringPropertyWithQuote",
query: "SqlQuery",
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
spark_connector_source: {
name: "NodeName", # required
connection_name: "EnclosedInStringProperty", # required
connector_name: "EnclosedInStringProperty", # required
connection_type: "EnclosedInStringProperty", # required
additional_options: {
"EnclosedInStringProperty" => "EnclosedInStringProperty",
},
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
redshift_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
redshift_tmp_dir: "EnclosedInStringProperty",
tmp_dir_iam_role: "EnclosedInStringProperty",
},
s3_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
partition_predicate: "EnclosedInStringProperty",
additional_options: {
bounded_size: 1,
bounded_files: 1,
},
},
s3_csv_source: {
name: "NodeName", # required
paths: ["EnclosedInStringProperty"], # required
compression_type: "gzip", # accepts gzip, bzip2
exclusions: ["EnclosedInStringProperty"],
group_size: "EnclosedInStringProperty",
group_files: "EnclosedInStringProperty",
recurse: false,
max_band: 1,
max_files_in_band: 1,
additional_options: {
bounded_size: 1,
bounded_files: 1,
enable_sample_path: false,
sample_path: "EnclosedInStringProperty",
},
separator: "comma", # required, accepts comma, ctrla, pipe, semicolon, tab
escaper: "EnclosedInStringPropertyWithQuote",
quote_char: "quote", # required, accepts quote, quillemet, single_quote, disabled
multiline: false,
with_header: false,
write_header: false,
skip_first: false,
optimize_performance: false,
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
s3_json_source: {
name: "NodeName", # required
paths: ["EnclosedInStringProperty"], # required
compression_type: "gzip", # accepts gzip, bzip2
exclusions: ["EnclosedInStringProperty"],
group_size: "EnclosedInStringProperty",
group_files: "EnclosedInStringProperty",
recurse: false,
max_band: 1,
max_files_in_band: 1,
additional_options: {
bounded_size: 1,
bounded_files: 1,
enable_sample_path: false,
sample_path: "EnclosedInStringProperty",
},
json_path: "EnclosedInStringProperty",
multiline: false,
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
s3_parquet_source: {
name: "NodeName", # required
paths: ["EnclosedInStringProperty"], # required
compression_type: "snappy", # accepts snappy, lzo, gzip, uncompressed, none
exclusions: ["EnclosedInStringProperty"],
group_size: "EnclosedInStringProperty",
group_files: "EnclosedInStringProperty",
recurse: false,
max_band: 1,
max_files_in_band: 1,
additional_options: {
bounded_size: 1,
bounded_files: 1,
enable_sample_path: false,
sample_path: "EnclosedInStringProperty",
},
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
relational_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
dynamo_db_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
jdbc_connector_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
connection_name: "EnclosedInStringProperty", # required
connection_table: "EnclosedInStringPropertyWithQuote", # required
connector_name: "EnclosedInStringProperty", # required
connection_type: "EnclosedInStringProperty", # required
additional_options: {
"EnclosedInStringProperty" => "EnclosedInStringProperty",
},
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
spark_connector_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
connection_name: "EnclosedInStringProperty", # required
connector_name: "EnclosedInStringProperty", # required
connection_type: "EnclosedInStringProperty", # required
additional_options: {
"EnclosedInStringProperty" => "EnclosedInStringProperty",
},
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
catalog_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
redshift_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
redshift_tmp_dir: "EnclosedInStringProperty",
tmp_dir_iam_role: "EnclosedInStringProperty",
upsert_redshift_options: {
table_location: "EnclosedInStringProperty",
connection_name: "EnclosedInStringProperty",
upsert_keys: ["EnclosedInStringProperty"],
},
},
s3_catalog_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
partition_keys: [
["EnclosedInStringProperty"],
],
table: "EnclosedInStringProperty", # required
database: "EnclosedInStringProperty", # required
schema_change_policy: {
enable_update_catalog: false,
update_behavior: "UPDATE_IN_DATABASE", # accepts UPDATE_IN_DATABASE, LOG
},
},
s3_glue_parquet_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
partition_keys: [
["EnclosedInStringProperty"],
],
path: "EnclosedInStringProperty", # required
compression: "snappy", # accepts snappy, lzo, gzip, uncompressed, none
schema_change_policy: {
enable_update_catalog: false,
update_behavior: "UPDATE_IN_DATABASE", # accepts UPDATE_IN_DATABASE, LOG
table: "EnclosedInStringProperty",
database: "EnclosedInStringProperty",
},
},
s3_direct_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
partition_keys: [
["EnclosedInStringProperty"],
],
path: "EnclosedInStringProperty", # required
compression: "EnclosedInStringProperty",
format: "json", # required, accepts json, csv, avro, orc, parquet
schema_change_policy: {
enable_update_catalog: false,
update_behavior: "UPDATE_IN_DATABASE", # accepts UPDATE_IN_DATABASE, LOG
table: "EnclosedInStringProperty",
database: "EnclosedInStringProperty",
},
},
apply_mapping: {
name: "NodeName", # required
inputs: ["NodeId"], # required
mapping: [ # required
{
to_key: "EnclosedInStringProperty",
from_path: ["EnclosedInStringProperty"],
from_type: "EnclosedInStringProperty",
to_type: "EnclosedInStringProperty",
dropped: false,
children: {
# recursive Mappings
},
},
],
},
select_fields: {
name: "NodeName", # required
inputs: ["NodeId"], # required
paths: [ # required
["EnclosedInStringProperty"],
],
},
drop_fields: {
name: "NodeName", # required
inputs: ["NodeId"], # required
paths: [ # required
["EnclosedInStringProperty"],
],
},
rename_field: {
name: "NodeName", # required
inputs: ["NodeId"], # required
source_path: ["EnclosedInStringProperty"], # required
target_path: ["EnclosedInStringProperty"], # required
},
spigot: {
name: "NodeName", # required
inputs: ["NodeId"], # required
path: "EnclosedInStringProperty", # required
topk: 1,
prob: 1.0,
},
join: {
name: "NodeName", # required
inputs: ["NodeId"], # required
join_type: "equijoin", # required, accepts equijoin, left, right, outer, leftsemi, leftanti
columns: [ # required
{
from: "EnclosedInStringProperty", # required
keys: [ # required
["EnclosedInStringProperty"],
],
},
],
},
split_fields: {
name: "NodeName", # required
inputs: ["NodeId"], # required
paths: [ # required
["EnclosedInStringProperty"],
],
},
select_from_collection: {
name: "NodeName", # required
inputs: ["NodeId"], # required
index: 1, # required
},
fill_missing_values: {
name: "NodeName", # required
inputs: ["NodeId"], # required
imputed_path: "EnclosedInStringProperty", # required
filled_path: "EnclosedInStringProperty",
},
filter: {
name: "NodeName", # required
inputs: ["NodeId"], # required
logical_operator: "AND", # required, accepts AND, OR
filters: [ # required
{
operation: "EQ", # required, accepts EQ, LT, GT, LTE, GTE, REGEX, ISNULL
negated: false,
values: [ # required
{
type: "COLUMNEXTRACTED", # required, accepts COLUMNEXTRACTED, CONSTANT
value: ["EnclosedInStringProperty"], # required
},
],
},
],
},
custom_code: {
name: "NodeName", # required
inputs: ["NodeId"], # required
code: "ExtendedString", # required
class_name: "EnclosedInStringProperty", # required
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
spark_sql: {
name: "NodeName", # required
inputs: ["NodeId"], # required
sql_query: "SqlQuery", # required
sql_aliases: [ # required
{
from: "NodeId", # required
alias: "EnclosedInStringPropertyWithQuote", # required
},
],
output_schemas: [
{
columns: [
{
name: "GlueStudioColumnNameString", # required
type: "ColumnTypeString",
},
],
},
],
},
direct_kinesis_source: {
name: "NodeName", # required
window_size: 1,
detect_schema: false,
streaming_options: {
endpoint_url: "EnclosedInStringProperty",
stream_name: "EnclosedInStringProperty",
classification: "EnclosedInStringProperty",
delimiter: "EnclosedInStringProperty",
starting_position: "latest", # accepts latest, trim_horizon, earliest
max_fetch_time_in_ms: 1,
max_fetch_records_per_shard: 1,
max_record_per_read: 1,
add_idle_time_between_reads: false,
idle_time_between_reads_in_ms: 1,
describe_shard_interval: 1,
num_retries: 1,
retry_interval_ms: 1,
max_retry_interval_ms: 1,
avoid_empty_batches: false,
stream_arn: "EnclosedInStringProperty",
role_arn: "EnclosedInStringProperty",
role_session_name: "EnclosedInStringProperty",
},
data_preview_options: {
polling_time: 1,
record_polling_limit: 1,
},
},
direct_kafka_source: {
name: "NodeName", # required
streaming_options: {
bootstrap_servers: "EnclosedInStringProperty",
security_protocol: "EnclosedInStringProperty",
connection_name: "EnclosedInStringProperty",
topic_name: "EnclosedInStringProperty",
assign: "EnclosedInStringProperty",
subscribe_pattern: "EnclosedInStringProperty",
classification: "EnclosedInStringProperty",
delimiter: "EnclosedInStringProperty",
starting_offsets: "EnclosedInStringProperty",
ending_offsets: "EnclosedInStringProperty",
poll_timeout_ms: 1,
num_retries: 1,
retry_interval_ms: 1,
max_offsets_per_trigger: 1,
min_partitions: 1,
},
window_size: 1,
detect_schema: false,
data_preview_options: {
polling_time: 1,
record_polling_limit: 1,
},
},
catalog_kinesis_source: {
name: "NodeName", # required
window_size: 1,
detect_schema: false,
table: "EnclosedInStringProperty", # required
database: "EnclosedInStringProperty", # required
streaming_options: {
endpoint_url: "EnclosedInStringProperty",
stream_name: "EnclosedInStringProperty",
classification: "EnclosedInStringProperty",
delimiter: "EnclosedInStringProperty",
starting_position: "latest", # accepts latest, trim_horizon, earliest
max_fetch_time_in_ms: 1,
max_fetch_records_per_shard: 1,
max_record_per_read: 1,
add_idle_time_between_reads: false,
idle_time_between_reads_in_ms: 1,
describe_shard_interval: 1,
num_retries: 1,
retry_interval_ms: 1,
max_retry_interval_ms: 1,
avoid_empty_batches: false,
stream_arn: "EnclosedInStringProperty",
role_arn: "EnclosedInStringProperty",
role_session_name: "EnclosedInStringProperty",
},
data_preview_options: {
polling_time: 1,
record_polling_limit: 1,
},
},
catalog_kafka_source: {
name: "NodeName", # required
window_size: 1,
detect_schema: false,
table: "EnclosedInStringProperty", # required
database: "EnclosedInStringProperty", # required
streaming_options: {
bootstrap_servers: "EnclosedInStringProperty",
security_protocol: "EnclosedInStringProperty",
connection_name: "EnclosedInStringProperty",
topic_name: "EnclosedInStringProperty",
assign: "EnclosedInStringProperty",
subscribe_pattern: "EnclosedInStringProperty",
classification: "EnclosedInStringProperty",
delimiter: "EnclosedInStringProperty",
starting_offsets: "EnclosedInStringProperty",
ending_offsets: "EnclosedInStringProperty",
poll_timeout_ms: 1,
num_retries: 1,
retry_interval_ms: 1,
max_offsets_per_trigger: 1,
min_partitions: 1,
},
data_preview_options: {
polling_time: 1,
record_polling_limit: 1,
},
},
drop_null_fields: {
name: "NodeName", # required
inputs: ["NodeId"], # required
null_check_box_list: {
is_empty: false,
is_null_string: false,
is_neg_one: false,
},
null_text_list: [
{
value: "EnclosedInStringProperty", # required
datatype: { # required
id: "GenericLimitedString", # required
label: "GenericLimitedString", # required
},
},
],
},
merge: {
name: "NodeName", # required
inputs: ["NodeId"], # required
source: "NodeId", # required
primary_keys: [ # required
["EnclosedInStringProperty"],
],
},
union: {
name: "NodeName", # required
inputs: ["NodeId"], # required
union_type: "ALL", # required, accepts ALL, DISTINCT
},
pii_detection: {
name: "NodeName", # required
inputs: ["NodeId"], # required
pii_type: "RowAudit", # required, accepts RowAudit, RowMasking, ColumnAudit, ColumnMasking
entity_types_to_detect: ["EnclosedInStringProperty"], # required
output_column_name: "EnclosedInStringProperty",
sample_fraction: 1.0,
threshold_fraction: 1.0,
mask_value: "MaskValue",
},
aggregate: {
name: "NodeName", # required
inputs: ["NodeId"], # required
groups: [ # required
["EnclosedInStringProperty"],
],
aggs: [ # required
{
column: ["EnclosedInStringProperty"], # required
agg_func: "avg", # required, accepts avg, countDistinct, count, first, last, kurtosis, max, min, skewness, stddev_samp, stddev_pop, sum, sumDistinct, var_samp, var_pop
},
],
},
drop_duplicates: {
name: "NodeName", # required
inputs: ["NodeId"], # required
columns: [
["GenericLimitedString"],
],
},
governed_catalog_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
partition_keys: [
["EnclosedInStringProperty"],
],
table: "EnclosedInStringProperty", # required
database: "EnclosedInStringProperty", # required
schema_change_policy: {
enable_update_catalog: false,
update_behavior: "UPDATE_IN_DATABASE", # accepts UPDATE_IN_DATABASE, LOG
},
},
governed_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
partition_predicate: "EnclosedInStringProperty",
additional_options: {
bounded_size: 1,
bounded_files: 1,
},
},
microsoft_sql_server_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
my_sql_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
oracle_sql_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
postgre_sql_catalog_source: {
name: "NodeName", # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
microsoft_sql_server_catalog_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
my_sql_catalog_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
oracle_sql_catalog_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
postgre_sql_catalog_target: {
name: "NodeName", # required
inputs: ["NodeId"], # required
database: "EnclosedInStringProperty", # required
table: "EnclosedInStringProperty", # required
},
},
},
execution_class: "FLEX", # accepts FLEX, STANDARD
},
}
Constant Summary collapse
- SENSITIVE =
[]
Instance Attribute Summary collapse
-
#job_name ⇒ String
The name of the job definition to update.
-
#job_update ⇒ Types::JobUpdate
Specifies the values with which to update the job definition.
Instance Attribute Details
#job_name ⇒ String
The name of the job definition to update.
25456 25457 25458 25459 25460 25461 |
# File 'lib/aws-sdk-glue/types.rb', line 25456 class UpdateJobRequest < Struct.new( :job_name, :job_update) SENSITIVE = [] include Aws::Structure end |
#job_update ⇒ Types::JobUpdate
Specifies the values with which to update the job definition. Unspecified configuration is removed or reset to default values.
25456 25457 25458 25459 25460 25461 |
# File 'lib/aws-sdk-glue/types.rb', line 25456 class UpdateJobRequest < Struct.new( :job_name, :job_update) SENSITIVE = [] include Aws::Structure end |