使用作业书签跟踪已处理的数据

以下是为 Amazon S3 数据源生成的脚本的示例。使用作业书签所需的脚本部分以粗体和斜体显示。有关这些元素的更多信息，请参阅 GlueContext 阶级 API 和 DynamicFrameWriter 阶级 API。

# Sample Script
import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job

## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME'])
sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)
## @type: DataSource
## @args: [database = "database", table_name = "relatedqueries_csv", transformation_ctx = "datasource0"]
## @return: datasource0
## @inputs: []
datasource0 = glueContext.create_dynamic_frame.from_catalog(database = "database", table_name = "relatedqueries_csv", transformation_ctx = "datasource0")
## @type: ApplyMapping
## @args: [mapping = [("col0", "string", "name", "string"), ("col1", "string", "number", "string")], transformation_ctx = "applymapping1"]
## @return: applymapping1
## @inputs: [frame = datasource0]
applymapping1 = ApplyMapping.apply(frame = datasource0, mappings = [("col0", "string", "name", "string"), ("col1", "string", "number", "string")], transformation_ctx = "applymapping1")
## @type: DataSink
## @args: [connection_type = "s3", connection_options = {"path": "s3://input_path"}, format = "json", transformation_ctx = "datasink2"]
## @return: datasink2
## @inputs: [frame = applymapping1]
datasink2 = glueContext.write_dynamic_frame.from_options(frame = applymapping1, connection_type = "s3", connection_options = {"path": "s3://input_path"}, format = "json", transformation_ctx = "datasink2")

job.commit()

以下是为 JDBC 源生成的脚本的示例。源表是一个将 empno 列作为主键的员工表。尽管默认情况下，如果未指定书签键，则任务会使用顺序主键作为书签键，但由于 empno 不一定是连续的，值中可能会有间隙，它不能作为默认书签键。因此，脚本会将 empno 显式指定为书签键。代码的此部分以粗体和斜体显示。

import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job

## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME'])

sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)
## @type: DataSource
## @args: [database = "hr", table_name = "emp", transformation_ctx = "datasource0"]
## @return: datasource0
## @inputs: []
datasource0 = glueContext.create_dynamic_frame.from_catalog(database = "hr", table_name = "emp", transformation_ctx = "datasource0", additional_options = {"jobBookmarkKeys":["empno"],"jobBookmarkKeysSortOrder":"asc"})
## @type: ApplyMapping
## @args: [mapping = [("ename", "string", "ename", "string"), ("hrly_rate", "decimal(38,0)", "hrly_rate", "decimal(38,0)"), ("comm", "decimal(7,2)", "comm", "decimal(7,2)"), ("hiredate", "timestamp", "hiredate", "timestamp"), ("empno", "decimal(5,0)", "empno", "decimal(5,0)"), ("mgr", "decimal(5,0)", "mgr", "decimal(5,0)"), ("photo", "string", "photo", "string"), ("job", "string", "job", "string"), ("deptno", "decimal(3,0)", "deptno", "decimal(3,0)"), ("ssn", "decimal(9,0)", "ssn", "decimal(9,0)"), ("sal", "decimal(7,2)", "sal", "decimal(7,2)")], transformation_ctx = "applymapping1"]
## @return: applymapping1
## @inputs: [frame = datasource0]
applymapping1 = ApplyMapping.apply(frame = datasource0, mappings = [("ename", "string", "ename", "string"), ("hrly_rate", "decimal(38,0)", "hrly_rate", "decimal(38,0)"), ("comm", "decimal(7,2)", "comm", "decimal(7,2)"), ("hiredate", "timestamp", "hiredate", "timestamp"), ("empno", "decimal(5,0)", "empno", "decimal(5,0)"), ("mgr", "decimal(5,0)", "mgr", "decimal(5,0)"), ("photo", "string", "photo", "string"), ("job", "string", "job", "string"), ("deptno", "decimal(3,0)", "deptno", "decimal(3,0)"), ("ssn", "decimal(9,0)", "ssn", "decimal(9,0)"), ("sal", "decimal(7,2)", "sal", "decimal(7,2)")], transformation_ctx = "applymapping1")
## @type: DataSink
## @args: [connection_type = "s3", connection_options = {"path": "s3://hr/employees"}, format = "csv", transformation_ctx = "datasink2"]
## @return: datasink2
## @inputs: [frame = applymapping1]
datasink2 = glueContext.write_dynamic_frame.from_options(frame = applymapping1, connection_type = "s3", connection_options = {"path": "s3://hr/employees"}, format = "csv", transformation_ctx = "datasink2")
job.commit()