You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
`env {
execution.parallelism = 1
job.mode = "BATCH"
}
source {
Kafka {
result_table_name = "test"
schema = {
fields {
"UserEmail"= "string",
"StaffId"= "string",
"CardNumber"= "string",
"PunchCardDate"= "string",
"SwipingCardDateTime"= "string",
"PunchCardTime"= "string",
"CheckinType"= "string",
"LocationDetail"= "string",
"DataSource"= "string",
"SwipingCardType"= "string",
"LocationTitle"= "string",
"WifiName"= "string",
"Notes"= "string",
"FacilityIdentify"= "string",
"SigninRegion"= "string",
"WgsCoordate"= "string",
"SigninResult"= "string",
"WifiMacAddress"= "string",
"IsWifiSignin"= "string",
"ClockType"= "string",
"Lat"= "string",
"Lng"= "string",
"CoordinateSystem"= "string",
"CreatedTime"= "string",
"ModifiedTime"= "string"
}
}
#format="json"
#field_delimiter = ","
topic = "record-2024-01-23"
bootstrap.servers = "hadoop101:9092"
consumer.group = "seatunnel_group"
#start_mode="earliest"
#commit_on_checkpoint=true
kafka.config = {
client.id = "client_1"
#max.poll.records = "1000000"
# auto.offset.reset = "earliest"
# enable.auto.commit = "false"
}
}
}
transform {
sql {
source_table_name="test"
result_table_name = "test2"
query = "select StaffId,CreatedTime,ModifiedTime, UserEmail ,CardNumber ,PunchCardDate,SwipingCardDateTime ,PunchCardTime ,CheckinType ,LocationDetail ,DataSource ,SwipingCardType ,LocationTitle ,WifiName ,Notes ,FacilityIdentify,SigninRegion ,WgsCoordate ,SigninResult,WifiMacAddress ,IsWifiSignin,ClockType ,Lat ,Lng ,CoordinateSystem from test"
}
}
sink {
Doris {
source_table_name = "test2"
fenodes="192.168.10.100:8030"
table.identifier = "demo.ods_records"
username="root"
password=""
sink.label-prefix = "test_111"
#doris.column_separator="\t"
#doris.columns="StaffId,CreatedTime,ModifiedTime, UserEmail ,CardNumber ,PunchCardDate,SwipingCardDateTime ,PunchCardTime ,CheckinType ,LocationDetail ,DataSource ,SwipingCardType ,LocationTitle ,WifiName ,Notes ,FacilityIdentify,SigninRegion ,WgsCoordate ,SigninResult,WifiMacAddress ,IsWifiSignin,ClockType ,Lat ,Lng ,CoordinateSystem"
doris.config = {
format="json"
read_json_by_line="true"
}
}
}
`
Why can batch synchronization only synchronize 500 items at a time? Also, streaming only supports seatunnelosh consumption. Using Flink and Spark consumption shows that offset has been consumed, but the data has not actually entered my Doris account
Beta Was this translation helpful? Give feedback.
All reactions