blob: efe0929ba0cb3a3df17b86110e3c0a15e30727dd [file] [log] [blame]
{
"name": "prof_streaming",
"process.type": "streaming",
"data.sources": [
{
"name": "source",
"connector": {
"type": "kafka",
"version": "0.8",
"dataframe.name": "this",
"config": {
"kafka.config": {
"bootstrap.servers": "10.147.177.107:9092",
"group.id": "group1",
"auto.offset.reset": "smallest",
"auto.commit.enable": "false"
},
"topics": "test",
"key.type": "java.lang.String",
"value.type": "java.lang.String"
},
"pre.proc": [
{
"dsl.type": "df-ops",
"in.dataframe.name": "this",
"out.dataframe.name": "s1",
"rule": "from_json"
},
{
"dsl.type": "spark-sql",
"out.dataframe.name": "this",
"rule": "select name, age from s1"
}
]
},
"checkpoint": {
"file.path": "hdfs://localhost/griffin/streaming/dump/source",
"info.path": "source",
"ready.time.interval": "10s",
"ready.time.delay": "0",
"time.range": [
"0",
"0"
]
}
}
],
"evaluate.rule": {
"rules": [
{
"dsl.type": "griffin-dsl",
"dq.type": "profiling",
"out.dataframe.name": "prof",
"rule": "select count(name) as `cnt`, max(age) as `max`, min(age) as `min` from source",
"out": [
{
"type": "metric",
"name": "prof"
}
]
},
{
"dsl.type": "griffin-dsl",
"dq.type": "profiling",
"out.dataframe.name": "grp",
"rule": "select name, count(*) as `cnt` from source group by name",
"out": [
{
"type": "metric",
"name": "name_group",
"flatten": "array"
}
]
}
]
},
"sinks": [
"CONSOLE",
"ELASTICSEARCH"
]
}