AWS Data Pipeline não está mais disponível para novos clientes. Os clientes existentes do AWS Data Pipeline podem continuar usando o serviço normalmente. Saiba mais

As traduções são geradas por tradução automática. Em caso de conflito entre o conteúdo da tradução e da versão original em inglês, a versão em inglês prevalecerá.

PigActivity

PigActivity fornece suporte nativo para scripts Pig AWS Data Pipeline sem a necessidade de usar ShellCommandActivity ouEmrActivity. Além disso, PigActivity oferece suporte ao armazenamento de dados. Quando o campo de estágio é definido como verdadeiro, o AWS Data Pipeline prepara os dados de entrada como um esquema em Pig sem um código adicional do usuário.

Exemplo

O exemplo de pipeline a seguir mostra como usar PigActivity. O exemplo de pipeline a seguir executa as seguintes etapas:

{
  "objects": [
    {
      "id": "MyInputData1",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "directoryPath": "s3://example-bucket/pigTestInput",
      "name": "MyInputData1",
      "dataFormat": {
        "ref": "MyInputDataType1"
      },
      "type": "S3DataNode"
    },
    {
      "id": "MyPigActivity4",
      "scheduleType": "CRON",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "input": {
        "ref": "MyOutputData3"
      },
      "pipelineLogUri": "s3://example-bucket/path/",
      "name": "MyPigActivity4",
      "runsOn": {
        "ref": "MyEmrResource"
      },
      "type": "PigActivity",
      "dependsOn": {
        "ref": "MyPigActivity3"
      },
      "output": {
        "ref": "MyOutputData4"
      },
      "script": "B = LIMIT ${input1} 1; ${output1} = FOREACH B GENERATE one;",
      "stage": "true"
    },
    {
      "id": "MyPigActivity3",
      "scheduleType": "CRON",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "input": {
        "ref": "MyOutputData2"
      },
      "pipelineLogUri": "s3://example-bucket/path",
      "name": "MyPigActivity3",
      "runsOn": {
        "ref": "MyEmrResource"
      },
      "script": "B = LIMIT ${input1} 2; ${output1} = FOREACH B GENERATE Fifth;",
      "type": "PigActivity",
      "dependsOn": {
        "ref": "MyPigActivity2"
      },
      "output": {
        "ref": "MyOutputData3"
      },
      "stage": "true"
    },
    {
      "id": "MyOutputData2",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "name": "MyOutputData2",
      "directoryPath": "s3://example-bucket/PigActivityOutput2",
      "dataFormat": {
        "ref": "MyOutputDataType2"
      },
      "type": "S3DataNode"
    },
    {
      "id": "MyOutputData1",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "name": "MyOutputData1",
      "directoryPath": "s3://example-bucket/PigActivityOutput1",
      "dataFormat": {
        "ref": "MyOutputDataType1"
      },
      "type": "S3DataNode"
    },
    {
      "id": "MyInputDataType1",
      "name": "MyInputDataType1",
      "column": [
        "First STRING",
        "Second STRING",
        "Third STRING",
        "Fourth STRING",
        "Fifth STRING",
        "Sixth STRING",
        "Seventh STRING",
        "Eighth STRING",
        "Ninth STRING",
        "Tenth STRING"
      ],
      "inputRegEx": "^(\\\\S+) (\\\\S+) (\\\\S+) (\\\\S+) (\\\\S+) (\\\\S+) (\\\\S+) (\\\\S+) (\\\\S+) (\\\\S+)",
      "type": "RegEx"
    },
    {
      "id": "MyEmrResource",
      "region": "us-east-1",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "keyPair": "example-keypair",
      "masterInstanceType": "m1.small",
      "enableDebugging": "true",
      "name": "MyEmrResource",
      "actionOnTaskFailure": "continue",
      "type": "EmrCluster"
    },
    {
      "id": "MyOutputDataType4",
      "name": "MyOutputDataType4",
      "column": "one STRING",
      "type": "CSV"
    },
    {
      "id": "MyOutputData4",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "directoryPath": "s3://example-bucket/PigActivityOutput3",
      "name": "MyOutputData4",
      "dataFormat": {
        "ref": "MyOutputDataType4"
      },
      "type": "S3DataNode"
    },
    {
      "id": "MyOutputDataType1",
      "name": "MyOutputDataType1",
      "column": [
        "First STRING",
        "Second STRING",
        "Third STRING",
        "Fourth STRING",
        "Fifth STRING",
        "Sixth STRING",
        "Seventh STRING",
        "Eighth STRING"
      ],
      "columnSeparator": "*",
      "type": "Custom"
    },
    {
      "id": "MyOutputData3",
      "username": "___",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "insertQuery": "insert into #{table} (one) values (?)",
      "name": "MyOutputData3",
      "*password": "___",
      "runsOn": {
        "ref": "MyEmrResource"
      },
      "connectionString": "jdbc:mysql://example-database-instance:3306/example-database",
      "selectQuery": "select * from #{table}",
      "table": "example-table-name",
      "type": "MySqlDataNode"
    },
    {
      "id": "MyOutputDataType2",
      "name": "MyOutputDataType2",
      "column": [
        "Third STRING",
        "Fourth STRING",
        "Fifth STRING",
        "Sixth STRING",
        "Seventh STRING",
        "Eighth STRING"
      ],
      "type": "TSV"
    },
    {
      "id": "MyPigActivity2",
      "scheduleType": "CRON",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "input": {
        "ref": "MyOutputData1"
      },
      "pipelineLogUri": "s3://example-bucket/path",
      "name": "MyPigActivity2",
      "runsOn": {
        "ref": "MyEmrResource"
      },
      "dependsOn": {
        "ref": "MyPigActivity1"
      },
      "type": "PigActivity",
      "script": "B = LIMIT ${input1} 3; ${output1} = FOREACH B GENERATE Third, Fourth, Fifth, Sixth, Seventh, Eighth;",
      "output": {
        "ref": "MyOutputData2"
      },
      "stage": "true"
    },
    {
      "id": "MyEmrResourcePeriod",
      "startDateTime": "2013-05-20T00:00:00",
      "name": "MyEmrResourcePeriod",
      "period": "1 day",
      "type": "Schedule",
      "endDateTime": "2013-05-21T00:00:00"
    },
    {
      "id": "MyPigActivity1",
      "scheduleType": "CRON",
      "schedule": {
        "ref": "MyEmrResourcePeriod"
      },
      "input": {
        "ref": "MyInputData1"
      },
      "pipelineLogUri": "s3://example-bucket/path",
      "scriptUri": "s3://example-bucket/script/pigTestScipt.q",
      "name": "MyPigActivity1",
      "runsOn": {
        "ref": "MyEmrResource"
      },
      "scriptVariable": [
        "column1=First",
        "column2=Second",
        "three=3"
      ],
      "type": "PigActivity",
      "output": {
        "ref": "MyOutputData1"
      },
      "stage": "true"
    }
  ]
}

O conteúdo de pigTestScript.q é o seguinte.

B = LIMIT ${input1} $three; ${output1} = FOREACH B GENERATE $column1, $column2, Third, Fourth, Fifth, Sixth, Seventh, Eighth;

Sintaxe

Consulte também