AWS Data Pipeline ya no está disponible para nuevos clientes. Los clientes actuales de AWS Data Pipeline pueden seguir utilizando el servicio con normalidad. Más información

Las traducciones son generadas a través de traducción automática. En caso de conflicto entre la traducción y la version original de inglés, prevalecerá la version en inglés.

PigActivity

PigActivity proporciona soporte nativo para los scripts de Pig AWS Data Pipeline sin la necesidad de usar ShellCommandActivity oEmrActivity. Además, PigActivity admite la puesta en escena de datos. Cuando el campo de uso transitorio se establece en true, AWS Data Pipeline almacena de modo transitorio los datos de entrada como un esquema en Pig sin código adicional del usuario.

Ejemplo

En la siguiente canalización de ejemplo se muestra cómo utilizar PigActivity. En la canalización de ejemplo se ejecutan los siguientes pasos:

{
  "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"
    }
  ]
}

El contenido de pigTestScript.q es el siguiente.

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

Sintaxis

Véase también