Amazon Simple Storage Service
开发人员指南 (API 版本 2006-03-01)
AWS 文档中描述的 AWS 服务或功能可能因区域而异。要查看适用于中国区域的差异,请参阅 Amazon AWS 入门

使用 适用于 Java 的开发工具包 从对象中选择内容

使用 Amazon S3 Select 通过 selectObjectContent 方法来选择对象的内容,成功时将返回 SQL 表达式的结果。指定的存储桶和对象键必须存在,否则将出现错误。

例 示例

以下 Java 代码返回对象 (包含以 CSV 格式存储的数据) 中存储的每条记录的第一列的值。它还请求返回 ProgressStats 消息。必须提供有效的存储桶名称和包含 CSV 格式的数据的对象。

有关如何创建和测试有效示例的说明,请参阅 测试 Amazon S3 Java 代码示例

package com.amazonaws; import com.amazonaws.services.s3.AmazonS3; import com.amazonaws.services.s3.AmazonS3ClientBuilder; import com.amazonaws.services.s3.model.CSVInput; import com.amazonaws.services.s3.model.CSVOutput; import com.amazonaws.services.s3.model.CompressionType; import com.amazonaws.services.s3.model.ExpressionType; import com.amazonaws.services.s3.model.InputSerialization; import com.amazonaws.services.s3.model.OutputSerialization; import com.amazonaws.services.s3.model.SelectObjectContentEvent; import com.amazonaws.services.s3.model.SelectObjectContentEventVisitor; import com.amazonaws.services.s3.model.SelectObjectContentRequest; import com.amazonaws.services.s3.model.SelectObjectContentResult; import java.io.File; import java.io.FileOutputStream; import java.io.InputStream; import java.io.OutputStream; import java.util.concurrent.atomic.AtomicBoolean; import static com.amazonaws.util.IOUtils.copy; /** * This example shows how to query data from S3Select and consume the response in the form of an * InputStream of records and write it to a file. */ public class RecordInputStreamExample { private static final String BUCKET_NAME = "${my-s3-bucket}"; private static final String CSV_OBJECT_KEY = "${my-csv-object-key}"; private static final String S3_SELECT_RESULTS_PATH = "${my-s3-select-results-path}"; private static final String QUERY = "select s._1 from S3Object s"; public static void main(String[] args) throws Exception { final AmazonS3 s3Client = AmazonS3ClientBuilder.defaultClient(); SelectObjectContentRequest request = generateBaseCSVRequest(BUCKET_NAME, CSV_OBJECT_KEY, QUERY); final AtomicBoolean isResultComplete = new AtomicBoolean(false); try (OutputStream fileOutputStream = new FileOutputStream(new File (S3_SELECT_RESULTS_PATH)); SelectObjectContentResult result = s3Client.selectObjectContent(request)) { InputStream resultInputStream = result.getPayload().getRecordsInputStream( new SelectObjectContentEventVisitor() { @Override public void visit(SelectObjectContentEvent.StatsEvent event) { System.out.println( "Received Stats, Bytes Scanned: " + event.getDetails().getBytesScanned() + " Bytes Processed: " + event.getDetails().getBytesProcessed()); } /* * An End Event informs that the request has finished successfully. */ @Override public void visit(SelectObjectContentEvent.EndEvent event) { isResultComplete.set(true); System.out.println("Received End Event. Result is complete."); } } ); copy(resultInputStream, fileOutputStream); } /* * The End Event indicates all matching records have been transmitted. * If the End Event is not received, the results may be incomplete. */ if (!isResultComplete.get()) { throw new Exception("S3 Select request was incomplete as End Event was not received."); } } private static SelectObjectContentRequest generateBaseCSVRequest(String bucket, String key, String query) { SelectObjectContentRequest request = new SelectObjectContentRequest(); request.setBucketName(bucket); request.setKey(key); request.setExpression(query); request.setExpressionType(ExpressionType.SQL); InputSerialization inputSerialization = new InputSerialization(); inputSerialization.setCsv(new CSVInput()); inputSerialization.setCompressionType(CompressionType.NONE); request.setInputSerialization(inputSerialization); OutputSerialization outputSerialization = new OutputSerialization(); outputSerialization.setCsv(new CSVOutput()); request.setOutputSerialization(outputSerialization); return request; } }