Example usage for com.amazonaws.services.s3.model InputSerialization InputSerialization

Introduction

In this page you can find the example usage for com.amazonaws.services.s3.model InputSerialization InputSerialization.

Prototype

InputSerialization

Source Link

Usage

From source file:com.facebook.presto.hive.S3SelectCsvRecordReader.java

License:Apache License

@Override
public SelectObjectContentRequest buildSelectObjectRequest(Properties schema, String query, Path path) {
    SelectObjectContentRequest selectObjectRequest = new SelectObjectContentRequest();
    URI uri = path.toUri();/*from  w w w.j  a  v  a2s  .  c  om*/
    selectObjectRequest.setBucketName(PrestoS3FileSystem.getBucketName(uri));
    selectObjectRequest.setKey(PrestoS3FileSystem.keyFromPath(path));
    selectObjectRequest.setExpression(query);
    selectObjectRequest.setExpressionType(ExpressionType.SQL);

    String fieldDelimiter = getFieldDelimiter(schema);
    String quoteChar = schema.getProperty(QUOTE_CHAR, null);
    String escapeChar = schema.getProperty(ESCAPE_CHAR, null);

    CSVInput selectObjectCSVInputSerialization = new CSVInput();
    selectObjectCSVInputSerialization.setRecordDelimiter(lineDelimiter);
    selectObjectCSVInputSerialization.setFieldDelimiter(fieldDelimiter);
    selectObjectCSVInputSerialization.setComments(COMMENTS_CHAR_STR);
    selectObjectCSVInputSerialization.setQuoteCharacter(quoteChar);
    selectObjectCSVInputSerialization.setQuoteEscapeCharacter(escapeChar);
    InputSerialization selectObjectInputSerialization = new InputSerialization();

    CompressionCodec codec = compressionCodecFactory.getCodec(path);
    if (codec instanceof GzipCodec) {
        selectObjectInputSerialization.setCompressionType(CompressionType.GZIP);
    } else if (codec instanceof BZip2Codec) {
        selectObjectInputSerialization.setCompressionType(CompressionType.BZIP2);
    } else if (codec != null) {
        throw new PrestoException(NOT_SUPPORTED, "Compression extension not supported for S3 Select: " + path);
    }

    selectObjectInputSerialization.setCsv(selectObjectCSVInputSerialization);
    selectObjectRequest.setInputSerialization(selectObjectInputSerialization);

    OutputSerialization selectObjectOutputSerialization = new OutputSerialization();
    CSVOutput selectObjectCSVOutputSerialization = new CSVOutput();
    selectObjectCSVOutputSerialization.setRecordDelimiter(lineDelimiter);
    selectObjectCSVOutputSerialization.setFieldDelimiter(fieldDelimiter);
    selectObjectCSVOutputSerialization.setQuoteCharacter(quoteChar);
    selectObjectCSVOutputSerialization.setQuoteEscapeCharacter(escapeChar);
    selectObjectOutputSerialization.setCsv(selectObjectCSVOutputSerialization);
    selectObjectRequest.setOutputSerialization(selectObjectOutputSerialization);

    return selectObjectRequest;
}

---

From source file:org.apache.flink.streaming.tests.util.s3.S3QueryUtil.java

License:Apache License

private static SelectObjectContentRequest generateBaseCSVRequest(String bucket, String key, String query) {
    SelectObjectContentRequest request = new SelectObjectContentRequest();
    request.setBucketName(bucket);/*from   w w  w . j  a v  a2  s .co  m*/
    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;
}

---