從數據流到大型查詢編寫STRUCT數組

Question

我正在嘗試從Dataflow管道到大型查詢編寫一個Structs數組字段，生成的表的架構是正確的，但是字段中沒有數據被填充。

我的DoFn函數：

public class ProcessIpBlocks {

    public static class IpBlocksToIp extends DoFn<TableRow, TableRow> {

        private static final long serialVersionUID = 1L;

        @Override
        public void processElement(ProcessContext c) throws JSONException {

            TableRow row = c.element();
            DateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
            Calendar cal = Calendar.getInstance();


            long startIp = 0L, endIp = 0L;
            if(row.get("start_ip") != null)
                startIp = Long.parseLong((String)row.get("start_ip"));

            if(row.get("end_ip") != null)
                endIp = Long.parseLong((String)row.get("end_ip"));

            for(long i= startIp; i<=endIp; i++)
            {
                TableRow outputRow = new TableRow();
                outputRow.set("start_ip", startIp);
                outputRow.set("ip", i);

                if(row.get("postal_code") != null && !((String)row.get("postal_code")).isEmpty()){

                    System.out.println("This is getting written to logs");
                    endIp = Long.parseLong((String)row.get("end_ip"));
                    JSONArray atrArray = new JSONArray();

                    JSONObject atr = new JSONObject();
                    atr.put("id", "zippostal_code");

                    JSONArray atrValueArray = new JSONArray();
                    atr.put("value", atrValueArray.put((String)row.get("postal_code")));


                    atr.put("pr", 0.5);
                    atr.put("dt", cal.getTime());
                    atrArray.put(atr);
                    outputRow.set("atr", atrArray);
                }

                c.output(outputRow);
            }
        }
    }

}

我的管道寫步驟：

iPBlocksToIPData.apply("Foo", ParDo.of(new ProcessIpBlocks.IpBlocksToIp()))
        .apply(BigQueryIO.Write
                .named("WriteIPs")
                .to(String.format("%1$s:%2$s.%3$s",projectId, eventDataset, ipBlocksToIpTable))
                .withSchema(schema)
                .withWriteDisposition(BigQueryIO.Write.WriteDisposition.WRITE_TRUNCATE)
                .withCreateDisposition(BigQueryIO.Write.CreateDisposition.CREATE_IF_NEEDED));

Answer 1

下面的解決方案有效，使用TableRow而不是JSONArray

公共課Foo {

public static class Foo extends DoFn<TableRow, TableRow> {


    @Override
    public void processElement(ProcessContext c) throws JSONException {

        TableRow row = c.element();
        DateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
        Calendar cal = Calendar.getInstance();


        long startIp = 0L, endIp = 0L;
        if(row.get("start_ip") != null)
            startIp = Long.parseLong((String)row.get("start_ip"));

        if(row.get("end_ip") != null)
            endIp = Long.parseLong((String)row.get("end_ip"));

        for(long i= startIp; i<=endIp; i++)
        {
            TableRow outputRow = new TableRow();
            outputRow.set("start_ip", startIp);
            outputRow.set("ip", i);

            if(row.get("postal_code") != null && !((String)row.get("postal_code")).isEmpty()){

                endIp = Long.parseLong((String)row.get("end_ip"));

                TableRow atrRow = new TableRow();
                atrRow.set("id", "zippostal_code");
                atrRow.set("value", new String[] {(String)row.get("postal_code")});



                outputRow.set("atr", atrRow);
            }

            System.out.println(outputRow);

            c.output(outputRow);
        }
    }
}