我有一个Hbase表,它有一个唯一的rowkey和一个列族和一列..我有一个TSV文件,大约有300多列。此文件中的rowkey是两列的组合值。所以现在我需要比较表和文件中的rowkey,如果rowkey匹配,那么我需要将表列值作为相应rowkey的TSV文件中的最后一列插入。我编写了以下代码,但它总是执行else部分。
package mapReduce;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileReader;
import java.io.FileWriter;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
public class Tsv_read{
private static Configuration conf = null;
static {
conf = HBaseConfiguration.create();
}
@SuppressWarnings("resource")
public static void main(String[] arg) throws Exception {
BufferedReader TSVFile =
new BufferedReader(new FileReader("Path/to/file/.tsv"));
String dataRow = TSVFile.readLine();
List<String> list = new ArrayList<String>();
while (dataRow != null){
list.clear();
String[] dataArray = dataRow.split("\t");
for (String item:dataArray) {
HTable table = new HTable(conf, "Table name"); //Hbase table name
Scan s = new Scan();
ResultScanner ss = table.getScanner(s);
for(Result r:ss){
for(KeyValue kv : r.raw()){
//System.out.println("Rowkey :" +dataArray[12]+"-"+dataArray[13]);
//System.out.print(new String(kv.getRow()) + " ");
if((dataArray[12]+"-"+dataArray[13]).equals(new String(kv.getRow()))){ //Comparing the rowkeys from file and table (doesn't work)
System.out.println("File Rowkey :"+dataArray[12]+"-"+dataArray[13]);
System.out.println("Table Row key"+new String(kv.getRow()));
//dataArray[392]=new String(kv.getValue());
FileWriter fstream = new FileWriter("/path/to/the/file/*.tsv",true);
BufferedWriter fbw = new BufferedWriter(fstream);
fbw.write(new String(kv.getValue())); //inserting the value to the tsv file
fbw.newLine();
fbw.close();
System.out.println("Column value written succesfully");
}
else //always executes this part
{
System.out.println("RowKey not found :" +new String(kv.getRow()));
}
/*System.out.print(new String(kv.getFamily()) + ":");
System.out.print(new String(kv.getQualifier()) + " ");
System.out.print(kv.getTimestamp() + " ");*/
//System.out.println(new String(kv.getValue()));
list.add(item);
}
}
}
Iterator<String> it = list.iterator();
while (it.hasNext()) {
String txt = it.next();
System.out.print(txt+" ");
}
System.out.println(); // Print the data line.
dataRow = TSVFile.readLine();
}
TSVFile.close();
System.out.println();
} //main()
}
样本记录:
dataArray [12] +“ - ”+ dataArray [13] = 3049620139673452544-5172983457411783096
在Hbase表中,rowkey也具有相同格式的值。
我不能分享整个记录,因为它有300多列。
TSV文件Siz e:大约10GB
Hbase表:大约10254950行。
感谢任何帮助。提前谢谢。
答案 0 :(得分:1)
而不是将其写为
if((dataArray [12] +“ - ”+ dataArray [13])。equals(new String(kv.getRow()))){//比较文件和表中的rowkeys(不起作用)
试试这个
if((dataArray [12] +“ - ”+ dataArray [13])。equals(Bytes.toString(kv.getRow()))){
您没有正确获取行值。
尝试使用此更新代码,它使用Get而不是hbase扫描,运行时间更短
while (dataRow != null) {
list.clear();
String[] dataArray = dataRow.split("\t");
for (String item : dataArray) {
String key = dataArray[12] + "-" + dataArray[13];
HTable table = new HTable(conf, "Table name"); // Hbase table
// name
Get get = new Get(Bytes.toBytes(key));
Result r = table.get(get);
if (r != null && r.size() > 0) {
for (KeyValue kv : r.raw()) {
System.out.println("File Rowkey :" + key);
System.out.println("Table Row key"
+ Bytes.toString(kv.getRow()));
FileWriter fstream = new FileWriter(
"/path/to/the/file/*.tsv", true);
BufferedWriter fbw = new BufferedWriter(fstream);
fbw.write(new String(kv.getValue())); // inserting the
// value to the
// tsv file
fbw.newLine();
fbw.close();
System.out.println("Column value written succesfully");
}
} else {
System.out.println("RowKey not found :" + key);
}
list.add(item);
}
}