项目中遇到集群开启kerbrose,需要spark读写hbase,刚开始仅仅做如下配置来获取connection
val configuration = HBaseConfiguration.create
...(设置kerbrose配置)
UserGroupInformation.setConfiguration(configuration)
UserGroupInformation.loginUserFromKeytab(prop.KERBEROSE_PRINCIPAL, keyTab)
val connection: Connection = ConnectionFactory.createConnection(configuration)
这样获取hbase连接如果任务仅在本地运行是可以成功读取hbase的,但我的任务需要在spark excutor读写hbase,此时这样用就报错:
,后来花了两三天各种查资料调试才解决该问题:
主要是要用
val connection: Connection = ConnectionFactory.createConnection(config, loginedUser)
来获取链接,现把代码贴上:
import java.io.File
import ***.DmpProperties
import org.apache.commons.logging.LogFactory
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.hbase.security.User
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.hbase._
import org.apache.hadoop.hbase.client._
import org.apache.spark.SparkFiles
import scala.collection.JavaConversions._
import org.apache.hadoop.security.UserGroupInformation
/**
*/
object HbaseUtilNew{
private val log = LogFactory.getLog(this.getClass)
def hbaseConfig(prop: DmpProperties): Configuration ={
try{
val configuration = HBaseConfiguration.create
configuration.set(HConstants.ZOOKEEPER_QUORUM, prop.HBASE_ZOOKEEPER_QUORUM)
configuration.set(HConstants.ZOOKEEPER_CLIENT_PORT, prop.HBASE_ZOOKEEPER_PROPERTY_CLIENT_PORT)
configuration.set(HConstants.ZOOKEEPER_ZNODE_PARENT, prop.HBASE_ZOOKEEPER_ZNODE_PARENT)
if(prop.IS_KERBEROSE){
configuration.set("hadoop.security.authentication", "kerberos")
configuration.set("hbase.security.authentication", "kerberos")
configuration.set("hbase.security.authorization", "true")
configuration.set("hbase.master.kerberos.principal", prop.KERBEROSE_MASTER_PRINCIPAL)
configuration.set("hbase.regionserver.kerberos.principal", prop.KERBEROSE_REGIONSERVER_PRINCIPAL)
getHBaseAuthentication(configuration, prop)
// val userGroupInformation = UserGroupInformation.loginUserFromKeytabAndReturnUGI(prop.KERBEROSE_PRINCIPAL, keyTab)
// UserGroupInformation.setLoginUser(userGroupInformation)
}
configuration
}catch {
case ex:Exception => ex.printStackTrace()
throw new IllegalArgumentException("init hbase error", ex)
}
}
def getHBaseAuthentication(configuration: Configuration,prop:DmpProperties): Unit ={
if(prop.IS_KERBEROSE){
LogUtil.info(log,"getHBaseAuthentication...")
UserGroupInformation.setConfiguration(configuration)
val keyTab = SparkFiles.get(new File(prop.KERBEROSE_KEYTAB).getName)
LogUtil.info(log,"excutor keytab: "+keyTab)
UserGroupInformation.loginUserFromKeytab(prop.KERBEROSE_PRINCIPAL, keyTab)
LogUtil.info(log,"getHBaseAuthentication over")
}
}
def getConnection(prop: DmpProperties): Connection ={
try{
LogUtil.info(log,"create Hbase Connection...")
val config: Configuration = hbaseConfig(prop)
val loginedUser: User = getAuthenticatedUser(config,prop)
val connection: Connection = ConnectionFactory.createConnection(config, loginedUser)
LogUtil.info(log,s"hbase connection created, loginedUser: ${loginedUser.getName}")
connection
}catch {
case ex:Exception => ex.printStackTrace()
throw new IllegalArgumentException("===== get hbase connect failed", ex)
}
}
def getAuthenticatedUser(configuration: Configuration, prop:DmpProperties): User ={
getHBaseAuthentication(configuration, prop);
try{
val loginedUser: User = User.create(UserGroupInformation.getLoginUser())
LogUtil.info(log,s"====getAuthenticatedUser: ${loginedUser.getName}")
loginedUser
}catch {
case ex:Exception => ex.printStackTrace()
throw new IllegalArgumentException("===== getAuthenticatedUser failed", ex)
}
}
}
package org.apache.hadoop.hbase.mapreduce;
import java.io.IOException;
import java.util.Collections;
import java.util.List;
import java.util.Properties;
import ***.DmpProperties;
import ***.HbaseUtilNew;
import ***.LogUtil;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configurable;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.classification.InterfaceAudience;
import org.apache.hadoop.hbase.classification.InterfaceStability;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.RegionLocator;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.security.User;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.hbase.util.Pair;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.util.StringUtils;
/**
* Convert HBase tabular data into a format that is consumable by Map/Reduce.
* 此类继承了TableInputFormatBase,重写了其中的connection方法,获得经过认证的user,即可对hbase进行读操作
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class MyTableInputFormat extends TableInputFormatBase
implements Configurable {
@SuppressWarnings("hiding")
private static final Log LOG = LogFactory.getLog(MyTableInputFormat.class);
/** Job parameter that specifies the input table. */
public static final String INPUT_TABLE = "hbase.mapreduce.inputtable";
/**
* If specified, use start keys of this table to split.
* This is useful when you are preparing data for bulkload.
*/
private static final String SPLIT_TABLE = "hbase.mapreduce.splittable";
/** Base-64 encoded scanner. All other SCAN_ confs are ignored if this is specified.
* {@link TableMapReduceUtil#convertScanToString(Scan)} for more details.
*/
public static final String SCAN = "hbase.mapreduce.scan";
/** Scan start row */
public static final String SCAN_ROW_START = "hbase.mapreduce.scan.row.start";
/** Scan stop row */
public static final String SCAN_ROW_STOP = "hbase.mapreduce.scan.row.stop";
/** Column Family to Scan */
public static final String SCAN_COLUMN_FAMILY = "hbase.mapreduce.scan.column.family";
/** Space delimited list of columns and column families to scan. */
public static final String SCAN_COLUMNS = "hbase.mapreduce.scan.columns";
/** The timestamp used to filter columns with a specific timestamp. */
public static final String SCAN_TIMESTAMP = "hbase.mapreduce.scan.timestamp";
/** The starting timestamp used to filter columns with a specific range of versions. */
public static final String SCAN_TIMERANGE_START = "hbase.mapreduce.scan.timerange.start";
/** The ending timestamp used to filter columns with a specific range of versions. */
public static final String SCAN_TIMERANGE_END = "hbase.mapreduce.scan.timerange.end";
/** The maximum number of version to return. */
public static final String SCAN_MAXVERSIONS = "hbase.mapreduce.scan.maxversions";
/** Set to false to disable server-side caching of blocks for this scan. */
public static final String SCAN_CACHEBLOCKS = "hbase.mapreduce.scan.cacheblocks";
/** The number of rows for caching that will be passed to scanners. */
public static final String SCAN_CACHEDROWS = "hbase.mapreduce.scan.cachedrows";
/** Set the maximum number of values to return for each call to next(). */
public static final String SCAN_BATCHSIZE = "hbase.mapreduce.scan.batchsize";
/** Specify if we have to shuffle the map tasks. */
public static final String SHUFFLE_MAPS = "hbase.mapreduce.inputtable.shufflemaps";
/** The configuration. */
private Configuration conf = null;
/** The kerberos authenticated user*/
private User user;
/**
* Returns the current configuration.
*
* @return The current configuration.
* @see Configurable#getConf()
*/
@Override
public Configuration getConf() {
return conf;
}
/**
* Sets the configuration. This is used to set the details for the table to
* be scanned.
*
* @param configuration The configuration to set.
* @see Configurable#setConf(
* Configuration)
*/
@Override
@edu.umd.cs.findbugs.annotations.SuppressWarnings(value="REC_CATCH_EXCEPTION",
justification="Intentional")
public void setConf(Configuration configuration) {
this.conf = configuration;
//=========get kerberos authentication before create hbase connection==========
//注意获取用户之前要再次认证
user = HbaseUtilNew.getAuthenticatedUser(conf, DmpProperties.getInstance());
LogUtil.info(LOG, "user:" + user.getName());
//=============================================================================
Scan scan = null;
if (conf.get(SCAN) != null) {
try {
scan = TableMapReduceUtil.convertStringToScan(conf.get(SCAN));
} catch (IOException e) {
LOG.error("An error occurred.", e);
}
} else {
try {
scan = new Scan();
if (conf.get(SCAN_ROW_START) != null) {
scan.setStartRow(Bytes.toBytes(conf.get(SCAN_ROW_START)));
}
if (conf.get(SCAN_ROW_STOP) != null) {
scan.setStopRow(Bytes.toBytes(conf.get(SCAN_ROW_STOP)));
}
if (conf.get(SCAN_COLUMNS) != null) {
addColumns(scan, conf.get(SCAN_COLUMNS));
}
if (conf.get(SCAN_COLUMN_FAMILY) != null) {
scan.addFamily(Bytes.toBytes(conf.get(SCAN_COLUMN_FAMILY)));
}
if (conf.get(SCAN_TIMESTAMP) != null) {
scan.setTimeStamp(Long.parseLong(conf.get(SCAN_TIMESTAMP)));
}
if (conf.get(SCAN_TIMERANGE_START) != null && conf.get(SCAN_TIMERANGE_END) != null) {
scan.setTimeRange(
Long.parseLong(conf.get(SCAN_TIMERANGE_START)),
Long.parseLong(conf.get(SCAN_TIMERANGE_END)));
}
if (conf.get(SCAN_MAXVERSIONS) != null) {
scan.setMaxVersions(Integer.parseInt(conf.get(SCAN_MAXVERSIONS)));
}
if (conf.get(SCAN_CACHEDROWS) != null) {
scan.setCaching(Integer.parseInt(conf.get(SCAN_CACHEDROWS)));
}
if (conf.get(SCAN_BATCHSIZE) != null) {
scan.setBatch(Integer.parseInt(conf.get(SCAN_BATCHSIZE)));
}
// false by default, full table scans generate too much BC churn
scan.setCacheBlocks((conf.getBoolean(SCAN_CACHEBLOCKS, false)));
} catch (Exception e) {
LOG.error(StringUtils.stringifyException(e));
}
}
setScan(scan);
}
@Override
protected void initialize(JobContext context) throws IOException {
// Do we have to worry about mis-matches between the Configuration from setConf and the one
// in this context?
TableName tableName = TableName.valueOf(conf.get(INPUT_TABLE));
try {
//====================add authenticated user ===================
initializeTable(ConnectionFactory.createConnection(new Configuration(conf),user), tableName);
} catch (Exception e) {
LOG.error(StringUtils.stringifyException(e));
}
}
/**
* Parses a combined family and qualifier and adds either both or just the
* family in case there is no qualifier. This assumes the older colon
* divided notation, e.g. "family:qualifier".
*
* @param scan The Scan to update.
* @param familyAndQualifier family and qualifier
* @throws IllegalArgumentException When familyAndQualifier is invalid.
*/
private static void addColumn(Scan scan, byte[] familyAndQualifier) {
byte [][] fq = KeyValue.parseColumn(familyAndQualifier);
if (fq.length == 1) {
scan.addFamily(fq[0]);
} else if (fq.length == 2) {
scan.addColumn(fq[0], fq[1]);
} else {
throw new IllegalArgumentException("Invalid familyAndQualifier provided.");
}
}
/**
* Adds an array of columns specified using old format, family:qualifier.
* <p>
* Overrides previous calls to {@link Scan#addColumn(byte[], byte[])}for any families in the
* input.
*
* @param scan The Scan to update.
* @param columns array of columns, formatted as <code>family:qualifier</code>
* @see Scan#addColumn(byte[], byte[])
*/
public static void addColumns(Scan scan, byte [][] columns) {
for (byte[] column : columns) {
addColumn(scan, column);
}
}
/**
* Calculates the splits that will serve as input for the map tasks. The
* number of splits matches the number of regions in a table. Splits are shuffled if
* required.
* @param context The current job context.
* @return The list of input splits.
* @throws IOException When creating the list of splits fails.
* @see org.apache.hadoop.mapreduce.InputFormat#getSplits(
* JobContext)
*/
@Override
public List<InputSplit> getSplits(JobContext context) throws IOException {
List<InputSplit> splits = super.getSplits(context);
if ((conf.get(SHUFFLE_MAPS) != null) && "true".equals(conf.get(SHUFFLE_MAPS).toLowerCase())) {
Collections.shuffle(splits);
}
return splits;
}
/**
* Convenience method to parse a string representation of an array of column specifiers.
*
* @param scan The Scan to update.
* @param columns The columns to parse.
*/
private static void addColumns(Scan scan, String columns) {
String[] cols = columns.split(" ");
for (String col : cols) {
addColumn(scan, Bytes.toBytes(col));
}
}
@Override
protected Pair<byte[][], byte[][]> getStartEndKeys() throws IOException {
if (conf.get(SPLIT_TABLE) != null) {
TableName splitTableName = TableName.valueOf(conf.get(SPLIT_TABLE));
//====================add authenticated user ===================
try (Connection conn = ConnectionFactory.createConnection(getConf(),user)) {
try (RegionLocator rl = conn.getRegionLocator(splitTableName)) {
return rl.getStartEndKeys();
}
}
}
return super.getStartEndKeys();
}
/**
* Sets split table in map-reduce job.
*/
public static void configureSplitTable(Job job, TableName tableName) {
job.getConfiguration().set(SPLIT_TABLE, tableName.getNameAsString());
}
}
/**
*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.hadoop.hbase.mapreduce;
import java.io.IOException;
import ***.DmpProperties;
import ***.HbaseUtilNew;
import ***.LogUtil;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.hbase.classification.InterfaceAudience;
import org.apache.hadoop.hbase.classification.InterfaceStability;
import org.apache.hadoop.conf.Configurable;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HConstants;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.BufferedMutator;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Mutation;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.security.User;
import org.apache.hadoop.hbase.zookeeper.ZKUtil;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.OutputCommitter;
import org.apache.hadoop.mapreduce.OutputFormat;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
/**
* Convert Map/Reduce output and write it to an HBase table. The KEY is ignored
* while the output value <u>must</u> be either a {@link Put} or a
* {@link Delete} instance.
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class MyTableOutputFormat<KEY> extends OutputFormat<KEY, Mutation>
implements Configurable {
private static final Log LOG = LogFactory.getLog(MyTableOutputFormat.class);
/** Job parameter that specifies the output table. */
public static final String OUTPUT_TABLE = "hbase.mapred.outputtable";
/**
* Optional job parameter to specify a peer cluster.
* Used specifying remote cluster when copying between hbase clusters (the
* source is picked up from <code>hbase-site.xml</code>).
* @see TableMapReduceUtil#initTableReducerJob(String, Class, org.apache.hadoop.mapreduce.Job, Class, String, String, String)
*/
public static final String QUORUM_ADDRESS = "hbase.mapred.output.quorum";
/** Optional job parameter to specify peer cluster's ZK client port */
public static final String QUORUM_PORT = "hbase.mapred.output.quorum.port";
/** Optional specification of the rs class name of the peer cluster */
public static final String
REGION_SERVER_CLASS = "hbase.mapred.output.rs.class";
/** Optional specification of the rs impl name of the peer cluster */
public static final String
REGION_SERVER_IMPL = "hbase.mapred.output.rs.impl";
/** The configuration. */
private Configuration conf = null;
/** The kerberos authenticated user*/
private User user;
/**
* Writes the reducer output to an HBase table.
*/
protected class TableRecordWriter
extends RecordWriter<KEY, Mutation> {
private Connection connection;
private BufferedMutator mutator;
/**
* @throws IOException
*
*/
public TableRecordWriter() throws IOException {
String tableName = conf.get(OUTPUT_TABLE);
//====================add authenticated user ===================
this.connection = ConnectionFactory.createConnection(conf,user);
this.mutator = connection.getBufferedMutator(TableName.valueOf(tableName));
LOG.info("Created table instance for " + tableName);
}
/**
* Closes the writer, in this case flush table commits.
*
* @param context The context.
* @throws IOException When closing the writer fails.
* @see RecordWriter#close(TaskAttemptContext)
*/
@Override
public void close(TaskAttemptContext context)
throws IOException {
mutator.close();
connection.close();
}
/**
* Writes a key/value pair into the table.
*
* @param key The key.
* @param value The value.
* @throws IOException When writing fails.
* @see RecordWriter#write(Object, Object)
*/
@Override
public void write(KEY key, Mutation value)
throws IOException {
if (!(value instanceof Put) && !(value instanceof Delete)) {
throw new IOException("Pass a Delete or a Put");
}
mutator.mutate(value);
}
}
/**
* Creates a new record writer.
*
* @param context The current task context.
* @return The newly created writer instance.
* @throws IOException When creating the writer fails.
* @throws InterruptedException When the jobs is cancelled.
*/
@Override
public RecordWriter<KEY, Mutation> getRecordWriter(TaskAttemptContext context)
throws IOException, InterruptedException {
return new TableRecordWriter();
}
/**
* Checks if the output target exists.
*
* @param context The current context.
* @throws IOException When the check fails.
* @throws InterruptedException When the job is aborted.
* @see OutputFormat#checkOutputSpecs(JobContext)
*/
@Override
public void checkOutputSpecs(JobContext context) throws IOException,
InterruptedException {
// TODO Check if the table exists?
}
/**
* Returns the output committer.
*
* @param context The current context.
* @return The committer.
* @throws IOException When creating the committer fails.
* @throws InterruptedException When the job is aborted.
* @see OutputFormat#getOutputCommitter(TaskAttemptContext)
*/
@Override
public OutputCommitter getOutputCommitter(TaskAttemptContext context)
throws IOException, InterruptedException {
return new TableOutputCommitter();
}
@Override
public Configuration getConf() {
return conf;
}
@Override
public void setConf(Configuration otherConf) {
this.conf = HBaseConfiguration.create(otherConf);
//=========get kerberos authentication before create hbase connection==========
user = HbaseUtilNew.getAuthenticatedUser(conf, DmpProperties.getInstance());
LogUtil.info(LOG, "user:" + user.getName());
String tableName = this.conf.get(OUTPUT_TABLE);
if(tableName == null || tableName.length() <= 0) {
throw new IllegalArgumentException("Must specify table name");
}
String address = this.conf.get(QUORUM_ADDRESS);
int zkClientPort = this.conf.getInt(QUORUM_PORT, 0);
String serverClass = this.conf.get(REGION_SERVER_CLASS);
String serverImpl = this.conf.get(REGION_SERVER_IMPL);
try {
if (address != null) {
ZKUtil.applyClusterKeyToConf(this.conf, address);
}
if (serverClass != null) {
this.conf.set(HConstants.REGION_SERVER_IMPL, serverImpl);
}
if (zkClientPort != 0) {
this.conf.setInt(HConstants.ZOOKEEPER_CLIENT_PORT, zkClientPort);
}
} catch(IOException e) {
LOG.error(e);
throw new RuntimeException(e);
}
}
}
package hbase
import java.io.IOException
import ***.DmpProperties
import ***.util._
import org.apache.commons.logging.LogFactory
import org.apache.hadoop.hbase.TableName
import org.apache.hadoop.hbase.client.{Connection, Put}
import org.apache.hadoop.hbase.mapreduce.{MyTableOutputFormat, TableOutputFormat}
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.mapreduce.Job
import org.apache.hadoop.hbase.client.{Get, Put, Result}
import org.apache.hadoop.hbase.util.Bytes
import org.apache.log4j.{Level, Logger}
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
object HbaseWriteTest {
private val log = LogFactory.getLog(this.getClass)
def main(args: Array[String]) {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.hadoop").setLevel(Level.WARN)
Logger.getLogger("org.apache.zookeeper").setLevel(Level.WARN)
Logger.getLogger("org.apache.hive").setLevel(Level.WARN)
println("------------------ main start ------------------")
val dmpProperties = DmpProperties.getInstance()
val conf = new SparkConf()
.setAppName("HbaseWriteTes")
.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
if(!CommonUtil.isLinux){
conf.setMaster("local[1]")
}
val sc = new SparkContext(conf)
if(dmpProperties.IS_KERBEROSE){
val driver_keytab = dmpProperties.KERBEROSE_KEYTAB
sc.addFile(driver_keytab)
}
val job = {
try {
val hbaseConf = HbaseUtilNew.hbaseConfig(dmpProperties)
hbaseConf.set(TableOutputFormat.OUTPUT_TABLE, dmpProperties.HBASE_USER_DEVICEID_TABLE)
lazy val job = Job.getInstance(hbaseConf)
job.setOutputKeyClass(classOf[ImmutableBytesWritable])
job.setOutputValueClass(classOf[Result])
job.setOutputFormatClass(classOf[MyTableOutputFormat[ImmutableBytesWritable]])
job
} catch {
case ex: IOException => throw new Exception("init hbase error", ex)
}
}
val aa=args(0)
val bb=args(1)
// val seq = List("r1|cf1|v1","r2|cf1|v2","r3|cf1|v3","r4|cf1|v4")
val seq = List(aa,bb)
val rdd: RDD[String] = sc.parallelize(seq)
val putRdd = rdd.map(record => {
LogUtil.info(log,s"record: ${record}")
val split: Array[String] = record.split("\\|")
val rowkey = split(0)
val cf = split(1)
val value = split(2)
LogUtil.info(log,s"rowkey: ${rowkey}, cf: ${cf}, value: ${value},")
val put: Put = new Put(Bytes.toBytes(rowkey))
put.addColumn(Bytes.toBytes(cf), Bytes.toBytes("c1"), Bytes.toBytes(value))
(new ImmutableBytesWritable, put)
})
putRdd.saveAsNewAPIHadoopDataset(job.getConfiguration)
sc.stop()
}
}
package hbase
import ***.DmpProperties
import ***.util._
import org.apache.commons.logging.LogFactory
import org.apache.hadoop.hbase.CellUtil
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.mapreduce.{MyTableInputFormat, TableInputFormat}
import org.apache.hadoop.hbase.util.Bytes
import org.apache.log4j.{Level, Logger}
import org.apache.spark.{SparkConf, SparkContext}
object HbaseReadTest {
private val log = LogFactory.getLog(this.getClass)
def main(args: Array[String]) {
Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
Logger.getLogger("org.apache.hadoop").setLevel(Level.WARN)
Logger.getLogger("org.apache.zookeeper").setLevel(Level.WARN)
Logger.getLogger("org.apache.hive").setLevel(Level.WARN)
println("------------------ main start ------------------")
val dmpProperties = DmpProperties.getInstance()
val conf = new SparkConf()
.setAppName("HbaseReadTes")
.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
if(!CommonUtil.isLinux){
conf.setMaster("local[1]")
}
val sc = new SparkContext(conf)
if(dmpProperties.IS_KERBEROSE){
val driver_keytab = dmpProperties.KERBEROSE_KEYTAB
sc.addFile(driver_keytab)
}
val hbaseConf = HbaseUtilNew.hbaseConfig(dmpProperties)
hbaseConf.set(TableInputFormat.INPUT_TABLE, dmpProperties.HBASE_USER_DEVICEID_TABLE)
val hbaseRdd = sc.newAPIHadoopRDD(hbaseConf, classOf[MyTableInputFormat],
classOf[ImmutableBytesWritable],
classOf[org.apache.hadoop.hbase.client.Result])
import scala.collection.JavaConversions._
val keyValueRdd = hbaseRdd.map(_._2).map{ result =>
val hbaseValue = result.listCells().map(cell => {
val rowkey = Bytes.toString(CellUtil.cloneRow(cell))
val column = Bytes.toString(CellUtil.cloneQualifier(cell))
val value = Bytes.toString(CellUtil.cloneValue(cell))
(rowkey, column, value)
}).toSet
hbaseValue
}.flatMap(x => x)
val collect: Array[(String, String, String)] = keyValueRdd.collect()
println("============== size: "+collect.size)
println("============== collect(0): "+collect(0))
sc.stop()
}
}
用MyTableInputFormat 和 MyTableOutputFormat 替换 TableInputFormat、TableOutputFormat