Hcatalog 简明教程

export HADOOP_HOME=/usr/local/hadoop
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export PATH=$PATH:$HADOOP_HOME/sbin:$HADOOP_HOME/bin

$ source ~/.bashrc

$ cd $HADOOP_HOME/etc/hadoop

export JAVA_HOME=/usr/local/jdk1.7.0_71

<configuration>
   <property>
      <name>fs.default.name</name>
      <value>hdfs://localhost:9000</value>
   </property>
</configuration>

dfs.replication (data replication value) = 1

(In the following path /hadoop/ is the user name.
hadoopinfra/hdfs/namenode is the directory created by hdfs file system.)

namenode path = //home/hadoop/hadoopinfra/hdfs/namenode

(hadoopinfra/hdfs/datanode is the directory created by hdfs file system.)
datanode path = //home/hadoop/hadoopinfra/hdfs/datanode

<configuration>
   <property>
      <name>dfs.replication</name>
      <value>1</value>
   </property>

   <property>
      <name>dfs.name.dir</name>
      <value>file:///home/hadoop/hadoopinfra/hdfs/namenode</value>
   </property>

   <property>
      <name>dfs.data.dir</name>
      <value>file:///home/hadoop/hadoopinfra/hdfs/datanode</value>
   </property>
</configuration>

<configuration>
   <property>
      <name>yarn.nodemanager.aux-services</name>
      <value>mapreduce_shuffle</value>
   </property>
</configuration>

$ cp mapred-site.xml.template mapred-site.xml

<configuration>
   <property>
      <name>mapreduce.framework.name</name>
      <value>yarn</value>
   </property>
</configuration>

$ cd ~
$ hdfs namenode -format

10/24/14 21:30:55 INFO namenode.NameNode: STARTUP_MSG:
/************************************************************
STARTUP_MSG: Starting NameNode
STARTUP_MSG: host = localhost/192.168.1.11
STARTUP_MSG: args = [-format]
STARTUP_MSG: version = 2.4.1
...
...
10/24/14 21:30:56 INFO common.Storage: Storage directory
/home/hadoop/hadoopinfra/hdfs/namenode has been successfully formatted.
10/24/14 21:30:56 INFO namenode.NNStorageRetentionManager: Going to retain 1
images with txid >= 0 10/24/14 21:30:56 INFO util.ExitUtil: Exiting with status 0
10/24/14 21:30:56 INFO namenode.NameNode: SHUTDOWN_MSG:
/************************************************************
SHUTDOWN_MSG: Shutting down NameNode at localhost/192.168.1.11
************************************************************/

$ start-dfs.sh

10/24/14 21:37:56 Starting namenodes on [localhost]
localhost: starting namenode, logging to
/home/hadoop/hadoop-2.4.1/logs/hadoop-hadoop-namenode-localhost.out localhost:
starting datanode, logging to
   /home/hadoop/hadoop-2.4.1/logs/hadoop-hadoop-datanode-localhost.out
Starting secondary namenodes [0.0.0.0]

$ start-yarn.sh

starting yarn daemons
starting resourcemanager, logging to /home/hadoop/hadoop-2.4.1/logs/
yarn-hadoop-resourcemanager-localhost.out
localhost: starting nodemanager, logging to
   /home/hadoop/hadoop-2.4.1/logs/yarn-hadoop-nodemanager-localhost.out

http://localhost:50070/

http://localhost:8088/

$ tar zxvf apache-hive-0.14.0-bin.tar.gz
$ ls

apache-hive-0.14.0-bin apache-hive-0.14.0-bin.tar.gz

$ su -
passwd:
# cd /home/user/Download
# mv apache-hive-0.14.0-bin /usr/local/hive
# exit

export HIVE_HOME=/usr/local/hive
export PATH=$PATH:$HIVE_HOME/bin
export CLASSPATH=$CLASSPATH:/usr/local/Hadoop/lib/*:.
export CLASSPATH=$CLASSPATH:/usr/local/hive/lib/*:.

$ source ~/.bashrc

$ cd ~
$ wget http://archive.apache.org/dist/db/derby/db-derby-10.4.2.0/db-derby-10.4.2.0-bin.tar.gz

$ ls

db-derby-10.4.2.0-bin.tar.gz

$ tar zxvf db-derby-10.4.2.0-bin.tar.gz
$ ls

db-derby-10.4.2.0-bin db-derby-10.4.2.0-bin.tar.gz

$ su -
passwd:
# cd /home/user
# mv db-derby-10.4.2.0-bin /usr/local/derby
# exit

export DERBY_HOME=/usr/local/derby
export PATH=$PATH:$DERBY_HOME/bin
export CLASSPATH=$CLASSPATH:$DERBY_HOME/lib/derby.jar:$DERBY_HOME/lib/derbytools.jar

$ source ~/.bashrc

$ mkdir $DERBY_HOME/data

CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.] table_name
[(col_name data_type [COMMENT col_comment], ...)]
[COMMENT table_comment]
[ROW FORMAT row_format]
[STORED AS file_format]

COMMENT ‘Employee details’
FIELDS TERMINATED BY ‘\t’
LINES TERMINATED BY ‘\n’
STORED IN TEXT FILE

./hcat –e "CREATE TABLE IF NOT EXISTS employee ( eid int, name String,
   salary String, destination String) \
COMMENT 'Employee details' \
ROW FORMAT DELIMITED \
FIELDS TERMINATED BY ‘\t’ \
LINES TERMINATED BY ‘\n’ \
STORED AS TEXTFILE;"

OK
Time taken: 5.905 seconds

LOAD DATA [LOCAL] INPATH 'filepath' [OVERWRITE] INTO TABLE tablename
[PARTITION (partcol1=val1, partcol2=val2 ...)]

1201  Gopal        45000    Technical manager
1202  Manisha      45000    Proof reader
1203  Masthanvali  40000    Technical writer
1204  Kiran        40000    Hr Admin
1205  Kranthi      30000    Op Admin

./hcat –e "LOAD DATA LOCAL INPATH '/home/user/sample.txt'
OVERWRITE INTO TABLE employee;"

OK
Time taken: 15.905 seconds

ALTER TABLE name RENAME TO new_name
ALTER TABLE name ADD COLUMNS (col_spec[, col_spec ...])
ALTER TABLE name DROP [COLUMN] column_name
ALTER TABLE name CHANGE column_name new_name new_type
ALTER TABLE name REPLACE COLUMNS (col_spec[, col_spec ...])

CREATE VIEW [IF NOT EXISTS] [db_name.]view_name [(column_name [COMMENT column_comment], ...) ]
[COMMENT view_comment]
[TBLPROPERTIES (property_name = property_value, ...)]
AS SELECT ...;

+------+-------------+--------+-------------------+-------+
|  ID  |    Name     | Salary |    Designation    | Dept  |
+------+-------------+--------+-------------------+-------+
| 1201 |    Gopal    | 45000  | Technical manager |  TP   |
| 1202 |   Manisha   | 45000  | Proofreader       |  PR   |
| 1203 | Masthanvali | 30000  | Technical writer  |  TP   |
| 1204 |    Kiran    | 40000  | Hr Admin          |  HR   |
| 1205 |   Kranthi   | 30000  | Op Admin          | Admin |
+------+-------------+--------+-------------------+-------+

./hcat –e "CREATE VIEW Emp_Deg_View (salary COMMENT ' salary more than 35,000')
   AS SELECT id, name, salary, designation FROM employee WHERE salary ≥ 35000;"

OK
Time taken: 5.3 seconds

DROP VIEW [IF EXISTS] view_name;

DROP VIEW Emp_Deg_View;

id, name,   dept, yoj
1,  gopal,   TP, 2012
2,  kiran,   HR, 2012
3,  kaleel,  SC, 2013
4, Prasanth, SC, 2013

1, gopal, TP, 2012
2, kiran, HR, 2012

3, kaleel,   SC, 2013
4, Prasanth, SC, 2013

ALTER TABLE table_name ADD [IF NOT EXISTS] PARTITION partition_spec
[LOCATION 'location1'] partition_spec [LOCATION 'location2'] ...;
partition_spec:
: (p_column = p_col_value, p_column = p_col_value, ...)

./hcat –e "ALTER TABLE employee ADD PARTITION (year = '2013') location '/2012/part2012';"

./hcat –e "CREATE INDEX inedx_salary ON TABLE employee(salary)
AS 'org.apache.hadoop.hive.ql.index.compact.CompactIndexHandler';"

1, 3
3, 2
5, 1

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;

import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import org.apache.HCatalog.common.HCatConstants;
import org.apache.HCatalog.data.DefaultHCatRecord;
import org.apache.HCatalog.data.HCatRecord;
import org.apache.HCatalog.data.schema.HCatSchema;

import org.apache.HCatalog.mapreduce.HCatInputFormat;
import org.apache.HCatalog.mapreduce.HCatOutputFormat;
import org.apache.HCatalog.mapreduce.InputJobInfo;
import org.apache.HCatalog.mapreduce.OutputJobInfo;

public class GroupByAge extends Configured implements Tool {

   public static class Map extends Mapper<WritableComparable,
      HCatRecord, IntWritable, IntWritable> {
      int age;

      @Override
      protected void map(
         WritableComparable key, HCatRecord value,
         org.apache.hadoop.mapreduce.Mapper<WritableComparable,
         HCatRecord, IntWritable, IntWritable>.Context context
      )throws IOException, InterruptedException {
         age = (Integer) value.get(1);
         context.write(new IntWritable(age), new IntWritable(1));
      }
   }

   public static class Reduce extends Reducer<IntWritable, IntWritable,
      WritableComparable, HCatRecord> {
      @Override
      protected void reduce(
         IntWritable key, java.lang.Iterable<IntWritable> values,
         org.apache.hadoop.mapreduce.Reducer<IntWritable, IntWritable,
         WritableComparable, HCatRecord>.Context context
      )throws IOException ,InterruptedException {
         int sum = 0;
         Iterator<IntWritable> iter = values.iterator();

         while (iter.hasNext()) {
            sum++;
            iter.next();
         }

         HCatRecord record = new DefaultHCatRecord(2);
         record.set(0, key.get());
         record.set(1, sum);
         context.write(null, record);
      }
   }

   public int run(String[] args) throws Exception {
      Configuration conf = getConf();
      args = new GenericOptionsParser(conf, args).getRemainingArgs();

      String serverUri = args[0];
      String inputTableName = args[1];
      String outputTableName = args[2];
      String dbName = null;
      String principalID = System

      .getProperty(HCatConstants.HCAT_METASTORE_PRINCIPAL);
      if (principalID != null)
      conf.set(HCatConstants.HCAT_METASTORE_PRINCIPAL, principalID);
      Job job = new Job(conf, "GroupByAge");
      HCatInputFormat.setInput(job, InputJobInfo.create(dbName, inputTableName, null));

      // initialize HCatOutputFormat
      job.setInputFormatClass(HCatInputFormat.class);
      job.setJarByClass(GroupByAge.class);
      job.setMapperClass(Map.class);
      job.setReducerClass(Reduce.class);

      job.setMapOutputKeyClass(IntWritable.class);
      job.setMapOutputValueClass(IntWritable.class);
      job.setOutputKeyClass(WritableComparable.class);
      job.setOutputValueClass(DefaultHCatRecord.class);

      HCatOutputFormat.setOutput(job, OutputJobInfo.create(dbName, outputTableName, null));
      HCatSchema s = HCatOutputFormat.getTableSchema(job);
      System.err.println("INFO: output schema explicitly set for writing:" + s);
      HCatOutputFormat.setSchema(job, s);
      job.setOutputFormatClass(HCatOutputFormat.class);
      return (job.waitForCompletion(true) ? 0 : 1);
   }

   public static void main(String[] args) throws Exception {
      int exitCode = ToolRunner.run(new GroupByAge(), args);
      System.exit(exitCode);
   }
}

bin/hadoop fs -copyFromLocal $HCAT_HOME/share/HCatalog/HCatalog-core-0.5.0.jar /tmp
bin/hadoop fs -copyFromLocal $HIVE_HOME/lib/hive-metastore-0.10.0.jar /tmp
bin/hadoop fs -copyFromLocal $HIVE_HOME/lib/libthrift-0.7.0.jar /tmp
bin/hadoop fs -copyFromLocal $HIVE_HOME/lib/hive-exec-0.10.0.jar /tmp
bin/hadoop fs -copyFromLocal $HIVE_HOME/lib/libfb303-0.7.0.jar /tmp
bin/hadoop fs -copyFromLocal $HIVE_HOME/lib/jdo2-api-2.3-ec.jar /tmp
bin/hadoop fs -copyFromLocal $HIVE_HOME/lib/slf4j-api-1.6.1.jar /tmp

export LIB_JARS=hdfs:///tmp/HCatalog-core-0.5.0.jar,
hdfs:///tmp/hive-metastore-0.10.0.jar,
hdfs:///tmp/libthrift-0.7.0.jar,
hdfs:///tmp/hive-exec-0.10.0.jar,
hdfs:///tmp/libfb303-0.7.0.jar,
hdfs:///tmp/jdo2-api-2.3-ec.jar,
hdfs:///tmp/slf4j-api-1.6.1.jar

$HADOOP_HOME/bin/hadoop jar GroupByAge tmp/hive

001, Rajiv,    Reddy,       21, 9848022337, Hyderabad
002, siddarth, Battacharya, 22, 9848022338, Kolkata
003, Rajesh,   Khanna,      22, 9848022339, Delhi
004, Preethi,  Agarwal,     21, 9848022330, Pune
005, Trupthi,  Mohanthy,    23, 9848022336, Bhuwaneshwar
006, Archana,  Mishra,      23, 9848022335, Chennai
007, Komal,    Nayak,       24, 9848022334, trivendram
008, Bharathi, Nambiayar,   24, 9848022333, Chennai

student = LOAD 'hdfs://localhost:9000/pig_data/student_details.txt' USING
   PigStorage(',') as (id:int, firstname:chararray, lastname:chararray,
   phone:chararray, city:chararray);

student_order = ORDER student BY age DESC;
STORE student_order INTO 'student_order_table' USING org.apache.HCatalog.pig.HCatStorer();
student_limit = LIMIT student_order 4;
Dump student_limit;

$./pig -useHCatalog hdfs://localhost:9000/pig_data/sample_script.pig