在Oozie中配置 map-reduce workflow

## prepare wordcount case
$ cd ~/work/oozie-5.2.1
$ tree oozie
oozie
├── apps
│   └── wordcount
│       ├── job.properties
│       ├── job.properties.orig
│       ├── lib
│       │   └── wordcount.jar
│       ├── workflow.xml
│       └── workflow.xml.orig
└── data
    └── wordcount
        └── input
           └── in.txt

$ cat oozie/apps/wordcount/job.properties

nameNode=hdfs://localhost:9000
resourceManager=localhost:8032
queueName=default
oozieRoot=user/${user.name}/oozie

oozie.wf.application.path=${nameNode}/${oozieRoot}/apps/wordcount/workflow.xml
inputDir=data/wordcount/input
outputDir=data/wordcount/output

$ cat oozie/apps/wordcount/workflow.xml

<workflow-app xmlns="uri:oozie:workflow:1.0" name="wordcount-wf">
    <start to="wordcount-node"/>
    <action name="wordcount-node">
        <map-reduce>
            <resource-manager>${resourceManager}</resource-manager>
            <name-node>${nameNode}</name-node>
            <prepare>
                <delete path="${nameNode}/${oozieRoot}/${outputDir}"/>
            </prepare>
            <configuration>
                <property>
                    <name>mapred.mapper.new-api</name>
                    <value>true</value>
                </property>
                <property>
                    <name>mapred.reducer.new-api</name>
                    <value>true</value>
                </property>
                <property>
                    <name>mapreduce.job.queuename</name>
                    <value>${queueName}</value>
                </property>
                <property>
                    <name>mapreduce.job.map.class</name>
                    <value>WordCount$TokenizerMapper</value>
                </property>
                <property>
                    <name>mapreduce.job.reduce.class</name>
                    <value>WordCount$IntSumReducer</value>
                </property>
                <property>
                    <name>mapreduce.job.output.key.class</name>
                    <value>org.apache.hadoop.io.Text</value>
                </property>
                <property>
                    <name>mapreduce.job.output.value.class</name>
                    <value>org.apache.hadoop.io.IntWritable</value>
                </property>
                <property>
                    <name>mapreduce.input.fileinputformat.inputdir</name>
					<value>${nameNode}/${oozieRoot}/${inputDir}</value>
                </property>
                <property>
                    <name>mapreduce.output.fileoutputformat.outputdir</name>
                    <value>${nameNode}/${oozieRoot}/${outputDir}</value>
                </property>
            </configuration>
        </map-reduce>
        <ok to="end"/>
        <error to="fail"/>
    </action>
    <kill name="fail">
        <message>Map/Reduce failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    <end name="end"/>
</workflow-app>

Note: all key / value pairs in workflow.xml can be searched from
http://localhost:8088/cluster -> Application's History -> Job / Configuration

$ cat oozie/data/wordcount/input/in.txt

hadoop
mapreduce
hdfs
hbase
hdfs
spark
hive
hcatalog
sqoop
flume
kafka
oozie
hue

## upload case
$ hdfs dfs -put oozie /user/sun_xo/oozie
$ hdfs dfs -rm -f -r /user/sun_xo/oozie/data/wordcount/output

## start oozie
$ cd ~/work/oozie-5.2.1
$ bin/oozied.sh start
$ export OOZIE_URL=http://localhost:11000/oozie
$ bin/oozie job -config oozie/apps/wordcount/job.properties -run
job: 0000000-220523112321053-oozie-sun_-W
$ bin/oozie job -info 0000000-220523112321053-oozie-sun_-W

ob ID : 0000000-220602202911687-oozie-sun_-W
------------------------------------------------------------------------------------------------------------------------------------
Workflow Name : wordcount-wf
App Path      : hdfs://localhost:9000/user/sun_xo/oozie/apps/wordcount/workflow.xml
Status        : SUCCEEDED
Run           : 0
User          : sun_xo
Group         : -
Created       : 2022-06-02 12:30 GMT
Started       : 2022-06-02 12:30 GMT
Last Modified : 2022-06-02 12:30 GMT
Ended         : 2022-06-02 12:30 GMT
CoordAction ID: -

Actions
------------------------------------------------------------------------------------------------------------------------------------
ID                                                                            Status    Ext ID                 Ext Status Err Code  
------------------------------------------------------------------------------------------------------------------------------------
[email protected]:start:                                  OK        -                      OK         -         
------------------------------------------------------------------------------------------------------------------------------------
[email protected]                           OK        application_1653709899071_0004SUCCEEDED  -         
------------------------------------------------------------------------------------------------------------------------------------
[email protected]                                      OK        -                      OK         -         
------------------------------------------------------------------------------------------------------------------------------------

$ hdfs dfs -cat "/user/sun_xo/oozie/data/wordcount/output/*"

flume	1
hadoop	1
hbase	1
hcatalog	1
hdfs	2
hive	1
hue	1
kafka	1
mapreduce	1
oozie	1
spark	1
sqoop	1

reference: 搭建Ozzie环境
reference: 搭建map-reduce开发环境