Java 如何读取从oozie到scala（spark）的文件路径？

我需要使用oozie来安排spark作业，但我不知道如何使用oozie为特定日期生成文件路径并在scala中读取路径。示例配置有输入和输出，但这两个名称在多个地方使用，这使我感到困惑。如果我将${INPUT}传递给shell脚本，我不确定它是文件路径还是数据。因为

<property>
   <name>INPUT</name>
   <value>${coord:dataIn('INPUT_GCM_LOG')}</value>
</property>

<coordinator-app name="myjob"
             frequency="${coord:hours (1)}"
             start="${start_time}"
             end="${end_time}"
             timezone="${timezone}" xmlns="uri:oozie:coordinator:0.3">
<controls>
    <timeout>21600</timeout>
    <concurrency>${concurrency}</concurrency>
</controls>
<datasets>
    <dataset name="INPUT" frequency="${coord:hours(1)}" initial-instance="${ds_start}" timezone="${timezone}">
        <uri-template>${INPUT_TEMPLATE}</uri-template>
    </dataset>
    <dataset name="OUTPUT" frequency="${coord:days(1)}" initial-instance="${ds_start}" timezone="${timezone}">
        <uri-template>${OUTPUT_TEMPLATE}</uri-template>
    </dataset>
</datasets>
<input-events>
    <data-in name="INPUT" dataset="INPUT">
        <instance>${coord:current(0)}</instance>
    </data-in>
</input-events>
<output-events>
    <data-out name="OUTPUT" dataset="OUTPUT">
        <instance>${coord:current(0)}</instance>
    </data-out>
</output-events>
<action>
    <workflow>
        <app-path>${app_dir}</app-path>
        <configuration>
            <property>
                <name>INPUT</name>
                <value>${coord:dataIn('INPUT_GCM_LOG')}</value>
            </property>
            <property>
                <name>OUTPUT</name>
                <value>${coord:dataOut('OUTPUT')}</value>
            </property>
        </configuration>
    </workflow>
</action>

<action name="spark_shell" retry-max="0" retry-interval="0">
    <shell xmlns="uri:oozie:shell-action:0.1">
        <job-tracker>${job_tracker}</job-tracker>
        <name-node>${name_node}</name-node>
        <prepare>
            <delete path="${OUTPUT_TEMPLATE}" />
        </prepare>
        <configuration>
            <property>
                <name>mapreduce.job.queuename</name>
                <value>${queue_name}</value>
            </property>
            <property>
                <name>mapreduce.job.acl-view-job</name>
                <value>*</value>
            </property>
            <property>
                <name>oozie.launcher.mapreduce.map.memory.mb</name>
                <value>6144</value>
            </property>
            <property>
                <name>oozie.launcher.mapreduce.job.acl-view-job</name>
                <value>*</value>
            </property>
            <property>
                <name>mapreduce.job.acl-modify-job</name>
                <value>*</value>
            </property>
        </configuration>
        <exec>run.sh</exec>
        <argument>${INPUT}</argument>
        <argument>${OUTPUT}</argument>
        <env-var>HADOOP_USER_NAME=${USER}</env-var>
        <env-var>YARN_CONF_DIR=/usr/lib/spark/conf</env-var>
        <env-var>HADOOP_CONF_DIR=/etc/hadoop/conf</env-var>
        <file>lib/run.sh</file>
        <archive>/user/bac/spark-1.6.1-bin-hadoop2.6</archive>
    </shell>
    <ok to="end" />
    <error to="fail" />
</action>

<kill name="fail">
    <message>fail : ERROR MSG - [${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>

<end name='end' />

# Coordinator
oozie.coord.application.path=/user/xxx/xxxx
app_dir=/user/xxx/xxxx

oozie.use.system.libpath=true
oozie.user=xxxxx
# Workflow
job_tracker=mycluster
name_node=hdfs://mycluster
queue_name=xxxxx
thrift_uri=xxxx
oozie_server=xxxx
job_name=xxxx
# ACL
acl_view_job=*
acl_modify_job=*

#input datasets
INPUT_TEMPLATE=/projects/xxx/${YEAR}${MONTH}${DAY}/${HOUR}

#output datasets
OUTPUT_TEMPLATE=/projects/xxx/${YEAR}${MONTH}${DAY}/${HOUR}/output
start_time=2016-12-04T00:00Z
end_time=2017-12-05T00:00Z
ds_start=2013-01-01T00:00Z
concurrency=2
#params
timezone=UTC
USER=xxx