dharkum

package HiveUDF; 
 import java.util.regex.Matcher; 
 import java.util.regex.Pattern; 
 import org.apache.hadoop.hive.ql.exec.UDF; 
 public final class FindPattern extends UDF 
 { 
     public static String evaluate(String targetString, String strPattern) 
     {                  
         // Pattern matching on the input pattern 
         Pattern p = Pattern.compile(strPattern); 

dharkum

CREATE EXTERNAL TABLE IF NOT EXISTS WebFeeds 
 ( 
 UserID int, 
 Message String 
 ) 
 ROW FORMAT DELIMITED 
 FIELDS TERMINATED BY ',' 
 STORED AS TEXTFILE 
 LOCATION 'wasb://install@myprimarystorage.blob.core.windows.net/webfeeds'; 
 

dharkum

param 
( 
  
 ############################################################################# 
 ### Please edit the values of the parameters below for your configuration ### 
 ############################################################################# 
 
 [string]$PrimarySubscriptionName="<Your Subscription Name>", # Replace <Your Subscription Name> with your Azure subscription name 
 [string]$HDInsightClusterLocation="West US", # This is the data center where you are going to provision this HDInsight cluster 
 [string]$HDInsightClusterName="MyHDICluster", # This is the name that you want for the HDInsight cluster 

dharkum

############################################################################# 
### Please edit the values of the parameters below for your configuration ### 
############################################################################# 
 
$subscriptionName = "<Your Azure Subscription Name>" 
$clusterName = "MyHDICluster" # HDInsight Cluster Name 
 
############################################################################ 
###                               End Edits                              ### 
############################################################################ 

dharkum

<coordinator-app name="MY_APP" frequency="${coord:months(1)}" start="${jobStart}" end="${jobEnd}" timezone="UTC" xmlns="uri:oozie:coordinator:0.3">
    <datasets>
      <dataset name="input1" frequency="${coord:months(1)}" initial-instance="${initialInstance}" timezone="UTC">
         <uri-template>hcat://headnode0:9083/default/samplelog/dt=${YEAR}-${MONTH}</uri-template>
      </dataset>
   </datasets>
   <input-events>
      <data-in name="coordInput1" dataset="input1">
          <instance>${coord:current(1)}</instance>
      </data-in>

dharkum

<workflow-app xmlns="uri:oozie:workflow:0.2" name="hive-wf">
    <start to="hive-node"/>
    <action name="hive-node">
        <hive xmlns="uri:oozie:hive-action:0.2">
           <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <configuration>
                <property>
                    <name>mapred.job.queue.name</name>
                    <value>default</value>

dharkum

ALTER TABLE samplelog DROP IF EXISTS PARTITION (dt<'${DROPDT}');

dharkum

#region edits

# This is the name of the Azure HDInsight Subscription
[string]$SubscriptionName = "Contoso2014"
# This is the HDInsight Cluster Name that you want to work with
[string]$HDInsightClusterName = "ServerLogs" 
# The table specified here will be dropped, please ensure that this is a test table 
[string]$TableName = "samplelog" 
# This is the location where the external table's data will be located on WASB

dharkum

#region edits

# Your HDInsight Cluster Name
$HDIClusterName = "ServerLogs" 
# Your HDInisght Cluster Admin User Name
$MyHDInsightUserName = "sysadmin"
# Your HDInsight Cluster Admin Password 
$MyHdInsightPwd = "xxxx"
# Your HDInsight Metastore User Name

dharkum

##################### Begin Edits ####################
#region edits
param
(
    # NOTE: All the storage accounts and containers need to be created on the same data center as the HDInsight cluster and would need to be created prior to running the script
    # They can be created from the Azure Management Portal

    # This is the name of your Azure Subscription that will be used for provisiong Azure HDInsight
    [string]$PrimarySubscriptionName="xxx",
    # This is the primary storage account that needs to be created on the same data center as your HDInsight Cluster