Skip to content

Java fixes #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rmkr-dev merged 4 commits into from
Nov 22, 2025
Merged

Java fixes #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b416346
Fix XML formatting in pom.xml
rmkr-dev Nov 22, 2025
0b083b2
Refactor map method to include TableMapper context
rmkr-dev Nov 22, 2025
724bfd4
Fix method signature in ArchivalTagReducer
rmkr-dev Nov 22, 2025
73d19be
Add import for TableMapReduceUtil in AnonymizationPipelineDriver
rmkr-dev Nov 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,8 @@
<maven.compiler.target>11</maven.compiler.target>
<hadoop.version>3.3.4</hadoop.version>
<hbase.version>2.4.15</hbase.version>
<mapr.version>6.1.0-mapr</mapr.version> </properties>
<mapr.version>6.1.0-mapr</mapr.version>
</properties>

<dependencies>
<dependency>
Expand All @@ -26,6 +27,13 @@
<scope>provided</scope>
</dependency>

<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-mapreduce</artifactId>
<version>${hbase.version}</version>
<scope>provided</scope>
</dependency>

<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
Expand Down
1 change: 1 addition & 0 deletions src/main/java/com/mapr/health/driver/AnonymizationPipelineDriver.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;

public class AnonymizationPipelineDriver extends Configured implements Tool {

Expand Down
8 changes: 3 additions & 5 deletions src/main/java/com/mapr/health/job1/PHIAnonymizationMapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,8 @@
import com.mapr.health.util.SchemaUtility;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
Expand All @@ -26,9 +24,10 @@ public class PHIAnonymizationMapper
private final Text outputValue = new Text();

@Override
public void map(ImmutableBytesWritable rowKey, Result result, Context context)
public void map(ImmutableBytesWritable rowKey, Result result, TableMapper<Text, Text>.Context context)
throws IOException, InterruptedException {


// 1. Extract Raw PHI and Metadata
byte[] patientNameBytes = result.getValue(SchemaUtility.RAW_PHI_CF, SchemaUtility.PATIENT_NAME_COL);
byte[] visitDateBytes = result.getValue(SchemaUtility.METADATA_CF, SchemaUtility.VISIT_DATE_COL);
Expand All @@ -54,7 +53,6 @@ public void map(ImmutableBytesWritable rowKey, Result result, Context context)
// 3. Prepare output for temporary MapR-FS location
// Key: Hashed Patient ID
// Value: All non-PHI/Anonymized data that needs to be retained (e.g., VISIT_DATE)

outputKey.set(anonymizedId);
outputValue.set(visitDate);

Expand Down
4 changes: 2 additions & 2 deletions src/main/java/com/mapr/health/job2/ArchivalTagReducer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
import com.mapr.health.util.SchemaUtility;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.Text;

import java.io.IOException;
Expand All @@ -17,7 +17,7 @@ public class ArchivalTagReducer
extends TableReducer<Text, Text, ImmutableBytesWritable> {

@Override
public void reduce(Text key, Iterable<Text> values, Context context)
public void reduce(Text key, Iterable<Text> values, TableReducer<Text, Text, ImmutableBytesWritable>.Context context)
throws IOException, InterruptedException {

// The key is the final RowKey: AnonymizedID_VisitDate
Expand Down