From 658a087c648e7b40eee90fb4f96eebf0a22fd675 Mon Sep 17 00:00:00 2001
From: Kshitij <notkshitij@git.kska.io>
Date: Sun, 12 Oct 2025 23:38:15 +0530
Subject: [PATCH] Added code for hadoop.

---
 Codes/Code-1.4/CharacterCountDriver.java  | 31 ++++++++++
 Codes/Code-1.4/CharacterCountMapper.java  | 21 +++++++
 Codes/Code-1.4/CharacterCountReducer.java | 19 ++++++
 Codes/Code-1.4/Commands.md                | 74 +++++++++++++++++++++++
 4 files changed, 145 insertions(+)
 create mode 100644 Codes/Code-1.4/CharacterCountDriver.java
 create mode 100644 Codes/Code-1.4/CharacterCountMapper.java
 create mode 100644 Codes/Code-1.4/CharacterCountReducer.java
 create mode 100644 Codes/Code-1.4/Commands.md

diff --git a/Codes/Code-1.4/CharacterCountDriver.java b/Codes/Code-1.4/CharacterCountDriver.java
new file mode 100644
index 0000000..1598773
--- /dev/null
+++ b/Codes/Code-1.4/CharacterCountDriver.java
@@ -0,0 +1,31 @@
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+
+public class CharacterCountDriver {
+    public static void main(String[] args) throws Exception {
+        if (args.length != 2) {
+            System.err.println("Usage: CharacterCountDriver <input path> <output path>");
+            System.exit(-1);
+        }
+
+        Configuration conf = new Configuration();
+        Job job = Job.getInstance(conf, "Character Count");
+        job.setJarByClass(CharacterCountDriver.class);
+        job.setMapperClass(CharacterCountMapper.class);
+        job.setCombinerClass(CharacterCountReducer.class);
+        job.setReducerClass(CharacterCountReducer.class);
+        job.setOutputKeyClass(Text.class);
+        job.setOutputValueClass(IntWritable.class);
+        
+        FileInputFormat.addInputPath(job, new Path(args[0]));
+        FileOutputFormat.setOutputPath(job, new Path(args[1]));
+
+        System.exit(job.waitForCompletion(true) ? 0 : 1);
+    }
+}
+
diff --git a/Codes/Code-1.4/CharacterCountMapper.java b/Codes/Code-1.4/CharacterCountMapper.java
new file mode 100644
index 0000000..05bf850
--- /dev/null
+++ b/Codes/Code-1.4/CharacterCountMapper.java
@@ -0,0 +1,21 @@
+import java.io.IOException;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Mapper;
+
+public class CharacterCountMapper extends Mapper<Object, Text, Text, IntWritable> {
+    private final static IntWritable one = new IntWritable(1);
+    private Text character = new Text();
+
+    @Override
+    protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
+        String line = value.toString().toLowerCase();
+        for (char c : line.toCharArray()) {
+            if (Character.isAlphabetic(c)) {
+                character.set(String.valueOf(c));
+                context.write(character, one);
+            }
+        }
+    }
+}
+
diff --git a/Codes/Code-1.4/CharacterCountReducer.java b/Codes/Code-1.4/CharacterCountReducer.java
new file mode 100644
index 0000000..3bccfc3
--- /dev/null
+++ b/Codes/Code-1.4/CharacterCountReducer.java
@@ -0,0 +1,19 @@
+import java.io.IOException;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Reducer;
+
+public class CharacterCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
+    private IntWritable result = new IntWritable();
+
+    @Override
+    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
+        int count = 0;
+        for (IntWritable val : values) {
+            count += val.get();
+        }
+        result.set(count);
+        context.write(key, result);
+    }
+}
+
diff --git a/Codes/Code-1.4/Commands.md b/Codes/Code-1.4/Commands.md
new file mode 100644
index 0000000..6d69b88
--- /dev/null
+++ b/Codes/Code-1.4/Commands.md
@@ -0,0 +1,74 @@
+### List of Commands
+
+1. **Create a Directory for Your Project**:
+
+   ```bash
+   mkdir ~/hadoop_char_count
+   cd ~/hadoop_char_count
+   ```
+
+2. **Compile the Java Files**:
+
+   ```bash
+   javac -classpath $(hadoop classpath) -d . CharacterCountMapper.java CharacterCountReducer.java CharacterCountDriver.java
+   ```
+
+3. **Create the JAR File**:
+
+   ```bash
+   jar cvf CharacterCount.jar *.class
+   ```
+
+4. **Create Input Directory in HDFS** (if needed):
+
+   ```bash
+   hdfs dfs -mkdir -p /user/hduser/input
+   ```
+
+5. **Upload Input File to HDFS**:
+
+   ```bash
+   hdfs dfs -put /path/to/your/local/input.txt /user/hduser/input/
+   ```
+
+6. **Run the MapReduce Job**:
+
+   ```bash
+   hadoop jar CharacterCount.jar CharacterCountDriver /user/hduser/input /user/hduser/output
+   ```
+
+7. **Remove Existing Output Directory** (if needed):
+
+   ```bash
+   hdfs dfs -rm -r /user/hduser/output
+   ```
+
+8. **List Contents of the Output Directory**:
+
+   ```bash
+   hdfs dfs -ls /user/hduser/output
+   ```
+
+9. **View the Output File**:
+
+   ```bash
+   hdfs dfs -cat /user/hduser/output/part-r-00000
+   ```
+
+10. **View Output with `more` or `less`**:
+
+    ```bash
+    hdfs dfs -cat /user/hduser/output/part-r-00000 | more
+    ```
+    or
+    ```bash
+    hdfs dfs -cat /user/hduser/output/part-r-00000 | less
+    ```
+
+11. **Copy Output to Local File System (Optional)**:
+
+    ```bash
+    hdfs dfs -get /user/hduser/output/part-r-00000 /path/to/local/directory/
+    ```
+
+---