Simplify and consolidate examples in Developing an MR App chapter.

ch05/src/main/java/v2/MaxTemperatureDriver.java

@@ -10,7 +10,6 @@
 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 import org.apache.hadoop.util.Tool;
 import org.apache.hadoop.util.ToolRunner;
-
 import v1.MaxTemperatureReducer;
 
 // vv MaxTemperatureDriverV2

ch05/src/main/java/v2/MaxTemperatureMapper.java

@@ -1,32 +1,29 @@
 package v2;
-//== MaxTemperatureMapperV2
+// cc MaxTemperatureMapperV2 A Mapper that uses a utility class to parse records
 
 import java.io.IOException;
 
 import org.apache.hadoop.io.IntWritable;
 import org.apache.hadoop.io.LongWritable;
 import org.apache.hadoop.io.Text;
 import org.apache.hadoop.mapreduce.Mapper;
+import v2.NcdcRecordParser;
 
+// vv MaxTemperatureMapperV2
 public class MaxTemperatureMapper
-  extends Mapper<LongWritable, Text, Text, IntWritable> {
-
-//vv MaxTemperatureMapperV2
+    extends Mapper<LongWritable, Text, Text, IntWritable> {
+
+  /*[*/private NcdcRecordParser parser = new NcdcRecordParser();/*]*/
+
   @Override
   public void map(LongWritable key, Text value, Context context)
       throws IOException, InterruptedException {
-
-    String line = value.toString();
-    String year = line.substring(15, 19);
-    /*[*/String temp = line.substring(87, 92);
-    if (!missing(temp)) {/*]*/
-        int airTemperature = Integer.parseInt(temp);
-        context.write(new Text(year), new IntWritable(airTemperature));
-    /*[*/}/*]*/
+
+    /*[*/parser.parse(value);/*]*/
+    if (/*[*/parser.isValidTemperature()/*]*/) {
+      context.write(new Text(/*[*/parser.getYear()/*]*/),
+          new IntWritable(/*[*/parser.getAirTemperature()/*]*/));
+    }
   }
-
-  /*[*/private boolean missing(String temp) {
-    return temp.equals("+9999");
-  }/*]*/
-//^^ MaxTemperatureMapperV2
 }
+// ^^ MaxTemperatureMapperV2

ch05/src/main/java/v3/NcdcRecordParser.java → ch05/src/main/java/v2/NcdcRecordParser.java

@@ -1,8 +1,8 @@
-// cc NcdcRecordParserV3 A class for parsing weather records in NCDC format
-package v3;
+// cc NcdcRecordParserV2 A class for parsing weather records in NCDC format
+package v2;
 import org.apache.hadoop.io.Text;
 
-// vv NcdcRecordParserV3
+// vv NcdcRecordParserV2
 public class NcdcRecordParser {
 
   private static final int MISSING_TEMPERATURE = 9999;
@@ -40,4 +40,4 @@ public int getAirTemperature() {
     return airTemperature;
   }
 }
-// ^^ NcdcRecordParserV3
+// ^^ NcdcRecordParserV2

ch05/src/main/java/v3/MaxTemperatureDriver.java

@@ -12,7 +12,7 @@
 
 import v1.MaxTemperatureReducer;
 
-// Identical to v2 except for v3 mapper
+//Identical to v2 except for v3 mapper
 public class MaxTemperatureDriver extends Configured implements Tool {
 
   @Override

ch05/src/main/java/v3/MaxTemperatureMapper.java

@@ -1,5 +1,5 @@
+// == MaxTemperatureMapperV3
 package v3;
-// cc MaxTemperatureMapperV3 A Mapper that uses a utility class to parse records
 
 import java.io.IOException;
 
@@ -8,21 +8,33 @@
 import org.apache.hadoop.io.Text;
 import org.apache.hadoop.mapreduce.Mapper;
 
-// vv MaxTemperatureMapperV3
+import v2.NcdcRecordParser;
+
+//vv MaxTemperatureMapperV3
 public class MaxTemperatureMapper
   extends Mapper<LongWritable, Text, Text, IntWritable> {
+
+  /*[*/enum Temperature {
+    OVER_100
+  }/*]*/
 
-  /*[*/private NcdcRecordParser parser = new NcdcRecordParser();/*]*/
-  
+  private NcdcRecordParser parser = new NcdcRecordParser();
+
   @Override
   public void map(LongWritable key, Text value, Context context)
       throws IOException, InterruptedException {
 
-    /*[*/parser.parse(value);/*]*/
-    if (/*[*/parser.isValidTemperature()/*]*/) {
-      context.write(new Text(/*[*/parser.getYear()/*]*/),
-          new IntWritable(/*[*/parser.getAirTemperature()/*]*/));
+    parser.parse(value);
+    if (parser.isValidTemperature()) {
+      int airTemperature = parser.getAirTemperature();
+      /*[*/if (airTemperature > 1000) {
+        System.err.println("Temperature over 100 degrees for input: " + value);
+        context.setStatus("Detected possibly corrupt record: see logs.");
+        context.getCounter(Temperature.OVER_100).increment(1);
+      }/*]*/
+      context.write(new Text(parser.getYear()), new IntWritable(airTemperature));
     }
   }
 }
-// ^^ MaxTemperatureMapperV3
+//^^ MaxTemperatureMapperV3
+

ch05/src/main/java/v4/MaxTemperatureMapper.java

@@ -1,40 +1,34 @@
-// == MaxTemperatureMapperV4
 package v4;
-
+// cc MaxTemperatureMapperV4 Mapper for maximum temperature example
 import java.io.IOException;
 
 import org.apache.hadoop.io.IntWritable;
 import org.apache.hadoop.io.LongWritable;
 import org.apache.hadoop.io.Text;
 import org.apache.hadoop.mapreduce.Mapper;
 
-import v3.NcdcRecordParser;
-
-//vv MaxTemperatureMapperV4
+// vv MaxTemperatureMapperV4
 public class MaxTemperatureMapper
   extends Mapper<LongWritable, Text, Text, IntWritable> {
-
-  /*[*/enum Temperature {
-    OVER_100
-  }/*]*/
 
-  private NcdcRecordParser parser = new NcdcRecordParser();
+  enum Temperature {
+    MALFORMED
+  }
 
+  private NcdcRecordParser parser = new NcdcRecordParser();
+
   @Override
   public void map(LongWritable key, Text value, Context context)
       throws IOException, InterruptedException {
 
     parser.parse(value);
     if (parser.isValidTemperature()) {
       int airTemperature = parser.getAirTemperature();
-      /*[*/if (airTemperature > 1000) {
-        System.err.println("Temperature over 100 degrees for input: " + value);
-        context.setStatus("Detected possibly corrupt record: see logs.");
-        context.getCounter(Temperature.OVER_100).increment(1);
-      }/*]*/
       context.write(new Text(parser.getYear()), new IntWritable(airTemperature));
+    } else if (parser.isMalformedTemperature()) {
+      System.err.println("Ignoring possibly corrupt input: " + value);
+      context.getCounter(Temperature.MALFORMED).increment(1);
     }
   }
 }
-//^^ MaxTemperatureMapperV4
-
+// ^^ MaxTemperatureMapperV4

ch05/src/main/java/v5/NcdcRecordParser.java → ch05/src/main/java/v4/NcdcRecordParser.java

@@ -1,4 +1,4 @@
-package v5;
+package v4;
 import org.apache.hadoop.io.Text;
 
 public class NcdcRecordParser {