Update more ch07 examples to use new API.

rasay · Sep 28, 2011 · 877a834 · 877a834
1 parent 1f4b02c
commit 877a834
Show file tree

Hide file tree

Showing 5 changed files with 13 additions and 8 deletions.
diff --git a/ch07/src/main/java/MinimalMapReduceWithDefaults.java b/ch07/src/main/java/MinimalMapReduceWithDefaults.java
@@ -21,24 +21,22 @@ public int run(String[] args) throws Exception {
       return -1;
     }
 
-    /*[*/job.setInputFormatClass(TextInputFormat.class); // cf setInputFormat
+    /*[*/job.setInputFormatClass(TextInputFormat.class);
 
-    // job.setNumMapTasks(1); cf not in new API
-    job.setMapperClass(Mapper.class); // Mapper is abstract and the identity
-    //job.setMapRunnerClass(MapRunner.class); // Override Mapper to control flow
+    job.setMapperClass(Mapper.class);
 
     job.setMapOutputKeyClass(LongWritable.class);
     job.setMapOutputValueClass(Text.class);
 
     job.setPartitionerClass(HashPartitioner.class);
 
     job.setNumReduceTasks(1);
-    job.setReducerClass(Reducer.class); // identity
+    job.setReducerClass(Reducer.class);
 
     job.setOutputKeyClass(LongWritable.class);
     job.setOutputValueClass(Text.class);
 
-    job.setOutputFormatClass(TextOutputFormat.class);/*]*/ // cf setOutputFormat
+    job.setOutputFormatClass(TextOutputFormat.class);/*]*/
 
     return job.waitForCompletion(true) ? 0 : 1;
   }

diff --git a/ch07/src/main/java/NonSplittableTextInputFormat.java b/ch07/src/main/java/NonSplittableTextInputFormat.java
@@ -1,10 +1,11 @@
+// == NonSplittableTextInputFormat
 import org.apache.hadoop.fs.Path;
 import org.apache.hadoop.mapreduce.JobContext;
 import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
 
 public class NonSplittableTextInputFormat extends TextInputFormat {
   @Override
-  protected boolean isSplitable(JobContext context, Path file) {;
+  protected boolean isSplitable(JobContext context, Path file) {
     return false;
   }
 }
diff --git a/snippet/bin/check_manuscript.py b/snippet/bin/check_manuscript.py
@@ -3,6 +3,8 @@
 # Check that the expected (or actual) snippets are in the manuscript. E.g.
 # bin/check_manuscript.py  ~/workspace/htdg2/ch11.xml expected/ch11/grunt/*
 
+# TODO: ignore id elements in the XML in the book.
+# Need to use an XML parser for this.
 import sys
 
 manuscript = open(sys.argv[1], 'r').read()

diff --git a/snippet/bin/check_manuscript.sh b/snippet/bin/check_manuscript.sh
@@ -7,4 +7,6 @@ actual="$bin"/../actual
 
 $bin/check_manuscript.py  ~/workspace/htdg3/ch02.xml $actual/ch02/*
 $bin/check_manuscript.py  ~/workspace/htdg3/ch04.xml $actual/ch04/*
-$bin/check_manuscript.py  ~/workspace/htdg3/ch05.xml $actual/ch05/*
+$bin/check_manuscript.py  ~/workspace/htdg3/ch05.xml $actual/ch05/*
+$bin/check_manuscript.py  ~/workspace/htdg3/ch07.xml $actual/ch07/*
+$bin/check_manuscript.py  ~/workspace/htdg3/ch07.xml $actual/common/*
diff --git a/snippet/bin/generate_listings.sh b/snippet/bin/generate_listings.sh
@@ -9,3 +9,5 @@ actual="$bin"/../actual
 perl $bin/phragmite_db.pl $actual/ch02/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch02)
 perl $bin/phragmite_db.pl $actual/ch04/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch04)
 perl $bin/phragmite_db.pl $actual/ch05/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch05)
+perl $bin/phragmite_db.pl $actual/ch07/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch07)
+perl $bin/phragmite_db.pl $actual/common/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../common)