Rename ch02 to ch02-mr-intro.

trahasch · Sep 18, 2014 · 0c3d3fc · 0c3d3fc
1 parent 8710b56
commit 0c3d3fc
Show file tree

Hide file tree

Showing 50 changed files with 49 additions and 69 deletions.
diff --git a/README b/README
@@ -44,25 +44,5 @@ Again, you can specify hadoop.version to use a particular Hadoop 2 version:
 
 You should then be able to run the examples from the book.
 
-Chapter names for "Hadoop: The Definitive Guide", Third Edition
-
-ch01 - Meet Hadoop
-ch02 - MapReduce
-ch03 - The Hadoop Distributed Filesystem
-ch04 - Hadoop I/O
-ch05 - Developing a MapReduce Application
-ch06 - How MapReduce Works
-ch07 - MapReduce Types and Formats
-ch08 - MapReduce Features
-ch09 - Setting Up a Hadoop Cluster
-ch10 - Administering Hadoop
-ch11 - Pig
-ch12 - Hive
-ch13 - HBase
-ch14 - ZooKeeper
-ch15 - Sqoop
-ch16 - Case Studies
-
-app1 - Installing Apache Hadoop
-app2 - Cloudera's Distribution for Hadoop
-app3 - Preparing the NCDC Weather Data
+For chapter names for "Hadoop: The Definitive Guide", see
+https://github.com/tomwhite/hadoop-book/wiki/Chapter-Numbers-By-Edition
diff --git a/ch02/pom.xml → ch02-mr-intro/pom.xml b/ch02/pom.xml → ch02-mr-intro/pom.xml
@@ -8,7 +8,7 @@
     <relativePath>../hadoop-meta/pom.xml</relativePath>
   </parent>
   <groupId>com.hadoopbook</groupId>
-  <artifactId>ch02</artifactId>
+  <artifactId>ch02-mr-intro</artifactId>
   <packaging>jar</packaging>
   <version>3.0</version>
   <name>Chapter 2: MapReduce</name>

diff --git a/ch02/src/main/awk/max_temperature.sh → ...-mr-intro/src/main/awk/max_temperature.sh b/ch02/src/main/awk/max_temperature.sh → ...-mr-intro/src/main/awk/max_temperature.sh
diff --git a/ch02/src/main/cpp/Makefile → ch02-mr-intro/src/main/cpp/Makefile b/ch02/src/main/cpp/Makefile → ch02-mr-intro/src/main/cpp/Makefile
diff --git a/ch02/src/main/cpp/max_temperature.cpp → ...mr-intro/src/main/cpp/max_temperature.cpp b/ch02/src/main/cpp/max_temperature.cpp → ...mr-intro/src/main/cpp/max_temperature.cpp
diff --git a/...rc/main/examples/MaxTemperature/input.txt → ...rc/main/examples/MaxTemperature/input.txt b/...rc/main/examples/MaxTemperature/input.txt → ...rc/main/examples/MaxTemperature/input.txt
diff --git a/...amples/MaxTemperature/output/part-r-00000 → ...amples/MaxTemperature/output/part-r-00000 b/...amples/MaxTemperature/output/part-r-00000 → ...amples/MaxTemperature/output/part-r-00000
diff --git a/...ples/MaxTemperatureWithCombiner/input.txt → ...ples/MaxTemperatureWithCombiner/input.txt b/...ples/MaxTemperatureWithCombiner/input.txt → ...ples/MaxTemperatureWithCombiner/input.txt
diff --git a/...mperatureWithCombiner/output/part-r-00000 → ...mperatureWithCombiner/output/part-r-00000 b/...mperatureWithCombiner/output/part-r-00000 → ...mperatureWithCombiner/output/part-r-00000
diff --git a/...main/examples/OldMaxTemperature/input.txt → ...main/examples/OldMaxTemperature/input.txt b/...main/examples/OldMaxTemperature/input.txt → ...main/examples/OldMaxTemperature/input.txt
diff --git a/...mples/OldMaxTemperature/output/part-00000 → ...mples/OldMaxTemperature/output/part-00000 b/...mples/OldMaxTemperature/output/part-00000 → ...mples/OldMaxTemperature/output/part-00000
diff --git a/...in/examples/max_temperature.cpp.input.txt → ...in/examples/max_temperature.cpp.input.txt b/...in/examples/max_temperature.cpp.input.txt → ...in/examples/max_temperature.cpp.input.txt
diff --git a/ch02-mr-intro/src/main/examples/max_temperature_hadoop.input.txt b/ch02-mr-intro/src/main/examples/max_temperature_hadoop.input.txt
@@ -0,0 +1,5 @@
+hadoop jar $HADOOP_HOME/share/hadoop/tools/lib/hadoop-streaming-*.jar \
+  -input input/ncdc/sample.txt \
+  -output output \
+  -mapper ch02-mr-intro/src/main/ruby/max_temperature_map.rb \
+  -reducer ch02-mr-intro/src/main/ruby/max_temperature_reduce.rb
diff --git a/ch02-mr-intro/src/main/examples/max_temperature_hadoop_cluster.input.txt b/ch02-mr-intro/src/main/examples/max_temperature_hadoop_cluster.input.txt
@@ -0,0 +1,8 @@
+hadoop jar $HADOOP_HOME/share/hadoop/tools/lib/hadoop-streaming-*.jar \
+  -files ch02-mr-intro/src/main/ruby/max_temperature_map.rb,\
+ch02-mr-intro/src/main/ruby/max_temperature_reduce.rb \
+  -input input/ncdc/all \
+  -output output \
+  -mapper ch02-mr-intro/src/main/ruby/max_temperature_map.rb \
+  -combiner ch02-mr-intro/src/main/ruby/max_temperature_reduce.rb \
+  -reducer ch02-mr-intro/src/main/ruby/max_temperature_reduce.rb
diff --git a/ch02-mr-intro/src/main/examples/max_temperature_py/2/input.txt b/ch02-mr-intro/src/main/examples/max_temperature_py/2/input.txt
@@ -0,0 +1,5 @@
+hadoop jar $HADOOP_HOME/share/hadoop/tools/lib/hadoop-streaming-*.jar \
+  -input input/ncdc/sample.txt \
+  -output output \
+  -mapper ch02-mr-intro/src/main/python/max_temperature_map.py \
+  -reducer ch02-mr-intro/src/main/python/max_temperature_reduce.py
diff --git a/...es/max_temperature_py/2/output/part-00000 → ...es/max_temperature_py/2/output/part-00000 b/...es/max_temperature_py/2/output/part-00000 → ...es/max_temperature_py/2/output/part-00000
diff --git a/ch02-mr-intro/src/main/examples/max_temperature_py/input.txt b/ch02-mr-intro/src/main/examples/max_temperature_py/input.txt
@@ -0,0 +1,5 @@
+hadoop jar $HADOOP_HOME/share/hadoop/tools/lib/hadoop-streaming-*.jar \
+  -input input/ncdc/sample.txt \
+  -output output \
+  -mapper ch02-mr-intro/src/main/python/max_temperature_map.py \
+  -reducer ch02-mr-intro/src/main/python/max_temperature_reduce.py
diff --git a/...es/max_temperature_py/output/part-r-00000 → ...es/max_temperature_py/output/part-r-00000 b/...es/max_temperature_py/output/part-r-00000 → ...es/max_temperature_py/output/part-r-00000
diff --git a/ch02-mr-intro/src/main/examples/max_temperature_py/pseudo/input.txt b/ch02-mr-intro/src/main/examples/max_temperature_py/pseudo/input.txt
@@ -0,0 +1,7 @@
+hadoop jar $HADOOP_HOME/share/hadoop/tools/lib/hadoop-streaming-*.jar \
+  -files ch02-mr-intro/src/main/python/max_temperature_map.py,\
+ch02-mr-intro/src/main/python/max_temperature_reduce.py \
+  -input input/ncdc/sample.txt \
+  -output output \
+  -mapper ch02-mr-intro/src/main/python/max_temperature_map.py \
+  -reducer ch02-mr-intro/src/main/python/max_temperature_reduce.py
diff --git a/...x_temperature_py/pseudo/output/part-00000 → ...x_temperature_py/pseudo/output/part-00000 b/...x_temperature_py/pseudo/output/part-00000 → ...x_temperature_py/pseudo/output/part-00000
diff --git a/ch02/src/main/java/MaxTemperature.java → ...r-intro/src/main/java/MaxTemperature.java b/ch02/src/main/java/MaxTemperature.java → ...r-intro/src/main/java/MaxTemperature.java
diff --git a/ch02/src/main/java/MaxTemperatureMapper.java → ...o/src/main/java/MaxTemperatureMapper.java b/ch02/src/main/java/MaxTemperatureMapper.java → ...o/src/main/java/MaxTemperatureMapper.java
diff --git a/.../src/main/java/MaxTemperatureReducer.java → .../src/main/java/MaxTemperatureReducer.java b/.../src/main/java/MaxTemperatureReducer.java → .../src/main/java/MaxTemperatureReducer.java
diff --git a/...main/java/MaxTemperatureWithCombiner.java → ...main/java/MaxTemperatureWithCombiner.java b/...main/java/MaxTemperatureWithCombiner.java → ...main/java/MaxTemperatureWithCombiner.java
diff --git a/ch02/src/main/java/OldMaxTemperature.java → ...ntro/src/main/java/OldMaxTemperature.java b/ch02/src/main/java/OldMaxTemperature.java → ...ntro/src/main/java/OldMaxTemperature.java
diff --git a/.../src/main/java/oldapi/MaxTemperature.java → .../src/main/java/oldapi/MaxTemperature.java b/.../src/main/java/oldapi/MaxTemperature.java → .../src/main/java/oldapi/MaxTemperature.java
diff --git a/...ain/java/oldapi/MaxTemperatureMapper.java → ...ain/java/oldapi/MaxTemperatureMapper.java b/...ain/java/oldapi/MaxTemperatureMapper.java → ...ain/java/oldapi/MaxTemperatureMapper.java
diff --git a/...in/java/oldapi/MaxTemperatureReducer.java → ...in/java/oldapi/MaxTemperatureReducer.java b/...in/java/oldapi/MaxTemperatureReducer.java → ...in/java/oldapi/MaxTemperatureReducer.java
diff --git a/...va/oldapi/MaxTemperatureWithCombiner.java → ...va/oldapi/MaxTemperatureWithCombiner.java b/...va/oldapi/MaxTemperatureWithCombiner.java → ...va/oldapi/MaxTemperatureWithCombiner.java
diff --git a/ch02/src/main/python/max_temperature_map.py → ...ro/src/main/python/max_temperature_map.py b/ch02/src/main/python/max_temperature_map.py → ...ro/src/main/python/max_temperature_map.py
diff --git a/...src/main/python/max_temperature_reduce.py → ...src/main/python/max_temperature_reduce.py b/...src/main/python/max_temperature_reduce.py → ...src/main/python/max_temperature_reduce.py
diff --git a/ch02/src/main/ruby/max_temperature_map.rb → ...ntro/src/main/ruby/max_temperature_map.rb b/ch02/src/main/ruby/max_temperature_map.rb → ...ntro/src/main/ruby/max_temperature_map.rb
diff --git a/ch02/src/main/ruby/max_temperature_reduce.rb → ...o/src/main/ruby/max_temperature_reduce.rb b/ch02/src/main/ruby/max_temperature_reduce.rb → ...o/src/main/ruby/max_temperature_reduce.rb
diff --git a/ch02/src/main/sh/max_temp.sh → ch02-mr-intro/src/main/sh/max_temp.sh b/ch02/src/main/sh/max_temp.sh → ch02-mr-intro/src/main/sh/max_temp.sh
@@ -12,14 +12,14 @@ hadoop MaxTemperature input/ncdc/sample.txt output
 cat output/part-00000
 : ^^ max_temp_java_output
 : vv max_temp_ruby_map
-cat input/ncdc/sample.txt | ch02/src/main/ruby/max_temperature_map.rb
+cat input/ncdc/sample.txt | ch02-mr-intro/src/main/ruby/max_temperature_map.rb
 : ^^ max_temp_ruby_map
 : vv max_temp_ruby_pipeline
-cat input/ncdc/sample.txt | ch02/src/main/ruby/max_temperature_map.rb | \
-  sort | ch02/src/main/ruby/max_temperature_reduce.rb
+cat input/ncdc/sample.txt | ch02-mr-intro/src/main/ruby/max_temperature_map.rb | \
+  sort | ch02-mr-intro/src/main/ruby/max_temperature_reduce.rb
 : ^^ max_temp_ruby_pipeline
 : vv max_temp_python_pipeline
-cat input/ncdc/sample.txt | ch02/src/main/python/max_temperature_map.py | \
-  sort | ch02/src/main/python/max_temperature_reduce.py
+cat input/ncdc/sample.txt | ch02-mr-intro/src/main/python/max_temperature_map.py | \
+  sort | ch02-mr-intro/src/main/python/max_temperature_reduce.py
 : ^^ max_temp_python_pipeline
 
diff --git a/ch02/src/main/examples/max_temperature_hadoop.input.txt b/ch02/src/main/examples/max_temperature_hadoop.input.txt
diff --git a/ch02/src/main/examples/max_temperature_hadoop_cluster.input.txt b/ch02/src/main/examples/max_temperature_hadoop_cluster.input.txt
diff --git a/ch02/src/main/examples/max_temperature_py/2/input.txt b/ch02/src/main/examples/max_temperature_py/2/input.txt
diff --git a/ch02/src/main/examples/max_temperature_py/input.txt b/ch02/src/main/examples/max_temperature_py/input.txt
diff --git a/ch02/src/main/examples/max_temperature_py/pseudo/input.txt b/ch02/src/main/examples/max_temperature_py/pseudo/input.txt
diff --git a/ch04/pom.xml b/ch04/pom.xml
@@ -15,7 +15,7 @@
   <dependencies>
     <dependency>
       <groupId>com.hadoopbook</groupId>
-      <artifactId>ch02</artifactId>
+      <artifactId>ch02-mr-intro</artifactId>
       <version>3.0</version>
     </dependency>
     <dependency>

diff --git a/ch07/pom.xml b/ch07/pom.xml
@@ -20,7 +20,7 @@
     </dependency>
     <dependency>
       <groupId>com.hadoopbook</groupId>
-      <artifactId>ch02</artifactId>
+      <artifactId>ch02-mr-intro</artifactId>
       <version>3.0</version>
     </dependency>
     <dependency>

diff --git a/ch08/pom.xml b/ch08/pom.xml
@@ -20,7 +20,7 @@
     </dependency>
     <dependency>
       <groupId>com.hadoopbook</groupId>
-      <artifactId>ch02</artifactId>
+      <artifactId>ch02-mr-intro</artifactId>
       <version>3.0</version>
     </dependency>
     <dependency>

diff --git a/ch18-crunch/src/main/java/crunch/MaxTemperatureCrunch.java b/ch18-crunch/src/main/java/crunch/MaxTemperatureCrunch.java
@@ -16,7 +16,7 @@
 import org.apache.crunch.impl.mr.MRPipeline;
 import org.apache.crunch.io.To;
 
-// Crunch version of ch02 MaxTemperature
+// Crunch version of ch02-mr-intro MaxTemperature
 public class MaxTemperatureCrunch {
 
   public static void main(String[] args) throws Exception {

diff --git a/ch18-crunch/src/main/java/crunch/MaxTemperatureCrunchWithShutdownHook.java b/ch18-crunch/src/main/java/crunch/MaxTemperatureCrunchWithShutdownHook.java
@@ -14,7 +14,7 @@
 import static org.apache.crunch.types.writable.Writables.strings;
 import static org.apache.crunch.types.writable.Writables.tableOf;
 
-// Crunch version of ch02 MaxTemperature
+// Crunch version of ch02-mr-intro MaxTemperature
 public class MaxTemperatureCrunchWithShutdownHook {
 
   public static void main(String[] args) throws Exception {

diff --git a/hadoop-examples/pom.xml b/hadoop-examples/pom.xml
@@ -21,7 +21,7 @@
     </dependency>
     <dependency>
       <groupId>com.hadoopbook</groupId>
-      <artifactId>ch02</artifactId>
+      <artifactId>ch02-mr-intro</artifactId>
       <version>3.0</version>
     </dependency>
     <dependency>

diff --git a/pom.xml b/pom.xml
@@ -11,7 +11,7 @@
   <modules>
     <module>book</module>
     <module>common</module>
-    <module>ch02</module>
+    <module>ch02-mr-intro</module>
     <module>ch03</module>
     <module>ch04</module>
     <module>ch06-avro</module>

diff --git a/snippet/README b/snippet/README
@@ -17,4 +17,4 @@ mvn verify
 mvn verify -DargLine="-Dexample.mode=pseudo"
 
 # Run the examples from chapter 2 only
-mvn verify -DargLine="-Dexample.chapters=ch02"
+mvn verify -DargLine="-Dexample.chapters=ch02-mr-intro"
diff --git a/snippet/bin/check_manuscript.sh b/snippet/bin/check_manuscript.sh
@@ -7,7 +7,7 @@ actual="$bin"/../actual
 book_workspace=~/book-workspace/htdg-git
 
 # Should add remaining chapters: ch03 ch04 ch14
-for ch in ch02 ch03 ch05 ch07 ch08 # ch11 ch12
+for ch in ch02-mr-intro ch03 ch05 ch07 ch08 # ch11 ch12
 do
   # remove id attributes from program listings, and add a newline before </programlisting>
   sed '/<programlisting/s/ id="[^"]*"//; s|</programlisting>|\

diff --git a/snippet/bin/generate_listings.sh b/snippet/bin/generate_listings.sh
@@ -6,7 +6,7 @@ bin=`cd "$bin"; pwd`
 
 actual="$bin"/../actual
 
-perl $bin/phragmite_db.pl $actual/ch02/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch02)
+perl $bin/phragmite_db.pl $actual/ch02-mr-intro/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch02-mr-intro)
 perl $bin/phragmite_db.pl $actual/ch03/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch03)
 perl $bin/phragmite_db.pl $actual/ch04/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch04)
 perl $bin/phragmite_db.pl $actual/ch06-avro/ $(grep -ElR '(// ?cc|// ?==)' --include '*.java' $bin/../../ch06-avro)

diff --git a/snippet/src/test/java/ExamplesIT.java b/snippet/src/test/java/ExamplesIT.java
@@ -58,7 +58,7 @@ public class ExamplesIT {
   private static final String MODE_DEFAULT = "local";
 
   private static final String EXAMPLE_CHAPTERS_PROPERTY = "example.chapters";
-  private static final String EXAMPLE_CHAPTERS_DEFAULT = "ch02,ch04,ch06-avro,ch05,ch07,ch08";
+  private static final String EXAMPLE_CHAPTERS_DEFAULT = "ch02-mr-intro,ch04,ch06-avro,ch05,ch07,ch08";
 
   private static final IOFileFilter HIDDEN_FILE_FILTER =
     new OrFileFilter(HiddenFileFilter.HIDDEN, new PrefixFileFilter("_"));