init

12 files changed, 84 insertions, 0 deletions

diff --git a/hadoop/cacheArchive/input b/hadoop/cacheArchive/input
new file mode 100644
index 0000000..71ac1b5
--- /dev/null
+++ b/hadoop/cacheArchive/input
@@ -0,0 +1,8 @@
+a
+b
+c
+d
+e
+f
+g
+h
diff --git a/hadoop/cacheArchive/mapper.py b/hadoop/cacheArchive/mapper.py
new file mode 100644
index 0000000..a7dd9f4
--- /dev/null
+++ b/hadoop/cacheArchive/mapper.py
@@ -0,0 +1,15 @@
+#!/usr/bin/env python2
+
+import sys
+
+sys.path.append('.')
+import my_module, other_module
+from my_module import mod_a
+from my_module import mod_b
+from other_module import other
+
+for line in sys.stdin:
+  mod_a.bla(line)
+  mod_b.blubb(line)
+  other.foo(line)
+
diff --git a/hadoop/cacheArchive/my_module.zip b/hadoop/cacheArchive/my_module.zip
new file mode 100644
index 0000000..65d960b
--- /dev/null
+++ b/hadoop/cacheArchive/my_module.zip
diff --git a/hadoop/cacheArchive/my_module/__init__.py b/hadoop/cacheArchive/my_module/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/hadoop/cacheArchive/my_module/__init__.py
diff --git a/hadoop/cacheArchive/my_module/mod_a.py b/hadoop/cacheArchive/my_module/mod_a.py
new file mode 100644
index 0000000..ab65e6e
--- /dev/null
+++ b/hadoop/cacheArchive/my_module/mod_a.py
@@ -0,0 +1,3 @@
+def bla(a):
+  print a.strip()
+
diff --git a/hadoop/cacheArchive/my_module/mod_b.py b/hadoop/cacheArchive/my_module/mod_b.py
new file mode 100644
index 0000000..d684220
--- /dev/null
+++ b/hadoop/cacheArchive/my_module/mod_b.py
@@ -0,0 +1,3 @@
+def blubb(a):
+  print a.strip()
+
diff --git a/hadoop/cacheArchive/other_module.zip b/hadoop/cacheArchive/other_module.zip
new file mode 100644
index 0000000..af99f7d
--- /dev/null
+++ b/hadoop/cacheArchive/other_module.zip
diff --git a/hadoop/cacheArchive/other_module/__init__.py b/hadoop/cacheArchive/other_module/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/hadoop/cacheArchive/other_module/__init__.py
diff --git a/hadoop/cacheArchive/other_module/other.py b/hadoop/cacheArchive/other_module/other.py
new file mode 100644
index 0000000..fa55d0b
--- /dev/null
+++ b/hadoop/cacheArchive/other_module/other.py
@@ -0,0 +1,3 @@
+def foo(a):
+  print a.strip()
+
diff --git a/hadoop/cacheArchive/output/part-00000 b/hadoop/cacheArchive/output/part-00000
new file mode 100644
index 0000000..89955ae
--- /dev/null
+++ b/hadoop/cacheArchive/output/part-00000
@@ -0,0 +1,12 @@
+a	
+a	
+a	
+b	
+b	
+b	
+c	
+c	
+c	
+d	
+d	
+d	
diff --git a/hadoop/cacheArchive/output/part-00001 b/hadoop/cacheArchive/output/part-00001
new file mode 100644
index 0000000..04576d4
--- /dev/null
+++ b/hadoop/cacheArchive/output/part-00001
@@ -0,0 +1,12 @@
+e	
+e	
+e	
+f	
+f	
+f	
+g	
+g	
+g	
+h	
+h	
+h	
diff --git a/hadoop/cacheArchive/streaming.sh b/hadoop/cacheArchive/streaming.sh
new file mode 100755
index 0000000..6bc9cda
--- /dev/null
+++ b/hadoop/cacheArchive/streaming.sh
@@ -0,0 +1,28 @@
+#!/bin/sh
+
+HADOOP_HOME=/usr/lib/hadoop
+HADOOP_VERSION=0.20.2-cdh3u1
+JAR=contrib/streaming/hadoop-streaming-$HADOOP_VERSION.jar
+HSTREAMING="$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/$JAR"
+
+hadoop dfs -put input input
+hadoop dfs -put my_module.zip my_module.zip
+hadoop dfs -put other_module.zip other_module.zip
+
+IN=input
+OUT=output
+
+$HSTREAMING \
+    -input  $IN\
+    -output $OUT \
+    -mapper "python mapper.py" \
+    -reducer "NONE" \
+    -file mapper.py\
+    -cacheArchive 'hdfs:///user/simianer/my_module.zip#my_module' \
+    -cacheArchive 'hdfs:///user/simianer/other_module.zip#other_module' \
+    -jobconf mapred.reduce.tasks=30 #hier mal 30 statt 3
+
+hadoop dfs -get $OUT .
+hadoop dfs -rm $IN
+hadoop dfs -rmr $OUT
+