Add initial files for WordCount

WordCount/bin/current_version.txt

+hadoop-streaming-2.6.3.jar as hadoop-streaming.jar

WordCount/map.py

+#!/usr/bin/env python2.7
+
+import sys
+
+# input comes from STDIN (standard input)
+for line in sys.stdin:
+    # remove leading and trailing whitespace
+    line = line.strip()
+    # split the line into words
+    words = line.split()
+    # increase counters
+    for word in words:
+        # write the results to STDOUT (standard output);
+        # what we output here will be the input for the
+        # Reduce step, i.e. the input for reducer.py
+        #
+        # tab-delimited; the trivial word count is 1
+        print '%s\t%s' % (word, 1)
+

WordCount/red.py

+#!/usr/bin/env python2.7
+
+from operator import itemgetter
+import sys
+
+current_word = None
+current_count = 0
+word = None
+
+# input comes from STDIN
+for line in sys.stdin:
+    # remove leading and trailing whitespace
+    line = line.strip()
+
+    # parse the input we got from mapper.py
+    word, count = line.split('\t', 1)
+
+    # convert count (currently a string) to int
+    try:
+        count = int(count)
+    except ValueError:
+        # count was not a number, so silently
+        # ignore/discard this line
+        continue
+
+    # this IF-switch only works because Hadoop sorts map output
+    # by key (here: word) before it is passed to the reducer
+    if current_word == word:
+        current_count += count
+    else:
+        if current_word:
+            # write result to STDOUT
+            print '%s\t%s' % (current_word, current_count)
+        current_count = count
+        current_word = word
+
+# do not forget to output the last word if needed!
+if current_word == word:
+    print '%s\t%s' % (current_word, current_count)

WordCount/run_wordcount.sh

+#!/bin/bash
+

WordCount/switch_streaming_jar.sh

+#!/bin/bash
+
+dirname="$(dirname "$0")"
+
+if ! [ -z $1 ]; then
+    jarname="hadoop-streaming-$1.jar"
+    echo "Switch to $jarname; copying $dirname/bin/$jarname to $dirname/hadoop-streaming.jar"
+    cp $dirname/bin/$jarname $dirname/hadoop-streaming.jar
+    echo "$jarname as hadoop-streaming.jar" > $dirname/bin/current_version.txt
+else
+    if [ -f $dirname/bin/current_version.txt ]; then
+        cat $dirname/bin/current_version.txt
+    fi
+    echo "Usage: $0 <jar-version>"
+    echo "  e.g. $0 2.6.3"
+    echo "Choices:"
+    ls $dirname/bin/*.jar
+fi
\ No newline at end of file