ruby 
#!/usr/bin/env ruby 
STDIN.each_line do |line| 
val = line 
year, temp, q = val[15,4], val[87,5], val[92,1] 
puts "#{year}t#{temp}" if (temp != "+9999" && q =~ /[01459]/) 
end 

ruby 
#!/usr/bin/env ruby 
last_key, max_val = nil, -1000000 
STDIN.each_line do |line| 
key, val = line.split("t") 
if last_key && last_key != key 
puts "#{last_key}t#{max_val}" 
last_key, max_val = key, val.to_i 
else 
last_key, max_val = key, [max_val, val.to_i].max 
end 
end 
puts "#{last_key}t#{max_val}" if last_key 

% hadoop jar $HADOOP_INSTALL/contrib/streaming/hadoop-*-streaming.jar 
-input input/ncdc/sample.txt 
-output output 
-mapper ch02/src/main/ruby/max_temperature_map.rb 
-reducer ch02/src/main/ruby/max_temperature_reduce.rb

#!/usr/bin/env python
import re
import sys
for line in sys.stdin:
val = line.strip()
(year, temp, q) = (val[15:19], val[87:92], val[92:93])
if (temp != "+9999" and re.match("[01459]", q)):
print "%st%s" % (year, temp)

#!/usr/bin/env python
import sys
(last_key, max_val) = (None, -sys.maxint)
for line in sys.stdin:
(key, val) = line.strip().split("t")
if last_key and last_key != key:
print "%st%s" % (last_key, max_val)
(last_key, max_val) = (key, int(val))
else:
(last_key, max_val) = (key, max(max_val, int(val)))
if last_key:
print "%st%s" % (last_key, max_val)

% hadoop jar $HADOOP_INSTALL/contrib/streaming/hadoop-*-streaming.jar 
-input input/ncdc/sample.txt 
-output output 
-mapper ch02/src/main/ruby/max_temperature_map.py
-reducer ch02/src/main/ruby/max_temperature_reduce.py

#!/usr/bin/env bash
# NLineInputFormat gives a single line: key is offset, value is S3 URI
read offset s3file
# Retrieve file from S3 to local disk
echo "reporter:status:Retrieving $s3file" >&2
$HADOOP_INSTALL/bin/hadoop fs -get $s3file .
# Un-bzip and un-tar the local file
target=`basename $s3file .tar.bz2`
mkdir -p $target
echo "reporter:status:Un-tarring $s3file to $target" >&2
tar jxf `basename $s3file` -C $target
# Un-gzip each station file and concat into one file
echo "reporter:status:Un-gzipping $target" >&2
for file in $target/*/*
do
gunzip -c $file >> $target.all
echo "reporter:status:Processed $file" >&2
done
# Put gzipped version into HDFS
echo "reporter:status:Gzipping $target and putting in HDFS" >&2
gzip -c $target.all | $HADOOP_INSTALL/bin/hadoop fs -put - gz/$target.gz

% hadoop jar $HADOOP_INSTALL/contrib/streaming/hadoop-*-streaming.jar 
-D mapred.reduce.tasks=0 
-D mapred.map.tasks.speculative.execution=false 
-D mapred.task.timeout=12000000 
-input ncdc_files.txt 
-inputformat org.apache.hadoop.mapred.lib.NLineInputFormat 
-output output 
-mapper load_ncdc_map.sh 
-file load_ncdc_map.sh

% hadoop jar $HADOOP_INSTALL/contrib/streaming/hadoop-*-streaming.jar 
-input input/ncdc/all 
-output output 
-mapper "ch02/src/main/ruby/max_temperature_map.rb | sort |
ch02/src/main/ruby/max_temperature_reduce.rb" 
-reducer ch02/src/main/ruby/max_temperature_reduce.rb 
-file ch02/src/main/ruby/max_temperature_map.rb 
-file ch02/src/main/ruby/max_temperature_reduce.rb