Launch a 10 node EMR cluster and run a Java word count against a single common crawl segment.

emr-examples-single-segment-10-node-java.sh

# Word count, Java-fied.
#
# In this implementation, the job knows how to discover its input URIs based
# on the max.segments argument, which specifies how many crawl segments
# to process.
#
# See the code for details.

$ elastic-mapreduce \
  --create \
  --name "Common Crawl word count" \
  --enable-debugging \
  --ami-version latest \
  --instance-group master --instance-count 1 --instance-type m2.2xlarge \
  --instance-group core --instance-count 10 --instance-type c1.xlarge \
  --jar s3n://emr-examples.dius.com.au/java/emr-examples.jar \
  --main-class au.com.dius.emr.CommonCrawlTool \
  --arg -D --arg target.words=hello,world \
  --arg -D --arg max.segments=1