Aggregate data using a parallel loop

  # Use a parallel loop to make ten queries to a public BigQuery dataset and 
 # use a shared variable to accumulate a count of words; after all iterations 
 # complete, return the total number of words across all documents 
 main 
 : 
  
 params 
 : 
  
 [ 
 input 
 ] 
  
 steps 
 : 
  
 - 
  
 init 
 : 
  
 assign 
 : 
  
 - 
  
 numWords 
 : 
  
 0 
  
 - 
  
 corpuses 
 : 
  
 - 
  
 sonnets 
  
 - 
  
 various 
  
 - 
  
 1kinghenryvi 
  
 - 
  
 2kinghenryvi 
  
 - 
  
 3kinghenryvi 
  
 - 
  
 comedyoferrors 
  
 - 
  
 kingrichardiii 
  
 - 
  
 titusandronicus 
  
 - 
  
 tamingoftheshrew 
  
 - 
  
 loveslabourslost 
  
 - 
  
 runQueries 
 : 
  
 parallel 
 : 
  
 # 'numWords' is shared so it can be written within the parallel loop 
  
 shared 
 : 
  
 [ 
 numWords 
 ] 
  
 for 
 : 
  
 value 
 : 
  
 corpus 
  
 in 
 : 
  
 ${corpuses} 
  
 steps 
 : 
  
 - 
  
 runQuery 
 : 
  
 call 
 : 
  
 googleapis.bigquery.v2.jobs.query 
  
 args 
 : 
  
 projectId 
 : 
  
 ${sys.get_env("GOOGLE_CLOUD_PROJECT_ID")} 
  
 body 
 : 
  
 useLegacySql 
 : 
  
 false 
  
 query 
 : 
  
 ${"SELECT COUNT(DISTINCT word) FROM `bigquery-public-data.samples.shakespeare` " + " WHERE corpus='" + corpus + "' "} 
  
 result 
 : 
  
 query 
  
 - 
  
 add 
 : 
  
 assign 
 : 
  
 - 
  
 numWords 
 : 
  
 ${numWords + int(query.rows[0].f[0].v)} 
  
 # first result is the count 
  
 - 
  
 done 
 : 
  
 return 
 : 
  
 ${numWords}