gistfile1.sh

#create a test index with shingle mapping
curl -XPUT localhost:9200/test -d '{
   "settings":{
      "index":{
         "analysis":{
            "analyzer":{
               "analyzer_shingle":{
                  "tokenizer":"standard",
                  "filter":["standard", "lowercase", "filter_stop", "filter_shingle"]
               }
            },
            "filter":{
               "filter_shingle":{
                  "type":"shingle",
                  "max_shingle_size":5,
                  "min_shingle_size":2,
                  "output_unigrams":"true"
               },
               "filter_stop":{
                  "type":"stop",
                  "enable_position_increments":"false"
               }
            }
         }
      }
   },
   "mappings":{
      "product":{
         "properties":{
            "title":{
               "search_analyzer":"analyzer_shingle",
               "index_analyzer":"analyzer_shingle",
               "type":"string"
            }
         }
      }
   }
}'

#Add some docs to the index
curl -XPOST localhost:9200/test/product/1 -d '{"title" : "Sample product title for shingles"}'
curl -XPOST localhost:9200/test/product/2 -d '{"title" : "Another title"}'
curl -XPOST localhost:9200/test/product/3 -d '{"title" : "Shingles is a viral disease"}'

#Analyze API to check out shingling
curl -XGET 'localhost:9200/test/_analyze?analyzer=analyzer_shingle&pretty' -d 'Test text to see shingles' | grep token

#Sample search
curl -XGET 'localhost:9200/test/product/_search?q=title:product+title&pretty'

#this one won't return anything, because of the stop filter
curl -XGET 'localhost:9200/test/product/_search?q=title:is+a&pretty'

#while this one will, because we emit unigrams
curl -XGET 'localhost:9200/test/product/_search?q=title:is+a+viral&pretty'