Ngram example

gistfile1.txt

###################
# CREATE THE INDEX:
###################
curl -XPUT 'http://127.0.0.1:9200/test/?pretty=1'  -d '
{
   "settings" : {
      "analysis" : {
         "filter" : {
            "edge_ngram" : {
               "side" : "front",
               "max_gram" : 20,
               "min_gram" : 1,
               "type" : "edgeNGram"
            }
         },
         "analyzer" : {
            "ascii_ngram" : {
               "filter" : [
                  "standard",
                  "lowercase",
                  "asciifolding",
                  "nGram"
               ],
               "type" : "custom",
               "tokenizer" : "standard"
            },
            "ascii_std" : {
               "filter" : [
                  "standard",
                  "lowercase",
                  "asciifolding"
               ],
               "type" : "custom",
               "tokenizer" : "standard"
            },
            "ascii_edge_ngram" : {
               "filter" : [
                  "standard",
                  "lowercase",
                  "asciifolding",
                  "edge_ngram"
               ],
               "type" : "custom",
               "tokenizer" : "standard"
            }
         }
      }
   }
}
'

# [Sun May  8 12:56:59 2011] Response:
# {
#    "ok" : true,
#    "acknowledged" : true
# }



###################
# PUT THE MAPPING
###################
curl -XPUT 'http://127.0.0.1:9200/test/website/_mapping?pretty=1'  -d '
{
   "website" : {
      "properties" : {
         "title" : {
            "search_analyzer" : "ascii_std",
            "index_analyzer" : "ascii_edge_ngram",
            "type" : "string"
         },
         "description" : {
            "search_analyzer" : "ascii_std",
            "index_analyzer" : "ascii_edge_ngram",
            "type" : "string"
         },
         "tags" : {
            "search_analyzer" : "ascii_std",
            "index_analyzer" : "ascii_edge_ngram",
            "type" : "string"
         },
         "uri" : {
            "type" : "string",
            "include_in_all" : 0,
            "analyzer" : "ascii_ngram"
         }
      }
   }
}
'

# [Sun May  8 12:58:16 2011] Response:
# {
#    "ok" : true,
#    "acknowledged" : true
# }


###################
# INDEX A DOC
###################
curl -XPOST 'http://127.0.0.1:9200/test/website?pretty=1'  -d '
{
   "title" : "a german news site",
   "description" : "very helpful",
   "tags" : [
      "news",
      "german"
   ],
   "uri" : "http://www.heise.de"
}
'

# [Sun May  8 12:58:52 2011] Response:
# {
#    "ok" : true,
#    "_index" : "test",
#    "_id" : "veqYjNIiRI2KT5nQGNSRIQ",
#    "_type" : "website",
#    "_version" : 1
# }


###################
# SEARCH FOR 'ger'
###################
curl -XGET 'http://127.0.0.1:9200/test/website/_search?pretty=1'  -d '
{
   "query" : {
      "dis_max" : {
         "queries" : [
            {
               "field" : {
                  "uri" : "ger"
               }
            },
            {
               "field" : {
                  "_all" : "ger"
               }
            }
         ]
      }
   }
}
'

# [Sun May  8 12:59:07 2011] Response:
# {
#    "hits" : {
#       "hits" : [
#          {
#             "_source" : {
#                "title" : "a german news site",
#                "description" : "very helpful",
#                "uri" : "http://www.heise.de",
#                "tags" : [
#                   "news",
#                   "german"
#                ]
#             },
#             "_score" : 0.0025187703,
#             "_index" : "test",
#             "_id" : "veqYjNIiRI2KT5nQGNSRIQ",
#             "_type" : "website"
#          }
#       ],
#       "max_score" : 0.0025187703,
#       "total" : 1
#    },
#    "timed_out" : false,
#    "_shards" : {
#       "failed" : 0,
#       "successful" : 5,
#       "total" : 5
#    },
#    "took" : 2
# }


###################
# SEARCH FOR 'eis'
###################
curl -XGET 'http://127.0.0.1:9200/test/website/_search?pretty=1'  -d '
{
   "query" : {
      "dis_max" : {
         "queries" : [
            {
               "field" : {
                  "uri" : "eis"
               }
            },
            {
               "field" : {
                  "_all" : "eis"
               }
            }
         ]
      }
   }
}
'

# [Sun May  8 12:59:57 2011] Response:
# {
#    "hits" : {
#       "hits" : [
#          {
#             "_source" : {
#                "title" : "a german news site",
#                "description" : "very helpful",
#                "uri" : "http://www.heise.de",
#                "tags" : [
#                   "news",
#                   "german"
#                ]
#             },
#             "_score" : 0.08433159,
#             "_index" : "test",
#             "_id" : "veqYjNIiRI2KT5nQGNSRIQ",
#             "_type" : "website"
#          }
#       ],
#       "max_score" : 0.08433159,
#       "total" : 1
#    },
#    "timed_out" : false,
#    "_shards" : {
#       "failed" : 0,
#       "successful" : 5,
#       "total" : 5
#    },
#    "took" : 4
# }