Created
April 19, 2012 16:20
-
-
Save uzicorp/2422090 to your computer and use it in GitHub Desktop.
Experiment with Shingle Filter and Stoplist
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/sh | |
curl -XDELETE http://localhost:9200/shinglephrase | |
curl -XPOST http://localhost:9200/shinglephrase/ -d ' | |
{ | |
"settings":{ | |
"index":{ | |
"number_of_shards":5, | |
"number_of_replicas":1 | |
}, | |
"analysis":{ | |
"filter":{ | |
"myCustomShingle":{ | |
"type":"shingle", | |
"max_shingle_size":2, | |
"output_unigrams":true | |
} | |
}, | |
"analyzer":{ | |
"myAnalyzer":{ | |
"type":"custom", | |
"tokenizer":"standard", | |
"filter":[ | |
"lowercase", | |
"myCustomShingle", | |
"stop", | |
"kstem" | |
] | |
} | |
} | |
} | |
}, | |
"mappings":{ | |
"messages":{ | |
"_source":{ | |
"enabled":true | |
}, | |
"_all":{ | |
"enabled":false | |
}, | |
"index.query.default_field":"msg", | |
"properties":{ | |
"response_time":{ | |
"format":"dateOptionalTime", | |
"type":"date" | |
}, | |
"process_id":{ | |
"type":"long" | |
}, | |
"msg":{ | |
"type":"string", | |
"analyzer":"myAnalyzer", | |
"store":"yes", | |
"term_vector":"with_positions_offsets" | |
} | |
} | |
} | |
} | |
} | |
' | |
sleep 1 | |
######################################################################################################################## | |
# Dump a 10 messages into this index | |
######################################################################################################################## | |
curl -XPUT 'http://localhost:9200/_bulk' --data-binary ' | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":1}} | |
{"_id":1,"process_id":1,"response_time":"2012-01-01T00:00:00.000Z","msg":"test message"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":2}} | |
{"_id":2,"process_id":2,"response_time":"2012-01-01T00:00:00.000Z","msg":"no way"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":3}} | |
{"_id":3,"process_id":3,"response_time":"2012-01-01T00:00:00.000Z","msg":"no way"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":4}} | |
{"_id":4,"process_id":4,"response_time":"2012-01-01T00:00:00.000Z","msg":"a problem"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":5}} | |
{"_id":5,"process_id":5,"response_time":"2012-01-01T00:00:00.000Z","msg":"a problem"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":6}} | |
{"_id":6,"process_id":6,"response_time":"2012-01-01T00:00:00.000Z","msg":"my problem"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":7}} | |
{"_id":7,"process_id":7,"response_time":"2012-01-01T00:00:00.000Z","msg":"and the"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":8}} | |
{"_id":8,"process_id":8,"response_time":"2012-01-01T00:00:00.000Z","msg":"and I"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":9}} | |
{"_id":9,"process_id":9,"response_time":"2012-01-01T00:00:00.000Z","msg":"and I"} | |
{"index":{"_index":"shinglephrase","_type":"messages","_id":10}} | |
{"_id":10,"process_id":10,"response_time":"2012-01-01T00:00:00.000Z","msg":"and I"} | |
' | |
sleep 1 | |
######################################################################################################################## | |
# Top 10 | |
######################################################################################################################## | |
curl -X POST "http://localhost:9200/shinglephrase/_search?&pretty=true" -d ' | |
{ | |
"size":"0", | |
"query": { | |
"match_all": {} | |
}, | |
"facets": { | |
"blah": { | |
"terms": { | |
"field": "msg", | |
"analyzer": "myAnalyzer", | |
"exclude": [ | |
"i" | |
], | |
"size": "10" | |
} | |
} | |
} | |
} | |
' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment