Details
-
Improvement
-
Resolution: Not a Bug
-
Major
-
6.5.0
Description
Build: 6.5.0.3143/3883/3274
1: Load dataset attached
2. Create index with :
|
{
|
"mapping": { |
"default_analyzer": "standard", |
"default_datetime_parser": "dateTimeOptional", |
"type_field": "type", |
"default_mapping": { |
"default_analyzer": "", |
"dynamic": true, |
"enabled": false |
},
|
"default_type": "_default", |
"analysis": { |
"analyzers": { |
"customAnalyzer1": { |
"type": "custom", |
"char_filters": [ |
"mapping" |
],
|
"tokenizer": "unicode", |
"token_filters": [ |
"shingle", |
"front_edge_ngram" |
]
|
}
|
},
|
"token_maps": { |
"stopwords": { |
"tokens": [ |
"i", |
"me", |
"my", |
"myself", |
"we", |
"our", |
"ours", |
"ourselves", |
"you", |
"your", |
"yours", |
"yourself", |
"yourselves", |
"he", |
"him", |
"his", |
"himself", |
"she", |
"her", |
"hers", |
"herself", |
"it", |
"its", |
"itself", |
"they", |
"them", |
"their", |
"theirs", |
"themselves", |
"what", |
"which", |
"who", |
"whom", |
"this", |
"that", |
"these", |
"those", |
"am", |
"is", |
"are", |
"was", |
"were", |
"be", |
"been", |
"being", |
"have", |
"has", |
"had", |
"having", |
"do", |
"does", |
"did", |
"doing", |
"would", |
"should", |
"could", |
"ought", |
"i'm", |
"you're", |
"he's", |
"she's", |
"it's", |
"we're", |
"they're", |
"i've", |
"you've", |
"we've", |
"they've", |
"i'd", |
"you'd", |
"he'd", |
"she'd", |
"we'd", |
"they'd", |
"i'll", |
"you'll", |
"he'll", |
"she'll", |
"we'll", |
"they'll", |
"isn't", |
"aren't", |
"wasn't", |
"weren't", |
"hasn't", |
"haven't", |
"hadn't", |
"doesn't", |
"don't", |
"didn't", |
"won't", |
"wouldn't", |
"shan't", |
"shouldn't", |
"can't", |
"cannot", |
"couldn't", |
"mustn't", |
"let's", |
"that's", |
"who's", |
"what's", |
"here's", |
"there's", |
"when's", |
"where's", |
"why's", |
"how's", |
"a", |
"an", |
"the", |
"and", |
"but", |
"if", |
"or", |
"because", |
"as", |
"until", |
"while", |
"of", |
"at", |
"by", |
"for", |
"with", |
"about", |
"against", |
"between", |
"into", |
"through", |
"during", |
"before", |
"after", |
"above", |
"below", |
"to", |
"from", |
"up", |
"down", |
"in", |
"out", |
"on", |
"off", |
"over", |
"under", |
"again", |
"further", |
"then", |
"once", |
"here", |
"there", |
"when", |
"where", |
"why", |
"how", |
"all", |
"any", |
"both", |
"each", |
"few", |
"more", |
"most", |
"other", |
"some", |
"such", |
"no", |
"nor", |
"not", |
"only", |
"own", |
"same", |
"so", |
"than", |
"too", |
"very" |
],
|
"type": "custom" |
}
|
},
|
"tokenizers": { |
"alphanumeric": { |
"regexp": "[0-9a-zA-Z_]*", |
"type": "regexp" |
}
|
},
|
"char_filters": { |
"mapping": { |
"regexp": "[f]", |
"type": "regexp", |
"replace": "ph" |
}
|
},
|
"token_filters": { |
"dict_compound_en": { |
"dict_token_map": "stop_en", |
"type": "dict_compound" |
},
|
"keyword_marker": { |
"type": "keyword_marker", |
"keywords_token_map": "stopwords" |
},
|
"truncate": { |
"length": 10, |
"type": "truncate_token" |
},
|
"dict_compound_fr": { |
"dict_token_map": "articles_fr", |
"type": "dict_compound" |
},
|
"ngram": { |
"max": 5, |
"type": "ngram", |
"min": 3 |
},
|
"front_edge_ngram": { |
"max": 5, |
"type": "edge_ngram", |
"back": false, |
"min": 3 |
},
|
"back_edge_ngram": { |
"max": 5, |
"type": "edge_ngram", |
"back": true, |
"min": 3 |
},
|
"shingle": { |
"output_original": "false", |
"min": 2, |
"filler": "", |
"max": 5, |
"separator": "", |
"type": "shingle" |
},
|
"length": { |
"max": 5, |
"type": "length", |
"min": 3 |
},
|
"stopwords": { |
"stop_token_map": "stopwords", |
"type": "stop_tokens" |
}
|
}
|
},
|
"default_field": "_all", |
"types": { |
"emp": { |
"enabled": true, |
"dynamic": false, |
"properties": { |
"dept": { |
"enabled": true, |
"dynamic": false, |
"properties": {}, |
"fields": [ |
{
|
"index": true, |
"name": "dept", |
"include_in_all": true, |
"type": "text", |
"analyzer": "customAnalyzer1", |
"include_term_vectors": true, |
"store": false |
}
|
]
|
},
|
"join_date": { |
"enabled": true, |
"dynamic": false, |
"properties": {}, |
"fields": [ |
{
|
"index": true, |
"name": "join_date", |
"include_in_all": true, |
"type": "datetime", |
"analyzer": "", |
"include_term_vectors": true, |
"store": false |
}
|
]
|
},
|
"manages": { |
"enabled": true, |
"dynamic": false, |
"properties": { |
"team_size": { |
"enabled": true, |
"dynamic": false, |
"properties": {}, |
"fields": [ |
{
|
"index": true, |
"name": "team_size", |
"include_in_all": true, |
"type": "number", |
"analyzer": "", |
"include_term_vectors": true, |
"store": false |
}
|
]
|
},
|
"reports": { |
"enabled": true, |
"dynamic": false, |
"properties": {}, |
"fields": [ |
{
|
"index": true, |
"name": "reports", |
"include_in_all": true, |
"type": "text", |
"analyzer": "customAnalyzer1", |
"include_term_vectors": true, |
"store": false |
}
|
]
|
}
|
},
|
"fields": [] |
},
|
"languages_known": { |
"enabled": true, |
"dynamic": false, |
"properties": {}, |
"fields": [ |
{
|
"index": true, |
"name": "languages_known", |
"include_in_all": true, |
"type": "text", |
"analyzer": "customAnalyzer1", |
"include_term_vectors": true, |
"store": false |
}
|
]
|
}
|
},
|
"fields": [] |
}
|
}
|
}
|
|
3. Following query retruns 0 results where ES results in 2 results
|
2019-08-02 10:18:31 | INFO | MainProcess | Cluster_Thread | [task.execute] ----------------------------------------------------- Query # 53 ---------------------------------------------------- |
2019-08-02 10:18:31 | INFO | MainProcess | Cluster_Thread | [fts_base.run_fts_query] Running query \{"indexName": "custom_index", "from": 0, "fields": [], "explain": false, "ctl": {"timeout": 60000, "consistency": {"vectors": {}, "level": ""}}, "query": \{"field": "manages.reports", "match_phrase": "Balandria Deandra Kory"}, "size": 10000000} on node: 192.168.10.12: |
2019-08-02 10:18:31 | INFO | MainProcess | Cluster_Thread | [task.execute] Status: \{u'successful': 6, u'failed': 0, u'total': 6} |
2019-08-02 10:18:31 | INFO | MainProcess | Cluster_Thread | [task.execute] FTS hits for query: \{"field": "manages.reports", "match_phrase": "Balandria Deandra Kory"} is 0 (took 0.954437ms) |
2019-08-02 10:18:31 | INFO | MainProcess | Cluster_Thread | [es_base.search] ES query '\{u'query': {u'match_phrase': {u'manages.reports': u'Balandria Deandra Kory'}}}' |
2019-08-02 10:18:31 | INFO | MainProcess | Cluster_Thread | [task.execute] ES hits for query: \{"query": {"match_phrase": {"manages.reports": "Balandria Deandra Kory"}}} on es_index is 2 (took 3ms) |
2019-08-02 10:18:31 | ERROR | MainProcess | Cluster_Thread | [task.execute] FAIL: FTS hits: 0, while ES hits: 2 |
2019-08-02 10:26:55 | ERROR | MainProcess | Cluster_Thread | [task.execute] FAIL: Following 2 docs were not returned by FTS, but ES, printing 50: [u'emp10000825', u'emp10000884'] |
|
Job: centos-fts_custom-map-rqg-scorch
Test: ./testrunner -i test.ini -p get-logs=False,stop-on-failure=False,GROUP=P1,doc-per-day=1,bucket_size=200,scan_consistency=NOT_BOUNDED -t fts.stable_topology_fts.StableTopFTS.index_query_custom_mapping,items=1000,custom_map=True,num_custom_analyzers=1,multiple_filters=true,cm_id=35,num_queries=100,compare_es=True,GROUP=P1,disable_HTP=True,get-logs=False,stop-on-failure=False,index_type=upside_down,cluster=D+F,fts_quota=750
Not sure if this is regression, this behaves the same with the build 6.5.0-3143/3274
Attachments
Issue Links
- mentioned in
-
Page Loading...