jprante / elasticsearch-plugin-bundle

A bundle of useful Elasticsearch plugins

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

baseform:illegal_argument_exception

541079843 opened this issue · comments

Hi,
With the baseform plugin from version 2.3.4.0 of the bundle (and ES 2.3.4) , I got the error message
"reason":{"type":"illegal_argument_exception","reason":"Less than 2 subSpans.size():1"} .

The query string I uesed is
{ "query": { "function_score": { "query": { "bool": { "must": [ { "multi_match": { "query": "all company", "fields": [ "title.en", "content.en^0.1" ] } } ] } }, "functions": [ { "script_score": { "script": "(1)" } } ], "score_mode": "multiply" } }, "highlight": { "fields": { "content.en": { "pre_tags": [ "<span class=\"highlight\">" ], "post_tags": [ "</span>" ], "fragment_size": 200, "number_of_fragments": 1 }, "title.en": { "pre_tags": [ "<span class=\"highlight\">" ], "post_tags": [ "</span>" ], "fragment_size": 200, "number_of_fragments": 1 } } } }
And the index setting and mapping string is
{ "settings":{ "number_of_shards": 3, "number_of_replicas": 1, "analysis": { "analyzer": { "english": { "tokenizer": "standard", "filter": [ "lowercase", "synonym_en", "english_stop", "trim", "baseform", "english_possessive_stemmer", "english_stemmer" ], "char_filter": [ "html_strip" ] }, "ngram_analyzer": { "tokenizer": "ngram_tokenizer" } }, "filter": { "synonym_en": { "type": "synonym", "ignore_case": true, "tokenizer": "standard", "synonyms_path": "analysis/synonym_en.txt" }, "english_stop": { "type": "stop", "stopwords_path": "stopwords/english.txt" }, "english_stemmer": { "type": "stemmer", "language": "english" }, "english_possessive_stemmer": { "type": "stemmer", "language": "possessive_english" }, "baseform" : { "type" : "baseform", "language" : "en" }, "remove_empty": { "type" : "stop", "stopwords" : [ " ", " " ] } } } }, "document": { "_source": { "enabled": true }, "_all": { "enabled": true }, "dynamic": false, "properties": { "id": { "type": "string", "index": "not_analyzed" }, "title": { "type": "string", "index": "analyzed", "fields": { "en": { "type": "string", "analyzer": "english" } } }, "content": { "type": "string", "index": "analyzed", "store": "true", "norms": { "enabled": false }, "fields": { "en": { "type": "string", "analyzer": "english", "norms": { "enabled": false } } } } } } }'

The result of ES searching with the query string reported error message always , unless removing the 'highlight ' party from the query stringor reindex the documents without the 'basethform' module . By the way , the search key words is 'all comanies' what I input , and the word 'all' is a stop word.
So , can you help me to resolve the issue ?
Thank you very much.