Details
-
Bug
-
Resolution: Invalid
-
Medium
-
4.6.3
-
None
-
Yes
Description
If you on a multilingual setup have language dependent analysis ( like stemming), search is broken with the following exception:
{"error":{"root_cause":[],"type":"search_phase_execution_exception","reason":"","phase":"fetch","grouped":true,"failed_shards":[],"caused_by":{"type":"illegal_state_exception","reason":"Can't
merge suggest entries, this might be caused by suggest calls across
multiple indices with different analysis chains. Suggest entries have
different text actual [cars] expected [car]"}},"status":500}
How to reproduce:
- Configure Norwegian and English language using admin-ui and siteaccess config
- Add the elastic search config listed later in the ticket
- Create folder (in eng-GB) with
- title "The quick brown fox jumps houses"
- Short description: "fast cars are better than slow ones"
- Search for "car" in admin-ui, it works
- But the following searches causes exception:
- cars
- house
- houses
- The exceptions happens when you click on the "Search" button
# Base configuration for Elasticsearch
parameters:
env(ELASTICSEARCH_URL): '%env(ELASTICSEARCH_DSN)%'
elasticsearch_dsn: "%env(ELASTICSEARCH_URL)%"
ibexa_elasticsearch:
connections:
default:
hosts:
- "%elasticsearch_dsn%"
index_templates:
- norwegian
- english
debug: true
trace: true
document_group_resolver: 'Ibexa\Elasticsearch\ElasticSearch\Index\Group\LanguageGroupResolver'
index_templates:
norwegian:
# "order" not supported:
#order: 10
patterns:
- "*_nor_no*"
settings:
analysis:
normalizer:
lowercase_normalizer:
type: custom
char_filter: []
filter:
- lowercase
analyzer:
ibexa_spellcheck_analyzer:
type: custom
tokenizer: lowercase
filter:
- lowercase
- norwegian_stop
- norwegian_keywords
- norwegian_stemmer
- ibexa_spellcheck_shingle_filter
ibexa_spellcheck_raw_analyzer:
type: custom
tokenizer: standard
filter:
- lowercase
- norwegian_stop
- norwegian_keywords
- norwegian_stemmer
filter:
ibexa_spellcheck_shingle_filter:
type: shingle
min_shingle_size: 2
max_shingle_size: 3
norwegian_stop:
type: stop
stopwords: "_norwegian_"
norwegian_keywords:
type: keyword_marker
keywords: []
norwegian_stemmer:
type: stemmer
# https://www.elastic.co/guide/en/elasticsearch/reference/7.17/analysis-stemmer-tokenfilter.html#analysis-stemmer-tokenfilter-configure-parms
# language: norwegian
language: light_norwegian
refresh_interval: "-1"
index:
mapping:
total_fields:
limit: 5000
mappings:
dynamic_templates:
- ez_int:
match: "*_i"
mapping:
type: integer
- ez_mint:
match: "*_mi"
mapping:
type: integer
- ez_id:
match: "*_id"
mapping:
type: keyword
- ez_mid:
match: "*_mid"
mapping:
type: keyword
- ez_string:
match: "*_s"
mapping:
type: keyword
normalizer: lowercase_normalizer
- ez_mstring:
match: "*_ms"
mapping:
type: keyword
normalizer: lowercase_normalizer
- ez_long:
match: "*_l"
mapping:
type: long
- ez_mlong:
match: "*_ml"
mapping:
type: long
- ez_text_fulltext:
match: "*_fulltext"
mapping:
type: text
analyzer: ibexa_spellcheck_analyzer
- ez_text:
match: "*_t"
mapping:
type: text
analyzer: ibexa_spellcheck_analyzer
- ez_boolean:
match: "*_b"
mapping:
type: boolean
- ez_mboolean:
match: "*_mb"
mapping:
type: boolean
- ez_float:
match: "*_f"
mapping:
type: float
- ez_double:
match: "*_d"
mapping:
type: double
- ez_date:
match: "*_dt"
mapping:
type: date
- ez_geolocation:
match: "*_gl"
mapping:
type: geo_point
- ez_spellcheck:
match: "*_spellcheck"
mapping:
type: text
analyzer: ibexa_spellcheck_analyzer
fields:
raw:
type: text
analyzer: ibexa_spellcheck_raw_analyzer
english:
patterns:
- "*_eng_gb*"
settings:
analysis:
normalizer:
lowercase_normalizer:
type: custom
char_filter: []
filter:
- lowercase
analyzer:
ibexa_spellcheck_analyzer:
type: custom
tokenizer: lowercase
filter:
- lowercase
- english_stop
- english_keywords
- english_stemmer
- english_possessive_stemmer
- ibexa_spellcheck_shingle_filter
ibexa_spellcheck_raw_analyzer:
type: custom
tokenizer: standard
filter:
- lowercase
- english_stop
- english_keywords
- english_stemmer
- english_possessive_stemmer
filter:
ibexa_spellcheck_shingle_filter:
type: shingle
min_shingle_size: 2
max_shingle_size: 3
english_stop:
type: stop
stopwords: "_english_"
english_keywords:
type: keyword_marker
keywords: []
english_stemmer:
type: stemmer
# https://www.elastic.co/guide/en/elasticsearch/reference/7.17/analysis-stemmer-tokenfilter.html#analysis-stemmer-tokenfilter-configure-parms
language: light_english
"english_possessive_stemmer": {
"type": "stemmer",
"language": "possessive_english"
}
refresh_interval: "-1"
index:
mapping:
total_fields:
limit: 5000
mappings:
dynamic_templates:
- ez_int:
match: "*_i"
mapping:
type: integer
- ez_mint:
match: "*_mi"
mapping:
type: integer
- ez_id:
match: "*_id"
mapping:
type: keyword
- ez_mid:
match: "*_mid"
mapping:
type: keyword
- ez_string:
match: "*_s"
mapping:
type: keyword
normalizer: lowercase_normalizer
- ez_mstring:
match: "*_ms"
mapping:
type: keyword
normalizer: lowercase_normalizer
- ez_long:
match: "*_l"
mapping:
type: long
- ez_mlong:
match: "*_ml"
mapping:
type: long
- ez_text_fulltext:
match: "*_fulltext"
mapping:
type: text
analyzer: ibexa_spellcheck_analyzer
- ez_text:
match: "*_t"
mapping:
type: text
analyzer: ibexa_spellcheck_analyzer
- ez_boolean:
match: "*_b"
mapping:
type: boolean
- ez_mboolean:
match: "*_mb"
mapping:
type: boolean
- ez_float:
match: "*_f"
mapping:
type: float
- ez_double:
match: "*_d"
mapping:
type: double
- ez_date:
match: "*_dt"
mapping:
type: date
- ez_geolocation:
match: "*_gl"
mapping:
type: geo_point
- ez_spellcheck:
match: "*_spellcheck"
mapping:
type: text
analyzer: ibexa_spellcheck_analyzer
fields:
raw:
type: text
analyzer: ibexa_spellcheck_raw_analyzer