Bonjour a tous ,
ma question est la suivante :
je ne vois pas quel token ou mapping utilisé pour remédier a ma problématique :
dans mon moteur de recherche local pour pdf (avec le plug in ingest attachment).
lorsque j'écris un par exemple un prénom , il va me trouver dans le document toute les fois ou le prénom est mentionné , mais j'aimerais qu'il me le souligne qu'une seul fois.
ayant quelque difficulté a écrire ma problématique en anglais, je ne sais pas forcement la formuler dans la langue de shakespear . Je vous ai mis les settings de mon index "pdf".
merci pour vos réponse
{
"settings": {
"index": {
"max_ngram_diff": "20",
"blocks": {
"write": "true"
},
"provided_name": "pdf",
"creation_date": "1632383182575",
"sort": {
"field": "web_path",
"order": "desc"
},
"analysis": {
"analyzer": {
"name_analyzer": {
"filter": [
"lowercase"
],
"type": "custom",
"tokenizer": "trigram"
}
},
"tokenizer": {
"trigram": {
"type": "nGram",
"min_gram": "5",
"max_gram": "15"
}
}
},
"number_of_replicas": "1",
"uuid": "KoQ6cySVQ-uWl3lNFEbX2w",
"version": {
"created": "7140199"
},
"codec": "best_compression",
"highlight": {
"max_analyzed_offset": "10000000"
},
"routing": {
"allocation": {
"include": {
"_tier_preference": "data_content"
}
}
},
"number_of_shards": "2"
}
},
"defaults": {
"index": {
"flush_after_merge": "512mb",
"final_pipeline": "_none",
"max_inner_result_window": "100",
"unassigned": {
"node_left": {
"delayed_timeout": "1m"
}
},
"max_terms_count": "65536",
"rollup": {
"source": {
"name": "",
"uuid": ""
}
},
"lifecycle": {
"name": "",
"parse_origination_date": "false",
"step": {
"wait_time_threshold": "12h"
},
"indexing_complete": "false",
"rollover_alias": "",
"origination_date": "-1"
},
"routing_partition_size": "1",
"force_memory_term_dictionary": "false",
"max_docvalue_fields_search": "100",
"merge": {
"scheduler": {
"max_thread_count": "4",
"auto_throttle": "true",
"max_merge_count": "9"
},
"policy": {
"floor_segment": "2mb",
"max_merge_at_once_explicit": "30",
"max_merge_at_once": "10",
"max_merged_segment": "5gb",
"expunge_deletes_allowed": "10.0",
"segments_per_tier": "10.0",
"deletes_pct_allowed": "33.0"
}
},
"max_refresh_listeners": "1000",
"max_regex_length": "1000",
"load_fixed_bitset_filters_eagerly": "true",
"number_of_routing_shards": "2",
"write": {
"wait_for_active_shards": "1"
},
"verified_before_close": "false",
"mapping": {
"coerce": "false",
"nested_fields": {
"limit": "50"
},
"depth": {
"limit": "20"
},
"field_name_length": {
"limit": "9223372036854775807"
},
"total_fields": {
"limit": "1000"
},
"nested_objects": {
"limit": "10000"
},
"ignore_malformed": "false"
},
"source_only": "false",
"soft_deletes": {
"enabled": "true",
"retention": {
"operations": "0"
},
"retention_lease": {
"period": "12h"
}
},
"max_script_fields": "32",
"query": {
"default_field": [
"*"
],
"parse": {
"allow_unmapped_fields": "true"
}
},
"format": "0",
"frozen": "false",
"sort": {
"missing": [],
"mode": []
},
"priority": "1",
"max_rescore_window": "10000",
"max_adjacency_matrix_filters": "100",
"analyze": {
"max_token_count": "10000"
},
"gc_deletes": "60s",
"top_metrics_max_size": "10",
"optimize_auto_generated_id": "true",
"hidden": "false",
"translog": {
"generation_threshold_size": "64mb",
"flush_threshold_size": "512mb",
"sync_interval": "5s",
"retention": {
"size": "-1",
"age": "-1"
},
"durability": "REQUEST"
},
"auto_expand_replicas": "false",
"mapper": {
"dynamic": "true"
},
"recovery": {
"type": ""
},
"requests": {
"cache": {
"enable": "true"
}
},
"data_path": "",
"routing": {
"rebalance": {
"enable": "all"
},
"allocation": {
"include": {
"_tier": ""
},
"disk": {
"watermark": {
"ignore": "false"
}
},
"exclude": {
"_tier": ""
},
"require": {
"_tier": ""
},
"enable": "all",
"total_shards_per_node": "-1"
}
},
"search": {
"slowlog": {
"level": "TRACE",
"threshold": {
"fetch": {
"warn": "-1",
"trace": "-1",
"debug": "-1",
"info": "-1"
},
"query": {
"warn": "-1",
"trace": "-1",
"debug": "-1",
"info": "-1"
}
}
},
"idle": {
"after": "30s"
},
"throttled": "false"
},
"fielddata": {
"cache": "node"
},
"default_pipeline": "_none",
"max_slices_per_scroll": "1024",
"shard": {
"check_on_startup": "false"
},
"xpack": {
"watcher": {
"template": {
"version": ""
}
},
"version": "",
"ccr": {
"following_index": "false"
}
},
"percolator": {
"map_unmapped_fields_as_text": "false"
},
"allocation": {
"max_retries": "5",
"existing_shards_allocator": "gateway_allocator"
},
"refresh_interval": "1s",
"indexing": {
"slowlog": {
"reformat": "true",
"threshold": {
"index": {
"warn": "-1",
"trace": "-1",
"debug": "-1",
"info": "-1"
}
},
"source": "1000",
"level": "TRACE"
}
},
"compound_format": "0.1",
"blocks": {
"metadata": "false",
"read": "false",
"read_only_allow_delete": "false",
"read_only": "false"
},
"max_result_window": "10000",
"store": {
"stats_refresh_interval": "10s",
"type": "",
"fs": {
"fs_lock": "native"
},
"preload": [],
"snapshot": {
"snapshot_name": "",
"index_uuid": "",
"cache": {
"prewarm": {
"enabled": "true"
},
"enabled": "true",
"excluded_file_types": []
},
"repository_uuid": "",
"uncached_chunk_size": "-1b",
"index_name": "",
"partial": "false",
"blob_cache": {
"metadata_files": {
"max_length": "64kb"
}
},
"repository_name": "",
"snapshot_uuid": ""
}
},
"queries": {
"cache": {
"enabled": "true"
}
},
"shard_limit": {
"group": "normal"
},
"warmer": {
"enabled": "true"
},
"max_shingle_diff": "3",
"query_string": {
"lenient": "false"
}
}
}
}
.