From b7404fb0f696807db3a92bc2c4c73c2d208e59ef Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Thu, 30 Jan 2020 00:51:56 -0800 Subject: ES schemas: make keywords case-insensitive by default But not applying asciifolding; don't see any need to do so? --- extra/elasticsearch/container_schema.json | 38 ++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 13 deletions(-) (limited to 'extra/elasticsearch/container_schema.json') diff --git a/extra/elasticsearch/container_schema.json b/extra/elasticsearch/container_schema.json index 3be261a2..be3a408e 100644 --- a/extra/elasticsearch/container_schema.json +++ b/extra/elasticsearch/container_schema.json @@ -20,6 +20,18 @@ "char_filter": [ "icu_normalizer" ], "filter": [ "icu_folding" ] } + }, + "normalizer": { + "default": { + "type": "custom", + "char_filter": [], + "filter": ["lowercase"] + }, + "caseSensitive": { + "type": "custom", + "char_filter": [], + "filter": [] + } } } } @@ -27,23 +39,23 @@ "mappings": { "container": { "properties": { - "ident": { "type": "keyword", "doc_values": false }, - "state": { "type": "keyword" }, - "revision": { "type": "keyword", "doc_values": false }, + "ident": { "type": "keyword", "normalizer": "default", "doc_values": false }, + "state": { "type": "keyword", "normalizer": "default" }, + "revision": { "type": "keyword", "normalizer": "default", "doc_values": false }, "name": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" }, "original_name": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" }, "publisher": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" }, "abbrev": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" }, "aliases": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" }, - "container_type": { "type": "keyword" }, - "issnl": { "type": "keyword" }, - "issns": { "type": "keyword" }, - "wikidata_qid": { "type": "keyword" }, - "country": { "type": "keyword" }, - "region": { "type": "keyword" }, - "discipline": { "type": "keyword" }, - "languages": { "type": "keyword" }, - "mimetypes": { "type": "keyword" }, + "container_type": { "type": "keyword", "normalizer": "default" }, + "issnl": { "type": "keyword", "normalizer": "default" }, + "issns": { "type": "keyword", "normalizer": "default" }, + "wikidata_qid": { "type": "keyword", "normalizer": "default" }, + "country": { "type": "keyword", "normalizer": "default" }, + "region": { "type": "keyword", "normalizer": "default" }, + "discipline": { "type": "keyword", "normalizer": "default" }, + "languages": { "type": "keyword", "normalizer": "default" }, + "mimetypes": { "type": "keyword", "normalizer": "default" }, "first_year": { "type": "integer" }, "last_year": { "type": "integer" }, @@ -57,7 +69,7 @@ "any_kbart": { "type": "boolean" }, "any_jstor": { "type": "boolean" }, "any_ia_sim": { "type": "boolean" }, - "sherpa_romeo_color": { "type": "keyword" }, + "sherpa_romeo_color": { "type": "keyword", "normalizer": "default" }, "releases_total": { "type": "integer" }, "releases_kbart": { "type": "integer" }, -- cgit v1.2.3