From 77cc94e1f4a7f585a9049cc7a11fcd21c7f13787 Mon Sep 17 00:00:00 2001 From: jamie Date: Tue, 30 Apr 2024 15:30:19 +0100 Subject: [PATCH 1/4] Remove unused index config --- .../fixtures/index/ImagesIndexFixtures.scala | 4 +- .../fixtures/index/WorksIndexFixtures.scala | 4 +- .../analysis.works_indexed.2023-11-09.json | 357 ---------- .../mappings.images_indexed.2023-11-09.json | 597 ----------------- .../mappings.works_indexed.2023-11-09.json | 618 ------------------ 5 files changed, 4 insertions(+), 1576 deletions(-) delete mode 100644 index_config/analysis.works_indexed.2023-11-09.json delete mode 100644 index_config/mappings.images_indexed.2023-11-09.json delete mode 100644 index_config/mappings.works_indexed.2023-11-09.json diff --git a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala index 0856273efc..17576f171d 100644 --- a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala +++ b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala @@ -12,8 +12,8 @@ trait ImagesIndexFixtures extends IndexFixturesBase { def withLocalImagesIndex[R]: Fixture[Index, R] = { withLocalElasticSearchIndex[R](config = getConfig( - mappings = "mappings.images_indexed.2023-11-09.json", - analysis = "analysis.works_indexed.2023-11-09.json" + mappings = "mappings.images_indexed.2024-01-09.json", + analysis = "analysis.works_indexed.2024-01-09.json" ) ) } diff --git a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala index 7804a46f51..58810ef9a8 100644 --- a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala +++ b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala @@ -31,8 +31,8 @@ trait WorksIndexFixtures extends IndexFixturesBase { def withLocalWorksIndex[R]: Fixture[Index, R] = { withLocalElasticSearchIndex[R](config = getConfig( - mappings = "mappings.works_indexed.2023-11-09.json", - analysis = "analysis.works_indexed.2023-11-09.json" + mappings = "mappings.works_indexed.2024-01-09.json", + analysis = "analysis.works_indexed.2024-01-09.json" ) ) } diff --git a/index_config/analysis.works_indexed.2023-11-09.json b/index_config/analysis.works_indexed.2023-11-09.json deleted file mode 100644 index 50b6e20542..0000000000 --- a/index_config/analysis.works_indexed.2023-11-09.json +++ /dev/null @@ -1,357 +0,0 @@ -{ - "char_filter": { - "zero_width_spaces": { - "type": "mapping", - "mappings": [ - "\\u200C=>\\u0020" - ] - }, - "slash_remover": { - "type": "pattern_replace", - "pattern": "/", - "replacement": "" - }, - "remove_punctuation": { - "type": "pattern_replace", - "_name": "Removes non-letter, non-numeric, and non-whitespace characters. Respects other character sets.", - "pattern": "[^\\p{L}\\p{Nd}\\s]", - "replacement": "" - } - }, - "filter": { - "word_delimiter": { - "type": "word_delimiter_graph", - "preserve_original": "true" - }, - "asciifolding": { - "type": "asciifolding" - }, - "shingle": { - "type": "shingle", - "min_shingle_size": 2, - "max_shingle_size": 3, - "output_unigrams": true - }, - "arabic_stemmer": { - "type": "stemmer", - "language": "arabic" - }, - "bengali_stemmer": { - "type": "stemmer", - "language": "bengali" - }, - "possessive_english": { - "type": "stemmer", - "language": "possessive_english" - }, - "english_stemmer": { - "type": "stemmer", - "language": "english" - }, - "french_elision": { - "type": "elision", - "articles_case": true, - "articles": [ - "l", - "m", - "t", - "qu", - "n", - "s", - "j", - "d", - "c", - "jusqu", - "quoiqu", - "lorsqu", - "puisqu" - ] - }, - "french_stemmer": { - "type": "stemmer", - "language": "light_french" - }, - "german_stemmer": { - "type": "stemmer", - "language": "light_german" - }, - "hindi_stemmer": { - "type": "stemmer", - "language": "hindi" - }, - "italian_elision": { - "type": "elision", - "articles": [ - "c", - "l", - "all", - "dall", - "dell", - "nell", - "sull", - "coll", - "pell", - "gl", - "agl", - "dagl", - "degl", - "negl", - "sugl", - "un", - "m", - "t", - "s", - "v", - "d" - ], - "articles_case": true - }, - "italian_stemmer": { - "type": "stemmer", - "language": "light_italian" - }, - "spanish_stemmer": { - "type": "stemmer", - "language": "light_spanish" - }, - "pattern_replace_vv_w": { - "type": "pattern_replace", - "pattern": "vv", - "replacement": "w" - }, - "pattern_replace_uu_w": { - "type": "pattern_replace", - "pattern": "uu", - "replacement": "w" - }, - "pattern_replace_v_u": { - "type": "pattern_replace", - "pattern": "v", - "replacement": "u" - }, - "pattern_replace_j_i": { - "type": "pattern_replace", - "pattern": "j", - "replacement": "i" - }, - "pattern_replace_g_j": { - "type": "pattern_replace", - "pattern": "g", - "replacement": "j" - } - }, - "analyzer": { - "arabic": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "word_delimiter", - "lowercase", - "decimal_digit", - "arabic_normalization", - "arabic_stemmer", - "shingle" - ] - }, - "bengali": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "word_delimiter", - "lowercase", - "decimal_digit", - "indic_normalization", - "bengali_normalization", - "bengali_stemmer", - "shingle" - ] - }, - "english": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "possessive_english", - "asciifolding", - "word_delimiter", - "lowercase", - "english_stemmer", - "shingle" - ] - }, - "english_without_shingles": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "possessive_english", - "asciifolding", - "word_delimiter", - "lowercase", - "english_stemmer" - ] - }, - "normalized_whole_phrase": { - "char_filter": [ - "remove_punctuation" - ], - "tokenizer": "keyword", - "filter": [ - "asciifolding", - "lowercase" - ] - }, - "french": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "french_elision", - "word_delimiter", - "lowercase", - "french_stemmer", - "shingle" - ] - }, - "german": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "word_delimiter", - "lowercase", - "german_normalization", - "german_stemmer", - "shingle" - ] - }, - "hindi": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "word_delimiter", - "lowercase", - "decimal_digit", - "indic_normalization", - "hindi_normalization", - "hindi_stemmer", - "shingle" - ] - }, - "italian": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "italian_elision", - "word_delimiter", - "lowercase", - "italian_stemmer", - "shingle" - ] - }, - "persian": { - "char_filter": [ - "zero_width_spaces", - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "word_delimiter", - "lowercase", - "decimal_digit", - "arabic_normalization", - "persian_normalization", - "shingle" - ] - }, - "spanish": { - "char_filter": [ - "slash_remover" - ], - "tokenizer": "whitespace", - "filter": [ - "word_delimiter", - "lowercase", - "spanish_stemmer", - "shingle" - ] - }, - "lowercase": { - "char_filter": [ - "slash_remover" - ], - "filter": [ - "asciifolding", - "word_delimiter", - "lowercase" - ], - "type": "custom", - "tokenizer": "whitespace" - }, - "cased": { - "char_filter": [ - "slash_remover" - ], - "filter": [ - "asciifolding", - "word_delimiter" - ], - "type": "custom", - "tokenizer": "whitespace" - }, - "base": { - "char_filter": [ - "slash_remover" - ], - "filter": [ - "word_delimiter" - ], - "type": "custom", - "tokenizer": "whitespace" - }, - "path_analyzer": { - "filter": [ - "asciifolding", - "lowercase" - ], - "type": "custom", - "tokenizer": "path_hierarchy" - }, - "swappable_characters": { - "char_filter": [ - "slash_remover" - ], - "filter": [ - "word_delimiter", - "asciifolding", - "lowercase", - "pattern_replace_vv_w", - "pattern_replace_uu_w", - "pattern_replace_v_u", - "pattern_replace_j_i", - "pattern_replace_g_j" - ], - "type": "custom", - "tokenizer": "whitespace" - }, - "lowercase_whitespace_tokens": { - "filter": [ - "lowercase" - ], - "type": "custom", - "tokenizer": "whitespace" - } - } -} diff --git a/index_config/mappings.images_indexed.2023-11-09.json b/index_config/mappings.images_indexed.2023-11-09.json deleted file mode 100644 index 433f82424a..0000000000 --- a/index_config/mappings.images_indexed.2023-11-09.json +++ /dev/null @@ -1,597 +0,0 @@ -{ - "dynamic": "strict", - "properties": { - "aggregatableValues": { - "properties": { - "locations": { - "properties": { - "license": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - }, - "source": { - "properties": { - "contributors": { - "properties": { - "agent": { - "properties": { - "label": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - } - } - }, - "genres": { - "properties": { - "label": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - }, - "subjects": { - "properties": { - "label": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - } - } - } - } - }, - "filterableValues": { - "properties": { - "locations.license.id": { - "type": "keyword" - }, - "source.contributors.agent.label": { - "type": "keyword" - }, - "source.genres.label": { - "type": "keyword" - }, - "source.genres.concepts.id": { - "type": "keyword" - }, - "source.subjects.label": { - "type": "keyword" - }, - "source.production.dates.range.from": { - "type": "date" - } - } - }, - "vectorValues": { - "properties": { - "features1": { - "type": "dense_vector", - "dims": 2048 - }, - "features2": { - "type": "dense_vector", - "dims": 2048 - }, - "paletteEmbedding": { - "type": "dense_vector", - "dims": 1000, - "index": true, - "similarity": "dot_product" - }, - "reducedFeatures": { - "type": "dense_vector", - "dims": 1024, - "index": true, - "similarity": "dot_product" - } - } - }, - "debug": { - "dynamic": "false", - "properties": { - "indexedTime": { - "type": "date" - } - } - }, - "display": { - "type": "object", - "enabled": false - }, - "modifiedTime": { - "type": "date" - }, - "query": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase" - }, - "source": { - "properties": { - "alternativeTitles": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - } - } - }, - "collectionPath": { - "properties": { - "label": { - "type": "keyword", - "normalizer": "lowercase", - "fields": { - "path": { - "type": "text", - "analyzer": "path_analyzer", - "search_analyzer": "whitespace" - } - } - }, - "path": { - "type": "keyword", - "normalizer": "lowercase", - "fields": { - "path": { - "type": "text", - "analyzer": "path_analyzer", - "search_analyzer": "whitespace" - } - } - } - } - }, - "contributors.agent.label": { - "type": "text", - "analyzer": "english" - }, - "description": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "edition": { - "type": "text", - "analyzer": "english" - }, - "genres.concepts.label": { - "type": "text", - "analyzer": "english" - }, - "id": { - "type": "keyword", - "normalizer": "lowercase" - }, - "sourceIdentifier.value": { - "type": "keyword", - "normalizer": "lowercase" - }, - "identifiers.value": { - "type": "keyword", - "normalizer": "lowercase" - }, - "images": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase" - }, - "identifiers.value": { - "type": "keyword", - "normalizer": "lowercase" - } - } - }, - "items": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase" - }, - "identifiers.value": { - "type": "keyword", - "normalizer": "lowercase" - } - } - }, - "languages.label": { - "type": "text", - "analyzer": "lowercase" - }, - "lettering": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - } - } - }, - "notes.contents": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "partOf.title": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "physicalDescription": { - "type": "text", - "analyzer": "english" - }, - "production.label": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "referenceNumber": { - "type": "keyword", - "normalizer": "lowercase", - "fields": { - "path": { - "type": "text", - "analyzer": "path_analyzer", - "search_analyzer": "whitespace" - } - } - }, - "subjects.concepts.label": { - "type": "text", - "analyzer": "english" - }, - "title": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "english_without_shingles": { - "type": "text", - "analyzer": "english_without_shingles" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - } - } - } - } - } - } -} diff --git a/index_config/mappings.works_indexed.2023-11-09.json b/index_config/mappings.works_indexed.2023-11-09.json deleted file mode 100644 index d7ea679db2..0000000000 --- a/index_config/mappings.works_indexed.2023-11-09.json +++ /dev/null @@ -1,618 +0,0 @@ -{ - "dynamic": "strict", - "properties": { - "aggregatableValues": { - "properties": { - "availabilities": { - "eager_global_ordinals": true, - "type": "keyword" - }, - "contributors": { - "properties": { - "agent": { - "properties": { - "label": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - } - } - }, - "genres": { - "properties": { - "label": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - }, - "items": { - "properties": { - "locations": { - "properties": { - "license": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - } - } - }, - "languages": { - "eager_global_ordinals": true, - "type": "keyword" - }, - "production": { - "properties": { - "dates": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - }, - "subjects": { - "properties": { - "label": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - }, - "workType": { - "eager_global_ordinals": true, - "type": "keyword" - } - } - }, - "filterableValues": { - "properties": { - "format.id": { - "type": "keyword" - }, - "workType": { - "type": "keyword" - }, - "production.dates.range.from": { - "type": "date" - }, - "languages.id": { - "type": "keyword" - }, - "genres.label": { - "type": "keyword" - }, - "genres.concepts.id": { - "type": "keyword" - }, - "subjects.label": { - "type": "keyword" - }, - "contributors.agent.label": { - "type": "keyword" - }, - "identifiers.value": { - "type": "keyword" - }, - "items.locations.license.id": { - "type": "keyword" - }, - "items.locations.accessConditions.status.id": { - "type": "keyword" - }, - "items.id": { - "type": "keyword" - }, - "items.identifiers.value": { - "type": "keyword" - }, - "items.locations.locationType.id": { - "type": "keyword" - }, - "partOf.id": { - "type": "keyword" - }, - "partOf.title": { - "type": "keyword" - }, - "availabilities.id": { - "type": "keyword" - } - } - }, - "debug": { - "dynamic": "false", - "properties": { - "indexedTime": { - "type": "date" - } - } - }, - "display": { - "type": "object", - "enabled": false - }, - "query": { - "properties": { - "collectionPath": { - "properties": { - "label": { - "type": "keyword", - "normalizer": "lowercase", - "fields": { - "path": { - "type": "text", - "analyzer": "path_analyzer", - "search_analyzer": "lowercase_whitespace_tokens" - } - } - }, - "path": { - "type": "keyword", - "normalizer": "lowercase", - "fields": { - "path": { - "type": "text", - "analyzer": "path_analyzer", - "search_analyzer": "lowercase_whitespace_tokens" - } - } - } - } - }, - "alternativeTitles": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - } - } - }, - "contributors.agent.label": { - "type": "text", - "analyzer": "english" - }, - "description": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "edition": { - "type": "text", - "analyzer": "english" - }, - "genres.concepts.label": { - "type": "text", - "analyzer": "english" - }, - "id": { - "type": "keyword", - "normalizer": "lowercase" - }, - "sourceIdentifier.value": { - "type": "keyword", - "normalizer": "lowercase" - }, - "identifiers.value": { - "type": "keyword", - "normalizer": "lowercase" - }, - "images.id": { - "type": "keyword", - "normalizer": "lowercase" - }, - "images.identifiers.value": { - "type": "text", - "analyzer": "lowercase" - }, - "items.id": { - "type": "keyword", - "normalizer": "lowercase" - }, - "items.identifiers.value": { - "type": "keyword", - "normalizer": "lowercase" - }, - "languages.label": { - "type": "text", - "analyzer": "lowercase" - }, - "lettering": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - } - } - }, - "notes.contents": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "partOf.title": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "physicalDescription": { - "type": "text", - "analyzer": "english" - }, - "production.label": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - } - } - }, - "referenceNumber": { - "type": "keyword", - "normalizer": "lowercase", - "fields": { - "path": { - "type": "text", - "analyzer": "path_analyzer", - "search_analyzer": "lowercase_whitespace_tokens" - } - } - }, - "subjects.concepts.label": { - "type": "text", - "analyzer": "english" - }, - "title": { - "type": "text", - "analyzer": "lowercase", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic" - }, - "bengali": { - "type": "text", - "analyzer": "bengali" - }, - "english": { - "type": "text", - "analyzer": "english" - }, - "english_without_shingles": { - "type": "text", - "analyzer": "english_without_shingles" - }, - "french": { - "type": "text", - "analyzer": "french" - }, - "german": { - "type": "text", - "analyzer": "german" - }, - "hindi": { - "type": "text", - "analyzer": "hindi" - }, - "italian": { - "type": "text", - "analyzer": "italian" - }, - "persian": { - "type": "text", - "analyzer": "persian" - }, - "spanish": { - "type": "text", - "analyzer": "spanish" - }, - "swappable_characters": { - "type": "text", - "analyzer": "swappable_characters" - }, - "cased": { - "type": "text", - "analyzer": "cased" - }, - "base": { - "type": "text", - "analyzer": "base" - }, - "normalized_whole_phrase": { - "type": "text", - "analyzer": "normalized_whole_phrase" - } - } - } - } - }, - "redirectTarget": { - "type": "object", - "dynamic": "false" - }, - "type": { - "type": "keyword" - } - } -} From bd5dae1d64b46f118fe932f0d91163fd6c919896 Mon Sep 17 00:00:00 2001 From: jamie Date: Tue, 30 Apr 2024 15:47:37 +0100 Subject: [PATCH 2/4] Add new index config --- .../analysis.works_indexed.2024-04-30.json | 371 ++++++++ .../mappings.works_indexed.2024-04-30.json | 789 ++++++++++++++++++ 2 files changed, 1160 insertions(+) create mode 100644 index_config/analysis.works_indexed.2024-04-30.json create mode 100644 index_config/mappings.works_indexed.2024-04-30.json diff --git a/index_config/analysis.works_indexed.2024-04-30.json b/index_config/analysis.works_indexed.2024-04-30.json new file mode 100644 index 0000000000..c751e73aa2 --- /dev/null +++ b/index_config/analysis.works_indexed.2024-04-30.json @@ -0,0 +1,371 @@ +{ + "filter": { + "pattern_replace_g_j": { + "pattern": "g", + "type": "pattern_replace", + "replacement": "j" + }, + "pattern_replace_j_i": { + "pattern": "j", + "type": "pattern_replace", + "replacement": "i" + }, + "french_elision": { + "type": "elision", + "articles": [ + "l", + "m", + "t", + "qu", + "n", + "s", + "j", + "d", + "c", + "jusqu", + "quoiqu", + "lorsqu", + "puisqu" + ], + "articles_case": "true" + }, + "pattern_replace_uu_w": { + "pattern": "uu", + "type": "pattern_replace", + "replacement": "w" + }, + "pattern_replace_vv_w": { + "pattern": "vv", + "type": "pattern_replace", + "replacement": "w" + }, + "hindi_stemmer": { + "type": "stemmer", + "language": "hindi" + }, + "pattern_replace_v_u": { + "pattern": "v", + "type": "pattern_replace", + "replacement": "u" + }, + "german_stemmer": { + "type": "stemmer", + "language": "light_german" + }, + "english_stemmer": { + "type": "stemmer", + "language": "english" + }, + "italian_elision": { + "type": "elision", + "articles": [ + "c", + "l", + "all", + "dall", + "dell", + "nell", + "sull", + "coll", + "pell", + "gl", + "agl", + "dagl", + "degl", + "negl", + "sugl", + "un", + "m", + "t", + "s", + "v", + "d" + ], + "articles_case": "true" + }, + "asciifolding": { + "type": "asciifolding" + }, + "possessive_english": { + "type": "stemmer", + "language": "possessive_english" + }, + "spanish_stemmer": { + "type": "stemmer", + "language": "light_spanish" + }, + "arabic_stemmer": { + "type": "stemmer", + "language": "arabic" + }, + "french_stemmer": { + "type": "stemmer", + "language": "light_french" + }, + "italian_stemmer": { + "type": "stemmer", + "language": "light_italian" + }, + "word_delimiter": { + "type": "word_delimiter_graph", + "preserve_original": "true" + }, + "bengali_stemmer": { + "type": "stemmer", + "language": "bengali" + }, + "long_query_token_limiter": { + "type": "limit", + "max_token_count": 75 + } + }, + "analyzer": { + "german": { + "filter": [ + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "german_normalization", + "german_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "spanish": { + "filter": [ + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "spanish_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "swappable_characters": { + "filter": [ + "word_delimiter", + "long_query_token_limiter", + "asciifolding", + "lowercase", + "pattern_replace_vv_w", + "pattern_replace_uu_w", + "pattern_replace_v_u", + "pattern_replace_j_i", + "pattern_replace_g_j" + ], + "char_filter": [ + "slash_remover" + ], + "type": "custom", + "tokenizer": "whitespace" + }, + "lowercase": { + "filter": [ + "asciifolding", + "word_delimiter", + "lowercase" + ], + "char_filter": [ + "slash_remover" + ], + "type": "custom", + "tokenizer": "whitespace" + }, + "lowercase_token_limited": { + "filter": [ + "asciifolding", + "word_delimiter", + "long_query_token_limiter", + "lowercase" + ], + "char_filter": [ + "slash_remover" + ], + "type": "custom", + "tokenizer": "whitespace" + }, + "italian": { + "filter": [ + "italian_elision", + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "italian_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "lowercase_whitespace_tokens": { + "filter": [ + "lowercase" + ], + "type": "custom", + "tokenizer": "whitespace" + }, + "path_analyzer": { + "filter": [ + "asciifolding", + "lowercase" + ], + "type": "custom", + "tokenizer": "path_hierarchy" + }, + "persian": { + "filter": [ + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "decimal_digit", + "arabic_normalization", + "persian_normalization" + ], + "char_filter": [ + "zero_width_spaces", + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "cased": { + "filter": [ + "asciifolding", + "word_delimiter", + "long_query_token_limiter" + ], + "char_filter": [ + "slash_remover" + ], + "type": "custom", + "tokenizer": "whitespace" + }, + "arabic": { + "filter": [ + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "decimal_digit", + "arabic_normalization", + "arabic_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "bengali": { + "filter": [ + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "decimal_digit", + "indic_normalization", + "bengali_normalization", + "bengali_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "english": { + "filter": [ + "possessive_english", + "asciifolding", + "word_delimiter", + "lowercase", + "english_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "english_token_limited": { + "filter": [ + "possessive_english", + "asciifolding", + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "english_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "hindi": { + "filter": [ + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "decimal_digit", + "indic_normalization", + "hindi_normalization", + "hindi_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "french": { + "filter": [ + "french_elision", + "word_delimiter", + "long_query_token_limiter", + "lowercase", + "french_stemmer" + ], + "char_filter": [ + "slash_remover" + ], + "tokenizer": "whitespace" + }, + "base": { + "filter": [ + "word_delimiter", + "long_query_token_limiter" + ], + "char_filter": [ + "slash_remover" + ], + "type": "custom", + "tokenizer": "whitespace" + }, + "normalized_whole_phrase": { + "filter": [ + "asciifolding", + "lowercase" + ], + "char_filter": [ + "remove_punctuation" + ], + "tokenizer": "keyword" + } + }, + "char_filter": { + "slash_remover": { + "pattern": "/", + "type": "pattern_replace", + "replacement": "" + }, + "remove_punctuation": { + "pattern": "[^\\p{L}\\p{Nd}\\s]", + "_name": "Removes non-letter, non-numeric, and non-whitespace characters. Respects other character sets.", + "type": "pattern_replace", + "replacement": "" + }, + "zero_width_spaces": { + "type": "mapping", + "mappings": [ + "\\u200C=>\\u0020" + ] + } + } +} diff --git a/index_config/mappings.works_indexed.2024-04-30.json b/index_config/mappings.works_indexed.2024-04-30.json new file mode 100644 index 0000000000..312912af84 --- /dev/null +++ b/index_config/mappings.works_indexed.2024-04-30.json @@ -0,0 +1,789 @@ +{ + "dynamic": "strict", + "properties": { + "aggregatableValues": { + "properties": { + "availabilities": { + "type": "keyword", + "eager_global_ordinals": true + }, + "contributors": { + "properties": { + "agent": { + "properties": { + "label": { + "type": "keyword", + "eager_global_ordinals": true + } + } + } + } + }, + "genres": { + "properties": { + "label": { + "type": "keyword", + "eager_global_ordinals": true + } + } + }, + "items": { + "properties": { + "locations": { + "properties": { + "license": { + "type": "keyword", + "eager_global_ordinals": true + } + } + } + } + }, + "languages": { + "type": "keyword", + "eager_global_ordinals": true + }, + "production": { + "properties": { + "dates": { + "type": "keyword", + "eager_global_ordinals": true + } + } + }, + "subjects": { + "properties": { + "label": { + "type": "keyword", + "eager_global_ordinals": true + } + } + }, + "workType": { + "type": "keyword", + "eager_global_ordinals": true + } + } + }, + "debug": { + "dynamic": "false", + "properties": { + "indexedTime": { + "type": "date" + }, + "mergeCandidates": { + "properties": { + "id": { + "properties": { + "canonicalId": { + "type": "keyword" + } + } + } + } + } + } + }, + "display": { + "type": "object", + "enabled": false + }, + "filterableValues": { + "properties": { + "availabilities": { + "properties": { + "id": { + "type": "keyword" + } + } + }, + "contributors": { + "properties": { + "agent": { + "properties": { + "label": { + "type": "keyword" + } + } + } + } + }, + "format": { + "properties": { + "id": { + "type": "keyword" + } + } + }, + "genres": { + "properties": { + "concepts": { + "properties": { + "id": { + "type": "keyword" + } + } + }, + "label": { + "type": "keyword" + } + } + }, + "identifiers": { + "properties": { + "value": { + "type": "keyword" + } + } + }, + "items": { + "properties": { + "id": { + "type": "keyword" + }, + "identifiers": { + "properties": { + "value": { + "type": "keyword" + } + } + }, + "locations": { + "properties": { + "accessConditions": { + "properties": { + "status": { + "properties": { + "id": { + "type": "keyword" + } + } + } + } + }, + "license": { + "properties": { + "id": { + "type": "keyword" + } + } + }, + "locationType": { + "properties": { + "id": { + "type": "keyword" + } + } + } + } + } + } + }, + "languages": { + "properties": { + "id": { + "type": "keyword" + } + } + }, + "partOf": { + "properties": { + "id": { + "type": "keyword" + }, + "title": { + "type": "keyword" + } + } + }, + "production": { + "properties": { + "dates": { + "properties": { + "range": { + "properties": { + "from": { + "type": "date" + } + } + } + } + } + } + }, + "subjects": { + "properties": { + "label": { + "type": "keyword" + } + } + }, + "workType": { + "type": "keyword" + } + } + }, + "query": { + "properties": { + "alternativeTitles": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "collectionPath": { + "properties": { + "label": { + "type": "keyword", + "normalizer": "lowercase", + "fields": { + "path": { + "type": "text", + "analyzer": "path_analyzer", + "search_analyzer": "lowercase_whitespace_tokens" + } + } + }, + "path": { + "type": "keyword", + "normalizer": "lowercase", + "fields": { + "path": { + "type": "text", + "analyzer": "path_analyzer", + "search_analyzer": "lowercase_whitespace_tokens" + } + } + } + } + }, + "contributors": { + "properties": { + "agent": { + "properties": { + "label": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + } + } + } + } + }, + "description": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "edition": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "genres": { + "properties": { + "concepts": { + "properties": { + "label": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + } + } + } + } + }, + "id": { + "type": "keyword", + "normalizer": "lowercase" + }, + "identifiers": { + "properties": { + "value": { + "type": "keyword", + "normalizer": "lowercase" + } + } + }, + "images": { + "properties": { + "id": { + "type": "keyword", + "normalizer": "lowercase" + }, + "identifiers": { + "properties": { + "value": { + "type": "keyword", + "normalizer": "lowercase" + } + } + } + } + }, + "items": { + "properties": { + "id": { + "type": "keyword", + "normalizer": "lowercase" + }, + "identifiers": { + "properties": { + "value": { + "type": "keyword", + "normalizer": "lowercase" + } + } + } + } + }, + "languages": { + "properties": { + "label": { + "type": "text", + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + } + } + }, + "lettering": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "notes": { + "properties": { + "contents": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + } + } + }, + "partOf": { + "properties": { + "title": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + } + } + }, + "physicalDescription": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "production": { + "properties": { + "label": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + } + } + }, + "referenceNumber": { + "type": "keyword", + "normalizer": "lowercase", + "fields": { + "path": { + "type": "text", + "analyzer": "path_analyzer", + "search_analyzer": "lowercase_whitespace_tokens" + } + } + }, + "sourceIdentifier": { + "properties": { + "value": { + "type": "keyword", + "normalizer": "lowercase" + } + } + }, + "subjects": { + "properties": { + "concepts": { + "properties": { + "label": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + } + } + } + } + }, + "title": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "normalized_whole_phrase": { + "type": "text", + "analyzer": "normalized_whole_phrase" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + } + } + }, + "redirectTarget": { + "type": "object", + "dynamic": "false" + }, + "type": { + "type": "keyword" + } + } +} From 0bfb882c8a1ee92d0b9919b7bc66776fe6f9e313 Mon Sep 17 00:00:00 2001 From: jamie Date: Tue, 30 Apr 2024 15:47:53 +0100 Subject: [PATCH 3/4] Remove defunct index config dupes --- .../main/resources/imagesIndexProperties.json | 605 ------------ .../src/test/resources/ImagesIndexConfig.json | 803 ---------------- .../src/test/resources/WorksIndexConfig.json | 880 ------------------ 3 files changed, 2288 deletions(-) delete mode 100644 common/internal_model/src/main/resources/imagesIndexProperties.json delete mode 100644 common/internal_model/src/test/resources/ImagesIndexConfig.json delete mode 100644 common/internal_model/src/test/resources/WorksIndexConfig.json diff --git a/common/internal_model/src/main/resources/imagesIndexProperties.json b/common/internal_model/src/main/resources/imagesIndexProperties.json deleted file mode 100644 index 13bf20d93f..0000000000 --- a/common/internal_model/src/main/resources/imagesIndexProperties.json +++ /dev/null @@ -1,605 +0,0 @@ -{ - "aggregatableValues": { - "properties": { - "locations": { - "properties": { - "license": { - "type": "keyword" - } - } - }, - "source": { - "properties": { - "contributors": { - "properties": { - "agent": { - "properties": { - "label": { - "type": "keyword" - } - } - } - } - }, - "genres": { - "properties": { - "label": { - "type": "keyword" - } - } - }, - "subjects": { - "properties": { - "label": { - "type": "keyword" - } - } - } - } - } - } - }, - "display": { - "type": "object", - "enabled": false - }, - "modifiedTime": { - "type": "date" - }, - "query": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "inferredData": { - "properties": { - "aspectRatio": { - "type": "float" - }, - "features1": { - "type": "dense_vector", - "dims": 2048 - }, - "features2": { - "type": "dense_vector", - "dims": 2048 - }, - "reducedFeatures": { - "type": "dense_vector", - "dims": 1024, - "index": true, - "similarity": "dot_product" - }, - "paletteEmbedding": { - "type": "dense_vector", - "dims": 1000, - "index": true, - "similarity": "dot_product" - }, - "averageColorHex": { - "type": "keyword" - } - } - }, - "locations": { - "properties": { - "license": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - }, - "source": { - "properties": { - "alternativeTitles": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - }, - "availabilities": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "collectionPath": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "cleanPath": { - "type": "text", - "analyzer": "clean_path_analyzer" - }, - "path": { - "type": "text", - "analyzer": "exact_path_analyzer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "path": { - "type": "text", - "fields": { - "clean": { - "type": "text", - "analyzer": "clean_path_analyzer" - }, - "keyword": { - "type": "keyword" - } - }, - "analyzer": "exact_path_analyzer" - } - } - }, - "contributors": { - "properties": { - "agent": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - } - } - }, - "description": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - } - } - }, - "edition": { - "type": "text" - }, - "genres": { - "properties": { - "concepts": { - "properties": { - "id": { - "type": "keyword" - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "type": { - "type": "keyword" - }, - "format": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "workType": { - "type": "keyword" - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - }, - "images": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - } - } - }, - "items": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - }, - "locations": { - "properties": { - "accessConditions": { - "properties": { - "status": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - }, - "license": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "locationType": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - } - } - }, - "languages": { - "properties": { - "id": { - "type": "keyword" - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "lettering": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - }, - "notes": { - "properties": { - "contents": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - } - } - } - } - }, - "partOf": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "title": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - } - } - }, - "physicalDescription": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "keyword": { - "type": "keyword" - } - } - }, - "production": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "dates": { - "properties": { - "range": { - "properties": { - "from": { - "type": "date" - } - } - } - } - } - } - }, - "referenceNumber": { - "type": "keyword" - }, - "subjects": { - "properties": { - "concepts": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - }, - "title": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - } - } - }, - "sourceIdentifier": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - } - } - }, - "debug": { - "dynamic": "false", - "properties": { - "indexedTime": { - "type": "date" - } - } - } -} diff --git a/common/internal_model/src/test/resources/ImagesIndexConfig.json b/common/internal_model/src/test/resources/ImagesIndexConfig.json deleted file mode 100644 index bc352c2453..0000000000 --- a/common/internal_model/src/test/resources/ImagesIndexConfig.json +++ /dev/null @@ -1,803 +0,0 @@ -{ - "mappings": { - "dynamic": "strict", - "properties": { - "aggregatableValues": { - "properties": { - "locations": { - "properties": { - "license": { - "type": "keyword" - } - } - }, - "source": { - "properties": { - "contributors": { - "properties": { - "agent": { - "properties": { - "label": { - "type": "keyword" - } - } - } - } - }, - "genres": { - "properties": { - "label": { - "type": "keyword" - } - } - }, - "subjects": { - "properties": { - "label": { - "type": "keyword" - } - } - } - } - } - } - }, - "display": { - "type": "object", - "enabled": false - }, - "modifiedTime": { - "type": "date" - }, - "query": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "inferredData": { - "properties": { - "aspectRatio": { - "type": "float" - }, - "features1": { - "type": "dense_vector", - "dims": 2048 - }, - "features2": { - "type": "dense_vector", - "dims": 2048 - }, - "reducedFeatures": { - "type": "dense_vector", - "dims": 1024, - "index": true, - "similarity": "dot_product" - }, - "paletteEmbedding": { - "type": "dense_vector", - "dims": 1000, - "index": true, - "similarity": "dot_product" - }, - "averageColorHex": { - "type": "keyword" - } - } - }, - "locations": { - "properties": { - "license": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - }, - "source": { - "properties": { - "alternativeTitles": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - }, - "availabilities": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "collectionPath": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "cleanPath": { - "type": "text", - "analyzer": "clean_path_analyzer" - }, - "path": { - "type": "text", - "analyzer": "exact_path_analyzer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "path": { - "type": "text", - "fields": { - "clean": { - "type": "text", - "analyzer": "clean_path_analyzer" - }, - "keyword": { - "type": "keyword" - } - }, - "analyzer": "exact_path_analyzer" - } - } - }, - "contributors": { - "properties": { - "agent": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - } - } - }, - "description": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - } - } - }, - "edition": { - "type": "text" - }, - "genres": { - "properties": { - "concepts": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "id": { - "type": "keyword" - } - } - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "type": { - "type": "keyword" - }, - "format": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "workType": { - "type": "keyword" - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - }, - "images": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - } - } - }, - "items": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - }, - "locations": { - "properties": { - "accessConditions": { - "properties": { - "status": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - }, - "license": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "locationType": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - } - } - }, - "languages": { - "properties": { - "id": { - "type": "keyword" - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "lettering": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - }, - "notes": { - "properties": { - "contents": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - } - } - } - } - }, - "partOf": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "title": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - } - } - }, - "physicalDescription": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "keyword": { - "type": "keyword" - } - } - }, - "production": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "dates": { - "properties": { - "range": { - "properties": { - "from": { - "type": "date" - } - } - } - } - } - } - }, - "referenceNumber": { - "type": "keyword" - }, - "subjects": { - "properties": { - "concepts": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - }, - "title": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - } - } - } - } - }, - "sourceIdentifier": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - } - } - } - }, - "debug": { - "dynamic": "false", - "properties": { - "indexedTime": { - "type": "date" - } - } - } - } - }, - "settings": { - "index": { - "analysis": { - "filter": { - "punctuation": { - "type": "pattern_replace", - "pattern": "[^0-9\\p{L}\\s]", - "replacement": "" - }, - "english_stemmer": { - "name": "english", - "type": "stemmer" - }, - "shingle_token_filter": { - "max_shingle_size": "4", - "min_shingle_size": "2", - "type": "shingle" - }, - "hindi_stemmer": { - "name": "hindi", - "type": "stemmer" - }, - "arabic_stemmer": { - "name": "arabic", - "type": "stemmer" - }, - "english_possessive_stemmer": { - "name": "possessive_english", - "type": "stemmer" - }, - "french_stemmer": { - "name": "french", - "type": "stemmer" - }, - "italian_stemmer": { - "name": "italian", - "type": "stemmer" - }, - "german_stemmer": { - "name": "german", - "type": "stemmer" - }, - "asciifolding_token_filter": { - "type": "asciifolding", - "preserve_original": "true" - }, - "bengali_stemmer": { - "name": "bengali", - "type": "stemmer" - } - }, - "char_filter": { - "slashes_char_filter": { - "type": "mapping", - "mappings": [ - "/=> __" - ] - } - }, - "normalizer": { - "lowercase_normalizer": { - "filter": [ - "lowercase" - ], - "type": "custom" - } - }, - "analyzer": { - "hindi_analyzer": { - "filter": [ - "lowercase", - "hindi_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "asciifolding_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "exact_path_analyzer": { - "type": "custom", - "tokenizer": "path_hierarchy" - }, - "arabic_analyzer": { - "filter": [ - "lowercase", - "arabic_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "english_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter", - "english_stemmer", - "english_possessive_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "english_cased_analyzer": { - "filter": [ - "asciifolding_token_filter", - "english_stemmer", - "english_possessive_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "bengali_analyzer": { - "filter": [ - "lowercase", - "bengali_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "german_analyzer": { - "filter": [ - "lowercase", - "german_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "slashes_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter" - ], - "char_filter": [ - "slashes_char_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "clean_path_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "path_hierarchy" - }, - "shingle_asciifolding_analyzer": { - "filter": [ - "lowercase", - "punctuation", - "shingle_token_filter", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "shingle_cased_analyzer": { - "filter": [ - "punctuation", - "shingle_token_filter", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "french_analyzer": { - "filter": [ - "lowercase", - "french_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "whitespace_analyzer": { - "type": "custom", - "tokenizer": "whitespace" - }, - "italian_analyzer": { - "filter": [ - "lowercase", - "italian_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - } - } - } - } - } -} diff --git a/common/internal_model/src/test/resources/WorksIndexConfig.json b/common/internal_model/src/test/resources/WorksIndexConfig.json deleted file mode 100644 index dfd7551546..0000000000 --- a/common/internal_model/src/test/resources/WorksIndexConfig.json +++ /dev/null @@ -1,880 +0,0 @@ -{ - "mappings": { - "dynamic": "strict", - "properties": { - "aggregatableValues": { - "properties": { - "availabilities": { - "type": "keyword" - }, - "contributors": { - "properties": { - "agent": { - "properties": { - "label": { - "type": "keyword" - } - } - } - } - }, - "genres": { - "properties": { - "label": { - "type": "keyword" - } - } - }, - "items": { - "properties": { - "locations": { - "properties": { - "license": { - "type": "keyword" - } - } - } - } - }, - "languages": { - "type": "keyword" - }, - "production": { - "properties": { - "dates": { - "type": "keyword" - } - } - }, - "subjects": { - "properties": { - "label": { - "type": "keyword" - } - } - }, - "workType": { - "type": "keyword" - } - } - }, - "debug": { - "dynamic": "false", - "properties": { - "indexedTime": { - "type": "date" - }, - "mergeCandidates.id.canonicalId": { - "type": "keyword" - } - } - }, - "display": { - "type": "object", - "enabled": false - }, - "query": { - "properties": { - "allIdentifiers": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "alternativeTitles": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "english_cased": { - "type": "text", - "analyzer": "english_cased_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - }, - "shingles_cased": { - "type": "text", - "analyzer": "shingle_cased_analyzer" - } - }, - "copy_to": [ - "query.titlesAndContributors" - ] - }, - "availabilities": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "collectionPath": { - "properties": { - "label": { - "type": "text", - "fields": { - "cleanPath": { - "type": "text", - "analyzer": "clean_path_analyzer" - }, - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "path": { - "type": "text", - "analyzer": "exact_path_analyzer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "path": { - "type": "text", - "fields": { - "clean": { - "type": "text", - "analyzer": "clean_path_analyzer" - }, - "keyword": { - "type": "keyword" - } - }, - "analyzer": "exact_path_analyzer" - } - } - }, - "contributors": { - "properties": { - "agent": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "copy_to": [ - "query.titlesAndContributors" - ], - "analyzer": "asciifolding_analyzer" - } - } - } - } - }, - "description": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - } - } - }, - "edition": { - "type": "text" - }, - "format": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "genres": { - "properties": { - "concepts": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - }, - "id": { - "type": "keyword" - } - } - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer", - "copy_to": [ - "query.allIdentifiers" - ] - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer", - "copy_to": [ - "query.allIdentifiers" - ] - } - } - }, - "images": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer", - "copy_to": [ - "query.allIdentifiers" - ] - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer", - "copy_to": [ - "query.allIdentifiers" - ] - } - } - } - } - }, - "items": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer", - "copy_to": [ - "query.allIdentifiers" - ] - }, - "identifiers": { - "properties": { - "value": { - "type": "keyword", - "normalizer": "lowercase_normalizer", - "copy_to": [ - "query.allIdentifiers" - ] - } - } - }, - "locations": { - "properties": { - "accessConditions": { - "properties": { - "status": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - }, - "license": { - "properties": { - "id": { - "type": "keyword" - } - } - }, - "locationType": { - "properties": { - "id": { - "type": "keyword" - } - } - } - } - } - } - }, - "languages": { - "properties": { - "id": { - "type": "keyword" - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "lettering": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "english_cased": { - "type": "text", - "analyzer": "english_cased_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - }, - "shingles_cased": { - "type": "text", - "analyzer": "shingle_cased_analyzer" - } - } - }, - "notes": { - "properties": { - "contents": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - } - } - } - } - }, - "partOf": { - "properties": { - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "title": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "english_cased": { - "type": "text", - "analyzer": "english_cased_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - }, - "shingles_cased": { - "type": "text", - "analyzer": "shingle_cased_analyzer" - } - } - } - } - }, - "physicalDescription": { - "type": "text", - "fields": { - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "keyword": { - "type": "keyword" - } - } - }, - "production": { - "properties": { - "dates": { - "properties": { - "range": { - "properties": { - "from": { - "type": "date" - } - } - } - } - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "referenceNumber": { - "type": "keyword", - "copy_to": [ - "query.allIdentifiers" - ] - }, - "subjects": { - "properties": { - "concepts": { - "properties": { - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "id": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "label": { - "type": "text", - "fields": { - "keyword": { - "type": "keyword" - }, - "lowercaseKeyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - } - }, - "analyzer": "asciifolding_analyzer" - } - } - }, - "title": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "english_cased": { - "type": "text", - "analyzer": "english_cased_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "keyword": { - "type": "keyword", - "normalizer": "lowercase_normalizer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - }, - "shingles_cased": { - "type": "text", - "analyzer": "shingle_cased_analyzer" - } - }, - "copy_to": [ - "query.titlesAndContributors" - ] - }, - "titlesAndContributors": { - "type": "text", - "fields": { - "arabic": { - "type": "text", - "analyzer": "arabic_analyzer" - }, - "bengali": { - "type": "text", - "analyzer": "bengali_analyzer" - }, - "english": { - "type": "text", - "analyzer": "english_analyzer" - }, - "french": { - "type": "text", - "analyzer": "french_analyzer" - }, - "german": { - "type": "text", - "analyzer": "german_analyzer" - }, - "hindi": { - "type": "text", - "analyzer": "hindi_analyzer" - }, - "italian": { - "type": "text", - "analyzer": "italian_analyzer" - }, - "shingles": { - "type": "text", - "analyzer": "shingle_asciifolding_analyzer" - }, - "english_cased": { - "type": "text", - "analyzer": "english_cased_analyzer" - }, - "shingles_cased": { - "type": "text", - "analyzer": "shingle_cased_analyzer" - } - } - }, - "type": { - "type": "keyword" - }, - "workType": { - "type": "keyword" - } - } - }, - "redirectTarget": { - "type": "object", - "dynamic": "false" - }, - "type": { - "type": "keyword" - } - } - }, - "settings": { - "index": { - "analysis": { - "filter": { - "punctuation": { - "type": "pattern_replace", - "pattern": "[^0-9\\p{L}\\s]", - "replacement": "" - }, - "english_stemmer": { - "name": "english", - "type": "stemmer" - }, - "shingle_token_filter": { - "max_shingle_size": "4", - "min_shingle_size": "2", - "type": "shingle" - }, - "hindi_stemmer": { - "name": "hindi", - "type": "stemmer" - }, - "arabic_stemmer": { - "name": "arabic", - "type": "stemmer" - }, - "english_possessive_stemmer": { - "name": "possessive_english", - "type": "stemmer" - }, - "french_stemmer": { - "name": "french", - "type": "stemmer" - }, - "italian_stemmer": { - "name": "italian", - "type": "stemmer" - }, - "german_stemmer": { - "name": "german", - "type": "stemmer" - }, - "asciifolding_token_filter": { - "type": "asciifolding", - "preserve_original": "true" - }, - "bengali_stemmer": { - "name": "bengali", - "type": "stemmer" - } - }, - "char_filter": { - "slashes_char_filter": { - "type": "mapping", - "mappings": [ - "/=> __" - ] - } - }, - "normalizer": { - "lowercase_normalizer": { - "filter": [ - "lowercase" - ], - "type": "custom" - } - }, - "analyzer": { - "hindi_analyzer": { - "filter": [ - "lowercase", - "hindi_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "asciifolding_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "exact_path_analyzer": { - "type": "custom", - "tokenizer": "path_hierarchy" - }, - "arabic_analyzer": { - "filter": [ - "lowercase", - "arabic_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "english_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter", - "english_stemmer", - "english_possessive_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "english_cased_analyzer": { - "filter": [ - "asciifolding_token_filter", - "english_stemmer", - "english_possessive_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "bengali_analyzer": { - "filter": [ - "lowercase", - "bengali_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "german_analyzer": { - "filter": [ - "lowercase", - "german_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "slashes_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter" - ], - "char_filter": [ - "slashes_char_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "clean_path_analyzer": { - "filter": [ - "lowercase", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "path_hierarchy" - }, - "shingle_asciifolding_analyzer": { - "filter": [ - "lowercase", - "punctuation", - "shingle_token_filter", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "shingle_cased_analyzer": { - "filter": [ - "punctuation", - "shingle_token_filter", - "asciifolding_token_filter" - ], - "type": "custom", - "tokenizer": "standard" - }, - "french_analyzer": { - "filter": [ - "lowercase", - "french_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - }, - "whitespace_analyzer": { - "type": "custom", - "tokenizer": "whitespace" - }, - "italian_analyzer": { - "filter": [ - "lowercase", - "italian_stemmer" - ], - "type": "custom", - "tokenizer": "standard" - } - } - } - } - } -} From 3862de0e33a5a68709c863713210149b8a53a4d9 Mon Sep 17 00:00:00 2001 From: jamie Date: Wed, 1 May 2024 11:57:01 +0100 Subject: [PATCH 4/4] Need to update images config too --- .../fixtures/index/ImagesIndexFixtures.scala | 2 +- .../fixtures/index/WorksIndexFixtures.scala | 4 +- .../mappings.images_indexed.2024-04-30.json | 617 ++++++++++++++++++ 3 files changed, 620 insertions(+), 3 deletions(-) create mode 100644 index_config/mappings.images_indexed.2024-04-30.json diff --git a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala index 17576f171d..d2d5b27ac7 100644 --- a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala +++ b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/ImagesIndexFixtures.scala @@ -13,7 +13,7 @@ trait ImagesIndexFixtures extends IndexFixturesBase { withLocalElasticSearchIndex[R](config = getConfig( mappings = "mappings.images_indexed.2024-01-09.json", - analysis = "analysis.works_indexed.2024-01-09.json" + analysis = "analysis.works_indexed.2024-04-30.json" ) ) } diff --git a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala index 58810ef9a8..c24fcdf3aa 100644 --- a/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala +++ b/common/internal_model/src/test/scala/weco/catalogue/internal_model/fixtures/index/WorksIndexFixtures.scala @@ -31,8 +31,8 @@ trait WorksIndexFixtures extends IndexFixturesBase { def withLocalWorksIndex[R]: Fixture[Index, R] = { withLocalElasticSearchIndex[R](config = getConfig( - mappings = "mappings.works_indexed.2024-01-09.json", - analysis = "analysis.works_indexed.2024-01-09.json" + mappings = "mappings.works_indexed.2024-04-30.json", + analysis = "analysis.works_indexed.2024-04-30.json" ) ) } diff --git a/index_config/mappings.images_indexed.2024-04-30.json b/index_config/mappings.images_indexed.2024-04-30.json new file mode 100644 index 0000000000..bb1843d7b7 --- /dev/null +++ b/index_config/mappings.images_indexed.2024-04-30.json @@ -0,0 +1,617 @@ +{ + "dynamic": "strict", + "properties": { + "aggregatableValues": { + "properties": { + "locations": { + "properties": { + "license": { + "eager_global_ordinals": true, + "type": "keyword" + } + } + }, + "source": { + "properties": { + "contributors": { + "properties": { + "agent": { + "properties": { + "label": { + "eager_global_ordinals": true, + "type": "keyword" + } + } + } + } + }, + "genres": { + "properties": { + "label": { + "eager_global_ordinals": true, + "type": "keyword" + } + } + }, + "subjects": { + "properties": { + "label": { + "eager_global_ordinals": true, + "type": "keyword" + } + } + } + } + } + } + }, + "filterableValues": { + "properties": { + "locations.license.id": { + "type": "keyword" + }, + "source.contributors.agent.label": { + "type": "keyword" + }, + "source.genres.label": { + "type": "keyword" + }, + "source.genres.concepts.id": { + "type": "keyword" + }, + "source.subjects.label": { + "type": "keyword" + }, + "source.production.dates.range.from": { + "type": "date" + } + } + }, + "vectorValues": { + "properties": { + "features1": { + "type": "dense_vector", + "dims": 2048 + }, + "features2": { + "type": "dense_vector", + "dims": 2048 + }, + "paletteEmbedding": { + "type": "dense_vector", + "dims": 1000, + "index": true, + "similarity": "dot_product" + }, + "reducedFeatures": { + "type": "dense_vector", + "dims": 1024, + "index": true, + "similarity": "dot_product" + } + } + }, + "debug": { + "dynamic": "false", + "properties": { + "indexedTime": { + "type": "date" + } + } + }, + "display": { + "type": "object", + "enabled": false + }, + "modifiedTime": { + "type": "date" + }, + "query": { + "properties": { + "id": { + "type": "keyword", + "normalizer": "lowercase" + }, + "source": { + "properties": { + "alternativeTitles": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "collectionPath": { + "properties": { + "label": { + "type": "keyword", + "normalizer": "lowercase", + "fields": { + "path": { + "type": "text", + "analyzer": "path_analyzer", + "search_analyzer": "lowercase_whitespace_tokens" + } + } + }, + "path": { + "type": "keyword", + "normalizer": "lowercase", + "fields": { + "path": { + "type": "text", + "analyzer": "path_analyzer", + "search_analyzer": "lowercase_whitespace_tokens" + } + } + } + } + }, + "contributors.agent.label": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "description": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "edition": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "genres.concepts.label": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "id": { + "type": "keyword", + "normalizer": "lowercase" + }, + "sourceIdentifier.value": { + "type": "keyword", + "normalizer": "lowercase" + }, + "identifiers.value": { + "type": "keyword", + "normalizer": "lowercase" + }, + "images": { + "properties": { + "id": { + "type": "keyword", + "normalizer": "lowercase" + }, + "identifiers.value": { + "type": "keyword", + "normalizer": "lowercase" + } + } + }, + "items": { + "properties": { + "id": { + "type": "keyword", + "normalizer": "lowercase" + }, + "identifiers.value": { + "type": "keyword", + "normalizer": "lowercase" + } + } + }, + "languages.label": { + "type": "text", + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "lettering": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "notes.contents": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "partOf.title": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "physicalDescription": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "production.label": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + }, + "referenceNumber": { + "type": "keyword", + "normalizer": "lowercase", + "fields": { + "path": { + "type": "text", + "analyzer": "path_analyzer", + "search_analyzer": "lowercase_whitespace_tokens" + } + } + }, + "subjects.concepts.label": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "title": { + "type": "text", + "fields": { + "arabic": { + "type": "text", + "analyzer": "arabic" + }, + "base": { + "type": "text", + "analyzer": "base" + }, + "bengali": { + "type": "text", + "analyzer": "bengali" + }, + "cased": { + "type": "text", + "analyzer": "cased" + }, + "english": { + "type": "text", + "analyzer": "english", + "search_analyzer": "english_token_limited" + }, + "french": { + "type": "text", + "analyzer": "french" + }, + "german": { + "type": "text", + "analyzer": "german" + }, + "hindi": { + "type": "text", + "analyzer": "hindi" + }, + "italian": { + "type": "text", + "analyzer": "italian" + }, + "normalized_whole_phrase": { + "type": "text", + "analyzer": "normalized_whole_phrase" + }, + "persian": { + "type": "text", + "analyzer": "persian" + }, + "spanish": { + "type": "text", + "analyzer": "spanish" + }, + "swappable_characters": { + "type": "text", + "analyzer": "swappable_characters" + } + }, + "analyzer": "lowercase", + "search_analyzer": "lowercase_token_limited" + } + } + } + } + } + } +}