@elastic/schemas 0.4.4 → 0.4.5

package/src/es/json/_types.analysis.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","$defs":{"_types.analysis__StopWords":{"oneOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopWordLanguage"},{"type":"array","items":{"type":"string"}}],"description":"Language value, such as _arabic_ or _thai_. Defaults to _english_.\nEach language value corresponds to a predefined list of stop words in Lucene. See Stop words by language for supported language values and their stop words.\nAlso accepts an array of stop words."},"_types.analysis__StopWordLanguage":{"enum":["_arabic_","_armenian_","_basque_","_bengali_","_brazilian_","_bulgarian_","_catalan_","_cjk_","_czech_","_danish_","_dutch_","_english_","_estonian_","_finnish_","_french_","_galician_","_german_","_greek_","_hindi_","_hungarian_","_indonesian_","_irish_","_italian_","_latvian_","_lithuanian_","_norwegian_","_persian_","_portuguese_","_romanian_","_russian_","_serbian_","_sorani_","_spanish_","_swedish_","_thai_","_turkish_","_none_"]},"_types.analysis__IcuCollationStrength":{"enum":["primary","secondary","tertiary","quaternary","identical"]},"_types.analysis__IcuCollationDecomposition":{"enum":["no","identical"]},"_types.analysis__IcuCollationAlternate":{"enum":["shifted","non-ignorable"]},"_types.analysis__IcuCollationCaseFirst":{"enum":["lower","upper"]},"_types.analysis__CharFilter":{"oneOf":[{"type":"string"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CharFilterDefinition"}]},"_types.analysis__CharFilterDefinition":{"oneOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HtmlStripCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__MappingCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternReplaceCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiIterationMarkCharFilter"}]},"_types.analysis__HtmlStripCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"html_strip"},"escaped_tags":{"type":"array","items":{"type":"string"}}},"required":["type"]},"_types.analysis__MappingCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"mapping"},"mappings":{"type":"array","items":{"type":"string"}},"mappings_path":{"type":"string"}},"required":["type"]},"_types.analysis__PatternReplaceCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern_replace"},"flags":{"type":"string"},"pattern":{"type":"string"},"replacement":{"type":"string"}},"required":["type","pattern"]},"_types.analysis__IcuNormalizationCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_normalizer"},"mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationMode"},"name":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationType"},"unicode_set_filter":{"type":"string"}},"required":["type"]},"_types.analysis__IcuNormalizationMode":{"enum":["decompose","compose"]},"_types.analysis__IcuNormalizationType":{"enum":["nfc","nfkc","nfkc_cf"]},"_types.analysis__KuromojiIterationMarkCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_iteration_mark"},"normalize_kana":{"type":"boolean"},"normalize_kanji":{"type":"boolean"}},"required":["type","normalize_kana","normalize_kanji"]},"_types.analysis__TokenFilter":{"oneOf":[{"type":"string"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenFilterDefinition"}]},"_types.analysis__TokenFilterDefinition":{"oneOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ApostropheTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ArabicStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ArabicNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__AsciiFoldingTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__BengaliNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__BrazilianStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CjkBigramTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CjkWidthTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ClassicTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CommonGramsTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ConditionTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CzechStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DecimalDigitTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DelimitedPayloadTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DutchStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__EdgeNGramTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ElisionTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__FingerprintTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__FlattenGraphTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__FrenchStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__GermanNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__GermanStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HindiNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HunspellTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HyphenationDecompounderTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IndicNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeepTypesTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeepWordsTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeywordMarkerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeywordRepeatTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LengthTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LimitTokenCountTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LowercaseTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__MinHashTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__MultiplexerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NGramTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NoriPartOfSpeechTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternCaptureTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternReplaceTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PersianNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PersianStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PorterStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PredicateTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__RemoveDuplicatesTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ReverseTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__RussianStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ScandinavianFoldingTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ScandinavianNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SerbianNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ShingleTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SnowballTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SoraniNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StemmerOverrideTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StemmerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymGraphTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TrimTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TruncateTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__UniqueTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__UppercaseTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__WordDelimiterGraphTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__WordDelimiterTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__JaStopTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiStemmerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiReadingFormTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiPartOfSpeechTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuFoldingTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuTransformTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DictionaryDecompounderTokenFilter"}]},"_types.analysis__ApostropheTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"apostrophe"}},"required":["type"]},"_types.analysis__ArabicStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"arabic_stem"}},"required":["type"]},"_types.analysis__ArabicNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"arabic_normalization"}},"required":["type"]},"_types.analysis__AsciiFoldingTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"asciifolding"},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, emit both original tokens and folded tokens. Defaults to `false`."}},"required":["type"]},"_types.analysis__BengaliNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"bengali_normalization"}},"required":["type"]},"_types.analysis__BrazilianStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"brazilian_stem"}},"required":["type"]},"_types.analysis__CjkBigramTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"cjk_bigram"},"ignored_scripts":{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CjkBigramIgnoredScript"},"description":"Array of character scripts for which to disable bigrams."},"output_unigrams":{"type":"boolean","description":"If `true`, emit tokens in both bigram and unigram form. If `false`, a CJK character is output in unigram form when it has no adjacent characters. Defaults to `false`."}},"required":["type"]},"_types.analysis__CjkBigramIgnoredScript":{"enum":["han","hangul","hiragana","katakana"]},"_types.analysis__CjkWidthTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"cjk_width"}},"required":["type"]},"_types.analysis__ClassicTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"classic"}},"required":["type"]},"_types.analysis__CommonGramsTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"common_grams"},"common_words":{"type":"array","items":{"type":"string"},"description":"A list of tokens. The filter generates bigrams for these tokens.\nEither this or the `common_words_path` parameter is required."},"common_words_path":{"type":"string","description":"Path to a file containing a list of tokens. The filter generates bigrams for these tokens.\nThis path must be absolute or relative to the `config` location. The file must be UTF-8 encoded. Each token in the file must be separated by a line break.\nEither this or the `common_words` parameter is required."},"ignore_case":{"type":"boolean","description":"If `true`, matches for common words matching are case-insensitive. Defaults to `false`."},"query_mode":{"type":"boolean","description":"If `true`, the filter excludes the following tokens from the output:\n- Unigrams for common words\n- Unigrams for terms followed by common words\nDefaults to `false`. We recommend enabling this parameter for search analyzers."}},"required":["type"]},"_types.analysis__ConditionTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"condition"},"filter":{"type":"array","items":{"type":"string"},"description":"Array of token filters. If a token matches the predicate script in the `script` parameter, these filters are applied to the token in the order provided."},"script":{"$ref":"./_types.json#/$defs/_types__Script","description":"Predicate script used to apply token filters. If a token matches this script, the filters in the `filter` parameter are applied to the token."}},"required":["type","filter","script"]},"_types.analysis__CzechStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"czech_stem"}},"required":["type"]},"_types.analysis__DecimalDigitTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"decimal_digit"}},"required":["type"]},"_types.analysis__DelimitedPayloadTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"delimited_payload"},"delimiter":{"type":"string","description":"Character used to separate tokens from payloads. Defaults to `|`."},"encoding":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DelimitedPayloadEncoding","description":"Data type for the stored payload."}},"required":["type"]},"_types.analysis__DelimitedPayloadEncoding":{"enum":["int","float","identity"]},"_types.analysis__DutchStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"dutch_stem"}},"required":["type"]},"_types.analysis__EdgeNGramTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"edge_ngram"},"max_gram":{"type":"number","description":"Maximum character length of a gram. For custom token filters, defaults to `2`. For the built-in edge_ngram filter, defaults to `1`."},"min_gram":{"type":"number","description":"Minimum character length of a gram. Defaults to `1`."},"side":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__EdgeNGramSide","description":"Indicates whether to truncate tokens from the `front` or `back`. Defaults to `front`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Emits original token when set to `true`. Defaults to `false`."}},"required":["type"]},"_types.analysis__EdgeNGramSide":{"enum":["front","back"]},"_types.analysis__ElisionTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"elision"},"articles":{"type":"array","items":{"type":"string"},"description":"List of elisions to remove.\nTo be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.\nFor custom `elision` filters, either this parameter or `articles_path` must be specified."},"articles_path":{"type":"string","description":"Path to a file that contains a list of elisions to remove.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each elision in the file must be separated by a line break.\nTo be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.\nFor custom `elision` filters, either this parameter or `articles` must be specified."},"articles_case":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, elision matching is case insensitive. If `false`, elision matching is case sensitive. Defaults to `false`."}},"required":["type"]},"_types.analysis__FingerprintTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"fingerprint"},"max_output_size":{"type":"number","description":"Maximum character length, including whitespace, of the output token. Defaults to `255`. Concatenated tokens longer than this will result in no token output."},"separator":{"type":"string","description":"Character to use to concatenate the token stream input. Defaults to a space."}},"required":["type"]},"_types.analysis__FlattenGraphTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"flatten_graph"}},"required":["type"]},"_types.analysis__FrenchStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"french_stem"}},"required":["type"]},"_types.analysis__GermanNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"german_normalization"}},"required":["type"]},"_types.analysis__GermanStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"german_stem"}},"required":["type"]},"_types.analysis__HindiNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"hindi_normalization"}},"required":["type"]},"_types.analysis__HunspellTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"hunspell"},"dedup":{"type":"boolean","description":"If `true`, duplicate tokens are removed from the filter’s output. Defaults to `true`."},"dictionary":{"type":"string","description":"One or more `.dic` files (e.g, `en_US.dic`, my_custom.dic) to use for the Hunspell dictionary.\nBy default, the `hunspell` filter uses all `.dic` files in the `<$ES_PATH_CONF>/hunspell/<locale>` directory specified using the `lang`, `language`, or `locale` parameter."},"locale":{"type":"string","description":"Locale directory used to specify the `.aff` and `.dic` files for a Hunspell dictionary."},"longest_only":{"type":"boolean","description":"If `true`, only the longest stemmed version of each token is included in the output. If `false`, all stemmed versions of the token are included. Defaults to `false`."}},"required":["type","locale"]},"_types.analysis__HyphenationDecompounderTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"max_subword_size":{"type":"number","description":"Maximum subword character length. Longer subword tokens are excluded from the output. Defaults to `15`."},"min_subword_size":{"type":"number","description":"Minimum subword character length. Shorter subword tokens are excluded from the output. Defaults to `2`."},"min_word_size":{"type":"number","description":"Minimum word character length. Shorter word tokens are excluded from the output. Defaults to `5`."},"only_longest_match":{"type":"boolean","description":"If `true`, only include the longest matching subword. Defaults to `false`."},"word_list":{"type":"array","items":{"type":"string"},"description":"A list of subwords to look for in the token stream. If found, the subword is included in the token output.\nEither this parameter or `word_list_path` must be specified."},"word_list_path":{"type":"string","description":"Path to a file that contains a list of subwords to find in the token stream. If found, the subword is included in the token output.\nThis path must be absolute or relative to the config location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break.\nEither this parameter or `word_list` must be specified."},"type":{"const":"hyphenation_decompounder"},"hyphenation_patterns_path":{"type":"string","description":"Path to an Apache FOP (Formatting Objects Processor) XML hyphenation pattern file.\nThis path must be absolute or relative to the `config` location. Only FOP v1.2 compatible files are supported."},"no_sub_matches":{"type":"boolean","description":"If `true`, do not match sub tokens in tokens that are in the word list. Defaults to `false`."},"no_overlapping_matches":{"type":"boolean","description":"If `true`, do not allow overlapping tokens. Defaults to `false`."}},"required":["type","hyphenation_patterns_path"]},"_types.analysis__IndicNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"indic_normalization"}},"required":["type"]},"_types.analysis__KeepTypesTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keep_types"},"mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeepTypesMode","description":"Indicates whether to keep or remove the specified token types."},"types":{"type":"array","items":{"type":"string"},"description":"List of token types to keep or remove."}},"required":["type","types"]},"_types.analysis__KeepTypesMode":{"enum":["include","exclude"]},"_types.analysis__KeepWordsTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keep"},"keep_words":{"type":"array","items":{"type":"string"},"description":"List of words to keep. Only tokens that match words in this list are included in the output.\nEither this parameter or `keep_words_path` must be specified."},"keep_words_case":{"type":"boolean","description":"If `true`, lowercase all keep words. Defaults to `false`."},"keep_words_path":{"type":"string","description":"Path to a file that contains a list of words to keep. Only tokens that match words in this list are included in the output.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.\nEither this parameter or `keep_words` must be specified."}},"required":["type"]},"_types.analysis__KeywordMarkerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keyword_marker"},"ignore_case":{"type":"boolean","description":"If `true`, matching for the `keywords` and `keywords_path` parameters ignores letter case. Defaults to `false`."},"keywords":{"oneOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Array of keywords. Tokens that match these keywords are not stemmed.\nThis parameter, `keywords_path`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`."},"keywords_path":{"type":"string","description":"Path to a file that contains a list of keywords. Tokens that match these keywords are not stemmed.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.\nThis parameter, `keywords`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`."},"keywords_pattern":{"type":"string","description":"Java regular expression used to match tokens. Tokens that match this expression are marked as keywords and not stemmed.\nThis parameter, `keywords`, or `keywords_path` must be specified. You cannot specify this parameter and `keywords` or `keywords_pattern`."}},"required":["type"]},"_types.analysis__KeywordRepeatTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keyword_repeat"}},"required":["type"]},"_types.analysis__KStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kstem"}},"required":["type"]},"_types.analysis__LengthTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"length"},"max":{"type":"number","description":"Maximum character length of a token. Longer tokens are excluded from the output. Defaults to `Integer.MAX_VALUE`, which is `2^31-1` or `2147483647`."},"min":{"type":"number","description":"Minimum character length of a token. Shorter tokens are excluded from the output. Defaults to `0`."}},"required":["type"]},"_types.analysis__LimitTokenCountTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"limit"},"consume_all_tokens":{"type":"boolean","description":"If `true`, the limit filter exhausts the token stream, even if the `max_token_count` has already been reached. Defaults to `false`."},"max_token_count":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Maximum number of tokens to keep. Once this limit is reached, any remaining tokens are excluded from the output. Defaults to `1`."}},"required":["type"]},"_types.analysis__LowercaseTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"lowercase"},"language":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LowercaseTokenFilterLanguages","description":"Language-specific lowercase token filter to use."}},"required":["type"]},"_types.analysis__LowercaseTokenFilterLanguages":{"enum":["greek","irish","turkish"]},"_types.analysis__MinHashTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"min_hash"},"bucket_count":{"type":"number","description":"Number of buckets to which hashes are assigned. Defaults to `512`."},"hash_count":{"type":"number","description":"Number of ways to hash each token in the stream. Defaults to `1`."},"hash_set_size":{"type":"number","description":"Number of hashes to keep from each bucket. Defaults to `1`.\nHashes are retained by ascending size, starting with the bucket’s smallest hash first."},"with_rotation":{"type":"boolean","description":"If `true`, the filter fills empty buckets with the value of the first non-empty bucket to its circular right if the `hash_set_size` is `1`. If the `bucket_count` argument is greater than 1, this parameter defaults to `true`. Otherwise, this parameter defaults to `false`."}},"required":["type"]},"_types.analysis__MultiplexerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"multiplexer"},"filters":{"type":"array","items":{"type":"string"},"description":"A list of token filters to apply to incoming tokens."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true` (the default) then emit the original token in addition to the filtered tokens."}},"required":["type","filters"]},"_types.analysis__NGramTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"ngram"},"max_gram":{"type":"number","description":"Maximum length of characters in a gram. Defaults to `2`."},"min_gram":{"type":"number","description":"Minimum length of characters in a gram. Defaults to `1`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Emits original token when set to `true`. Defaults to `false`."}},"required":["type"]},"_types.analysis__NoriPartOfSpeechTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"nori_part_of_speech"},"stoptags":{"type":"array","items":{"type":"string"},"description":"An array of part-of-speech tags that should be removed."}},"required":["type"]},"_types.analysis__PatternCaptureTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern_capture"},"patterns":{"type":"array","items":{"type":"string"},"description":"A list of regular expressions to match."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If set to `true` (the default) it will emit the original token."}},"required":["type","patterns"]},"_types.analysis__PatternReplaceTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern_replace"},"all":{"type":"boolean","description":"If `true`, all substrings matching the pattern parameter’s regular expression are replaced. If `false`, the filter replaces only the first matching substring in each token. Defaults to `true`."},"flags":{"type":"string"},"pattern":{"type":"string","description":"Regular expression, written in Java’s regular expression syntax. The filter replaces token substrings matching this pattern with the substring in the `replacement` parameter."},"replacement":{"type":"string","description":"Replacement substring. Defaults to an empty substring (`\"\"`)."}},"required":["type","pattern"]},"_types.analysis__PersianNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"persian_normalization"}},"required":["type"]},"_types.analysis__PersianStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"persian_stem"}},"required":["type"]},"_types.analysis__PorterStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"porter_stem"}},"required":["type"]},"_types.analysis__PredicateTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"predicate_token_filter"},"script":{"$ref":"./_types.json#/$defs/_types__Script","description":"Script containing a condition used to filter incoming tokens. Only tokens that match this script are included in the output."}},"required":["type","script"]},"_types.analysis__RemoveDuplicatesTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"remove_duplicates"}},"required":["type"]},"_types.analysis__ReverseTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"reverse"}},"required":["type"]},"_types.analysis__RussianStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"russian_stem"}},"required":["type"]},"_types.analysis__ScandinavianFoldingTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"scandinavian_folding"}},"required":["type"]},"_types.analysis__ScandinavianNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"scandinavian_normalization"}},"required":["type"]},"_types.analysis__SerbianNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"serbian_normalization"}},"required":["type"]},"_types.analysis__ShingleTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"shingle"},"filler_token":{"type":"string","description":"String used in shingles as a replacement for empty positions that do not contain a token. This filler token is only used in shingles, not original unigrams. Defaults to an underscore (`_`)."},"max_shingle_size":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Maximum number of tokens to concatenate when creating shingles. Defaults to `2`."},"min_shingle_size":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Minimum number of tokens to concatenate when creating shingles. Defaults to `2`."},"output_unigrams":{"type":"boolean","description":"If `true`, the output includes the original input tokens. If `false`, the output only includes shingles; the original input tokens are removed. Defaults to `true`."},"output_unigrams_if_no_shingles":{"type":"boolean","description":"If `true`, the output includes the original input tokens only if no shingles are produced; if shingles are produced, the output only includes shingles. Defaults to `false`."},"token_separator":{"type":"string","description":"Separator used to concatenate adjacent tokens to form a shingle. Defaults to a space (`\" \"`)."}},"required":["type"]},"_types.analysis__SnowballTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"snowball"},"language":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SnowballLanguage","description":"Controls the language used by the stemmer."}},"required":["type"]},"_types.analysis__SnowballLanguage":{"enum":["Arabic","Armenian","Basque","Catalan","Danish","Dutch","English","Estonian","Finnish","French","German","German2","Hungarian","Italian","Irish","Kp","Lithuanian","Lovins","Norwegian","Porter","Portuguese","Romanian","Russian","Serbian","Spanish","Swedish","Turkish"]},"_types.analysis__SoraniNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"sorani_normalization"}},"required":["type"]},"_types.analysis__StemmerOverrideTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"stemmer_override"},"rules":{"type":"array","items":{"type":"string"},"description":"A list of mapping rules to use."},"rules_path":{"type":"string","description":"A path (either relative to `config` location, or absolute) to a list of mappings."}},"required":["type"]},"_types.analysis__StemmerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"stemmer"},"language":{"type":"string"}},"required":["type"]},"_types.analysis__StopTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"stop"},"ignore_case":{"type":"boolean","description":"If `true`, stop word matching is case insensitive. For example, if `true`, a stop word of the matches and removes `The`, `THE`, or `the`. Defaults to `false`."},"remove_trailing":{"type":"boolean","description":"If `true`, the last token of a stream is removed if it’s a stop word. Defaults to `true`."},"stopwords":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopWords","description":"Language value, such as `_arabic_` or `_thai_`. Defaults to `_english_`."},"stopwords_path":{"type":"string","description":"Path to a file that contains a list of stop words to remove.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each stop word in the file must be separated by a line break."}},"required":["type"]},"_types.analysis__SynonymGraphTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"expand":{"type":"boolean","description":"Expands definitions for equivalent synonym rules. Defaults to `true`."},"format":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymFormat","description":"Sets the synonym rules format."},"lenient":{"type":"boolean","description":"If `true` ignores errors while parsing the synonym rules. It is important to note that only those synonym rules which cannot get parsed are ignored. Defaults to the value of the `updateable` setting."},"synonyms":{"type":"array","items":{"type":"string"},"description":"Used to define inline synonyms."},"synonyms_path":{"type":"string","description":"Used to provide a synonym file. This path must be absolute or relative to the `config` location."},"synonyms_set":{"oneOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Provide one or more synonym sets created through the Synonyms Management APIs. Maximum 100 sets per filter."},"tokenizer":{"type":"string","description":"Controls the tokenizers that will be used to tokenize the synonym, this parameter is for backwards compatibility for indices that created before 6.0."},"updateable":{"type":"boolean","description":"If `true` allows reloading search analyzers to pick up changes to synonym files. Only to be used for search analyzers. Defaults to `false`."},"type":{"const":"synonym_graph"}},"required":["type"]},"_types.analysis__SynonymFormat":{"enum":["solr","wordnet"]},"_types.analysis__SynonymTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"expand":{"type":"boolean","description":"Expands definitions for equivalent synonym rules. Defaults to `true`."},"format":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymFormat","description":"Sets the synonym rules format."},"lenient":{"type":"boolean","description":"If `true` ignores errors while parsing the synonym rules. It is important to note that only those synonym rules which cannot get parsed are ignored. Defaults to the value of the `updateable` setting."},"synonyms":{"type":"array","items":{"type":"string"},"description":"Used to define inline synonyms."},"synonyms_path":{"type":"string","description":"Used to provide a synonym file. This path must be absolute or relative to the `config` location."},"synonyms_set":{"oneOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Provide one or more synonym sets created through the Synonyms Management APIs. Maximum 100 sets per filter."},"tokenizer":{"type":"string","description":"Controls the tokenizers that will be used to tokenize the synonym, this parameter is for backwards compatibility for indices that created before 6.0."},"updateable":{"type":"boolean","description":"If `true` allows reloading search analyzers to pick up changes to synonym files. Only to be used for search analyzers. Defaults to `false`."},"type":{"const":"synonym"}},"required":["type"]},"_types.analysis__TrimTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"trim"}},"required":["type"]},"_types.analysis__TruncateTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"truncate"},"length":{"type":"number","description":"Character limit for each token. Tokens exceeding this limit are truncated. Defaults to `10`."}},"required":["type"]},"_types.analysis__UniqueTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"unique"},"only_on_same_position":{"type":"boolean","description":"If `true`, only remove duplicate tokens in the same position. Defaults to `false`."}},"required":["type"]},"_types.analysis__UppercaseTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"uppercase"}},"required":["type"]},"_types.analysis__WordDelimiterGraphTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"catenate_all":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphanumeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_numbers":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of numeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_words":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphabetical characters separated by non-alphabetic delimiters. Defaults to `false`."},"generate_number_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only numeric characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"generate_word_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only alphabetical characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, the filter includes the original version of any split tokens in the output. This original version includes non-alphanumeric delimiters. Defaults to `false`."},"protected_words":{"type":"array","items":{"type":"string"},"description":"Array of tokens the filter won’t split."},"protected_words_path":{"type":"string","description":"Path to a file that contains a list of tokens the filter won’t split.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break."},"split_on_case_change":{"type":"boolean","description":"If `true`, the filter splits tokens at letter case transitions. For example: camelCase -> [ camel, Case ]. Defaults to `true`."},"split_on_numerics":{"type":"boolean","description":"If `true`, the filter splits tokens at letter-number transitions. For example: j2se -> [ j, 2, se ]. Defaults to `true`."},"stem_english_possessive":{"type":"boolean","description":"If `true`, the filter removes the English possessive (`'s`) from the end of each token. For example: O'Neil's -> [ O, Neil ]. Defaults to `true`."},"type_table":{"type":"array","items":{"type":"string"},"description":"Array of custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type_table_path":{"type":"string","description":"Path to a file that contains custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type":{"const":"word_delimiter_graph"},"adjust_offsets":{"type":"boolean","description":"If `true`, the filter adjusts the offsets of split or catenated tokens to better reflect their actual position in the token stream. Defaults to `true`."},"ignore_keywords":{"type":"boolean","description":"If `true`, the filter skips tokens with a keyword attribute of true. Defaults to `false`."}},"required":["type"]},"_types.analysis__WordDelimiterTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"catenate_all":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphanumeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_numbers":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of numeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_words":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphabetical characters separated by non-alphabetic delimiters. Defaults to `false`."},"generate_number_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only numeric characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"generate_word_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only alphabetical characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, the filter includes the original version of any split tokens in the output. This original version includes non-alphanumeric delimiters. Defaults to `false`."},"protected_words":{"type":"array","items":{"type":"string"},"description":"Array of tokens the filter won’t split."},"protected_words_path":{"type":"string","description":"Path to a file that contains a list of tokens the filter won’t split.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break."},"split_on_case_change":{"type":"boolean","description":"If `true`, the filter splits tokens at letter case transitions. For example: camelCase -> [ camel, Case ]. Defaults to `true`."},"split_on_numerics":{"type":"boolean","description":"If `true`, the filter splits tokens at letter-number transitions. For example: j2se -> [ j, 2, se ]. Defaults to `true`."},"stem_english_possessive":{"type":"boolean","description":"If `true`, the filter removes the English possessive (`'s`) from the end of each token. For example: O'Neil's -> [ O, Neil ]. Defaults to `true`."},"type_table":{"type":"array","items":{"type":"string"},"description":"Array of custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type_table_path":{"type":"string","description":"Path to a file that contains custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type":{"const":"word_delimiter"}},"required":["type"]},"_types.analysis__JaStopTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"ja_stop"},"stopwords":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopWords"}},"required":["type"]},"_types.analysis__KuromojiStemmerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_stemmer"},"minimum_length":{"type":"number"}},"required":["type","minimum_length"]},"_types.analysis__KuromojiReadingFormTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_readingform"},"use_romaji":{"type":"boolean"}},"required":["type","use_romaji"]},"_types.analysis__KuromojiPartOfSpeechTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_part_of_speech"},"stoptags":{"type":"array","items":{"type":"string"}}},"required":["type","stoptags"]},"_types.analysis__IcuCollationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_collation"},"alternate":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationAlternate"},"caseFirst":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationCaseFirst"},"caseLevel":{"type":"boolean"},"country":{"type":"string"},"decomposition":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationDecomposition"},"hiraganaQuaternaryMode":{"type":"boolean"},"language":{"type":"string"},"numeric":{"type":"boolean"},"rules":{"type":"string"},"strength":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationStrength"},"variableTop":{"type":"string"},"variant":{"type":"string"}},"required":["type"]},"_types.analysis__IcuFoldingTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_folding"},"unicode_set_filter":{"type":"string"}},"required":["type","unicode_set_filter"]},"_types.analysis__IcuNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_normalizer"},"name":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationType"}},"required":["type","name"]},"_types.analysis__IcuTransformTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_transform"},"dir":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuTransformDirection"},"id":{"type":"string"}},"required":["type","id"]},"_types.analysis__IcuTransformDirection":{"enum":["forward","reverse"]},"_types.analysis__PhoneticTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"phonetic"},"encoder":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticEncoder"},"languageset":{"oneOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticLanguage"},{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticLanguage"}}]},"max_code_len":{"type":"number"},"name_type":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticNameType"},"replace":{"type":"boolean"},"rule_type":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticRuleType"}},"required":["type","encoder"]},"_types.analysis__PhoneticEncoder":{"enum":["metaphone","double_metaphone","soundex","refined_soundex","caverphone1","caverphone2","cologne","nysiis","koelnerphonetik","haasephonetik","beider_morse","daitch_mokotoff"]},"_types.analysis__PhoneticLanguage":{"enum":["any","common","cyrillic","english","french","german","hebrew","hungarian","polish","romanian","russian","spanish"]},"_types.analysis__PhoneticNameType":{"enum":["generic","ashkenazi","sephardic"]},"_types.analysis__PhoneticRuleType":{"enum":["approx","exact"]},"_types.analysis__DictionaryDecompounderTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"max_subword_size":{"type":"number","description":"Maximum subword character length. Longer subword tokens are excluded from the output. Defaults to `15`."},"min_subword_size":{"type":"number","description":"Minimum subword character length. Shorter subword tokens are excluded from the output. Defaults to `2`."},"min_word_size":{"type":"number","description":"Minimum word character length. Shorter word tokens are excluded from the output. Defaults to `5`."},"only_longest_match":{"type":"boolean","description":"If `true`, only include the longest matching subword. Defaults to `false`."},"word_list":{"type":"array","items":{"type":"string"},"description":"A list of subwords to look for in the token stream. If found, the subword is included in the token output.\nEither this parameter or `word_list_path` must be specified."},"word_list_path":{"type":"string","description":"Path to a file that contains a list of subwords to find in the token stream. If found, the subword is included in the token output.\nThis path must be absolute or relative to the config location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break.\nEither this parameter or `word_list` must be specified."},"type":{"const":"dictionary_decompounder"}},"required":["type"]},"_types.analysis__Tokenizer":{"oneOf":[{"type":"string"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenizerDefinition"}]},"_types.analysis__TokenizerDefinition":{"oneOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CharGroupTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ClassicTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__EdgeNGramTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeywordTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LetterTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LowercaseTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NGramTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PathHierarchyTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SimplePatternTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SimplePatternSplitTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StandardTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ThaiTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__UaxEmailUrlTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__WhitespaceTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NoriTokenizer"}]},"_types.analysis__CharGroupTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"char_group"},"tokenize_on_chars":{"type":"array","items":{"type":"string"}},"max_token_length":{"type":"number"}},"required":["type","tokenize_on_chars"]},"_types.analysis__ClassicTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"classic"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__EdgeNGramTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"edge_ngram"},"custom_token_chars":{"type":"string"},"max_gram":{"type":"number"},"min_gram":{"type":"number"},"token_chars":{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenChar"}}},"required":["type"]},"_types.analysis__TokenChar":{"enum":["letter","digit","whitespace","punctuation","symbol","custom"]},"_types.analysis__KeywordTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keyword"},"buffer_size":{"type":"number"}},"required":["type"]},"_types.analysis__LetterTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"letter"}},"required":["type"]},"_types.analysis__LowercaseTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"lowercase"}},"required":["type"]},"_types.analysis__NGramTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"ngram"},"custom_token_chars":{"type":"string"},"max_gram":{"type":"number"},"min_gram":{"type":"number"},"token_chars":{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenChar"}}},"required":["type"]},"_types.analysis__PathHierarchyTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"path_hierarchy"},"buffer_size":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified"},"delimiter":{"type":"string"},"replacement":{"type":"string"},"reverse":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified"},"skip":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified"}},"required":["type"]},"_types.analysis__PatternTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern"},"flags":{"type":"string"},"group":{"type":"number"},"pattern":{"type":"string"}},"required":["type"]},"_types.analysis__SimplePatternTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"simple_pattern"},"pattern":{"type":"string"}},"required":["type"]},"_types.analysis__SimplePatternSplitTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"simple_pattern_split"},"pattern":{"type":"string"}},"required":["type"]},"_types.analysis__StandardTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"standard"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__ThaiTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"thai"}},"required":["type"]},"_types.analysis__UaxEmailUrlTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"uax_url_email"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__WhitespaceTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"whitespace"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__IcuTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_tokenizer"},"rule_files":{"type":"string"}},"required":["type","rule_files"]},"_types.analysis__KuromojiTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_tokenizer"},"discard_punctuation":{"type":"boolean"},"mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiTokenizationMode"},"nbest_cost":{"type":"number"},"nbest_examples":{"type":"string"},"user_dictionary":{"type":"string"},"user_dictionary_rules":{"type":"array","items":{"type":"string"}},"discard_compound_token":{"type":"boolean"}},"required":["type","mode"]},"_types.analysis__KuromojiTokenizationMode":{"enum":["normal","search","extended"]},"_types.analysis__NoriTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"nori_tokenizer"},"decompound_mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NoriDecompoundMode"},"discard_punctuation":{"type":"boolean"},"user_dictionary":{"type":"string"},"user_dictionary_rules":{"type":"array","items":{"type":"string"}}},"required":["type"]},"_types.analysis__NoriDecompoundMode":{"enum":["discard","none","mixed"]}}}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","$defs":{"_types.analysis__StopWords":{"anyOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopWordLanguage"},{"type":"array","items":{"type":"string"}}],"description":"Language value, such as _arabic_ or _thai_. Defaults to _english_.\nEach language value corresponds to a predefined list of stop words in Lucene. See Stop words by language for supported language values and their stop words.\nAlso accepts an array of stop words."},"_types.analysis__StopWordLanguage":{"enum":["_arabic_","_armenian_","_basque_","_bengali_","_brazilian_","_bulgarian_","_catalan_","_cjk_","_czech_","_danish_","_dutch_","_english_","_estonian_","_finnish_","_french_","_galician_","_german_","_greek_","_hindi_","_hungarian_","_indonesian_","_irish_","_italian_","_latvian_","_lithuanian_","_norwegian_","_persian_","_portuguese_","_romanian_","_russian_","_serbian_","_sorani_","_spanish_","_swedish_","_thai_","_turkish_","_none_"]},"_types.analysis__IcuCollationStrength":{"enum":["primary","secondary","tertiary","quaternary","identical"]},"_types.analysis__IcuCollationDecomposition":{"enum":["no","identical"]},"_types.analysis__IcuCollationAlternate":{"enum":["shifted","non-ignorable"]},"_types.analysis__IcuCollationCaseFirst":{"enum":["lower","upper"]},"_types.analysis__CharFilter":{"anyOf":[{"type":"string"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CharFilterDefinition"}]},"_types.analysis__CharFilterDefinition":{"anyOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HtmlStripCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__MappingCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternReplaceCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationCharFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiIterationMarkCharFilter"}]},"_types.analysis__HtmlStripCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"html_strip"},"escaped_tags":{"type":"array","items":{"type":"string"}}},"required":["type"]},"_types.analysis__MappingCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"mapping"},"mappings":{"type":"array","items":{"type":"string"}},"mappings_path":{"type":"string"}},"required":["type"]},"_types.analysis__PatternReplaceCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern_replace"},"flags":{"type":"string"},"pattern":{"type":"string"},"replacement":{"type":"string"}},"required":["type","pattern"]},"_types.analysis__IcuNormalizationCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_normalizer"},"mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationMode"},"name":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationType"},"unicode_set_filter":{"type":"string"}},"required":["type"]},"_types.analysis__IcuNormalizationMode":{"enum":["decompose","compose"]},"_types.analysis__IcuNormalizationType":{"enum":["nfc","nfkc","nfkc_cf"]},"_types.analysis__KuromojiIterationMarkCharFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_iteration_mark"},"normalize_kana":{"type":"boolean"},"normalize_kanji":{"type":"boolean"}},"required":["type","normalize_kana","normalize_kanji"]},"_types.analysis__TokenFilter":{"anyOf":[{"type":"string"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenFilterDefinition"}]},"_types.analysis__TokenFilterDefinition":{"anyOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ApostropheTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ArabicStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ArabicNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__AsciiFoldingTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__BengaliNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__BrazilianStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CjkBigramTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CjkWidthTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ClassicTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CommonGramsTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ConditionTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CzechStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DecimalDigitTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DelimitedPayloadTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DutchStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__EdgeNGramTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ElisionTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__FingerprintTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__FlattenGraphTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__FrenchStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__GermanNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__GermanStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HindiNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HunspellTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__HyphenationDecompounderTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IndicNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeepTypesTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeepWordsTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeywordMarkerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeywordRepeatTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LengthTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LimitTokenCountTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LowercaseTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__MinHashTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__MultiplexerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NGramTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NoriPartOfSpeechTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternCaptureTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternReplaceTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PersianNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PersianStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PorterStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PredicateTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__RemoveDuplicatesTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ReverseTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__RussianStemTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ScandinavianFoldingTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ScandinavianNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SerbianNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ShingleTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SnowballTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SoraniNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StemmerOverrideTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StemmerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymGraphTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TrimTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TruncateTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__UniqueTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__UppercaseTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__WordDelimiterGraphTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__WordDelimiterTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__JaStopTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiStemmerTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiReadingFormTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiPartOfSpeechTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuFoldingTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuTransformTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticTokenFilter"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DictionaryDecompounderTokenFilter"}]},"_types.analysis__ApostropheTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"apostrophe"}},"required":["type"]},"_types.analysis__ArabicStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"arabic_stem"}},"required":["type"]},"_types.analysis__ArabicNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"arabic_normalization"}},"required":["type"]},"_types.analysis__AsciiFoldingTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"asciifolding"},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, emit both original tokens and folded tokens. Defaults to `false`."}},"required":["type"]},"_types.analysis__BengaliNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"bengali_normalization"}},"required":["type"]},"_types.analysis__BrazilianStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"brazilian_stem"}},"required":["type"]},"_types.analysis__CjkBigramTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"cjk_bigram"},"ignored_scripts":{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CjkBigramIgnoredScript"},"description":"Array of character scripts for which to disable bigrams."},"output_unigrams":{"type":"boolean","description":"If `true`, emit tokens in both bigram and unigram form. If `false`, a CJK character is output in unigram form when it has no adjacent characters. Defaults to `false`."}},"required":["type"]},"_types.analysis__CjkBigramIgnoredScript":{"enum":["han","hangul","hiragana","katakana"]},"_types.analysis__CjkWidthTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"cjk_width"}},"required":["type"]},"_types.analysis__ClassicTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"classic"}},"required":["type"]},"_types.analysis__CommonGramsTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"common_grams"},"common_words":{"type":"array","items":{"type":"string"},"description":"A list of tokens. The filter generates bigrams for these tokens.\nEither this or the `common_words_path` parameter is required."},"common_words_path":{"type":"string","description":"Path to a file containing a list of tokens. The filter generates bigrams for these tokens.\nThis path must be absolute or relative to the `config` location. The file must be UTF-8 encoded. Each token in the file must be separated by a line break.\nEither this or the `common_words` parameter is required."},"ignore_case":{"type":"boolean","description":"If `true`, matches for common words matching are case-insensitive. Defaults to `false`."},"query_mode":{"type":"boolean","description":"If `true`, the filter excludes the following tokens from the output:\n- Unigrams for common words\n- Unigrams for terms followed by common words\nDefaults to `false`. We recommend enabling this parameter for search analyzers."}},"required":["type"]},"_types.analysis__ConditionTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"condition"},"filter":{"type":"array","items":{"type":"string"},"description":"Array of token filters. If a token matches the predicate script in the `script` parameter, these filters are applied to the token in the order provided."},"script":{"$ref":"./_types.json#/$defs/_types__Script","description":"Predicate script used to apply token filters. If a token matches this script, the filters in the `filter` parameter are applied to the token."}},"required":["type","filter","script"]},"_types.analysis__CzechStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"czech_stem"}},"required":["type"]},"_types.analysis__DecimalDigitTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"decimal_digit"}},"required":["type"]},"_types.analysis__DelimitedPayloadTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"delimited_payload"},"delimiter":{"type":"string","description":"Character used to separate tokens from payloads. Defaults to `|`."},"encoding":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__DelimitedPayloadEncoding","description":"Data type for the stored payload."}},"required":["type"]},"_types.analysis__DelimitedPayloadEncoding":{"enum":["int","float","identity"]},"_types.analysis__DutchStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"dutch_stem"}},"required":["type"]},"_types.analysis__EdgeNGramTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"edge_ngram"},"max_gram":{"type":"number","description":"Maximum character length of a gram. For custom token filters, defaults to `2`. For the built-in edge_ngram filter, defaults to `1`."},"min_gram":{"type":"number","description":"Minimum character length of a gram. Defaults to `1`."},"side":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__EdgeNGramSide","description":"Indicates whether to truncate tokens from the `front` or `back`. Defaults to `front`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Emits original token when set to `true`. Defaults to `false`."}},"required":["type"]},"_types.analysis__EdgeNGramSide":{"enum":["front","back"]},"_types.analysis__ElisionTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"elision"},"articles":{"type":"array","items":{"type":"string"},"description":"List of elisions to remove.\nTo be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.\nFor custom `elision` filters, either this parameter or `articles_path` must be specified."},"articles_path":{"type":"string","description":"Path to a file that contains a list of elisions to remove.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each elision in the file must be separated by a line break.\nTo be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.\nFor custom `elision` filters, either this parameter or `articles` must be specified."},"articles_case":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, elision matching is case insensitive. If `false`, elision matching is case sensitive. Defaults to `false`."}},"required":["type"]},"_types.analysis__FingerprintTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"fingerprint"},"max_output_size":{"type":"number","description":"Maximum character length, including whitespace, of the output token. Defaults to `255`. Concatenated tokens longer than this will result in no token output."},"separator":{"type":"string","description":"Character to use to concatenate the token stream input. Defaults to a space."}},"required":["type"]},"_types.analysis__FlattenGraphTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"flatten_graph"}},"required":["type"]},"_types.analysis__FrenchStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"french_stem"}},"required":["type"]},"_types.analysis__GermanNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"german_normalization"}},"required":["type"]},"_types.analysis__GermanStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"german_stem"}},"required":["type"]},"_types.analysis__HindiNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"hindi_normalization"}},"required":["type"]},"_types.analysis__HunspellTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"hunspell"},"dedup":{"type":"boolean","description":"If `true`, duplicate tokens are removed from the filter’s output. Defaults to `true`."},"dictionary":{"type":"string","description":"One or more `.dic` files (e.g, `en_US.dic`, my_custom.dic) to use for the Hunspell dictionary.\nBy default, the `hunspell` filter uses all `.dic` files in the `<$ES_PATH_CONF>/hunspell/<locale>` directory specified using the `lang`, `language`, or `locale` parameter."},"locale":{"type":"string","description":"Locale directory used to specify the `.aff` and `.dic` files for a Hunspell dictionary."},"longest_only":{"type":"boolean","description":"If `true`, only the longest stemmed version of each token is included in the output. If `false`, all stemmed versions of the token are included. Defaults to `false`."}},"required":["type","locale"]},"_types.analysis__HyphenationDecompounderTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"max_subword_size":{"type":"number","description":"Maximum subword character length. Longer subword tokens are excluded from the output. Defaults to `15`."},"min_subword_size":{"type":"number","description":"Minimum subword character length. Shorter subword tokens are excluded from the output. Defaults to `2`."},"min_word_size":{"type":"number","description":"Minimum word character length. Shorter word tokens are excluded from the output. Defaults to `5`."},"only_longest_match":{"type":"boolean","description":"If `true`, only include the longest matching subword. Defaults to `false`."},"word_list":{"type":"array","items":{"type":"string"},"description":"A list of subwords to look for in the token stream. If found, the subword is included in the token output.\nEither this parameter or `word_list_path` must be specified."},"word_list_path":{"type":"string","description":"Path to a file that contains a list of subwords to find in the token stream. If found, the subword is included in the token output.\nThis path must be absolute or relative to the config location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break.\nEither this parameter or `word_list` must be specified."},"type":{"const":"hyphenation_decompounder"},"hyphenation_patterns_path":{"type":"string","description":"Path to an Apache FOP (Formatting Objects Processor) XML hyphenation pattern file.\nThis path must be absolute or relative to the `config` location. Only FOP v1.2 compatible files are supported."},"no_sub_matches":{"type":"boolean","description":"If `true`, do not match sub tokens in tokens that are in the word list. Defaults to `false`."},"no_overlapping_matches":{"type":"boolean","description":"If `true`, do not allow overlapping tokens. Defaults to `false`."}},"required":["type","hyphenation_patterns_path"]},"_types.analysis__IndicNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"indic_normalization"}},"required":["type"]},"_types.analysis__KeepTypesTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keep_types"},"mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeepTypesMode","description":"Indicates whether to keep or remove the specified token types."},"types":{"type":"array","items":{"type":"string"},"description":"List of token types to keep or remove."}},"required":["type","types"]},"_types.analysis__KeepTypesMode":{"enum":["include","exclude"]},"_types.analysis__KeepWordsTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keep"},"keep_words":{"type":"array","items":{"type":"string"},"description":"List of words to keep. Only tokens that match words in this list are included in the output.\nEither this parameter or `keep_words_path` must be specified."},"keep_words_case":{"type":"boolean","description":"If `true`, lowercase all keep words. Defaults to `false`."},"keep_words_path":{"type":"string","description":"Path to a file that contains a list of words to keep. Only tokens that match words in this list are included in the output.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.\nEither this parameter or `keep_words` must be specified."}},"required":["type"]},"_types.analysis__KeywordMarkerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keyword_marker"},"ignore_case":{"type":"boolean","description":"If `true`, matching for the `keywords` and `keywords_path` parameters ignores letter case. Defaults to `false`."},"keywords":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Array of keywords. Tokens that match these keywords are not stemmed.\nThis parameter, `keywords_path`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`."},"keywords_path":{"type":"string","description":"Path to a file that contains a list of keywords. Tokens that match these keywords are not stemmed.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.\nThis parameter, `keywords`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`."},"keywords_pattern":{"type":"string","description":"Java regular expression used to match tokens. Tokens that match this expression are marked as keywords and not stemmed.\nThis parameter, `keywords`, or `keywords_path` must be specified. You cannot specify this parameter and `keywords` or `keywords_pattern`."}},"required":["type"]},"_types.analysis__KeywordRepeatTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keyword_repeat"}},"required":["type"]},"_types.analysis__KStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kstem"}},"required":["type"]},"_types.analysis__LengthTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"length"},"max":{"type":"number","description":"Maximum character length of a token. Longer tokens are excluded from the output. Defaults to `Integer.MAX_VALUE`, which is `2^31-1` or `2147483647`."},"min":{"type":"number","description":"Minimum character length of a token. Shorter tokens are excluded from the output. Defaults to `0`."}},"required":["type"]},"_types.analysis__LimitTokenCountTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"limit"},"consume_all_tokens":{"type":"boolean","description":"If `true`, the limit filter exhausts the token stream, even if the `max_token_count` has already been reached. Defaults to `false`."},"max_token_count":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Maximum number of tokens to keep. Once this limit is reached, any remaining tokens are excluded from the output. Defaults to `1`."}},"required":["type"]},"_types.analysis__LowercaseTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"lowercase"},"language":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LowercaseTokenFilterLanguages","description":"Language-specific lowercase token filter to use."}},"required":["type"]},"_types.analysis__LowercaseTokenFilterLanguages":{"enum":["greek","irish","turkish"]},"_types.analysis__MinHashTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"min_hash"},"bucket_count":{"type":"number","description":"Number of buckets to which hashes are assigned. Defaults to `512`."},"hash_count":{"type":"number","description":"Number of ways to hash each token in the stream. Defaults to `1`."},"hash_set_size":{"type":"number","description":"Number of hashes to keep from each bucket. Defaults to `1`.\nHashes are retained by ascending size, starting with the bucket’s smallest hash first."},"with_rotation":{"type":"boolean","description":"If `true`, the filter fills empty buckets with the value of the first non-empty bucket to its circular right if the `hash_set_size` is `1`. If the `bucket_count` argument is greater than 1, this parameter defaults to `true`. Otherwise, this parameter defaults to `false`."}},"required":["type"]},"_types.analysis__MultiplexerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"multiplexer"},"filters":{"type":"array","items":{"type":"string"},"description":"A list of token filters to apply to incoming tokens."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true` (the default) then emit the original token in addition to the filtered tokens."}},"required":["type","filters"]},"_types.analysis__NGramTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"ngram"},"max_gram":{"type":"number","description":"Maximum length of characters in a gram. Defaults to `2`."},"min_gram":{"type":"number","description":"Minimum length of characters in a gram. Defaults to `1`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Emits original token when set to `true`. Defaults to `false`."}},"required":["type"]},"_types.analysis__NoriPartOfSpeechTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"nori_part_of_speech"},"stoptags":{"type":"array","items":{"type":"string"},"description":"An array of part-of-speech tags that should be removed."}},"required":["type"]},"_types.analysis__PatternCaptureTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern_capture"},"patterns":{"type":"array","items":{"type":"string"},"description":"A list of regular expressions to match."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If set to `true` (the default) it will emit the original token."}},"required":["type","patterns"]},"_types.analysis__PatternReplaceTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern_replace"},"all":{"type":"boolean","description":"If `true`, all substrings matching the pattern parameter’s regular expression are replaced. If `false`, the filter replaces only the first matching substring in each token. Defaults to `true`."},"flags":{"type":"string"},"pattern":{"type":"string","description":"Regular expression, written in Java’s regular expression syntax. The filter replaces token substrings matching this pattern with the substring in the `replacement` parameter."},"replacement":{"type":"string","description":"Replacement substring. Defaults to an empty substring (`\"\"`)."}},"required":["type","pattern"]},"_types.analysis__PersianNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"persian_normalization"}},"required":["type"]},"_types.analysis__PersianStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"persian_stem"}},"required":["type"]},"_types.analysis__PorterStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"porter_stem"}},"required":["type"]},"_types.analysis__PredicateTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"predicate_token_filter"},"script":{"$ref":"./_types.json#/$defs/_types__Script","description":"Script containing a condition used to filter incoming tokens. Only tokens that match this script are included in the output."}},"required":["type","script"]},"_types.analysis__RemoveDuplicatesTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"remove_duplicates"}},"required":["type"]},"_types.analysis__ReverseTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"reverse"}},"required":["type"]},"_types.analysis__RussianStemTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"russian_stem"}},"required":["type"]},"_types.analysis__ScandinavianFoldingTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"scandinavian_folding"}},"required":["type"]},"_types.analysis__ScandinavianNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"scandinavian_normalization"}},"required":["type"]},"_types.analysis__SerbianNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"serbian_normalization"}},"required":["type"]},"_types.analysis__ShingleTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"shingle"},"filler_token":{"type":"string","description":"String used in shingles as a replacement for empty positions that do not contain a token. This filler token is only used in shingles, not original unigrams. Defaults to an underscore (`_`)."},"max_shingle_size":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Maximum number of tokens to concatenate when creating shingles. Defaults to `2`."},"min_shingle_size":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"Minimum number of tokens to concatenate when creating shingles. Defaults to `2`."},"output_unigrams":{"type":"boolean","description":"If `true`, the output includes the original input tokens. If `false`, the output only includes shingles; the original input tokens are removed. Defaults to `true`."},"output_unigrams_if_no_shingles":{"type":"boolean","description":"If `true`, the output includes the original input tokens only if no shingles are produced; if shingles are produced, the output only includes shingles. Defaults to `false`."},"token_separator":{"type":"string","description":"Separator used to concatenate adjacent tokens to form a shingle. Defaults to a space (`\" \"`)."}},"required":["type"]},"_types.analysis__SnowballTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"snowball"},"language":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SnowballLanguage","description":"Controls the language used by the stemmer."}},"required":["type"]},"_types.analysis__SnowballLanguage":{"enum":["Arabic","Armenian","Basque","Catalan","Danish","Dutch","English","Estonian","Finnish","French","German","German2","Hungarian","Italian","Irish","Kp","Lithuanian","Lovins","Norwegian","Porter","Portuguese","Romanian","Russian","Serbian","Spanish","Swedish","Turkish"]},"_types.analysis__SoraniNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"sorani_normalization"}},"required":["type"]},"_types.analysis__StemmerOverrideTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"stemmer_override"},"rules":{"type":"array","items":{"type":"string"},"description":"A list of mapping rules to use."},"rules_path":{"type":"string","description":"A path (either relative to `config` location, or absolute) to a list of mappings."}},"required":["type"]},"_types.analysis__StemmerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"stemmer"},"language":{"type":"string"}},"required":["type"]},"_types.analysis__StopTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"stop"},"ignore_case":{"type":"boolean","description":"If `true`, stop word matching is case insensitive. For example, if `true`, a stop word of the matches and removes `The`, `THE`, or `the`. Defaults to `false`."},"remove_trailing":{"type":"boolean","description":"If `true`, the last token of a stream is removed if it’s a stop word. Defaults to `true`."},"stopwords":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopWords","description":"Language value, such as `_arabic_` or `_thai_`. Defaults to `_english_`."},"stopwords_path":{"type":"string","description":"Path to a file that contains a list of stop words to remove.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each stop word in the file must be separated by a line break."}},"required":["type"]},"_types.analysis__SynonymGraphTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"expand":{"type":"boolean","description":"Expands definitions for equivalent synonym rules. Defaults to `true`."},"format":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymFormat","description":"Sets the synonym rules format."},"lenient":{"type":"boolean","description":"If `true` ignores errors while parsing the synonym rules. It is important to note that only those synonym rules which cannot get parsed are ignored. Defaults to the value of the `updateable` setting."},"synonyms":{"type":"array","items":{"type":"string"},"description":"Used to define inline synonyms."},"synonyms_path":{"type":"string","description":"Used to provide a synonym file. This path must be absolute or relative to the `config` location."},"synonyms_set":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Provide one or more synonym sets created through the Synonyms Management APIs. Maximum 100 sets per filter."},"tokenizer":{"type":"string","description":"Controls the tokenizers that will be used to tokenize the synonym, this parameter is for backwards compatibility for indices that created before 6.0."},"updateable":{"type":"boolean","description":"If `true` allows reloading search analyzers to pick up changes to synonym files. Only to be used for search analyzers. Defaults to `false`."},"type":{"const":"synonym_graph"}},"required":["type"]},"_types.analysis__SynonymFormat":{"enum":["solr","wordnet"]},"_types.analysis__SynonymTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"expand":{"type":"boolean","description":"Expands definitions for equivalent synonym rules. Defaults to `true`."},"format":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SynonymFormat","description":"Sets the synonym rules format."},"lenient":{"type":"boolean","description":"If `true` ignores errors while parsing the synonym rules. It is important to note that only those synonym rules which cannot get parsed are ignored. Defaults to the value of the `updateable` setting."},"synonyms":{"type":"array","items":{"type":"string"},"description":"Used to define inline synonyms."},"synonyms_path":{"type":"string","description":"Used to provide a synonym file. This path must be absolute or relative to the `config` location."},"synonyms_set":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Provide one or more synonym sets created through the Synonyms Management APIs. Maximum 100 sets per filter."},"tokenizer":{"type":"string","description":"Controls the tokenizers that will be used to tokenize the synonym, this parameter is for backwards compatibility for indices that created before 6.0."},"updateable":{"type":"boolean","description":"If `true` allows reloading search analyzers to pick up changes to synonym files. Only to be used for search analyzers. Defaults to `false`."},"type":{"const":"synonym"}},"required":["type"]},"_types.analysis__TrimTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"trim"}},"required":["type"]},"_types.analysis__TruncateTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"truncate"},"length":{"type":"number","description":"Character limit for each token. Tokens exceeding this limit are truncated. Defaults to `10`."}},"required":["type"]},"_types.analysis__UniqueTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"unique"},"only_on_same_position":{"type":"boolean","description":"If `true`, only remove duplicate tokens in the same position. Defaults to `false`."}},"required":["type"]},"_types.analysis__UppercaseTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"uppercase"}},"required":["type"]},"_types.analysis__WordDelimiterGraphTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"catenate_all":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphanumeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_numbers":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of numeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_words":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphabetical characters separated by non-alphabetic delimiters. Defaults to `false`."},"generate_number_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only numeric characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"generate_word_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only alphabetical characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, the filter includes the original version of any split tokens in the output. This original version includes non-alphanumeric delimiters. Defaults to `false`."},"protected_words":{"type":"array","items":{"type":"string"},"description":"Array of tokens the filter won’t split."},"protected_words_path":{"type":"string","description":"Path to a file that contains a list of tokens the filter won’t split.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break."},"split_on_case_change":{"type":"boolean","description":"If `true`, the filter splits tokens at letter case transitions. For example: camelCase -> [ camel, Case ]. Defaults to `true`."},"split_on_numerics":{"type":"boolean","description":"If `true`, the filter splits tokens at letter-number transitions. For example: j2se -> [ j, 2, se ]. Defaults to `true`."},"stem_english_possessive":{"type":"boolean","description":"If `true`, the filter removes the English possessive (`'s`) from the end of each token. For example: O'Neil's -> [ O, Neil ]. Defaults to `true`."},"type_table":{"type":"array","items":{"type":"string"},"description":"Array of custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type_table_path":{"type":"string","description":"Path to a file that contains custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type":{"const":"word_delimiter_graph"},"adjust_offsets":{"type":"boolean","description":"If `true`, the filter adjusts the offsets of split or catenated tokens to better reflect their actual position in the token stream. Defaults to `true`."},"ignore_keywords":{"type":"boolean","description":"If `true`, the filter skips tokens with a keyword attribute of true. Defaults to `false`."}},"required":["type"]},"_types.analysis__WordDelimiterTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"catenate_all":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphanumeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_numbers":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of numeric characters separated by non-alphabetic delimiters. Defaults to `false`."},"catenate_words":{"type":"boolean","description":"If `true`, the filter produces catenated tokens for chains of alphabetical characters separated by non-alphabetic delimiters. Defaults to `false`."},"generate_number_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only numeric characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"generate_word_parts":{"type":"boolean","description":"If `true`, the filter includes tokens consisting of only alphabetical characters in the output. If `false`, the filter excludes these tokens from the output. Defaults to `true`."},"preserve_original":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified","description":"If `true`, the filter includes the original version of any split tokens in the output. This original version includes non-alphanumeric delimiters. Defaults to `false`."},"protected_words":{"type":"array","items":{"type":"string"},"description":"Array of tokens the filter won’t split."},"protected_words_path":{"type":"string","description":"Path to a file that contains a list of tokens the filter won’t split.\nThis path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break."},"split_on_case_change":{"type":"boolean","description":"If `true`, the filter splits tokens at letter case transitions. For example: camelCase -> [ camel, Case ]. Defaults to `true`."},"split_on_numerics":{"type":"boolean","description":"If `true`, the filter splits tokens at letter-number transitions. For example: j2se -> [ j, 2, se ]. Defaults to `true`."},"stem_english_possessive":{"type":"boolean","description":"If `true`, the filter removes the English possessive (`'s`) from the end of each token. For example: O'Neil's -> [ O, Neil ]. Defaults to `true`."},"type_table":{"type":"array","items":{"type":"string"},"description":"Array of custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type_table_path":{"type":"string","description":"Path to a file that contains custom type mappings for characters. This allows you to map non-alphanumeric characters as numeric or alphanumeric to avoid splitting on those characters."},"type":{"const":"word_delimiter"}},"required":["type"]},"_types.analysis__JaStopTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"ja_stop"},"stopwords":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StopWords"}},"required":["type"]},"_types.analysis__KuromojiStemmerTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_stemmer"},"minimum_length":{"type":"number"}},"required":["type","minimum_length"]},"_types.analysis__KuromojiReadingFormTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_readingform"},"use_romaji":{"type":"boolean"}},"required":["type","use_romaji"]},"_types.analysis__KuromojiPartOfSpeechTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_part_of_speech"},"stoptags":{"type":"array","items":{"type":"string"}}},"required":["type","stoptags"]},"_types.analysis__IcuCollationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_collation"},"alternate":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationAlternate"},"caseFirst":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationCaseFirst"},"caseLevel":{"type":"boolean"},"country":{"type":"string"},"decomposition":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationDecomposition"},"hiraganaQuaternaryMode":{"type":"boolean"},"language":{"type":"string"},"numeric":{"type":"boolean"},"rules":{"type":"string"},"strength":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuCollationStrength"},"variableTop":{"type":"string"},"variant":{"type":"string"}},"required":["type"]},"_types.analysis__IcuFoldingTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_folding"},"unicode_set_filter":{"type":"string"}},"required":["type","unicode_set_filter"]},"_types.analysis__IcuNormalizationTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_normalizer"},"name":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuNormalizationType"}},"required":["type","name"]},"_types.analysis__IcuTransformTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_transform"},"dir":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuTransformDirection"},"id":{"type":"string"}},"required":["type","id"]},"_types.analysis__IcuTransformDirection":{"enum":["forward","reverse"]},"_types.analysis__PhoneticTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"phonetic"},"encoder":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticEncoder"},"languageset":{"anyOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticLanguage"},{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticLanguage"}}]},"max_code_len":{"type":"number"},"name_type":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticNameType"},"replace":{"type":"boolean"},"rule_type":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PhoneticRuleType"}},"required":["type","encoder"]},"_types.analysis__PhoneticEncoder":{"enum":["metaphone","double_metaphone","soundex","refined_soundex","caverphone1","caverphone2","cologne","nysiis","koelnerphonetik","haasephonetik","beider_morse","daitch_mokotoff"]},"_types.analysis__PhoneticLanguage":{"enum":["any","common","cyrillic","english","french","german","hebrew","hungarian","polish","romanian","russian","spanish"]},"_types.analysis__PhoneticNameType":{"enum":["generic","ashkenazi","sephardic"]},"_types.analysis__PhoneticRuleType":{"enum":["approx","exact"]},"_types.analysis__DictionaryDecompounderTokenFilter":{"type":"object","properties":{"version":{"type":"string"},"max_subword_size":{"type":"number","description":"Maximum subword character length. Longer subword tokens are excluded from the output. Defaults to `15`."},"min_subword_size":{"type":"number","description":"Minimum subword character length. Shorter subword tokens are excluded from the output. Defaults to `2`."},"min_word_size":{"type":"number","description":"Minimum word character length. Shorter word tokens are excluded from the output. Defaults to `5`."},"only_longest_match":{"type":"boolean","description":"If `true`, only include the longest matching subword. Defaults to `false`."},"word_list":{"type":"array","items":{"type":"string"},"description":"A list of subwords to look for in the token stream. If found, the subword is included in the token output.\nEither this parameter or `word_list_path` must be specified."},"word_list_path":{"type":"string","description":"Path to a file that contains a list of subwords to find in the token stream. If found, the subword is included in the token output.\nThis path must be absolute or relative to the config location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break.\nEither this parameter or `word_list` must be specified."},"type":{"const":"dictionary_decompounder"}},"required":["type"]},"_types.analysis__Tokenizer":{"anyOf":[{"type":"string"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenizerDefinition"}]},"_types.analysis__TokenizerDefinition":{"anyOf":[{"$ref":"./_types.analysis.json#/$defs/_types.analysis__CharGroupTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ClassicTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__EdgeNGramTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KeywordTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LetterTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__LowercaseTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NGramTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PathHierarchyTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__PatternTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SimplePatternTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__SimplePatternSplitTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__StandardTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__ThaiTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__UaxEmailUrlTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__WhitespaceTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__IcuTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiTokenizer"},{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NoriTokenizer"}]},"_types.analysis__CharGroupTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"char_group"},"tokenize_on_chars":{"type":"array","items":{"type":"string"}},"max_token_length":{"type":"number"}},"required":["type","tokenize_on_chars"]},"_types.analysis__ClassicTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"classic"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__EdgeNGramTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"edge_ngram"},"custom_token_chars":{"type":"string"},"max_gram":{"type":"number"},"min_gram":{"type":"number"},"token_chars":{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenChar"}}},"required":["type"]},"_types.analysis__TokenChar":{"enum":["letter","digit","whitespace","punctuation","symbol","custom"]},"_types.analysis__KeywordTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"keyword"},"buffer_size":{"type":"number"}},"required":["type"]},"_types.analysis__LetterTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"letter"}},"required":["type"]},"_types.analysis__LowercaseTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"lowercase"}},"required":["type"]},"_types.analysis__NGramTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"ngram"},"custom_token_chars":{"type":"string"},"max_gram":{"type":"number"},"min_gram":{"type":"number"},"token_chars":{"type":"array","items":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__TokenChar"}}},"required":["type"]},"_types.analysis__PathHierarchyTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"path_hierarchy"},"buffer_size":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified"},"delimiter":{"type":"string"},"replacement":{"type":"string"},"reverse":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified"},"skip":{"$ref":"./_spec_utils.json#/$defs/_spec_utils__Stringified"}},"required":["type"]},"_types.analysis__PatternTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"pattern"},"flags":{"type":"string"},"group":{"type":"number"},"pattern":{"type":"string"}},"required":["type"]},"_types.analysis__SimplePatternTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"simple_pattern"},"pattern":{"type":"string"}},"required":["type"]},"_types.analysis__SimplePatternSplitTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"simple_pattern_split"},"pattern":{"type":"string"}},"required":["type"]},"_types.analysis__StandardTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"standard"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__ThaiTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"thai"}},"required":["type"]},"_types.analysis__UaxEmailUrlTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"uax_url_email"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__WhitespaceTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"whitespace"},"max_token_length":{"type":"number"}},"required":["type"]},"_types.analysis__IcuTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"icu_tokenizer"},"rule_files":{"type":"string"}},"required":["type","rule_files"]},"_types.analysis__KuromojiTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"kuromoji_tokenizer"},"discard_punctuation":{"type":"boolean"},"mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__KuromojiTokenizationMode"},"nbest_cost":{"type":"number"},"nbest_examples":{"type":"string"},"user_dictionary":{"type":"string"},"user_dictionary_rules":{"type":"array","items":{"type":"string"}},"discard_compound_token":{"type":"boolean"}},"required":["type","mode"]},"_types.analysis__KuromojiTokenizationMode":{"enum":["normal","search","extended"]},"_types.analysis__NoriTokenizer":{"type":"object","properties":{"version":{"type":"string"},"type":{"const":"nori_tokenizer"},"decompound_mode":{"$ref":"./_types.analysis.json#/$defs/_types.analysis__NoriDecompoundMode"},"discard_punctuation":{"type":"boolean"},"user_dictionary":{"type":"string"},"user_dictionary_rules":{"type":"array","items":{"type":"string"}}},"required":["type"]},"_types.analysis__NoriDecompoundMode":{"enum":["discard","none","mixed"]}}}