{ "analyzer": { "text": { "type": "custom", "tokenizer": "icu_tokenizer", "char_filter": [ "nnbsp_norm", "thai_repl_pat", "dotted_I_fix", "thai_charfilter" ], "filter": [ "homoglyph_norm", "icu_normalizer", "decimal_digit", "thai_stop", "asciifolding" ] }, "plain": { "type": "custom", "char_filter": [ "nnbsp_norm", "word_break_helper" ], "tokenizer": "standard", "filter": [ "icu_normalizer" ] }, "plain_search": { "type": "custom", "char_filter": [ "nnbsp_norm", "word_break_helper" ], "tokenizer": "standard", "filter": [ "icu_normalizer" ] }, "short_text": { "type": "custom", "tokenizer": "whitespace", "filter": [ "icu_normalizer", "aggressive_splitting", "asciifolding_preserve", "dedup_asciifolding" ] }, "short_text_search": { "type": "custom", "tokenizer": "whitespace", "filter": [ "icu_normalizer", "aggressive_splitting" ] }, "source_text_plain": { "type": "custom", "tokenizer": "standard", "filter": [ "icu_normalizer" ], "char_filter": [ "word_break_helper_source_text" ] }, "source_text_plain_search": { "type": "custom", "char_filter": [ "word_break_helper_source_text" ], "tokenizer": "standard", "filter": [ "icu_normalizer" ] }, "suggest": { "type": "custom", "tokenizer": "standard", "filter": [ "icu_normalizer", "suggest_shingle" ] }, "suggest_reverse": { "type": "custom", "tokenizer": "standard", "filter": [ "icu_normalizer", "suggest_shingle", "reverse" ] }, "token_reverse": { "type": "custom", "tokenizer": "no_splitting", "filter": [ "reverse" ] }, "near_match": { "type": "custom", "char_filter": [ "near_space_flattener" ], "tokenizer": "no_splitting", "filter": [ "icu_normalizer" ] }, "near_match_asciifolding": { "type": "custom", "char_filter": [ "near_space_flattener" ], "tokenizer": "no_splitting", "filter": [ "truncate_keyword", "icu_normalizer", "asciifolding" ] }, "prefix": { "type": "custom", "char_filter": [ "near_space_flattener" ], "tokenizer": "prefix", "filter": [ "icu_normalizer" ] }, "prefix_asciifolding": { "type": "custom", "char_filter": [ "near_space_flattener" ], "tokenizer": "prefix", "filter": [ "icu_normalizer", "asciifolding" ] }, "word_prefix": { "type": "custom", "tokenizer": "standard", "filter": [ "icu_normalizer", "prefix_ngram_filter" ] }, "keyword": { "type": "custom", "tokenizer": "no_splitting", "filter": [ "truncate_keyword" ] }, "lowercase_keyword": { "type": "custom", "tokenizer": "no_splitting", "filter": [ "truncate_keyword", "icu_normalizer" ] }, "trigram": { "type": "custom", "tokenizer": "trigram", "filter": [ "icu_normalizer" ] }, "text_search": { "type": "custom", "tokenizer": "icu_tokenizer", "char_filter": [ "nnbsp_norm", "thai_repl_pat", "dotted_I_fix", "thai_charfilter" ], "filter": [ "homoglyph_norm", "icu_normalizer", "decimal_digit", "thai_stop", "asciifolding" ] } }, "filter": { "suggest_shingle": { "type": "shingle", "min_shingle_size": 2, "max_shingle_size": 3, "output_unigrams": true }, "lowercase": { "type": "lowercase" }, "aggressive_splitting": { "type": "word_delimiter", "stem_english_possessive": false, "preserve_original": false }, "prefix_ngram_filter": { "type": "edgeNGram", "max_gram": 255 }, "asciifolding": { "type": "asciifolding", "preserve_original": false }, "asciifolding_preserve": { "type": "asciifolding", "preserve_original": true }, "truncate_keyword": { "type": "truncate", "length": 5000 }, "remove_empty": { "type": "length", "min": 1 }, "icu_normalizer": { "type": "icu_normalizer", "name": "nfkc_cf" }, "thai_stop": { "type": "stop", "stopwords": "_thai_" }, "dedup_asciifolding": { "type": "unique", "only_on_same_position": true } }, "tokenizer": { "prefix": { "type": "edgeNGram", "max_gram": 255 }, "no_splitting": { "type": "keyword" }, "trigram": { "type": "nGram", "min_gram": 3, "max_gram": 3 } }, "char_filter": { "near_space_flattener": { "type": "mapping", "mappings": [ "'=>\\u0020", "\\u2019=>\\u0020", "\\u02BC=>\\u0020", "_=>\\u0020", "-=>\\u0020" ] }, "nnbsp_norm": { "type": "mapping", "mappings": [ "\\u202F=>\\u0020" ] }, "word_break_helper": { "type": "mapping", "mappings": [ "_=>\\u0020", ".=>\\u0020", "(=>\\u0020", ")=>\\u0020" ] }, "word_break_helper_source_text": { "type": "mapping", "mappings": [ "_=>\\u0020", ".=>\\u0020", "(=>\\u0020", ")=>\\u0020", ":=>\\u0020" ] }, "dotted_I_fix": { "type": "mapping", "mappings": [ "\u0130=>I" ] }, "thai_repl_pat": { "type": "pattern_replace", "pattern": "(?<=\\p{Nd})([\u0e01-\u0e4f])|(?<=[\u0e01-\u0e4f])(\\p{Nd})|(?<=[\u0e01-\u0e4f])\\.([\u0e01-\u0e4f])", "replacement": " $1$2$3" }, "thai_charfilter": { "type": "mapping", "mappings": [ "_=>\\u0020", ";=>\\u0020", ":=>\\u0020", "\u00b7=>\\u0020", "\u2027=>\\u0020", "\u0e03=>\u0e02", "\u0e05=>\u0e04", "\\u0e4d\\u0e32=>\\u0e33", "\\u0e4d\\u0e48\\u0e32=>\\u0e48\\u0e33", "\\u0e4d\\u0e49\\u0e32=>\\u0e49\\u0e33", "\\u0e33\\u0e48=>\\u0e48\\u0e33", "\\u0e33\\u0e49=>\\u0e49\\u0e33", "\\u0E34\\u0E4D=>\\u0E36", "\\u0E4D\\u0E34=>\\u0E36" ] } } }