{
    "analyzer": {
        "text": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": [
                "homoglyph_norm",
                "lowercase",
                "mirandese_elision",
                "mirandese_stop"
            ],
            "char_filter": [
                "nnbsp_norm"
            ]
        },
        "plain": {
            "type": "custom",
            "char_filter": [
                "nnbsp_norm",
                "word_break_helper"
            ],
            "tokenizer": "standard",
            "filter": [
                "lowercase"
            ]
        },
        "plain_search": {
            "type": "custom",
            "char_filter": [
                "nnbsp_norm",
                "word_break_helper"
            ],
            "tokenizer": "standard",
            "filter": [
                "lowercase"
            ]
        },
        "short_text": {
            "type": "custom",
            "tokenizer": "whitespace",
            "filter": [
                "lowercase",
                "aggressive_splitting",
                "asciifolding_preserve",
                "dedup_asciifolding"
            ]
        },
        "short_text_search": {
            "type": "custom",
            "tokenizer": "whitespace",
            "filter": [
                "lowercase",
                "aggressive_splitting"
            ]
        },
        "source_text_plain": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": [
                "lowercase"
            ],
            "char_filter": [
                "word_break_helper_source_text"
            ]
        },
        "source_text_plain_search": {
            "type": "custom",
            "char_filter": [
                "word_break_helper_source_text"
            ],
            "tokenizer": "standard",
            "filter": [
                "lowercase"
            ]
        },
        "suggest": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": [
                "lowercase",
                "suggest_shingle"
            ]
        },
        "suggest_reverse": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": [
                "lowercase",
                "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": [
                "lowercase"
            ]
        },
        "near_match_asciifolding": {
            "type": "custom",
            "char_filter": [
                "near_space_flattener"
            ],
            "tokenizer": "no_splitting",
            "filter": [
                "truncate_keyword",
                "lowercase",
                "asciifolding"
            ]
        },
        "prefix": {
            "type": "custom",
            "char_filter": [
                "near_space_flattener"
            ],
            "tokenizer": "prefix",
            "filter": [
                "lowercase"
            ]
        },
        "prefix_asciifolding": {
            "type": "custom",
            "char_filter": [
                "near_space_flattener"
            ],
            "tokenizer": "prefix",
            "filter": [
                "lowercase",
                "asciifolding"
            ]
        },
        "word_prefix": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": [
                "lowercase",
                "prefix_ngram_filter"
            ]
        },
        "keyword": {
            "type": "custom",
            "tokenizer": "no_splitting",
            "filter": [
                "truncate_keyword"
            ]
        },
        "lowercase_keyword": {
            "type": "custom",
            "tokenizer": "no_splitting",
            "filter": [
                "truncate_keyword",
                "lowercase"
            ]
        },
        "trigram": {
            "type": "custom",
            "tokenizer": "trigram",
            "filter": [
                "lowercase"
            ]
        },
        "text_search": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": [
                "homoglyph_norm",
                "lowercase",
                "mirandese_elision",
                "mirandese_stop"
            ],
            "char_filter": [
                "nnbsp_norm"
            ]
        }
    },
    "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
        },
        "mirandese_elision": {
            "type": "elision",
            "articles_case": true,
            "articles": [
                "l",
                "d",
                "qu"
            ]
        },
        "mirandese_stop": {
            "type": "stop",
            "stopwords": [
                "de",
                "a",
                "la",
                "l",
                "que",
                "quei",
                "i",
                "an",
                "ne",
                "en",
                "un",
                "pa",
                "para",
                "cun",
                "n\u00f3",
                "nan",
                "nun",
                "ua",
                "\u0169a",
                "ls",
                "los",
                "se",
                "na",
                "por",
                "mais",
                "m\u00e1s",
                "las",
                "cumo",
                "mas",
                "al",
                "el",
                "sou",
                "sue",
                "\u00f3",
                "u",
                "ou",
                "quando",
                "muito",
                "mui",
                "mi",
                "mos",
                "nos",
                "y\u00e1",
                "you",
                "tamien",
                "solo",
                "pul",
                "pula",
                "ant\u00e9",
                "at\u00e9",
                "esso",
                "isso",
                "eilha",
                "antre",
                "a\u00e7puis",
                "adepuis",
                "adespuis",
                "apuis",
                "\u00e7puis",
                "depuis",
                "sien",
                "sin",
                "mesmo",
                "miesmo",
                "als",
                "sous",
                "quien",
                "nas",
                "me",
                "mi",
                "esse",
                "eilhes",
                "tu",
                "essa",
                "nun",
                "nien",
                "nin",
                "sues",
                "miu",
                "mie",
                "nua",
                "n\u0169a",
                "puls",
                "eilhas",
                "qual",
                "n\u00f3s",
                "le",
                "deilhes",
                "essas",
                "esses",
                "pulas",
                "este",
                "del",
                "tu",
                "ti",
                "te",
                "b\u00f3s",
                "bos",
                "les",
                "mius",
                "mies",
                "tou",
                "tue",
                "tous",
                "tues",
                "nuosso",
                "nuossa",
                "nuossos",
                "nuossas",
                "deilha",
                "deilhas",
                "esta",
                "estes",
                "estas",
                "aquel",
                "aqueilha",
                "aqueilhes",
                "aqueilhas",
                "esto",
                "isto",
                "aqueilho",
                "aquilho",
                "stou",
                "st\u00e1",
                "stamos",
                "stan",
                "stube",
                "stubo",
                "stubimos",
                "stub\u00edrun",
                "staba",
                "st\u00e1bamos",
                "st\u00e1ban",
                "stubira",
                "stub\u00edramos",
                "steia",
                "st\u00e9iamos",
                "stemos",
                "st\u00e9ian",
                "sten",
                "stubisse",
                "stub\u00edssemos",
                "stub\u00edssen",
                "stubir",
                "stubirmos",
                "stub\u00edren",
                "hei",
                "hai",
                "h\u00e1",
                "hemos",
                "han",
                "hoube",
                "houbimos",
                "houb\u00edrun",
                "houbira",
                "houb\u00edramos",
                "haba",
                "haia",
                "h\u00e1bamos",
                "h\u00e1iamos",
                "h\u00e1ban",
                "h\u00e1ian",
                "houbisse",
                "habisse",
                "houb\u00edssemos",
                "hab\u00edssemos",
                "houb\u00edssen",
                "hab\u00edssen",
                "houbir",
                "houbirmos",
                "houb\u00edren",
                "sou",
                "somos",
                "son",
                "sano",
                "era",
                "\u00e9ramos",
                "\u00e9ran",
                "fui",
                "fui",
                "fumos",
                "f\u00farun",
                "fura",
                "f\u00faramos",
                "seia",
                "s\u00e9iamos",
                "s\u00e9ian",
                "fusse",
                "f\u00fassemos",
                "f\u00fassen",
                "fur",
                "furmos",
                "f\u00faren",
                "serei",
                "ser\u00e1",
                "seremos",
                "seran",
                "serano",
                "serie",
                "seriemos",
                "serien",
                "tengo",
                "ten",
                "tenemos",
                "t\u00e9nen",
                "tenie",
                "teniemos",
                "tenien",
                "tube",
                "tubo",
                "tubimos",
                "tub\u00edrun",
                "tubira",
                "tub\u00edramos",
                "tenga",
                "t\u00e9ngamos",
                "t\u00e9ngan",
                "tubisse",
                "tub\u00edssemos",
                "tub\u00edssen",
                "tubir",
                "tubirmos",
                "tub\u00edren",
                "tenerei",
                "tener\u00e1",
                "teneremos",
                "teneran",
                "teneria",
                "teneriemos",
                "tenerien",
                "ye",
                "fui",
                "ten",
                "ser",
                "hai",
                "h\u00e1",
                "st\u00e1",
                "era",
                "tener",
                "stan",
                "tenie",
                "f\u00faran",
                "t\u00e9nen",
                "habie",
                "seia",
                "ser\u00e1",
                "tengo",
                "fusse"
            ]
        },
        "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"
            ]
        }
    }
}