Grammalecte  Check-in [edcc777d4b]

            ("OEIL", "ŒIL"),
            ("apele", "appel"),
            ("Co2", "CO₂"),
            ("emmppâiiiller", "empailler"),
            ("testt", "test"),
            ("apelaion", "appellation"),
            ("exsepttion", "exception"),

            ("ebriete", "ébriété"),
            ("ennormmement", "énormément"),
            ("sintaxik", "syntaxique")
        ]:
            #with timeblock(sWord):
            for lSugg in self.oSpellChecker.suggest(sWrong):
                #print(sWord, "->", " ".join(lSugg))
                self.assertIn(sSugg, lSugg)

    [a|à] [>bât|ba+s|bat+s] [on|ont|>ton|>thon] [>rond|ron+s]  [pu+s|put|pue+s]
        <<- /loc/ ->> à bâtons rompus                   && Confusion. Locution « à bâtons rompus ».|https://fr.wiktionary.org/wiki/%C3%A0_b%C3%A2tons_rompus

TEST: s’organiser, comme on put, {{à bas thon rond pu}}                             ->> à bâtons rompus
TEST: actions {{à bâton rompu}}                                                     ->> à bâtons rompus
TEST: discuter à bâtons rompus


__conf_à_bon_port__
    !! à bon port ¡¡
    [à|a] bon [>porc|>pore|>port]
        <<- /conf/ ->> à bon port                                           && Locution adverbiale “à bon port”.|https://fr.wiktionary.org/wiki/%C3%A0_bon_port

TEST: {{a bon porc}}                                                                ->> à bon port


__conf_à_cor_et_à_cri__
    !! à cor et à cri ¡¡
    [a|à] [corps|cor+s] [et|est|es|ait|ais|aies|é|è|ei|ai|aient] [à|a] [cri+s|crie+s|crit]
        <<- /loc/ ->> à cor et à cri                    && Locution adverbiale invariable. (Le cor est un instrument à vent utilisé pour la chasse.)|https://fr.wiktionary.org/wiki/%C3%A0_cor_et_%C3%A0_cri

TEST: Elles hurlèrent {{à corps et à cris}}.                                        ->> à cor et à cri

    [>avaler|>bouffer|>cuire|>élever|>égorger|>frire|>manger|>mâcher|>mastiquer|>rôtir|>tuer] $:D¬:R [>pore|>port]
    >élevage [de|d’] [>pore|>port]
        <<- /conf/ --1>> porc|porcs                                         && Confusion. Pour évoquer l’animal, écrivez “porc”.|https://fr.wiktionary.org/wiki/porc

    >pore [qui|qué] [>pique|>pic]
    >porc [qui|qué] [>pique|>pic]
    >port [qui|qué] [>pique|>pic]
        <<- /conf/ morph(<1, ":D|<start>|>[(,]") ->> porc-épic|porcs-épics  && Confusion générale ? Si vous parlez de l’animal, écrivez “porc-épic”.|https://fr.wiktionary.org/wiki/porc-%C3%A9pic

    ## port
    [>pore|>porc] [de|d’] [plaisance|pêche]
    [>pore|>porc] [>maritime|>spatial]
        <<- /conf/ -1>> port|ports                                          && Confusion. Pour évoquer un havre côtier où les bateaux accostent, écrivez “port”.|https://fr.wiktionary.org/wiki/port

    [<start>|,|le|au|du]  [pore|porc]  [de|d’]  [Alexandrie|Algésiras|Almirante␣Barroso|Amsterdam|Angra␣dos␣Reis|Anvers|Baltimore|Bandar␣Abbas|Bandar␣Khomeini|Bangkok|Barcelone|Bayonne|Beaumont|Bergen|Bintulu|Bombay|Bordeaux|Botaş|Bremerhaven|Brisbane|Brême|Busan|Bâton-Rouge|Calais|Calcutta|Callao|Cannes|Canton|Cayo␣Arcas|Ceyhan|Chennai|Cherbourg|Chiba|Chittagong|Colombo|Constanța|Corpus␣Christi|Daesan|Dakar|Dalian|Dampier|Dieppe|Djeddah|Dubaï|Dunkerque|Durban|el-Dekheila|Gladstone|Goa|Grimsby|Guangzhou|Gwangyang|Gênes|Göteborg|Hambourg|Hampton␣Roads|Hay␣Point|Honfleur|Hong-Kong|Hong␣Kong|Honshu|Houston|Huntington-Tristate|Hô-Chi-Minh-Ville|Ibiza|Immingham|Inchon|Istanbul|Itaguaí|Itaqui|Izmir|Izmit|Jaffa|Jakarta|Jawaharlal␣Nehru|Jebel␣Ali|Jubail|Kaohsiung|Karachi|Kitakyushu|Kobe|Kota␣Baru|Laem␣Chabang|Lake␣Charles|La␣Nouvelle-Orléans|La␣Rochelle|Lianyungang|Londres|Long␣Beach|Lorient|Los␣Angeles|Madras|Manille|Marseille|Miami|Milford␣Haven|Mobile|Monaco|Montréal|Mormugão|Mumbai|Nagoya|Nantes|Naples|Newcastle|New␣Jersey|New␣York|Nice|Ningbo-Zhoushann|Novorossiysk|Odessa|Oran|Osaka|Ouistreham|Oust-Louga|Paradip|Paranaguá|Philadelphie|Plaquemine|Pohang|Porto-Vecchio|Port␣Hedlandn|Primorsk|Qingdao|Qinhuangdao|Quibéron|Quimper|Richards␣Bay|Rizhao|Rome|Rotterdam|Rouen|Saigon|Saint-Pétersbourg|Saldanha␣Bay|Santos|San␣Lorenzo|Sepetiba|Shanghai|Shenzhen|Singapour|Southampton|São␣Sebastião|Taichung|Tanger|Tangshan|Tanjung␣Pelepas|Tanjung␣Priok|Texas␣City|Tianjin|Tientsin|Tokyo|Toulon|Trieste|Tsingtao|Tubarão|Tunis|Ulsan|Valence|Vancouver|Vannes|Venise|Visakhapatnam|Waigaoqiao|Washington|Wellington|Wuhan|Xiamen|Xingang|Yanbu|Yangshan|Yantian|Yingkou|Yokohama|Youjne|Zeebruges]
    [<start>|,|le|au|du]  [pore|porc]  du       [Havre|Touquet]
        <<- /conf/ -2>> port                                                && Confusion. Pour évoquer un havre côtier où les bateaux accostent, écrivez “port”.|https://fr.wiktionary.org/wiki/port

    frais [de|d’] [>pore|>porc]
        <<- /conf/ --1>> port                                               && Confusion. Locution “frais de port”.|https://fr.wiktionary.org/wiki/frais_de_port


    [>accoster|>amarrer] ?@:[WX]¿ au [>pore|>porc]
    [>accoster|>amarrer] ?@:[WX]¿ à ce ?petit¿ [>pore|>porc]
        <<- /conf/ --1>> port                                               && Confusion. Pour évoquer un havre côtier où les bateaux accostent, écrivez “port”.|https://fr.wiktionary.org/wiki/port

    [>pore|>porc] [usb|RJ45|DVI|HDMI|Ethernet|DisplayPort]
        <<- /conf/ -1>> port|ports                                          && Confusion. Pour évoquer les connecteurs, écrivez “port”.|https://fr.wiktionary.org/wiki/port

    [pore|porc] de l’ [écharpe|étoile|épée]
    [pore|porc] du masque
        <<- /conf/ -1>> port                                                && Confusion. Pour évoquer ce que l’on porte, écrivez “port”.|https://fr.wiktionary.org/wiki/port

TEST: les {{ports}} de la peau                                              ->> pore|pores
TEST: du {{port}} au caramel                                                ->> porc|porcs
TEST: elle prépare une blanquette de {{port}}                               ->> porc
TEST: un filet mignon de {{pore}}                                           ->> porc
TEST: j’en ai marre de bouffer du {{port}}                                  ->> porc|porcs
TEST: un {{porc qui pique}}                                                 ->> porc-épic|porcs-épics
TEST: le {{pore}} de l’étoile jaune                                         ->> port
TEST: un petit {{porc}} de plaisance                                        ->> port|ports

TEST: les frais de {{pore}}                                                 ->> port
TEST: Accoste au {{porc}}                                                   ->> port
TEST: le {{pore}} de La Rochelle                                            ->> port
TEST: Connecte le {{pore}} USB                                              ->> port|ports
TEST: transpirer par tous les {{porcs}}                                     ->> pores
TEST: je transporte des porcs de Calais à Londres.

        for (let c of sWord) {
            sNewWord += this._xTransCharsForSpelling.gl_get(c, c);
        }
        return sNewWord.normalize("NFC");
    },

    _xTransCharsForSimplification: new Map([
        ['à', 'a'],  ['é', 'e'],  ['î', 'i'],  ['ô', 'o'],  ['û', 'u'],  ['ÿ', 'i'],   ['y', 'i'],
        ['â', 'a'],  ['è', 'e'],  ['ï', 'i'],  ['ö', 'o'],  ['ù', 'u'],  ['ŷ', 'i'],
        ['ä', 'a'],  ['ê', 'e'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'i'],
        ['á', 'a'],  ['ë', 'e'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'i'],
        ['ā', 'a'],  ['ē', 'e'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'i'],
        ['ç', 'c'],  ['ñ', 'n'],
        ['œ', 'oe'], ['æ', 'ae'],
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st'],
        ["⁰", "0"], ["¹", "1"], ["²", "2"], ["³", "3"], ["⁴", "4"], ["⁵", "5"], ["⁶", "6"], ["⁷", "7"], ["⁸", "8"], ["⁹", "9"],
        ["₀", "0"], ["₁", "1"], ["₂", "2"], ["₃", "3"], ["₄", "4"], ["₅", "5"], ["₆", "6"], ["₇", "7"], ["₈", "8"], ["₉", "9"],
        ["’", ""], ["'", ""], ["ʼ", ""], ["‘", ""], ["‛", ""], ["´", ""], ["`", ""], ["′", ""], ["‵", ""], ["՚", ""], ["ꞌ", ""], ["Ꞌ", ""],
        ["-", ""]

        let i = 1;
        for (let c of sWord) {
            if (c != sWord.slice(i, i+1) || (c == 'e' && sWord.slice(i, i+2) != "ee")) {  // exception for <e> to avoid confusion between crée / créai
                sNewWord += c;
            }
            i++;
        }
        return sNewWord.replace(/eau/g, "o").replace(/au/g, "o").replace(/ei/g, "e").replace(/ai/g, "e").replace(/ph/g, "f");
    },

    cleanWord: function (sWord) {
        // word clean for the user who make commun and preditive error help suggest
        // remove letters repeated more than 2 times
        return sWord.replace(/(.)\1{2,}/ig,'$1$1');
    },

        self.sSimplifiedWord = st.simplifyWord(sWord)
        self.nDistLimit = nDistLimit  if nDistLimit >= 0  else  (len(sWord) // 3) + 1 # used in suggest()
        self.nMinDist = 1000
        # Temporary sets
        self.aAllSugg = set()   # All suggestions, even the one rejected
        self.dAccSugg = {}      # Accepted suggestions
        # Parameters

        self.nSuggLimit = nSuggLimit            # number of returned suggestions
        self.nTempSuggLimit = nSuggLimit * 6    # limit of accepted suggestions (ends search over this limit)

    def addSugg (self, sSugg, nDeep=0):
        "add a suggestion to the suggestion list"
        if sSugg in self.aAllSugg:
            return
        self.aAllSugg.add(sSugg)
        nSimDist = st.distanceSift4(self.sSimplifiedWord, st.simplifyWord(sSugg))
        #st.showDistance(self.sSimplifiedWord, st.simplifyWord(sSugg))
        if nSimDist < self.nMinDist:
            self.nMinDist = nSimDist
        if nSimDist <= (self.nMinDist + 1):
            nDist = min(st.distanceDamerauLevenshtein(self.sWord, sSugg), st.distanceDamerauLevenshtein(self.sSimplifiedWord, st.simplifyWord(sSugg)))
            #print(">", end="")
            #st.showDistance(self.sWord, sSugg)
            self.dAccSugg[sSugg] = min(nDist, nSimDist+1)
            if len(self.dAccSugg) > self.nTempSuggLimit:
                self.nDistLimit = -1  # suggest() ends searching when this variable = -1
        self.nDistLimit = min(self.nDistLimit, self.nMinDist+1)

    def getSuggestions (self):
        "return a list of suggestions"

def spellingNormalization (sWord):
    "nomalization NFC and removing ligatures"
    return unicodedata.normalize("NFC", sWord.translate(_xTransCharsForSpelling))


_xTransCharsForSimplification = str.maketrans({
    'à': 'a',  'é': 'e',  'î': 'i',  'ô': 'o',  'û': 'u',  'ÿ': 'i', 'y': 'i',
    'â': 'a',  'è': 'e',  'ï': 'i',  'ö': 'o',  'ù': 'u',  'ŷ': 'i',
    'ä': 'a',  'ê': 'e',  'í': 'i',  'ó': 'o',  'ü': 'u',  'ý': 'i',
    'á': 'a',  'ë': 'e',  'ì': 'i',  'ò': 'o',  'ú': 'u',  'ỳ': 'i',
    'ā': 'a',  'ē': 'e',  'ī': 'i',  'ō': 'o',  'ū': 'u',  'ȳ': 'i',
    'ç': 'c',  'ñ': 'n',
    'œ': 'oe',  'æ': 'ae',
    'ſ': 's',  'ffi': 'ffi',  'ffl': 'ffl',  'ff': 'ff',  'ſt': 'ft',  'fi': 'fi',  'fl': 'fl',  'st': 'st',
    "⁰": "0", "¹": "1", "²": "2", "³": "3", "⁴": "4", "⁵": "5", "⁶": "6", "⁷": "7", "⁸": "8", "⁹": "9",
    "₀": "0", "₁": "1", "₂": "2", "₃": "3", "₄": "4", "₅": "5", "₆": "6", "₇": "7", "₈": "8", "₉": "9",
    "’": "", "'": "", "ʼ": "", "‘": "", "‛": "", "´": "", "`": "", "′": "", "‵": "", "՚": "", "ꞌ": "", "Ꞌ": "",
    "-": ""
})

def simplifyWord (sWord):
    "word simplication before calculating distance between words"
    sWord = sWord.lower().translate(_xTransCharsForSimplification)
    sNewWord = ""
    for i, c in enumerate(sWord, 1):
        if c != sWord[i:i+1] or (c == 'e' and sWord[i:i+2] != "ee"):  # exception for <e> to avoid confusion between crée / créai
            sNewWord += c
    return sNewWord.replace("eau", "o").replace("au", "o").replace("ei", "e").replace("ai", "ei").replace("ph", "f")


def cleanWord (sWord):
    "remove letters repeated more than 2 times"
    return re.sub("(.)\\1{2,}", '\\1\\1', sWord)