"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.Tokenizer = exports.Charset = void 0;
const separators_1 = require("./edi/separators");
class Charset {
    constructor(name, configuration, admissibleAlphabet, unicode = false) {
        this.name = name;
        const exclude = configuration.delimiters();
        const alphas = this.compile(admissibleAlphabet, exclude, unicode);
        this.alpha = alphas[0];
        this.alphanumeric = alphas[1];
        if (unicode) {
            this.numeric = /[-]?[\p{Nd}]*/g;
            this.decimal = /[\p{Nd}]*/gu;
        }
        else {
            this.numeric = /[-]?[0-9]*/g;
            this.decimal = /[0-9]*/g;
        }
    }
    compile(admissibleAlphabet, excludes, unicode = false) {
        const flag = unicode ? "gu" : "g";
        let output = "";
        for (const seq of admissibleAlphabet) {
            if (seq.length > 1) {
                const start = seq[0].codePointAt(0);
                const end = seq[1].codePointAt(0);
                if (start && end) {
                    for (let i = start; i <= end; i++) {
                        if (!excludes.includes(i)) {
                            output += separators_1.Separators.escapeIfNeeded(String.fromCodePoint(i));
                        }
                    }
                }
            }
            else {
                const idx = seq[0].codePointAt(0);
                if (idx) {
                    output += separators_1.Separators.escapeIfNeeded(String.fromCodePoint(idx));
                }
            }
        }
        const ret = [];
        ret.push(new RegExp("[" + output + "]*", flag));
        ret.push(new RegExp("[0-9" + output + "]*", flag));
        return ret;
    }
}
exports.Charset = Charset;
class UNOA extends Charset {
    constructor(config) {
        super("UNOA", config, UNOA.charset);
    }
}
UNOA.charset = [
    ["\u0020"],
    ["\u0028", "\u0029"],
    ["\u002C", "\u002F"],
    ["\u003D"],
    ["\u0041", "\u005A"]
];
class UNOB extends Charset {
    constructor(config) {
        super("UNOB", config, UNOB.charset);
    }
}
UNOB.charset = [
    ["\u0020", "\u0022"],
    ["\u0041", "\u005A"],
    ["\u0025", "\u002F"],
    ["\u003A", "\u003F"],
    ["\u0061", "\u007A"]
];
class UNOC extends Charset {
    constructor(config) {
        super("UNOC", config, UNOC.charset);
    }
}
UNOC.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0", "\u00FF"]
];
class UNOD extends Charset {
    constructor(config) {
        super("UNOD", config, UNOD.charset);
    }
}
UNOD.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0"], ["\u0104"], ["\u02D8"], ["\u0141"], ["\u00A4"], ["\u013D"], ["\u015A"], ["\u00A7"], ["\u0048"], ["\u0160"], ["\u015E"], ["\u0164"], ["\u0179"], ["\u00AD"], ["\u017D"], ["\u017B"],
    ["\u00B0"], ["\u0105"], ["\u02DB"], ["\u0142"], ["\u00B4"], ["\u013E"], ["\u015B"], ["\u02C7"], ["\u00B8"], ["\u0161"], ["\u015F"], ["\u0165"], ["\u017A"], ["\u02DD"], ["\u017E"], ["\u017C"],
    ["\u0154"], ["\u00C1"], ["\u00C2"], ["\u0102"], ["\u00C4"], ["\u0139"], ["\u0106"], ["\u00C7"], ["\u010C"], ["\u00C9"], ["\u0118"], ["\u00CB"], ["\u011A"], ["\u00CD"], ["\u00CE"], ["\u010E"],
    ["\u0110"], ["\u0143"], ["\u0147"], ["\u00D3"], ["\u00D4"], ["\u0150"], ["\u00D6"], ["\u00D7"], ["\u0158"], ["\u016E"], ["\u00DA"], ["\u0170"], ["\u00DC"], ["\u00DD"], ["\u0162"], ["\u00DF"],
    ["\u0155"], ["\u00E1"], ["\u00E2"], ["\u0103"], ["\u00E4"], ["\u013A"], ["\u0107"], ["\u00E7"], ["\u010D"], ["\u00E9"], ["\u0119"], ["\u00EB"], ["\u011B"], ["\u00ED"], ["\u00EE"], ["\u010F"],
    ["\u0111"], ["\u0144"], ["\u0148"], ["\u00F3"], ["\u00F4"], ["\u0151"], ["\u00F6"], ["\u00F7"], ["\u0159"], ["\u016F"], ["\u00FA"], ["\u0171"], ["\u00FC"], ["\u00FD"], ["\u0163"], ["\u02D9"]
];
class UNOE extends Charset {
    constructor(config) {
        super("UNOE", config, UNOE.charset);
    }
}
UNOE.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0"], ["\u0401", "\u040C"], ["\u00AD"], ["\u040E", "\u044F"],
    ["\u2116"], ["\u0451", "\u045C"], ["\u00A7"], ["\u045E"], ["\u045F"]
];
class UNOF extends Charset {
    constructor(config) {
        super("UNOF", config, UNOF.charset);
    }
}
UNOF.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0"], ["\u2018", "\u2019"], ["\u00A3"], ["\u20AC"], ["\u20AF"], ["\u00A6", "\u00A9"], ["\u037A"], ["\u00AB", "\u00AD"], ["\u2015"],
    ["\u00B0", "\u00B3"], ["\u0384", "\u0386"], ["\u00B7"], ["\u0388", "\u038A"], ["\u00BB"], ["\u038C", "\u03A1"],
    ["\u03A3", "\u03CE"]
];
class UNOG extends Charset {
    constructor(config) {
        super("UNOG", config, UNOG.charset);
    }
}
UNOG.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0"], ["\u0126"], ["\u02D8"], ["\u00A3"], ["\u00A4"], ["\u0124"], ["\u00A7"], ["\u00A8"], ["\u0130"], ["\u015E"], ["\u011E"], ["\u0134"], ["\u00AD"], ["\u017B"],
    ["\u00B0"], ["\u0127"], ["\u00B2"], ["\u00B3", "\u00B5"], ["\u0125"], ["\u00B7"], ["\u00B8"], ["\u0131"], ["\u015F"], ["\u011F"], ["\u0135"], ["\u00BD"], ["\u017C"],
    ["\u00C0", "\u00C2"], ["\u00C4"], ["\u010A"], ["\u0108"], ["\u00C7", "\u00CF"],
    ["\u00D1", "\u00D4"], ["\u0120"], ["\u00D6"], ["\u00D7"], ["\u011C"], ["\u00D9", "\u00DC"], ["\u016C"], ["\u015C"], ["\u00DF", "\u00E2"],
    ["\u00E4"], ["\u010B"], ["\u0109"], ["\u00E7", "\u00EF"],
    ["\u00F1", "\u00F4"], ["\u0121"], ["\u00F6"], ["\u00F7"], ["\u011D"], ["\u00F9", "\u00FC"], ["\u016D"], ["\u015D"], ["\u02D9"]
];
class UNOH extends Charset {
    constructor(config) {
        super("UNOH", config, UNOH.charset);
    }
}
UNOH.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0"], ["\u0104"], ["\u0138"], ["\u0156"], ["\u00A4"], ["\u0128"], ["\u013B"], ["\u00A7"], ["\u00A8"], ["\u0160"], ["\u0112"], ["\u0122"], ["\u0166"], ["\u00AD"], ["\u017D"], ["\u00AF"],
    ["\u00B0"], ["\u0105"], ["\u02DB"], ["\u0157"], ["\u00B4"], ["\u0129"], ["\u013C"], ["\u02C7"], ["\u00B8"], ["\u0161"], ["\u0113"], ["\u0123"], ["\u0167"], ["\u014A"], ["\u017E"], ["\u014B"],
    ["\u0100"], ["\u00C1", "\u00C6"], ["\u012E"], ["\u010C"], ["\u00C9"], ["\u0118"], ["\u00CB"], ["\u0116"], ["\u00CD"], ["\u00CE"], ["\u012A"],
    ["\u0110"], ["\u0145"], ["\u014C"], ["\u0136"], ["\u00D4", "\u00D8"], ["\u0172"], ["\u00DA", "\u00DC"], ["\u0168"], ["\u016A"], ["\u00DF"],
    ["\u0101"], ["\u00E1", "\u00E6"], ["\u012F"], ["\u010D"], ["\u00E9"], ["\u0119"], ["\u00EB"], ["\u0117"], ["\u00ED"], ["\u00EE"], ["\u0128"],
    ["\u0111"], ["\u0146"], ["\u014D"], ["\u0137"], ["\u00F4", "\u00F8"], ["\u0173"], ["\u00FA", "\u00FC"], ["\u0169"], ["\u0168"], ["\u02D9"]
];
class UNOI extends Charset {
    constructor(config) {
        super("UNOI", config, UNOI.charset);
    }
}
UNOI.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0"], ["\u00A4"], ["\u060C"], ["\u00AD"],
    ["\u061B"], ["\u061F"],
    ["\u0621", "\u063A"],
    ["\u0640", "\u0652"]
];
class UNOJ extends Charset {
    constructor(config) {
        super("UNOJ", config, UNOJ.charset);
    }
}
UNOJ.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0"], ["\u00A2", "\u00A9"], ["\u00D7"], ["\u00AB", "\u00B9"],
    ["\u00F7"], ["\u00BB", "\u00BE"],
    ["\u2017"], ["\u05D0", "\u05EA"],
    ["\u200E"], ["\u200F"]
];
class UNOK extends Charset {
    constructor(config) {
        super("UNOK", config, UNOK.charset);
    }
}
UNOK.charset = [
    ["\u0020", "\u002F"],
    ["\u003A", "\u007E"],
    ["\u00A0", "\u00CF"],
    ["\u011E"], ["\u00D1", "\u00DC"], ["\u0130"], ["\u015E"], ["\u00DF", "\u00EF"],
    ["\u011F"], ["\u00F1", "\u00FC"], ["\u0131"], ["\u015F"], ["\u00FF"]
];
class Tokenizer {
    constructor(config) {
        this.errors = {
            secondDecimalMark: function () {
                return new Error("Cannot accept a second decimal mark while parsing a number");
            }
        };
        this.regexes = this.setCharsetBasedOnConfig(config);
        this.regex = this.regexes.alphanumeric;
        this.buffer = "";
    }
    alpha() {
        this.regex = this.regexes.alpha;
    }
    alphanumeric() {
        this.regex = this.regexes.alphanumeric;
    }
    numeric() {
        this.regex = this.regexes.numeric;
    }
    decimal(chunk, index) {
        let result = ".";
        switch (this.regex) {
            case this.regexes.numeric:
                this.regex = this.regexes.decimal;
                break;
            case this.regexes.alpha:
            case this.regexes.alphanumeric:
                result = chunk.charAt(index);
                break;
            case this.regexes.decimal:
                throw this.errors.secondDecimalMark();
        }
        this.buffer += result;
    }
    setCharsetBasedOnConfig(config) {
        switch (config.charset) {
            case "UNOA":
                this.regexes = new UNOA(config);
                break;
            case "UNOB":
                this.regexes = new UNOB(config);
                break;
            case "UNOC":
                this.regexes = new UNOC(config);
                break;
            case "UNOD":
                this.regexes = new UNOD(config);
                break;
            case "UNOE":
                this.regexes = new UNOE(config);
                break;
            case "UNOF":
                this.regexes = new UNOF(config);
                break;
            case "UNOG":
                this.regexes = new UNOG(config);
                break;
            case "UNOH":
                this.regexes = new UNOH(config);
                break;
            case "UNOI":
                this.regexes = new UNOI(config);
                break;
            case "UNOJ":
                this.regexes = new UNOJ(config);
                break;
            case "UNOK":
                this.regexes = new UNOK(config);
                break;
            default:
                throw new Error(`Unsupported charset encoding '${config.charset}'`);
        }
        return this.regexes;
    }
    segment(chunk, index) {
        let code;
        const start = index;
        while ((code = chunk.charCodeAt(index) || 0) < 91 && code > 64) {
            index++;
        }
        this.buffer += chunk.slice(start, index);
        return index;
    }
    data(chunk, index) {
        this.regex.lastIndex = index;
        this.regex.test(chunk);
        this.buffer += chunk.slice(index, this.regex.lastIndex);
        return this.regex.lastIndex;
    }
    release(chunk, index) {
        this.buffer += chunk.charAt(index);
    }
    length() {
        return this.buffer.length - (this.regex === this.regexes.decimal ? 1 : 0);
    }
    content() {
        return this.buffer;
    }
}
exports.Tokenizer = Tokenizer;
//# sourceMappingURL=tokenizer.js.map