6.locales-currencies-tz.js

// Sect 6.2 Language Tags
// ======================

import {
    expBCP47Syntax,
    expExtSequences,
    expVariantDupes,
    expSingletonDupes
} from './exp';

import {
    hop,
    arrJoin,
    arrSlice
} from "./util.js";

// Default locale is the first-added locale data for us
export let defaultLocale;
export function setDefaultLocale(locale) {
    defaultLocale = locale;
}

// IANA Subtag Registry redundant tag and subtag maps
const redundantTags = {
    tags: {
        "art-lojban": "jbo",
        "i-ami": "ami",
        "i-bnn": "bnn",
        "i-hak": "hak",
        "i-klingon": "tlh",
        "i-lux": "lb",
        "i-navajo": "nv",
        "i-pwn": "pwn",
        "i-tao": "tao",
        "i-tay": "tay",
        "i-tsu": "tsu",
        "no-bok": "nb",
        "no-nyn": "nn",
        "sgn-BE-FR": "sfb",
        "sgn-BE-NL": "vgt",
        "sgn-CH-DE": "sgg",
        "zh-guoyu": "cmn",
        "zh-hakka": "hak",
        "zh-min-nan": "nan",
        "zh-xiang": "hsn",
        "sgn-BR": "bzs",
        "sgn-CO": "csn",
        "sgn-DE": "gsg",
        "sgn-DK": "dsl",
        "sgn-ES": "ssp",
        "sgn-FR": "fsl",
        "sgn-GB": "bfi",
        "sgn-GR": "gss",
        "sgn-IE": "isg",
        "sgn-IT": "ise",
        "sgn-JP": "jsl",
        "sgn-MX": "mfs",
        "sgn-NI": "ncs",
        "sgn-NL": "dse",
        "sgn-NO": "nsl",
        "sgn-PT": "psr",
        "sgn-SE": "swl",
        "sgn-US": "ase",
        "sgn-ZA": "sfs",
        "zh-cmn": "cmn",
        "zh-cmn-Hans": "cmn-Hans",
        "zh-cmn-Hant": "cmn-Hant",
        "zh-gan": "gan",
        "zh-wuu": "wuu",
        "zh-yue": "yue"
    },
    subtags: {
        BU: "MM",
        DD: "DE",
        FX: "FR",
        TP: "TL",
        YD: "YE",
        ZR: "CD",
        heploc: "alalc97",
        'in': "id",
        iw: "he",
        ji: "yi",
        jw: "jv",
        mo: "ro",
        ayx: "nun",
        bjd: "drl",
        ccq: "rki",
        cjr: "mom",
        cka: "cmr",
        cmk: "xch",
        drh: "khk",
        drw: "prs",
        gav: "dev",
        hrr: "jal",
        ibi: "opa",
        kgh: "kml",
        lcq: "ppr",
        mst: "mry",
        myt: "mry",
        sca: "hle",
        tie: "ras",
        tkk: "twm",
        tlw: "weo",
        tnf: "prs",
        ybd: "rki",
        yma: "lrr"
    },
    extLang: {
        aao: ["aao", "ar"],
        abh: ["abh", "ar"],
        abv: ["abv", "ar"],
        acm: ["acm", "ar"],
        acq: ["acq", "ar"],
        acw: ["acw", "ar"],
        acx: ["acx", "ar"],
        acy: ["acy", "ar"],
        adf: ["adf", "ar"],
        ads: ["ads", "sgn"],
        aeb: ["aeb", "ar"],
        aec: ["aec", "ar"],
        aed: ["aed", "sgn"],
        aen: ["aen", "sgn"],
        afb: ["afb", "ar"],
        afg: ["afg", "sgn"],
        ajp: ["ajp", "ar"],
        apc: ["apc", "ar"],
        apd: ["apd", "ar"],
        arb: ["arb", "ar"],
        arq: ["arq", "ar"],
        ars: ["ars", "ar"],
        ary: ["ary", "ar"],
        arz: ["arz", "ar"],
        ase: ["ase", "sgn"],
        asf: ["asf", "sgn"],
        asp: ["asp", "sgn"],
        asq: ["asq", "sgn"],
        asw: ["asw", "sgn"],
        auz: ["auz", "ar"],
        avl: ["avl", "ar"],
        ayh: ["ayh", "ar"],
        ayl: ["ayl", "ar"],
        ayn: ["ayn", "ar"],
        ayp: ["ayp", "ar"],
        bbz: ["bbz", "ar"],
        bfi: ["bfi", "sgn"],
        bfk: ["bfk", "sgn"],
        bjn: ["bjn", "ms"],
        bog: ["bog", "sgn"],
        bqn: ["bqn", "sgn"],
        bqy: ["bqy", "sgn"],
        btj: ["btj", "ms"],
        bve: ["bve", "ms"],
        bvl: ["bvl", "sgn"],
        bvu: ["bvu", "ms"],
        bzs: ["bzs", "sgn"],
        cdo: ["cdo", "zh"],
        cds: ["cds", "sgn"],
        cjy: ["cjy", "zh"],
        cmn: ["cmn", "zh"],
        coa: ["coa", "ms"],
        cpx: ["cpx", "zh"],
        csc: ["csc", "sgn"],
        csd: ["csd", "sgn"],
        cse: ["cse", "sgn"],
        csf: ["csf", "sgn"],
        csg: ["csg", "sgn"],
        csl: ["csl", "sgn"],
        csn: ["csn", "sgn"],
        csq: ["csq", "sgn"],
        csr: ["csr", "sgn"],
        czh: ["czh", "zh"],
        czo: ["czo", "zh"],
        doq: ["doq", "sgn"],
        dse: ["dse", "sgn"],
        dsl: ["dsl", "sgn"],
        dup: ["dup", "ms"],
        ecs: ["ecs", "sgn"],
        esl: ["esl", "sgn"],
        esn: ["esn", "sgn"],
        eso: ["eso", "sgn"],
        eth: ["eth", "sgn"],
        fcs: ["fcs", "sgn"],
        fse: ["fse", "sgn"],
        fsl: ["fsl", "sgn"],
        fss: ["fss", "sgn"],
        gan: ["gan", "zh"],
        gds: ["gds", "sgn"],
        gom: ["gom", "kok"],
        gse: ["gse", "sgn"],
        gsg: ["gsg", "sgn"],
        gsm: ["gsm", "sgn"],
        gss: ["gss", "sgn"],
        gus: ["gus", "sgn"],
        hab: ["hab", "sgn"],
        haf: ["haf", "sgn"],
        hak: ["hak", "zh"],
        hds: ["hds", "sgn"],
        hji: ["hji", "ms"],
        hks: ["hks", "sgn"],
        hos: ["hos", "sgn"],
        hps: ["hps", "sgn"],
        hsh: ["hsh", "sgn"],
        hsl: ["hsl", "sgn"],
        hsn: ["hsn", "zh"],
        icl: ["icl", "sgn"],
        ils: ["ils", "sgn"],
        inl: ["inl", "sgn"],
        ins: ["ins", "sgn"],
        ise: ["ise", "sgn"],
        isg: ["isg", "sgn"],
        isr: ["isr", "sgn"],
        jak: ["jak", "ms"],
        jax: ["jax", "ms"],
        jcs: ["jcs", "sgn"],
        jhs: ["jhs", "sgn"],
        jls: ["jls", "sgn"],
        jos: ["jos", "sgn"],
        jsl: ["jsl", "sgn"],
        jus: ["jus", "sgn"],
        kgi: ["kgi", "sgn"],
        knn: ["knn", "kok"],
        kvb: ["kvb", "ms"],
        kvk: ["kvk", "sgn"],
        kvr: ["kvr", "ms"],
        kxd: ["kxd", "ms"],
        lbs: ["lbs", "sgn"],
        lce: ["lce", "ms"],
        lcf: ["lcf", "ms"],
        liw: ["liw", "ms"],
        lls: ["lls", "sgn"],
        lsg: ["lsg", "sgn"],
        lsl: ["lsl", "sgn"],
        lso: ["lso", "sgn"],
        lsp: ["lsp", "sgn"],
        lst: ["lst", "sgn"],
        lsy: ["lsy", "sgn"],
        ltg: ["ltg", "lv"],
        lvs: ["lvs", "lv"],
        lzh: ["lzh", "zh"],
        max: ["max", "ms"],
        mdl: ["mdl", "sgn"],
        meo: ["meo", "ms"],
        mfa: ["mfa", "ms"],
        mfb: ["mfb", "ms"],
        mfs: ["mfs", "sgn"],
        min: ["min", "ms"],
        mnp: ["mnp", "zh"],
        mqg: ["mqg", "ms"],
        mre: ["mre", "sgn"],
        msd: ["msd", "sgn"],
        msi: ["msi", "ms"],
        msr: ["msr", "sgn"],
        mui: ["mui", "ms"],
        mzc: ["mzc", "sgn"],
        mzg: ["mzg", "sgn"],
        mzy: ["mzy", "sgn"],
        nan: ["nan", "zh"],
        nbs: ["nbs", "sgn"],
        ncs: ["ncs", "sgn"],
        nsi: ["nsi", "sgn"],
        nsl: ["nsl", "sgn"],
        nsp: ["nsp", "sgn"],
        nsr: ["nsr", "sgn"],
        nzs: ["nzs", "sgn"],
        okl: ["okl", "sgn"],
        orn: ["orn", "ms"],
        ors: ["ors", "ms"],
        pel: ["pel", "ms"],
        pga: ["pga", "ar"],
        pks: ["pks", "sgn"],
        prl: ["prl", "sgn"],
        prz: ["prz", "sgn"],
        psc: ["psc", "sgn"],
        psd: ["psd", "sgn"],
        pse: ["pse", "ms"],
        psg: ["psg", "sgn"],
        psl: ["psl", "sgn"],
        pso: ["pso", "sgn"],
        psp: ["psp", "sgn"],
        psr: ["psr", "sgn"],
        pys: ["pys", "sgn"],
        rms: ["rms", "sgn"],
        rsi: ["rsi", "sgn"],
        rsl: ["rsl", "sgn"],
        sdl: ["sdl", "sgn"],
        sfb: ["sfb", "sgn"],
        sfs: ["sfs", "sgn"],
        sgg: ["sgg", "sgn"],
        sgx: ["sgx", "sgn"],
        shu: ["shu", "ar"],
        slf: ["slf", "sgn"],
        sls: ["sls", "sgn"],
        sqk: ["sqk", "sgn"],
        sqs: ["sqs", "sgn"],
        ssh: ["ssh", "ar"],
        ssp: ["ssp", "sgn"],
        ssr: ["ssr", "sgn"],
        svk: ["svk", "sgn"],
        swc: ["swc", "sw"],
        swh: ["swh", "sw"],
        swl: ["swl", "sgn"],
        syy: ["syy", "sgn"],
        tmw: ["tmw", "ms"],
        tse: ["tse", "sgn"],
        tsm: ["tsm", "sgn"],
        tsq: ["tsq", "sgn"],
        tss: ["tss", "sgn"],
        tsy: ["tsy", "sgn"],
        tza: ["tza", "sgn"],
        ugn: ["ugn", "sgn"],
        ugy: ["ugy", "sgn"],
        ukl: ["ukl", "sgn"],
        uks: ["uks", "sgn"],
        urk: ["urk", "ms"],
        uzn: ["uzn", "uz"],
        uzs: ["uzs", "uz"],
        vgt: ["vgt", "sgn"],
        vkk: ["vkk", "ms"],
        vkt: ["vkt", "ms"],
        vsi: ["vsi", "sgn"],
        vsl: ["vsl", "sgn"],
        vsv: ["vsv", "sgn"],
        wuu: ["wuu", "zh"],
        xki: ["xki", "sgn"],
        xml: ["xml", "sgn"],
        xmm: ["xmm", "ms"],
        xms: ["xms", "sgn"],
        yds: ["yds", "sgn"],
        ysl: ["ysl", "sgn"],
        yue: ["yue", "zh"],
        zib: ["zib", "sgn"],
        zlm: ["zlm", "ms"],
        zmi: ["zmi", "ms"],
        zsl: ["zsl", "sgn"],
        zsm: ["zsm", "ms"]
    }
};

/**
 * Convert only a-z to uppercase as per section 6.1 of the spec
 */
export function toLatinUpperCase (str) {
    let i = str.length;

    while (i--) {
        let ch = str.charAt(i);

        if (ch >= "a" && ch <= "z")
            str = str.slice(0, i) + ch.toUpperCase() + str.slice(i+1);
    }

    return str;
}

/**
 * The IsStructurallyValidLanguageTag abstract operation verifies that the locale
 * argument (which must be a String value)
 *
 * - represents a well-formed BCP 47 language tag as specified in RFC 5646 section
 *   2.1, or successor,
 * - does not include duplicate variant subtags, and
 * - does not include duplicate singleton subtags.
 *
 * The abstract operation returns true if locale can be generated from the ABNF
 * grammar in section 2.1 of the RFC, starting with Language-Tag, and does not
 * contain duplicate variant or singleton subtags (other than as a private use
 * subtag). It returns false otherwise. Terminal value characters in the grammar are
 * interpreted as the Unicode equivalents of the ASCII octet values given.
 */
export function /* 6.2.2 */IsStructurallyValidLanguageTag(locale) {
    // represents a well-formed BCP 47 language tag as specified in RFC 5646
    if (!expBCP47Syntax.test(locale))
        return false;

    // does not include duplicate variant subtags, and
    if (expVariantDupes.test(locale))
        return false;

    // does not include duplicate singleton subtags.
    if (expSingletonDupes.test(locale))
        return false;

    return true;
}

/**
 * The CanonicalizeLanguageTag abstract operation returns the canonical and case-
 * regularized form of the locale argument (which must be a String value that is
 * a structurally valid BCP 47 language tag as verified by the
 * IsStructurallyValidLanguageTag abstract operation). It takes the steps
 * specified in RFC 5646 section 4.5, or successor, to bring the language tag
 * into canonical form, and to regularize the case of the subtags, but does not
 * take the steps to bring a language tag into “extlang form” and to reorder
 * variant subtags.

 * The specifications for extensions to BCP 47 language tags, such as RFC 6067,
 * may include canonicalization rules for the extension subtag sequences they
 * define that go beyond the canonicalization rules of RFC 5646 section 4.5.
 * Implementations are allowed, but not required, to apply these additional rules.
 */
export function /* 6.2.3 */CanonicalizeLanguageTag (locale) {
    let match, parts;

    // A language tag is in 'canonical form' when the tag is well-formed
    // according to the rules in Sections 2.1 and 2.2

    // Section 2.1 says all subtags use lowercase...
    locale = locale.toLowerCase();

    // ...with 2 exceptions: 'two-letter and four-letter subtags that neither
    // appear at the start of the tag nor occur after singletons.  Such two-letter
    // subtags are all uppercase (as in the tags "en-CA-x-ca" or "sgn-BE-FR") and
    // four-letter subtags are titlecase (as in the tag "az-Latn-x-latn").
    parts = locale.split('-');
    for (let i = 1, max = parts.length; i < max; i++) {
        // Two-letter subtags are all uppercase
        if (parts[i].length === 2)
            parts[i] = parts[i].toUpperCase();

        // Four-letter subtags are titlecase
        else if (parts[i].length === 4)
            parts[i] = parts[i].charAt(0).toUpperCase() + parts[i].slice(1);

        // Is it a singleton?
        else if (parts[i].length === 1 && parts[i] !== 'x')
            break;
    }
    locale = arrJoin.call(parts, '-');

    // The steps laid out in RFC 5646 section 4.5 are as follows:

    // 1.  Extension sequences are ordered into case-insensitive ASCII order
    //     by singleton subtag.
    if ((match = locale.match(expExtSequences)) && match.length > 1) {
        // The built-in sort() sorts by ASCII order, so use that
        match.sort();

        // Replace all extensions with the joined, sorted array
        locale = locale.replace(
            RegExp('(?:' + expExtSequences.source + ')+', 'i'),
            arrJoin.call(match, '')
        );
    }

    // 2.  Redundant or grandfathered tags are replaced by their 'Preferred-
    //     Value', if there is one.
    if (hop.call(redundantTags.tags, locale))
        locale = redundantTags.tags[locale];

    // 3.  Subtags are replaced by their 'Preferred-Value', if there is one.
    //     For extlangs, the original primary language subtag is also
    //     replaced if there is a primary language subtag in the 'Preferred-
    //     Value'.
    parts = locale.split('-');

    for (let i = 1, max = parts.length; i < max; i++) {
        if (hop.call(redundantTags.subtags, parts[i]))
            parts[i] = redundantTags.subtags[parts[i]];

        else if (hop.call(redundantTags.extLang, parts[i])) {
            parts[i] = redundantTags.extLang[parts[i]][0];

            // For extlang tags, the prefix needs to be removed if it is redundant
            if (i === 1 && redundantTags.extLang[parts[1]][1] === parts[0]) {
                parts = arrSlice.call(parts, i++);
                max -= 1;
            }
        }
    }

    return arrJoin.call(parts, '-');
}

/**
 * The DefaultLocale abstract operation returns a String value representing the
 * structurally valid (6.2.2) and canonicalized (6.2.3) BCP 47 language tag for the
 * host environment’s current locale.
 */
export function /* 6.2.4 */DefaultLocale () {
    return defaultLocale;
}

// Sect 6.3 Currency Codes
// =======================

const expCurrencyCode = /^[A-Z]{3}$/;

/**
 * The IsWellFormedCurrencyCode abstract operation verifies that the currency argument
 * (after conversion to a String value) represents a well-formed 3-letter ISO currency
 * code. The following steps are taken:
 */
export function /* 6.3.1 */IsWellFormedCurrencyCode(currency) {
    // 1. Let `c` be ToString(currency)
    let c = String(currency);

    // 2. Let `normalized` be the result of mapping c to upper case as described
    //    in 6.1.
    let normalized = toLatinUpperCase(c);

    // 3. If the string length of normalized is not 3, return false.
    // 4. If normalized contains any character that is not in the range "A" to "Z"
    //    (U+0041 to U+005A), return false.
    if (expCurrencyCode.test(normalized) === false)
        return false;

    // 5. Return true
    return true;
}