intl-messageformat-parser
Version:
Parses ICU Message strings into an AST via JavaScript.
384 lines (383 loc) • 14.9 kB
JavaScript
;
Object.defineProperty(exports, "__esModule", { value: true });
exports.parseNumberSkeleton = exports.parseDateTimeSkeleton = void 0;
var tslib_1 = require("tslib");
/**
* https://unicode.org/reports/tr35/tr35-dates.html#Date_Field_Symbol_Table
* Credit: https://github.com/caridy/intl-datetimeformat-pattern/blob/master/index.js
* with some tweaks
*/
var DATE_TIME_REGEX = /(?:[Eec]{1,6}|G{1,5}|[Qq]{1,5}|(?:[yYur]+|U{1,5})|[ML]{1,5}|d{1,2}|D{1,3}|F{1}|[abB]{1,5}|[hkHK]{1,2}|w{1,2}|W{1}|m{1,2}|s{1,2}|[zZOvVxX]{1,4})(?=([^']*'[^']*')*[^']*$)/g;
/**
* Parse Date time skeleton into Intl.DateTimeFormatOptions
* Ref: https://unicode.org/reports/tr35/tr35-dates.html#Date_Field_Symbol_Table
* @public
* @param skeleton skeleton string
*/
function parseDateTimeSkeleton(skeleton) {
var result = {};
skeleton.replace(DATE_TIME_REGEX, function (match) {
var len = match.length;
switch (match[0]) {
// Era
case 'G':
result.era = len === 4 ? 'long' : len === 5 ? 'narrow' : 'short';
break;
// Year
case 'y':
result.year = len === 2 ? '2-digit' : 'numeric';
break;
case 'Y':
case 'u':
case 'U':
case 'r':
throw new RangeError('`Y/u/U/r` (year) patterns are not supported, use `y` instead');
// Quarter
case 'q':
case 'Q':
throw new RangeError('`q/Q` (quarter) patterns are not supported');
// Month
case 'M':
case 'L':
result.month = ['numeric', '2-digit', 'short', 'long', 'narrow'][len - 1];
break;
// Week
case 'w':
case 'W':
throw new RangeError('`w/W` (week) patterns are not supported');
case 'd':
result.day = ['numeric', '2-digit'][len - 1];
break;
case 'D':
case 'F':
case 'g':
throw new RangeError('`D/F/g` (day) patterns are not supported, use `d` instead');
// Weekday
case 'E':
result.weekday = len === 4 ? 'short' : len === 5 ? 'narrow' : 'short';
break;
case 'e':
if (len < 4) {
throw new RangeError('`e..eee` (weekday) patterns are not supported');
}
result.weekday = ['short', 'long', 'narrow', 'short'][len - 4];
break;
case 'c':
if (len < 4) {
throw new RangeError('`c..ccc` (weekday) patterns are not supported');
}
result.weekday = ['short', 'long', 'narrow', 'short'][len - 4];
break;
// Period
case 'a': // AM, PM
result.hour12 = true;
break;
case 'b': // am, pm, noon, midnight
case 'B': // flexible day periods
throw new RangeError('`b/B` (period) patterns are not supported, use `a` instead');
// Hour
case 'h':
result.hourCycle = 'h12';
result.hour = ['numeric', '2-digit'][len - 1];
break;
case 'H':
result.hourCycle = 'h23';
result.hour = ['numeric', '2-digit'][len - 1];
break;
case 'K':
result.hourCycle = 'h11';
result.hour = ['numeric', '2-digit'][len - 1];
break;
case 'k':
result.hourCycle = 'h24';
result.hour = ['numeric', '2-digit'][len - 1];
break;
case 'j':
case 'J':
case 'C':
throw new RangeError('`j/J/C` (hour) patterns are not supported, use `h/H/K/k` instead');
// Minute
case 'm':
result.minute = ['numeric', '2-digit'][len - 1];
break;
// Second
case 's':
result.second = ['numeric', '2-digit'][len - 1];
break;
case 'S':
case 'A':
throw new RangeError('`S/A` (second) patterns are not supported, use `s` instead');
// Zone
case 'z': // 1..3, 4: specific non-location format
result.timeZoneName = len < 4 ? 'short' : 'long';
break;
case 'Z': // 1..3, 4, 5: The ISO8601 varios formats
case 'O': // 1, 4: miliseconds in day short, long
case 'v': // 1, 4: generic non-location format
case 'V': // 1, 2, 3, 4: time zone ID or city
case 'X': // 1, 2, 3, 4: The ISO8601 varios formats
case 'x': // 1, 2, 3, 4: The ISO8601 varios formats
throw new RangeError('`Z/O/v/V/X/x` (timeZone) patterns are not supported, use `z` instead');
}
return '';
});
return result;
}
exports.parseDateTimeSkeleton = parseDateTimeSkeleton;
function icuUnitToEcma(unit) {
return unit.replace(/^(.*?)-/, '');
}
var FRACTION_PRECISION_REGEX = /^\.(?:(0+)(\*)?|(#+)|(0+)(#+))$/g;
var SIGNIFICANT_PRECISION_REGEX = /^(@+)?(\+|#+)?$/g;
var INTEGER_WIDTH_REGEX = /(\*)(0+)|(#+)(0+)|(0+)/g;
var CONCISE_INTEGER_WIDTH_REGEX = /^(0+)$/;
function parseSignificantPrecision(str) {
var result = {};
str.replace(SIGNIFICANT_PRECISION_REGEX, function (_, g1, g2) {
// @@@ case
if (typeof g2 !== 'string') {
result.minimumSignificantDigits = g1.length;
result.maximumSignificantDigits = g1.length;
}
// @@@+ case
else if (g2 === '+') {
result.minimumSignificantDigits = g1.length;
}
// .### case
else if (g1[0] === '#') {
result.maximumSignificantDigits = g1.length;
}
// .@@## or .@@@ case
else {
result.minimumSignificantDigits = g1.length;
result.maximumSignificantDigits =
g1.length + (typeof g2 === 'string' ? g2.length : 0);
}
return '';
});
return result;
}
function parseSign(str) {
switch (str) {
case 'sign-auto':
return {
signDisplay: 'auto',
};
case 'sign-accounting':
case '()':
return {
currencySign: 'accounting',
};
case 'sign-always':
case '+!':
return {
signDisplay: 'always',
};
case 'sign-accounting-always':
case '()!':
return {
signDisplay: 'always',
currencySign: 'accounting',
};
case 'sign-except-zero':
case '+?':
return {
signDisplay: 'exceptZero',
};
case 'sign-accounting-except-zero':
case '()?':
return {
signDisplay: 'exceptZero',
currencySign: 'accounting',
};
case 'sign-never':
case '+_':
return {
signDisplay: 'never',
};
}
}
function parseConciseScientificAndEngineeringStem(stem) {
// Engineering
var result;
if (stem[0] === 'E' && stem[1] === 'E') {
result = {
notation: 'engineering',
};
stem = stem.slice(2);
}
else if (stem[0] === 'E') {
result = {
notation: 'scientific',
};
stem = stem.slice(1);
}
if (result) {
var signDisplay = stem.slice(0, 2);
if (signDisplay === '+!') {
result.signDisplay = 'always';
stem = stem.slice(2);
}
else if (signDisplay === '+?') {
result.signDisplay = 'exceptZero';
stem = stem.slice(2);
}
if (!CONCISE_INTEGER_WIDTH_REGEX.test(stem)) {
throw new Error('Malformed concise eng/scientific notation');
}
result.minimumIntegerDigits = stem.length;
}
return result;
}
function parseNotationOptions(opt) {
var result = {};
var signOpts = parseSign(opt);
if (signOpts) {
return signOpts;
}
return result;
}
/**
* https://github.com/unicode-org/icu/blob/master/docs/userguide/format_parse/numbers/skeletons.md#skeleton-stems-and-options
*/
function parseNumberSkeleton(tokens) {
var result = {};
for (var _i = 0, tokens_1 = tokens; _i < tokens_1.length; _i++) {
var token = tokens_1[_i];
switch (token.stem) {
case 'percent':
case '%':
result.style = 'percent';
continue;
case '%x100':
result.style = 'percent';
result.scale = 100;
continue;
case 'currency':
result.style = 'currency';
result.currency = token.options[0];
continue;
case 'group-off':
case ',_':
result.useGrouping = false;
continue;
case 'precision-integer':
case '.':
result.maximumFractionDigits = 0;
continue;
case 'measure-unit':
case 'unit':
result.style = 'unit';
result.unit = icuUnitToEcma(token.options[0]);
continue;
case 'compact-short':
case 'K':
result.notation = 'compact';
result.compactDisplay = 'short';
continue;
case 'compact-long':
case 'KK':
result.notation = 'compact';
result.compactDisplay = 'long';
continue;
case 'scientific':
result = tslib_1.__assign(tslib_1.__assign(tslib_1.__assign({}, result), { notation: 'scientific' }), token.options.reduce(function (all, opt) { return (tslib_1.__assign(tslib_1.__assign({}, all), parseNotationOptions(opt))); }, {}));
continue;
case 'engineering':
result = tslib_1.__assign(tslib_1.__assign(tslib_1.__assign({}, result), { notation: 'engineering' }), token.options.reduce(function (all, opt) { return (tslib_1.__assign(tslib_1.__assign({}, all), parseNotationOptions(opt))); }, {}));
continue;
case 'notation-simple':
result.notation = 'standard';
continue;
// https://github.com/unicode-org/icu/blob/master/icu4c/source/i18n/unicode/unumberformatter.h
case 'unit-width-narrow':
result.currencyDisplay = 'narrowSymbol';
result.unitDisplay = 'narrow';
continue;
case 'unit-width-short':
result.currencyDisplay = 'code';
result.unitDisplay = 'short';
continue;
case 'unit-width-full-name':
result.currencyDisplay = 'name';
result.unitDisplay = 'long';
continue;
case 'unit-width-iso-code':
result.currencyDisplay = 'symbol';
continue;
case 'scale':
result.scale = parseFloat(token.options[0]);
continue;
// https://unicode-org.github.io/icu/userguide/format_parse/numbers/skeletons.html#integer-width
case 'integer-width':
if (token.options.length > 1) {
throw new RangeError('integer-width stems only accept a single optional option');
}
token.options[0].replace(INTEGER_WIDTH_REGEX, function (_, g1, g2, g3, g4, g5) {
if (g1) {
result.minimumIntegerDigits = g2.length;
}
else if (g3 && g4) {
throw new Error('We currently do not support maximum integer digits');
}
else if (g5) {
throw new Error('We currently do not support exact integer digits');
}
return '';
});
continue;
}
// https://unicode-org.github.io/icu/userguide/format_parse/numbers/skeletons.html#integer-width
if (CONCISE_INTEGER_WIDTH_REGEX.test(token.stem)) {
result.minimumIntegerDigits = token.stem.length;
continue;
}
if (FRACTION_PRECISION_REGEX.test(token.stem)) {
// Precision
// https://unicode-org.github.io/icu/userguide/format_parse/numbers/skeletons.html#fraction-precision
// precision-integer case
if (token.options.length > 1) {
throw new RangeError('Fraction-precision stems only accept a single optional option');
}
token.stem.replace(FRACTION_PRECISION_REGEX, function (_, g1, g2, g3, g4, g5) {
// .000* case (before ICU67 it was .000+)
if (g2 === '*') {
result.minimumFractionDigits = g1.length;
}
// .### case
else if (g3 && g3[0] === '#') {
result.maximumFractionDigits = g3.length;
}
// .00## case
else if (g4 && g5) {
result.minimumFractionDigits = g4.length;
result.maximumFractionDigits = g4.length + g5.length;
}
else {
result.minimumFractionDigits = g1.length;
result.maximumFractionDigits = g1.length;
}
return '';
});
if (token.options.length) {
result = tslib_1.__assign(tslib_1.__assign({}, result), parseSignificantPrecision(token.options[0]));
}
continue;
}
// https://unicode-org.github.io/icu/userguide/format_parse/numbers/skeletons.html#significant-digits-precision
if (SIGNIFICANT_PRECISION_REGEX.test(token.stem)) {
result = tslib_1.__assign(tslib_1.__assign({}, result), parseSignificantPrecision(token.stem));
continue;
}
var signOpts = parseSign(token.stem);
if (signOpts) {
result = tslib_1.__assign(tslib_1.__assign({}, result), signOpts);
}
var conciseScientificAndEngineeringOpts = parseConciseScientificAndEngineeringStem(token.stem);
if (conciseScientificAndEngineeringOpts) {
result = tslib_1.__assign(tslib_1.__assign({}, result), conciseScientificAndEngineeringOpts);
}
}
return result;
}
exports.parseNumberSkeleton = parseNumberSkeleton;