/*!
|
* XRegExp Unicode Base 4.0.0
|
* <xregexp.com>
|
* Steven Levithan (c) 2008-2017 MIT License
|
*/
|
|
export default (XRegExp) => {
|
|
/**
|
* Adds base support for Unicode matching:
|
* - Adds syntax `\p{..}` for matching Unicode tokens. Tokens can be inverted using `\P{..}` or
|
* `\p{^..}`. Token names ignore case, spaces, hyphens, and underscores. You can omit the
|
* braces for token names that are a single letter (e.g. `\pL` or `PL`).
|
* - Adds flag A (astral), which enables 21-bit Unicode support.
|
* - Adds the `XRegExp.addUnicodeData` method used by other addons to provide character data.
|
*
|
* Unicode Base relies on externally provided Unicode character data. Official addons are
|
* available to provide data for Unicode categories, scripts, blocks, and properties.
|
*
|
* @requires XRegExp
|
*/
|
|
// ==--------------------------==
|
// Private stuff
|
// ==--------------------------==
|
|
// Storage for Unicode data
|
const unicode = {};
|
|
// Reuse utils
|
const dec = XRegExp._dec;
|
const hex = XRegExp._hex;
|
const pad4 = XRegExp._pad4;
|
|
// Generates a token lookup name: lowercase, with hyphens, spaces, and underscores removed
|
function normalize(name) {
|
return name.replace(/[- _]+/g, '').toLowerCase();
|
}
|
|
// Gets the decimal code of a literal code unit, \xHH, \uHHHH, or a backslash-escaped literal
|
function charCode(chr) {
|
const esc = /^\\[xu](.+)/.exec(chr);
|
return esc ?
|
dec(esc[1]) :
|
chr.charCodeAt(chr[0] === '\\' ? 1 : 0);
|
}
|
|
// Inverts a list of ordered BMP characters and ranges
|
function invertBmp(range) {
|
let output = '';
|
let lastEnd = -1;
|
|
XRegExp.forEach(
|
range,
|
/(\\x..|\\u....|\\?[\s\S])(?:-(\\x..|\\u....|\\?[\s\S]))?/,
|
(m) => {
|
const start = charCode(m[1]);
|
if (start > (lastEnd + 1)) {
|
output += `\\u${pad4(hex(lastEnd + 1))}`;
|
if (start > (lastEnd + 2)) {
|
output += `-\\u${pad4(hex(start - 1))}`;
|
}
|
}
|
lastEnd = charCode(m[2] || m[1]);
|
}
|
);
|
|
if (lastEnd < 0xFFFF) {
|
output += `\\u${pad4(hex(lastEnd + 1))}`;
|
if (lastEnd < 0xFFFE) {
|
output += '-\\uFFFF';
|
}
|
}
|
|
return output;
|
}
|
|
// Generates an inverted BMP range on first use
|
function cacheInvertedBmp(slug) {
|
const prop = 'b!';
|
return (
|
unicode[slug][prop] ||
|
(unicode[slug][prop] = invertBmp(unicode[slug].bmp))
|
);
|
}
|
|
// Combines and optionally negates BMP and astral data
|
function buildAstral(slug, isNegated) {
|
const item = unicode[slug];
|
let combined = '';
|
|
if (item.bmp && !item.isBmpLast) {
|
combined = `[${item.bmp}]${item.astral ? '|' : ''}`;
|
}
|
if (item.astral) {
|
combined += item.astral;
|
}
|
if (item.isBmpLast && item.bmp) {
|
combined += `${item.astral ? '|' : ''}[${item.bmp}]`;
|
}
|
|
// Astral Unicode tokens always match a code point, never a code unit
|
return isNegated ?
|
`(?:(?!${combined})(?:[\uD800-\uDBFF][\uDC00-\uDFFF]|[\0-\uFFFF]))` :
|
`(?:${combined})`;
|
}
|
|
// Builds a complete astral pattern on first use
|
function cacheAstral(slug, isNegated) {
|
const prop = isNegated ? 'a!' : 'a=';
|
return (
|
unicode[slug][prop] ||
|
(unicode[slug][prop] = buildAstral(slug, isNegated))
|
);
|
}
|
|
// ==--------------------------==
|
// Core functionality
|
// ==--------------------------==
|
|
/*
|
* Add astral mode (flag A) and Unicode token syntax: `\p{..}`, `\P{..}`, `\p{^..}`, `\pC`.
|
*/
|
XRegExp.addToken(
|
// Use `*` instead of `+` to avoid capturing `^` as the token name in `\p{^}`
|
/\\([pP])(?:{(\^?)([^}]*)}|([A-Za-z]))/,
|
(match, scope, flags) => {
|
const ERR_DOUBLE_NEG = 'Invalid double negation ';
|
const ERR_UNKNOWN_NAME = 'Unknown Unicode token ';
|
const ERR_UNKNOWN_REF = 'Unicode token missing data ';
|
const ERR_ASTRAL_ONLY = 'Astral mode required for Unicode token ';
|
const ERR_ASTRAL_IN_CLASS = 'Astral mode does not support Unicode tokens within character classes';
|
// Negated via \P{..} or \p{^..}
|
let isNegated = match[1] === 'P' || !!match[2];
|
// Switch from BMP (0-FFFF) to astral (0-10FFFF) mode via flag A
|
const isAstralMode = flags.includes('A');
|
// Token lookup name. Check `[4]` first to avoid passing `undefined` via `\p{}`
|
let slug = normalize(match[4] || match[3]);
|
// Token data object
|
let item = unicode[slug];
|
|
if (match[1] === 'P' && match[2]) {
|
throw new SyntaxError(ERR_DOUBLE_NEG + match[0]);
|
}
|
if (!unicode.hasOwnProperty(slug)) {
|
throw new SyntaxError(ERR_UNKNOWN_NAME + match[0]);
|
}
|
|
// Switch to the negated form of the referenced Unicode token
|
if (item.inverseOf) {
|
slug = normalize(item.inverseOf);
|
if (!unicode.hasOwnProperty(slug)) {
|
throw new ReferenceError(`${ERR_UNKNOWN_REF + match[0]} -> ${item.inverseOf}`);
|
}
|
item = unicode[slug];
|
isNegated = !isNegated;
|
}
|
|
if (!(item.bmp || isAstralMode)) {
|
throw new SyntaxError(ERR_ASTRAL_ONLY + match[0]);
|
}
|
if (isAstralMode) {
|
if (scope === 'class') {
|
throw new SyntaxError(ERR_ASTRAL_IN_CLASS);
|
}
|
|
return cacheAstral(slug, isNegated);
|
}
|
|
return scope === 'class' ?
|
(isNegated ? cacheInvertedBmp(slug) : item.bmp) :
|
`${(isNegated ? '[^' : '[') + item.bmp}]`;
|
},
|
{
|
scope: 'all',
|
optionalFlags: 'A',
|
leadChar: '\\'
|
}
|
);
|
|
/**
|
* Adds to the list of Unicode tokens that XRegExp regexes can match via `\p` or `\P`.
|
*
|
* @memberOf XRegExp
|
* @param {Array} data Objects with named character ranges. Each object may have properties
|
* `name`, `alias`, `isBmpLast`, `inverseOf`, `bmp`, and `astral`. All but `name` are
|
* optional, although one of `bmp` or `astral` is required (unless `inverseOf` is set). If
|
* `astral` is absent, the `bmp` data is used for BMP and astral modes. If `bmp` is absent,
|
* the name errors in BMP mode but works in astral mode. If both `bmp` and `astral` are
|
* provided, the `bmp` data only is used in BMP mode, and the combination of `bmp` and
|
* `astral` data is used in astral mode. `isBmpLast` is needed when a token matches orphan
|
* high surrogates *and* uses surrogate pairs to match astral code points. The `bmp` and
|
* `astral` data should be a combination of literal characters and `\xHH` or `\uHHHH` escape
|
* sequences, with hyphens to create ranges. Any regex metacharacters in the data should be
|
* escaped, apart from range-creating hyphens. The `astral` data can additionally use
|
* character classes and alternation, and should use surrogate pairs to represent astral code
|
* points. `inverseOf` can be used to avoid duplicating character data if a Unicode token is
|
* defined as the exact inverse of another token.
|
* @example
|
*
|
* // Basic use
|
* XRegExp.addUnicodeData([{
|
* name: 'XDigit',
|
* alias: 'Hexadecimal',
|
* bmp: '0-9A-Fa-f'
|
* }]);
|
* XRegExp('\\p{XDigit}:\\p{Hexadecimal}+').test('0:3D'); // -> true
|
*/
|
XRegExp.addUnicodeData = (data) => {
|
const ERR_NO_NAME = 'Unicode token requires name';
|
const ERR_NO_DATA = 'Unicode token has no character data ';
|
let item;
|
|
for (let i = 0; i < data.length; ++i) {
|
item = data[i];
|
if (!item.name) {
|
throw new Error(ERR_NO_NAME);
|
}
|
if (!(item.inverseOf || item.bmp || item.astral)) {
|
throw new Error(ERR_NO_DATA + item.name);
|
}
|
unicode[normalize(item.name)] = item;
|
if (item.alias) {
|
unicode[normalize(item.alias)] = item;
|
}
|
}
|
|
// Reset the pattern cache used by the `XRegExp` constructor, since the same pattern and
|
// flags might now produce different results
|
XRegExp.cache.flush('patterns');
|
};
|
|
/**
|
* @ignore
|
*
|
* Return a reference to the internal Unicode definition structure for the given Unicode
|
* Property if the given name is a legal Unicode Property for use in XRegExp `\p` or `\P` regex
|
* constructs.
|
*
|
* @memberOf XRegExp
|
* @param {String} name Name by which the Unicode Property may be recognized (case-insensitive),
|
* e.g. `'N'` or `'Number'`. The given name is matched against all registered Unicode
|
* Properties and Property Aliases.
|
* @returns {Object} Reference to definition structure when the name matches a Unicode Property.
|
*
|
* @note
|
* For more info on Unicode Properties, see also http://unicode.org/reports/tr18/#Categories.
|
*
|
* @note
|
* This method is *not* part of the officially documented API and may change or be removed in
|
* the future. It is meant for userland code that wishes to reuse the (large) internal Unicode
|
* structures set up by XRegExp.
|
*/
|
XRegExp._getUnicodeProperty = (name) => {
|
const slug = normalize(name);
|
return unicode[slug];
|
};
|
};
|
