123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136 |
- "use strict";
- var __importDefault = (this && this.__importDefault) || function (mod) {
- return (mod && mod.__esModule) ? mod : { "default": mod };
- };
- Object.defineProperty(exports, "__esModule", { value: true });
- exports.escapeUTF8 = exports.escape = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.encodeXML = void 0;
- var xml_json_1 = __importDefault(require("./maps/xml.json"));
- var inverseXML = getInverseObj(xml_json_1.default);
- var xmlReplacer = getInverseReplacer(inverseXML);
- /**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using XML entities.
- *
- * If a character has no equivalent entity, a
- * numeric hexadecimal reference (eg. `ü`) will be used.
- */
- exports.encodeXML = getASCIIEncoder(inverseXML);
- var entities_json_1 = __importDefault(require("./maps/entities.json"));
- var inverseHTML = getInverseObj(entities_json_1.default);
- var htmlReplacer = getInverseReplacer(inverseHTML);
- /**
- * Encodes all entities and non-ASCII characters in the input.
- *
- * This includes characters that are valid ASCII characters in HTML documents.
- * For example `#` will be encoded as `#`. To get a more compact output,
- * consider using the `encodeNonAsciiHTML` function.
- *
- * If a character has no equivalent entity, a
- * numeric hexadecimal reference (eg. `ü`) will be used.
- */
- exports.encodeHTML = getInverse(inverseHTML, htmlReplacer);
- /**
- * Encodes all non-ASCII characters, as well as characters not valid in HTML
- * documents using HTML entities.
- *
- * If a character has no equivalent entity, a
- * numeric hexadecimal reference (eg. `ü`) will be used.
- */
- exports.encodeNonAsciiHTML = getASCIIEncoder(inverseHTML);
- function getInverseObj(obj) {
- return Object.keys(obj)
- .sort()
- .reduce(function (inverse, name) {
- inverse[obj[name]] = "&" + name + ";";
- return inverse;
- }, {});
- }
- function getInverseReplacer(inverse) {
- var single = [];
- var multiple = [];
- for (var _i = 0, _a = Object.keys(inverse); _i < _a.length; _i++) {
- var k = _a[_i];
- if (k.length === 1) {
- // Add value to single array
- single.push("\\" + k);
- }
- else {
- // Add value to multiple array
- multiple.push(k);
- }
- }
- // Add ranges to single characters.
- single.sort();
- for (var start = 0; start < single.length - 1; start++) {
- // Find the end of a run of characters
- var end = start;
- while (end < single.length - 1 &&
- single[end].charCodeAt(1) + 1 === single[end + 1].charCodeAt(1)) {
- end += 1;
- }
- var count = 1 + end - start;
- // We want to replace at least three characters
- if (count < 3)
- continue;
- single.splice(start, count, single[start] + "-" + single[end]);
- }
- multiple.unshift("[" + single.join("") + "]");
- return new RegExp(multiple.join("|"), "g");
- }
- // /[^\0-\x7F]/gu
- var reNonASCII = /(?:[\x80-\uD7FF\uE000-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]|[\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?:[^\uD800-\uDBFF]|^)[\uDC00-\uDFFF])/g;
- var getCodePoint =
- // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
- String.prototype.codePointAt != null
- ? // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
- function (str) { return str.codePointAt(0); }
- : // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
- function (c) {
- return (c.charCodeAt(0) - 0xd800) * 0x400 +
- c.charCodeAt(1) -
- 0xdc00 +
- 0x10000;
- };
- function singleCharReplacer(c) {
- return "&#x" + (c.length > 1 ? getCodePoint(c) : c.charCodeAt(0))
- .toString(16)
- .toUpperCase() + ";";
- }
- function getInverse(inverse, re) {
- return function (data) {
- return data
- .replace(re, function (name) { return inverse[name]; })
- .replace(reNonASCII, singleCharReplacer);
- };
- }
- var reEscapeChars = new RegExp(xmlReplacer.source + "|" + reNonASCII.source, "g");
- /**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using numeric hexadecimal reference (eg. `ü`).
- *
- * Have a look at `escapeUTF8` if you want a more concise output at the expense
- * of reduced transportability.
- *
- * @param data String to escape.
- */
- function escape(data) {
- return data.replace(reEscapeChars, singleCharReplacer);
- }
- exports.escape = escape;
- /**
- * Encodes all characters not valid in XML documents using numeric hexadecimal
- * reference (eg. `ü`).
- *
- * Note that the output will be character-set dependent.
- *
- * @param data String to escape.
- */
- function escapeUTF8(data) {
- return data.replace(xmlReplacer, singleCharReplacer);
- }
- exports.escapeUTF8 = escapeUTF8;
- function getASCIIEncoder(obj) {
- return function (data) {
- return data.replace(reEscapeChars, function (c) { return obj[c] || singleCharReplacer(c); });
- };
- }
|