2 var __importDefault = (this && this.__importDefault) || function (mod) {
3 return (mod && mod.__esModule) ? mod : { "default": mod };
5 Object.defineProperty(exports, "__esModule", { value: true });
6 exports.escapeUTF8 = exports.escape = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.encodeXML = void 0;
7 var xml_json_1 = __importDefault(require("./maps/xml.json"));
8 var inverseXML = getInverseObj(xml_json_1.default);
9 var xmlReplacer = getInverseReplacer(inverseXML);
11 * Encodes all non-ASCII characters, as well as characters not valid in XML
12 * documents using XML entities.
14 * If a character has no equivalent entity, a
15 * numeric hexadecimal reference (eg. `ü`) will be used.
17 exports.encodeXML = getASCIIEncoder(inverseXML);
18 var entities_json_1 = __importDefault(require("./maps/entities.json"));
19 var inverseHTML = getInverseObj(entities_json_1.default);
20 var htmlReplacer = getInverseReplacer(inverseHTML);
22 * Encodes all entities and non-ASCII characters in the input.
24 * This includes characters that are valid ASCII characters in HTML documents.
25 * For example `#` will be encoded as `#`. To get a more compact output,
26 * consider using the `encodeNonAsciiHTML` function.
28 * If a character has no equivalent entity, a
29 * numeric hexadecimal reference (eg. `ü`) will be used.
31 exports.encodeHTML = getInverse(inverseHTML, htmlReplacer);
33 * Encodes all non-ASCII characters, as well as characters not valid in HTML
34 * documents using HTML entities.
36 * If a character has no equivalent entity, a
37 * numeric hexadecimal reference (eg. `ü`) will be used.
39 exports.encodeNonAsciiHTML = getASCIIEncoder(inverseHTML);
40 function getInverseObj(obj) {
41 return Object.keys(obj)
43 .reduce(function (inverse, name) {
44 inverse[obj[name]] = "&" + name + ";";
48 function getInverseReplacer(inverse) {
51 for (var _i = 0, _a = Object.keys(inverse); _i < _a.length; _i++) {
54 // Add value to single array
55 single.push("\\" + k);
58 // Add value to multiple array
62 // Add ranges to single characters.
64 for (var start = 0; start < single.length - 1; start++) {
65 // Find the end of a run of characters
67 while (end < single.length - 1 &&
68 single[end].charCodeAt(1) + 1 === single[end + 1].charCodeAt(1)) {
71 var count = 1 + end - start;
72 // We want to replace at least three characters
75 single.splice(start, count, single[start] + "-" + single[end]);
77 multiple.unshift("[" + single.join("") + "]");
78 return new RegExp(multiple.join("|"), "g");
81 var reNonASCII = /(?:[\x80-\uD7FF\uE000-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]|[\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?:[^\uD800-\uDBFF]|^)[\uDC00-\uDFFF])/g;
83 // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
84 String.prototype.codePointAt != null
85 ? // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
86 function (str) { return str.codePointAt(0); }
87 : // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
89 return (c.charCodeAt(0) - 0xd800) * 0x400 +
94 function singleCharReplacer(c) {
95 return "&#x" + (c.length > 1 ? getCodePoint(c) : c.charCodeAt(0))
99 function getInverse(inverse, re) {
100 return function (data) {
102 .replace(re, function (name) { return inverse[name]; })
103 .replace(reNonASCII, singleCharReplacer);
106 var reEscapeChars = new RegExp(xmlReplacer.source + "|" + reNonASCII.source, "g");
108 * Encodes all non-ASCII characters, as well as characters not valid in XML
109 * documents using numeric hexadecimal reference (eg. `ü`).
111 * Have a look at `escapeUTF8` if you want a more concise output at the expense
112 * of reduced transportability.
114 * @param data String to escape.
116 function escape(data) {
117 return data.replace(reEscapeChars, singleCharReplacer);
119 exports.escape = escape;
121 * Encodes all characters not valid in XML documents using numeric hexadecimal
122 * reference (eg. `ü`).
124 * Note that the output will be character-set dependent.
126 * @param data String to escape.
128 function escapeUTF8(data) {
129 return data.replace(xmlReplacer, singleCharReplacer);
131 exports.escapeUTF8 = escapeUTF8;
132 function getASCIIEncoder(obj) {
133 return function (data) {
134 return data.replace(reEscapeChars, function (c) { return obj[c] || singleCharReplacer(c); });