1 | "use strict";
|
---|
2 | Object.defineProperty(exports, "__esModule", { value: true });
|
---|
3 | var surrogate_pairs_1 = require("./surrogate-pairs");
|
---|
4 | var HTML_ALPHA = ['apos', 'nbsp', 'iexcl', 'cent', 'pound', 'curren', 'yen', 'brvbar', 'sect', 'uml', 'copy', 'ordf', 'laquo', 'not', 'shy', 'reg', 'macr', 'deg', 'plusmn', 'sup2', 'sup3', 'acute', 'micro', 'para', 'middot', 'cedil', 'sup1', 'ordm', 'raquo', 'frac14', 'frac12', 'frac34', 'iquest', 'Agrave', 'Aacute', 'Acirc', 'Atilde', 'Auml', 'Aring', 'AElig', 'Ccedil', 'Egrave', 'Eacute', 'Ecirc', 'Euml', 'Igrave', 'Iacute', 'Icirc', 'Iuml', 'ETH', 'Ntilde', 'Ograve', 'Oacute', 'Ocirc', 'Otilde', 'Ouml', 'times', 'Oslash', 'Ugrave', 'Uacute', 'Ucirc', 'Uuml', 'Yacute', 'THORN', 'szlig', 'agrave', 'aacute', 'acirc', 'atilde', 'auml', 'aring', 'aelig', 'ccedil', 'egrave', 'eacute', 'ecirc', 'euml', 'igrave', 'iacute', 'icirc', 'iuml', 'eth', 'ntilde', 'ograve', 'oacute', 'ocirc', 'otilde', 'ouml', 'divide', 'oslash', 'ugrave', 'uacute', 'ucirc', 'uuml', 'yacute', 'thorn', 'yuml', 'quot', 'amp', 'lt', 'gt', 'OElig', 'oelig', 'Scaron', 'scaron', 'Yuml', 'circ', 'tilde', 'ensp', 'emsp', 'thinsp', 'zwnj', 'zwj', 'lrm', 'rlm', 'ndash', 'mdash', 'lsquo', 'rsquo', 'sbquo', 'ldquo', 'rdquo', 'bdquo', 'dagger', 'Dagger', 'permil', 'lsaquo', 'rsaquo', 'euro', 'fnof', 'Alpha', 'Beta', 'Gamma', 'Delta', 'Epsilon', 'Zeta', 'Eta', 'Theta', 'Iota', 'Kappa', 'Lambda', 'Mu', 'Nu', 'Xi', 'Omicron', 'Pi', 'Rho', 'Sigma', 'Tau', 'Upsilon', 'Phi', 'Chi', 'Psi', 'Omega', 'alpha', 'beta', 'gamma', 'delta', 'epsilon', 'zeta', 'eta', 'theta', 'iota', 'kappa', 'lambda', 'mu', 'nu', 'xi', 'omicron', 'pi', 'rho', 'sigmaf', 'sigma', 'tau', 'upsilon', 'phi', 'chi', 'psi', 'omega', 'thetasym', 'upsih', 'piv', 'bull', 'hellip', 'prime', 'Prime', 'oline', 'frasl', 'weierp', 'image', 'real', 'trade', 'alefsym', 'larr', 'uarr', 'rarr', 'darr', 'harr', 'crarr', 'lArr', 'uArr', 'rArr', 'dArr', 'hArr', 'forall', 'part', 'exist', 'empty', 'nabla', 'isin', 'notin', 'ni', 'prod', 'sum', 'minus', 'lowast', 'radic', 'prop', 'infin', 'ang', 'and', 'or', 'cap', 'cup', 'int', 'there4', 'sim', 'cong', 'asymp', 'ne', 'equiv', 'le', 'ge', 'sub', 'sup', 'nsub', 'sube', 'supe', 'oplus', 'otimes', 'perp', 'sdot', 'lceil', 'rceil', 'lfloor', 'rfloor', 'lang', 'rang', 'loz', 'spades', 'clubs', 'hearts', 'diams'];
|
---|
5 | var HTML_CODES = [39, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 34, 38, 60, 62, 338, 339, 352, 353, 376, 710, 732, 8194, 8195, 8201, 8204, 8205, 8206, 8207, 8211, 8212, 8216, 8217, 8218, 8220, 8221, 8222, 8224, 8225, 8240, 8249, 8250, 8364, 402, 913, 914, 915, 916, 917, 918, 919, 920, 921, 922, 923, 924, 925, 926, 927, 928, 929, 931, 932, 933, 934, 935, 936, 937, 945, 946, 947, 948, 949, 950, 951, 952, 953, 954, 955, 956, 957, 958, 959, 960, 961, 962, 963, 964, 965, 966, 967, 968, 969, 977, 978, 982, 8226, 8230, 8242, 8243, 8254, 8260, 8472, 8465, 8476, 8482, 8501, 8592, 8593, 8594, 8595, 8596, 8629, 8656, 8657, 8658, 8659, 8660, 8704, 8706, 8707, 8709, 8711, 8712, 8713, 8715, 8719, 8721, 8722, 8727, 8730, 8733, 8734, 8736, 8743, 8744, 8745, 8746, 8747, 8756, 8764, 8773, 8776, 8800, 8801, 8804, 8805, 8834, 8835, 8836, 8838, 8839, 8853, 8855, 8869, 8901, 8968, 8969, 8970, 8971, 9001, 9002, 9674, 9824, 9827, 9829, 9830];
|
---|
6 | var alphaIndex = {};
|
---|
7 | var numIndex = {};
|
---|
8 | (function () {
|
---|
9 | var i = 0;
|
---|
10 | var length = HTML_ALPHA.length;
|
---|
11 | while (i < length) {
|
---|
12 | var a = HTML_ALPHA[i];
|
---|
13 | var c = HTML_CODES[i];
|
---|
14 | alphaIndex[a] = String.fromCharCode(c);
|
---|
15 | numIndex[c] = a;
|
---|
16 | i++;
|
---|
17 | }
|
---|
18 | })();
|
---|
19 | var Html4Entities = /** @class */ (function () {
|
---|
20 | function Html4Entities() {
|
---|
21 | }
|
---|
22 | Html4Entities.prototype.decode = function (str) {
|
---|
23 | if (!str || !str.length) {
|
---|
24 | return '';
|
---|
25 | }
|
---|
26 | return str.replace(/&(#?[\w\d]+);?/g, function (s, entity) {
|
---|
27 | var chr;
|
---|
28 | if (entity.charAt(0) === "#") {
|
---|
29 | var code = entity.charAt(1).toLowerCase() === 'x' ?
|
---|
30 | parseInt(entity.substr(2), 16) :
|
---|
31 | parseInt(entity.substr(1));
|
---|
32 | if (!isNaN(code) || code >= -32768) {
|
---|
33 | if (code <= 65535) {
|
---|
34 | chr = String.fromCharCode(code);
|
---|
35 | }
|
---|
36 | else {
|
---|
37 | chr = surrogate_pairs_1.fromCodePoint(code);
|
---|
38 | }
|
---|
39 | }
|
---|
40 | }
|
---|
41 | else {
|
---|
42 | chr = alphaIndex[entity];
|
---|
43 | }
|
---|
44 | return chr || s;
|
---|
45 | });
|
---|
46 | };
|
---|
47 | Html4Entities.decode = function (str) {
|
---|
48 | return new Html4Entities().decode(str);
|
---|
49 | };
|
---|
50 | Html4Entities.prototype.encode = function (str) {
|
---|
51 | if (!str || !str.length) {
|
---|
52 | return '';
|
---|
53 | }
|
---|
54 | var strLength = str.length;
|
---|
55 | var result = '';
|
---|
56 | var i = 0;
|
---|
57 | while (i < strLength) {
|
---|
58 | var alpha = numIndex[str.charCodeAt(i)];
|
---|
59 | result += alpha ? "&" + alpha + ";" : str.charAt(i);
|
---|
60 | i++;
|
---|
61 | }
|
---|
62 | return result;
|
---|
63 | };
|
---|
64 | Html4Entities.encode = function (str) {
|
---|
65 | return new Html4Entities().encode(str);
|
---|
66 | };
|
---|
67 | Html4Entities.prototype.encodeNonUTF = function (str) {
|
---|
68 | if (!str || !str.length) {
|
---|
69 | return '';
|
---|
70 | }
|
---|
71 | var strLength = str.length;
|
---|
72 | var result = '';
|
---|
73 | var i = 0;
|
---|
74 | while (i < strLength) {
|
---|
75 | var cc = str.charCodeAt(i);
|
---|
76 | var alpha = numIndex[cc];
|
---|
77 | if (alpha) {
|
---|
78 | result += "&" + alpha + ";";
|
---|
79 | }
|
---|
80 | else if (cc < 32 || cc > 126) {
|
---|
81 | if (cc >= surrogate_pairs_1.highSurrogateFrom && cc <= surrogate_pairs_1.highSurrogateTo) {
|
---|
82 | result += '&#' + surrogate_pairs_1.getCodePoint(str, i) + ';';
|
---|
83 | i++;
|
---|
84 | }
|
---|
85 | else {
|
---|
86 | result += '&#' + cc + ';';
|
---|
87 | }
|
---|
88 | }
|
---|
89 | else {
|
---|
90 | result += str.charAt(i);
|
---|
91 | }
|
---|
92 | i++;
|
---|
93 | }
|
---|
94 | return result;
|
---|
95 | };
|
---|
96 | Html4Entities.encodeNonUTF = function (str) {
|
---|
97 | return new Html4Entities().encodeNonUTF(str);
|
---|
98 | };
|
---|
99 | Html4Entities.prototype.encodeNonASCII = function (str) {
|
---|
100 | if (!str || !str.length) {
|
---|
101 | return '';
|
---|
102 | }
|
---|
103 | var strLength = str.length;
|
---|
104 | var result = '';
|
---|
105 | var i = 0;
|
---|
106 | while (i < strLength) {
|
---|
107 | var c = str.charCodeAt(i);
|
---|
108 | if (c <= 255) {
|
---|
109 | result += str[i++];
|
---|
110 | continue;
|
---|
111 | }
|
---|
112 | if (c >= surrogate_pairs_1.highSurrogateFrom && c <= surrogate_pairs_1.highSurrogateTo) {
|
---|
113 | result += '&#' + surrogate_pairs_1.getCodePoint(str, i) + ';';
|
---|
114 | i++;
|
---|
115 | }
|
---|
116 | else {
|
---|
117 | result += '&#' + c + ';';
|
---|
118 | }
|
---|
119 | i++;
|
---|
120 | }
|
---|
121 | return result;
|
---|
122 | };
|
---|
123 | Html4Entities.encodeNonASCII = function (str) {
|
---|
124 | return new Html4Entities().encodeNonASCII(str);
|
---|
125 | };
|
---|
126 | return Html4Entities;
|
---|
127 | }());
|
---|
128 | exports.Html4Entities = Html4Entities;
|
---|