url-sanitizer 0.7.0 → 0.7.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -9
- package/dist/url-sanitizer.js +42 -41
- package/dist/url-sanitizer.js.map +2 -2
- package/dist/url-sanitizer.min.js +3 -3
- package/dist/url-sanitizer.min.js.map +3 -3
- package/package.json +7 -5
- package/src/mjs/uri-util.js +58 -59
package/package.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "url-sanitizer",
|
|
3
|
-
"description": "
|
|
3
|
+
"description": "URL sanitizer for Node.js (>=18), browsers and web sites.",
|
|
4
4
|
"author": "asamuzaK",
|
|
5
5
|
"homepage": "https://github.com/asamuzaK/urlSanitizer",
|
|
6
|
-
"bugs": "https://github.com/asamuzaK/urlSanitizer",
|
|
6
|
+
"bugs": "https://github.com/asamuzaK/urlSanitizer/issues",
|
|
7
7
|
"repository": {
|
|
8
8
|
"type": "git",
|
|
9
9
|
"url": "https://github.com/asamuzaK/urlSanitizer.git"
|
|
@@ -25,7 +25,9 @@
|
|
|
25
25
|
"bundle-src": "esbuild --format=esm --platform=browser --outfile=./dist/url-sanitizer.js --bundle --sourcemap ./bundle/index.js",
|
|
26
26
|
"bundle-min": "esbuild --format=esm --platform=browser --outfile=./dist/url-sanitizer.min.js --bundle --minify --sourcemap ./bundle/index.js",
|
|
27
27
|
"char": "node ./modules/index char -i",
|
|
28
|
-
"copy": "
|
|
28
|
+
"copy": "npm-run-all -s copy-*",
|
|
29
|
+
"copy-src": "copyfiles --up=1 --verbose src/**/* --exclude=src/mjs/dompurify.js bundle",
|
|
30
|
+
"copy-repl": "copyfiles --up=1 --verbose repl/dompurify.js bundle/mjs",
|
|
29
31
|
"include": "node ./modules/index include --dir=iana -i",
|
|
30
32
|
"lint": "eslint --fix .",
|
|
31
33
|
"test": "c8 --reporter=text mocha --exit test/*.test.js"
|
|
@@ -46,7 +48,7 @@
|
|
|
46
48
|
"eslint": "^8.33.0",
|
|
47
49
|
"eslint-config-standard": "^17.0.0",
|
|
48
50
|
"eslint-plugin-import": "^2.27.5",
|
|
49
|
-
"eslint-plugin-jsdoc": "^39.7.
|
|
51
|
+
"eslint-plugin-jsdoc": "^39.7.5",
|
|
50
52
|
"eslint-plugin-n": "^15.6.1",
|
|
51
53
|
"eslint-plugin-node": "^11.1.0",
|
|
52
54
|
"eslint-plugin-promise": "^6.1.1",
|
|
@@ -56,5 +58,5 @@
|
|
|
56
58
|
"sinon": "^15.0.1",
|
|
57
59
|
"undici": "^5.16.0"
|
|
58
60
|
},
|
|
59
|
-
"version": "0.7.
|
|
61
|
+
"version": "0.7.2"
|
|
60
62
|
}
|
package/src/mjs/uri-util.js
CHANGED
|
@@ -13,10 +13,11 @@ const HEX = 16;
|
|
|
13
13
|
const REG_BASE64 = /^[\da-z+/\-_=]+$/i;
|
|
14
14
|
const REG_DATA_URL = /data:[^,]*,[^"]+/g;
|
|
15
15
|
const REG_DATA_URL_BASE64 = /data:[^,]*;?base64,[\da-z+/\-_=]+/i;
|
|
16
|
-
const REG_MIME_DOM =
|
|
17
|
-
/^(?:text\/(?:ht|x)ml|application\/(?:xhtml\+)?xml|image\/svg\+xml)/;
|
|
18
16
|
const REG_HTML_SP = /[<>"'\s]/g;
|
|
19
17
|
const REG_HTML_SP_URL_ENC = /%(?:2(?:2|7)|3(?:C|E))/g;
|
|
18
|
+
const REG_HTML_SP_URL_ENC_SHORT = /%(?:2(?:2|7)|3(?:C|E))+?/;
|
|
19
|
+
const REG_MIME_DOM =
|
|
20
|
+
/^(?:text\/(?:ht|x)ml|application\/(?:xhtml\+)?xml|image\/svg\+xml)/;
|
|
20
21
|
const REG_NUM_REF = /&#(x(?:00)?[\dA-F]{2}|0?\d{1,3});?/ig;
|
|
21
22
|
const REG_SCHEME = /^[a-z][\da-z+\-.]*$/;
|
|
22
23
|
const REG_SCHEME_CUSTOM = /^(?:ext|web)\+[a-z]+$/;
|
|
@@ -31,7 +32,7 @@ const REG_URL_ENC_HTML_SP = /%26(?:(?:l|g|quo)t|%2339);?/g;
|
|
|
31
32
|
* @param {string} str - string
|
|
32
33
|
* @returns {string} - URL encoded string
|
|
33
34
|
*/
|
|
34
|
-
export const
|
|
35
|
+
export const getURLEncodedString = str => {
|
|
35
36
|
if (!isString(str)) {
|
|
36
37
|
throw new TypeError(`Expected String but got ${getType(str)}.`);
|
|
37
38
|
}
|
|
@@ -48,18 +49,12 @@ export const getUrlEncodedString = str => {
|
|
|
48
49
|
* @param {string} ch - URL encoded (percent encoded) char
|
|
49
50
|
* @returns {string} - escaped URL encoded HTML special char / URL encoded char
|
|
50
51
|
*/
|
|
51
|
-
export const
|
|
52
|
-
if (isString(ch)) {
|
|
53
|
-
|
|
54
|
-
ch = ch.toUpperCase();
|
|
55
|
-
} else {
|
|
56
|
-
throw new Error(`Invalid URL encoded character: ${ch}`);
|
|
57
|
-
}
|
|
58
|
-
} else {
|
|
59
|
-
throw new TypeError(`Expected String but got ${getType(ch)}.`);
|
|
52
|
+
export const escapeURLEncodedHTMLChars = ch => {
|
|
53
|
+
if (isString(ch) && REG_URL_ENC.test(ch)) {
|
|
54
|
+
ch = ch.toUpperCase();
|
|
60
55
|
}
|
|
61
56
|
const [amp, num, lt, gt, quot, apos] =
|
|
62
|
-
['&', '#', '<', '>', '"', "'"].map(
|
|
57
|
+
['&', '#', '<', '>', '"', "'"].map(getURLEncodedString);
|
|
63
58
|
let escapedChar;
|
|
64
59
|
if (ch === amp) {
|
|
65
60
|
escapedChar = `${amp}amp;`;
|
|
@@ -83,7 +78,7 @@ export const escapeUrlEncodedHtmlChars = ch => {
|
|
|
83
78
|
* @param {string} ch - URL encoded char
|
|
84
79
|
* @returns {string} - unescaped HTML special char
|
|
85
80
|
*/
|
|
86
|
-
export const
|
|
81
|
+
export const unescapeURLEncodedHTMLChars = ch => {
|
|
87
82
|
let unescapedChar;
|
|
88
83
|
if (/%26lt;?/.test(ch)) {
|
|
89
84
|
unescapedChar = '<';
|
|
@@ -116,7 +111,7 @@ export const parseBase64 = data => {
|
|
|
116
111
|
const textCharCodes = new Set(textChars);
|
|
117
112
|
let parsedData;
|
|
118
113
|
if (uint8arr.every(c => textCharCodes.has(c))) {
|
|
119
|
-
parsedData = bin.replace(/\s/g,
|
|
114
|
+
parsedData = bin.replace(/\s/g, getURLEncodedString);
|
|
120
115
|
} else {
|
|
121
116
|
parsedData = data;
|
|
122
117
|
}
|
|
@@ -130,7 +125,7 @@ export const parseBase64 = data => {
|
|
|
130
125
|
* @param {number} nest - nest level
|
|
131
126
|
* @returns {string} - parsed string
|
|
132
127
|
*/
|
|
133
|
-
export const
|
|
128
|
+
export const parseURLEncodedNumCharRef = (str, nest = 0) => {
|
|
134
129
|
if (!isString(str)) {
|
|
135
130
|
throw new TypeError(`Expected String but got ${getType(str)}.`);
|
|
136
131
|
}
|
|
@@ -160,7 +155,7 @@ export const parseUrlEncodedNumCharRef = (str, nest = 0) => {
|
|
|
160
155
|
if (textCharCodes.has(num)) {
|
|
161
156
|
res = `${preNum}${String.fromCharCode(num)}${postNum}`;
|
|
162
157
|
if (/#x?$/.test(preNum) || /^#(?:x(?:00)?[2-7]|\d)/.test(postNum)) {
|
|
163
|
-
res =
|
|
158
|
+
res = parseURLEncodedNumCharRef(res, ++nest);
|
|
164
159
|
}
|
|
165
160
|
} else if (num < HEX * HEX) {
|
|
166
161
|
res = `${preNum}${postNum}`;
|
|
@@ -177,7 +172,7 @@ export const parseUrlEncodedNumCharRef = (str, nest = 0) => {
|
|
|
177
172
|
* @param {string} dom - DOM input
|
|
178
173
|
* @returns {string} - purified DOM
|
|
179
174
|
*/
|
|
180
|
-
export const
|
|
175
|
+
export const purifyURLEncodedDOM = dom => {
|
|
181
176
|
if (!isString(dom)) {
|
|
182
177
|
throw new TypeError(`Expected String but got ${getType(dom)}.`);
|
|
183
178
|
}
|
|
@@ -249,12 +244,12 @@ export class URISchemes {
|
|
|
249
244
|
}
|
|
250
245
|
|
|
251
246
|
/**
|
|
252
|
-
*
|
|
247
|
+
* verify URI
|
|
253
248
|
*
|
|
254
249
|
* @param {string} uri - URI input
|
|
255
250
|
* @returns {boolean} - result
|
|
256
251
|
*/
|
|
257
|
-
|
|
252
|
+
verify(uri) {
|
|
258
253
|
let res;
|
|
259
254
|
if (isString(uri)) {
|
|
260
255
|
try {
|
|
@@ -296,6 +291,7 @@ export class URLSanitizer extends URISchemes {
|
|
|
296
291
|
* @param {Array.<string>} opt.allow - array of allowed schemes
|
|
297
292
|
* @param {Array.<string>} opt.deny - array of denied schemes
|
|
298
293
|
* @param {Array.<string>} opt.only - array of specific schemes to allow
|
|
294
|
+
* @param {boolean} opt.truncate - truncate tag and/or quote and the rest
|
|
299
295
|
* @returns {?string} - sanitized URL
|
|
300
296
|
*/
|
|
301
297
|
sanitize(url, opt = { allow: [], deny: [], only: [] }) {
|
|
@@ -303,7 +299,7 @@ export class URLSanitizer extends URISchemes {
|
|
|
303
299
|
this.#nest = 0;
|
|
304
300
|
throw new Error('Data URLs nested too deeply.');
|
|
305
301
|
}
|
|
306
|
-
const { allow, deny, only } = opt ?? {};
|
|
302
|
+
const { allow, deny, only, truncate } = opt ?? {};
|
|
307
303
|
const schemeMap = new Map([
|
|
308
304
|
['data', false],
|
|
309
305
|
['file', false],
|
|
@@ -375,7 +371,7 @@ export class URLSanitizer extends URISchemes {
|
|
|
375
371
|
}
|
|
376
372
|
}
|
|
377
373
|
let sanitizedUrl;
|
|
378
|
-
if (super.
|
|
374
|
+
if (super.verify(url)) {
|
|
379
375
|
const { hash, href, pathname, protocol, search } = new URL(url);
|
|
380
376
|
const scheme = protocol.replace(/:$/, '');
|
|
381
377
|
const schemeParts = scheme.split('+');
|
|
@@ -403,7 +399,7 @@ export class URLSanitizer extends URISchemes {
|
|
|
403
399
|
parsedData = parseBase64(data);
|
|
404
400
|
} else {
|
|
405
401
|
try {
|
|
406
|
-
const decodedData =
|
|
402
|
+
const decodedData = parseURLEncodedNumCharRef(parsedData);
|
|
407
403
|
const { protocol: dataScheme } = new URL(decodedData.trim());
|
|
408
404
|
const dataSchemeParts = dataScheme.replace(/:$/, '').split('+');
|
|
409
405
|
if (dataSchemeParts.some(s => REG_SCRIPT.test(s))) {
|
|
@@ -456,13 +452,19 @@ export class URLSanitizer extends URISchemes {
|
|
|
456
452
|
} else {
|
|
457
453
|
escapeHtml = true;
|
|
458
454
|
}
|
|
455
|
+
if (!schemeParts.includes('data') && truncate &&
|
|
456
|
+
REG_HTML_SP_URL_ENC_SHORT.test(urlToSanitize)) {
|
|
457
|
+
const item = REG_HTML_SP_URL_ENC_SHORT.exec(urlToSanitize);
|
|
458
|
+
const { index } = item;
|
|
459
|
+
urlToSanitize = urlToSanitize.substring(0, index);
|
|
460
|
+
}
|
|
459
461
|
if (urlToSanitize) {
|
|
460
462
|
sanitizedUrl = urlToSanitize
|
|
461
|
-
.replace(REG_HTML_SP,
|
|
462
|
-
.replace(REG_URL_ENC_AMP,
|
|
463
|
+
.replace(REG_HTML_SP, getURLEncodedString)
|
|
464
|
+
.replace(REG_URL_ENC_AMP, escapeURLEncodedHTMLChars);
|
|
463
465
|
if (escapeHtml) {
|
|
464
466
|
sanitizedUrl = sanitizedUrl
|
|
465
|
-
.replace(REG_HTML_SP_URL_ENC,
|
|
467
|
+
.replace(REG_HTML_SP_URL_ENC, escapeURLEncodedHTMLChars);
|
|
466
468
|
this.#nest = 0;
|
|
467
469
|
}
|
|
468
470
|
} else {
|
|
@@ -475,7 +477,7 @@ export class URLSanitizer extends URISchemes {
|
|
|
475
477
|
}
|
|
476
478
|
|
|
477
479
|
/**
|
|
478
|
-
* object with
|
|
480
|
+
* object with additional properties based on URL API
|
|
479
481
|
*
|
|
480
482
|
* @typedef {object} ParsedURL
|
|
481
483
|
* @property {string} input - URL input
|
|
@@ -503,7 +505,7 @@ export class URLSanitizer extends URISchemes {
|
|
|
503
505
|
*
|
|
504
506
|
* @param {string} url - URL input
|
|
505
507
|
* @param {object} opt - options
|
|
506
|
-
* @returns {ParsedURL} - result with
|
|
508
|
+
* @returns {ParsedURL} - result with enhanced props based on URL API
|
|
507
509
|
*/
|
|
508
510
|
parse(url, opt) {
|
|
509
511
|
if (!isString(url)) {
|
|
@@ -543,10 +545,10 @@ export class URLSanitizer extends URISchemes {
|
|
|
543
545
|
parsedData.substring(0, index),
|
|
544
546
|
parsedData.substring(index + htmlChar.length)
|
|
545
547
|
];
|
|
546
|
-
const
|
|
547
|
-
parsedData = `${preHtmlChar}${
|
|
548
|
+
const unescapedHtmlChar = unescapeURLEncodedHTMLChars(htmlChar);
|
|
549
|
+
parsedData = `${preHtmlChar}${unescapedHtmlChar}${postHtmlChar}`;
|
|
548
550
|
}
|
|
549
|
-
purifiedDom =
|
|
551
|
+
purifiedDom = purifyURLEncodedDOM(parsedData);
|
|
550
552
|
dataUrl.set('data', purifiedDom);
|
|
551
553
|
} else {
|
|
552
554
|
dataUrl.set('data', data);
|
|
@@ -595,7 +597,7 @@ const urlSanitizer = new URLSanitizer();
|
|
|
595
597
|
* @param {string} uri - URI input
|
|
596
598
|
* @returns {boolean} - result
|
|
597
599
|
*/
|
|
598
|
-
const
|
|
600
|
+
export const isURISync = uri => urlSanitizer.verify(uri);
|
|
599
601
|
|
|
600
602
|
/**
|
|
601
603
|
* is URI async
|
|
@@ -604,7 +606,26 @@ const isUri = uri => urlSanitizer.isURI(uri);
|
|
|
604
606
|
* @returns {Promise.<boolean>} - result
|
|
605
607
|
*/
|
|
606
608
|
export const isURI = async uri => {
|
|
607
|
-
const res = await
|
|
609
|
+
const res = await isURISync(uri);
|
|
610
|
+
return res;
|
|
611
|
+
};
|
|
612
|
+
|
|
613
|
+
/**
|
|
614
|
+
* parse URL sync
|
|
615
|
+
*
|
|
616
|
+
* @param {string} url - URL input
|
|
617
|
+
* @returns {ParsedURL} - result with extended props based on URL API
|
|
618
|
+
*/
|
|
619
|
+
export const parseURLSync = url => urlSanitizer.parse(url);
|
|
620
|
+
|
|
621
|
+
/**
|
|
622
|
+
* parse URL async
|
|
623
|
+
*
|
|
624
|
+
* @param {string} url - URL input
|
|
625
|
+
* @returns {Promise.<ParsedURL>} - result with extended props based on URL API
|
|
626
|
+
*/
|
|
627
|
+
export const parseURL = async url => {
|
|
628
|
+
const res = await parseURLSync(url);
|
|
608
629
|
return res;
|
|
609
630
|
};
|
|
610
631
|
|
|
@@ -615,7 +636,7 @@ export const isURI = async uri => {
|
|
|
615
636
|
* @param {object} opt - options
|
|
616
637
|
* @returns {?string} - sanitized URL
|
|
617
638
|
*/
|
|
618
|
-
const
|
|
639
|
+
export const sanitizeURLSync = (url, opt) => {
|
|
619
640
|
const parsedUrl = urlSanitizer.parse(url, opt ?? {
|
|
620
641
|
allow: [],
|
|
621
642
|
deny: [],
|
|
@@ -637,33 +658,11 @@ const sanitizeUrl = (url, opt) => {
|
|
|
637
658
|
* @returns {Promise.<?string>} - sanitized URL
|
|
638
659
|
*/
|
|
639
660
|
export const sanitizeURL = async (url, opt) => {
|
|
640
|
-
const res = await
|
|
641
|
-
return res;
|
|
642
|
-
};
|
|
643
|
-
|
|
644
|
-
/**
|
|
645
|
-
* parse URL sync
|
|
646
|
-
*
|
|
647
|
-
* @param {string} url - URL input
|
|
648
|
-
* @returns {ParsedURL} - result with extended props based on URL API
|
|
649
|
-
*/
|
|
650
|
-
const parseUrl = url => urlSanitizer.parse(url);
|
|
651
|
-
|
|
652
|
-
/**
|
|
653
|
-
* parse URL async
|
|
654
|
-
*
|
|
655
|
-
* @param {string} url - URL input
|
|
656
|
-
* @returns {Promise.<ParsedURL>} - result with extended props based on URL API
|
|
657
|
-
*/
|
|
658
|
-
export const parseURL = async url => {
|
|
659
|
-
const res = await parseUrl(url);
|
|
661
|
+
const res = await sanitizeURLSync(url, opt);
|
|
660
662
|
return res;
|
|
661
663
|
};
|
|
662
664
|
|
|
663
|
-
/* export instance
|
|
665
|
+
/* export instance */
|
|
664
666
|
export {
|
|
665
|
-
urlSanitizer as default
|
|
666
|
-
isUri as isURISync,
|
|
667
|
-
parseUrl as parseURLSync,
|
|
668
|
-
sanitizeUrl as sanitizeURLSync
|
|
667
|
+
urlSanitizer as default
|
|
669
668
|
};
|