Rietveld Code Review Tool
Help | Bug tracker | Discussion group | Source code

Side by Side Diff: lib/url.js

Issue 29772555: Issue 6647 - Stop converting domains from punycode to unicode (Closed)
Patch Set: Created May 6, 2018, 2:42 p.m.
Left:
Right:
Use n/p to move between diff chunks; N/P to move between comments.
Jump to:
View unified diff | Download patch
OLDNEW
1 /* 1 /*
2 * This file is part of Adblock Plus <https://adblockplus.org/>, 2 * This file is part of Adblock Plus <https://adblockplus.org/>,
3 * Copyright (C) 2006-present eyeo GmbH 3 * Copyright (C) 2006-present eyeo GmbH
4 * 4 *
5 * Adblock Plus is free software: you can redistribute it and/or modify 5 * Adblock Plus is free software: you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License version 3 as 6 * it under the terms of the GNU General Public License version 3 as
7 * published by the Free Software Foundation. 7 * published by the Free Software Foundation.
8 * 8 *
9 * Adblock Plus is distributed in the hope that it will be useful, 9 * Adblock Plus is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of 10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details. 12 * GNU General Public License for more details.
13 * 13 *
14 * You should have received a copy of the GNU General Public License 14 * You should have received a copy of the GNU General Public License
15 * along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. 15 * along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>.
16 */ 16 */
17 17
18 /** @module url */ 18 /** @module url */
19 19
20 "use strict"; 20 "use strict";
21 21
22 const {getDomain} = require("./tldjs"); 22 const {getDomain} = require("./tldjs");
23 const punycode = require("./punycode");
24
25 let getDecodedHostname =
26 /**
27 * Gets the IDN-decoded hostname from a URL object.
28 *
29 * @param {URL} url
30 * @return {string}
31 * @static
32 */
33 exports.getDecodedHostname = url =>
34 {
35 let {hostname} = url;
36
37 if (hostname.indexOf("xn--") == -1)
38 return hostname;
39
40 return punycode.toUnicode(hostname);
41 };
42 23
43 /** 24 /**
44 * Gets the IDN-decoded hostname from the URL of a frame. 25 * Gets the IDN-decoded hostname from the URL of a frame.
45 * If the URL don't have host information (like "about:blank" 26 * If the URL don't have host information (like "about:blank"
46 * and "data:" URLs) it falls back to the parent frame. 27 * and "data:" URLs) it falls back to the parent frame.
47 * 28 *
48 * @param {?Frame} frame 29 * @param {?Frame} frame
49 * @param {URL} [originUrl] 30 * @param {URL} [originUrl]
50 * @return {string} 31 * @return {string}
51 */ 32 */
52 exports.extractHostFromFrame = (frame, originUrl) => 33 exports.extractHostFromFrame = (frame, originUrl) =>
53 { 34 {
54 for (; frame; frame = frame.parent) 35 for (; frame; frame = frame.parent)
55 { 36 {
56 let hostname = getDecodedHostname(frame.url); 37 let hostname = frame.url.hostname;
57 if (hostname) 38 if (hostname)
58 return hostname; 39 return hostname;
59 } 40 }
60 41
61 return originUrl ? getDecodedHostname(originUrl) : ""; 42 return originUrl ? originUrl.hostname : "";
62 };
63
64 /**
65 * Converts a URL object into a string. For HTTP(S) URLs
66 * the hostname gets IDN-decoded and the hash is stripped.
67 *
68 * @param {URL} url
69 * @return {string}
70 */
71 exports.stringifyURL = url =>
72 {
73 let {protocol, href} = url;
74
75 if (protocol == "http:" || protocol == "https:")
76 {
77 let {hostname} = url;
78 if (hostname.indexOf("xn--") != -1)
79 href = href.replace(hostname, punycode.toUnicode(hostname));
80
81 let hash = href.indexOf("#");
82 if (hash != -1)
83 href = href.substr(0, hash);
84 }
85
86 return href;
87 }; 43 };
88 44
89 function isDomain(hostname) 45 function isDomain(hostname)
90 { 46 {
91 // No hostname or IPv4 address, also considering hexadecimal octets. 47 // No hostname or IPv4 address, also considering hexadecimal octets.
92 if (/^((0x[\da-f]+|\d+)(\.|$))*$/i.test(hostname)) 48 if (/^((0x[\da-f]+|\d+)(\.|$))*$/i.test(hostname))
93 return false; 49 return false;
94 50
95 // IPv6 address. Since there can't be colons in domains, we can 51 // IPv6 address. Since there can't be colons in domains, we can
96 // just check whether there are any colons to exclude IPv6 addresses. 52 // just check whether there are any colons to exclude IPv6 addresses.
97 return hostname.indexOf(":") == -1; 53 return hostname.indexOf(":") == -1;
98 } 54 }
99 55
100 /** 56 /**
101 * Checks whether the request's origin is different from the document's origin. 57 * Checks whether the request's origin is different from the document's origin.
102 * 58 *
103 * @param {URL} url The request URL 59 * @param {URL} url The request URL
104 * @param {string} documentHost The IDN-decoded hostname of the document 60 * @param {string} documentHost The IDN-decoded hostname of the document
105 * @return {Boolean} 61 * @return {Boolean}
106 */ 62 */
107 exports.isThirdParty = (url, documentHost) => 63 exports.isThirdParty = (url, documentHost) =>
108 { 64 {
109 let requestHost = getDecodedHostname(url).replace(/\.+$/, ""); 65 let requestHost = url.hostname.replace(/\.+$/, "");
110 documentHost = documentHost.replace(/\.+$/, ""); 66 documentHost = documentHost.replace(/\.+$/, "");
111 67
112 if (requestHost == documentHost) 68 if (requestHost == documentHost)
113 return false; 69 return false;
114 70
115 if (!isDomain(requestHost) || !isDomain(documentHost)) 71 if (!isDomain(requestHost) || !isDomain(documentHost))
116 return true; 72 return true;
117 73
118 return getDomain(requestHost) != getDomain(documentHost); 74 return getDomain(requestHost) != getDomain(documentHost);
119 }; 75 };
OLDNEW
« lib/options.js ('K') | « lib/requestBlocker.js ('k') | lib/whitelisting.js » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld