Issue 6402 - Split filter hit / request logging out into own API

lib/requestBlocker.js

 /*
  * This file is part of Adblock Plus <https://adblockplus.org/>,
  * Copyright (C) 2006-present eyeo GmbH
  *
  * Adblock Plus is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 3 as
  * published by the Free Software Foundation.
  *
  * Adblock Plus is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
  * along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /** @module requestBlocker */
 
 "use strict";
 
 const {Filter, RegExpFilter, BlockingFilter} =
   require("../adblockpluscore/lib/filterClasses");
 const {Subscription} = require("../adblockpluscore/lib/subscriptionClasses");
 const {defaultMatcher} = require("../adblockpluscore/lib/matcher");
 const {FilterNotifier} = require("../adblockpluscore/lib/filterNotifier");
 const {Prefs} = require("./prefs");
 const {checkWhitelisted, getKey} = require("./whitelisting");
-const {stringifyURL, extractHostFromFrame, isThirdParty} = require("./url");
+const {extractHostFromFrame, isThirdParty} = require("./url");
 const {port} = require("./messaging");
 const {logRequest: hitLoggerLogRequest} = require("./hitLogger");
 
 const extensionProtocol = new URL(browser.extension.getURL("")).protocol;
 
 // Chrome can't distinguish between OBJECT_SUBREQUEST and OBJECT requests.
 if (!browser.webRequest.ResourceType ||
     !("OBJECT_SUBREQUEST" in browser.webRequest.ResourceType))
 {
   RegExpFilter.typeMap.OBJECT_SUBREQUEST = RegExpFilter.typeMap.OBJECT;
@@ skipping 41 matching lines @@
   return [
     extractHostFromFrame(frame, originUrl),
     getKey(page, frame, originUrl),
     !!checkWhitelisted(page, frame, originUrl,
                        RegExpFilter.typeMap.GENERICBLOCK)
   ];
 }
 
 function matchRequest(url, type, docDomain, sitekey, specificOnly)
 {
-  let urlString = stringifyURL(url);
   let thirdParty = isThirdParty(url, docDomain);
-
-  return [
-    defaultMatcher.matchesAny(urlString, RegExpFilter.typeMap[type],
-                              docDomain, thirdParty, sitekey, specificOnly),
-    urlString,
-    thirdParty
-  ];
+  let filter = defaultMatcher.matchesAny(url.href, RegExpFilter.typeMap[type],
+                                         docDomain, thirdParty,
+                                         sitekey, specificOnly);
+  return [filter, thirdParty];
 }
 
 function getRelatedTabIds(details)
 {
   // This is the common case, the request is associated with a single tab.
   // If tabId is -1, its not (e.g. the request was sent by
   // a Service/Shared Worker) and we have to identify the related tabs.
   if (details.tabId != -1)
     return Promise.resolve([details.tabId]);
 
   let url;                    // Firefox provides "originUrl" indicating the
   if (details.originUrl)      // URL of the tab that caused this request.
     url = details.originUrl;  // In case of Service/Shared Worker, this is the
                               // URL of the tab that caused the worker to spawn.
 
   else if (details.initiator)        // Chromium >=63 provides "intiator" which
     url = details.initiator + "/*";  // is equivalent to "originUrl" on Firefox
                                      // except that its not a full URL but just
                                      // an origin (proto + host).
   else
     return Promise.resolve([]);
 
   return browser.tabs.query({url}).then(tabs => tabs.map(tab => tab.id));
 }
 
-function logRequest(tabIds, url, type, docDomain, thirdParty,
-                    sitekey, specificOnly, filter)
+function logRequest(tabIds, request, filter)
 {
   if (filter)
     FilterNotifier.emit("filter.hitCount", filter, 0, 0, tabIds);
 
-  hitLoggerLogRequest(
-    tabIds, url, type, docDomain,
-    thirdParty, sitekey,
-    specificOnly, filter
-  );
+  hitLoggerLogRequest(tabIds, request, filter);
 }
 
 browser.webRequest.onBeforeRequest.addListener(details =>
 {
   // Never block top-level documents.
   if (details.type == "main_frame")
     return;
 
   // Filter out requests from non web protocols. Ideally, we'd explicitly
   // specify the protocols we are interested in (i.e. http://, https://,
@@ skipping 38 matching lines @@
   // this can also indicate a request sent by a Shared/Service Worker).
   if (!frame && !originUrl)
     return;
 
   if (checkWhitelisted(page, frame, originUrl))
     return;
 
   let type = resourceTypes.get(details.type) || "OTHER";
   let [docDomain, sitekey, specificOnly] = getDocumentInfo(page, frame,
                                                            originUrl);
-  let [filter, urlString, thirdParty] = matchRequest(url, type, docDomain,
-                                                     sitekey, specificOnly);
+  let [filter, thirdParty] = matchRequest(url, type, docDomain,
+                                          sitekey, specificOnly);
 
   getRelatedTabIds(details).then(tabIds =>
   {
-    logRequest(tabIds, urlString, type, docDomain,
-               thirdParty, sitekey, specificOnly, filter);
+    logRequest(
+      tabIds,
+      {url: details.url, type, docDomain, thirdParty, sitekey, specificOnly},
+      filter
+    );
   });
 
   if (filter instanceof BlockingFilter)
     return {cancel: true};
 }, {urls: ["<all_urls>"]}, ["blocking"]);
 
 port.on("filters.collapse", (message, sender) =>
 {
   let {page, frame} = sender;
 
@@ skipping 20 matching lines @@
   return blocked && Prefs.hidePlaceholders;
 });
 
 port.on("request.blockedByRTCWrapper", (msg, sender) =>
 {
   let {page, frame} = sender;
 
   if (checkWhitelisted(page, frame))
     return false;
 
+  let {url} = msg;
   let [docDomain, sitekey, specificOnly] = getDocumentInfo(page, frame);
-  let [filter, url, thirdParty] = matchRequest(new URL(msg.url),
-                                               "WEBRTC", docDomain,
-                                               sitekey, specificOnly);
-
-  logRequest([sender.page.id], url, "WEBRTC", docDomain,
-             thirdParty, sitekey, specificOnly, filter);
+  let [filter, thirdParty] = matchRequest(new URL(url), "WEBRTC", docDomain,
+                                          sitekey, specificOnly);
+  logRequest(
+    [sender.page.id],
+    {url, type: "WEBRTC", docDomain, thirdParty, sitekey, specificOnly},
+    filter
+  );
 
   return filter instanceof BlockingFilter;
 });
 
 let ignoreFilterNotifications = false;
 let handlerBehaviorChangedQuota =
   browser.webRequest.MAX_HANDLER_BEHAVIOR_CHANGED_CALLS_PER_10_MINUTES;
 
 function propagateHandlerBehaviorChange()
 {
@@ skipping 51 matching lines @@
 }
 
 FilterNotifier.on("subscription.added", onFilterChange);
 FilterNotifier.on("subscription.removed", onFilterChange);
 FilterNotifier.on("subscription.updated", onFilterChange);
 FilterNotifier.on("subscription.disabled", arg => onFilterChange(arg, true));
 FilterNotifier.on("filter.added", onFilterChange);
 FilterNotifier.on("filter.removed", onFilterChange);
 FilterNotifier.on("filter.disabled", arg => onFilterChange(arg, true));
 FilterNotifier.on("load", onFilterChange);