Issue 3792 - Fix to support multiprocess firefox

lib/child/frameScript.js

-"use strict";

[Wladimir Palant, 2016/03/15 10:07:10]

We put "use strict" after the license header.

[sergei, 2016/03/16 14:44:23]

Done.

 /*
  * This Source Code is subject to the terms of the Mozilla Public License
  * version 2.0 (the "License"). You can obtain a copy of the License at
  * http://mozilla.org/MPL/2.0/.
  */
 
+"use strict";
+
+const {classes: Cc, interfaces: Ci, utils: Cu, results: Cr} = Components;
+
 /**
- * Sends exception to parent process script using "abpcrawler:reportException"
- * message with CPOW of the exception parameter.
- * @param e exception to be sent.
+ * @param e exception
  */
 function reportException(e)
 {
-  sendSyncMessage("abpcrawler:reportException", undefined, e);

[Wladimir Palant, 2016/03/15 10:07:10]

Don't send sync messages unless you absolutely cannot help it (no, this isn't
such a case).

[sergei, 2016/03/16 14:44:23]

Acknowledged.
JIC, it was sync here because CPOW is used (see comment in lib/crawler.js) here
and to avoid race conditions we should pass it using synchronous message.

+  let stack = "";
+  if (e && typeof e == "object" && "stack" in e)
+    stack = e.stack + "\n";
+
+  Cu.reportError(e);
+  dump(e + "\n" + stack + "\n");
 }
 
-const {classes: Cc, interfaces: Ci, utils: Cu} = Components;
-
-let {Services} = Cu.import("resource://gre/modules/Services.jsm", {});
-let {XPCOMUtils} = Cu.import("resource://gre/modules/XPCOMUtils.jsm", {});
+const {XPCOMUtils} = Cu.import("resource://gre/modules/XPCOMUtils.jsm", {});
 
 /**
- * Waits for finishing of the page loading, calls `gatherPageInfo` and sends
- * gahter information using "abpcrawler:pageInfoGathered" message.
- * https://developer.mozilla.org/en-US/docs/Mozilla/Tech/XPCOM/Reference/Interface/nsIWebProgressListener
+ * Progress listener capturing the data of the current page and calling
+ * onPageLoaded(data) when loading is finished, where data contains
+ * HTTP status and headers.
+ *
+ * @type nsIWebProgressListener
  */
 let webProgressListener =
 {
   onStateChange: function(webProgress, request, flags, status)
   {
-    if ((flags & Ci.nsIWebProgressListener.STATE_STOP) && (flags & Ci.nsIWebProgressListener.STATE_IS_WINDOW))
+    if (webProgress.DOMWindow == content &&
+        (flags & Ci.nsIWebProgressListener.STATE_STOP))
     {
+      // First time we receive STATE_STOP for about:blank and the second time
+      // for our interested URL which is distinct from about:blank.
+      // However we should not process about:blank because it can happen that
+      // the message with information about about:blank is delivered when the
+      // code in crawler.js is already waiting for a message from this tab.
+      // Another case we are not interested in is about:newtab.
+      if (content.location.protocol == "about:")
+        return;
+      let pageInfo = {channelStatus: status};
       if (request instanceof Ci.nsIHttpChannel)
       {
-        let pageInfo = {headers: []};
         try
         {
+          pageInfo.headers = [];
           pageInfo.headers.push("HTTP/x.x " + request.responseStatus + " " + request.responseStatusText);
-          request.visitResponseHeaders((header, value) =>pageInfo.headers.push(header + ": " + value));
+          request.visitResponseHeaders((header, value) => pageInfo.headers.push(header + ": " + value));
         }
         catch (e)
         {
           reportException(e);
         }
-        Object.assign(pageInfo, gatherPageInfo(content));
-        sendAsyncMessage("abpcrawler:pageInfoGathered", pageInfo);
       }
+      onPageLoaded(pageInfo);
     }
   },
 
-  // definitions of the remaining functions see related documentation
-  onLocationChange: function(webProgress, request, URI, flag) {},
-  onProgressChange: function(aWebProgress, aRequest, curSelf, maxSelf, curTot, maxTot) {},
-  onStatusChange: function(aWebProgress, aRequest, aStatus, aMessage) {},
-  onSecurityChange: function(aWebProgress, aRequest, aState) {},
- 
+  onLocationChange: function() {},
+  onProgressChange: function() {},
+  onStatusChange: function() {},
+  onSecurityChange: function() {},
+
   QueryInterface: XPCOMUtils.generateQI([Ci.nsIWebProgressListener, Ci.nsISupportsWeakReference])
 };
 
-let filter = Cc["@mozilla.org/appshell/component/browser-status-filter;1"]
-             .createInstance(Ci.nsIWebProgress);
-filter.addProgressListener(webProgressListener, Ci.nsIWebProgress.NOTIFY_ALL);
+function onPageLoaded(pageInfo)
+{
+  Object.assign(pageInfo, gatherPageInfo(content));
+  sendAsyncMessage("abpcrawler:pageInfoGathered", pageInfo);
+};
 
-let webProgress = docShell.QueryInterface(Ci.nsIInterfaceRequestor)
-                          .getInterface(Ci.nsIWebProgress);
-webProgress.addProgressListener(filter, Ci.nsIWebProgress.NOTIFY_ALL);
+let webProgress = docShell.QueryInterface(Ci.nsIInterfaceRequestor).getInterface(Ci.nsIWebProgress);
+webProgress.addProgressListener(webProgressListener, Ci.nsIWebProgress.NOTIFY_STATE_WINDOW);
 
 /**
- * Gathers information about page using DOM window.
+ * Gathers information about a DOM window.
  * Currently
  *  - creates a screenshot of the page
  *  - serializes the page source code
  * @param {nsIDOMWindow} wnd window to process
  * @return {Object} the object containing "screenshot" and "source" properties.
  */
 function gatherPageInfo(wnd)
 {
   let document = wnd.document;
-  let result = {};
-  if (document.documentElement)
+  let result = {errors:[]};
+  if (!document.documentElement)
   {
-    try
-    {
-      let canvas = document.createElementNS("http://www.w3.org/1999/xhtml", "canvas");
-      canvas.width = document.documentElement.scrollWidth;
-      canvas.height = document.documentElement.scrollHeight;
-      if (canvas.width > 0 && canvas.height > 0)
-      {
-        let context = canvas.getContext("2d");
-        context.drawWindow(wnd, 0, 0, canvas.width, canvas.height, "rgb(255, 255, 255)");
-        result.screenshot = canvas.toDataURL("image/jpeg", 0.8);
-      }
-      // TODO: Capture frames as well?
-      let serializer = new wnd.XMLSerializer();
-      result.source = serializer.serializeToString(document.documentElement);
-    }
-    catch (e)
-    {
-      reportException(e);
-      result.error = "Cannot gather page info";
-    }
+    result.errors.push("No document.documentElement");
+    return result;
   }
+
+  try
+  {
+    let canvas = document.createElementNS("http://www.w3.org/1999/xhtml", "canvas");
+    canvas.width = document.documentElement.scrollWidth;
+    canvas.height = document.documentElement.scrollHeight;
+    let context = canvas.getContext("2d");
+    context.drawWindow(wnd, 0, 0, canvas.width, canvas.height, "rgb(255, 255, 255)");
+    result.screenshot = canvas.toDataURL("image/jpeg", 0.8);
+  }
+  catch (e)
+  {
+    reportException(e);
+    result.errors.push("Cannot make page screenshot");
+  }
+
+  try
+  {
+    // TODO: Capture frames as well?
+    let serializer = new wnd.XMLSerializer();
+    result.source = serializer.serializeToString(document.documentElement);
+  }
+  catch(e)
+  {
+    reportException(e);
+    result.errors.push("Cannot obtain page source code");
+  }
+
   return result;
 }