Translate: infobars should not appear when a page has a refresh meta tag

chrome/renderer/chrome_render_view_observer.cc

 // Copyright (c) 2012 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "chrome/renderer/chrome_render_view_observer.h"
 
 #include "base/bind.h"
 #include "base/bind_helpers.h"
 #include "base/command_line.h"
 #include "base/debug/trace_event.h"
 #include "base/message_loop.h"
 #include "base/metrics/histogram.h"
-#include "base/string_util.h"
+#include "base/utf_string_conversions.h"
 #include "chrome/common/chrome_constants.h"
 #include "chrome/common/chrome_switches.h"
 #include "chrome/common/prerender_messages.h"
 #include "chrome/common/render_messages.h"
 #include "chrome/common/url_constants.h"
 #include "chrome/renderer/chrome_render_process_observer.h"
 #include "chrome/renderer/content_settings_observer.h"
 #include "chrome/renderer/extensions/dispatcher.h"
 #include "chrome/renderer/external_host_bindings.h"
 #include "chrome/renderer/frame_sniffer.h"
 #include "chrome/renderer/prerender/prerender_helper.h"
 #include "chrome/renderer/safe_browsing/phishing_classifier_delegate.h"
 #include "chrome/renderer/translate/translate_helper.h"
 #include "chrome/renderer/webview_color_overlay.h"
 #include "content/public/common/bindings_policy.h"
 #include "content/public/renderer/content_renderer_client.h"
 #include "content/public/renderer/render_view.h"
 #include "extensions/common/constants.h"
 #include "net/base/data_url.h"
 #include "skia/ext/platform_canvas.h"
 #include "third_party/WebKit/Source/Platform/chromium/public/WebCString.h"
 #include "third_party/WebKit/Source/Platform/chromium/public/WebRect.h"
 #include "third_party/WebKit/Source/Platform/chromium/public/WebSize.h"
 #include "third_party/WebKit/Source/Platform/chromium/public/WebString.h"
 #include "third_party/WebKit/Source/Platform/chromium/public/WebURLRequest.h"
 #include "third_party/WebKit/Source/Platform/chromium/public/WebVector.h"
 #include "third_party/WebKit/Source/WebKit/chromium/public/WebAccessibilityObject.h"
 #include "third_party/WebKit/Source/WebKit/chromium/public/WebDataSource.h"
 #include "third_party/WebKit/Source/WebKit/chromium/public/WebDocument.h"
+#include "third_party/WebKit/Source/WebKit/chromium/public/WebElement.h"
 #include "third_party/WebKit/Source/WebKit/chromium/public/WebFrame.h"
 #include "third_party/WebKit/Source/WebKit/chromium/public/WebInputEvent.h"
 #include "third_party/WebKit/Source/WebKit/chromium/public/WebView.h"
 #include "ui/base/ui_base_switches.h"
 #include "ui/gfx/favicon_size.h"
 #include "ui/gfx/size.h"
 #include "ui/gfx/skbitmap_operations.h"
 #include "v8/include/v8-testing.h"
+#include "webkit/glue/dom_operations.h"
 #include "webkit/glue/image_decoder.h"
 #include "webkit/glue/multi_resolution_image_resource_fetcher.h"
 #include "webkit/glue/webkit_glue.h"
 
 using WebKit::WebAccessibilityObject;
 using WebKit::WebCString;
 using WebKit::WebDataSource;
 using WebKit::WebDocument;
+using WebKit::WebElement;
 using WebKit::WebFrame;
 using WebKit::WebGestureEvent;
 using WebKit::WebIconURL;
 using WebKit::WebRect;
 using WebKit::WebSecurityOrigin;
 using WebKit::WebSize;
 using WebKit::WebString;
 using WebKit::WebTouchEvent;
 using WebKit::WebURL;
 using WebKit::WebURLRequest;
@@ skipping 114 matching lines @@
       capture_timer_(false, false) {
   const CommandLine& command_line = *CommandLine::ForCurrentProcess();
   render_view->GetWebView()->setPermissionClient(this);
   if (!command_line.HasSwitch(switches::kDisableClientSidePhishingDetection))
     OnSetClientSidePhishingDetection(true);
 }
 
 ChromeRenderViewObserver::~ChromeRenderViewObserver() {
 }
 
+// static
+bool ChromeRenderViewObserver::HasRefreshMetaTag(WebFrame* frame) {
+  if (!frame)
+    return false;
+  std::vector<WebElement> meta_elements;
+  WebDocument document = frame->document();
+  webkit_glue::GetMetaElementsWithAttribute(&document,
+                                            ASCIIToUTF16("http-equiv"),
+                                            ASCIIToUTF16("refresh"),
+                                            &meta_elements);
+  return meta_elements.size() != 0;
+}
+
 bool ChromeRenderViewObserver::OnMessageReceived(const IPC::Message& message) {
   bool handled = true;
   IPC_BEGIN_MESSAGE_MAP(ChromeRenderViewObserver, message)
     IPC_MESSAGE_HANDLER(ChromeViewMsg_WebUIJavaScript, OnWebUIJavaScript)
     IPC_MESSAGE_HANDLER(ChromeViewMsg_HandleMessageFromExternalHost,
                         OnHandleMessageFromExternalHost)
     IPC_MESSAGE_HANDLER(ChromeViewMsg_JavaScriptStressTestControl,
                         OnJavaScriptStressTestControl)
     IPC_MESSAGE_HANDLER(ChromeViewMsg_SetAllowDisplayingInsecureContent,
                         OnSetAllowDisplayingInsecureContent)
@@ skipping 405 matching lines @@
       webui_javascript_.get()) {
     render_view()->EvaluateScript(webui_javascript_->frame_xpath,
                                   webui_javascript_->jscript,
                                   webui_javascript_->id,
                                   webui_javascript_->notify_result);
     webui_javascript_.reset();
   }
 }
 
 void ChromeRenderViewObserver::DidStopLoading() {
+  int page_id = render_view()->GetPageId();
+  WebFrame* main_frame = render_view()->GetWebView()->mainFrame();
   CapturePageInfoLater(
+      page_id,
+      HasRefreshMetaTag(main_frame),
       false,  // preliminary_capture
       base::TimeDelta::FromMilliseconds(
           render_view()->GetContentStateImmediately() ?
               0 : kDelayForCaptureMs));
 
-  WebFrame* main_frame = render_view()->GetWebView()->mainFrame();
   GURL osd_url = main_frame->document().openSearchDescriptionURL();
   if (!osd_url.is_empty()) {
     Send(new ChromeViewHostMsg_PageHasOSDD(
         routing_id(), render_view()->GetPageId(), osd_url,
         search_provider::AUTODETECTED_PROVIDER));
   }
 }
 
 void ChromeRenderViewObserver::DidCommitProvisionalLoad(
     WebFrame* frame, bool is_new_navigation) {
   if (!is_new_navigation)
     return;
 
+  int page_id = render_view()->GetPageId();
   CapturePageInfoLater(
+      page_id,
+      HasRefreshMetaTag(frame),
       true,  // preliminary_capture
       base::TimeDelta::FromMilliseconds(kDelayForForcedCaptureMs));
 }
 
 void ChromeRenderViewObserver::DidClearWindowObject(WebFrame* frame) {
   if (render_view()->GetEnabledBindings() &
           content::BINDINGS_POLICY_EXTERNAL_HOST) {
     GetExternalHostBindings()->BindToJavascript(frame, "externalHost");
   }
 }
 
 void ChromeRenderViewObserver::DidHandleGestureEvent(
     const WebGestureEvent& event) {
   if (event.type != WebKit::WebGestureEvent::GestureTap)
     return;
 
   WebKit::WebTextInputType text_input_type =
       render_view()->GetWebView()->textInputType();
 
   render_view()->Send(new ChromeViewHostMsg_FocusedNodeTouched(
       routing_id(),
       text_input_type != WebKit::WebTextInputTypeNone));
 }
 
-void ChromeRenderViewObserver::CapturePageInfoLater(bool preliminary_capture,
+void ChromeRenderViewObserver::CapturePageInfoLater(int page_id,
+                                                    bool has_refresh,
+                                                    bool preliminary_capture,
                                                     base::TimeDelta delay) {
   capture_timer_.Start(
       FROM_HERE,
       delay,
       base::Bind(&ChromeRenderViewObserver::CapturePageInfo,
                  base::Unretained(this),
+                 page_id,
+                 has_refresh,
                  preliminary_capture));
 }
 
-void ChromeRenderViewObserver::CapturePageInfo(bool preliminary_capture) {
-  int page_id = render_view()->GetPageId();

[jochen (gone - plz use gerrit), 2013/05/02 09:48:42]

what's the reason to not just check for the meta tag here?

[Takashi Toyoshima, 2013/05/02 11:51:18]

Thanks.
You are right. I should just pass page_id and check the id is not changed here.
Refresh meta information and captured text should be consistent with page_id.

But, after revised my change, I find another problem. I'm not sure the reason
now, but I can not find refresh meta tag here in my test case using <meta
http-equiv="refresh" content="0;url=...>.

PageCapture returns apparently the first page contents, but refresh meta tag
disappears. I guess another code remove the tag when it handles the client
redirect.

I'll continue to investigate this problem.

[Takashi Toyoshima, 2013/05/02 12:13:58]

In the case of client redirect of meta refresh, page_id is not updated.

If a redirected second page is slow, we may capture incomplete document here. In
my case, I captured incomplete empty body and can not find refresh meta because
in this function, client redirect is already performed, and the second page is
waiting for loaded.

So, we should check refresh meta tag before posting task as my first change did.

-
+void ChromeRenderViewObserver::CapturePageInfo(int page_id,
+                                               bool has_refresh,
+                                               bool preliminary_capture) {
   if (!render_view()->GetWebView())
     return;
 
   WebFrame* main_frame = render_view()->GetWebView()->mainFrame();
   if (!main_frame)
     return;
 
   // Don't index/capture pages that are in view source mode.
   if (main_frame->isViewSourceModeEnabled())
     return;
 
   // Don't index/capture pages that failed to load.  This only checks the top
   // level frame so the thumbnail may contain a frame that failed to load.
   WebDataSource* ds = main_frame->dataSource();
   if (ds && ds->hasUnreachableURL())
     return;
 
   // Don't index/capture pages that are being prerendered.
   if (prerender::PrerenderHelper::IsPrerendering(render_view()))
     return;
 
   // Retrieve the frame's full text (up to kMaxIndexChars), and pass it to the
   // translate helper for language detection and possible translation.
   string16 contents;
   CaptureText(main_frame, &contents);
-  if (translate_helper_)
+  // Skip to handle translation when the page includes refresh meta tag.
+  // Because this page will be replaced without updating |page_id| soon.
+  if (translate_helper_ && !has_refresh)
     translate_helper_->PageCaptured(contents);
 
   // Skip indexing if this is not a new load.  Note that the case where
   // page_id == last_indexed_page_id_ is more complicated, since we need to
   // reindex if the toplevel URL has changed (such as from a redirect), even
   // though this may not cause the page id to be incremented.
   if (page_id < last_indexed_page_id_)
     return;
 
   bool same_page_id = last_indexed_page_id_ == page_id;
@@ skipping 72 matching lines @@
   if (!external_host_bindings_.get()) {
     external_host_bindings_.reset(new ExternalHostBindings(
         render_view(), routing_id()));
   }
   return external_host_bindings_.get();
 }
 
 bool ChromeRenderViewObserver::IsStrictSecurityHost(const std::string& host) {
   return (strict_security_hosts_.find(host) != strict_security_hosts_.end());
 }