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

chrome/renderer/chrome_render_view_observer.cc

Index: chrome/renderer/chrome_render_view_observer.cc
diff --git a/chrome/renderer/chrome_render_view_observer.cc b/chrome/renderer/chrome_render_view_observer.cc
index 8e0420c41d54153aa37eb1daf51e578784e4dfc1..344f6038aa7c9fd2a755f20e023e77b40b05a362 100644
--- a/chrome/renderer/chrome_render_view_observer.cc
+++ b/chrome/renderer/chrome_render_view_observer.cc
@@ -10,7 +10,7 @@
 #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"
@@ -40,6 +40,7 @@
 #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"
@@ -48,6 +49,7 @@
 #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"
@@ -56,6 +58,7 @@ using WebKit::WebAccessibilityObject;
 using WebKit::WebCString;
 using WebKit::WebDataSource;
 using WebKit::WebDocument;
+using WebKit::WebElement;
 using WebKit::WebFrame;
 using WebKit::WebGestureEvent;
 using WebKit::WebIconURL;
@@ -190,6 +193,19 @@ ChromeRenderViewObserver::ChromeRenderViewObserver(
 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)
@@ -615,13 +631,16 @@ void ChromeRenderViewObserver::DidStartLoading() {
 }
 
 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(
@@ -635,7 +654,10 @@ void ChromeRenderViewObserver::DidCommitProvisionalLoad(
   if (!is_new_navigation)
     return;
 
+  int page_id = render_view()->GetPageId();
   CapturePageInfoLater(
+      page_id,
+      HasRefreshMetaTag(frame),
       true,  // preliminary_capture
       base::TimeDelta::FromMilliseconds(kDelayForForcedCaptureMs));
 }
@@ -660,19 +682,23 @@ void ChromeRenderViewObserver::DidHandleGestureEvent(
       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;
 
@@ -698,7 +724,9 @@ void ChromeRenderViewObserver::CapturePageInfo(bool preliminary_capture) {
   // 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