OOPIFs: Deduplicating MHTML parts across frames.

content/common/frame_messages.h

Index: content/common/frame_messages.h
diff --git a/content/common/frame_messages.h b/content/common/frame_messages.h
index 23d68cafff10c2802d5cbd4a5259477dd22ee667..10a0a5713e8e301152face1a73e748a006ab7c19 100644
--- a/content/common/frame_messages.h
+++ b/content/common/frame_messages.h
@@ -5,6 +5,11 @@
 // IPC messages for interacting with frames.
 // Multiply-included message file, hence no include guard.
 
+#include <map>
+#include <set>
+#include <string>
+#include <vector>
+
 #include "cc/surfaces/surface_id.h"
 #include "cc/surfaces/surface_sequence.h"
 #include "content/common/content_export.h"
@@ -430,6 +435,39 @@ IPC_STRUCT_TRAITS_BEGIN(content::SavableSubframe)
   IPC_STRUCT_TRAITS_MEMBER(routing_id)
 IPC_STRUCT_TRAITS_END()
 
+using FrameRoutingIdToContentIdMap = std::map<int, std::string>;

[dcheng, 2015/12/11 07:36:05]

Do we still need to typedef this?

[Łukasz Anforowicz, 2015/12/14 19:39:02]

1. We do need a typedef - otherwise preprocessor will get confused - see
http://stackoverflow.com/questions/13842468/comma-in-c-c-macro

2. In the earlier CL (crrev.com/1386873003) I moved the typedef into a
singly-included section of this header file.

+IPC_STRUCT_BEGIN(FrameMsg_SerializeAsMHTML_Params)
+  // Job id - used to match responses to requests.
+  IPC_STRUCT_MEMBER(int, job_id)
+
+  // Destination file handle.
+  IPC_STRUCT_MEMBER(IPC::PlatformFileForTransit, destination_file)
+
+  // MHTML boundary marker / MIME multipart boundary maker.  The same
+  // |mhtml_boundary_marker| should be used for serialization of each frame.
+  IPC_STRUCT_MEMBER(std::string, mhtml_boundary_marker)
+
+  // Frame to content-id map.
+  // Keys are routing ids of either RenderFrames or RenderFrameProxies.
+  // Values are MHTML content-ids - see WebPageSerializer::generateMHTMLParts.
+  IPC_STRUCT_MEMBER(FrameRoutingIdToContentIdMap,
+                    frame_routing_id_to_content_id)
+
+  // |digests_of_uris_to_skip| contains digests of uris of MHTML parts that
+  // should be skipped.  This helps deduplicate mhtml parts across frames.
+  // SECURITY NOTE: Sha256 digests (rather than uris) are used to prevent
+  // disclosing uris to other renderer processes;  the digests should be
+  // generated using SHA256HashString function from crypto/sha2.h and hashing
+  // |salt + url.spec()|.
+  IPC_STRUCT_MEMBER(std::set<std::string>, digests_of_uris_to_skip)
+
+  // Salt used for |digests_of_uris_to_skip|.
+  IPC_STRUCT_MEMBER(std::string, salt)
+
+  // If |is_last_frame| is true, then an MHTML footer will be generated.
+  IPC_STRUCT_MEMBER(bool, is_last_frame)
+IPC_STRUCT_END()
+
 #if defined(OS_MACOSX) || defined(OS_ANDROID)
 // This message is used for supporting popup menus on Mac OS X and Android using
 // native controls. See the FrameHostMsg_ShowPopup message.
@@ -722,29 +760,11 @@ IPC_MESSAGE_ROUTED1(FrameMsg_GetSerializedHtmlWithLocalLinks,
                     FrameMsg_GetSerializedHtmlWithLocalLinks_Map);
 
 // Serialize target frame and its resources into MHTML and write it into the
-// provided destination file handle.
-//
-// When starting generation of a new MHTML document, one needs to start by
-// sending FrameMsg_SerializeAsMHTML for the *main* frame (main frame needs to
-// be the first part in the MHTML document + main frame will trigger generation
-// of the MHTML header).
-//
-// The same |mhtml_boundary_marker| should be used for serialization of each
-// frame (this string will be used as a mime multipart boundary within the mhtml
-// document).
-//
-// For more details about frame to content id map please see
-// WebPageSerializer::generateMHTMLParts method.
-//
-// |is_last_frame| controls whether the serializer in the renderer will
-// emit the MHTML footer.
-using FrameRoutingIdToContentIdMap = std::map<int, std::string>;
-IPC_MESSAGE_ROUTED5(FrameMsg_SerializeAsMHTML,
-                    int /* job_id (used to match responses to requests) */,
-                    IPC::PlatformFileForTransit /* destination file handle */,
-                    std::string /* mhtml boundary marker */,
-                    FrameRoutingIdToContentIdMap,
-                    bool /* is last frame */)
+// provided destination file handle.  Note that when serializing multiple
+// frames, one needs to serialize the *main* frame first (the main frame
+// needs to go first according to RFC2557 + the main frame will trigger
+// generation of the MHTML header).
+IPC_MESSAGE_ROUTED1(FrameMsg_SerializeAsMHTML, FrameMsg_SerializeAsMHTML_Params)
 
 IPC_MESSAGE_ROUTED1(FrameMsg_SetFrameOwnerProperties,
                     blink::WebFrameOwnerProperties /* frame_owner_properties */)
@@ -1271,9 +1291,10 @@ IPC_MESSAGE_ROUTED2(FrameHostMsg_SerializedHtmlWithLocalLinksResponse,
                     bool /* end of data? */)
 
 // Response to FrameMsg_SerializeAsMHTML.
-IPC_MESSAGE_ROUTED2(FrameHostMsg_SerializeAsMHTMLResponse,
+IPC_MESSAGE_ROUTED3(FrameHostMsg_SerializeAsMHTMLResponse,
                     int /* job_id (used to match responses to requests) */,
-                    bool /* true if success, false if error */)
+                    bool /* true if success, false if error */,
+                    std::set<GURL> /* uris of generated mhtml parts */)
 
 // Sent when the renderer updates hint for importance of a tab.
 IPC_MESSAGE_ROUTED1(FrameHostMsg_UpdatePageImportanceSignals,