Save Page As MHTML

content/browser/download/save_package.cc

Index: content/browser/download/save_package.cc
diff --git a/content/browser/download/save_package.cc b/content/browser/download/save_package.cc
index 627215074055513a769f17aeb11642fdad45892c..b816dd4b14d6b5d462d9c34cf15b3d6a2a84c325 100644
--- a/content/browser/download/save_package.cc
+++ b/content/browser/download/save_package.cc
@@ -141,8 +141,9 @@ SavePackage::SavePackage(WebContents* web_contents,
       wrote_to_completed_file_(false),
       wrote_to_failed_file_(false) {
   DCHECK(page_url_.is_valid());
-  DCHECK(save_type_ == content::SAVE_PAGE_TYPE_AS_ONLY_HTML ||
-         save_type_ == content::SAVE_PAGE_TYPE_AS_COMPLETE_HTML);
+  DCHECK((save_type_ == content::SAVE_PAGE_TYPE_AS_ONLY_HTML) ||
+         (save_type_ == content::SAVE_PAGE_TYPE_AS_MHTML) ||
+         (save_type_ == content::SAVE_PAGE_TYPE_AS_COMPLETE_HTML));
   DCHECK(!saved_main_file_path_.empty() &&
          saved_main_file_path_.value().length() <= kMaxFilePathLength);
   DCHECK(!saved_main_directory_path_.empty() &&
@@ -281,6 +282,20 @@ bool SavePackage::Init() {
     return false;
   }
 
+  if (save_type_ == content::SAVE_PAGE_TYPE_AS_MHTML) {
+    // Force the extension to be mht. If the extension is left as html, then
+    // chrome will render it as html when opened instead of mhtml.
+    // Force the extension before creating the DownloadItem.
+    // TODO(benjhayden): Figure out how to move this back into the file picker.
+    // If the .html file already exists, then the user will be prompted to
+    // replace it, even thought it won't be replaced. If the .mht already
+    // exists, then the user will not be prompted to replace it, even though it
+    // will be replaced. The user will only be prompted to replace the .mht if
+    // they type out the filename including .mht.
+    saved_main_file_path_ = saved_main_file_path_.ReplaceExtension(
+        FILE_PATH_LITERAL("mht"));
+  }
+
   // The download manager keeps ownership but adds us as an observer.
   download_ = download_manager_->CreateSavePackageDownloadItem(
       saved_main_file_path_, page_url_,
@@ -291,6 +306,9 @@ bool SavePackage::Init() {
     // Get directory
     DCHECK(!saved_main_directory_path_.empty());
     GetAllSavableResourceLinksForCurrentPage();
+  } else if (save_type_ == content::SAVE_PAGE_TYPE_AS_MHTML) {
+    web_contents()->GenerateMHTML(saved_main_file_path_, base::Bind(
+        &SavePackage::MHTMLGenerated, this));
   } else {
     wait_state_ = NET_FILES;
     SaveFileCreateInfo::SaveFileSource save_source = page_url_.SchemeIsFile() ?
@@ -311,6 +329,18 @@ bool SavePackage::Init() {
   return true;
 }
 
+void SavePackage::MHTMLGenerated(const FilePath& path, int64 size) {
+  if (size <= 0) {
+    Cancel(false);
+  } else {
+    download_->SetTotalBytes(size);
+    download_->OnAllDataSaved(size, DownloadItem::kEmptyFileHash);
+    download_->UpdateProgress(size, 0, "");
+    wrote_to_completed_file_ = true;
+    Finish();
+  }
+}
+
 // On POSIX, the length of |pure_file_name| + |file_name_ext| is further
 // restricted by NAME_MAX. The maximum allowed path looks like:
 // '/path/to/save_dir' + '/' + NAME_MAX.
@@ -706,8 +736,10 @@ void SavePackage::Finish() {
                  save_ids));
 
   if (download_) {
-    download_->OnAllDataSaved(all_save_items_count_,
-                              DownloadItem::kEmptyFileHash);
+    if (save_type_ != content::SAVE_PAGE_TYPE_AS_MHTML) {

[Randy Smith (Not in Mondays), 2012/04/16 17:45:47]

I'm somewhat torn about this and related logic.  It looks like the behavior
we're going to end up with is:
* HTML only: Size == count of items == 1
* HTML complete: Size == count of items == n
* MHTML: Size == number of bytes downloads

Before we were broken but consistent (size was always count of items).  Now
we're inconsistent, and to my mind, inconsistently inconsistent (because the
other single file case is still count of items rather than number of bytes).  Is
this really the behavior we want?

[benjhayden, 2012/04/16 19:08:06]

Done.

+      download_->OnAllDataSaved(all_save_items_count_,

[Randy Smith (Not in Mondays), 2012/04/16 17:45:47]

nit: If there's an easy, not too ugly way to do it, I'd like all the
OnAllDataSaved calls to be in the same place.  That way a) there's less chance
of us ending up with two or zero calls at some change in the future, and b)
whatever behavior we decide on with regard to size will be very visible at one
place in the code.

[benjhayden, 2012/04/16 19:08:06]

Done.

+                                DownloadItem::kEmptyFileHash);
+    }
     download_->MarkAsComplete();
     FinalizeDownloadEntry();
   }
@@ -775,8 +807,9 @@ void SavePackage::SaveFailed(const GURL& save_url) {
   if (download_)
     download_->UpdateProgress(completed_count(), CurrentSpeed(), "");
 
-  if (save_type_ == content::SAVE_PAGE_TYPE_AS_ONLY_HTML ||
-      save_item->save_source() == SaveFileCreateInfo::SAVE_FILE_FROM_DOM) {
+  if ((save_type_ == content::SAVE_PAGE_TYPE_AS_ONLY_HTML) ||
+      (save_type_ == content::SAVE_PAGE_TYPE_AS_MHTML) ||
+      (save_item->save_source() == SaveFileCreateInfo::SAVE_FILE_FROM_DOM)) {
     // We got error when saving page. Treat it as disk error.
     Cancel(true);
   }
@@ -882,9 +915,10 @@ void SavePackage::DoSavingProcess() {
       DCHECK(wait_state_ == HTML_DATA);
     }
   } else {
-    // Save as HTML only.
+    // Save as HTML only or MHTML.
     DCHECK(wait_state_ == NET_FILES);
-    DCHECK(save_type_ == content::SAVE_PAGE_TYPE_AS_ONLY_HTML);
+    DCHECK((save_type_ == content::SAVE_PAGE_TYPE_AS_ONLY_HTML) ||
+           (save_type_ == content::SAVE_PAGE_TYPE_AS_MHTML));
     if (waiting_item_queue_.size()) {
       DCHECK(all_save_items_count_ == waiting_item_queue_.size());
       SaveNextFile(false);