Use HTTP status return code to make SDCH handling more robust...

net/base/sdch_filter.cc

 // Copyright (c) 2006-2008 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 <limits.h>
 #include <ctype.h>
 #include <algorithm>
 
 #include "base/file_util.h"
 #include "base/histogram.h"
@@ skipping 209 matching lines @@
   UpdateReadTimes();
 
   if (WAITING_FOR_DICTIONARY_SELECTION == decoding_status_) {
     FilterStatus status = InitializeDictionary();
     if (FILTER_NEED_MORE_DATA == status)
       return FILTER_NEED_MORE_DATA;
     if (FILTER_ERROR == status) {
       DCHECK(DECODING_ERROR == decoding_status_);
       DCHECK(0 == dest_buffer_excess_index_);
       DCHECK(dest_buffer_excess_.empty());
-      if (possible_pass_through_) {
+      // This is where we try very hard to do error recovery, and make this
+      // protocol robust in teh face of proxies that do many different things.
+      // If we decide that things are looking very bad (too hard to recover),
+      // we may even issue a "meta-refresh" to reload the page without an SDCH
+      // advertisement (so that we are sure we're not hurting anything).  First
+      // we try for some light weight recovery, and teh final else clause below
+      // supports the last ditch meta-refresh approach.
+      //
+      // Watch out for an error page inserted by the proxy as part of a 40x
+      // error response.  When we see such content molestation, we certainly
+      // need to fall into the meta-refresh case.
+      bool successful_response = filter_context().GetResponseCode() == 200;
+      if (possible_pass_through_ && successful_response) {
+        // This is the most graceful response. There really was no error. We
+        // were just overly cautious.
         // We added the sdch coding tag, and it should not have been added.
         // This can happen in server experiments, where the server decides
         // not to use sdch, even though there is a dictionary.  To be
         // conservative, we locally added the tentative sdch (fearing that a
         // proxy stripped it!) and we must now recant (pass through).
         SdchManager::SdchErrorRecovery(SdchManager::DISCARD_TENTATIVE_SDCH);
         decoding_status_ = PASS_THROUGH;
         dest_buffer_excess_ = dictionary_hash_;  // Send what we scanned.
-      } else if (!dictionary_hash_is_plausible_) {
+      } else if (successful_response && !dictionary_hash_is_plausible_) {
         // One of the first 9 bytes precluded consideration as a hash.
         // This can't be an SDCH payload, even though the server said it was.
         // This is a major error, as the server or proxy tagged this SDCH even
         // though it is not!
         // The good news is that error recovery is clear...
         SdchManager::SdchErrorRecovery(SdchManager::PASSING_THROUGH_NON_SDCH);
         decoding_status_ = PASS_THROUGH;
         dest_buffer_excess_ = dictionary_hash_;  // Send what we scanned.
       } else {
-        // We don't have the dictionary that was demanded.
+        // This is where we try to do the expensive meta-refresh.
+        // Either this was an error response (probably an error page inserted
+        // by a proxy, as in bug 8916) or else we don't have the dictionary that
+        // was demanded.
         // With very low probability, random garbage data looked like a
         // dictionary specifier (8 ASCII characters followed by a null), but
         // that is sufficiently unlikely that we ignore it.
-        if (std::string::npos == mime_type_.find_first_of("text/html")) {
+        if (std::string::npos == mime_type_.find("text/html")) {
+          // Since we can't do a meta-refresh (along with an exponential
+          // backoff), we'll just make sure this NEVER happens again.
           SdchManager::BlacklistDomainForever(url_);
           if (was_cached_)
             SdchManager::SdchErrorRecovery(
                 SdchManager::CACHED_META_REFRESH_UNSUPPORTED);
           else
             SdchManager::SdchErrorRecovery(
                 SdchManager::META_REFRESH_UNSUPPORTED);
           return FILTER_ERROR;
         }
         // HTML content means we can issue a meta-refresh, and get the content
@@ skipping 141 matching lines @@
   memcpy(dest_buffer, dest_buffer_excess_.data() + dest_buffer_excess_index_,
          amount);
   dest_buffer_excess_index_ += amount;
   if (dest_buffer_excess_.size() <= dest_buffer_excess_index_) {
     DCHECK(dest_buffer_excess_.size() == dest_buffer_excess_index_);
     dest_buffer_excess_.clear();
     dest_buffer_excess_index_ = 0;
   }
   return amount;
 }