Sdch view for net-internals

net/filter/filter.cc

 // Copyright 2014 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 "net/filter/filter.h"
 
 #include "base/files/file_path.h"
 #include "base/strings/string_util.h"
 #include "net/base/filename_util_unsafe.h"
 #include "net/base/io_buffer.h"
@@ skipping 143 matching lines @@
 }
 
 // static
 void Filter::FixupEncodingTypes(
     const FilterContext& filter_context,
     std::vector<FilterType>* encoding_types) {
   std::string mime_type;
   bool success = filter_context.GetMimeType(&mime_type);
   DCHECK(success || mime_type.empty());
 
+  GURL url;
+  success = filter_context.GetURL(&url);
+
   if ((1 == encoding_types->size()) &&
       (FILTER_TYPE_GZIP == encoding_types->front())) {
     if (LowerCaseEqualsASCII(mime_type, kApplicationXGzip) ||
         LowerCaseEqualsASCII(mime_type, kApplicationGzip) ||
         LowerCaseEqualsASCII(mime_type, kApplicationXGunzip))
       // The server has told us that it sent us gziped content with a gzip
       // content encoding.  Sadly, Apache mistakenly sets these headers for all
       // .gz files.  We match Firefox's nsHttpChannel::ProcessNormal and ignore
       // the Content-Encoding here.
       encoding_types->clear();
 
-    GURL url;
+    DCHECK(success);
     std::string disposition;
-    success = filter_context.GetURL(&url);
-    DCHECK(success);
     filter_context.GetContentDisposition(&disposition);
     // Don't supply a MIME type here, since that may cause disk IO.
     base::FilePath::StringType extension =
         GenerateFileExtensionUnsafe(url, disposition, "UTF-8", "", "", "");
 
     if (filter_context.IsDownload()) {
       // We don't want to decompress gzipped files when the user explicitly
       // asks to download them.
       // For the case of svgz files, we use the extension to distinguish
       // between svgz files and svg files compressed with gzip by the server.
       // When viewing a .svgz file, we need to uncompress it, but we don't
       // want to do that when downloading.
       // See Firefox's nonDecodableExtensions in nsExternalHelperAppService.cpp
       if (EndsWith(extension, FILE_PATH_LITERAL(".gz"), false) ||
           LowerCaseEqualsASCII(extension, ".tgz") ||
           LowerCaseEqualsASCII(extension, ".svgz"))
         encoding_types->clear();
     } else {
       // When the user does not explicitly ask to download a file, if we get a
       // supported mime type, then we attempt to decompress in order to view it.
       // However, if it's not a supported mime type, then we will attempt to
       // download it, and in that case, don't decompress .gz/.tgz files.
       if ((EndsWith(extension, FILE_PATH_LITERAL(".gz"), false) ||
            LowerCaseEqualsASCII(extension, ".tgz")) &&
           !IsSupportedMimeType(mime_type))
         encoding_types->clear();
     }
   }
 
+  SdchManager* sdch_manager =
+      filter_context.GetURLRequestContext()->sdch_manager();
+
   // If the request was for SDCH content, then we might need additional fixups.
   if (!filter_context.IsSdchResponse()) {
     // It was not an SDCH request, so we'll just record stats.
     if (1 < encoding_types->size()) {
       // Multiple filters were intended to only be used for SDCH (thus far!)
-      SdchManager::SdchErrorRecovery(
-          SdchManager::MULTIENCODING_FOR_NON_SDCH_REQUEST);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::MULTIENCODING_FOR_NON_SDCH_REQUEST, url);
     }
     if ((1 == encoding_types->size()) &&
         (FILTER_TYPE_SDCH == encoding_types->front())) {
-        SdchManager::SdchErrorRecovery(
-            SdchManager::SDCH_CONTENT_ENCODE_FOR_NON_SDCH_REQUEST);
+        sdch_manager->SdchErrorRecovery(
+            SdchManager::SDCH_CONTENT_ENCODE_FOR_NON_SDCH_REQUEST, url);
     }
     return;
   }
 
   // The request was tagged as an SDCH request, which means the server supplied
   // a dictionary, and we advertised it in the request.  Some proxies will do
   // very strange things to the request, or the response, so we have to handle
   // them gracefully.
 
   // If content encoding included SDCH, then everything is "relatively" fine.
   if (!encoding_types->empty() &&
       (FILTER_TYPE_SDCH == encoding_types->front())) {
     // Some proxies (found currently in Argentina) strip the Content-Encoding
     // text from "sdch,gzip" to a mere "sdch" without modifying the compressed
     // payload.   To handle this gracefully, we simulate the "probably" deleted
     // ",gzip" by appending a tentative gzip decode, which will default to a
     // no-op pass through filter if it doesn't get gzip headers where expected.
     if (1 == encoding_types->size()) {
       encoding_types->push_back(FILTER_TYPE_GZIP_HELPING_SDCH);
-      SdchManager::SdchErrorRecovery(
-          SdchManager::OPTIONAL_GUNZIP_ENCODING_ADDED);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::OPTIONAL_GUNZIP_ENCODING_ADDED, url);
     }
     return;
   }
 
   // There are now several cases to handle for an SDCH request.  Foremost, if
   // the outbound request was stripped so as not to advertise support for
   // encodings, we might get back content with no encoding, or (for example)
   // just gzip.  We have to be sure that any changes we make allow for such
   // minimal coding to work.  That issue is why we use TENTATIVE filters if we
   // add any, as those filters sniff the content, and act as pass-through
@@ skipping 13 matching lines @@
   // The one unresolved failure mode comes when we advertise a dictionary, and
   // the server tries to *send* a gzipped file (not gzip encode content), and
   // then we could do a gzip decode :-(. Since SDCH is only (currently)
   // supported server side on paths that only send HTML content, this mode has
   // never surfaced in the wild (and is unlikely to).
   // We will gather a lot of stats as we perform the fixups
   if (StartsWithASCII(mime_type, kTextHtml, false)) {
     // Suspicious case: Advertised dictionary, but server didn't use sdch, and
     // we're HTML tagged.
     if (encoding_types->empty()) {
-      SdchManager::SdchErrorRecovery(
-          SdchManager::ADDED_CONTENT_ENCODING);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::ADDED_CONTENT_ENCODING, url);
     } else if (1 == encoding_types->size()) {
-      SdchManager::SdchErrorRecovery(
-          SdchManager::FIXED_CONTENT_ENCODING);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::FIXED_CONTENT_ENCODING, url);
     } else {
-      SdchManager::SdchErrorRecovery(
-          SdchManager::FIXED_CONTENT_ENCODINGS);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::FIXED_CONTENT_ENCODINGS, url);
     }
   } else {
     // Remarkable case!?!  We advertised an SDCH dictionary, content-encoding
     // was not marked for SDCH processing: Why did the server suggest an SDCH
     // dictionary in the first place??.  Also, the content isn't
     // tagged as HTML, despite the fact that SDCH encoding is mostly likely for
     // HTML: Did some anti-virus system strip this tag (sometimes they strip
     // accept-encoding headers on the request)??  Does the content encoding not
     // start with "text/html" for some other reason??  We'll report this as a
     // fixup to a binary file, but it probably really is text/html (some how).
     if (encoding_types->empty()) {
-      SdchManager::SdchErrorRecovery(
-          SdchManager::BINARY_ADDED_CONTENT_ENCODING);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::BINARY_ADDED_CONTENT_ENCODING, url);
     } else if (1 == encoding_types->size()) {
-      SdchManager::SdchErrorRecovery(
-          SdchManager::BINARY_FIXED_CONTENT_ENCODING);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::BINARY_FIXED_CONTENT_ENCODING, url);
     } else {
-      SdchManager::SdchErrorRecovery(
-          SdchManager::BINARY_FIXED_CONTENT_ENCODINGS);
+      sdch_manager->SdchErrorRecovery(
+          SdchManager::BINARY_FIXED_CONTENT_ENCODINGS, url);
     }
   }
 
   // Leave the existing encoding type to be processed first, and add our
   // tentative decodings to be done afterwards.  Vodaphone UK reportedyl will
   // perform a second layer of gzip encoding atop the server's sdch,gzip
   // encoding, and then claim that the content encoding is a mere gzip.  As a
   // result we'll need (in that case) to do the gunzip, plus our tentative
   // gunzip and tentative SDCH decoding.
   // This approach nicely handles the empty() list as well, and should work with
@@ skipping 89 matching lines @@
 
 void Filter::PushDataIntoNextFilter() {
   IOBuffer* next_buffer = next_filter_->stream_buffer();
   int next_size = next_filter_->stream_buffer_size();
   last_status_ = ReadFilteredData(next_buffer->data(), &next_size);
   if (FILTER_ERROR != last_status_)
     next_filter_->FlushStreamBuffer(next_size);
 }
 
 }  // namespace net