Add media file validation to utility process

media/base/media_file_checker.cc

Index: media/base/media_file_checker.cc
diff --git a/media/base/media_file_checker.cc b/media/base/media_file_checker.cc
new file mode 100644
index 0000000000000000000000000000000000000000..10968c7720e333e0273f275beca86562608d01f8
--- /dev/null
+++ b/media/base/media_file_checker.cc
@@ -0,0 +1,131 @@
+// Copyright 2013 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 "media/base/media_file_checker.h"
+
+#include <map>
+
+#include "base/bind.h"
+#include "base/stl_util.h"
+#include "base/time/time.h"
+#include "media/ffmpeg/ffmpeg_common.h"
+#include "media/filters/blocking_url_protocol.h"
+#include "media/filters/ffmpeg_glue.h"
+#include "media/filters/file_data_source.h"
+
+namespace media {
+
+namespace {
+
+const int64 kMaxCheckTimeIneconds = 5;

[DaleCurtis, 2013/08/08 21:04:33]

InSeconds

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

+
+void OnError(bool* called) {
+  *called = false;
+}
+
+struct StreamContext {
+  StreamContext()
+      : codec_context(NULL),
+        codec(NULL) {
+  }
+  AVCodecContext* codec_context;
+  AVCodec* codec;
+};
+
+}  // namespace
+
+
+MediaFileChecker::MediaFileChecker(base::PlatformFile file)
+    : file_(file),
+      file_closer_(&file_) {
+}
+
+MediaFileChecker::~MediaFileChecker() {
+}
+
+bool MediaFileChecker::Start(const base::TimeDelta& check_time) {
+  media::FileDataSource source;
+  bool read_ok = true;
+  media::BlockingUrlProtocol protocol(&source, base::Bind(&OnError, &read_ok));
+  media::FFmpegGlue glue(&protocol);
+  source.InitializeFromPlatformFile(file_);
+  AVFormatContext* format_context = glue.format_context();
+
+  if (!glue.OpenContext())
+    return false;
+
+  if (avformat_find_stream_info(format_context, NULL) < 0)
+    return false;
+
+  // Remember the codec for any decodable audio or video streams.
+  std::map<int, StreamContext> stream_contexts;
+  for (size_t i = 0; i < format_context->nb_streams; ++i) {
+    AVCodecContext* c = format_context->streams[i]->codec;
+    if (c->codec_type == AVMEDIA_TYPE_AUDIO ||
+        c->codec_type == AVMEDIA_TYPE_VIDEO) {
+      AVCodec* codec = avcodec_find_decoder(c->codec_id);
+      if (codec && avcodec_open2(c, codec, NULL) >= 0) {
+        stream_contexts[i].codec_context = c;
+        stream_contexts[i].codec = codec;

[DaleCurtis, 2013/08/08 21:04:33]

Doesn't look like you actually use codec anywhere.  Just make the map <int,
AVCodecContext*> ?  You can get rid of StreamContext then.

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

+      }
+    }
+  }
+
+  if (stream_contexts.size() == 0)
+    return false;
+
+  AVPacket packet;
+  scoped_ptr_malloc<AVFrame, media::ScopedPtrAVFree> frame(
+      avcodec_alloc_frame());
+  int result = 0;
+
+  base::Time deadline;

[DaleCurtis, 2013/08/08 21:04:33]

const base::Time deadline = base::Time::Now() + base::TimeDelta::FromSeconds(
    std::max(0, std::min(kMaxCheckTimeInSeconds, check_time)));

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Used std::min (negative check time will have the same result as 0).

+  const base::TimeDelta max_check_time =
+      base::TimeDelta::FromSeconds(kMaxCheckTimeIneconds);
+  if (check_time > max_check_time)
+    deadline = base::Time::Now() + max_check_time;
+  else
+    deadline = base::Time::Now() + check_time;
+
+  do {
+    result = av_read_frame(glue.format_context(), &packet);
+    if (result < 0)
+      break;
+

[DaleCurtis, 2013/08/08 21:04:33]

I think you need an av_dup_packet(&packet) here otherwise the data referred to
by the packet will get corrupted on the next call to decode.

Once you have that you'll also need an av_free_packet() for any packets you skip
decoding of.  See 143-147 here:

https://code.google.com/p/chromium/codesearch#chromium/src/media/filters/audi...

It's possible this isn't necessary anymore, but we do this everywhere else we
process packets.  The original text with this code can be seen on line 680 here:

https://codereview.chromium.org/10447035/diff/14016/media/filters/ffmpeg_demu...

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

+    if (!ContainsKey(stream_contexts, packet.stream_index))

[DaleCurtis, 2013/08/08 21:04:33]

You end up doing multiple map look ups below.  Instead just do it once and save
off the AVCodecContext pointer.

std::map<int, StreamContext>::const_iterator it = stream_contexts.find(...);
if (it == stream_contexts.end())
  continue;
AVCodecContext* av_context = it->second;

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

+      continue;
+
+    int frame_decoded = 0;
+    AVMediaType type =
+        stream_contexts[packet.stream_index].codec_context->codec_type;
+    if (type == AVMEDIA_TYPE_AUDIO) {
+      // A shallow copy of packet so we can slide packet.data as frames are
+      // decoded; otherwise av_free_packet() will corrupt memory.
+      AVPacket temp_packet = packet;
+      do {
+        avcodec_get_frame_defaults(frame.get());
+        result = avcodec_decode_audio4(
+            stream_contexts[packet.stream_index].codec_context, frame.get(),
+            &frame_decoded, &packet);

[DaleCurtis, 2013/08/08 21:04:33]

temp_packet

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

+        if (result < 0)
+          break;
+        temp_packet.size -= result;
+        temp_packet.data += result;
+      } while (temp_packet.size  > 0);

[DaleCurtis, 2013/08/08 21:04:33]

Extra space.

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

BTW - This is what made me think I didn't need the inner do-while loop. It also
doesn't do the temp_packet or av_dup_packet thing. But it only decodes one
stream, so...
https://code.google.com/p/chromium/codesearch/#chromium/src/media/test/ffmpeg...

+    } else if (type == AVMEDIA_TYPE_VIDEO) {
+      avcodec_get_frame_defaults(frame.get());
+      result = avcodec_decode_video2(
+          stream_contexts[packet.stream_index].codec_context, frame.get(),
+          &frame_decoded, &packet);
+    }
+  } while (base::Time::Now() < deadline && read_ok && result >= 0);
+
+  av_free_packet(&packet);

[DaleCurtis, 2013/08/08 21:04:33]

This needs to be inside the while loop.

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

+
+  if (result == AVERROR_EOF)

[DaleCurtis, 2013/08/08 21:04:33]

Could be rewritten as:
return read_ok && (result == AVERROR_EOF || result >= 0);

[vandebo (ex-Chrome), 2013/08/08 23:04:18]

Done.

+    result = 0;
+  return read_ok && result >= 0;
+}
+
+}  // namespace media