Use MIDIMessageQueue/IsValidWebMIDIData for MIDI byte stream validation

WebMIDI spec draft: http://www.w3.org/TR/webmidi/ 

WebMIDI API guarantees that MIDIInput::onmessage is called back with a single MIDI message. To guarantee this, this CL introduces MIDIMessageQueue class, which allows you to
- maintain fragmented MIDI message.
- Skip any invalid data sequence.
- Reorder MIDI messages so that "System Real Time Message", which can be inserted at any point of the byte stream, can be placed at the boundary of complete MIDI messages.
- (Optional) Reconstruct complete MIDI messages from data stream that is compressed with "running status".

This CL also replaces existing System Exclusive message validation logic in MIDIHost::OnSendData with MIDIHost::IsValidWebMIDIData, which can detect SysEx message even when it is concatenated with non-SysEx messages.

With this change, renderer/blink can be much simpler and free from this kind of data validation.

BUG=303599, 317355
TEST=media_unittests --gtest_filter=MIDI*, content_unittests --gtest_filter=MIDI*

Review URL: https://codereview.chromium.org/68353002

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@237558 0039d316-1c4b-4281-b951-d872f2087c98

6 files changed, 457 insertions, 0 deletions

diff --git a/media/midi/midi_message_queue.cc b/media/midi/midi_message_queue.cc
new file mode 100644
index 0000000..3452e80
--- /dev/null
+++ b/media/midi/midi_message_queue.cc
@@ -0,0 +1,119 @@
+// 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/midi/midi_message_queue.h"
+
+#include <algorithm>
+
+#include "base/logging.h"
+#include "media/midi/midi_message_util.h"
+
+namespace media {
+namespace {
+
+const uint8 kSysEx = 0xf0;
+const uint8 kEndOfSysEx = 0xf7;
+
+bool IsDataByte(uint8 data) {
+  return (data & 0x80) == 0;
+}
+
+bool IsFirstStatusByte(uint8 data) {
+  return !IsDataByte(data) && data != kEndOfSysEx;
+}
+
+bool IsSystemRealTimeMessage(uint8 data) {
+  return 0xf8 <= data && data <= 0xff;
+}
+
+}  // namespace
+
+MIDIMessageQueue::MIDIMessageQueue(bool allow_running_status)
+    : allow_running_status_(allow_running_status) {}
+
+MIDIMessageQueue::~MIDIMessageQueue() {}
+
+void MIDIMessageQueue::Add(const std::vector<uint8>& data) {
+  queue_.insert(queue_.end(), data.begin(), data.end());
+}
+
+void MIDIMessageQueue::Add(const uint8* data, size_t length) {
+  queue_.insert(queue_.end(), data, data + length);
+}
+
+void MIDIMessageQueue::Get(std::vector<uint8>* message) {
+  message->clear();
+
+  while (true) {
+    if (queue_.empty())
+      return;
+
+    const uint8 next = queue_.front();
+    queue_.pop_front();
+
+    // "System Real Time Messages" is a special kind of MIDI messages, which can
+    // appear at arbitrary byte position of MIDI stream. Here we reorder
+    // "System Real Time Messages" prior to |next_message_| so that each message
+    // can be clearly separated as a complete MIDI message.
+    if (IsSystemRealTimeMessage(next)) {
+      message->push_back(next);
+      return;
+    }
+
+    // Here |next_message_[0]| may contain the previous status byte when
+    // |allow_running_status_| is true. Following condition fixes up
+    // |next_message_| if running status condition is not fulfilled.
+    if (!next_message_.empty() &&
+        ((next_message_[0] == kSysEx && IsFirstStatusByte(next)) ||
+         (next_message_[0] != kSysEx && !IsDataByte(next)))) {
+      // An invalid data sequence is found or running status condition is not
+      // fulfilled.
+      next_message_.clear();
+    }
+
+    if (next_message_.empty()) {
+      if (IsFirstStatusByte(next)) {
+        next_message_.push_back(next);
+      } else {
+        // MIDI protocol doesn't provide any error correction mechanism in
+        // physical layers, and incoming messages can be corrupted, and should
+        // be corrected here.
+      }
+      continue;
+    }
+
+    // Here we can assume |next_message_| starts with a valid status byte.
+    const uint8 status_byte = next_message_[0];
+    next_message_.push_back(next);
+
+    if (status_byte == kSysEx) {
+      if (next == kEndOfSysEx) {
+        std::swap(*message, next_message_);
+        next_message_.clear();
+        return;
+      }
+      continue;
+    }
+
+    DCHECK(IsDataByte(next));
+    DCHECK_NE(kSysEx, status_byte);
+    const size_t target_len = GetMIDIMessageLength(status_byte);
+    if (next_message_.size() < target_len)
+      continue;
+    if (next_message_.size() == target_len) {
+      std::swap(*message, next_message_);
+      next_message_.clear();
+      if (allow_running_status_) {
+        // Speculatively keep the status byte in case of running status. If this
+        // assumption is not true, |next_message_| will be cleared anyway.
+        next_message_.push_back(status_byte);
+      }
+      return;
+    }
+
+    NOTREACHED();
+  }
+}
+
+}  // namespace media
diff --git a/media/midi/midi_message_queue.h b/media/midi/midi_message_queue.h
new file mode 100644
index 0000000..06f0f47
--- /dev/null
+++ b/media/midi/midi_message_queue.h
@@ -0,0 +1,72 @@
+// 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.
+
+#ifndef MEDIA_MIDI_MIDI_MESSAGE_QUEUE_H_
+#define MEDIA_MIDI_MIDI_MESSAGE_QUEUE_H_
+
+#include <deque>
+#include <vector>
+
+#include "base/basictypes.h"
+#include "media/base/media_export.h"
+
+namespace media {
+
+// A simple message splitter for possibly unsafe/corrupted MIDI data stream.
+// This class allows you to:
+// - maintain fragmented MIDI message.
+// - skip any invalid data sequence.
+// - reorder MIDI messages so that "System Real Time Message", which can be
+//   inserted at any point of the byte stream, is placed at the boundary of
+//   complete MIDI messages.
+// - (Optional) reconstruct complete MIDI messages from data stream where
+//   MIDI status byte is abbreviated (a.k.a. "running status").
+//
+// Example (pseudo message loop):
+//   MIDIMessageQueue queue(true);  // true to support "running status"
+//   while (true) {
+//     if (is_incoming_midi_data_available()) {
+//       std::vector<uint8> incoming_data;
+//       read_incoming_midi_data(&incoming_data)
+//       queue.Add(incoming_data);
+//     }
+//     while (true) {
+//       std::vector<uint8> next_message;
+//       queue.Get(&next_message);
+//       if (!next_message.empty())
+//         dispatch(next_message);
+//     }
+//   }
+class MEDIA_EXPORT MIDIMessageQueue {
+ public:
+  // Initializes the queue. Set true to |allow_running_status| to enable
+  // "MIDI running status" reconstruction.
+  explicit MIDIMessageQueue(bool allow_running_status);
+  ~MIDIMessageQueue();
+
+  // Enqueues |data| to the internal buffer.
+  void Add(const std::vector<uint8>& data);
+  void Add(const uint8* data, size_t length);
+
+  // Fills the next complete MIDI message into |message|. If |message| is
+  // not empty, the data sequence falls into one of the following types of
+  // MIDI message.
+  // - Single "Channel Voice Message"    (w/o "System Real Time Messages")
+  // - Single "Channel Mode Message"     (w/o "System Real Time Messages")
+  // - Single "System Exclusive Message" (w/o "System Real Time Messages")
+  // - Single "System Common Message"    (w/o "System Real Time Messages")
+  // - Single "System Real Time message"
+  // |message| is empty if there is no complete MIDI message any more.
+  void Get(std::vector<uint8>* message);
+
+ private:
+  std::deque<uint8> queue_;
+  std::vector<uint8> next_message_;
+  const bool allow_running_status_;
+  DISALLOW_COPY_AND_ASSIGN(MIDIMessageQueue);
+};
+
+}  // namespace media
+
+#endif  // MEDIA_MIDI_MIDI_MESSAGE_QUEUE_H_
diff --git a/media/midi/midi_message_queue_unittest.cc b/media/midi/midi_message_queue_unittest.cc
new file mode 100644
index 0000000..a00eea6
--- /dev/null
+++ b/media/midi/midi_message_queue_unittest.cc
@@ -0,0 +1,173 @@
+// 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/midi/midi_message_queue.h"
+
+#include "testing/gtest/include/gtest/gtest.h"
+
+namespace media {
+namespace {
+
+const uint8 kGMOn[] = { 0xf0, 0x7e, 0x7f, 0x09, 0x01, 0xf7 };
+const uint8 kGSOn[] = {
+  0xf0, 0x41, 0x10, 0x42, 0x12, 0x40, 0x00, 0x7f, 0x00, 0x41, 0xf7,
+};
+const uint8 kNoteOn[] = { 0x90, 0x3c, 0x7f };
+const uint8 kNoteOnWithRunningStatus[] = {
+  0x90, 0x3c, 0x7f, 0x3c, 0x7f, 0x3c, 0x7f,
+};
+const uint8 kChannelPressure[] = { 0xd0, 0x01 };
+const uint8 kChannelPressureWithRunningStatus[] = {
+  0xd0, 0x01, 0x01, 0x01,
+};
+const uint8 kTimingClock[] = { 0xf8 };
+const uint8 kBrokenData1[] = { 0x90 };
+const uint8 kBrokenData2[] = { 0xf7 };
+const uint8 kBrokenData3[] = { 0xf2, 0x00 };
+const uint8 kDataByte0[] = { 0x00 };
+
+template <typename T, size_t N>
+void Add(MIDIMessageQueue* queue, const T(&array)[N]) {
+  queue->Add(array, N);
+}
+
+template <typename T, size_t N>
+::testing::AssertionResult ExpectEqualSequence(
+    const char* expr1, const char* expr2,
+    const T(&expected)[N], const std::vector<T>& actual) {
+  if (actual.size() != N) {
+    return ::testing::AssertionFailure()
+        << "expected: " << ::testing::PrintToString(expected)
+        << ", actual: " << ::testing::PrintToString(actual);
+  }
+  for (size_t i = 0; i < N; ++i) {
+    if (expected[i] != actual[i]) {
+      return ::testing::AssertionFailure()
+          << "expected: " << ::testing::PrintToString(expected)
+          << ", actual: " << ::testing::PrintToString(actual);
+    }
+  }
+  return ::testing::AssertionSuccess();
+}
+
+#define EXPECT_MESSAGE(expected, actual)  \
+  EXPECT_PRED_FORMAT2(ExpectEqualSequence, expected, actual)
+
+TEST(MIDIMessageQueueTest, EmptyData) {
+  MIDIMessageQueue queue(false);
+  std::vector<uint8> message;
+  queue.Get(&message);
+  EXPECT_TRUE(message.empty());
+}
+
+TEST(MIDIMessageQueueTest, RunningStatusDisabled) {
+  MIDIMessageQueue queue(false);
+  Add(&queue, kGMOn);
+  Add(&queue, kBrokenData1);
+  Add(&queue, kNoteOnWithRunningStatus);
+  Add(&queue, kBrokenData2);
+  Add(&queue, kChannelPressureWithRunningStatus);
+  Add(&queue, kBrokenData3);
+  Add(&queue, kNoteOn);
+  Add(&queue, kBrokenData1);
+  Add(&queue, kGSOn);
+  Add(&queue, kBrokenData2);
+  Add(&queue, kTimingClock);
+  Add(&queue, kBrokenData3);
+
+  std::vector<uint8> message;
+  queue.Get(&message);
+  EXPECT_MESSAGE(kGMOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message) << "Running status should be ignored";
+  queue.Get(&message);
+  EXPECT_MESSAGE(kChannelPressure, message)
+      << "Running status should be ignored";
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kGSOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_TRUE(message.empty());
+}
+
+TEST(MIDIMessageQueueTest, RunningStatusEnabled) {
+  MIDIMessageQueue queue(true);
+  Add(&queue, kGMOn);
+  Add(&queue, kBrokenData1);
+  Add(&queue, kNoteOnWithRunningStatus);
+  Add(&queue, kBrokenData2);
+  Add(&queue, kChannelPressureWithRunningStatus);
+  Add(&queue, kBrokenData3);
+  Add(&queue, kNoteOn);
+  Add(&queue, kBrokenData1);
+  Add(&queue, kGSOn);
+  Add(&queue, kBrokenData2);
+  Add(&queue, kTimingClock);
+  Add(&queue, kDataByte0);
+
+  std::vector<uint8> message;
+  queue.Get(&message);
+  EXPECT_MESSAGE(kGMOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message)
+      << "Running status should be converted into a canonical MIDI message";
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message)
+      << "Running status should be converted into a canonical MIDI message";
+  queue.Get(&message);
+  EXPECT_MESSAGE(kChannelPressure, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kChannelPressure, message)
+      << "Running status should be converted into a canonical MIDI message";
+  queue.Get(&message);
+  EXPECT_MESSAGE(kChannelPressure, message)
+      << "Running status should be converted into a canonical MIDI message";
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kGSOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_TRUE(message.empty())
+      << "Running status must not be applied to real time messages";
+}
+
+TEST(MIDIMessageQueueTest, RunningStatusEnabledWithRealTimeEvent) {
+  MIDIMessageQueue queue(true);
+  const uint8 kNoteOnWithRunningStatusWithkTimingClock[] = {
+    0x90, 0xf8, 0x3c, 0xf8, 0x7f, 0xf8, 0x3c, 0xf8, 0x7f, 0xf8, 0x3c, 0xf8,
+    0x7f,
+  };
+  Add(&queue, kNoteOnWithRunningStatusWithkTimingClock);
+  std::vector<uint8> message;
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kTimingClock, message);
+  queue.Get(&message);
+  EXPECT_MESSAGE(kNoteOn, message);
+  queue.Get(&message);
+  EXPECT_TRUE(message.empty());
+}
+
+}  // namespace
+}  // namespace media
diff --git a/media/midi/midi_message_util.cc b/media/midi/midi_message_util.cc
new file mode 100644
index 0000000..83d3cc0
--- /dev/null
+++ b/media/midi/midi_message_util.cc
@@ -0,0 +1,34 @@
+// 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/midi/midi_message_util.h"
+
+namespace media {
+
+size_t GetMIDIMessageLength(uint8 status_byte) {
+  if (status_byte < 0x80)
+    return 0;
+  if (0x80 <= status_byte && status_byte <= 0xbf)
+    return 3;
+  if (0xc0 <= status_byte && status_byte <= 0xdf)
+    return 2;
+  if (0xe0 <= status_byte && status_byte <= 0xef)
+    return 3;
+  if (status_byte == 0xf0)
+    return 0;
+  if (status_byte == 0xf1)
+    return 2;
+  if (status_byte == 0xf2)
+    return 3;
+  if (status_byte == 0xf3)
+    return 2;
+  if (0xf4 <= status_byte && status_byte <= 0xf6)
+    return 1;
+  if (status_byte == 0xf7)
+    return 0;
+  // 0xf8 <= status_byte && status_byte <= 0xff
+  return 1;
+}
+
+}  // namespace media
diff --git a/media/midi/midi_message_util.h b/media/midi/midi_message_util.h
new file mode 100644
index 0000000..1dc6d3c
--- /dev/null
+++ b/media/midi/midi_message_util.h
@@ -0,0 +1,25 @@
+// 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.
+
+#ifndef MEDIA_MIDI_MIDI_MESSAGE_UTIL_H_
+#define MEDIA_MIDI_MIDI_MESSAGE_UTIL_H_
+
+#include <deque>
+#include <vector>
+
+#include "base/basictypes.h"
+#include "media/base/media_export.h"
+
+namespace media {
+
+// Returns the length of a MIDI message in bytes. Never returns 4 or greater.
+// Returns 0 if |status_byte| is:
+// - not a valid status byte, namely data byte.
+// - the MIDI System Exclusive message.
+// - the End of System Exclusive message.
+MEDIA_EXPORT size_t GetMIDIMessageLength(uint8 status_byte);
+
+}  // namespace media
+
+#endif  // MEDIA_MIDI_MIDI_MESSAGE_UTIL_H_
diff --git a/media/midi/midi_message_util_unittest.cc b/media/midi/midi_message_util_unittest.cc
new file mode 100644
index 0000000..af3679c
--- /dev/null
+++ b/media/midi/midi_message_util_unittest.cc
@@ -0,0 +1,34 @@
+// 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/midi/midi_message_util.h"
+
+#include "testing/gtest/include/gtest/gtest.h"
+
+namespace media {
+namespace {
+
+const uint8 kGMOn[] = { 0xf0, 0x7e, 0x7f, 0x09, 0x01, 0xf7 };
+const uint8 kNoteOn[] = { 0x90, 0x3c, 0x7f };
+const uint8 kChannelPressure[] = { 0xd0, 0x01 };
+const uint8 kTimingClock[] = { 0xf8 };
+
+TEST(GetMIDIMessageLengthTest, BasicTest) {
+  // Check basic functionarity
+  EXPECT_EQ(arraysize(kNoteOn), GetMIDIMessageLength(kNoteOn[0]));
+  EXPECT_EQ(arraysize(kChannelPressure),
+            GetMIDIMessageLength(kChannelPressure[0]));
+  EXPECT_EQ(arraysize(kTimingClock), GetMIDIMessageLength(kTimingClock[0]));
+
+  // SysEx message should be mapped to 0-length
+  EXPECT_EQ(0u, GetMIDIMessageLength(kGMOn[0]));
+
+  // Any data byte should be mapped to 0-length
+  EXPECT_EQ(0u, GetMIDIMessageLength(kGMOn[1]));
+  EXPECT_EQ(0u, GetMIDIMessageLength(kNoteOn[1]));
+  EXPECT_EQ(0u, GetMIDIMessageLength(kChannelPressure[1]));
+}
+
+}  // namespace
+}  // namespace media