Use MIDIMessageQueue/IsValidWebMIDIData for MIDI byte stream validation

media/midi/midi_message_util.cc

Index: media/midi/midi_message_util.cc
diff --git a/media/midi/midi_message_util.cc b/media/midi/midi_message_util.cc
new file mode 100644
index 0000000000000000000000000000000000000000..9c7b05ef22bef32c75a49efe487901711f45d39b
--- /dev/null
+++ b/media/midi/midi_message_util.cc
@@ -0,0 +1,175 @@
+// Copyright (c) 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 <algorithm>
+
+#include "base/logging.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;
+}
+
+size_t GetMessageLength(uint8 data) {
+  if (IsDataByte(data))
+    return 0;
+  else if (0x80 <= data && data <= 0xbf)

[scherkus (not reviewing), 2013/11/20 20:16:00]

nit: since you return every time I'd drop all the elses

[yukawa, 2013/11/21 01:19:40]

Done.

+    return 3;
+  else if (0xc0 <= data && data <= 0xdf)
+    return 2;
+  else if (0xe0 <= data && data <= 0xef)
+    return 3;
+  else if (data == 0xf0)
+    return 0;
+  else if (data == 0xf1)
+    return 2;
+  else if (data == 0xf2)
+    return 3;
+  else if (data == 0xf3)
+    return 2;
+  else if (0xf4 <= data && data <= 0xf6)
+    return 1;
+  else if (data == 0xf7)
+    return 0;
+  else  // 0xf8 <= data && data <= 0xff
+    return 1;
+}
+
+}  // 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 = GetMessageLength(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();
+  }
+}
+
+bool IsValidWebMIDIMessage(const std::vector<uint8>& data) {
+  bool in_sysex = false;
+  size_t waiting_data_length = 0;
+  for (size_t i = 0; i < data.size(); ++i) {
+    const uint8 current = data[i];
+    if (IsSystemRealTimeMessage(current))
+      continue;  // Real time message can be placed at any point.
+    if (waiting_data_length > 0) {
+      if (!IsDataByte(current))
+        return false;  // Error: |current| should have been data byte.
+      --waiting_data_length;
+      continue;  // Found data byte as expected.
+    }
+    if (in_sysex) {
+      if (data[i] == kEndOfSysEx)
+        in_sysex = false;
+      else if (!IsDataByte(current))
+        return false;  // Error: |current| should have been data byte.
+      continue;  // Found data byte as expected.
+    }
+    if (current == kSysEx) {
+      in_sysex = true;
+      continue;  // Found SysEX
+    }
+    waiting_data_length = GetMessageLength(current);
+    if (waiting_data_length == 0)
+      return false;  // Error: |current| should have been a valid status byte.
+    --waiting_data_length;  // Found status byte
+  }
+  return waiting_data_length == 0 && !in_sysex;
+}
+
+}  // namespace media