alternative ws header parser

net/websockets/websocket_frame_parser.cc

+// Copyright (c) 2012 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/websockets/websocket_frame_parser.h"
+
+#include <algorithm>
+#include "base/basictypes.h"
+#include "base/logging.h"
+#include "base/memory/scoped_ptr.h"
+#include "base/memory/scoped_vector.h"
+#include "base/memory/ref_counted.h"
+#include "net/base/big_endian.h"
+#include "net/websockets/websocket_frame.h"
+
+const uint8 kFinalBit = 0x80;
+const uint8 kReserved1Bit = 0x40;
+const uint8 kReserved2Bit = 0x20;
+const uint8 kReserved3Bit = 0x10;
+const uint8 kOpCodeMask = 0xF;
+const uint8 kMaskBit = 0x80;
+const uint8 kPayloadLengthMask = 0x7F;
+const uint64 kMaxPayloadLengthWithoutExtendedLengthField = 125;
+const uint64 kPayloadLengthWithTwoByteExtendedLengthField = 126;
+const uint64 kPayloadLengthWithEightByteExtendedLengthField = 127;
+
+namespace net {
+
+WebSocketFrameParser::WebSocketFrameParser()
+    : current_read_pos_(0),
+      frame_offset_(0),
+      failed_(false) {
+  std::fill(masking_key_,
+            masking_key_ + WebSocketFrameHeader::kMaskingKeyLength,
+            '\0');
+}
+
+WebSocketFrameParser::~WebSocketFrameParser() {
+}
+
+bool WebSocketFrameParser::Decode(
+    const char* data,
+    size_t length,
+    ScopedVector<WebSocketPartialFrame>* frames) {
+  if (failed_)
+    return false;
+  if (!length)
+    return true;
+
+  // TODO(yutak): Remove copy.
+  buffer_.insert(buffer_.end(), data, data + length);
+
+  while (current_read_pos_ < buffer_.size()) {
+    if (!current_frame_header_.get()) {
+      DecodeFrameHeader();
+      if (failed_)
+        return false;
+      // If frame header is incomplete, then carry over the remaining
+      // data to the next round of Decode().
+      if (!current_frame_header_.get())
+        break;
+    }
+
+    scoped_ptr<WebSocketPartialFrame> frame = DecodeFramePayload();
+    DCHECK(frame.get());
+    frames->push_back(frame.release());
+
+    if (current_frame_header_.get()) {
+      DCHECK(current_read_pos_ == buffer_.size());
+      break;
+    }
+  }
+
+  // Drain unnecessary data. TODO(yutak): Remove copy. (but how?)
+  buffer_.erase(buffer_.begin(), buffer_.begin() + current_read_pos_);
+  current_read_pos_ = 0;
+
+  // Sanity check: the size of carried-over data should not exceed
+  // the maximum possible length of a frame header.
+  static const size_t kMaximumFrameHeaderSize =
+      WebSocketFrameHeader::kBaseHeaderSize +
+      WebSocketFrameHeader::kMaximumExtendedLengthSize +
+      WebSocketFrameHeader::kMaskingKeyLength;
+  DCHECK_LT(buffer_.size(), kMaximumFrameHeaderSize);
+
+  return true;
+}
+
+void WebSocketFrameParser::DecodeFrameHeader() {
+  typedef WebSocketFrameHeader::OpCode OpCode;
+  static const int kMaskingKeyLength = WebSocketFrameHeader::kMaskingKeyLength;
+
+  DCHECK(!current_frame_header_.get());
+  DCHECK(current_read_pos_ == 0);
+  if (buffer_.size() < 2)
+    return;
+
+  // Pointer handling introduces requirement for developers to manage a kind of
+  // dynamic state.
+  uint8 first_byte = buffer_[0];
+  bool final = (first_byte & kFinalBit) != 0;
+  bool reserved1 = (first_byte & kReserved1Bit) != 0;
+  bool reserved2 = (first_byte & kReserved2Bit) != 0;
+  bool reserved3 = (first_byte & kReserved3Bit) != 0;
+  OpCode opcode = first_byte & kOpCodeMask;
+
+  uint8 second_byte = buffer_[1];
+  bool masked = (second_byte & kMaskBit) != 0;
+  uint64 payload_length = second_byte & kPayloadLengthMask;
+  bool valid_length_format = true;
+  int masking_offset = 2;
+  int masking_size = masked ? 4 : 0;
+  if (payload_length == kPayloadLengthWithTwoByteExtendedLengthField) {
+    // You may want to constant variable for following 4 and 10.
+    if (buffer_.size() < (masking_size + 4))
+      return;
+    uint16 payload_length_16;
+    ReadBigEndian(&buffer_[2], &payload_length_16);
+    if (payload_length <= kMaxPayloadLengthWithoutExtendedLengthField)
+      valid_length_format = false;
+  } else if (payload_length == kPayloadLengthWithEightByteExtendedLengthField) {
+    if (buffer_.size() < (masking_size + 10))
+      return;
+    // ditto.
+  }
+  if (!valid_length_format) {
+    failed_ = true;
+    buffer_.clear();
+    current_read_pos_ = 0;
+    current_frame_header_ = NULL;
+    frame_offset_ = 0;
+    return;
+  }
+
+  // ...
+}
+
+scoped_ptr<WebSocketPartialFrame> WebSocketFrameParser::DecodeFramePayload() {
+  static const int kMaskingKeyLength = WebSocketFrameHeader::kMaskingKeyLength;
+
+  const char* current = &buffer_.front() + current_read_pos_;
+  const char* end = &buffer_.front() + buffer_.size();
+  uint64 next_size = std::min<uint64>(
+      end - current,
+      current_frame_header_->payload_length - frame_offset_);
+
+  scoped_ptr<WebSocketPartialFrame> frame(new WebSocketPartialFrame);
+  frame->header = current_frame_header_;
+  frame->final_part = false;
+  frame->data.assign(current, current + next_size);
+  if (current_frame_header_->masked) {
+    // Unmask the payload.
+    // TODO(yutak): This could be faster by doing unmasking for each
+    // machine word (instead of each byte).
+    size_t key_offset = frame_offset_ % kMaskingKeyLength;
+    for (uint64 i = 0; i < next_size; ++i) {
+      frame->data[i] ^= masking_key_[key_offset];
+      key_offset = (key_offset + 1) % kMaskingKeyLength;
+    }
+  }
+
+  current_read_pos_ += next_size;
+  frame_offset_ += next_size;
+
+  DCHECK_LE(frame_offset_, current_frame_header_->payload_length);
+  if (frame_offset_ == current_frame_header_->payload_length) {
+    frame->final_part = true;
+    current_frame_header_ = NULL;
+    frame_offset_ = 0;
+    std::fill(masking_key_, masking_key_ + kMaskingKeyLength, '\0');
+  }
+
+  return frame.Pass();
+}
+
+}  // namespace net