author Henri Sivonen <hsivonen@hsivonen.fi>
Fri, 06 Jul 2018 10:44:43 +0300
changeset 489140 4ef0f163fdeb9afeddd87b37bfd987298c038542
parent 479153 3f522a95458d15844af23f792caff4e6c11f01e8
child 500377 2da6504c901e9474566aa1663d907bd58bed9edb
permissions -rw-r--r--
Bug 1402247 - Use encoding_rs for XPCOM string encoding conversions. r=Nika,erahm,froydnj. Correctness improvements: * UTF errors are handled safely per spec instead of dangerously truncating strings. * There are fewer converter implementations. Performance improvements: * The old code did exact buffer length math, which meant doing UTF math twice on each input string (once for length calculation and another time for conversion). Exact length math is more complicated when handling errors properly, which the old code didn't do. The new code does UTF math on the string content only once (when converting) but risks allocating more than once. There are heuristics in place to lower the probability of reallocation in cases where the double math avoidance isn't enough of a saving to absorb an allocation and memcpy. * Previously, in UTF-16 <-> UTF-8 conversions, an ASCII prefix was optimized but a single non-ASCII code point pessimized the rest of the string. The new code tries to get back on the fast ASCII path. * UTF-16 to Latin1 conversion guarantees less about handling of out-of-range input to eliminate an operation from the inner loop on x86/x86_64. * When assigning to a pre-existing string, the new code tries to reuse the old buffer instead of first releasing the old buffer and then allocating a new one. * When reallocating from the new code, the memcpy covers only the data that is part of the logical length of the old string instead of memcpying the whole capacity. (For old callers old excess memcpy behavior is preserved due to bogus callers. See bug 1472113.) * UTF-8 strings in XPConnect that are in the Latin1 range are passed to SpiderMonkey as Latin1. New features: * Conversion between UTF-8 and Latin1 is added in order to enable faster future interop between Rust code (or otherwise UTF-8-using code) and text node and SpiderMonkey code that uses Latin1. MozReview-Commit-ID: JaJuExfILM9

/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* vim: set ts=8 sts=2 et sw=2 tw=80: */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#ifndef InputStreamLengthWrapper_h
#define InputStreamLengthWrapper_h

#include "mozilla/Attributes.h"
#include "mozilla/Mutex.h"
#include "nsCOMPtr.h"
#include "nsIAsyncInputStream.h"
#include "nsICloneableInputStream.h"
#include "nsIIPCSerializableInputStream.h"
#include "nsISeekableStream.h"
#include "nsIInputStreamLength.h"

namespace mozilla {

// A wrapper keeps an inputStream together with its length.
// This class can be used for nsIInputStreams that do not implement
// nsIInputStreamLength.

class InputStreamLengthWrapper final : public nsIAsyncInputStream
                                     , public nsICloneableInputStream
                                     , public nsIIPCSerializableInputStream
                                     , public nsISeekableStream
                                     , public nsIInputStreamCallback
                                     , public nsIInputStreamLength

  // This method creates a InputStreamLengthWrapper around aInputStream if
  // this doesn't implement nsIInputStreamLength or
  // nsIInputStreamAsyncLength interface, but it implements
  // nsIAsyncInputStream. For this kind of streams,
  // InputStreamLengthHelper is not able to retrieve the length. This
  // method will make such streams ready to be used with
  // InputStreamLengthHelper.
  static already_AddRefed<nsIInputStream>
  MaybeWrap(already_AddRefed<nsIInputStream> aInputStream,
            int64_t aLength);

  // The length here will be used when nsIInputStreamLength::Length() is called.
  InputStreamLengthWrapper(already_AddRefed<nsIInputStream> aInputStream,
                           int64_t aLength);

  // This CTOR is meant to be used just for IPC.


  SetSourceStream(already_AddRefed<nsIInputStream> aInputStream);

  nsCOMPtr<nsIInputStream> mInputStream;

  // Raw pointers because these are just QI of mInputStream.
  nsICloneableInputStream* mWeakCloneableInputStream;
  nsIIPCSerializableInputStream* mWeakIPCSerializableInputStream;
  nsISeekableStream* mWeakSeekableInputStream;
  nsIAsyncInputStream* mWeakAsyncInputStream;

  int64_t mLength;
  bool mConsumed;

  mozilla::Mutex mMutex;

  // This is used for AsyncWait and it's protected by mutex.
  nsCOMPtr<nsIInputStreamCallback> mAsyncWaitCallback;

} // mozilla namespace

#endif // InputStreamLengthWrapper_h