DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (dcc6d7a0dc00)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* 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/. */

#include "nsString.h"
#include "nsIScriptableUConv.h"
#include "nsScriptableUConv.h"
#include "nsIStringStream.h"
#include "nsComponentManagerUtils.h"
#include "nsIUnicodeDecoder.h"
#include "nsIUnicodeEncoder.h"
#include "mozilla/dom/EncodingUtils.h"

using mozilla::dom::EncodingUtils;

/* Implementation file */
NS_IMPL_ISUPPORTS(nsScriptableUnicodeConverter, nsIScriptableUnicodeConverter)

nsScriptableUnicodeConverter::nsScriptableUnicodeConverter()
: mIsInternal(false)
{
}

nsScriptableUnicodeConverter::~nsScriptableUnicodeConverter()
{
}

nsresult
nsScriptableUnicodeConverter::ConvertFromUnicodeWithLength(const nsAString& aSrc,
                                                           int32_t* aOutLen,
                                                           char **_retval)
{
  if (!mEncoder)
    return NS_ERROR_FAILURE;

  nsresult rv = NS_OK;
  int32_t inLength = aSrc.Length();
  const nsAFlatString& flatSrc = PromiseFlatString(aSrc);
  rv = mEncoder->GetMaxLength(flatSrc.get(), inLength, aOutLen);
  if (NS_SUCCEEDED(rv)) {
    *_retval = (char*)malloc(*aOutLen+1);
    if (!*_retval)
      return NS_ERROR_OUT_OF_MEMORY;

    rv = mEncoder->Convert(flatSrc.get(), &inLength, *_retval, aOutLen);
    if (NS_SUCCEEDED(rv))
    {
      (*_retval)[*aOutLen] = '\0';
      return NS_OK;
    }
    free(*_retval);
  }
  *_retval = nullptr;
  return NS_ERROR_FAILURE;
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::ConvertFromUnicode(const nsAString& aSrc,
                                                 nsACString& _retval)
{
  int32_t len;
  char* str;
  nsresult rv = ConvertFromUnicodeWithLength(aSrc, &len, &str);
  if (NS_SUCCEEDED(rv)) {
    // No Adopt on nsACString :(
    if (!_retval.Assign(str, len, mozilla::fallible)) {
      rv = NS_ERROR_OUT_OF_MEMORY;
    }
    free(str);
  }
  return rv;
}

nsresult
nsScriptableUnicodeConverter::FinishWithLength(char **_retval, int32_t* aLength)
{
  if (!mEncoder)
    return NS_ERROR_FAILURE;

  int32_t finLength = 32;

  *_retval = (char *)malloc(finLength);
  if (!*_retval)
    return NS_ERROR_OUT_OF_MEMORY;

  nsresult rv = mEncoder->Finish(*_retval, &finLength);
  if (NS_SUCCEEDED(rv))
    *aLength = finLength;
  else
    free(*_retval);

  return rv;

}

NS_IMETHODIMP
nsScriptableUnicodeConverter::Finish(nsACString& _retval)
{
  // The documentation for this method says it should be called after
  // ConvertFromUnicode(). However, our own tests called it after
  // convertFromByteArray(), i.e. when *decoding*.
  // Assuming that there exists extensions that similarly call
  // this at the wrong time, let's deal. In general, it is a design
  // error for this class to handle conversions in both directions.
  if (!mEncoder) {
    _retval.Truncate();
    return NS_OK;
  }
  int32_t len;
  char* str;
  nsresult rv = FinishWithLength(&str, &len);
  if (NS_SUCCEEDED(rv)) {
    // No Adopt on nsACString :(
    if (!_retval.Assign(str, len, mozilla::fallible)) {
      rv = NS_ERROR_OUT_OF_MEMORY;
    }
    free(str);
  }
  return rv;
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::ConvertToUnicode(const nsACString& aSrc, nsAString& _retval)
{
  nsACString::const_iterator i;
  aSrc.BeginReading(i);
  return ConvertFromByteArray(reinterpret_cast<const uint8_t*>(i.get()),
                              aSrc.Length(),
                              _retval);
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::ConvertFromByteArray(const uint8_t* aData,
                                                   uint32_t aCount,
                                                   nsAString& _retval)
{
  if (!mDecoder)
    return NS_ERROR_FAILURE;

  nsresult rv = NS_OK;
  int32_t inLength = aCount;
  int32_t outLength;
  rv = mDecoder->GetMaxLength(reinterpret_cast<const char*>(aData),
                              inLength, &outLength);
  if (NS_SUCCEEDED(rv))
  {
    char16_t* buf = (char16_t*)malloc((outLength+1) * sizeof(char16_t));
    if (!buf)
      return NS_ERROR_OUT_OF_MEMORY;

    rv = mDecoder->Convert(reinterpret_cast<const char*>(aData),
                           &inLength, buf, &outLength);
    if (NS_SUCCEEDED(rv))
    {
      buf[outLength] = 0;
      if (!_retval.Assign(buf, outLength, mozilla::fallible)) {
        rv = NS_ERROR_OUT_OF_MEMORY;
      }
    }
    free(buf);
    return rv;
  }
  return NS_ERROR_FAILURE;

}

NS_IMETHODIMP
nsScriptableUnicodeConverter::ConvertToByteArray(const nsAString& aString,
                                                 uint32_t* aLen,
                                                 uint8_t** _aData)
{
  char* data;
  int32_t len;
  nsresult rv = ConvertFromUnicodeWithLength(aString, &len, &data);
  if (NS_FAILED(rv))
    return rv;
  nsXPIDLCString str;
  str.Adopt(data, len); // NOTE: This uses the XPIDLCString as a byte array

  rv = FinishWithLength(&data, &len);
  if (NS_FAILED(rv))
    return rv;

  str.Append(data, len);
  free(data);
  // NOTE: this being a byte array, it needs no null termination
  *_aData = reinterpret_cast<uint8_t*>(malloc(str.Length()));
  if (!*_aData)
    return NS_ERROR_OUT_OF_MEMORY;
  memcpy(*_aData, str.get(), str.Length());
  *aLen = str.Length();
  return NS_OK;
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::ConvertToInputStream(const nsAString& aString,
                                                   nsIInputStream** _retval)
{
  nsresult rv;
  nsCOMPtr<nsIStringInputStream> inputStream =
    do_CreateInstance("@mozilla.org/io/string-input-stream;1", &rv);
  if (NS_FAILED(rv))
    return rv;

  uint8_t* data;
  uint32_t dataLen;
  rv = ConvertToByteArray(aString, &dataLen, &data);
  if (NS_FAILED(rv))
    return rv;

  rv = inputStream->AdoptData(reinterpret_cast<char*>(data), dataLen);
  if (NS_FAILED(rv)) {
    free(data);
    return rv;
  }

  NS_ADDREF(*_retval = inputStream);
  return rv;
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::GetCharset(char * *aCharset)
{
  *aCharset = ToNewCString(mCharset);
  if (!*aCharset)
    return NS_ERROR_OUT_OF_MEMORY;

  return NS_OK;
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::SetCharset(const char * aCharset)
{
  mCharset.Assign(aCharset);
  return InitConverter();
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::GetIsInternal(bool *aIsInternal)
{
  *aIsInternal = mIsInternal;
  return NS_OK;
}

NS_IMETHODIMP
nsScriptableUnicodeConverter::SetIsInternal(const bool aIsInternal)
{
  mIsInternal = aIsInternal;
  return NS_OK;
}

nsresult
nsScriptableUnicodeConverter::InitConverter()
{
  mEncoder = nullptr;
  mDecoder = nullptr;

  nsAutoCString encoding;
  if (mIsInternal) {
    // For compatibility with legacy extensions, let's try to see if the label
    // happens to be ASCII-case-insensitively an encoding. This should allow
    // for things like "utf-7" and "x-Mac-Hebrew".
    nsAutoCString contractId;
    nsAutoCString label(mCharset);
    EncodingUtils::TrimSpaceCharacters(label);
    // Let's try in lower case if we didn't get an decoder. E.g. x-mac-ce
    // and x-imap4-modified-utf7 are all lower case.
    ToLowerCase(label);
    if (label.EqualsLiteral("replacement")) {
      // reject "replacement"
      return NS_ERROR_UCONV_NOCONV;
    }
    contractId.AssignLiteral(NS_UNICODEENCODER_CONTRACTID_BASE);
    contractId.Append(label);
    mEncoder = do_CreateInstance(contractId.get());
    contractId.AssignLiteral(NS_UNICODEDECODER_CONTRACTID_BASE);
    contractId.Append(label);
    mDecoder = do_CreateInstance(contractId.get());
    if (!mDecoder) {
      // The old code seemed to want both a decoder and an encoder. Since some
      // internal encodings will be decoder-only in the future, let's relax
      // this. Note that the other methods check mEncoder for null anyway.
      // Let's try the upper case. E.g. UTF-7 and ISO-2022-CN have upper
      // case Gecko-canonical names.
      ToUpperCase(label);
      contractId.AssignLiteral(NS_UNICODEENCODER_CONTRACTID_BASE);
      contractId.Append(label);
      mEncoder = do_CreateInstance(contractId.get());
      contractId.AssignLiteral(NS_UNICODEDECODER_CONTRACTID_BASE);
      contractId.Append(label);
      mDecoder = do_CreateInstance(contractId.get());
      // If still no decoder, use the normal non-internal case below.
    }
  }

  if (!mDecoder) {
    if (!EncodingUtils::FindEncodingForLabelNoReplacement(mCharset, encoding)) {
      return NS_ERROR_UCONV_NOCONV;
    }
    mEncoder = EncodingUtils::EncoderForEncoding(encoding);
    mDecoder = EncodingUtils::DecoderForEncoding(encoding);
  }

  // The UTF-8 decoder used to throw regardless of the error behavior.
  // Simulating the old behavior for compatibility with legacy callers
  // (including addons). If callers want a control over the behavior,
  // they should switch to TextDecoder.
  if (encoding.EqualsLiteral("UTF-8")) {
    mDecoder->SetInputErrorBehavior(nsIUnicodeDecoder::kOnError_Signal);
  }

  if (!mEncoder) {
    return NS_OK;
  }

  return mEncoder->SetOutputErrorBehavior(nsIUnicodeEncoder::kOnError_Replace,
                                          nullptr,
                                          (char16_t)'?');
}