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

Untracked file

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
/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* ***** BEGIN LICENSE BLOCK *****
 * Version: NPL 1.1/GPL 2.0/LGPL 2.1
 *
 * The contents of this file are subject to the Netscape Public License
 * Version 1.1 (the "License"); you may not use this file except in
 * compliance with the License. You may obtain a copy of the License at
 * http://www.mozilla.org/NPL/
 *
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the
 * License.
 *
 * The Original Code is mozilla.org code.
 *
 * The Initial Developer of the Original Code is 
 * Netscape Communications Corporation.
 * Portions created by the Initial Developer are Copyright (C) 1998
 * the Initial Developer. All Rights Reserved.
 *
 * Contributor(s):
 *
 *
 * Alternatively, the contents of this file may be used under the terms of
 * either the GNU General Public License Version 2 or later (the "GPL"), or
 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
 * in which case the provisions of the GPL or the LGPL are applicable instead
 * of those above. If you wish to allow use of your version of this file only
 * under the terms of either the GPL or the LGPL, and not to allow others to
 * use your version of this file under the terms of the NPL, indicate your
 * decision by deleting the provisions above and replace them with the notice
 * and other provisions required by the GPL or the LGPL. If you do not delete
 * the provisions above, a recipient may use your version of this file under
 * the terms of any one of the NPL, the GPL or the LGPL.
 *
 * ***** END LICENSE BLOCK ***** */

#include "nsConverterInputStream.h"
#include "nsICharsetConverterManager.h"
#include "nsIServiceManager.h"

#define CONVERTER_BUFFER_SIZE 8192

NS_IMPL_ISUPPORTS1(nsConverterInputStream, nsIConverterInputStream)
    
static NS_DEFINE_CID(kCharsetConverterManagerCID, NS_ICHARSETCONVERTERMANAGER_CID);

NS_IMETHODIMP
nsConverterInputStream::Init(nsIInputStream* aStream,
                             const char *aCharset,
                             PRInt32 aBufferSize,
                             PRBool aRecoverFromErrors)
{
    nsresult rv;

    if (aBufferSize <=0) aBufferSize=CONVERTER_BUFFER_SIZE;
    
    // get the decoder
    nsCOMPtr<nsICharsetConverterManager> ccm =
        do_GetService(kCharsetConverterManagerCID, &rv);
    if (NS_FAILED(rv)) return nsnull;

    rv = ccm->GetUnicodeDecoder(aCharset ? aCharset : "ISO-8859-1", getter_AddRefs(mConverter));
    if (NS_FAILED(rv)) return rv;
 
    // set up our buffers
    rv = NS_NewByteBuffer(getter_AddRefs(mByteData), nsnull, aBufferSize);
    if (NS_FAILED(rv)) return rv;

    rv = NS_NewUnicharBuffer(getter_AddRefs(mUnicharData), nsnull, aBufferSize);
    if (NS_FAILED(rv)) return rv;

    mInput = aStream;
    mRecoverFromErrors = aRecoverFromErrors;
    
    return NS_OK;
}

NS_IMETHODIMP
nsConverterInputStream::Close()
{
    mInput = nsnull;
    mConverter = nsnull;
    mByteData = nsnull;
    mUnicharData = nsnull;
    return NS_OK;
}

NS_IMETHODIMP
nsConverterInputStream::Read(PRUnichar* aBuf,
                             PRUint32 aCount,
                             PRUint32 *aReadCount)
{
  NS_ASSERTION(mUnicharDataLength >= mUnicharDataOffset, "unsigned madness");
  PRUint32 rv = mUnicharDataLength - mUnicharDataOffset;
  if (0 == rv) {
    // Fill the unichar buffer
    rv = Fill(&mLastErrorCode);
    if (rv == 0) {
      *aReadCount = 0;
      return mLastErrorCode;
    }
  }
  if (rv > aCount) {
    rv = aCount;
  }
  memcpy(aBuf, mUnicharData->GetBuffer() + mUnicharDataOffset,
         rv * sizeof(PRUnichar));
  mUnicharDataOffset += rv;
  *aReadCount = rv;
  return NS_OK;
}

NS_IMETHODIMP
nsConverterInputStream::ReadSegments(nsWriteUnicharSegmentFun aWriter,
                                     void* aClosure,
                                     PRUint32 aCount, PRUint32 *aReadCount)
{
  NS_ASSERTION(mUnicharDataLength >= mUnicharDataOffset, "unsigned madness");
  PRUint32 bytesToWrite = mUnicharDataLength - mUnicharDataOffset;
  nsresult rv;
  if (0 == bytesToWrite) {
    // Fill the unichar buffer
    bytesToWrite = Fill(&rv);
    if (bytesToWrite <= 0) {
      *aReadCount = 0;
      return rv;
    }
  }
  
  if (bytesToWrite > aCount)
    bytesToWrite = aCount;
  
  PRUint32 bytesWritten;
  PRUint32 totalBytesWritten = 0;

  while (bytesToWrite) {
    rv = aWriter(this, aClosure,
                 mUnicharData->GetBuffer() + mUnicharDataOffset,
                 totalBytesWritten, bytesToWrite, &bytesWritten);
    if (NS_FAILED(rv)) {
      // don't propagate errors to the caller
      break;
    }
    
    bytesToWrite -= bytesWritten;
    totalBytesWritten += bytesWritten;
    mUnicharDataOffset += bytesWritten;
    
  }

  *aReadCount = totalBytesWritten;

  return NS_OK;
}

PRUint32
nsConverterInputStream::Fill(nsresult * aErrorCode)
{
  if (nsnull == mInput) {
    // We already closed the stream!
    *aErrorCode = NS_BASE_STREAM_CLOSED;
    return 0;
  }

  if (NS_FAILED(mLastErrorCode)) {
    // We failed to completely convert last time, and error-recovery
    // is disabled.  We will fare no better this time, so...
    *aErrorCode = mLastErrorCode;
    return 0;
  }
  
  // We assume a many to one conversion and are using equal sizes for
  // the two buffers.  However if an error happens at the very start
  // of a byte buffer we may end up in a situation where n bytes lead
  // to n+1 unicode chars.  Thus we need to keep track of the leftover
  // bytes as we convert.
  
  PRInt32 nb = mByteData->Fill(aErrorCode, mInput, mLeftOverBytes);
#if defined(DEBUG_bzbarsky) && 0
  for (unsigned int foo = 0; foo < mByteData->GetLength(); ++foo) {
    fprintf(stderr, "%c", mByteData->GetBuffer()[foo]);
  }
  fprintf(stderr, "\n");
#endif
  if (nb <= 0 && mLeftOverBytes == 0) {
    // No more data 
    *aErrorCode = NS_OK;
    return 0;
  }

  NS_ASSERTION(PRUint32(nb) + mLeftOverBytes == mByteData->GetLength(),
               "mByteData is lying to us somewhere");
  
  // Now convert as much of the byte buffer to unicode as possible
  mUnicharDataOffset = 0;
  mUnicharDataLength = 0;
  PRUint32 srcConsumed = 0;
  do {
    PRInt32 srcLen = mByteData->GetLength() - srcConsumed;
    PRInt32 dstLen = mUnicharData->GetBufferSize() - mUnicharDataLength;
    *aErrorCode = mConverter->Convert(mByteData->GetBuffer()+srcConsumed,
                                      &srcLen,
                                      mUnicharData->GetBuffer()+mUnicharDataLength,
                                      &dstLen);
    mUnicharDataLength += dstLen;
    // XXX if srcLen is negative, we want to drop the _first_ byte in
    // the erroneous byte sequence and try again.  This is not quite
    // possible right now -- see bug 160784
    srcConsumed += srcLen;
    if (NS_FAILED(*aErrorCode) && mRecoverFromErrors) {
      NS_ASSERTION(0 < mUnicharData->GetBufferSize() - mUnicharDataLength,
                   "Decoder returned an error but filled the output buffer! "
                   "Should not happen.");
      mUnicharData->GetBuffer()[mUnicharDataLength++] = (PRUnichar)0xFFFD;
      ++srcConsumed;
      // XXX this is needed to make sure we don't underrun our buffer;
      // bug 160784 again
      srcConsumed = PR_MAX(srcConsumed, 0);
      mConverter->Reset();
    }
    NS_ASSERTION(srcConsumed <= mByteData->GetLength(),
                 "Whoa.  The converter should have returned NS_OK_UDEC_MOREINPUT before this point!");
  } while (mRecoverFromErrors &&
           NS_FAILED(*aErrorCode));

  mLeftOverBytes = mByteData->GetLength() - srcConsumed;

  return mUnicharDataLength;
}