summaryrefslogtreecommitdiffstats
path: root/src/libs/xpcom18a4/xpcom/io/nsUnicharInputStream.cpp
blob: 99e9364a9ee2280bc7acd50306d4164845a7d5a7 (plain)
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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* ***** BEGIN LICENSE BLOCK *****
 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
 *
 * The contents of this file are subject to the Mozilla 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/MPL/
 *
 * 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 of 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 MPL, 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 MPL, the GPL or the LGPL.
 *
 * ***** END LICENSE BLOCK ***** */


#include "nsIUnicharInputStream.h"
#include "nsIByteBuffer.h"
#include "nsIUnicharBuffer.h"
#include "nsIServiceManager.h"
#include "nsString.h"
#include "nsCRT.h"
#include "nsUTF8Utils.h"
#include <fcntl.h>
#if defined(NS_WIN32)
#include <io.h>
#else
#include <unistd.h>
#endif

class StringUnicharInputStream : public nsIUnicharInputStream {
public:
  StringUnicharInputStream(nsString* aString);

  NS_DECL_ISUPPORTS

  NS_IMETHOD Read(PRUnichar* aBuf,
                  PRUint32 aCount,
                  PRUint32 *aReadCount);
  NS_IMETHOD ReadSegments(nsWriteUnicharSegmentFun aWriter,
                          void* aClosure,
                          PRUint32 aCount, PRUint32* aReadCount);
  NS_IMETHOD Close();

  nsString* mString;
  PRUint32 mPos;
  PRUint32 mLen;

private:
  ~StringUnicharInputStream();
};

StringUnicharInputStream::StringUnicharInputStream(nsString* aString)
{
  mString = aString;
  mPos = 0;
  mLen = aString->Length();
}

StringUnicharInputStream::~StringUnicharInputStream()
{
  if (nsnull != mString) {
    delete mString;
  }
}

NS_IMETHODIMP
StringUnicharInputStream::Read(PRUnichar* aBuf,
                               PRUint32 aCount,
                               PRUint32 *aReadCount)
{
  if (mPos >= mLen) {
    *aReadCount = 0;
    return NS_OK;
  }
  const PRUnichar* us = mString->get();
  NS_ASSERTION(mLen >= mPos, "unsigned madness");
  PRUint32 amount = mLen - mPos;
  if (amount > aCount) {
    amount = aCount;
  }
  memcpy(aBuf, us + mPos, sizeof(PRUnichar) * amount);
  mPos += amount;
  *aReadCount = amount;
  return NS_OK;
}

NS_IMETHODIMP
StringUnicharInputStream::ReadSegments(nsWriteUnicharSegmentFun aWriter,
                                       void* aClosure,
                                       PRUint32 aCount, PRUint32 *aReadCount)
{
  PRUint32 bytesWritten;
  PRUint32 totalBytesWritten = 0;

  nsresult rv;
  aCount = PR_MIN(mString->Length() - mPos, aCount);
  
  while (aCount) {
    rv = aWriter(this, aClosure, mString->get() + mPos,
                 totalBytesWritten, aCount, &bytesWritten);
    
    if (NS_FAILED(rv)) {
      // don't propagate errors to the caller
      break;
    }
    
    aCount -= bytesWritten;
    totalBytesWritten += bytesWritten;
    mPos += bytesWritten;
  }
  
  *aReadCount = totalBytesWritten;
  
  return NS_OK;
}

nsresult StringUnicharInputStream::Close()
{
  mPos = mLen;
  if (nsnull != mString) {
    delete mString;
    mString = 0;
  }
  return NS_OK;
}

NS_IMPL_ISUPPORTS1(StringUnicharInputStream, nsIUnicharInputStream)

NS_COM nsresult
NS_NewStringUnicharInputStream(nsIUnicharInputStream** aInstancePtrResult,
                               nsString* aString)
{
  NS_PRECONDITION(nsnull != aString, "null ptr");
  NS_PRECONDITION(nsnull != aInstancePtrResult, "null ptr");
  if ((nsnull == aString) || (nsnull == aInstancePtrResult)) {
    return NS_ERROR_NULL_POINTER;
  }

  StringUnicharInputStream* it = new StringUnicharInputStream(aString);
  if (nsnull == it) {
    return NS_ERROR_OUT_OF_MEMORY;
  }

  return it->QueryInterface(NS_GET_IID(nsIUnicharInputStream),
                            (void**) aInstancePtrResult);
}

//----------------------------------------------------------------------

class UTF8InputStream : public nsIUnicharInputStream {
public:
  UTF8InputStream();
  nsresult Init(nsIInputStream* aStream, PRUint32 aBufSize);

  NS_DECL_ISUPPORTS
  NS_IMETHOD Read(PRUnichar* aBuf,
                  PRUint32 aCount,
                  PRUint32 *aReadCount);
  NS_IMETHOD ReadSegments(nsWriteUnicharSegmentFun aWriter,
                          void* aClosure,
                          PRUint32 aCount,
                          PRUint32 *aReadCount);
  NS_IMETHOD Close();

private:
  ~UTF8InputStream();

protected:
  PRInt32 Fill(nsresult * aErrorCode);

  static void CountValidUTF8Bytes(const char *aBuf, PRUint32 aMaxBytes, PRUint32& aValidUTF8bytes, PRUint32& aValidUCS2bytes);

  nsCOMPtr<nsIInputStream> mInput;
  nsCOMPtr<nsIByteBuffer> mByteData;
  nsCOMPtr<nsIUnicharBuffer> mUnicharData;
  
  PRUint32 mByteDataOffset;
  PRUint32 mUnicharDataOffset;
  PRUint32 mUnicharDataLength;
};

UTF8InputStream::UTF8InputStream() :
  mByteDataOffset(0),
  mUnicharDataOffset(0),
  mUnicharDataLength(0)
{
}

nsresult 
UTF8InputStream::Init(nsIInputStream* aStream, PRUint32 aBufferSize)
{
  if (aBufferSize == 0) {
    aBufferSize = 8192;
  }

  nsresult 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;

  return NS_OK;
}

NS_IMPL_ISUPPORTS1(UTF8InputStream,nsIUnicharInputStream)

UTF8InputStream::~UTF8InputStream()
{
  Close();
}

nsresult UTF8InputStream::Close()
{
  mInput = nsnull;
  mByteData = nsnull;
  mUnicharData = nsnull;

  return NS_OK;
}

nsresult UTF8InputStream::Read(PRUnichar* aBuf,
                               PRUint32 aCount,
                               PRUint32 *aReadCount)
{
  NS_ASSERTION(mUnicharDataLength >= mUnicharDataOffset, "unsigned madness");
  PRUint32 rv = mUnicharDataLength - mUnicharDataOffset;
  nsresult errorCode;
  if (0 == rv) {
    // Fill the unichar buffer
    rv = Fill(&errorCode);
    if (rv <= 0) {
      *aReadCount = 0;
      return errorCode;
    }
  }
  if (rv > aCount) {
    rv = aCount;
  }
  memcpy(aBuf, mUnicharData->GetBuffer() + mUnicharDataOffset,
         rv * sizeof(PRUnichar));
  mUnicharDataOffset += rv;
  *aReadCount = rv;
  return NS_OK;
}

NS_IMETHODIMP
UTF8InputStream::ReadSegments(nsWriteUnicharSegmentFun aWriter,
                              void* aClosure,
                              PRUint32 aCount, PRUint32 *aReadCount)
{
  NS_ASSERTION(mUnicharDataLength >= mUnicharDataOffset, "unsigned madness");
  PRUint32 bytesToWrite = mUnicharDataLength - mUnicharDataOffset;
  nsresult rv = NS_OK;
  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;
}

PRInt32 UTF8InputStream::Fill(nsresult * aErrorCode)
{
  if (nsnull == mInput) {
    // We already closed the stream!
    *aErrorCode = NS_BASE_STREAM_CLOSED;
    return -1;
  }

  NS_ASSERTION(mByteData->GetLength() >= mByteDataOffset, "unsigned madness");
  PRUint32 remainder = mByteData->GetLength() - mByteDataOffset;
  mByteDataOffset = remainder;
  PRInt32 nb = mByteData->Fill(aErrorCode, mInput, remainder);
  if (nb <= 0) {
    // Because we assume a many to one conversion, the lingering data
    // in the byte buffer must be a partial conversion
    // fragment. Because we know that we have recieved no more new
    // data to add to it, we can't convert it. Therefore, we discard
    // it.
    return nb;
  }
  NS_ASSERTION(remainder + nb == mByteData->GetLength(), "bad nb");

  // Now convert as much of the byte buffer to unicode as possible
  PRUint32 srcLen, dstLen;
  CountValidUTF8Bytes(mByteData->GetBuffer(),remainder + nb, srcLen, dstLen);

  // the number of UCS2 characters should always be <= the number of
  // UTF8 chars
  NS_ASSERTION( (remainder+nb >= srcLen), "cannot be longer than out buffer");
  NS_ASSERTION(PRInt32(dstLen) <= mUnicharData->GetBufferSize(),
               "Ouch. I would overflow my buffer if I wasn't so careful.");
  if (PRInt32(dstLen) > mUnicharData->GetBufferSize()) return 0;
  
  ConvertUTF8toUTF16 converter(mUnicharData->GetBuffer());
  
  nsASingleFragmentCString::const_char_iterator start = mByteData->GetBuffer();
  nsASingleFragmentCString::const_char_iterator end = mByteData->GetBuffer() + srcLen;
            
  copy_string(start, end, converter);
  NS_ASSERTION(converter.Length() == dstLen, "length mismatch");
               
  mUnicharDataOffset = 0;
  mUnicharDataLength = dstLen;
  mByteDataOffset = srcLen;
  
  return dstLen;
}

void
UTF8InputStream::CountValidUTF8Bytes(const char* aBuffer, PRUint32 aMaxBytes, PRUint32& aValidUTF8bytes, PRUint32& aValidUCS2chars)
{
  const char *c = aBuffer;
  const char *end = aBuffer + aMaxBytes;
  const char *lastchar = c;     // pre-initialize in case of 0-length buffer
  PRUint32 ucs2bytes = 0;
  while (c < end && *c) {
    lastchar = c;
    ucs2bytes++;
    
    if (UTF8traits::isASCII(*c))
      c++;
    else if (UTF8traits::is2byte(*c))
      c += 2;
    else if (UTF8traits::is3byte(*c))
      c += 3;
    else if (UTF8traits::is4byte(*c))
      c += 4;
    else if (UTF8traits::is5byte(*c))
      c += 5;
    else if (UTF8traits::is6byte(*c))
      c += 6;
    else {
      NS_WARNING("Unrecognized UTF8 string in UTF8InputStream::CountValidUTF8Bytes()");
      break; // Otherwise we go into an infinite loop.  But what happens now?
    }
  }
  if (c > end) {
    c = lastchar;
    ucs2bytes--;
  }

  aValidUTF8bytes = c - aBuffer;
  aValidUCS2chars = ucs2bytes;
}

NS_COM nsresult
NS_NewUTF8ConverterStream(nsIUnicharInputStream** aInstancePtrResult,
                          nsIInputStream* aStreamToWrap,
                          PRInt32 aBufferSize)
{
  // Create converter input stream
  UTF8InputStream* it = new UTF8InputStream();
  if (nsnull == it) {
    return NS_ERROR_OUT_OF_MEMORY;
  }

  nsresult rv = it->Init(aStreamToWrap, aBufferSize);
  if (NS_FAILED(rv))
    return rv;

  return it->QueryInterface(NS_GET_IID(nsIUnicharInputStream), 
                            (void **) aInstancePtrResult);
}