summaryrefslogtreecommitdiff
path: root/xpcom/io/nsUnicharInputStream.cpp
blob: 27c074c092fda5b50771537d23a84b55f66b6990 (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
/* -*- 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/. */

#include "nsUnicharInputStream.h"
#include "nsIInputStream.h"
#include "nsIServiceManager.h"
#include "nsString.h"
#include "nsTArray.h"
#include "nsAutoPtr.h"
#include "nsCRT.h"
#include "nsStreamUtils.h"
#include "nsUTF8Utils.h"
#include "mozilla/Attributes.h"
#include <fcntl.h>
#if defined(XP_WIN)
#include <io.h>
#else
#include <unistd.h>
#endif

#define STRING_BUFFER_SIZE 8192

class StringUnicharInputStream final : public nsIUnicharInputStream
{
public:
  explicit StringUnicharInputStream(const nsAString& aString) :
    mString(aString), mPos(0), mLen(aString.Length()) { }

  NS_DECL_ISUPPORTS
  NS_DECL_NSIUNICHARINPUTSTREAM

  nsString mString;
  uint32_t mPos;
  uint32_t mLen;

private:
  ~StringUnicharInputStream() { }
};

NS_IMETHODIMP
StringUnicharInputStream::Read(char16_t* aBuf,
                               uint32_t aCount,
                               uint32_t* aReadCount)
{
  if (mPos >= mLen) {
    *aReadCount = 0;
    return NS_OK;
  }
  nsAString::const_iterator iter;
  mString.BeginReading(iter);
  const char16_t* us = iter.get();
  uint32_t amount = mLen - mPos;
  if (amount > aCount) {
    amount = aCount;
  }
  memcpy(aBuf, us + mPos, sizeof(char16_t) * amount);
  mPos += amount;
  *aReadCount = amount;
  return NS_OK;
}

NS_IMETHODIMP
StringUnicharInputStream::ReadSegments(nsWriteUnicharSegmentFun aWriter,
                                       void* aClosure,
                                       uint32_t aCount, uint32_t* aReadCount)
{
  uint32_t bytesWritten;
  uint32_t totalBytesWritten = 0;

  nsresult rv;
  aCount = XPCOM_MIN(mString.Length() - mPos, aCount);

  nsAString::const_iterator iter;
  mString.BeginReading(iter);

  while (aCount) {
    rv = aWriter(this, aClosure, iter.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;
}

NS_IMETHODIMP
StringUnicharInputStream::ReadString(uint32_t aCount, nsAString& aString,
                                     uint32_t* aReadCount)
{
  if (mPos >= mLen) {
    *aReadCount = 0;
    return NS_OK;
  }
  uint32_t amount = mLen - mPos;
  if (amount > aCount) {
    amount = aCount;
  }
  aString = Substring(mString, mPos, amount);
  mPos += amount;
  *aReadCount = amount;
  return NS_OK;
}

nsresult
StringUnicharInputStream::Close()
{
  mPos = mLen;
  return NS_OK;
}

NS_IMPL_ISUPPORTS(StringUnicharInputStream, nsIUnicharInputStream)

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

class UTF8InputStream final : public nsIUnicharInputStream
{
public:
  UTF8InputStream();
  nsresult Init(nsIInputStream* aStream);

  NS_DECL_ISUPPORTS
  NS_DECL_NSIUNICHARINPUTSTREAM

private:
  ~UTF8InputStream();

protected:
  int32_t Fill(nsresult* aErrorCode);

  static void CountValidUTF8Bytes(const char* aBuf, uint32_t aMaxBytes,
                                  uint32_t& aValidUTF8bytes,
                                  uint32_t& aValidUTF16CodeUnits);

  nsCOMPtr<nsIInputStream> mInput;
  FallibleTArray<char> mByteData;
  FallibleTArray<char16_t> mUnicharData;

  uint32_t mByteDataOffset;
  uint32_t mUnicharDataOffset;
  uint32_t mUnicharDataLength;
};

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

nsresult
UTF8InputStream::Init(nsIInputStream* aStream)
{
  if (!mByteData.SetCapacity(STRING_BUFFER_SIZE, mozilla::fallible) ||
      !mUnicharData.SetCapacity(STRING_BUFFER_SIZE, mozilla::fallible)) {
    return NS_ERROR_OUT_OF_MEMORY;
  }
  mInput = aStream;

  return NS_OK;
}

NS_IMPL_ISUPPORTS(UTF8InputStream, nsIUnicharInputStream)

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

nsresult
UTF8InputStream::Close()
{
  mInput = nullptr;
  mByteData.Clear();
  mUnicharData.Clear();
  return NS_OK;
}

nsresult
UTF8InputStream::Read(char16_t* aBuf, uint32_t aCount, uint32_t* aReadCount)
{
  NS_ASSERTION(mUnicharDataLength >= mUnicharDataOffset, "unsigned madness");
  uint32_t readCount = mUnicharDataLength - mUnicharDataOffset;
  nsresult errorCode;
  if (0 == readCount) {
    // Fill the unichar buffer
    int32_t bytesRead = Fill(&errorCode);
    if (bytesRead <= 0) {
      *aReadCount = 0;
      return errorCode;
    }
    readCount = bytesRead;
  }
  if (readCount > aCount) {
    readCount = aCount;
  }
  memcpy(aBuf, mUnicharData.Elements() + mUnicharDataOffset,
         readCount * sizeof(char16_t));
  mUnicharDataOffset += readCount;
  *aReadCount = readCount;
  return NS_OK;
}

NS_IMETHODIMP
UTF8InputStream::ReadSegments(nsWriteUnicharSegmentFun aWriter,
                              void* aClosure,
                              uint32_t aCount, uint32_t* aReadCount)
{
  NS_ASSERTION(mUnicharDataLength >= mUnicharDataOffset, "unsigned madness");
  uint32_t bytesToWrite = mUnicharDataLength - mUnicharDataOffset;
  nsresult rv = NS_OK;
  if (0 == bytesToWrite) {
    // Fill the unichar buffer
    int32_t bytesRead = Fill(&rv);
    if (bytesRead <= 0) {
      *aReadCount = 0;
      return rv;
    }
    bytesToWrite = bytesRead;
  }

  if (bytesToWrite > aCount) {
    bytesToWrite = aCount;
  }

  uint32_t bytesWritten;
  uint32_t totalBytesWritten = 0;

  while (bytesToWrite) {
    rv = aWriter(this, aClosure,
                 mUnicharData.Elements() + 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;
}

NS_IMETHODIMP
UTF8InputStream::ReadString(uint32_t aCount, nsAString& aString,
                            uint32_t* aReadCount)
{
  NS_ASSERTION(mUnicharDataLength >= mUnicharDataOffset, "unsigned madness");
  uint32_t readCount = mUnicharDataLength - mUnicharDataOffset;
  nsresult errorCode;
  if (0 == readCount) {
    // Fill the unichar buffer
    int32_t bytesRead = Fill(&errorCode);
    if (bytesRead <= 0) {
      *aReadCount = 0;
      return errorCode;
    }
    readCount = bytesRead;
  }
  if (readCount > aCount) {
    readCount = aCount;
  }
  const char16_t* buf = mUnicharData.Elements() + mUnicharDataOffset;
  aString.Assign(buf, readCount);

  mUnicharDataOffset += readCount;
  *aReadCount = readCount;
  return NS_OK;
}

int32_t
UTF8InputStream::Fill(nsresult* aErrorCode)
{
  if (!mInput) {
    // We already closed the stream!
    *aErrorCode = NS_BASE_STREAM_CLOSED;
    return -1;
  }

  NS_ASSERTION(mByteData.Length() >= mByteDataOffset, "unsigned madness");
  uint32_t remainder = mByteData.Length() - mByteDataOffset;
  mByteDataOffset = remainder;
  uint32_t nb;
  *aErrorCode = NS_FillArray(mByteData, mInput, remainder, &nb);
  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 received no more new
    // data to add to it, we can't convert it. Therefore, we discard
    // it.
    return nb;
  }
  NS_ASSERTION(remainder + nb == mByteData.Length(), "bad nb");

  // Now convert as much of the byte buffer to unicode as possible
  uint32_t srcLen, dstLen;
  CountValidUTF8Bytes(mByteData.Elements(), 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(dstLen <= mUnicharData.Capacity(),
               "Ouch. I would overflow my buffer if I wasn't so careful.");
  if (dstLen > mUnicharData.Capacity()) {
    return 0;
  }

  ConvertUTF8toUTF16 converter(mUnicharData.Elements());

  nsASingleFragmentCString::const_char_iterator start = mByteData.Elements();
  nsASingleFragmentCString::const_char_iterator end = mByteData.Elements() + srcLen;

  copy_string(start, end, converter);
  if (converter.Length() != dstLen) {
    *aErrorCode = NS_BASE_STREAM_BAD_CONVERSION;
    return -1;
  }

  mUnicharDataOffset = 0;
  mUnicharDataLength = dstLen;
  mByteDataOffset = srcLen;

  return dstLen;
}

void
UTF8InputStream::CountValidUTF8Bytes(const char* aBuffer, uint32_t aMaxBytes,
                                     uint32_t& aValidUTF8bytes,
                                     uint32_t& aValidUTF16CodeUnits)
{
  const char* c = aBuffer;
  const char* end = aBuffer + aMaxBytes;
  const char* lastchar = c;  // pre-initialize in case of 0-length buffer
  uint32_t utf16length = 0;
  while (c < end && *c) {
    lastchar = c;
    utf16length++;

    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;
      utf16length++; // add 1 more because this will be converted to a
      // surrogate pair.
    } 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;
    utf16length--;
  }

  aValidUTF8bytes = c - aBuffer;
  aValidUTF16CodeUnits = utf16length;
}

nsresult
NS_NewUnicharInputStream(nsIInputStream* aStreamToWrap,
                         nsIUnicharInputStream** aResult)
{
  *aResult = nullptr;

  // Create converter input stream
  RefPtr<UTF8InputStream> it = new UTF8InputStream();
  nsresult rv = it->Init(aStreamToWrap);
  if (NS_FAILED(rv)) {
    return rv;
  }

  it.forget(aResult);
  return NS_OK;
}