summaryrefslogtreecommitdiff
path: root/parser/htmlparser/nsScanner.cpp
blob: 620764590a5e433f3b6eaae4ca263a0eff4fbf09 (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
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* vim: set ts=2 sw=2 et tw=78: */
/* 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/. */

//#define __INCREMENTAL 1

#include "mozilla/Attributes.h"
#include "mozilla/DebugOnly.h"

#include "nsScanner.h"
#include "nsDebug.h"
#include "nsReadableUtils.h"
#include "nsIInputStream.h"
#include "nsIFile.h"
#include "nsUTF8Utils.h" // for LossyConvertEncoding
#include "nsCRT.h"
#include "nsParser.h"
#include "nsCharsetSource.h"

#include "mozilla/dom/EncodingUtils.h"

using mozilla::dom::EncodingUtils;

nsReadEndCondition::nsReadEndCondition(const char16_t* aTerminateChars) :
  mChars(aTerminateChars), mFilter(char16_t(~0)) // All bits set
{
  // Build filter that will be used to filter out characters with
  // bits that none of the terminal chars have. This works very well
  // because terminal chars often have only the last 4-6 bits set and
  // normal ascii letters have bit 7 set. Other letters have even higher
  // bits set.
  
  // Calculate filter
  const char16_t *current = aTerminateChars;
  char16_t terminalChar = *current;
  while (terminalChar) {
    mFilter &= ~terminalChar;
    ++current;
    terminalChar = *current;
  }
}

/**
 *  Use this constructor if you want i/o to be based on 
 *  a single string you hand in during construction.
 *  This short cut was added for Javascript.
 *
 *  @update  gess 5/12/98
 *  @param   aMode represents the parser mode (nav, other)
 *  @return  
 */
nsScanner::nsScanner(const nsAString& anHTMLString)
{
  MOZ_COUNT_CTOR(nsScanner);

  mSlidingBuffer = nullptr;
  if (AppendToBuffer(anHTMLString)) {
    mSlidingBuffer->BeginReading(mCurrentPosition);
  } else {
    /* XXX see hack below, re: bug 182067 */
    memset(&mCurrentPosition, 0, sizeof(mCurrentPosition));
    mEndPosition = mCurrentPosition;
  }
  mMarkPosition = mCurrentPosition;
  mIncremental = false;
  mUnicodeDecoder = nullptr;
  mCharsetSource = kCharsetUninitialized;
}

/**
 *  Use this constructor if you want i/o to be based on strings 
 *  the scanner receives. If you pass a null filename, you
 *  can still provide data to the scanner via append.
 */
nsScanner::nsScanner(nsString& aFilename, bool aCreateStream)
  : mFilename(aFilename)
{
  MOZ_COUNT_CTOR(nsScanner);
  NS_ASSERTION(!aCreateStream, "This is always true.");

  mSlidingBuffer = nullptr;

  // XXX This is a big hack.  We need to initialize the iterators to something.
  // What matters is that mCurrentPosition == mEndPosition, so that our methods
  // believe that we are at EOF (see bug 182067).  We null out mCurrentPosition
  // so that we have some hope of catching null pointer dereferences associated
  // with this hack. --darin
  memset(&mCurrentPosition, 0, sizeof(mCurrentPosition));
  mMarkPosition = mCurrentPosition;
  mEndPosition = mCurrentPosition;

  mIncremental = true;

  mUnicodeDecoder = nullptr;
  mCharsetSource = kCharsetUninitialized;
  // XML defaults to UTF-8 and about:blank is UTF-8, too.
  SetDocumentCharset(NS_LITERAL_CSTRING("UTF-8"), kCharsetFromDocTypeDefault);
}

nsresult nsScanner::SetDocumentCharset(const nsACString& aCharset , int32_t aSource)
{
  if (aSource < mCharsetSource) // priority is lower than the current one
    return NS_OK;

  mCharsetSource = aSource;

  nsCString charsetName;
  mozilla::DebugOnly<bool> valid =
      EncodingUtils::FindEncodingForLabel(aCharset, charsetName);
  MOZ_ASSERT(valid, "Should never call with a bogus aCharset.");

  if (!mCharset.IsEmpty() && charsetName.Equals(mCharset)) {
    return NS_OK; // no difference, don't change it
  }

  // different, need to change it

  mCharset.Assign(charsetName);

  mUnicodeDecoder = EncodingUtils::DecoderForEncoding(mCharset);
  mUnicodeDecoder->SetInputErrorBehavior(nsIUnicodeDecoder::kOnError_Signal);

  return NS_OK;
}


/**
 *  default destructor
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  
 */
nsScanner::~nsScanner() {

  delete mSlidingBuffer;

  MOZ_COUNT_DTOR(nsScanner);
}

/**
 *  Resets current offset position of input stream to marked position. 
 *  This allows us to back up to this point if the need should arise, 
 *  such as when tokenization gets interrupted.
 *  NOTE: IT IS REALLY BAD FORM TO CALL RELEASE WITHOUT CALLING MARK FIRST!
 *
 *  @update  gess 5/12/98
 *  @param   
 *  @return  
 */
void nsScanner::RewindToMark(void){
  if (mSlidingBuffer) {
    mCurrentPosition = mMarkPosition;
  }
}


/**
 *  Records current offset position in input stream. This allows us
 *  to back up to this point if the need should arise, such as when
 *  tokenization gets interrupted.
 *
 *  @update  gess 7/29/98
 *  @param   
 *  @return  
 */
int32_t nsScanner::Mark() {
  int32_t distance = 0;
  if (mSlidingBuffer) {
    nsScannerIterator oldStart;
    mSlidingBuffer->BeginReading(oldStart);

    distance = Distance(oldStart, mCurrentPosition);

    mSlidingBuffer->DiscardPrefix(mCurrentPosition);
    mSlidingBuffer->BeginReading(mCurrentPosition);
    mMarkPosition = mCurrentPosition;
  }

  return distance;
}

/** 
 * Insert data to our underlying input buffer as
 * if it were read from an input stream.
 *
 * @update  harishd 01/12/99
 * @return  error code 
 */
bool nsScanner::UngetReadable(const nsAString& aBuffer) {
  if (!mSlidingBuffer) {
    return false;
  }

  mSlidingBuffer->UngetReadable(aBuffer,mCurrentPosition);
  mSlidingBuffer->BeginReading(mCurrentPosition); // Insertion invalidated our iterators
  mSlidingBuffer->EndReading(mEndPosition);
 
  return true;
}

/** 
 * Append data to our underlying input buffer as
 * if it were read from an input stream.
 *
 * @update  gess4/3/98
 * @return  error code 
 */
nsresult nsScanner::Append(const nsAString& aBuffer) {
  if (!AppendToBuffer(aBuffer))
    return NS_ERROR_OUT_OF_MEMORY;
  return NS_OK;
}

/**
 *  
 *  
 *  @update  gess 5/21/98
 *  @param   
 *  @return  
 */
nsresult nsScanner::Append(const char* aBuffer, uint32_t aLen)
{
  nsresult res = NS_OK;
  if (mUnicodeDecoder) {
    int32_t unicharBufLen = 0;

    nsresult rv = mUnicodeDecoder->GetMaxLength(aBuffer, aLen, &unicharBufLen);
    if (NS_WARN_IF(NS_FAILED(rv))) {
      return rv;
    }

    nsScannerString::Buffer* buffer = nsScannerString::AllocBuffer(unicharBufLen + 1);
    NS_ENSURE_TRUE(buffer,NS_ERROR_OUT_OF_MEMORY);
    char16_t *unichars = buffer->DataStart();

    int32_t totalChars = 0;
    int32_t unicharLength = unicharBufLen;

    do {
      int32_t srcLength = aLen;
      res = mUnicodeDecoder->Convert(aBuffer, &srcLength, unichars, &unicharLength);

      totalChars += unicharLength;
      // Continuation of failure case
      if(NS_FAILED(res)) {
        // if we failed, we consume one byte, replace it with the replacement
        // character and try the conversion again.

        // This is only needed because some decoders don't follow the
        // nsIUnicodeDecoder contract: they return a failure when *aDestLength
        // is 0 rather than the correct NS_OK_UDEC_MOREOUTPUT.  See bug 244177
        if ((unichars + unicharLength) >= buffer->DataEnd()) {
          NS_ERROR("Unexpected end of destination buffer");
          break;
        }

        // Since about:blank is empty, this line runs only for XML. Use a
        // character that's illegal in XML instead of U+FFFD in order to make
        // expat flag the error.
        unichars[unicharLength++] = 0xFFFF;

        unichars = unichars + unicharLength;
        unicharLength = unicharBufLen - (++totalChars);

        mUnicodeDecoder->Reset();

        if(((uint32_t) (srcLength + 1)) > aLen) {
          srcLength = aLen;
        }
        else {
          ++srcLength;
        }

        aBuffer += srcLength;
        aLen -= srcLength;
      }
    } while (NS_FAILED(res) && (aLen > 0));

    buffer->SetDataLength(totalChars);
    // Don't propagate return code of unicode decoder
    // since it doesn't reflect on our success or failure
    // - Ref. bug 87110
    res = NS_OK; 
    if (!AppendToBuffer(buffer))
      res = NS_ERROR_OUT_OF_MEMORY;
  }
  else {
    NS_WARNING("No decoder found.");
    res = NS_ERROR_FAILURE;
  }

  return res;
}

/**
 *  retrieve next char from scanners internal input stream
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  error code reflecting read status
 */
nsresult nsScanner::GetChar(char16_t& aChar) {
  if (!mSlidingBuffer || mCurrentPosition == mEndPosition) {
    aChar = 0;
    return kEOF;
  }

  aChar = *mCurrentPosition++;

  return NS_OK;
}


void nsScanner::BindSubstring(nsScannerSubstring& aSubstring, const nsScannerIterator& aStart, const nsScannerIterator& aEnd)
{
  aSubstring.Rebind(*mSlidingBuffer, aStart, aEnd);
}

void nsScanner::CurrentPosition(nsScannerIterator& aPosition)
{
  aPosition = mCurrentPosition;
}

void nsScanner::EndReading(nsScannerIterator& aPosition)
{
  aPosition = mEndPosition;
}
 
void nsScanner::SetPosition(nsScannerIterator& aPosition, bool aTerminate)
{
  if (mSlidingBuffer) {
    mCurrentPosition = aPosition;
    if (aTerminate && (mCurrentPosition == mEndPosition)) {
      mMarkPosition = mCurrentPosition;
      mSlidingBuffer->DiscardPrefix(mCurrentPosition);
    }
  }
}

bool nsScanner::AppendToBuffer(nsScannerString::Buffer* aBuf)
{
  if (!mSlidingBuffer) {
    mSlidingBuffer = new nsScannerString(aBuf);
    if (!mSlidingBuffer)
      return false;
    mSlidingBuffer->BeginReading(mCurrentPosition);
    mMarkPosition = mCurrentPosition;
    mSlidingBuffer->EndReading(mEndPosition);
  }
  else {
    mSlidingBuffer->AppendBuffer(aBuf);
    if (mCurrentPosition == mEndPosition) {
      mSlidingBuffer->BeginReading(mCurrentPosition);
    }
    mSlidingBuffer->EndReading(mEndPosition);
  }

  return true;
}

/**
 *  call this to copy bytes out of the scanner that have not yet been consumed
 *  by the tokenization process.
 *  
 *  @update  gess 5/12/98
 *  @param   aCopyBuffer is where the scanner buffer will be copied to
 *  @return  true if OK or false on OOM
 */
bool nsScanner::CopyUnusedData(nsString& aCopyBuffer) {
  if (!mSlidingBuffer) {
    aCopyBuffer.Truncate();
    return true;
  }

  nsScannerIterator start, end;
  start = mCurrentPosition;
  end = mEndPosition;

  return CopyUnicodeTo(start, end, aCopyBuffer);
}

/**
 *  Retrieve the name of the file that the scanner is reading from.
 *  In some cases, it's just a given name, because the scanner isn't
 *  really reading from a file.
 *  
 *  @update  gess 5/12/98
 *  @return  
 */
nsString& nsScanner::GetFilename(void) {
  return mFilename;
}

/**
 *  Conduct self test. Actually, selftesting for this class
 *  occurs in the parser selftest.
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  
 */

void nsScanner::SelfTest(void) {
#ifdef _DEBUG
#endif
}