Newer
Older
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
/*
* The Apache Software License, Version 1.1
*
* Copyright (c) 1999-2001 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache\@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation, and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.ibm.com . For more information
* on the Apache Software Foundation, please see
* <http://www.apache.org/>.
*/
/*
* $Id$
*/
// ---------------------------------------------------------------------------
// Includes
// ---------------------------------------------------------------------------
#include <xercesc/util/BitOps.hpp>
#include <xercesc/util/BinInputStream.hpp>
#include <xercesc/util/PlatformUtils.hpp>
#include <xercesc/util/RuntimeException.hpp>
#include <xercesc/util/TranscodingException.hpp>
#include <xercesc/util/TransService.hpp>
#include <xercesc/util/UTFDataFormatException.hpp>
#include <xercesc/util/XMLEBCDICTranscoder.hpp>
#include <xercesc/util/XMLString.hpp>
#include <xercesc/util/XMLUni.hpp>
#include <xercesc/sax/InputSource.hpp>
#include <xercesc/framework/XMLBuffer.hpp>
#include <xercesc/internal/CharTypeTables.hpp>
#include <xercesc/internal/XMLReader.hpp>
#include <xercesc/internal/XMLScanner.hpp>
#include <string.h>
// ---------------------------------------------------------------------------
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
// ---------------------------------------------------------------------------
// Checks whether all of the chars in the passed buffer are whitespace or
// not. Breaks out on the first non-whitespace.
//
bool XMLReader::isAllSpaces(const XMLCh* const toCheck
, const unsigned int count)
{
const XMLCh* curCh = toCheck;
const XMLCh* endPtr = toCheck + count;
while (curCh < endPtr)
{
if (!(fgCharCharsTable[*curCh++] & gWhitespaceCharMask))
return false;
}
return true;
}
//
// Checks whether at least one of the chars in the passed buffer are whitespace or
// not.
//
bool XMLReader::containsWhiteSpace(const XMLCh* const toCheck
, const unsigned int count)
{
const XMLCh* curCh = toCheck;
const XMLCh* endPtr = toCheck + count;
while (curCh < endPtr)
{
if (fgCharCharsTable[*curCh++] & gWhitespaceCharMask)
return true;
}
return false;
}
//
// This one is not called terribly often, so call the XMLChar utility
//
bool XMLReader::isPublicIdChar(const XMLCh toCheck)
{
if (fXMLVersion == XMLV1_1)
return XMLChar1_1::isPublicIdChar(toCheck);
else
return XMLChar1_0::isPublicIdChar(toCheck);
}
// ---------------------------------------------------------------------------
// XMLReader: Constructors and Destructor
// ---------------------------------------------------------------------------
XMLReader::XMLReader(const XMLCh* const pubId
, const XMLCh* const sysId
, BinInputStream* const streamToAdopt
, const RefFrom from
, const Types type
, const Sources source
fCharIndex(0)
, fCharsAvail(0)
, fCurCol(1)
, fCurLine(1)
, fEncodingStr(0)
, fForcedEncoding(false)
, fNoMore(false)
, fPublicId(XMLString::replicate(pubId))
, fRawBufIndex(0)
, fRawBytesAvail(0)
, fReaderNum(0xFFFFFFFF)
, fRefFrom(from)
, fSentTrailingSpace(false)
, fSource(source)
, fSrcOfsBase(0)
, fSrcOfsSupported(false)
, fCalculateSrcOfs(calculateSrcOfs)
, fStream(streamToAdopt)
, fSystemId(XMLString::replicate(sysId))
, fSwapped(false)
, fThrowAtEnd(throwAtEnd)
, fTranscoder(0)
, fType(type)
{
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
// Do an initial load of raw bytes
refreshRawBuffer();
// Ask the transcoding service if it supports src offset info
fSrcOfsSupported = XMLPlatformUtils::fgTransService->supportsSrcOfs();
//
// Use the recognizer class to get a basic sense of what family of
// encodings this file is in. We'll start off with a reader of that
// type, and update it later if needed when we read the XMLDecl line.
//
fEncoding = XMLRecognizer::basicEncodingProbe(fRawByteBuf, fRawBytesAvail);
#if defined(XERCES_DEBUG)
if ((fEncoding < XMLRecognizer::Encodings_Min)
|| (fEncoding > XMLRecognizer::Encodings_Max))
{
ThrowXML(RuntimeException, XMLExcepts::Reader_BadAutoEncoding);
}
#endif
fEncodingStr = XMLString::replicate(XMLRecognizer::nameForEncoding(fEncoding));
// Check whether the fSwapped flag should be set or not
checkForSwapped();
//
// This will check to see if the first line is an XMLDecl and, if
// so, decode that first line manually one character at a time. This
// leaves enough characters in the buffer that the high level code
// can get through the Decl and call us back with the real encoding.
//
doInitDecode();
//
// NOTE: We won't create a transcoder until we either get a call to
// setEncoding() or we get a call to refreshCharBuffer() and no
// transcoder has been set yet.
//
}
XMLReader::XMLReader(const XMLCh* const pubId
, const XMLCh* const sysId
, BinInputStream* const streamToAdopt
, const XMLCh* const encodingStr
, const RefFrom from
, const Types type
, const Sources source
fCharIndex(0)
, fCharsAvail(0)
, fCurCol(1)
, fCurLine(1)
, fEncoding(XMLRecognizer::UTF_8)
, fEncodingStr(0)
, fForcedEncoding(true)
, fNoMore(false)
, fPublicId(XMLString::replicate(pubId))
, fRawBufIndex(0)
, fRawBytesAvail(0)
, fReaderNum(0xFFFFFFFF)
, fRefFrom(from)
, fSentTrailingSpace(false)
, fSource(source)
, fSrcOfsBase(0)
, fSrcOfsSupported(false)
, fCalculateSrcOfs(calculateSrcOfs)
, fStream(streamToAdopt)
, fSystemId(XMLString::replicate(sysId))
, fSwapped(false)
, fThrowAtEnd(throwAtEnd)
, fTranscoder(0)
, fType(type)
{
// Do an initial load of raw bytes
refreshRawBuffer();
// Copy the encoding string to our member
fEncodingStr = XMLString::replicate(encodingStr);
// Ask the transcoding service if it supports src offset info
fSrcOfsSupported = XMLPlatformUtils::fgTransService->supportsSrcOfs();
//
// Map the passed encoding name to one of our enums. If it does not
// match one of the intrinsic encodings, it will come back 'other',
// which tells us to create a transcoder based reader.
//
fEncoding = XMLRecognizer::encodingForName(fEncodingStr);
// Check whether the fSwapped flag should be set or not
checkForSwapped();
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
//
// Create a transcoder for the encoding. Since the encoding has been
// forced, this will be the one we will use, period.
//
XMLTransService::Codes failReason;
if (fEncoding == XMLRecognizer::OtherEncoding)
{
//
// fEncodingStr not pre-recognized, use it
// directly for transcoder
//
fTranscoder = XMLPlatformUtils::fgTransService->makeNewTranscoderFor
(
fEncodingStr
, failReason
, kCharBufSize
);
}
else
{
//
// Use the recognized fEncoding to create the transcoder
//
fTranscoder = XMLPlatformUtils::fgTransService->makeNewTranscoderFor
(
fEncoding
, failReason
, kCharBufSize
);
}
if (!fTranscoder)
{
ThrowXML1
(
TranscodingException
, XMLExcepts::Trans_CantCreateCvtrFor
, fEncodingStr
);
}
//
// Note that, unlike above, we do not do an initial decode of the
// first line. We take the caller's word that the encoding is correct
// and just assume that the first bulk decode (kicked off by the first
// get of a character) will work.
//
// So we do here the slipping in of the leading space if required.
//
if ((fType == Type_PE) && (fRefFrom == RefFrom_NonLiteral))
{
// This represents no data from the source
fCharSizeBuf[fCharsAvail] = 0;
fCharBuf[fCharsAvail++] = chSpace;
}
}
XMLReader::XMLReader(const XMLCh* const pubId
, const XMLCh* const sysId
, BinInputStream* const streamToAdopt
, XMLRecognizer::Encodings encodingEnum
, const RefFrom from
, const Types type
, const Sources source
fCharIndex(0)
, fCharsAvail(0)
, fCurCol(1)
, fCurLine(1)
, fEncoding(XMLRecognizer::UTF_8)
, fEncodingStr(0)
, fForcedEncoding(true)
, fNoMore(false)
, fPublicId(XMLString::replicate(pubId))
, fRawBufIndex(0)
, fRawBytesAvail(0)
, fReaderNum(0xFFFFFFFF)
, fRefFrom(from)
, fSentTrailingSpace(false)
, fSource(source)
, fSrcOfsBase(0)
, fSrcOfsSupported(false)
, fCalculateSrcOfs(calculateSrcOfs)
, fStream(streamToAdopt)
, fSystemId(XMLString::replicate(sysId))
, fSwapped(false)
, fThrowAtEnd(throwAtEnd)
, fTranscoder(0)
, fType(type)
{
// Do an initial load of raw bytes
refreshRawBuffer();
// Ask the transcoding service if it supports src offset info
fSrcOfsSupported = XMLPlatformUtils::fgTransService->supportsSrcOfs();
//
// Use the passed encoding code
//
fEncoding = encodingEnum;
fEncodingStr = XMLString::replicate(XMLRecognizer::nameForEncoding(fEncoding));
// Check whether the fSwapped flag should be set or not
checkForSwapped();
//
// Create a transcoder for the encoding. Since the encoding has been
// forced, this will be the one we will use, period.
//
XMLTransService::Codes failReason;
fTranscoder = XMLPlatformUtils::fgTransService->makeNewTranscoderFor
(
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
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
, failReason
, kCharBufSize
);
if (!fTranscoder)
{
ThrowXML1
(
TranscodingException
, XMLExcepts::Trans_CantCreateCvtrFor
, fEncodingStr
);
}
//
// Note that, unlike above, we do not do an initial decode of the
// first line. We take the caller's word that the encoding is correct
// and just assume that the first bulk decode (kicked off by the first
// get of a character) will work.
//
// So we do here the slipping in of the leading space if required.
//
if ((fType == Type_PE) && (fRefFrom == RefFrom_NonLiteral))
{
// This represents no data from the source
fCharSizeBuf[fCharsAvail] = 0;
fCharBuf[fCharsAvail++] = chSpace;
}
}
XMLReader::~XMLReader()
{
delete [] fEncodingStr;
delete [] fPublicId;
delete [] fSystemId;
delete fStream;
delete fTranscoder;
}
// ---------------------------------------------------------------------------
// XMLReader: Character buffer management methods
// ---------------------------------------------------------------------------
unsigned int XMLReader::getSrcOffset() const
{
if (!fSrcOfsSupported || !fCalculateSrcOfs)
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
ThrowXML(RuntimeException, XMLExcepts::Reader_SrcOfsNotSupported);
//
// Take the current source offset and add in the sizes that we've
// eaten from the source so far.
//
unsigned int offset = fSrcOfsBase;
for (unsigned int index = 0; index < fCharIndex; index++)
offset += fCharSizeBuf[index];
return offset;
}
bool XMLReader::refreshCharBuffer()
{
// If the no more flag is set, then don't both doing anything
if (fNoMore)
return false;
unsigned int startInd;
// See if we have any existing chars.
const unsigned int spareChars = fCharsAvail - fCharIndex;
// If we are full, then don't do anything.
if (spareChars == kCharBufSize)
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
//
// If no transcoder has been created yet, then we never saw the
// any encoding="" string and the encoding was not forced, so lets
// create one now. We know that it won't change now.
//
// However, note that if we autosensed EBCDIC, then we have to
// consider it an error if we never got an encoding since we don't
// know what variant of EBCDIC it is.
//
if (!fTranscoder)
{
if (fEncoding == XMLRecognizer::EBCDIC)
ThrowXML(RuntimeException, XMLExcepts::Reader_EncodingStrRequired);
// Ask the transcoding service to make use a transcoder
XMLTransService::Codes failReason;
fTranscoder = XMLPlatformUtils::fgTransService->makeNewTranscoderFor
(
fEncodingStr
, failReason
, kCharBufSize
);
if (!fTranscoder)
{
ThrowXML1
(
TranscodingException
, XMLExcepts::Trans_CantCreateCvtrFor
, fEncodingStr
);
}
}
//
// Add the number of source bytes eaten so far to the base src
// offset member.
//
if (fCalculateSrcOfs) {
for (startInd = 0; startInd < fCharIndex; startInd++)
fSrcOfsBase += fCharSizeBuf[startInd];
}
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
//
// If there are spare chars, then move then down to the bottom. We
// have to move the char sizes down also.
//
startInd = 0;
if (spareChars)
{
for (unsigned int index = fCharIndex; index < fCharsAvail; index++)
{
fCharBuf[startInd] = fCharBuf[index];
fCharSizeBuf[startInd] = fCharSizeBuf[index];
startInd++;
}
}
//
// And then get more chars, starting after any spare chars that were
// left over from the last time.
//
fCharsAvail = xcodeMoreChars
(
&fCharBuf[startInd]
, &fCharSizeBuf[startInd]
, kCharBufSize - spareChars
);
// Add back in the spare chars
fCharsAvail += spareChars;
// Reset the buffer index to zero, so we start from the 0th char again
fCharIndex = 0;
//
// If no chars available, then we have to check for one last thing. If
// this is reader for a PE and its not being expanded inside a literal,
// then unget a trailing space. We use a boolean to avoid triggering
// this more than once.
//
if (!fCharsAvail
&& (fType == Type_PE)
&& (fRefFrom == RefFrom_NonLiteral)
&& !fSentTrailingSpace)
{
fCharBuf[0] = chSpace;
fCharsAvail = 1;
fSentTrailingSpace = true;
}
//
// If we are on our first block of chars and the encoding is one of the
// UTF-16 formats, then check the first char for the BOM and skip over
// it manually.
//
if (fCharsAvail)
{
if ((fCurLine == 1) && (fCurCol == 1))
{
if (((fEncoding == XMLRecognizer::UTF_16L)
|| (fEncoding == XMLRecognizer::UTF_16B))
&& !startInd)
{
if ((fCharBuf[startInd] == chUnicodeMarker)
|| (fCharBuf[startInd] == chSwappedUnicodeMarker))
{
fCharIndex++;
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
}
}
}
}
//
// If we get here with no more chars, then set the fNoMore flag which
// lets us optimize and know without checking that no more chars are
// available.
//
if (!fCharsAvail)
fNoMore = true;
return (fCharsAvail != 0);
}
// ---------------------------------------------------------------------------
// XMLReader: Scanning methods
// ---------------------------------------------------------------------------
bool XMLReader::getName(XMLBuffer& toFill, const bool token)
{
// Ok, first lets see if we have chars in the buffer. If not, then lets
// reload.
if (fCharIndex == fCharsAvail)
{
if (!refreshCharBuffer())
return false;
}
// Lets check the first char for being a first name char. If not, then
// what's the point in living mannnn? Just give up now. We only do this
// if its a name and not a name token that they want.
if (!token)
{
if (fXMLVersion == XMLV1_1 && ((fCharBuf[fCharIndex] >= 0xD800) && (fCharBuf[fCharIndex] <= 0xDB7F))) {
if ((fCharBuf[fCharIndex+1] < 0xDC00) || (fCharBuf[fCharIndex+1] > 0xDFFF))
return false;
// Looks ok, so lets eat it and put it in our buffer
toFill.append(fCharBuf[fCharIndex++]);
fCurCol++;
toFill.append(fCharBuf[fCharIndex++]);
fCurCol++;
}
else {
if (!isFirstNameChar(fCharBuf[fCharIndex]))
return false;
// Looks ok, so lets eat it and put it in our buffer. Update column also!
toFill.append(fCharBuf[fCharIndex++]);
fCurCol++;
}
}
// And now we loop until we run out of data in this reader or we hit
// a non-name char.
do {
while (fCharIndex < fCharsAvail)
{
// Check the current char and take it if its a name char. Else
// break out.
if (fXMLVersion == XMLV1_1 && ((fCharBuf[fCharIndex] >= 0xD800) && (fCharBuf[fCharIndex] <= 0xDB7F))) {
if ((fCharBuf[fCharIndex+1] < 0xDC00) || (fCharBuf[fCharIndex+1] > 0xDFFF))
return !toFill.isEmpty();
toFill.append(fCharBuf[fCharIndex++]);
fCurCol++;
toFill.append(fCharBuf[fCharIndex++]);
fCurCol++;
else {
if (!isNameChar(fCharBuf[fCharIndex]))
{
return !toFill.isEmpty();
}
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
}
// If we don't get no more, then break out.
} while (refreshCharBuffer());
return !toFill.isEmpty();
}
bool XMLReader::getSpaces(XMLBuffer& toFill)
{
//
// We just loop until we either hit a non-space or the end of this
// entity. We return true if we returned because of a non-space and
// false if because of end of entity.
//
// NOTE: We have to maintain line/col info here and we have to do
// whitespace normalization if we are not already internalized.
//
while (true)
{
// Loop through the current chars in the buffer
while (fCharIndex < fCharsAvail)
{
// Get the current char out of the buffer
XMLCh curCh = fCharBuf[fCharIndex];
//
// See if its a white space char. If so, then process it. Else
// we've hit a non-space and need to return.
//
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
{
// Eat this char
fCharIndex++;
//
// Ok, we've got some whitespace here. So we have to store
// it. But we have to normalize it and update the line and
// column info along the way.
//
if (curCh == chCR)
{
fCurCol = 1;
fCurLine++;
//
// If not already internalized, then convert it to an
// LF and eat any following LF.
//
if (fSource == Source_External)
{
if ((fCharIndex < fCharsAvail) || refreshCharBuffer())
{
if (fCharBuf[fCharIndex] == chLF
|| ((fCharBuf[fCharIndex] == chNEL) && fNEL))
fCharIndex++;
}
curCh = chLF;
}
}
else if (curCh == chLF
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
{
curCh = chLF;
fCurCol = 1;
fCurLine++;
}
else
{
fCurCol++;
}
// Ok we can add this guy to our buffer
toFill.append(curCh);
}
else
{
// Return true to indicate we broke out due to a whitespace
return true;
}
}
//
// We've eaten up the current buffer, so lets try to reload it. If
// we don't get anything new, then break out. If we do, then we go
// back to the top to keep getting spaces.
//
if (!refreshCharBuffer())
break;
}
return false;
}
bool XMLReader::getUpToCharOrWS(XMLBuffer& toFill, const XMLCh toCheck)
{
while (true)
{
// Loop through the current chars in the buffer
while (fCharIndex < fCharsAvail)
{
// Get the current char out of the buffer
XMLCh curCh = fCharBuf[fCharIndex];
//
// See if its not a white space or our target char, then process
// it. Else, we need to return.
//
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
{
// Eat this char
fCharIndex++;
//
// Ok, we've got some whitespace here. So we have to store
// it. But we have to normalize it and update the line and
// column info along the way.
//
if (curCh == chCR)
{
fCurCol = 1;
fCurLine++;
//
// If not already internalized, then convert it to an
// LF and eat any following LF.
//
if (fSource == Source_External)
{
if ((fCharIndex < fCharsAvail) || refreshCharBuffer())
{
if (fCharBuf[fCharIndex] == chLF
|| ((fCharBuf[fCharIndex] == chNEL) && fNEL))
fCharIndex++;
}
curCh = chLF;
}
}
else if (curCh == chLF
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
{
curCh = chLF;
fCurCol = 1;
fCurLine++;
}
else
{
fCurCol++;
}
// Add it to our buffer
toFill.append(curCh);
}
else
{
return true;
}
}
//
// We've eaten up the current buffer, so lets try to reload it. If
// we don't get anything new, then break out. If we do, then we go
// back to the top to keep getting spaces.
//
if (!refreshCharBuffer())
break;
}
// We never hit any non-space and ate up the whole reader
return false;
}
bool XMLReader::skipIfQuote(XMLCh& chGotten)
{
if (fCharIndex == fCharsAvail)
{
if (!refreshCharBuffer())
return false;
}
const XMLCh curCh = fCharBuf[fCharIndex];
if ((curCh == chDoubleQuote) || (curCh == chSingleQuote))
{
chGotten = curCh;
fCharIndex++;
fCurCol++;
return true;
}
return false;
}
bool XMLReader::skipSpaces(bool& skippedSomething)
{
// Remember the current line and column
Tinny Ng
committed
XMLSSize_t orgLine = fCurLine;
XMLSSize_t orgCol = fCurCol;
// We enter a loop where we skip over spaces until we hit the end of
// this reader or a non-space value. The return indicates whether we
// hit the non-space (true) or the end (false).
while (true)
{
// Loop through the current chars in the buffer
while (fCharIndex < fCharsAvail)
{
// See if its a white space char. If so, then process it. Else
// we've hit a non-space and need to return.
// Get the current char out of the buffer and eat it
XMLCh curCh = fCharBuf[fCharIndex++];
// Ok, we've got some whitespace here. So we have to store
// it. But we have to normalize it and update the line and
// column info along the way.
if (curCh == chCR)
{
fCurCol = 1;
fCurLine++;
// If not already internalized, then convert it to an
// LF and eat any following LF.
if (fSource == Source_External)
{
if ((fCharIndex < fCharsAvail) || refreshCharBuffer())
{
if (fCharBuf[fCharIndex] == chLF
|| ((fCharBuf[fCharIndex] == chNEL) && fNEL))
fCharIndex++;
}
}
}
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
{
skippedSomething = (orgLine != fCurLine) || (orgCol != fCurCol);
return true;
}
}
// We've eaten up the current buffer, so lets try to reload it. If
// we don't get anything new, then break out. If we do, then we go
// back to the top to keep getting spaces.
if (!refreshCharBuffer())
break;
}
// We never hit any non-space and ate up the whole reader
skippedSomething = (orgLine != fCurLine) || (orgCol != fCurCol);
return false;
}
bool XMLReader::skippedChar(const XMLCh toSkip)
{
//
// If the buffer is empty, then try to reload it. If we still get
// nothing, then return false.
//
if (fCharIndex == fCharsAvail)
{
if (!refreshCharBuffer())
return false;
}
//
// See if the current char is the one we want. If so, then we need
// to eat it and return true.
//
if (fCharBuf[fCharIndex] == toSkip)
{
fCharIndex++;
fCurCol++;
return true;
}
return false;
}
bool XMLReader::skippedSpace()
{
//
// If the buffer is empty, then try to reload it. If we still get
// nothing, then return false.
//
if (fCharIndex == fCharsAvail)
{
if (!refreshCharBuffer())
return false;
}
//
// See if the current char is a whitespace. If so, then we need to eat
// it and return true.
//
const XMLCh curCh = fCharBuf[fCharIndex];
{
// Eat the character
fCharIndex++;
if (curCh == chCR)
{
fCurLine++;
fCurCol = 1;
if (fSource == Source_External)
{
if ((fCharIndex < fCharsAvail) || refreshCharBuffer())
{
if (fCharBuf[fCharIndex] == chLF
|| ((fCharBuf[fCharIndex] == chNEL) && fNEL))
fCharIndex++;
}
}
}
else if (curCh == chLF