summaryrefslogtreecommitdiff
path: root/svtools/source/svrtf/parrtf.cxx
blob: 1c578d1603079dc71007deb85976f543189b3798 (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
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
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
461
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
501
502
503
504
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
570
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
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
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
685
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
/*************************************************************************
 *
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * Copyright 2000, 2010 Oracle and/or its affiliates.
 *
 * OpenOffice.org - a multi-platform office productivity suite
 *
 * This file is part of OpenOffice.org.
 *
 * OpenOffice.org is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License version 3
 * only, as published by the Free Software Foundation.
 *
 * OpenOffice.org is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License version 3 for more details
 * (a copy is included in the LICENSE file that accompanied this code).
 *
 * You should have received a copy of the GNU Lesser General Public License
 * version 3 along with OpenOffice.org.  If not, see
 * <http://www.openoffice.org/license.html>
 * for a copy of the LGPLv3 License.
 *
 ************************************************************************/

// MARKER(update_precomp.py): autogen include statement, do not remove
#include "precompiled_svtools.hxx"

/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil -*- */

#include <stdio.h>                      // for EOF
#include <rtl/tencinfo.h>
#include <tools/stream.hxx>
#include <tools/debug.hxx>
#include "rtftoken.h"
#include "rtfkeywd.hxx"
#include <svtools/parrtf.hxx>

const int MAX_STRING_LEN = 1024;
const int MAX_TOKEN_LEN = 128;

#define RTF_ISDIGIT( c ) (c >= '0' && c <= '9')
#define RTF_ISALPHA( c ) ( (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') )

SV_IMPL_VARARR( RtfParserStates_Impl, RtfParserState_Impl )

SvRTFParser::SvRTFParser( SvStream& rIn, BYTE nStackSize )
    : SvParser( rIn, nStackSize ),
    eUNICodeSet( RTL_TEXTENCODING_MS_1252 ),    // default ist ANSI-CodeSet
    nUCharOverread( 1 )
{
    // default ist ANSI-CodeSet
    SetSrcEncoding( RTL_TEXTENCODING_MS_1252 );
    bRTF_InTextRead = false;
}

SvRTFParser::~SvRTFParser()
{
}




int SvRTFParser::_GetNextToken()
{
    int nRet = 0;
    do {
        int bNextCh = true;
        switch( nNextCh )
        {
        case '\\':
            {
                // Steuerzeichen
                switch( nNextCh = GetNextChar() )
                {
                case '{':
                case '}':
                case '\\':
                case '+':       // habe ich in einem RTF-File gefunden
                case '~':       // nonbreaking space
                case '-':       // optional hyphen
                case '_':       // nonbreaking hyphen
                case '\'':      // HexValue
                    nNextCh = '\\';
                    rInput.SeekRel( -1 );
                    ScanText();
                    nRet = RTF_TEXTTOKEN;
                    bNextCh = 0 == nNextCh;
                    break;

                case '*':       // ignoreflag
                    nRet = RTF_IGNOREFLAG;
                    break;
                case ':':       // subentry in an index entry
                    nRet = RTF_SUBENTRYINDEX;
                    break;
                case '|':       // formula-charakter
                    nRet = RTF_FORMULA;
                    break;

                case 0x0a:
                case 0x0d:
                    nRet = RTF_PAR;
                    break;

                default:
                    if( RTF_ISALPHA( nNextCh ) )
                    {
                        aToken = '\\';
                        {
                            String aStrBuffer;
                            sal_Unicode* pStr = aStrBuffer.AllocBuffer(
                                                            MAX_TOKEN_LEN );
                            xub_StrLen nStrLen = 0;
                            do {
                                *(pStr + nStrLen++) = nNextCh;
                                if( MAX_TOKEN_LEN == nStrLen )
                                {
                                    aToken += aStrBuffer;
                                    aToken.GetBufferAccess();  // make unique string!
                                    nStrLen = 0;
                                }
                                nNextCh = GetNextChar();
                            } while( RTF_ISALPHA( nNextCh ) );
                            if( nStrLen )
                            {
                                aStrBuffer.ReleaseBufferAccess( nStrLen );
                                aToken += aStrBuffer;
                            }
                        }

                        // Minus fuer numerischen Parameter
                        int bNegValue = false;
                        if( '-' == nNextCh )
                        {
                            bNegValue = true;
                            nNextCh = GetNextChar();
                        }

                        // evt. Numerischer Parameter
                        if( RTF_ISDIGIT( nNextCh ) )
                        {
                            nTokenValue = 0;
                            do {
                                nTokenValue *= 10;
                                nTokenValue += nNextCh - '0';
                                nNextCh = GetNextChar();
                            } while( RTF_ISDIGIT( nNextCh ) );
                            if( bNegValue )
                                nTokenValue = -nTokenValue;
                            bTokenHasValue=true;
                        }
                        else if( bNegValue )        // das Minus wieder zurueck
                        {
                            nNextCh = '-';
                            rInput.SeekRel( -1 );
                        }
                        if( ' ' == nNextCh )        // Blank gehoert zum Token!
                            nNextCh = GetNextChar();

                        // suche das Token in der Tabelle:
                        if( 0 == (nRet = GetRTFToken( aToken )) )
                            // Unknown Control
                            nRet = RTF_UNKNOWNCONTROL;

                        // bug 76812 - unicode token handled as normal text
                        bNextCh = false;
                        switch( nRet )
                        {
                        case RTF_UC:
                            if( 0 <= nTokenValue )
                            {
                                nUCharOverread = (BYTE)nTokenValue;
#if 1
                                //cmc: other ifdef breaks #i3584
                                aParserStates[ aParserStates.Count()-1].
                                    nUCharOverread = nUCharOverread;
#else
                                if( !nUCharOverread )
                                    nUCharOverread = aParserStates[
                                        aParserStates.Count()-1].nUCharOverread;
                                else
                                    aParserStates[ aParserStates.Count()-1].
                                        nUCharOverread = nUCharOverread;
#endif
                            }
                            aToken.Erase(); // #i47831# erase token to prevent the token from beeing treated as text
                            // read next token
                            nRet = 0;
                            break;

                        case RTF_UPR:
                            if (!_inSkipGroup) {
                            // UPR - overread the group with the ansi
                            //       informations
                            while( '{' != _GetNextToken() )
                                ;
                            SkipGroup();
                            _GetNextToken();  // overread the last bracket
                            nRet = 0;
                            }
                            break;

                        case RTF_U:
                            if( !bRTF_InTextRead )
                            {
                                nRet = RTF_TEXTTOKEN;
                                aToken = (sal_Unicode)nTokenValue;

                                // overread the next n "RTF" characters. This
                                // can be also \{, \}, \'88
                                for( BYTE m = 0; m < nUCharOverread; ++m )
                                {
                                    sal_Unicode cAnsi = nNextCh;
                                    while( 0xD == cAnsi )
                                        cAnsi = GetNextChar();
                                    while( 0xA == cAnsi )
                                        cAnsi = GetNextChar();

                                    if( '\\' == cAnsi &&
                                        '\'' == ( cAnsi = GetNextChar() ))
                                        // HexValue ueberlesen
                                        cAnsi = GetHexValue();
                                    nNextCh = GetNextChar();
                                }
                                ScanText();
                                bNextCh = 0 == nNextCh;
                            }
                            break;
                        }
                    }
                    else if( SVPAR_PENDING != eState )
                    {
                        // Bug 34631 - "\ " ueberlesen - Blank als Zeichen
                        // eState = SVPAR_ERROR;
                        bNextCh = false;
                    }
                    break;
                }
            }
            break;

        case sal_Unicode(EOF):
            eState = SVPAR_ACCEPTED;
            nRet = nNextCh;
            break;

        case '{':
            {
                if( 0 <= nOpenBrakets )
                {
                    RtfParserState_Impl aState( nUCharOverread, GetSrcEncoding() );
                    aParserStates.Insert(
                        aState, sal::static_int_cast< USHORT >(nOpenBrakets) );
                }
                ++nOpenBrakets;
                DBG_ASSERT( nOpenBrakets == aParserStates.Count(),
                            "ParserStateStack unequal to bracket count" );
                nRet = nNextCh;
            }
            break;

        case '}':
            --nOpenBrakets;
            if( 0 <= nOpenBrakets )
            {
                aParserStates.Remove(
                    sal::static_int_cast< USHORT >(nOpenBrakets) );
                if( aParserStates.Count() )
                {
                    const RtfParserState_Impl& rRPS =
                            aParserStates[ aParserStates.Count() - 1 ];
                    nUCharOverread = rRPS.nUCharOverread;
                    SetSrcEncoding( rRPS.eCodeSet );
                }
                else
                {
                    nUCharOverread = 1;
                    SetSrcEncoding( GetCodeSet() );
                }
            }
            DBG_ASSERT( nOpenBrakets == aParserStates.Count(),
                        "ParserStateStack unequal to bracket count" );
            nRet = nNextCh;
            break;

        case 0x0d:
        case 0x0a:
            break;

        default:
            // es folgt normaler Text
            ScanText();
            nRet = RTF_TEXTTOKEN;
            bNextCh = 0 == nNextCh;
            break;
        }

        if( bNextCh )
            nNextCh = GetNextChar();

    } while( !nRet && SVPAR_WORKING == eState );
    return nRet;
}


sal_Unicode SvRTFParser::GetHexValue()
{
    // Hex-Wert sammeln
    register int n;
    register sal_Unicode nHexVal = 0;

    for( n = 0; n < 2; ++n )
    {
        nHexVal *= 16;
        nNextCh = GetNextChar();
        if( nNextCh >= '0' && nNextCh <= '9' )
            nHexVal += (nNextCh - 48);
        else if( nNextCh >= 'a' && nNextCh <= 'f' )
            nHexVal += (nNextCh - 87);
        else if( nNextCh >= 'A' && nNextCh <= 'F' )
            nHexVal += (nNextCh - 55);
    }
    return nHexVal;
}

void SvRTFParser::ScanText( const sal_Unicode cBreak )
{
    String aStrBuffer;
    int bWeiter = true;
    while( bWeiter && IsParserWorking() && aStrBuffer.Len() < MAX_STRING_LEN)
    {
        int bNextCh = true;
        switch( nNextCh )
        {
        case '\\':
            {
                switch (nNextCh = GetNextChar())
                {
                case '\'':
                    {

#if 0
                        // #i35653 patch from cmc
                        ByteString aByteString(static_cast<char>(GetHexValue()));
                        if (aByteString.Len())
                            aStrBuffer.Append(String(aByteString, GetSrcEncoding()));
#else
                        ByteString aByteString;
                        while (1)
                        {
                            aByteString.Append((char)GetHexValue());

                            bool bBreak = false;
                            sal_Char nSlash = '\\';
                            while (!bBreak)
                            {
                                wchar_t __next=GetNextChar();
                                if (__next>0xFF) // fix for #i43933# and #i35653#
                                {
                                    if (aByteString.Len())
                                        aStrBuffer.Append(String(aByteString, GetSrcEncoding()));
                                    aStrBuffer.Append((sal_Unicode)__next);

                                    aByteString.Erase();
                                    continue;
                                }
                                nSlash = (sal_Char)__next;
                                while (nSlash == 0xD || nSlash == 0xA)
                                    nSlash = (sal_Char)GetNextChar();

                                switch (nSlash)
                                {
                                    case '{':
                                    case '}':
                                    case '\\':
                                        bBreak = true;
                                        break;
                                    default:
                                        aByteString.Append(nSlash);
                                        break;
                                }
                            }

                            nNextCh = GetNextChar();

                            if (nSlash != '\\' || nNextCh != '\'')
                            {
                                rInput.SeekRel(-1);
                                nNextCh = nSlash;
                                break;
                            }
                        }

                        bNextCh = false;

                        if (aByteString.Len())
                            aStrBuffer.Append(String(aByteString, GetSrcEncoding()));
#endif
                    }
                    break;
                case '\\':
                case '}':
                case '{':
                case '+':       // habe ich in einem RTF-File gefunden
                    aStrBuffer.Append(nNextCh);
                    break;
                case '~':       // nonbreaking space
                    aStrBuffer.Append(static_cast< sal_Unicode >(0xA0));
                    break;
                case '-':       // optional hyphen
                    aStrBuffer.Append(static_cast< sal_Unicode >(0xAD));
                    break;
                case '_':       // nonbreaking hyphen
                    aStrBuffer.Append(static_cast< sal_Unicode >(0x2011));
                    break;

                case 'u':
                    // UNI-Code Zeichen lesen
                    {
                        nNextCh = GetNextChar();
                        rInput.SeekRel( -2 );

                        if( '-' == nNextCh || RTF_ISDIGIT( nNextCh ) )
                        {
                            bRTF_InTextRead = true;

                            String sSave( aToken );
                            nNextCh = '\\';
                            #ifdef DBG_UTIL
                            int nToken =
                            #endif
                                _GetNextToken();
                            DBG_ASSERT( RTF_U == nToken, "doch kein UNI-Code Zeichen" );
                            // dont convert symbol chars
                            aStrBuffer.Append(
                                static_cast< sal_Unicode >(nTokenValue));

                            // overread the next n "RTF" characters. This
                            // can be also \{, \}, \'88
                            for( BYTE m = 0; m < nUCharOverread; ++m )
                            {
                                sal_Unicode cAnsi = nNextCh;
                                while( 0xD == cAnsi )
                                    cAnsi = GetNextChar();
                                while( 0xA == cAnsi )
                                    cAnsi = GetNextChar();

                                if( '\\' == cAnsi &&
                                    '\'' == ( cAnsi = GetNextChar() ))
                                    // HexValue ueberlesen
                                    cAnsi = GetHexValue();
                                nNextCh = GetNextChar();
                            }
                            bNextCh = false;
                            aToken = sSave;
                            bRTF_InTextRead = false;
                        }
                        else
                        {
                            nNextCh = '\\';
                            bWeiter = false;        // Abbrechen, String zusammen
                        }
                    }
                    break;

                default:
                    rInput.SeekRel( -1 );
                    nNextCh = '\\';
                    bWeiter = false;        // Abbrechen, String zusammen
                    break;
                }
            }
            break;

        case sal_Unicode(EOF):
                eState = SVPAR_ERROR;
                // weiter
        case '{':
        case '}':
            bWeiter = false;
            break;

        case 0x0a:
        case 0x0d:
            break;

        default:
            if( nNextCh == cBreak || aStrBuffer.Len() >= MAX_STRING_LEN)
                bWeiter = false;
            else
            {
                do {
                    // alle anderen Zeichen kommen in den Text
                    aStrBuffer.Append(nNextCh);

                    if (sal_Unicode(EOF) == (nNextCh = GetNextChar()))
                    {
                        if (aStrBuffer.Len())
                            aToken += aStrBuffer;
                        return;
                    }
                } while
                (
                    (RTF_ISALPHA(nNextCh) || RTF_ISDIGIT(nNextCh)) &&
                    (aStrBuffer.Len() < MAX_STRING_LEN)
                );
                bNextCh = false;
            }
        }

        if( bWeiter && bNextCh )
            nNextCh = GetNextChar();
    }

    if (aStrBuffer.Len())
        aToken += aStrBuffer;
}


short SvRTFParser::_inSkipGroup=0;

void SvRTFParser::SkipGroup()
{
short nBrackets=1;
if (_inSkipGroup>0)
    return;
_inSkipGroup++;
#if 1   //#i16185# fecking \bin keyword
    do
    {
        switch (nNextCh)
        {
            case '{':
                ++nBrackets;
                break;
            case '}':
                if (!--nBrackets) {
                    _inSkipGroup--;
                    return;
                }
                break;
        }
        int nToken = _GetNextToken();
        if (nToken == RTF_BIN)
        {
            rInput.SeekRel(-1);
            rInput.SeekRel(nTokenValue);
            nNextCh = GetNextChar();
        }
        while (nNextCh==0xa || nNextCh==0xd)
        {
            nNextCh = GetNextChar();
        }
    } while (sal_Unicode(EOF) != nNextCh && IsParserWorking());
#else
    sal_Unicode cPrev = 0;
    do {
        switch( nNextCh )
        {
        case '{':
            if( '\\' != cPrev )
                ++nBrackets;
            break;

        case '}':
            if( '\\' != cPrev && !--nBrackets )
                return;
            break;

        case '\\':
            if( '\\' == cPrev )
                nNextCh = 0;
            break;
        }
        cPrev = nNextCh;
        nNextCh = GetNextChar();
    } while( sal_Unicode(EOF) != nNextCh && IsParserWorking() );
#endif

    if( SVPAR_PENDING != eState && '}' != nNextCh )
        eState = SVPAR_ERROR;
    _inSkipGroup--;
}

void SvRTFParser::ReadUnknownData() { SkipGroup(); }
void SvRTFParser::ReadBitmapData()  { SkipGroup(); }
void SvRTFParser::ReadOLEData()     { SkipGroup(); }


SvParserState SvRTFParser::CallParser()
{
    sal_Char cFirstCh;
    nNextChPos = rInput.Tell();
    rInput >> cFirstCh; nNextCh = cFirstCh;
    eState = SVPAR_WORKING;
    nOpenBrakets = 0;
    SetSrcEncoding( eCodeSet = RTL_TEXTENCODING_MS_1252 );
    eUNICodeSet = RTL_TEXTENCODING_MS_1252;     // default ist ANSI-CodeSet

    // die 1. beiden Token muessen '{' und \\rtf sein !!
    if( '{' == GetNextToken() && RTF_RTF == GetNextToken() )
    {
        AddRef();
        Continue( 0 );
        if( SVPAR_PENDING != eState )
            ReleaseRef();       // dann brauchen wir den Parser nicht mehr!
    }
    else
        eState = SVPAR_ERROR;

    return eState;
}

void SvRTFParser::Continue( int nToken )
{
//  DBG_ASSERT( SVPAR_CS_DONTKNOW == GetCharSet(),
//              "Zeichensatz wurde geaendert." );

    if( !nToken )
        nToken = GetNextToken();

    while( IsParserWorking() )
    {
        SaveState( nToken );
        switch( nToken )
        {
        case '}':
            if( nOpenBrakets )
                goto NEXTTOKEN;
            eState = SVPAR_ACCEPTED;
            break;

        case '{':
            // eine unbekannte Gruppe ?
            {
                if( RTF_IGNOREFLAG != GetNextToken() )
                    nToken = SkipToken( -1 );
                else if( RTF_UNKNOWNCONTROL != GetNextToken() )
                    nToken = SkipToken( -2 );
                else
                {
                    // gleich herausfiltern
                    ReadUnknownData();
                    nToken = GetNextToken();
                    if( '}' != nToken )
                        eState = SVPAR_ERROR;
                    break;      // auf zum naechsten Token!!
                }
            }
            goto NEXTTOKEN;

        case RTF_UNKNOWNCONTROL:
            break;      // unbekannte Token ueberspringen
        case RTF_NEXTTYPE:
        case RTF_ANSITYPE:
            SetSrcEncoding( eCodeSet = RTL_TEXTENCODING_MS_1252 );
            break;
        case RTF_MACTYPE:
            SetSrcEncoding( eCodeSet = RTL_TEXTENCODING_APPLE_ROMAN );
            break;
        case RTF_PCTYPE:
            SetSrcEncoding( eCodeSet = RTL_TEXTENCODING_IBM_437 );
            break;
        case RTF_PCATYPE:
            SetSrcEncoding( eCodeSet = RTL_TEXTENCODING_IBM_850 );
            break;
        case RTF_ANSICPG:
            eCodeSet = rtl_getTextEncodingFromWindowsCodePage(nTokenValue);
            SetSrcEncoding(eCodeSet);
            break;
        default:
NEXTTOKEN:
            NextToken( nToken );
            break;
        }
        if( IsParserWorking() )
            SaveState( 0 );         // bis hierhin abgearbeitet,
                                    // weiter mit neuem Token!
        nToken = GetNextToken();
    }
    if( SVPAR_ACCEPTED == eState && 0 < nOpenBrakets )
        eState = SVPAR_ERROR;
}

void SvRTFParser::SetEncoding( rtl_TextEncoding eEnc )
{
    if (eEnc == RTL_TEXTENCODING_DONTKNOW)
        eEnc = GetCodeSet();

    if (aParserStates.Count())
        aParserStates[aParserStates.Count() - 1].eCodeSet = eEnc;
    SetSrcEncoding(eEnc);
}

#ifdef USED
void SvRTFParser::SaveState( int nToken )
{
    SvParser::SaveState( nToken );
}

void SvRTFParser::RestoreState()
{
    SvParser::RestoreState();
}
#endif

/* vi:set tabstop=4 shiftwidth=4 expandtab: */