summaryrefslogtreecommitdiffstats
path: root/sax/source/expatwrap/xml2utf.cxx
blob: 1f044571d53d6609251513ea4d746e3dc5865aee (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
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
 * This file is part of the LibreOffice project.
 *
 * 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/.
 *
 * This file incorporates work covered by the following license notice:
 *
 *   Licensed to the Apache Software Foundation (ASF) under one or more
 *   contributor license agreements. See the NOTICE file distributed
 *   with this work for additional information regarding copyright
 *   ownership. The ASF licenses this file to you under the Apache
 *   License, Version 2.0 (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.apache.org/licenses/LICENSE-2.0 .
 */
#include <string.h>

#include <algorithm>

#include <sal/types.h>

#include <rtl/textenc.h>
#include <rtl/tencinfo.h>
#include <com/sun/star/io/NotConnectedException.hpp>
#include <com/sun/star/io/XInputStream.hpp>

using namespace ::com::sun::star::uno;
using namespace ::com::sun::star::io;


#include <xml2utf.hxx>
#include <memory>

namespace sax_expatwrap {

sal_Int32 XMLFile2UTFConverter::readAndConvert( Sequence<sal_Int8> &seq , sal_Int32 nMaxToRead )
{
    if( ! m_in.is() ) {
        throw NotConnectedException();
    }
    if( ! m_bStarted ) {
        // it should be possible to find the encoding attribute
        // within the first 512 bytes == 128 chars in UCS-4
        nMaxToRead = ::std::max( sal_Int32(512) , nMaxToRead );
    }

    sal_Int32 nRead;
    Sequence< sal_Int8 > seqStart;
    while( true )
    {
        nRead = m_in->readSomeBytes( seq , nMaxToRead );

        if( nRead + seqStart.getLength())
        {
            // if nRead is 0, the file is already eof.
            if( ! m_bStarted && nRead )
            {
                // ensure that enough data is available to parse encoding
                if( seqStart.hasElements() )
                {
                  // prefix with what we had so far.
                  sal_Int32 nLength = seq.getLength();
                  seq.realloc( seqStart.getLength() + nLength );

                  memmove (seq.getArray() + seqStart.getLength(),
                       seq.getConstArray(),
                       nLength);
                  memcpy  (seq.getArray(),
                       seqStart.getConstArray(),
                       seqStart.getLength());
                }

                // autodetection with the first bytes
                if( ! isEncodingRecognizable( seq ) )
                {
                  // remember what we have so far.
                  seqStart = seq;

                  // read more !
                  continue;
                }
                if( scanForEncoding( seq ) || !m_sEncoding.isEmpty() ) {
                    // initialize decoding
                    initializeDecoding();
                }
                seqStart = Sequence < sal_Int8 > ();
            }

            // do the encoding
            if( m_pText2Unicode && m_pUnicode2Text &&
                m_pText2Unicode->canContinue() ) {

                Sequence<sal_Unicode> seqUnicode = m_pText2Unicode->convert( seq );
                seq = m_pUnicode2Text->convert( seqUnicode.getConstArray(), seqUnicode.getLength() );
            }

            if( ! m_bStarted )
            {
                // it must now be ensured, that no encoding attribute exist anymore
                // ( otherwise the expat-Parser will crash )
                // This must be done after decoding !
                // ( e.g. Files decoded in ucs-4 cannot be read properly )
                m_bStarted = true;
                removeEncoding( seq );
            }
            nRead = seq.getLength();
        }

        break;
    }
    return nRead;
}

void XMLFile2UTFConverter::removeEncoding( Sequence<sal_Int8> &seq )
{
    const sal_Int8 *pSource = seq.getArray();
    if (seq.getLength() < 5 || strncmp(reinterpret_cast<const char *>(pSource), "<?xml", 5))
        return;

    // scan for encoding
    OString str( reinterpret_cast<char const *>(pSource), seq.getLength() );

    // cut sequence to first line break
    // find first line break;
    int nMax = str.indexOf( 10 );
    if( nMax >= 0 )
    {
        str = str.copy( 0 , nMax );
    }

    int nFound = str.indexOf( " encoding" );
    if( nFound < 0 )        return;

    int nStop;
    int nStart = str.indexOf( "\"" , nFound );
    if( nStart < 0 || str.indexOf( "'" , nFound ) < nStart )
    {
        nStart = str.indexOf( "'" , nFound );
        nStop  = str.indexOf( "'" , nStart +1 );
    }
    else
    {
        nStop  = str.indexOf( "\"" , nStart +1);
    }

    if( nStart >= 0 && nStop >= 0 && nStart+1 < nStop )
    {
        // remove encoding tag from file
        memmove(        &( seq.getArray()[nFound] ) ,
                        &( seq.getArray()[nStop+1]) ,
                        seq.getLength() - nStop -1);
        seq.realloc( seq.getLength() - ( nStop+1 - nFound ) );
    }
}

// Checks, if enough data has been accumulated to recognize the encoding
bool XMLFile2UTFConverter::isEncodingRecognizable( const Sequence< sal_Int8 > &seq)
{
    const sal_Int8 *pSource = seq.getConstArray();
    bool bCheckIfFirstClosingBracketExists = false;

    if( seq.getLength() < 8 ) {
        // no recognition possible, when less than 8 bytes are available
        return false;
    }

    if( ! strncmp( reinterpret_cast<const char *>(pSource), "<?xml", 5 ) ) {
        // scan if the <?xml tag finishes within this buffer
        bCheckIfFirstClosingBracketExists = true;
    }
    else if( ('<' == pSource[0] || '<' == pSource[2] ) &&
             ('?' == pSource[4] || '?' == pSource[6] ) )
    {
        // check for utf-16
        bCheckIfFirstClosingBracketExists = true;
    }
    else if( ( '<' == pSource[1] || '<' == pSource[3] ) &&
             ( '?' == pSource[5] || '?' == pSource[7] ) )
    {
        // check for
        bCheckIfFirstClosingBracketExists = true;
    }

    if( bCheckIfFirstClosingBracketExists )
    {
        // whole <?xml tag is valid
        return std::find(seq.begin(), seq.end(), '>') != seq.end();
    }

    // No <? tag in front, no need for a bigger buffer
    return true;
}

bool XMLFile2UTFConverter::scanForEncoding( Sequence< sal_Int8 > &seq )
{
    const sal_uInt8 *pSource = reinterpret_cast<const sal_uInt8*>( seq.getConstArray() );
    bool bReturn = true;

    if( seq.getLength() < 4 ) {
        // no recognition possible, when less than 4 bytes are available
        return false;
    }

    // first level : detect possible file formats
    if (seq.getLength() >= 5 && !strncmp(reinterpret_cast<const char *>(pSource), "<?xml", 5)) {
        // scan for encoding
        OString str( reinterpret_cast<const char *>(pSource), seq.getLength() );

        // cut sequence to first line break
        //find first line break;
        int nMax = str.indexOf( 10 );
        if( nMax >= 0 )
        {
            str = str.copy( 0 , nMax );
        }

        int nFound = str.indexOf( " encoding" );
        if( nFound >= 0 ) {
            int nStop;
            int nStart = str.indexOf( "\"" , nFound );
            if( nStart < 0 || str.indexOf( "'" , nFound ) < nStart )
            {
                nStart = str.indexOf( "'" , nFound );
                nStop  = str.indexOf( "'" , nStart +1 );
            }
            else
            {
                nStop  = str.indexOf( "\"" , nStart +1);
            }
            if( nStart >= 0 && nStop >= 0 && nStart+1 < nStop )
            {
                // encoding found finally
                m_sEncoding = str.copy( nStart+1 , nStop - nStart - 1 );
            }
        }
    }
    else if( 0xFE == pSource[0] &&
             0xFF == pSource[1] ) {
        // UTF-16 big endian
        // conversion is done so that encoding information can be easily extracted
        m_sEncoding = "utf-16";
    }
    else if( 0xFF == pSource[0] &&
             0xFE == pSource[1] ) {
        // UTF-16 little endian
        // conversion is done so that encoding information can be easily extracted
        m_sEncoding = "utf-16";
    }
    else if( 0x00 == pSource[0] && 0x3c == pSource[1]  && 0x00 == pSource[2] && 0x3f == pSource[3] ) {
        // UTF-16 big endian without byte order mark (this is (strictly speaking) an error.)
        // The byte order mark is simply added

        // simply add the byte order mark !
        seq.realloc( seq.getLength() + 2 );
        memmove( &( seq.getArray()[2] ) , seq.getArray() , seq.getLength() - 2 );
        reinterpret_cast<sal_uInt8*>(seq.getArray())[0] = 0xFE;
        reinterpret_cast<sal_uInt8*>(seq.getArray())[1] = 0xFF;

        m_sEncoding = "utf-16";
    }
    else if( 0x3c == pSource[0] && 0x00 == pSource[1]  && 0x3f == pSource[2] && 0x00 == pSource[3] ) {
        // UTF-16 little endian without byte order mark (this is (strictly speaking) an error.)
        // The byte order mark is simply added

        seq.realloc( seq.getLength() + 2 );
        memmove( &( seq.getArray()[2] ) , seq.getArray() , seq.getLength() - 2 );
        reinterpret_cast<sal_uInt8*>(seq.getArray())[0] = 0xFF;
        reinterpret_cast<sal_uInt8*>(seq.getArray())[1] = 0xFE;

        m_sEncoding = "utf-16";
    }
    else if( 0xEF == pSource[0] &&
             0xBB == pSource[1] &&
             0xBF == pSource[2] )
    {
        // UTF-8 BOM (byte order mark); signifies utf-8, and not byte order
        // The BOM is removed.
        memmove( seq.getArray(), &( seq.getArray()[3] ), seq.getLength()-3 );
        seq.realloc( seq.getLength() - 3 );
        m_sEncoding = "utf-8";
    }
    else if( 0x00 == pSource[0] && 0x00 == pSource[1]  && 0x00 == pSource[2] && 0x3c == pSource[3] ) {
        // UCS-4 big endian
        m_sEncoding = "ucs-4";
    }
    else if( 0x3c == pSource[0] && 0x00 == pSource[1]  && 0x00 == pSource[2] && 0x00 == pSource[3] ) {
        // UCS-4 little endian
        m_sEncoding = "ucs-4";
    }
/* TODO: no need to test for the moment since we return sal_False like default case anyway
    else if( 0x4c == pSource[0] && 0x6f == pSource[1]  &&
             0xa7 == static_cast<unsigned char> (pSource[2]) &&
             0x94 == static_cast<unsigned char> (pSource[3]) ) {
        // EBCDIC
        bReturn = sal_False;   // must be extended
    }
*/
    else {
        // other
        // UTF8 is directly recognized by the parser.
        bReturn = false;
    }

    return bReturn;
}

void XMLFile2UTFConverter::initializeDecoding()
{

    if( !m_sEncoding.isEmpty() )
    {
        rtl_TextEncoding encoding = rtl_getTextEncodingFromMimeCharset( m_sEncoding.getStr() );
        if( encoding != RTL_TEXTENCODING_UTF8 )
        {
            m_pText2Unicode = std::make_unique<Text2UnicodeConverter>( m_sEncoding );
            m_pUnicode2Text = std::make_unique<Unicode2TextConverter>( RTL_TEXTENCODING_UTF8 );
        }
    }
}


// Text2UnicodeConverter


Text2UnicodeConverter::Text2UnicodeConverter( const OString &sEncoding )
    : m_convText2Unicode(nullptr)
    , m_contextText2Unicode(nullptr)
{
    rtl_TextEncoding encoding = rtl_getTextEncodingFromMimeCharset( sEncoding.getStr() );
    if( RTL_TEXTENCODING_DONTKNOW == encoding )
    {
        m_bCanContinue = false;
        m_bInitialized = false;
    }
    else
    {
        init( encoding );
    }
}

Text2UnicodeConverter::~Text2UnicodeConverter()
{
    if( m_bInitialized )
    {
        rtl_destroyTextToUnicodeContext( m_convText2Unicode , m_contextText2Unicode );
        rtl_destroyUnicodeToTextConverter( m_convText2Unicode );
    }
}

void Text2UnicodeConverter::init( rtl_TextEncoding encoding )
{
    m_bCanContinue = true;
    m_bInitialized = true;

    m_convText2Unicode  = rtl_createTextToUnicodeConverter(encoding);
    m_contextText2Unicode = rtl_createTextToUnicodeContext( m_convText2Unicode );
}


Sequence<sal_Unicode> Text2UnicodeConverter::convert( const Sequence<sal_Int8> &seqText )
{
    sal_uInt32 uiInfo;
    sal_Size nSrcCvtBytes   = 0;
    sal_Size nTargetCount   = 0;
    sal_Size nSourceCount   = 0;

    // the whole source size
    sal_Int32   nSourceSize = seqText.getLength() + m_seqSource.getLength();
    Sequence<sal_Unicode>   seqUnicode ( nSourceSize );

    const sal_Int8 *pbSource = seqText.getConstArray();
    std::unique_ptr<sal_Int8[]> pbTempMem;

    if( m_seqSource.hasElements() ) {
        // put old rest and new byte sequence into one array
        pbTempMem.reset(new sal_Int8[ nSourceSize ]);
        memcpy( pbTempMem.get() , m_seqSource.getConstArray() , m_seqSource.getLength() );
        memcpy( &(pbTempMem[ m_seqSource.getLength() ]) , seqText.getConstArray() , seqText.getLength() );
        pbSource = pbTempMem.get();

        // set to zero again
        m_seqSource = Sequence< sal_Int8 >();
    }

    while( true ) {

        /* All invalid characters are transformed to the unicode undefined char */
        nTargetCount +=     rtl_convertTextToUnicode(
                                    m_convText2Unicode,
                                    m_contextText2Unicode,
                                    reinterpret_cast<const char *>(&( pbSource[nSourceCount] )),
                                    nSourceSize - nSourceCount ,
                                    &( seqUnicode.getArray()[ nTargetCount ] ),
                                    seqUnicode.getLength() - nTargetCount,
                                    RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_DEFAULT   |
                                    RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_DEFAULT |
                                    RTL_TEXTTOUNICODE_FLAGS_INVALID_DEFAULT,
                                    &uiInfo,
                                    &nSrcCvtBytes );
        nSourceCount += nSrcCvtBytes;

        if( uiInfo & RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOOSMALL ) {
            // save necessary bytes for next conversion
            seqUnicode.realloc( seqUnicode.getLength() * 2 );
            continue;
        }
        break;
    }
    if( uiInfo & RTL_TEXTTOUNICODE_INFO_SRCBUFFERTOOSMALL ) {
        m_seqSource.realloc( nSourceSize - nSourceCount );
        memcpy( m_seqSource.getArray() , &(pbSource[nSourceCount]) , nSourceSize-nSourceCount );
    }

    // set to correct unicode size
    seqUnicode.realloc( nTargetCount );

    return seqUnicode;
}


// Unicode2TextConverter


Unicode2TextConverter::Unicode2TextConverter( rtl_TextEncoding encoding )
{
    m_convUnicode2Text  = rtl_createUnicodeToTextConverter( encoding );
    m_contextUnicode2Text = rtl_createUnicodeToTextContext( m_convUnicode2Text );
}


Unicode2TextConverter::~Unicode2TextConverter()
{
    rtl_destroyUnicodeToTextContext( m_convUnicode2Text , m_contextUnicode2Text );
    rtl_destroyUnicodeToTextConverter( m_convUnicode2Text );
}


Sequence<sal_Int8> Unicode2TextConverter::convert(const sal_Unicode *puSource , sal_Int32 nSourceSize)
{
    std::unique_ptr<sal_Unicode[]> puTempMem;

    if( m_seqSource.hasElements() ) {
        // For surrogates !
        // put old rest and new byte sequence into one array
        // In general when surrogates are used, they should be rarely
        // cut off between two convert()-calls. So this code is used
        // rarely and the extra copy is acceptable.
        puTempMem.reset(new sal_Unicode[ nSourceSize + m_seqSource.getLength()]);
        memcpy( puTempMem.get() ,
                m_seqSource.getConstArray() ,
                m_seqSource.getLength() * sizeof( sal_Unicode ) );
        memcpy(
            &(puTempMem[ m_seqSource.getLength() ]) ,
            puSource ,
            nSourceSize*sizeof( sal_Unicode ) );
        puSource = puTempMem.get();
        nSourceSize += m_seqSource.getLength();

        m_seqSource = Sequence< sal_Unicode > ();
    }


    sal_Size nTargetCount = 0;
    sal_Size nSourceCount = 0;

    sal_uInt32 uiInfo;
    sal_Size nSrcCvtChars;

    // take nSourceSize * 3 as preference
    // this is an upper boundary for converting to utf8,
    // which most often used as the target.
    sal_Int32 nSeqSize =  nSourceSize * 3;

    Sequence<sal_Int8>  seqText( nSeqSize );
    char *pTarget = reinterpret_cast<char *>(seqText.getArray());
    while( true ) {

        nTargetCount += rtl_convertUnicodeToText(
                                    m_convUnicode2Text,
                                    m_contextUnicode2Text,
                                    &( puSource[nSourceCount] ),
                                    nSourceSize - nSourceCount ,
                                    &( pTarget[nTargetCount] ),
                                    nSeqSize - nTargetCount,
                                    RTL_UNICODETOTEXT_FLAGS_UNDEFINED_DEFAULT |
                                    RTL_UNICODETOTEXT_FLAGS_INVALID_DEFAULT ,
                                    &uiInfo,
                                    &nSrcCvtChars);
        nSourceCount += nSrcCvtChars;

        if( uiInfo & RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL ) {
            nSeqSize = nSeqSize *2;
            seqText.realloc( nSeqSize );  // double array size
            pTarget = reinterpret_cast<char *>(seqText.getArray());
            continue;
        }
        break;
    }

    // for surrogates
    if( uiInfo & RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL ) {
        m_seqSource.realloc( nSourceSize - nSourceCount );
        memcpy( m_seqSource.getArray() ,
                &(puSource[nSourceCount]),
                (nSourceSize - nSourceCount) * sizeof( sal_Unicode ) );
    }

    // reduce the size of the buffer (fast, no copy necessary)
    seqText.realloc( nTargetCount );

    return seqText;
}

}

/* vim:set shiftwidth=4 softtabstop=4 expandtab: */