summaryrefslogtreecommitdiffstats
path: root/binfilter/bf_svtools/source/misc/tl_strascii.cxx
blob: 4baf7ef7d4b4e60d2d1f8c8b59129079ca1394b0 (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
/* -*- 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 .
 */

namespace binfilter
{

#ifdef DBG_UTIL

static sal_Bool ImplDbgCheckAsciiStr( const sal_Char* pAsciiStr, sal_Int32 nLen )
{
    while ( nLen && *pAsciiStr )
    {
        if ( ((unsigned char)*pAsciiStr) > 127 )
            return sal_False;
        ++pAsciiStr,
        --nLen;
    }

    return sal_True;
}

#endif

// =======================================================================

static void ImplCopyAsciiStr( sal_Unicode* pDest, const sal_Char* pSrc,
                              sal_Int32 nLen )
{
    DBG_ASSERT( ImplDbgCheckAsciiStr( pSrc, nLen ),
                "UniString::CopyAsciiStr() - pAsciiStr include characters > 127" );

    while ( nLen )
    {
        *pDest = (unsigned char)*pSrc;
        ++pDest,
        ++pSrc,
        --nLen;
    }
}

// =======================================================================

static sal_Int32 ImplStringCompareAscii( const sal_Unicode* pStr1, const sal_Char* pStr2 )
{
    sal_Int32 nRet;
    while ( ((nRet = ((sal_Int32)*pStr1)-((sal_Int32)((unsigned char)*pStr2))) == 0) &&
            *pStr2 )
    {
        ++pStr1,
        ++pStr2;
    }

    return nRet;
}

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

static sal_Int32 ImplStringCompareAscii( const sal_Unicode* pStr1, const sal_Char* pStr2,
                                         xub_StrLen nCount )
{
    sal_Int32 nRet = 0;
    while ( nCount &&
            ((nRet = ((sal_Int32)*pStr1)-((sal_Int32)((unsigned char)*pStr2))) == 0) &&
            *pStr2 )
    {
        ++pStr1,
        ++pStr2,
        --nCount;
    }

    return nRet;
}

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

static sal_Int32 ImplStringCompareWithoutZeroAscii( const sal_Unicode* pStr1, const sal_Char* pStr2,
                                                    xub_StrLen nCount )
{
    sal_Int32 nRet = 0;
    while ( nCount &&
            ((nRet = ((sal_Int32)*pStr1)-((sal_Int32)((unsigned char)*pStr2))) == 0) )
    {
        ++pStr1,
        ++pStr2,
        --nCount;
    }

    return nRet;
}

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

static sal_Int32 ImplStringICompareAscii( const sal_Unicode* pStr1, const sal_Char* pStr2 )
{
    sal_Int32   nRet;
    sal_Unicode c1;
    sal_Char    c2;
    do
    {
        // Ist das Zeichen zwischen 'A' und 'Z' dann umwandeln
        c1 = *pStr1;
        c2 = *pStr2;
        if ( (c1 >= 65) && (c1 <= 90) )
            c1 += 32;
        if ( (c2 >= 65) && (c2 <= 90) )
            c2 += 32;
        nRet = ((sal_Int32)c1)-((sal_Int32)((unsigned char)c2));
        if ( nRet != 0 )
            break;

        ++pStr1,
        ++pStr2;
    }
    while ( c2 );

    return nRet;
}

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

static sal_Int32 ImplStringICompareAscii( const sal_Unicode* pStr1, const sal_Char* pStr2,
                                          xub_StrLen nCount )
{
    sal_Int32   nRet = 0;
    sal_Unicode c1;
    sal_Char    c2;
    do
    {
        if ( !nCount )
            break;

        // Ist das Zeichen zwischen 'A' und 'Z' dann umwandeln
        c1 = *pStr1;
        c2 = *pStr2;
        if ( (c1 >= 65) && (c1 <= 90) )
            c1 += 32;
        if ( (c2 >= 65) && (c2 <= 90) )
            c2 += 32;
        nRet = ((sal_Int32)c1)-((sal_Int32)((unsigned char)c2));
        if ( nRet != 0 )
            break;

        ++pStr1,
        ++pStr2,
        --nCount;
    }
    while ( c2 );

    return nRet;
}

// =======================================================================

UniString UniString::CreateFromAscii( const sal_Char* pAsciiStr )
{
    DBG_ASSERT( pAsciiStr, "UniString::CreateFromAscii() - pAsciiStr is NULL" );

    // Stringlaenge ermitteln
    xub_StrLen nLen = ImplStringLen( pAsciiStr );

    UniString aTempStr;
    if ( nLen )
    {
        ImplCopyAsciiStr( aTempStr.AllocBuffer( nLen ), pAsciiStr, nLen );
    }
    return aTempStr;
}

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

UniString UniString::CreateFromAscii( const sal_Char* pAsciiStr, xub_StrLen nLen )
{
    DBG_ASSERT( pAsciiStr, "UniString::CreateFromAscii() - pAsciiStr is NULL" );

    // Stringlaenge ermitteln
    if ( nLen == STRING_LEN )
        nLen = ImplStringLen( pAsciiStr );

    UniString aTempStr;

    if ( nLen )
    {
        ImplCopyAsciiStr( aTempStr.AllocBuffer( nLen ), pAsciiStr, nLen );
    }
    return aTempStr;
}

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

UniString& UniString::AssignAscii( const sal_Char* pAsciiStr )
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( pAsciiStr, "UniString::AssignAscii() - pAsciiStr is NULL" );

    // Stringlaenge ermitteln
    xub_StrLen nLen = ImplStringLen( pAsciiStr );

    if ( !nLen )
    {
        STRING_NEW((STRING_TYPE **)&mpData);
    }
    else
    {
        // Wenn String genauso lang ist, wie der String, dann direkt kopieren
        if ( (nLen == mpData->mnLen) && (mpData->mnRefCount == 1) )
            ImplCopyAsciiStr( mpData->maStr, pAsciiStr, nLen );
        else
        {
            // Alte Daten loeschen
            STRING_RELEASE((STRING_TYPE *)mpData);

            // Daten initialisieren und String kopieren
            mpData = ImplAllocData( nLen );
            ImplCopyAsciiStr( mpData->maStr, pAsciiStr, nLen );
        }
    }

    return *this;
}

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

UniString& UniString::AssignAscii( const sal_Char* pAsciiStr, xub_StrLen nLen )
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( pAsciiStr, "UniString::AssignAscii() - pAsciiStr is NULL" );

    if ( nLen == STRING_LEN )
        nLen = ImplStringLen( pAsciiStr );

#ifdef DBG_UTIL
    if ( DbgIsAssert() )
    {
        for ( xub_StrLen i = 0; i < nLen; ++i )
        {
            if ( !pAsciiStr[i] )
            {
                OSL_FAIL( "UniString::AssignAscii() : nLen is wrong" );
            }
        }
    }
#endif

    if ( !nLen )
    {
        STRING_NEW((STRING_TYPE **)&mpData);
    }
    else
    {
        // Wenn String genauso lang ist, wie der String, dann direkt kopieren
        if ( (nLen == mpData->mnLen) && (mpData->mnRefCount == 1) )
            ImplCopyAsciiStr( mpData->maStr, pAsciiStr, nLen );
        else
        {
            // Alte Daten loeschen
            STRING_RELEASE((STRING_TYPE *)mpData);

            // Daten initialisieren und String kopieren
            mpData = ImplAllocData( nLen );
            ImplCopyAsciiStr( mpData->maStr, pAsciiStr, nLen );
        }
    }

    return *this;
}

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

UniString& UniString::AppendAscii( const sal_Char* pAsciiStr )
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( pAsciiStr, "UniString::AppendAscii() - pAsciiStr is NULL" );

    // Stringlaenge ermitteln
    sal_Int32 nCopyLen = ImplStringLen( pAsciiStr );

    // Ueberlauf abfangen
    nCopyLen = ImplGetCopyLen( mpData->mnLen, nCopyLen );

    // Ist es kein leerer String
    if ( nCopyLen )
    {
        // Neue Datenstruktur und neuen String erzeugen
        UniStringData* pNewData = ImplAllocData( mpData->mnLen+nCopyLen );

        // String kopieren
        memcpy( pNewData->maStr, mpData->maStr, mpData->mnLen*sizeof( sal_Unicode ) );
        ImplCopyAsciiStr( pNewData->maStr+mpData->mnLen, pAsciiStr, nCopyLen );

        // Alte Daten loeschen und Neue zuweisen
        STRING_RELEASE((STRING_TYPE *)mpData);
        mpData = pNewData;
    }

    return *this;
}

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

UniString& UniString::AppendAscii( const sal_Char* pAsciiStr, xub_StrLen nLen )
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( pAsciiStr, "UniString::AppendAscii() - pAsciiStr is NULL" );

    if ( nLen == STRING_LEN )
        nLen = ImplStringLen( pAsciiStr );

#ifdef DBG_UTIL
    if ( DbgIsAssert() )
    {
        for ( xub_StrLen i = 0; i < nLen; ++i )
        {
            if ( !pAsciiStr[i] )
            {
                OSL_FAIL( "UniString::AppendAscii() : nLen is wrong" );
            }
        }
    }
#endif

    // Ueberlauf abfangen
    sal_Int32 nCopyLen = ImplGetCopyLen( mpData->mnLen, nLen );

    // Ist es kein leerer String
    if ( nCopyLen )
    {
        // Neue Datenstruktur und neuen String erzeugen
        UniStringData* pNewData = ImplAllocData( mpData->mnLen+nCopyLen );

        // String kopieren
        memcpy( pNewData->maStr, mpData->maStr, mpData->mnLen*sizeof( sal_Unicode ) );
        ImplCopyAsciiStr( pNewData->maStr+mpData->mnLen, pAsciiStr, nCopyLen );

        // Alte Daten loeschen und Neue zuweisen
        STRING_RELEASE((STRING_TYPE *)mpData);
        mpData = pNewData;
    }

    return *this;
}

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

UniString& UniString::InsertAscii( const char* pAsciiStr, xub_StrLen nIndex )
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( pAsciiStr, "UniString::InsertAscii() - pAsciiStr is NULL" );

    // Stringlaenge ermitteln
    sal_Int32 nCopyLen = ImplStringLen( pAsciiStr );

    // Ueberlauf abfangen
    nCopyLen = ImplGetCopyLen( mpData->mnLen, nCopyLen );

    // Ist der einzufuegende String ein Leerstring
    if ( !nCopyLen )
        return *this;

    // Index groesser als Laenge
    if ( nIndex > mpData->mnLen )
        nIndex = static_cast< xub_StrLen >(mpData->mnLen);

    // Neue Laenge ermitteln und neuen String anlegen
    UniStringData* pNewData = ImplAllocData( mpData->mnLen+nCopyLen );

    // String kopieren
    memcpy( pNewData->maStr, mpData->maStr, nIndex*sizeof( sal_Unicode ) );
    ImplCopyAsciiStr( pNewData->maStr+nIndex, pAsciiStr, nCopyLen );
    memcpy( pNewData->maStr+nIndex+nCopyLen, mpData->maStr+nIndex,
            (mpData->mnLen-nIndex)*sizeof( sal_Unicode ) );

    // Alte Daten loeschen und Neue zuweisen
    STRING_RELEASE((STRING_TYPE *)mpData);
    mpData = pNewData;

    return *this;
}

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

StringCompare UniString::CompareToAscii( const sal_Char* pAsciiStr,
                                         xub_StrLen nLen ) const
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, nLen ),
                "UniString::CompareToAscii() - pAsciiStr include characters > 127" );

    // String vergleichen
    sal_Int32 nCompare = ImplStringCompareAscii( mpData->maStr, pAsciiStr, nLen );

    // Rueckgabewert anpassen
    if ( nCompare == 0 )
        return COMPARE_EQUAL;
    else if ( nCompare < 0 )
        return COMPARE_LESS;
    else
        return COMPARE_GREATER;
}

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

StringCompare UniString::CompareIgnoreCaseToAscii( const sal_Char* pAsciiStr,
                                                   xub_StrLen nLen ) const
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, nLen ),
                "UniString::CompareIgnoreCaseToAscii() - pAsciiStr include characters > 127" );

    // String vergleichen
    sal_Int32 nCompare = ImplStringICompareAscii( mpData->maStr, pAsciiStr, nLen );

    // Rueckgabewert anpassen
    if ( nCompare == 0 )
        return COMPARE_EQUAL;
    else if ( nCompare < 0 )
        return COMPARE_LESS;
    else
        return COMPARE_GREATER;
}

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

sal_Bool UniString::EqualsAscii( const sal_Char* pAsciiStr ) const
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, STRING_LEN ),
                "UniString::EqualsAscii() - pAsciiStr include characters > 127" );

    return (ImplStringCompareAscii( mpData->maStr, pAsciiStr ) == 0);
}

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

sal_Bool UniString::EqualsIgnoreCaseAscii( const sal_Char* pAsciiStr ) const
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, STRING_LEN ),
                "UniString::EqualsIgnoreCaseAscii() - pAsciiStr include characters > 127" );

    return (ImplStringICompareAscii( mpData->maStr, pAsciiStr ) == 0);
}

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

sal_Bool UniString::EqualsAscii( const sal_Char* pAsciiStr,
                             xub_StrLen nIndex, xub_StrLen nLen ) const
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, nLen ),
                "UniString::EqualsAscii() - pAsciiStr include characters > 127" );

    // Are there enough codes for comparing?
    if ( nIndex > mpData->mnLen )
        return (*pAsciiStr == 0);

    return (ImplStringCompareAscii( mpData->maStr+nIndex, pAsciiStr, nLen ) == 0);
}

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

sal_Bool UniString::EqualsIgnoreCaseAscii( const sal_Char* pAsciiStr,
                                       xub_StrLen nIndex, xub_StrLen nLen ) const
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, nLen ),
                "UniString::EqualsIgnoreCaseAscii() - pAsciiStr include characters > 127" );

    // Are there enough codes for comparing?
    if ( nIndex > mpData->mnLen )
        return (*pAsciiStr == 0);

    return (ImplStringICompareAscii( mpData->maStr+nIndex, pAsciiStr, nLen ) == 0);
}

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

xub_StrLen UniString::SearchAscii( const sal_Char* pAsciiStr, xub_StrLen nIndex ) const
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, STRING_LEN ),
                "UniString::SearchAscii() - pAsciiStr include characters > 127" );

    sal_Int32 nLen = mpData->mnLen;
    xub_StrLen nStrLen  = ImplStringLen( pAsciiStr );

    // Falls die Laenge des uebergebenen Strings 0 ist oder der Index
    // hinter dem String liegt, dann wurde der String nicht gefunden
    if ( !nStrLen || (nIndex >= nLen) )
        return STRING_NOTFOUND;

    const sal_Unicode* pStr = mpData->maStr;
    pStr += nIndex;

    if ( nStrLen == 1 )
    {
        sal_Unicode cSearch = (unsigned char)*pAsciiStr;
        while ( nIndex < nLen )
        {
            if ( *pStr == cSearch )
                return nIndex;
            ++pStr,
            ++nIndex;
        }
    }
    else
    {
        // Nur innerhalb des Strings suchen
        while ( nLen - nIndex >= nStrLen )
        {
            // Stimmt der String ueberein
            if ( ImplStringCompareWithoutZeroAscii( pStr, pAsciiStr, nStrLen ) == 0 )
                return nIndex;
            ++pStr,
            ++nIndex;
        }
    }

    return STRING_NOTFOUND;
}

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

xub_StrLen UniString::SearchAndReplaceAscii( const sal_Char* pAsciiStr, const UniString& rRepStr,
                                             xub_StrLen nIndex )
{
    DBG_CHKTHIS( UniString, DbgCheckUniString );
    DBG_ASSERT( ImplDbgCheckAsciiStr( pAsciiStr, STRING_LEN ),
                "UniString::SearchAndReplaceAscii() - pAsciiStr include characters > 127" );

    xub_StrLen nSPos = SearchAscii( pAsciiStr, nIndex );
    if ( nSPos != STRING_NOTFOUND )
        Replace( nSPos, ImplStringLen( pAsciiStr ), rRepStr );

    return nSPos;
}

}

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