summaryrefslogtreecommitdiff
path: root/sal/inc/rtl/ustring.hxx
blob: ace4b1ae7179041dc43b935ace4808a9cc6174b5 (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
711
712
713
714
715
716
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
763
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
794
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
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
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
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*************************************************************************
 *
 * 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.
 *
 ************************************************************************/

#ifndef _RTL_USTRING_HXX_
#define _RTL_USTRING_HXX_

#include "sal/config.h"

#include <cassert>

#include "osl/diagnose.h"
#include <rtl/ustring.h>
#include <rtl/string.hxx>
#include <rtl/memory.h>
#include "sal/log.hxx"

#if defined EXCEPTIONS_OFF
#include <stdlib.h>
#else
#include <new>
#endif

namespace rtl
{
/* ======================================================================= */

/**
  This String class provide base functionality for C++ like Unicode
  character array handling. The advantage of this class is, that it
  handle all the memory management for you - and it do it
  more efficient. If you assign a string to another string, the
  data of both strings are shared (without any copy operation or
  memory allocation) as long as you do not change the string. This class
  stores also the length of the string, so that many operations are
  faster as the C-str-functions.

  This class provide only readonly string handling. So you could create
  a string and you could only query the content from this string.
  It provide also functionality to change the string, but this results
  in every case in a new string instance (in the most cases with an
  memory allocation). You don't have functionality to change the
  content of the string. If you want change the string content, than
  you should us the OStringBuffer class, which provide these
  functionality and avoid to much memory allocation.

  The design of this class is similar to the string classes in Java
  and so more people should have fewer understanding problems when they
  use this class.
*/

class OUString
{
public:
    /// @cond INTERNAL
    rtl_uString * pData;
    /// @endcond

private:
    class DO_NOT_ACQUIRE{};

    OUString( rtl_uString * value, SAL_UNUSED_PARAMETER DO_NOT_ACQUIRE * )
    {
        pData = value;
    }

public:
    /**
      New string containing no characters.
    */
    OUString() SAL_THROW(())
    {
        pData = 0;
        rtl_uString_new( &pData );
    }

    /**
      New string from OUString.

      @param    str         a OUString.
    */
    OUString( const OUString & str ) SAL_THROW(())
    {
        pData = str.pData;
        rtl_uString_acquire( pData );
    }

    /**
      New string from OUString data.

      @param    str         a OUString data.
    */
    OUString( rtl_uString * str )  SAL_THROW(())
    {
        pData = str;
        rtl_uString_acquire( pData );
    }

    /** New OUString from OUString data without acquiring it.  Takeover of ownership.

        The SAL_NO_ACQUIRE dummy parameter is only there to distinguish this
        from other constructors.

        @param str
               OUString data
    */
    inline OUString( rtl_uString * str, __sal_NoAcquire ) SAL_THROW(())
        { pData = str; }

    /**
      New string from a single Unicode character.

      @param    value       a Unicode character.
    */
    explicit OUString( sal_Unicode value ) SAL_THROW(())
        : pData (0)
    {
        rtl_uString_newFromStr_WithLength( &pData, &value, 1 );
    }

    /**
      New string from a Unicode character buffer array.

      @param    value       a NULL-terminated Unicode character array.
    */
    OUString( const sal_Unicode * value ) SAL_THROW(())
    {
        pData = 0;
        rtl_uString_newFromStr( &pData, value );
    }

    /**
      New string from a Uniocde character buffer array.

      @param    value       a Unicode character array.
      @param    length      the number of character which should be copied.
                            The character array length must be greater or
                            equal than this value.
    */
    OUString( const sal_Unicode * value, sal_Int32 length ) SAL_THROW(())
    {
        pData = 0;
        rtl_uString_newFromStr_WithLength( &pData, value, length );
    }

    /**
      New string from a 8-Bit character buffer array.

      @param    value           a 8-Bit character array.
      @param    length          the number of character which should be converted.
                                The 8-Bit character array length must be
                                greater or equal than this value.
      @param    encoding        the text encoding from which the 8-Bit character
                                sequence should be converted.
      @param    convertFlags    flags which controls the conversion.
                                see RTL_TEXTTOUNICODE_FLAGS_...

      @exception std::bad_alloc is thrown if an out-of-memory condition occurs
    */
    OUString( const sal_Char * value, sal_Int32 length,
              rtl_TextEncoding encoding,
              sal_uInt32 convertFlags = OSTRING_TO_OUSTRING_CVTFLAGS )
    {
        pData = 0;
        rtl_string2UString( &pData, value, length, encoding, convertFlags );
        if (pData == 0) {
#if defined EXCEPTIONS_OFF
            SAL_WARN("sal", "std::bad_alloc but EXCEPTIONS_OFF");
#else
            throw std::bad_alloc();
#endif
        }
    }

    /** Create a new string from an array of Unicode code points.

        @param codePoints
        an array of at least codePointCount code points, which each must be in
        the range from 0 to 0x10FFFF, inclusive.  May be null if codePointCount
        is zero.

        @param codePointCount
        the non-negative number of code points.

        @exception std::bad_alloc
        is thrown if either an out-of-memory condition occurs or the resulting
        number of UTF-16 code units would have been larger than SAL_MAX_INT32.

        @since UDK 3.2.7
    */
    inline explicit OUString(
        sal_uInt32 const * codePoints, sal_Int32 codePointCount):
        pData(NULL)
    {
        rtl_uString_newFromCodePoints(&pData, codePoints, codePointCount);
        if (pData == NULL) {
#if defined EXCEPTIONS_OFF
            abort();
#else
            throw std::bad_alloc();
#endif
        }
    }

    /**
      Release the string data.
    */
    ~OUString() SAL_THROW(())
    {
        rtl_uString_release( pData );
    }

    /** Provides an OUString const & passing a storage pointer of an
        rtl_uString * handle.
        It is more convenient to use C++ OUString member functions when dealing
        with rtl_uString * handles.  Using this function avoids unnecessary
        acquire()/release() calls for a temporary OUString object.

        @param ppHandle
               pointer to storage
        @return
               OUString const & based on given storage
    */
    static inline OUString const & unacquired( rtl_uString * const * ppHandle )
        { return * reinterpret_cast< OUString const * >( ppHandle ); }

    /**
      Assign a new string.

      @param    str         a OUString.
    */
    OUString & operator=( const OUString & str ) SAL_THROW(())
    {
        rtl_uString_assign( &pData, str.pData );
        return *this;
    }

    /**
      Append a string to this string.

      @param    str         a OUString.
    */
    OUString & operator+=( const OUString & str ) SAL_THROW(())
    {
        rtl_uString_newConcat( &pData, pData, str.pData );
        return *this;
    }

    /**
      Returns the length of this string.

      The length is equal to the number of Unicode characters in this string.

      @return   the length of the sequence of characters represented by this
                object.
    */
    sal_Int32 getLength() const SAL_THROW(()) { return pData->length; }

    /**
      Checks if a string is empty.

      @return   sal_True if the string is empty;
                sal_False, otherwise.

      @since LibreOffice 3.4
    */
    sal_Bool isEmpty() const SAL_THROW(())
    {
        if ( pData->length )
            return sal_False;
        else
            return sal_True;
    }

    /**
      Returns a pointer to the Unicode character buffer from this string.

      It isn't necessarily NULL terminated.

      @return   a pointer to the Unicode characters buffer from this object.
    */
    const sal_Unicode * getStr() const SAL_THROW(()) { return pData->buffer; }

    /**
      Access to individual characters.

      @param index must be non-negative and less than length.

      @return the character at the given index.

      @since LibreOffice 3.5
    */
    sal_Unicode operator [](sal_Int32 index) const { return getStr()[index]; }

    /**
      Compares two strings.

      The comparison is based on the numeric value of each character in
      the strings and return a value indicating their relationship.
      This function can't be used for language specific sorting.

      @param    str         the object to be compared.
      @return   0 - if both strings are equal
                < 0 - if this string is less than the string argument
                > 0 - if this string is greater than the string argument
    */
    sal_Int32 compareTo( const OUString & str ) const SAL_THROW(())
    {
        return rtl_ustr_compare_WithLength( pData->buffer, pData->length,
                                            str.pData->buffer, str.pData->length );
    }

    /**
      Compares two strings with an maximum count of characters.

      The comparison is based on the numeric value of each character in
      the strings and return a value indicating their relationship.
      This function can't be used for language specific sorting.

      @param    str         the object to be compared.
      @param    maxLength   the maximum count of characters to be compared.
      @return   0 - if both strings are equal
                < 0 - if this string is less than the string argument
                > 0 - if this string is greater than the string argument

      @since UDK 3.2.7
    */
    sal_Int32 compareTo( const OUString & str, sal_Int32 maxLength ) const SAL_THROW(())
    {
        return rtl_ustr_shortenedCompare_WithLength( pData->buffer, pData->length,
                                                     str.pData->buffer, str.pData->length, maxLength );
    }

    /**
      Compares two strings in reverse order.

      The comparison is based on the numeric value of each character in
      the strings and return a value indicating their relationship.
      This function can't be used for language specific sorting.

      @param    str         the object to be compared.
      @return   0 - if both strings are equal
                < 0 - if this string is less than the string argument
                > 0 - if this string is greater than the string argument
    */
    sal_Int32 reverseCompareTo( const OUString & str ) const SAL_THROW(())
    {
        return rtl_ustr_reverseCompare_WithLength( pData->buffer, pData->length,
                                                   str.pData->buffer, str.pData->length );
    }

    /**
      Perform a comparison of two strings.

      The result is true if and only if second string
      represents the same sequence of characters as the first string.
      This function can't be used for language specific comparison.

      @param    str         the object to be compared.
      @return   sal_True if the strings are equal;
                sal_False, otherwise.
    */
    sal_Bool equals( const OUString & str ) const SAL_THROW(())
    {
        if ( pData->length != str.pData->length )
            return sal_False;
        if ( pData == str.pData )
            return sal_True;
        return rtl_ustr_reverseCompare_WithLength( pData->buffer, pData->length,
                                                   str.pData->buffer, str.pData->length ) == 0;
    }

    /**
      Perform a ASCII lowercase comparison of two strings.

      The result is true if and only if second string
      represents the same sequence of characters as the first string,
      ignoring the case.
      Character values between 65 and 90 (ASCII A-Z) are interpreted as
      values between 97 and 122 (ASCII a-z).
      This function can't be used for language specific comparison.

      @param    str         the object to be compared.
      @return   sal_True if the strings are equal;
                sal_False, otherwise.
    */
    sal_Bool equalsIgnoreAsciiCase( const OUString & str ) const SAL_THROW(())
    {
        if ( pData->length != str.pData->length )
            return sal_False;
        if ( pData == str.pData )
            return sal_True;
        return rtl_ustr_compareIgnoreAsciiCase_WithLength( pData->buffer, pData->length,
                                                           str.pData->buffer, str.pData->length ) == 0;
    }

   /**
      Match against a substring appearing in this string.

      The result is true if and only if the second string appears as a substring
      of this string, at the given position.
      This function can't be used for language specific comparison.

      @param    str         the object (substring) to be compared.
      @param    fromIndex   the index to start the comparion from.
                            The index must be greater or equal than 0
                            and less or equal as the string length.
      @return   sal_True if str match with the characters in the string
                at the given position;
                sal_False, otherwise.
    */
    sal_Bool match( const OUString & str, sal_Int32 fromIndex = 0 ) const SAL_THROW(())
    {
        return rtl_ustr_shortenedCompare_WithLength( pData->buffer+fromIndex, pData->length-fromIndex,
                                                     str.pData->buffer, str.pData->length, str.pData->length ) == 0;
    }

    /**
      Match against a substring appearing in this string, ignoring the case of
      ASCII letters.

      The result is true if and only if the second string appears as a substring
      of this string, at the given position.
      Character values between 65 and 90 (ASCII A-Z) are interpreted as
      values between 97 and 122 (ASCII a-z).
      This function can't be used for language specific comparison.

      @param    str         the object (substring) to be compared.
      @param    fromIndex   the index to start the comparion from.
                            The index must be greater or equal than 0
                            and less or equal as the string length.
      @return   sal_True if str match with the characters in the string
                at the given position;
                sal_False, otherwise.
    */
    sal_Bool matchIgnoreAsciiCase( const OUString & str, sal_Int32 fromIndex = 0 ) const SAL_THROW(())
    {
        return rtl_ustr_shortenedCompareIgnoreAsciiCase_WithLength( pData->buffer+fromIndex, pData->length-fromIndex,
                                                                    str.pData->buffer, str.pData->length,
                                                                    str.pData->length ) == 0;
    }

    /**
      Compares two strings.

      The comparison is based on the numeric value of each character in
      the strings and return a value indicating their relationship.
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated.
      This function can't be used for language specific sorting.

      @param  asciiStr      the 8-Bit ASCII character string to be compared.
      @return   0 - if both strings are equal
                < 0 - if this string is less than the string argument
                > 0 - if this string is greater than the string argument
    */
    sal_Int32 compareToAscii( const sal_Char* asciiStr ) const SAL_THROW(())
    {
        return rtl_ustr_ascii_compare_WithLength( pData->buffer, pData->length, asciiStr );
    }

    /**
      Compares two strings with an maximum count of characters.

      The comparison is based on the numeric value of each character in
      the strings and return a value indicating their relationship.
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated.
      This function can't be used for language specific sorting.

      @param  asciiStr          the 8-Bit ASCII character string to be compared.
      @param  maxLength         the maximum count of characters to be compared.
      @return   0 - if both strings are equal
                < 0 - if this string is less than the string argument
                > 0 - if this string is greater than the string argument
    */
    sal_Int32 compareToAscii( const sal_Char * asciiStr, sal_Int32 maxLength ) const SAL_THROW(())
    {
        return rtl_ustr_ascii_shortenedCompare_WithLength( pData->buffer, pData->length,
                                                           asciiStr, maxLength );
    }

    /**
      Compares two strings in reverse order.

      This could be useful, if normally both strings start with the same
      content. The comparison is based on the numeric value of each character
      in the strings and return a value indicating their relationship.
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated and must be greater or
      equal as asciiStrLength.
      This function can't be used for language specific sorting.

      @param    asciiStr        the 8-Bit ASCII character string to be compared.
      @param    asciiStrLength  the length of the ascii string
      @return   0 - if both strings are equal
                < 0 - if this string is less than the string argument
                > 0 - if this string is greater than the string argument
    */
    sal_Int32 reverseCompareToAsciiL( const sal_Char * asciiStr, sal_Int32 asciiStrLength ) const SAL_THROW(())
    {
        return rtl_ustr_asciil_reverseCompare_WithLength( pData->buffer, pData->length,
                                                          asciiStr, asciiStrLength );
    }

    /**
      Perform a comparison of two strings.

      The result is true if and only if second string
      represents the same sequence of characters as the first string.
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated.
      This function can't be used for language specific comparison.

      @param    asciiStr        the 8-Bit ASCII character string to be compared.
      @return   sal_True if the strings are equal;
                sal_False, otherwise.
    */
    sal_Bool equalsAscii( const sal_Char* asciiStr ) const SAL_THROW(())
    {
        return rtl_ustr_ascii_compare_WithLength( pData->buffer, pData->length,
                                                  asciiStr ) == 0;
    }

    /**
      Perform a comparison of two strings.

      The result is true if and only if second string
      represents the same sequence of characters as the first string.
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated and must be greater or
      equal as asciiStrLength.
      This function can't be used for language specific comparison.

      @param    asciiStr         the 8-Bit ASCII character string to be compared.
      @param    asciiStrLength   the length of the ascii string
      @return   sal_True if the strings are equal;
                sal_False, otherwise.
    */
    sal_Bool equalsAsciiL( const sal_Char* asciiStr, sal_Int32 asciiStrLength ) const SAL_THROW(())
    {
        if ( pData->length != asciiStrLength )
            return sal_False;

        return rtl_ustr_asciil_reverseEquals_WithLength(
                    pData->buffer, asciiStr, asciiStrLength );
    }

    /**
      Perform a ASCII lowercase comparison of two strings.

      The result is true if and only if second string
      represents the same sequence of characters as the first string,
      ignoring the case.
      Character values between 65 and 90 (ASCII A-Z) are interpreted as
      values between 97 and 122 (ASCII a-z).
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated.
      This function can't be used for language specific comparison.

      @param    asciiStr        the 8-Bit ASCII character string to be compared.
      @return   sal_True if the strings are equal;
                sal_False, otherwise.
    */
    sal_Bool equalsIgnoreAsciiCaseAscii( const sal_Char * asciiStr ) const SAL_THROW(())
    {
        return rtl_ustr_ascii_compareIgnoreAsciiCase_WithLength( pData->buffer, pData->length, asciiStr ) == 0;
    }

    /**
      Compares two ASCII strings ignoring case

      The comparison is based on the numeric value of each character in
      the strings and return a value indicating their relationship.
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated.
      This function can't be used for language specific sorting.

      @param  asciiStr      the 8-Bit ASCII character string to be compared.
      @return   0 - if both strings are equal
                < 0 - if this string is less than the string argument
                > 0 - if this string is greater than the string argument

      @since LibreOffice 3.5
    */
    sal_Int32 compareToIgnoreAsciiCaseAscii( const sal_Char * asciiStr ) const SAL_THROW(())
    {
        return rtl_ustr_ascii_compareIgnoreAsciiCase_WithLength( pData->buffer, pData->length, asciiStr );
    }

    /**
      Perform a ASCII lowercase comparison of two strings.

      The result is true if and only if second string
      represents the same sequence of characters as the first string,
      ignoring the case.
      Character values between 65 and 90 (ASCII A-Z) are interpreted as
      values between 97 and 122 (ASCII a-z).
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated and must be greater or
      equal as asciiStrLength.
      This function can't be used for language specific comparison.

      @param    asciiStr        the 8-Bit ASCII character string to be compared.
      @param    asciiStrLength  the length of the ascii string
      @return   sal_True if the strings are equal;
                sal_False, otherwise.
    */
    sal_Bool equalsIgnoreAsciiCaseAsciiL( const sal_Char * asciiStr, sal_Int32 asciiStrLength ) const SAL_THROW(())
    {
        if ( pData->length != asciiStrLength )
            return sal_False;

        return rtl_ustr_ascii_compareIgnoreAsciiCase_WithLength( pData->buffer, pData->length, asciiStr ) == 0;
    }

    /**
      Match against a substring appearing in this string.

      The result is true if and only if the second string appears as a substring
      of this string, at the given position.
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated and must be greater or
      equal as asciiStrLength.
      This function can't be used for language specific comparison.

      @param    asciiStr    the object (substring) to be compared.
      @param    asciiStrLength the length of asciiStr.
      @param    fromIndex   the index to start the comparion from.
                            The index must be greater or equal than 0
                            and less or equal as the string length.
      @return   sal_True if str match with the characters in the string
                at the given position;
                sal_False, otherwise.
    */
    sal_Bool matchAsciiL( const sal_Char* asciiStr, sal_Int32 asciiStrLength, sal_Int32 fromIndex = 0 ) const SAL_THROW(())
    {
        return rtl_ustr_ascii_shortenedCompare_WithLength( pData->buffer+fromIndex, pData->length-fromIndex,
                                                           asciiStr, asciiStrLength ) == 0;
    }

    /**
      Match against a substring appearing in this string, ignoring the case of
      ASCII letters.

      The result is true if and only if the second string appears as a substring
      of this string, at the given position.
      Character values between 65 and 90 (ASCII A-Z) are interpreted as
      values between 97 and 122 (ASCII a-z).
      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated and must be greater or
      equal as asciiStrLength.
      This function can't be used for language specific comparison.

      @param    asciiStr        the 8-Bit ASCII character string to be compared.
      @param    asciiStrLength  the length of the ascii string
      @param    fromIndex       the index to start the comparion from.
                                The index must be greater or equal than 0
                                and less or equal as the string length.
      @return   sal_True if str match with the characters in the string
                at the given position;
                sal_False, otherwise.
    */
    sal_Bool matchIgnoreAsciiCaseAsciiL( const sal_Char* asciiStr, sal_Int32 asciiStrLength, sal_Int32 fromIndex = 0 ) const SAL_THROW(())
    {
        return rtl_ustr_ascii_shortenedCompareIgnoreAsciiCase_WithLength( pData->buffer+fromIndex, pData->length-fromIndex,
                                                                          asciiStr, asciiStrLength ) == 0;
    }

    /**
      Check whether this string ends with a given ASCII string.

      @param asciiStr a sequence of at least asciiStrLength ASCII characters
          (bytes in the range 0x00--0x7F)
      @param asciiStrLength the length of asciiStr; must be non-negative
      @return true if this string ends with asciiStr; otherwise, false is
      returned

      @since UDK 3.2.7
     */
    inline bool endsWithAsciiL(char const * asciiStr, sal_Int32 asciiStrLength)
        const
    {
        return asciiStrLength <= pData->length
            && rtl_ustr_asciil_reverseEquals_WithLength(
                pData->buffer + pData->length - asciiStrLength, asciiStr,
                asciiStrLength);
    }

    /**
      Check whether this string ends with a given ASCII string, ignoring the
      case of ASCII letters.

      @param asciiStr a sequence of at least asciiStrLength ASCII characters
          (bytes in the range 0x00--0x7F)
      @param asciiStrLength the length of asciiStr; must be non-negative
      @return true if this string ends with asciiStr, ignoring the case of ASCII
      letters ("A"--"Z" and "a"--"z"); otherwise, false is returned
     */
    inline bool endsWithIgnoreAsciiCaseAsciiL(
        char const * asciiStr, sal_Int32 asciiStrLength) const
    {
        return asciiStrLength <= pData->length
            && (rtl_ustr_ascii_compareIgnoreAsciiCase_WithLengths(
                    pData->buffer + pData->length - asciiStrLength,
                    asciiStrLength, asciiStr, asciiStrLength)
                == 0);
    }

    friend sal_Bool     operator == ( const OUString& rStr1,    const OUString& rStr2 ) SAL_THROW(())
                        { return rStr1.getLength() == rStr2.getLength() && rStr1.compareTo( rStr2 ) == 0; }
    friend sal_Bool     operator == ( const OUString& rStr1,    const sal_Unicode * pStr2 ) SAL_THROW(())
                        { return rStr1.compareTo( pStr2 ) == 0; }
    friend sal_Bool     operator == ( const sal_Unicode * pStr1,    const OUString& rStr2 ) SAL_THROW(())
                        { return OUString( pStr1 ).compareTo( rStr2 ) == 0; }

    friend sal_Bool     operator != ( const OUString& rStr1,        const OUString& rStr2 ) SAL_THROW(())
                        { return !(operator == ( rStr1, rStr2 )); }
    friend sal_Bool     operator != ( const OUString& rStr1,    const sal_Unicode * pStr2 ) SAL_THROW(())
                        { return !(operator == ( rStr1, pStr2 )); }
    friend sal_Bool     operator != ( const sal_Unicode * pStr1,    const OUString& rStr2 ) SAL_THROW(())
                        { return !(operator == ( pStr1, rStr2 )); }

    friend sal_Bool     operator <  ( const OUString& rStr1,    const OUString& rStr2 ) SAL_THROW(())
                        { return rStr1.compareTo( rStr2 ) < 0; }
    friend sal_Bool     operator >  ( const OUString& rStr1,    const OUString& rStr2 ) SAL_THROW(())
                        { return rStr1.compareTo( rStr2 ) > 0; }
    friend sal_Bool     operator <= ( const OUString& rStr1,    const OUString& rStr2 ) SAL_THROW(())
                        { return rStr1.compareTo( rStr2 ) <= 0; }
    friend sal_Bool     operator >= ( const OUString& rStr1,    const OUString& rStr2 ) SAL_THROW(())
                        { return rStr1.compareTo( rStr2 ) >= 0; }

    /**
      Returns a hashcode for this string.

      @return   a hash code value for this object.

      @see rtl::OUStringHash for convenient use of boost::unordered_map
    */
    sal_Int32 hashCode() const SAL_THROW(())
    {
        return rtl_ustr_hashCode_WithLength( pData->buffer, pData->length );
    }

    /**
      Returns the index within this string of the first occurrence of the
      specified character, starting the search at the specified index.

      @param    ch          character to be located.
      @param    fromIndex   the index to start the search from.
                            The index must be greater or equal than 0
                            and less or equal as the string length.
      @return   the index of the first occurrence of the character in the
                character sequence represented by this string that is
                greater than or equal to fromIndex, or
                -1 if the character does not occur.
    */
    sal_Int32 indexOf( sal_Unicode ch, sal_Int32 fromIndex = 0 ) const SAL_THROW(())
    {
        sal_Int32 ret = rtl_ustr_indexOfChar_WithLength( pData->buffer+fromIndex, pData->length-fromIndex, ch );
        return (ret < 0 ? ret : ret+fromIndex);
    }

    /**
      Returns the index within this string of the last occurrence of the
      specified character, searching backward starting at the end.

      @param    ch          character to be located.
      @return   the index of the last occurrence of the character in the
                character sequence represented by this string, or
                -1 if the character does not occur.
    */
    sal_Int32 lastIndexOf( sal_Unicode ch ) const SAL_THROW(())
    {
        return rtl_ustr_lastIndexOfChar_WithLength( pData->buffer, pData->length, ch );
    }

    /**
      Returns the index within this string of the last occurrence of the
      specified character, searching backward starting before the specified
      index.

      @param    ch          character to be located.
      @param    fromIndex   the index before which to start the search.
      @return   the index of the last occurrence of the character in the
                character sequence represented by this string that
                is less than fromIndex, or -1
                if the character does not occur before that point.
    */
    sal_Int32 lastIndexOf( sal_Unicode ch, sal_Int32 fromIndex ) const SAL_THROW(())
    {
        return rtl_ustr_lastIndexOfChar_WithLength( pData->buffer, fromIndex, ch );
    }

    /**
      Returns the index within this string of the first occurrence of the
      specified substring, starting at the specified index.

      If str doesn't include any character, always -1 is
      returned. This is also the case, if both strings are empty.

      @param    str         the substring to search for.
      @param    fromIndex   the index to start the search from.
      @return   If the string argument occurs one or more times as a substring
                within this string at the starting index, then the index
                of the first character of the first such substring is
                returned. If it does not occur as a substring starting
                at fromIndex or beyond, -1 is returned.
    */
    sal_Int32 indexOf( const OUString & str, sal_Int32 fromIndex = 0 ) const SAL_THROW(())
    {
        sal_Int32 ret = rtl_ustr_indexOfStr_WithLength( pData->buffer+fromIndex, pData->length-fromIndex,
                                                        str.pData->buffer, str.pData->length );
        return (ret < 0 ? ret : ret+fromIndex);
    }

    /**
       Returns the index within this string of the first occurrence of the
       specified ASCII substring, starting at the specified index.

       @param str
       the substring to be searched for.  Need not be null-terminated, but must
       be at least as long as the specified len.  Must only contain characters
       in the ASCII range 0x00--7F.

       @param len
       the length of the substring; must be non-negative.

       @param fromIndex
       the index to start the search from.  Must be in the range from zero to
       the length of this string, inclusive.

       @return
       the index (starting at 0) of the first character of the first occurrence
       of the substring within this string starting at the given fromIndex, or
       -1 if the substring does not occur.  If len is zero, -1 is returned.

       @since UDK 3.2.7
    */
    sal_Int32 indexOfAsciiL(
        char const * str, sal_Int32 len, sal_Int32 fromIndex = 0) const
        SAL_THROW(())
    {
        sal_Int32 ret = rtl_ustr_indexOfAscii_WithLength(
            pData->buffer + fromIndex, pData->length - fromIndex, str, len);
        return ret < 0 ? ret : ret + fromIndex;
    }

    /**
      Returns the index within this string of the last occurrence of
      the specified substring, searching backward starting at the end.

      The returned index indicates the starting index of the substring
      in this string.
      If str doesn't include any character, always -1 is
      returned. This is also the case, if both strings are empty.

      @param    str         the substring to search for.
      @return   If the string argument occurs one or more times as a substring
                within this string, then the index of the first character of
                the last such substring is returned. If it does not occur as
                a substring, -1 is returned.
    */
    sal_Int32 lastIndexOf( const OUString & str ) const SAL_THROW(())
    {
        return rtl_ustr_lastIndexOfStr_WithLength( pData->buffer, pData->length,
                                                   str.pData->buffer, str.pData->length );
    }

    /**
      Returns the index within this string of the last occurrence of
      the specified substring, searching backward starting before the specified
      index.

      The returned index indicates the starting index of the substring
      in this string.
      If str doesn't include any character, always -1 is
      returned. This is also the case, if both strings are empty.

      @param    str         the substring to search for.
      @param    fromIndex   the index before which to start the search.
      @return   If the string argument occurs one or more times as a substring
                within this string before the starting index, then the index
                of the first character of the last such substring is
                returned. Otherwise, -1 is returned.
    */
    sal_Int32 lastIndexOf( const OUString & str, sal_Int32 fromIndex ) const SAL_THROW(())
    {
        return rtl_ustr_lastIndexOfStr_WithLength( pData->buffer, fromIndex,
                                                   str.pData->buffer, str.pData->length );
    }

    /**
       Returns the index within this string of the last occurrence of the
       specified ASCII substring.

       @param str
       the substring to be searched for.  Need not be null-terminated, but must
       be at least as long as the specified len.  Must only contain characters
       in the ASCII range 0x00--7F.

       @param len
       the length of the substring; must be non-negative.

       @return
       the index (starting at 0) of the first character of the last occurrence
       of the substring within this string, or -1 if the substring does not
       occur.  If len is zero, -1 is returned.

       @since UDK 3.2.7
    */
    sal_Int32 lastIndexOfAsciiL(char const * str, sal_Int32 len) const
        SAL_THROW(())
    {
        return rtl_ustr_lastIndexOfAscii_WithLength(
            pData->buffer, pData->length, str, len);
    }

    /**
      Returns a new string that is a substring of this string.

      The substring begins at the specified beginIndex.  It is an error for
      beginIndex to be negative or to be greater than the length of this string.

      @param     beginIndex   the beginning index, inclusive.
      @return    the specified substring.
    */
    OUString copy( sal_Int32 beginIndex ) const SAL_THROW(())
    {
        assert(beginIndex >= 0 && beginIndex <= getLength());
        if ( beginIndex == 0 )
            return *this;
        else
        {
            rtl_uString* pNew = 0;
            rtl_uString_newFromStr_WithLength( &pNew, pData->buffer+beginIndex, getLength()-beginIndex );
            return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
        }
    }

    /**
      Returns a new string that is a substring of this string.

      The substring begins at the specified beginIndex and contains count
      characters.  It is an error for either beginIndex or count to be negative,
      or for beginIndex + count to be greater than the length of this string.

      @param     beginIndex   the beginning index, inclusive.
      @param     count        the number of characters.
      @return    the specified substring.
    */
    OUString copy( sal_Int32 beginIndex, sal_Int32 count ) const SAL_THROW(())
    {
        assert(beginIndex >= 0 && beginIndex <= getLength() && count >= 0);
        if ( (beginIndex == 0) && (count == getLength()) )
            return *this;
        else
        {
            rtl_uString* pNew = 0;
            rtl_uString_newFromStr_WithLength( &pNew, pData->buffer+beginIndex, count );
            return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
        }
    }

    /**
      Concatenates the specified string to the end of this string.

      @param    str   the string that is concatenated to the end
                      of this string.
      @return   a string that represents the concatenation of this string
                followed by the string argument.
    */
    OUString concat( const OUString & str ) const SAL_THROW(())
    {
        rtl_uString* pNew = 0;
        rtl_uString_newConcat( &pNew, pData, str.pData );
        return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
    }

    friend OUString operator+( const OUString& rStr1, const OUString& rStr2  ) SAL_THROW(())
    {
        return rStr1.concat( rStr2 );
    }

    /**
      Returns a new string resulting from replacing n = count characters
      from position index in this string with newStr.

      @param  index   the replacing index in str.
                      The index must be greater or equal as 0 and
                      less or equal as the length of the string.
      @param  count   the count of charcters that will replaced
                      The count must be greater or equal as 0 and
                      less or equal as the length of the string minus index.
      @param  newStr  the new substring.
      @return the new string.
    */
    OUString replaceAt( sal_Int32 index, sal_Int32 count, const OUString& newStr ) const SAL_THROW(())
    {
        rtl_uString* pNew = 0;
        rtl_uString_newReplaceStrAt( &pNew, pData, index, count, newStr.pData );
        return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns a new string resulting from replacing all occurrences of
      oldChar in this string with newChar.

      If the character oldChar does not occur in the character sequence
      represented by this object, then the string is assigned with
      str.

      @param    oldChar     the old character.
      @param    newChar     the new character.
      @return   a string derived from this string by replacing every
                occurrence of oldChar with newChar.
    */
    OUString replace( sal_Unicode oldChar, sal_Unicode newChar ) const SAL_THROW(())
    {
        rtl_uString* pNew = 0;
        rtl_uString_newReplace( &pNew, pData, oldChar, newChar );
        return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Converts from this string all ASCII uppercase characters (65-90)
      to ASCII lowercase characters (97-122).

      This function can't be used for language specific conversion.
      If the string doesn't contain characters which must be converted,
      then the new string is assigned with str.

      @return   the string, converted to ASCII lowercase.
    */
    OUString toAsciiLowerCase() const SAL_THROW(())
    {
        rtl_uString* pNew = 0;
        rtl_uString_newToAsciiLowerCase( &pNew, pData );
        return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Converts from this string all ASCII lowercase characters (97-122)
      to ASCII uppercase characters (65-90).

      This function can't be used for language specific conversion.
      If the string doesn't contain characters which must be converted,
      then the new string is assigned with str.

      @return   the string, converted to ASCII uppercase.
    */
    OUString toAsciiUpperCase() const SAL_THROW(())
    {
        rtl_uString* pNew = 0;
        rtl_uString_newToAsciiUpperCase( &pNew, pData );
        return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns a new string resulting from removing white space from both ends
      of the string.

      All characters that have codes less than or equal to
      32 (the space character) are considered to be white space.
      If the string doesn't contain white spaces at both ends,
      then the new string is assigned with str.

      @return   the string, with white space removed from the front and end.
    */
    OUString trim() const SAL_THROW(())
    {
        rtl_uString* pNew = 0;
        rtl_uString_newTrim( &pNew, pData );
        return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns a token in the string.

      Example:
        sal_Int32 nIndex = 0;
        do
        {
            ...
            OUString aToken = aStr.getToken( 0, ';', nIndex );
            ...
        }
        while ( nIndex >= 0 );

      @param    token       the number of the token to return
      @param    cTok        the character which seperate the tokens.
      @param    index       the position at which the token is searched in the
                            string.
                            The index must not be greater than the length of the
                            string.
                            This param is set to the position of the
                            next token or to -1, if it is the last token.
      @return   the token; if either token or index is negative, an empty token
                is returned (and index is set to -1)
    */
    OUString getToken( sal_Int32 token, sal_Unicode cTok, sal_Int32& index ) const SAL_THROW(())
    {
        rtl_uString * pNew = 0;
        index = rtl_uString_getToken( &pNew, pData, token, cTok, index );
        return OUString( pNew, (DO_NOT_ACQUIRE *)0 );
    }

    /**
      Returns the Boolean value from this string.

      This function can't be used for language specific conversion.

      @return   sal_True, if the string is 1 or "True" in any ASCII case.
                sal_False in any other case.
    */
    sal_Bool toBoolean() const SAL_THROW(())
    {
        return rtl_ustr_toBoolean( pData->buffer );
    }

    /**
      Returns the first character from this string.

      @return   the first character from this string or 0, if this string
                is emptry.
    */
    sal_Unicode toChar() const SAL_THROW(())
    {
        return pData->buffer[0];
    }

    /**
      Returns the int32 value from this string.

      This function can't be used for language specific conversion.

      @param    radix       the radix (between 2 and 36)
      @return   the int32 represented from this string.
                0 if this string represents no number.
    */
    sal_Int32 toInt32( sal_Int16 radix = 10 ) const SAL_THROW(())
    {
        return rtl_ustr_toInt32( pData->buffer, radix );
    }

    /**
      Returns the int64 value from this string.

      This function can't be used for language specific conversion.

      @param    radix       the radix (between 2 and 36)
      @return   the int64 represented from this string.
                0 if this string represents no number.
    */
    sal_Int64 toInt64( sal_Int16 radix = 10 ) const SAL_THROW(())
    {
        return rtl_ustr_toInt64( pData->buffer, radix );
    }

    /**
      Returns the float value from this string.

      This function can't be used for language specific conversion.

      @return   the float represented from this string.
                0.0 if this string represents no number.
    */
    float toFloat() const SAL_THROW(())
    {
        return rtl_ustr_toFloat( pData->buffer );
    }

    /**
      Returns the double value from this string.

      This function can't be used for language specific conversion.

      @return   the double represented from this string.
                0.0 if this string represents no number.
    */
    double toDouble() const SAL_THROW(())
    {
        return rtl_ustr_toDouble( pData->buffer );
    }


    /**
       Return a canonical representation for a string.

       A pool of strings, initially empty is maintained privately
       by the string class. On invocation, if present in the pool
       the original string will be returned. Otherwise this string,
       or a copy thereof will be added to the pool and returned.

       @return
       a version of the string from the pool.

       @exception std::bad_alloc is thrown if an out-of-memory condition occurs

       @since UDK 3.2.7
    */
    OUString intern() const
    {
        rtl_uString * pNew = 0;
        rtl_uString_intern( &pNew, pData );
        if (pNew == 0) {
#if defined EXCEPTIONS_OFF
            SAL_WARN("sal", "std::bad_alloc but EXCEPTIONS_OFF");
#else
            throw std::bad_alloc();
#endif
        }
        return OUString( pNew, (DO_NOT_ACQUIRE *)0 );
    }

    /**
       Return a canonical representation for a converted string.

       A pool of strings, initially empty is maintained privately
       by the string class. On invocation, if present in the pool
       the original string will be returned. Otherwise this string,
       or a copy thereof will be added to the pool and returned.

       @param    value           a 8-Bit character array.
       @param    length          the number of character which should be converted.
                                 The 8-Bit character array length must be
                                 greater or equal than this value.
       @param    encoding        the text encoding from which the 8-Bit character
                                 sequence should be converted.
       @param    convertFlags    flags which controls the conversion.
                                 see RTL_TEXTTOUNICODE_FLAGS_...
       @param    pInfo           pointer to return conversion status or NULL.

       @return
       a version of the converted string from the pool.

       @exception std::bad_alloc is thrown if an out-of-memory condition occurs

       @since UDK 3.2.7
    */
    static OUString intern( const sal_Char * value, sal_Int32 length,
                            rtl_TextEncoding encoding,
                            sal_uInt32 convertFlags = OSTRING_TO_OUSTRING_CVTFLAGS,
                            sal_uInt32 *pInfo = NULL )
    {
        rtl_uString * pNew = 0;
        rtl_uString_internConvert( &pNew, value, length, encoding,
                                   convertFlags, pInfo );
        if (pNew == 0) {
#if defined EXCEPTIONS_OFF
            SAL_WARN("sal", "std::bad_alloc but EXCEPTIONS_OFF");
#else
            throw std::bad_alloc();
#endif
        }
        return OUString( pNew, (DO_NOT_ACQUIRE *)0 );
    }

    /**
      Converts to an OString, signalling failure.

      @param pTarget
      An out parameter receiving the converted OString.  Must not be null; the
      contents are not modified if conversion fails (convertToOString returns
      false).

      @param nEncoding
      The text encoding to convert into.  Must be an octet encoding (i.e.,
      rtl_isOctetTextEncoding(nEncoding) must return true).

      @param nFlags
      A combination of RTL_UNICODETOTEXT_FLAGS that detail how to do the
      conversion (see rtl_convertUnicodeToText).  RTL_UNICODETOTEXT_FLAGS_FLUSH
      need not be included, it is implicitly assumed.  Typical uses are either
      RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR |
      RTL_UNICODETOTEXT_FLAGS_INVALID_ERROR (fail if a Unicode character cannot
      be converted to the target nEncoding) or OUSTRING_TO_OSTRING_CVTFLAGS
      (make a best efforts conversion).

      @return
      True if the conversion succeeded, false otherwise.
     */
    inline bool convertToString(OString * pTarget, rtl_TextEncoding nEncoding,
                                sal_uInt32 nFlags) const
    {
        return rtl_convertUStringToString(&pTarget->pData, pData->buffer,
                                            pData->length, nEncoding, nFlags);
    }

    /** Iterate through this string based on code points instead of UTF-16 code
        units.

        See Chapter 3 of The Unicode Standard 5.0 (Addison--Wesley, 2006) for
        definitions of the various terms used in this description.

        This string is interpreted as a sequence of zero or more UTF-16 code
        units.  For each index into this sequence (from zero to one less than
        the length of the sequence, inclusive), a code point represented
        starting at the given index is computed as follows:

        - If the UTF-16 code unit addressed by the index constitutes a
        well-formed UTF-16 code unit sequence, the computed code point is the
        scalar value encoded by that UTF-16 code unit sequence.

        - Otherwise, if the index is at least two UTF-16 code units away from
        the end of the sequence, and the sequence of two UTF-16 code units
        addressed by the index constitutes a well-formed UTF-16 code unit
        sequence, the computed code point is the scalar value encoded by that
        UTF-16 code unit sequence.

        - Otherwise, the computed code point is the UTF-16 code unit addressed
        by the index.  (This last case catches unmatched surrogates as well as
        indices pointing into the middle of surrogate pairs.)

        @param indexUtf16
        pointer to a UTF-16 based index into this string; must not be null.  On
        entry, the index must be in the range from zero to the length of this
        string (in UTF-16 code units), inclusive.  Upon successful return, the
        index will be updated to address the UTF-16 code unit that is the given
        incrementCodePoints away from the initial index.

        @param incrementCodePoints
        the number of code points to move the given *indexUtf16.  If
        non-negative, moving is done after determining the code point at the
        index.  If negative, moving is done before determining the code point
        at the (then updated) index.  The value must be such that the resulting
        UTF-16 based index is in the range from zero to the length of this
        string (in UTF-16 code units), inclusive.

        @return
        the code point (an integer in the range from 0 to 0x10FFFF, inclusive)
        that is represented within this string starting at the index computed as
        follows:  If incrementCodePoints is non-negative, the index is the
        initial value of *indexUtf16; if incrementCodePoints is negative, the
        index is the updated value of *indexUtf16.  In either case, the computed
        index must be in the range from zero to one less than the length of this
        string (in UTF-16 code units), inclusive.

        @since UDK 3.2.7
    */
    inline sal_uInt32 iterateCodePoints(
        sal_Int32 * indexUtf16, sal_Int32 incrementCodePoints = 1) const
    {
        return rtl_uString_iterateCodePoints(
            pData, indexUtf16, incrementCodePoints);
    }

    /**
      Returns the string representation of the sal_Bool argument.

      If the sal_Bool is true, the string "true" is returned.
      If the sal_Bool is false, the string "false" is returned.
      This function can't be used for language specific conversion.

      @param    b   a sal_Bool.
      @return   a string with the string representation of the argument.
    */
    static OUString valueOf( sal_Bool b ) SAL_THROW(())
    {
        sal_Unicode aBuf[RTL_USTR_MAX_VALUEOFBOOLEAN];
        rtl_uString* pNewData = 0;
        rtl_uString_newFromStr_WithLength( &pNewData, aBuf, rtl_ustr_valueOfBoolean( aBuf, b ) );
        return OUString( pNewData, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns the string representation of the char argument.

      @param    c   a character.
      @return   a string with the string representation of the argument.
    */
    static OUString valueOf( sal_Unicode c ) SAL_THROW(())
    {
        return OUString( &c, 1 );
    }

    /**
      Returns the string representation of the int argument.

      This function can't be used for language specific conversion.

      @param    i           a int32.
      @param    radix       the radix (between 2 and 36)
      @return   a string with the string representation of the argument.
    */
    static OUString valueOf( sal_Int32 i, sal_Int16 radix = 10 ) SAL_THROW(())
    {
        sal_Unicode aBuf[RTL_USTR_MAX_VALUEOFINT32];
        rtl_uString* pNewData = 0;
        rtl_uString_newFromStr_WithLength( &pNewData, aBuf, rtl_ustr_valueOfInt32( aBuf, i, radix ) );
        return OUString( pNewData, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns the string representation of the long argument.

      This function can't be used for language specific conversion.

      @param    ll          a int64.
      @param    radix       the radix (between 2 and 36)
      @return   a string with the string representation of the argument.
    */
    static OUString valueOf( sal_Int64 ll, sal_Int16 radix = 10 ) SAL_THROW(())
    {
        sal_Unicode aBuf[RTL_USTR_MAX_VALUEOFINT64];
        rtl_uString* pNewData = 0;
        rtl_uString_newFromStr_WithLength( &pNewData, aBuf, rtl_ustr_valueOfInt64( aBuf, ll, radix ) );
        return OUString( pNewData, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns the string representation of the float argument.

      This function can't be used for language specific conversion.

      @param    f           a float.
      @return   a string with the string representation of the argument.
    */
    static OUString valueOf( float f ) SAL_THROW(())
    {
        sal_Unicode aBuf[RTL_USTR_MAX_VALUEOFFLOAT];
        rtl_uString* pNewData = 0;
        rtl_uString_newFromStr_WithLength( &pNewData, aBuf, rtl_ustr_valueOfFloat( aBuf, f ) );
        return OUString( pNewData, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns the string representation of the double argument.

      This function can't be used for language specific conversion.

      @param    d           a double.
      @return   a string with the string representation of the argument.
    */
    static OUString valueOf( double d ) SAL_THROW(())
    {
        sal_Unicode aBuf[RTL_USTR_MAX_VALUEOFDOUBLE];
        rtl_uString* pNewData = 0;
        rtl_uString_newFromStr_WithLength( &pNewData, aBuf, rtl_ustr_valueOfDouble( aBuf, d ) );
        return OUString( pNewData, (DO_NOT_ACQUIRE*)0 );
    }

    /**
      Returns a OUString copied without conversion from an ASCII
      character string.

      Since this method is optimized for performance, the ASCII character
      values are not converted in any way. The caller has to make sure that
      all ASCII characters are in the allowed range between 0 and
      127. The ASCII string must be NULL-terminated.

      @param    value       the 8-Bit ASCII character string
      @return   a string with the string representation of the argument.
     */
    static OUString createFromAscii( const sal_Char * value ) SAL_THROW(())
    {
        rtl_uString* pNew = 0;
        rtl_uString_newFromAscii( &pNew, value );
        return OUString( pNew, (DO_NOT_ACQUIRE*)0 );
    }
};

/* ======================================================================= */

/** A helper to use OUStrings with hash maps.

    Instances of this class are unary function objects that can be used as
    hash function arguments to boost::unordered_map and similar constructs.
 */
struct OUStringHash
{
    /** Compute a hash code for a string.

        @param rString
        a string.

        @return
        a hash code for the string.  This hash code should not be stored
        persistently, as its computation may change in later revisions.
     */
    size_t operator()(const rtl::OUString& rString) const
        { return (size_t)rString.hashCode(); }
};

/* ======================================================================= */

/** Convert an OString to an OUString, using a specific text encoding.

    The lengths of the two strings may differ (e.g., for double-byte
    encodings, UTF-7, UTF-8).

    @param rStr
    an OString to convert.

    @param encoding
    the text encoding to use for conversion.

    @param convertFlags
    flags which control the conversion.  Either use
    OSTRING_TO_OUSTRING_CVTFLAGS, or see
    <http://udk.openoffice.org/cpp/man/spec/textconversion.html> for more
    details.
 */
inline OUString OStringToOUString( const OString & rStr,
                                   rtl_TextEncoding encoding,
                                   sal_uInt32 convertFlags = OSTRING_TO_OUSTRING_CVTFLAGS )
{
    return OUString( rStr.getStr(), rStr.getLength(), encoding, convertFlags );
}

/** Convert an OUString to an OString, using a specific text encoding.

    The lengths of the two strings may differ (e.g., for double-byte
    encodings, UTF-7, UTF-8).

    @param rStr
    an OUString to convert.

    @param encoding
    the text encoding to use for conversion.

    @param convertFlags
    flags which control the conversion.  Either use
    OUSTRING_TO_OSTRING_CVTFLAGS, or see
    <http://udk.openoffice.org/cpp/man/spec/textconversion.html> for more
    details.
 */
inline OString OUStringToOString( const OUString & rUnicode,
                                  rtl_TextEncoding encoding,
                                  sal_uInt32 convertFlags = OUSTRING_TO_OSTRING_CVTFLAGS )
{
    return OString( rUnicode.getStr(), rUnicode.getLength(), encoding, convertFlags );
}

/* ======================================================================= */

} /* Namespace */

#endif /* _RTL_USTRING_HXX */

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