-
Notifications
You must be signed in to change notification settings - Fork 104
Expand file tree
/
Copy pathCsvReader.cs
More file actions
2508 lines (2165 loc) · 104 KB
/
CsvReader.cs
File metadata and controls
2508 lines (2165 loc) · 104 KB
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
using System;
using System.Collections;
using System.Collections.Generic;
#if !NETSTANDARD1_3
using System.Data;
using System.Data.Common;
#endif
using System.Globalization;
using System.IO;
using LumenWorks.Framework.IO.Csv.Resources;
using Debug = System.Diagnostics.Debug;
namespace LumenWorks.Framework.IO.Csv
{
using System.Text;
/// <summary>
/// Represents a reader that provides fast, non-cached, forward-only access to CSV data.
/// </summary>
#if NETSTANDARD1_3
public partial class CsvReader : IEnumerable<string[]>, IDisposable
#else
public partial class CsvReader : IDataReader, IEnumerable<string[]>
#endif
{
/// <summary>
/// Defines the default buffer size.
/// </summary>
public const int DefaultBufferSize = 0x1000;
/// <summary>
/// Defines the default delimiter character separating each field.
/// </summary>
public const char DefaultDelimiter = ',';
/// <summary>
/// Defines the default quote character wrapping every field.
/// </summary>
public const char DefaultQuote = '"';
/// <summary>
/// Defines the default escape character letting insert quotation characters inside a quoted field.
/// </summary>
public const char DefaultEscape = '"';
/// <summary>
/// Defines the default comment character indicating that a line is commented out.
/// </summary>
public const char DefaultComment = '#';
/// <summary>
/// Defines the default value for AddMark indicating should the CsvReader add null bytes removal mark ([removed x null bytes])
/// </summary>
private const bool DefaultAddMark = false;
/// <summary>
/// Defines the default value for Threshold indicating when the CsvReader should replace/remove consecutive null bytes
/// </summary>
private const int DefaultThreshold = 60;
/// <summary>
/// Contains the <see cref="T:TextReader"/> pointing to the CSV file.
/// </summary>
private TextReader _reader;
/// <summary>
/// Indicates if the class is initialized.
/// </summary>
private bool _initialized;
/// <summary>
/// Contains the dictionary of field indexes by header. The key is the field name and the value is its index.
/// </summary>
private Dictionary<string, int> _fieldHeaderIndexes;
/// <summary>
/// Contains the starting position of the next unread field.
/// </summary>
private int _nextFieldStart;
/// <summary>
/// Contains the index of the next unread field.
/// </summary>
private int _nextFieldIndex;
/// <summary>
/// Contains the array of the field values for the current record.
/// A null value indicates that the field have not been parsed.
/// </summary>
private string[] _fields;
/// <summary>
/// Contains the maximum number of fields to retrieve for each record.
/// </summary>
private int _fieldCount;
/// <summary>
/// Contains the read buffer.
/// </summary>
private char[] _buffer;
/// <summary>
/// Contains the current read buffer length.
/// </summary>
private int _bufferLength;
/// <summary>
/// Indicates if the end of the reader has been reached.
/// </summary>
private bool _eof;
/// <summary>
/// Indicates if the last read operation reached an EOL character.
/// </summary>
private bool _eol;
/// <summary>
/// Indicates if the first record is in cache.
/// This can happen when initializing a reader with no headers
/// because one record must be read to get the field count automatically
/// </summary>
private bool _firstRecordInCache;
/// <summary>
/// Like CsvReader(TextReader reader, bool hasHeaders) but removes consecutive null bytes above a threshold from source stream.
/// </summary>
/// <param name="stream">A <see cref="T:Stream"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="encoding"> specifies the encoding of the underlying stream.</param>
/// <param name="addMark"><see langword="true"/> if want to add a mark ([removed x null bytes]) to indicate removal, remove silently if <see langword="false"/>.</param>
/// <param name="threshold">only consecutive null bytes above this threshold will be removed or replaced by a mark.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="stream"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="stream"/>.</exception>
public CsvReader(Stream stream, bool hasHeaders, Encoding encoding, bool addMark = DefaultAddMark, int threshold = DefaultThreshold)
: this(new NullRemovalStreamReader(stream, addMark, threshold, encoding), hasHeaders)
{
}
/// <summary>
/// Like CsvReader(TextReader reader, bool hasHeaders, int bufferSize) but removes consecutive null bytes above a threshold from source stream.
/// </summary>
/// <param name="stream">A <see cref="T:Stream"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="encoding"> specifies the encoding of the underlying stream.</param>
/// <param name="bufferSize">The buffer size in bytes.</param>
/// <param name="addMark"><see langword="true"/> if want to add a mark ([removed x null bytes]) to indicate removal, remove silently if <see langword="false"/>.</param>
/// <param name="threshold"> only consecutive null bytes above this threshold will be removed or replaced by a mark.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="stream"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="stream"/>.</exception>
public CsvReader(Stream stream, bool hasHeaders, Encoding encoding, int bufferSize, bool addMark = DefaultAddMark, int threshold = DefaultThreshold)
: this(new NullRemovalStreamReader(stream, addMark, threshold, encoding, bufferSize), hasHeaders, bufferSize)
{
}
/// <summary>
/// Like CsvReader(TextReader reader, bool hasHeaders, char delimiter) but removes consecutive null bytes above a threshold from source stream.
/// </summary>
/// <param name="stream">A <see cref="T:Stream"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="encoding"> specifies the encoding of the underlying stream.</param>
/// <param name="delimiter">The delimiter character separating each field (default is ',').</param>
/// <param name="addMark"><see langword="true"/> if want to add a mark ([removed x null bytes]) to indicate removal, remove silently if <see langword="false"/>.</param>
/// <param name="threshold"> only consecutive null bytes above this threshold will be removed or replaced by a mark.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="stream"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="stream"/>.</exception>
public CsvReader(Stream stream, bool hasHeaders, Encoding encoding, char delimiter, bool addMark = DefaultAddMark, int threshold = DefaultThreshold)
: this(new NullRemovalStreamReader(stream, addMark, threshold, encoding), hasHeaders, delimiter)
{
}
/// <summary>
/// Like CsvReader(TextReader reader, bool hasHeaders, char delimiter, int bufferSize) but removes consecutive null bytes above a threshold from source stream.
/// </summary>
/// <param name="stream">A <see cref="T:Stream"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="encoding"> specifies the encoding of the underlying stream.</param>
/// <param name="delimiter">The delimiter character separating each field (default is ',').</param>
/// <param name="bufferSize">The buffer size in bytes.</param>
/// <param name="addMark"><see langword="true"/> if want to add a mark ([removed x null bytes]) to indicate removal, remove silently if <see langword="false"/>.</param>
/// <param name="threshold"> only consecutive null bytes above this threshold will be removed or replaced by a mark.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="stream"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="stream"/>.</exception>
public CsvReader(Stream stream, bool hasHeaders, Encoding encoding, char delimiter, int bufferSize, bool addMark = DefaultAddMark, int threshold = DefaultThreshold)
: this(new NullRemovalStreamReader(stream, addMark, threshold, encoding, bufferSize), hasHeaders, delimiter, bufferSize)
{
}
/// <summary>
/// Like CsvReader(TextReader reader, bool hasHeaders, char delimiter, char quote, char escape, char comment, ValueTrimmingOptions trimmingOptions, string nullValue)
/// but removes consecutive null bytes above a threshold from source stream.
/// </summary>
/// <param name="stream">A <see cref="T:Stream"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="encoding"> specifies the encoding of the underlying stream.</param>
/// <param name="delimiter">The delimiter character separating each field (default is ',').</param>
/// <param name="quote">The quotation character wrapping every field (default is ''').</param>
/// <param name="escape">
/// The escape character letting insert quotation characters inside a quoted field (default is '\').
/// If no escape character, set to '\0' to gain some performance.
/// </param>
/// <param name="comment">The comment character indicating that a line is commented out (default is '#').</param>
/// <param name="trimmingOptions">Determines which values should be trimmed.</param>
/// <param name="nullValue">The value which denotes a DbNull-value.</param>
/// <param name="addMark"><see langword="true"/> if want to add a mark ([removed x null bytes]) to indicate removal, remove silently if <see langword="false"/>.</param>
/// <param name="threshold"> only consecutive null bytes above this threshold will be removed or replaced by a mark.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="stream"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="stream"/>.</exception>
public CsvReader(Stream stream, bool hasHeaders, Encoding encoding, char delimiter, char quote, char escape, char comment, ValueTrimmingOptions trimmingOptions, string nullValue = null, bool addMark = DefaultAddMark, int threshold = DefaultThreshold)
: this(new NullRemovalStreamReader(stream, addMark, threshold, encoding), hasHeaders, delimiter, quote, escape, comment, trimmingOptions, DefaultBufferSize, nullValue)
{
}
/// <summary>
/// Like CsvReader(TextReader reader, bool hasHeaders, char delimiter, char quote, char escape, char comment, ValueTrimmingOptions trimmingOptions, int bufferSize, string nullValue)
/// but removes consecutive null bytes above a threshold from source stream.
/// </summary>
/// <param name="stream">A <see cref="T:Stream"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="encoding"> specifies the encoding of the underlying stream.</param>
/// <param name="delimiter">The delimiter character separating each field (default is ',').</param>
/// <param name="quote">The quotation character wrapping every field (default is ''').</param>
/// <param name="escape">
/// The escape character letting insert quotation characters inside a quoted field (default is '\').
/// If no escape character, set to '\0' to gain some performance.
/// </param>
/// <param name="comment">The comment character indicating that a line is commented out (default is '#').</param>
/// <param name="trimmingOptions">Determines which values should be trimmed.</param>
/// <param name="bufferSize">The buffer size in bytes.</param>
/// <param name="nullValue">The value which denotes a DbNull-value.</param>
/// <param name="addMark"><see langword="true"/> if want to add a mark ([removed x null bytes]) to indicate removal, remove silently if <see langword="false"/>.</param>
/// <param name="threshold"> only consecutive null bytes above this threshold will be removed or replace by a mark.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="stream"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="stream"/>.</exception>
public CsvReader(Stream stream, bool hasHeaders, Encoding encoding, char delimiter, char quote, char escape, char comment, ValueTrimmingOptions trimmingOptions, int bufferSize, string nullValue = null, bool addMark = DefaultAddMark, int threshold = DefaultThreshold)
: this(new NullRemovalStreamReader(stream, addMark, threshold, encoding, bufferSize), hasHeaders, delimiter, quote, escape, comment, trimmingOptions, bufferSize, nullValue)
{
}
/// <summary>
/// Initializes a new instance of the CsvReader class.
/// </summary>
/// <param name="reader">A <see cref="T:TextReader"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/>If field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="reader"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="reader"/>.</exception>
public CsvReader(TextReader reader, bool hasHeaders) : this(reader, hasHeaders, DefaultDelimiter, DefaultQuote)
{
}
/// <summary>
/// Initializes a new instance of the CsvReader class.
/// </summary>
/// <param name="reader">A <see cref="T:TextReader"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="bufferSize">The buffer size in bytes.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="reader"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="reader"/>.</exception>
public CsvReader(TextReader reader, bool hasHeaders, int bufferSize) : this(reader, hasHeaders, DefaultDelimiter, DefaultQuote, bufferSize: bufferSize)
{
}
/// <summary>
/// Initializes a new instance of the CsvReader class.
/// </summary>
/// <param name="reader">A <see cref="T:TextReader"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="delimiter">The delimiter character separating each field (default is ',').</param>
/// <exception cref="T:ArgumentNullException"><paramref name="reader"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="reader"/>.</exception>
public CsvReader(TextReader reader, bool hasHeaders, char delimiter) : this(reader, hasHeaders, delimiter, DefaultQuote)
{
}
/// <summary>
/// Initializes a new instance of the CsvReader class.
/// </summary>
/// <param name="reader">A <see cref="T:TextReader"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="delimiter">The delimiter character separating each field (default is ',').</param>
/// <param name="bufferSize">The buffer size in bytes.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="reader"/> is a <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentException">Cannot read from <paramref name="reader"/>.</exception>
public CsvReader(TextReader reader, bool hasHeaders, char delimiter, int bufferSize) : this(reader, hasHeaders, delimiter, DefaultQuote, bufferSize: bufferSize)
{
}
/// <summary>
/// Initializes a new instance of the CsvReader class.
/// </summary>
/// <param name="reader">A <see cref="T:TextReader"/> pointing to the CSV file.</param>
/// <param name="hasHeaders"><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</param>
/// <param name="delimiter">The delimiter character separating each field (default is ',').</param>
/// <param name="quote">The quotation character wrapping every field (default is ''').</param>
/// <param name="escape">
/// The escape character letting insert quotation characters inside a quoted field (default is '\').
/// If no escape character, set to '\0' to gain some performance.
/// </param>
/// <param name="comment">The comment character indicating that a line is commented out (default is '#').</param>
/// <param name="trimmingOptions">Determines which values should be trimmed.</param>
/// <param name="bufferSize">The buffer size in bytes.</param>
/// <param name="nullValue">The value which denotes a DbNull-value.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="reader"/> is a <see langword="null"/>.</exception>
/// <exception cref="ArgumentOutOfRangeException"><paramref name="bufferSize"/> must be 1 or more.</exception>
public CsvReader(TextReader reader, bool hasHeaders = true, char delimiter = DefaultDelimiter, char quote = DefaultQuote, char escape = DefaultEscape, char comment = DefaultComment, ValueTrimmingOptions trimmingOptions = ValueTrimmingOptions.UnquotedOnly, int bufferSize = DefaultBufferSize, string nullValue = null)
{
#if DEBUG
#if !NETSTANDARD1_3
_allocStack = new System.Diagnostics.StackTrace();
#endif
#endif
if (reader == null)
{
throw new ArgumentNullException(nameof(reader));
}
if (bufferSize <= 0)
{
throw new ArgumentOutOfRangeException(nameof(bufferSize), bufferSize, ExceptionMessage.BufferSizeTooSmall);
}
BufferSize = bufferSize;
var streamReader = reader as StreamReader;
if (streamReader != null)
{
var stream = streamReader.BaseStream;
if (stream.CanSeek)
{
// Handle bad implementations returning 0 or less
if (stream.Length > 0)
{
BufferSize = (int) Math.Min(bufferSize, stream.Length);
}
}
}
_reader = reader;
Delimiter = delimiter;
Quote = quote;
Escape = escape;
Comment = comment;
HasHeaders = hasHeaders;
TrimmingOption = trimmingOptions;
NullValue = nullValue;
SupportsMultiline = true;
SkipEmptyLines = true;
Columns = new List<Column>();
DefaultHeaderName = "Column";
FileRecordIndex = -1;
DefaultParseErrorAction = ParseErrorAction.RaiseEvent;
}
/// <summary>
/// Occurs when there is an error while parsing the CSV stream.
/// </summary>
public event EventHandler<ParseErrorEventArgs> ParseError;
/// <summary>
/// Raises the <see cref="M:ParseError"/> event.
/// </summary>
/// <param name="e">The <see cref="ParseErrorEventArgs"/> that contains the event data.</param>
protected virtual void OnParseError(ParseErrorEventArgs e)
{
var handler = ParseError;
handler?.Invoke(this, e);
}
/// <summary>
/// Occurs when HasHeaders is true and a duplicate Column Header Name is encountered.
/// Setting the HeaderName property on this column will prevent the library from throwing a duplicate key exception
/// </summary>
public event EventHandler<DuplicateHeaderEventArgs> DuplicateHeaderEncountered;
/// <summary>
/// Gets the comment character indicating that a line is commented out.
/// </summary>
/// <value>The comment character indicating that a line is commented out.</value>
public char Comment { get; }
/// <summary>
/// Gets the escape character letting insert quotation characters inside a quoted field.
/// </summary>
/// <value>The escape character letting insert quotation characters inside a quoted field.</value>
public char Escape { get; }
/// <summary>
/// Gets the delimiter character separating each field.
/// </summary>
/// <value>The delimiter character separating each field.</value>
public char Delimiter { get; }
/// <summary>
/// Gets the quotation character wrapping every field.
/// </summary>
/// <value>The quotation character wrapping every field.</value>
public char Quote { get; }
/// <summary>
/// Indicates if field names are located on the first non commented line.
/// </summary>
/// <value><see langword="true"/> if field names are located on the first non commented line, otherwise, <see langword="false"/>.</value>
public bool HasHeaders { get; }
/// <summary>
/// Indicates if spaces at the start and end of a field are trimmed.
/// </summary>
/// <value><see langword="true"/> if spaces at the start and end of a field are trimmed, otherwise, <see langword="false"/>.</value>
public ValueTrimmingOptions TrimmingOption { get; }
/// <summary>
/// Contains the value which denotes a DbNull-value.
/// </summary>
public string NullValue { get; }
/// <summary>
/// Gets the buffer size.
/// </summary>
public int BufferSize { get; }
/// <summary>
/// Gets or sets the default action to take when a parsing error has occured.
/// </summary>
/// <value>The default action to take when a parsing error has occured.</value>
public ParseErrorAction DefaultParseErrorAction { get; set; }
/// <summary>
/// Gets or sets the action to take when a field is missing.
/// </summary>
/// <value>The action to take when a field is missing.</value>
public MissingFieldAction MissingFieldAction { get; set; }
/// <summary>
/// Gets or sets a value indicating if the reader supports multiline fields.
/// </summary>
/// <value>A value indicating if the reader supports multiline field.</value>
public bool SupportsMultiline { get; set; }
/// <summary>
/// Gets or sets a value giving a maxmimum length (in bytes) for any quoted field.
/// </summary>
/// <value>The maximum length (in bytes) of a CSV field.</value>
public int? MaxQuotedFieldLength { get; set; }
/// <summary>
/// Gets or sets a value indicating if the reader will skip empty lines.
/// </summary>
/// <value>A value indicating if the reader will skip empty lines.</value>
public bool SkipEmptyLines { get; set; }
/// <summary>
/// Gets or sets the default header name when it is an empty string or only whitespaces.
/// The header index will be appended to the specified name.
/// </summary>
/// <value>The default header name when it is an empty string or only whitespaces.</value>
public string DefaultHeaderName { get; set; }
/// <summary>
/// Gets or sets column information for the CSV.
/// </summary>
public IList<Column> Columns { get; set; }
/// <summary>
/// Gets or sets whether we should use the column default values if the field is not in the record.
/// </summary>
public bool UseColumnDefaults { get; set; }
/// <summary>
/// Gets the maximum number of fields to retrieve for each record.
/// </summary>
/// <value>The maximum number of fields to retrieve for each record.</value>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public int FieldCount
{
get
{
EnsureInitialize();
return _fieldCount;
}
}
/// <summary>
/// Gets a value that indicates whether the current stream position is at the end of the stream.
/// </summary>
/// <value><see langword="true"/> if the current stream position is at the end of the stream; otherwise <see langword="false"/>.</value>
public virtual bool EndOfStream { get; private set; }
/// <summary>
/// Gets the field headers.
/// </summary>
/// <returns>The field headers or an empty array if headers are not supported.</returns>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public string[] GetFieldHeaders()
{
EnsureInitialize();
Debug.Assert(Columns != null, "Columns must be non null.");
var fieldHeaders = new string[Columns.Count];
for (var i = 0; i < fieldHeaders.Length; i++)
{
fieldHeaders[i] = Columns[i].Name;
}
return fieldHeaders;
}
/// <summary>
/// Gets the current record index in the CSV file.
/// <para>
/// A value of <see cref="M:Int32.MinValue"/> means that the reader has not been initialized yet.
/// Otherwise, a negative value means that no record has been read yet.
/// </para>
/// </summary>
/// <value>The current record index in the CSV file.</value>
protected long FileRecordIndex { get; private set; }
/// <summary>
/// Gets the current record index in the CSV file.
/// <para>
/// A value of <see cref="M:Int32.MinValue"/> means that the reader has not been initialized yet.
/// Otherwise, a negative value means that no record has been read yet.
/// </para>
/// </summary>
/// <value>The current record index in the CSV file.</value>
public virtual long CurrentRecordIndex => FileRecordIndex;
/// <summary>
/// Indicates if one or more field are missing for the current record.
/// Resets after each successful record read.
/// </summary>
public bool MissingFieldFlag { get; private set; }
/// <summary>
/// Indicates if a parse error occured for the current record.
/// Resets after each successful record read.
/// </summary>
public bool ParseErrorFlag { get; private set; }
/// <summary>
/// Gets the field with the specified name and record position. <see cref="M:hasHeaders"/> must be <see langword="true"/>.
/// </summary>
/// <value>
/// The field with the specified name and record position.
/// </value>
/// <exception cref="T:ArgumentNullException"><paramref name="field"/> is <see langword="null"/> or an empty string.</exception>
/// <exception cref="T:InvalidOperationException">The CSV does not have headers (<see cref="M:HasHeaders"/> property is <see langword="false"/>).</exception>
/// <exception cref="T:ArgumentException"><paramref name="field"/> not found.</exception>
/// <exception cref="T:ArgumentOutOfRangeException">Record index must be > 0.</exception>
/// <exception cref="T:InvalidOperationException">Cannot move to a previous record in forward-only mode.</exception>
/// <exception cref="T:EndOfStreamException">Cannot read record at <paramref name="record"/>.</exception>
/// <exception cref="T:MalformedCsvException">The CSV appears to be corrupt at the current position.</exception>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public string this[int record, string field]
{
get
{
if (!MoveTo(record))
{
throw new InvalidOperationException(string.Format(CultureInfo.InvariantCulture, ExceptionMessage.CannotReadRecordAtIndex, record));
}
return this[field];
}
}
/// <summary>
/// Gets the field at the specified index and record position.
/// </summary>
/// <value>
/// The field at the specified index and record position.
/// A <see langword="null"/> is returned if the field cannot be found for the record.
/// </value>
/// <exception cref="T:ArgumentOutOfRangeException"><paramref name="field"/> must be included in [0, <see cref="M:FieldCount"/>[.</exception>
/// <exception cref="T:ArgumentOutOfRangeException">Record index must be > 0.</exception>
/// <exception cref="T:InvalidOperationException">Cannot move to a previous record in forward-only mode.</exception>
/// <exception cref="T:EndOfStreamException">Cannot read record at <paramref name="record"/>.</exception>
/// <exception cref="T:MalformedCsvException">The CSV appears to be corrupt at the current position.</exception>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public string this[int record, int field]
{
get
{
if (!MoveTo(record))
{
throw new InvalidOperationException(string.Format(CultureInfo.InvariantCulture, ExceptionMessage.CannotReadRecordAtIndex, record));
}
return this[field];
}
}
/// <summary>
/// Gets the field with the specified name. <see cref="M:hasHeaders"/> must be <see langword="true"/>.
/// </summary>
/// <value>
/// The field with the specified name.
/// </value>
/// <exception cref="T:ArgumentNullException"><paramref name="field"/> is <see langword="null"/> or an empty string.</exception>
/// <exception cref="T:InvalidOperationException">The CSV does not have headers (<see cref="M:HasHeaders"/> property is <see langword="false"/>).</exception>
/// <exception cref="T:ArgumentException"><paramref name="field"/> not found.</exception>
/// <exception cref="T:MalformedCsvException">The CSV appears to be corrupt at the current position.</exception>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public string this[string field]
{
get
{
if (string.IsNullOrEmpty(field))
{
throw new ArgumentNullException(nameof(field));
}
if (!HasHeaders)
{
throw new InvalidOperationException(ExceptionMessage.NoHeaders);
}
var index = GetFieldIndex(field);
if (index < 0)
{
throw new ArgumentException(string.Format(CultureInfo.InvariantCulture, ExceptionMessage.FieldHeaderNotFound, field), "field");
}
return this[index];
}
}
/// <summary>
/// Gets the field at the specified index.
/// </summary>
/// <value>The field at the specified index.</value>
/// <exception cref="T:ArgumentOutOfRangeException"><paramref name="field"/> must be included in [0, <see cref="M:FieldCount"/>[.</exception>
/// <exception cref="T:InvalidOperationException">No record read yet. Call ReadLine() first.</exception>
/// <exception cref="T:MalformedCsvException">The CSV appears to be corrupt at the current position.</exception>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public virtual string this[int field] => ReadField(field, false, false);
/// <summary>
/// Ensures that the reader is initialized.
/// </summary>
private void EnsureInitialize()
{
if (!_initialized)
{
ReadNextRecord(true, false);
}
Debug.Assert(Columns != null);
Debug.Assert(Columns.Count > 0 || (Columns.Count == 0 && (_fieldHeaderIndexes == null || _fieldHeaderIndexes.Count == 0)));
}
/// <summary>
/// Gets the field index for the provided header.
/// </summary>
/// <param name="header">The header to look for.</param>
/// <returns>The field index for the provided header. -1 if not found.</returns>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public int GetFieldIndex(string header)
{
EnsureInitialize();
if (_fieldHeaderIndexes != null && _fieldHeaderIndexes.TryGetValue(header, out int index))
{
return index;
}
else
{
return -1;
}
}
/// <summary>
/// Checks if a header exists in the current fieldHedaerIndexes
/// </summary>
/// <param name="header">The header to look for.</param>
/// <returns>A flag indicating if the header exists</returns>
public bool HasHeader(string header)
{
EnsureInitialize();
if (string.IsNullOrEmpty(header))
{
throw new ArgumentNullException(nameof(header));
}
if (_fieldHeaderIndexes != null)
{
return _fieldHeaderIndexes.ContainsKey(header);
}
else
{
return false;
}
}
/// <summary>
/// Copies the field array of the current record to a one-dimensional array, starting at the beginning of the target array.
/// </summary>
/// <param name="array"> The one-dimensional <see cref="T:Array"/> that is the destination of the fields of the current record.</param>
/// <param name="index">The zero-based index in <paramref name="array"/> at which copying begins.</param>
/// <exception cref="T:ArgumentNullException"><paramref name="array"/> is <see langword="null"/>.</exception>
/// <exception cref="T:ArgumentOutOfRangeException"><paramref name="index"/> is les than zero or is equal to or greater than the length <paramref name="array"/>.</exception>
/// <exception cref="InvalidOperationException">No current record.</exception>
/// <exception cref="ArgumentException">The number of fields in the record is greater than the available space from <paramref name="index"/> to the end of <paramref name="array"/>.</exception>
public void CopyCurrentRecordTo(string[] array, int index = 0)
{
if (array == null)
{
throw new ArgumentNullException(nameof(array));
}
if (index < 0 || index >= array.Length)
{
throw new ArgumentOutOfRangeException(nameof(index), index, string.Empty);
}
if (FileRecordIndex < 0 || !_initialized)
{
throw new InvalidOperationException(ExceptionMessage.NoCurrentRecord);
}
if (array.Length - index < _fieldCount)
{
throw new ArgumentException(ExceptionMessage.NotEnoughSpaceInArray, nameof(array));
}
for (var i = 0; i < _fieldCount; i++)
{
array[index + i] = ParseErrorFlag ? null : this[i];
}
}
/// <summary>
/// Gets the current raw CSV data.
/// </summary>
/// <remarks>Used for exception handling purpose.</remarks>
/// <returns>The current raw CSV data.</returns>
public string GetCurrentRawData()
{
if (_buffer != null && _bufferLength > 0)
{
return new string(_buffer, 0, _bufferLength);
}
else
{
return string.Empty;
}
}
/// <summary>
/// Indicates whether the specified Unicode character is categorized as white space.
/// </summary>
/// <param name="c">A Unicode character.</param>
/// <returns><see langword="true"/> if <paramref name="c"/> is white space; otherwise, <see langword="false"/>.</returns>
private bool IsWhiteSpace(char c)
{
// Handle cases where the delimiter is a whitespace (e.g. tab)
if (c == Delimiter)
{
return false;
}
else
{
// See char.IsLatin1(char c) in Reflector
if (c <= '\x00ff')
{
return (c == ' ' || c == '\t');
}
else
{
return (CharUnicodeInfo.GetUnicodeCategory(c) == UnicodeCategory.SpaceSeparator);
}
}
}
/// <summary>
/// Moves to the specified record index.
/// </summary>
/// <param name="record">The record index.</param>
/// <returns><c>true</c> if the operation was successful; otherwise, <c>false</c>.</returns>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
public virtual bool MoveTo(long record)
{
if (record < FileRecordIndex)
{
return false;
}
// Get number of record to read
var offset = record - FileRecordIndex;
while (offset > 0)
{
if (!ReadNextRecord())
{
return false;
}
offset--;
}
return true;
}
/// <summary>
/// Parses a new line delimiter.
/// </summary>
/// <param name="pos">The starting position of the parsing. Will contain the resulting end position.</param>
/// <returns><see langword="true"/> if a new line delimiter was found; otherwise, <see langword="false"/>.</returns>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
private bool ParseNewLine(ref int pos)
{
Debug.Assert(pos <= _bufferLength);
// Check if already at the end of the buffer
if (pos == _bufferLength)
{
pos = 0;
if (!ReadBuffer())
{
return false;
}
}
var c = _buffer[pos];
// Treat \r as new line only if it's not the delimiter
if (c == '\r' && Delimiter != '\r')
{
pos++;
// Skip following \n (if there is one)
if (pos < _bufferLength)
{
if (_buffer[pos] == '\n')
{
pos++;
}
}
else
{
if (ReadBuffer())
{
if (_buffer[0] == '\n')
{
pos = 1;
}
else
{
pos = 0;
}
}
}
if (pos >= _bufferLength)
{
ReadBuffer();
pos = 0;
}
return true;
}
else if (c == '\n')
{
pos++;
if (pos >= _bufferLength)
{
ReadBuffer();
pos = 0;
}
return true;
}
return false;
}
/// <summary>
/// Determines whether the character at the specified position is a new line delimiter.
/// </summary>
/// <param name="pos">The position of the character to verify.</param>
/// <returns><see langword="true"/> if the character at the specified position is a new line delimiter; otherwise, <see langword="false"/>.</returns>
private bool IsNewLine(int pos)
{
Debug.Assert(pos < _bufferLength);
var c = _buffer[pos];
if (c == '\n')
{
return true;
}
else if (c == '\r' && Delimiter != '\r')
{
return true;
}
else
{
return false;
}
}
/// <summary>
/// Fills the buffer with data from the reader.
/// </summary>
/// <returns><see langword="true"/> if data was successfully read; otherwise, <see langword="false"/>.</returns>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
private bool ReadBuffer()
{
if (_eof)
{
return false;
}
CheckDisposed();
_bufferLength = _reader.Read(_buffer, 0, BufferSize);
if (_bufferLength > 0)
{
return true;
}
else
{
_eof = true;
_buffer = null;
return false;
}
}
/// <summary>
/// Reads the field at the specified index.
/// Any unread fields with an inferior index will also be read as part of the required parsing.
/// </summary>
/// <param name="field">The field index.</param>
/// <param name="initializing">Indicates if the reader is currently initializing.</param>
/// <param name="discardValue">Indicates if the value(s) are discarded.</param>
/// <returns>
/// The field at the specified index.
/// A <see langword="null"/> indicates that an error occured or that the last field has been reached during initialization.
/// </returns>
/// <exception cref="ArgumentOutOfRangeException"><paramref name="field"/> is out of range.</exception>
/// <exception cref="InvalidOperationException">There is no current record.</exception>
/// <exception cref="MissingFieldCsvException">The CSV data appears to be missing a field.</exception>
/// <exception cref="MalformedCsvException">The CSV data appears to be malformed.</exception>
/// <exception cref="T:System.ComponentModel.ObjectDisposedException">The instance has been disposed of.</exception>
private string ReadField(int field, bool initializing, bool discardValue)
{
if (!initializing)
{
var maxField = UseColumnDefaults ? Columns.Count : _fieldCount;
if (field < 0 || field >= maxField)
{
throw new ArgumentOutOfRangeException(nameof(field), field, string.Format(CultureInfo.InvariantCulture, ExceptionMessage.FieldIndexOutOfRange, field));
}
if (FileRecordIndex < 0)
{
throw new InvalidOperationException(ExceptionMessage.NoCurrentRecord);
}
if (Columns.Count > field && !string.IsNullOrEmpty(Columns[field].OverrideValue))
{
// Use the override value for this column.
return Columns[field].OverrideValue;
}
if (field >= _fieldCount)
{
// Use the column default as UseColumnDefaults is true at this point
return Columns[field].DefaultValue;
}
// Directly return field if cached
if (_fields[field] != null)
{
return _fields[field];
}
if (MissingFieldFlag)
{
return HandleMissingField(null, field, ref _nextFieldStart);
}
}
CheckDisposed();
var index = _nextFieldIndex;