-
Notifications
You must be signed in to change notification settings - Fork 1
/
rapidcsv.h
1053 lines (966 loc) · 30.1 KB
/
rapidcsv.h
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
/*
* rapidcsv.h
*
* URL: https://github.com/d99kris/rapidcsv
* Version: 3.1
*
* Copyright (C) 2017-2018 Kristofer Berggren
* All rights reserved.
*
* rapidcsv is distributed under the BSD 3-Clause license, see LICENSE for details.
*
*/
#pragma once
#include <algorithm>
#include <cassert>
#include <cmath>
#include <fstream>
#include <iostream>
#include <map>
#include <sstream>
#include <string>
#include <typeinfo>
#include <vector>
#if defined(_MSC_VER)
#include <BaseTsd.h>
typedef SSIZE_T ssize_t;
#endif
namespace rapidcsv
{
#if defined(_MSC_VER)
static const bool sPlatformHasCR = true;
#else
static const bool sPlatformHasCR = false;
#endif
/**
* @brief Datastructure holding parameters controlling how invalid numbers (including
* empty strings) should be handled.
*/
struct ConverterParams
{
/**
* @brief Constructor
* @param pHasDefaultConverter specifies if conversion of non-numerical strings shall be
* converted to a default numerical value, instead of causing
* an exception to be thrown (default).
* @param pDefaultFloat floating-point default value to represent invalid numbers.
* @param pDefaultInteger integer default value to represent invalid numbers.
*/
explicit ConverterParams(const bool pHasDefaultConverter = false,
const long double pDefaultFloat = std::numeric_limits<long double>::signaling_NaN(),
const long long pDefaultInteger = 0)
: mHasDefaultConverter(pHasDefaultConverter)
, mDefaultFloat(pDefaultFloat)
, mDefaultInteger(pDefaultInteger)
{
}
/**
* @brief specifies if conversion of non-numerical strings shall be converted to a default
* numerical value, instead of causing an exception to be thrown (default).
*/
bool mHasDefaultConverter;
/**
* @brief floating-point default value to represent invalid numbers.
*/
long double mDefaultFloat;
/**
* @brief integer default value to represent invalid numbers.
*/
long long mDefaultInteger;
};
/**
* @brief Exception thrown when attempting to access Document data in a datatype which
* is not supported by the Converter class.
*/
class no_converter : public std::exception
{
/**
* @brief Provides details about the exception
* @returns an explanatory string
*/
virtual const char* what() const throw()
{
return "unsupported conversion datatype";
}
};
/**
* @brief Class providing conversion to/from numerical datatypes and strings. Only
* intended for rapidcsv internal usage, but exposed externally to allow
* specialization for custom datatype conversions.
*/
template<typename T>
class Converter
{
public:
/**
* @brief Constructor
* @param pConverterParams specifies how conversion of non-numerical values to
* numerical datatype shall be handled.
*/
Converter(const ConverterParams& pConverterParams)
: mConverterParams(pConverterParams)
{
}
/**
* @brief Converts numerical value to string representation.
* @param pVal numerical value
* @param pStr output string
*/
void ToStr(const T& pVal, std::string& pStr) const
{
if (typeid(T) == typeid(int) ||
typeid(T) == typeid(long) ||
typeid(T) == typeid(long long) ||
typeid(T) == typeid(unsigned) ||
typeid(T) == typeid(unsigned long) ||
typeid(T) == typeid(unsigned long long) ||
typeid(T) == typeid(float) ||
typeid(T) == typeid(double) ||
typeid(T) == typeid(long double) ||
typeid(T) == typeid(char))
{
std::ostringstream out;
out << pVal;
pStr = out.str();
}
else
{
throw no_converter();
}
}
/**
* @brief Converts string holding a numerical value to numerical datatype representation.
* @param pVal numerical value
* @param pStr output string
*/
void ToVal(const std::string& pStr, T& pVal) const
{
try
{
if (typeid(T) == typeid(int))
{
pVal = static_cast<T>(std::stoi(pStr));
return;
}
else if (typeid(T) == typeid(long))
{
pVal = static_cast<T>(std::stol(pStr));
return;
}
else if (typeid(T) == typeid(long long))
{
pVal = static_cast<T>(std::stoll(pStr));
return;
}
else if (typeid(T) == typeid(unsigned))
{
pVal = static_cast<T>(std::stoul(pStr));
return;
}
else if (typeid(T) == typeid(unsigned long))
{
pVal = static_cast<T>(std::stoul(pStr));
return;
}
else if (typeid(T) == typeid(unsigned long long))
{
pVal = static_cast<T>(std::stoull(pStr));
return;
}
}
catch (...)
{
if (!mConverterParams.mHasDefaultConverter)
{
throw;
}
else
{
pVal = static_cast<T>(mConverterParams.mDefaultInteger);
return;
}
}
try
{
if (typeid(T) == typeid(float))
{
pVal = static_cast<T>(std::stof(pStr));
return;
}
else if (typeid(T) == typeid(double))
{
pVal = static_cast<T>(std::stod(pStr));
return;
}
else if (typeid(T) == typeid(long double))
{
pVal = static_cast<T>(std::stold(pStr));
return;
}
}
catch (...)
{
if (!mConverterParams.mHasDefaultConverter)
{
throw;
}
else
{
pVal = static_cast<T>(mConverterParams.mDefaultFloat);
return;
}
}
if (typeid(T) == typeid(char))
{
pVal = static_cast<T>(pStr[0]);
return;
}
else
{
throw no_converter();
}
}
private:
const ConverterParams& mConverterParams;
};
/**
* @brief Specialized implementation handling string to string conversion.
* @param pVal string
* @param pStr string
*/
template<>
inline void Converter<std::string>::ToStr(const std::string& pVal, std::string& pStr) const
{
pStr = pVal;
}
/**
* @brief Specialized implementation handling string to string conversion.
* @param pVal string
* @param pStr string
*/
template<>
inline void Converter<std::string>::ToVal(const std::string& pStr, std::string& pVal) const
{
pVal = pStr;
}
/**
* @brief Datastructure holding parameters controlling which row and column should be
* treated as labels.
*/
struct LabelParams
{
/**
* @brief Constructor
* @param pColumnNameIdx specifies the zero-based row index of the column labels, setting
* it to -1 prevents column lookup by label name, and gives access
* to all rows as document data.
* @param pRowNameIdx specifies the zero-based column index of the row labels, setting
* it to -1 prevents row lookup by label name, and gives access
* to all columns as document data.
*/
explicit LabelParams(const int pColumnNameIdx = 0, const int pRowNameIdx = 0)
: mColumnNameIdx(pColumnNameIdx)
, mRowNameIdx(pRowNameIdx)
{
}
/**
* @brief specifies the zero-based row index of the column labels.
*/
int mColumnNameIdx;
/**
* @brief specifies the zero-based column index of the row labels.
*/
int mRowNameIdx;
};
/**
* @brief Datastructure holding parameters controlling how the CSV data fields are separated.
*/
struct SeparatorParams
{
/**
* @brief Constructor
* @param pSeparator specifies the column separator (default ',').
* @param pHasCR specifies whether a new document (i.e. not an existing document read)
* should use CR/LF instead of only LF (default is to use standard
* behavior of underlying platforms - CR/LF for Win, and LF for others).
*/
explicit SeparatorParams(const char pSeparator = ',', const bool pHasCR = sPlatformHasCR)
: mSeparator(pSeparator)
, mHasCR(pHasCR)
{
}
/**
* @brief specifies the column separator.
*/
char mSeparator;
/**
* @brief specifies whether new documents should use CR/LF instead of LF.
*/
bool mHasCR;
};
/**
* @brief Class representing a CSV document.
*/
class Document
{
public:
/**
* @brief Constructor
* @param pPath specifies the path of an existing CSV-file to populate the Document
* data with.
* @param pLabelParams specifies which row and column should be treated as labels.
* @param pSeparatorParams specifies which field and row separators should be used.
* @param pConverterParams specifies how invalid numbers (including empty strings) should be
* handled.
*/
explicit Document(const std::string& pPath = std::string(),
const LabelParams& pLabelParams = LabelParams(),
const SeparatorParams& pSeparatorParams = SeparatorParams(),
const ConverterParams& pConverterParams = ConverterParams())
: mPath(pPath)
, mLabelParams(pLabelParams)
, mSeparatorParams(pSeparatorParams)
, mConverterParams(pConverterParams)
{
if (!mPath.empty())
{
ReadCsv();
}
}
/**
* @brief Constructor
* @param pStream CSV data content.
* @param pLength CSV data length.
* @param pLabelParams specifies which row and column should be treated as labels.
* @param pSeparatorParams specifies which field and row separators should be used.
* @param pConverterParams specifies how invalid numbers (including empty strings) should be
* handled.
*/
explicit Document(std::istream &pStream, std::streamsize pLength,
const LabelParams& pLabelParams = LabelParams(),
const SeparatorParams& pSeparatorParams = SeparatorParams(),
const ConverterParams& pConverterParams = ConverterParams())
: mPath()
, mLabelParams(pLabelParams)
, mSeparatorParams(pSeparatorParams)
, mConverterParams(pConverterParams)
{
ReadCsv(pStream, pLength);
}
/**
* @brief Copy constructor
* @param pDocument specifies the Document instance to copy.
*/
explicit Document(const Document& pDocument)
: mPath(pDocument.mPath)
, mLabelParams(pDocument.mLabelParams)
, mSeparatorParams(pDocument.mSeparatorParams)
, mConverterParams(pDocument.mConverterParams)
, mData(pDocument.mData)
, mColumnNames(pDocument.mColumnNames)
, mRowNames(pDocument.mRowNames)
{
}
/**
* @brief Read Document data from file.
* @param pPath specifies the path of an existing CSV-file to populate the Document
* data with.
*/
void Load(const std::string& pPath)
{
mPath = pPath;
ReadCsv();
}
/**
* @brief Write Document data to file.
* @param pPath optionally specifies the path where the CSV-file will be created
* (if not specified, the original path provided when creating or
* loading the Document data will be used).
*/
void Save(const std::string& pPath = std::string())
{
if (!pPath.empty())
{
mPath = pPath;
}
WriteCsv();
}
/**
* @brief Write Document data to stream.
* @param pStream Stream to write the data to.
*/
void Save(std::ostream &pStream)
{
WriteCsv(pStream);
}
/**
* @brief Get column by index.
* @param pColumnIdx zero-based column index.
* @returns vector of column data.
*/
template<typename T>
std::vector<T> GetColumn(const size_t pColumnIdx) const
{
const ssize_t columnIdx = pColumnIdx + (mLabelParams.mRowNameIdx + 1);
std::vector<T> column;
Converter<T> converter(mConverterParams);
for (auto itRow = mData.begin(); itRow != mData.end(); ++itRow)
{
if (std::distance(mData.begin(), itRow) > mLabelParams.mColumnNameIdx)
{
T val;
converter.ToVal(itRow->at(columnIdx), val);
column.push_back(val);
}
}
return column;
}
/**
* @brief Get column by name.
* @param pColumnName column label name.
* @returns vector of column data.
*/
template<typename T>
std::vector<T> GetColumn(const std::string& pColumnName) const
{
const ssize_t columnIdx = GetColumnIdx(pColumnName);
if (columnIdx < 0)
{
throw std::out_of_range("column not found: " + pColumnName);
}
return GetColumn<T>(columnIdx);
}
/**
* @brief Set column by index.
* @param pColumnIdx zero-based column index.
* @param pColumn vector of column data.
*/
template<typename T>
void SetColumn(const size_t pColumnIdx, const std::vector<T>& pColumn)
{
const size_t columnIdx = pColumnIdx + (mLabelParams.mRowNameIdx + 1);
while (pColumn.size() + (mLabelParams.mColumnNameIdx + 1) > GetDataRowCount())
{
std::vector<std::string> row;
row.resize(GetDataColumnCount());
mData.push_back(row);
}
if ((columnIdx + 1) > GetDataColumnCount())
{
for (auto itRow = mData.begin(); itRow != mData.end(); ++itRow)
{
itRow->resize(columnIdx + 1 + (mLabelParams.mRowNameIdx + 1));
}
}
Converter<T> converter(mConverterParams);
for (auto itRow = pColumn.begin(); itRow != pColumn.end(); ++itRow)
{
std::string str;
converter.ToStr(*itRow, str);
mData.at(std::distance(pColumn.begin(), itRow) + (mLabelParams.mColumnNameIdx + 1)).at(columnIdx) = str;
}
}
/**
* @brief Set column by name.
* @param pColumnName column label name.
* @param pColumn vector of column data.
*/
template<typename T>
void SetColumn(const std::string& pColumnName, const std::vector<T>& pColumn)
{
const ssize_t columnIdx = GetColumnIdx(pColumnName);
if (columnIdx < 0)
{
throw std::out_of_range("column not found: " + pColumnName);
}
SetColumn<T>(columnIdx, pColumn);
}
/**
* @brief Remove column by index.
* @param pColumnIdx zero-based column index.
*/
void RemoveColumn(const size_t pColumnIdx)
{
const ssize_t columnIdx = pColumnIdx + (mLabelParams.mRowNameIdx + 1);
for (auto itRow = mData.begin(); itRow != mData.end(); ++itRow)
{
itRow->erase(itRow->begin() + columnIdx);
}
}
/**
* @brief Remove column by name.
* @param pColumnName column label name.
*/
void RemoveColumn(const std::string& pColumnName)
{
ssize_t columnIdx = GetColumnIdx(pColumnName);
if (columnIdx < 0)
{
throw std::out_of_range("column not found: " + pColumnName);
}
RemoveColumn(columnIdx);
}
/**
* @brief Get number of data columns.
* @returns column count.
*/
size_t GetColumnCount() const
{
return (mData.size() > 0) ? (mData.at(0).size() - (mLabelParams.mRowNameIdx + 1)) : 0;
}
/**
* @brief Get row by index.
* @param pRowIdx zero-based row index.
* @returns vector of row data.
*/
template<typename T>
std::vector<T> GetRow(const size_t pRowIdx) const
{
const ssize_t rowIdx = pRowIdx + (mLabelParams.mColumnNameIdx + 1);
std::vector<T> row;
Converter<T> converter(mConverterParams);
for (auto itCol = mData.at(rowIdx).begin(); itCol != mData.at(rowIdx).end(); ++itCol)
{
if (std::distance(mData.at(rowIdx).begin(), itCol) > mLabelParams.mRowNameIdx)
{
T val;
converter.ToVal(*itCol, val);
row.push_back(val);
}
}
return row;
}
/**
* @brief Get row by name.
* @param pRowName row label name.
* @returns vector of row data.
*/
template<typename T>
std::vector<T> GetRow(const std::string& pRowName) const
{
ssize_t rowIdx = GetRowIdx(pRowName);
if (rowIdx < 0)
{
throw std::out_of_range("row not found: " + pRowName);
}
return GetRow<T>(rowIdx);
}
/**
* @brief Set row by index.
* @param pRowIdx zero-based row index.
* @param pRow vector of row data.
*/
template<typename T>
void SetRow(const size_t pRowIdx, const std::vector<T>& pRow)
{
const size_t rowIdx = pRowIdx + (mLabelParams.mColumnNameIdx + 1);
while ((rowIdx + 1) > GetDataRowCount())
{
std::vector<std::string> row;
row.resize(GetDataColumnCount());
mData.push_back(row);
}
if (pRow.size() > GetDataColumnCount())
{
for (auto itRow = mData.begin(); itRow != mData.end(); ++itRow)
{
itRow->resize(pRow.size() + (mLabelParams.mRowNameIdx + 1));
}
}
Converter<T> converter(mConverterParams);
for (auto itCol = pRow.begin(); itCol != pRow.end(); ++itCol)
{
std::string str;
converter.ToStr(*itCol, str);
mData.at(rowIdx).at(std::distance(pRow.begin(), itCol) + (mLabelParams.mRowNameIdx + 1)) = str;
}
}
/**
* @brief Set row by name.
* @param pRowName row label name.
* @param pRow vector of row data.
*/
template<typename T>
void SetRow(const std::string& pRowName, const std::vector<T>& pRow)
{
ssize_t rowIdx = GetRowIdx(pRowName);
if (rowIdx < 0)
{
throw std::out_of_range("row not found: " + pRowName);
}
return SetRow<T>(rowIdx, pRow);
}
/**
* @brief Remove row by index.
* @param pRowIdx zero-based row index.
*/
void RemoveRow(const size_t pRowIdx)
{
const ssize_t rowIdx = pRowIdx + (mLabelParams.mColumnNameIdx + 1);
mData.erase(mData.begin() + rowIdx);
}
/**
* @brief Remove row by name.
* @param pRowName row label name.
*/
void RemoveRow(const std::string& pRowName)
{
ssize_t rowIdx = GetRowIdx(pRowName);
if (rowIdx < 0)
{
throw std::out_of_range("row not found: " + pRowName);
}
RemoveRow(rowIdx);
}
/**
* @brief Get number of data rows.
* @returns row count.
*/
size_t GetRowCount() const
{
return mData.size() - (mLabelParams.mColumnNameIdx + 1);
}
/**
* @brief Get cell by index.
* @param pRowIdx zero-based row index.
* @param pColumnIdx zero-based column index.
* @returns cell data.
*/
template<typename T>
T GetCell(const size_t pColumnIdx, const size_t pRowIdx) const
{
const ssize_t columnIdx = pColumnIdx + (mLabelParams.mRowNameIdx + 1);
const ssize_t rowIdx = pRowIdx + (mLabelParams.mColumnNameIdx + 1);
T val;
Converter<T> converter(mConverterParams);
converter.ToVal(mData.at(rowIdx).at(columnIdx), val);
return val;
}
/**
* @brief Get cell by name.
* @param pColumnName column label name.
* @param pRowName row label name.
* @returns cell data.
*/
template<typename T>
T GetCell(const std::string& pColumnName, const std::string& pRowName) const
{
const ssize_t columnIdx = GetColumnIdx(pColumnName);
if (columnIdx < 0)
{
throw std::out_of_range("column not found: " + pColumnName);
}
const ssize_t rowIdx = GetRowIdx(pRowName);
if (rowIdx < 0)
{
throw std::out_of_range("row not found: " + pRowName);
}
return GetCell<T>(columnIdx, rowIdx);
}
/**
* @brief Set cell by index.
* @param pRowIdx zero-based row index.
* @param pColumnIdx zero-based column index.
* @param pCell cell data.
*/
template<typename T>
void SetCell(const size_t pColumnIdx, const size_t pRowIdx, const T& pCell)
{
const size_t columnIdx = pColumnIdx + (mLabelParams.mRowNameIdx + 1);
const size_t rowIdx = pRowIdx + (mLabelParams.mColumnNameIdx + 1);
while ((rowIdx + 1) > GetDataRowCount())
{
std::vector<std::string> row;
row.resize(GetDataColumnCount());
mData.push_back(row);
}
if ((columnIdx + 1) > GetDataColumnCount())
{
for (auto itRow = mData.begin(); itRow != mData.end(); ++itRow)
{
itRow->resize(columnIdx + 1);
}
}
std::string str;
Converter<T> converter(mConverterParams);
converter.ToStr(pCell, str);
mData.at(rowIdx).at(columnIdx) = str;
}
/**
* @brief Set cell by name.
* @param pColumnName column label name.
* @param pRowName row label name.
* @param pCell cell data.
*/
template<typename T>
void SetCell(const std::string& pColumnName, const std::string& pRowName, const T& pCell)
{
const ssize_t columnIdx = GetColumnIdx(pColumnName);
if (columnIdx < 0)
{
throw std::out_of_range("column not found: " + pColumnName);
}
const ssize_t rowIdx = GetRowIdx(pRowName);
if (rowIdx < 0)
{
throw std::out_of_range("row not found: " + pRowName);
}
SetCell<T>(columnIdx, rowIdx, pCell);
}
/**
* @brief Get column name
* @param pColumnIdx zero-based column index.
* @returns column name.
*/
std::string GetColumnName(const ssize_t pColumnIdx)
{
const ssize_t columnIdx = pColumnIdx + (mLabelParams.mRowNameIdx + 1);
if (mLabelParams.mColumnNameIdx < 0)
{
throw std::out_of_range("column name row index < 0: " + std::to_string(mLabelParams.mColumnNameIdx));
}
return mData.at(mLabelParams.mColumnNameIdx).at(columnIdx);
}
/**
* @brief Set column name
* @param pColumnIdx zero-based column index.
* @param pColumnName column name.
*/
void SetColumnName(size_t pColumnIdx, const std::string& pColumnName)
{
const ssize_t columnIdx = pColumnIdx + (mLabelParams.mRowNameIdx + 1);
mColumnNames[pColumnName] = columnIdx;
if (mLabelParams.mColumnNameIdx < 0)
{
throw std::out_of_range("column name row index < 0: " + std::to_string(mLabelParams.mColumnNameIdx));
}
mData.at(mLabelParams.mColumnNameIdx).at(columnIdx) = pColumnName;
}
/**
* @brief Get column names
* @returns vector of column names.
*/
std::vector<std::string> GetColumnNames()
{
if (mLabelParams.mColumnNameIdx >= 0)
{
return std::vector<std::string>(mData.at(mLabelParams.mColumnNameIdx).begin() +
(mLabelParams.mRowNameIdx + 1),
mData.at(mLabelParams.mColumnNameIdx).end());
}
return std::vector<std::string>();
}
/**
* @brief Get row name
* @param pRowIdx zero-based column index.
* @returns row name.
*/
std::string GetRowName(const ssize_t pRowIdx)
{
const ssize_t rowIdx = pRowIdx + (mLabelParams.mColumnNameIdx + 1);
if (mLabelParams.mRowNameIdx < 0)
{
throw std::out_of_range("row name column index < 0: " + std::to_string(mLabelParams.mRowNameIdx));
}
return mData.at(rowIdx).at(mLabelParams.mRowNameIdx);
}
/**
* @brief Set row name
* @param pRowIdx zero-based row index.
* @param pRowName row name.
*/
void SetRowName(size_t pRowIdx, const std::string& pRowName)
{
const ssize_t rowIdx = pRowIdx + (mLabelParams.mColumnNameIdx + 1);
mRowNames[pRowName] = rowIdx;
if (mLabelParams.mRowNameIdx < 0)
{
throw std::out_of_range("row name column index < 0: " + std::to_string(mLabelParams.mRowNameIdx));
}
mData.at(rowIdx).at(mLabelParams.mRowNameIdx) = pRowName;
}
/**
* @brief Get row names
* @returns vector of row names.
*/
std::vector<std::string> GetRowNames()
{
std::vector<std::string> rownames;
if (mLabelParams.mRowNameIdx >= 0)
{
for (auto itRow = mData.begin(); itRow != mData.end(); ++itRow)
{
if (std::distance(mData.begin(), itRow) > mLabelParams.mColumnNameIdx)
{
rownames.push_back(itRow->at(mLabelParams.mRowNameIdx));
}
}
}
return rownames;
}
private:
void ReadCsv()
{
std::ifstream file;
file.exceptions(std::ifstream::failbit | std::ifstream::badbit);
file.open(mPath, std::ios::binary | std::ios::ate);
std::streamsize fileLength = file.tellg();
file.seekg(0, std::ios::beg);
ReadCsv(file, fileLength);
}
void ReadCsv(std::istream &file, std::streamsize fileLength)
{
const std::streamsize bufLength = 64 * 1024;
std::vector<char> buffer(bufLength);
std::vector<std::string> row;
std::string cell;
bool quoted = false;
int cr = 0;
int lf = 0;
while (fileLength > 0)
{
long long readLength = std::min(fileLength, bufLength);
file.read(buffer.data(), readLength);
for (int i = 0; i < readLength; ++i)
{
if (buffer[i] == '"')
{
if (cell.empty() || cell[0] == '"')
{
quoted = !quoted;
}
cell += buffer[i];
}
else if (buffer[i] == mSeparatorParams.mSeparator)
{
if (!quoted)
{
row.push_back(cell);
cell.clear();
}
else
{
cell += buffer[i];
}
}
else if (buffer[i] == '\r')
{
++cr;
}
else if (buffer[i] == '\n')
{
++lf;
row.push_back(cell);
cell.clear();
mData.push_back(row);
row.clear();
quoted = false; // disallow line breaks in quoted string, by auto-unquote at linebreak
}
else
{
cell += buffer[i];
}
}
fileLength -= readLength;
}
// Handle last line without linebreak
if (!cell.empty() || !row.empty())
{
row.push_back(cell);
cell.clear();
mData.push_back(row);
row.clear();
}
// Assume CR/LF if at least half the linebreaks have CR
mSeparatorParams.mHasCR = (cr > (lf / 2));
// Set up column labels
if ((mLabelParams.mColumnNameIdx >= 0) &&
(mData.size() > 0))
{
int i = 0;
for (auto& columnName : mData[mLabelParams.mColumnNameIdx])
{
mColumnNames[columnName] = i++;
}
}
// Set up row labels
if ((mLabelParams.mRowNameIdx >= 0) &&
(static_cast<ssize_t>(mData.size()) >
(mLabelParams.mColumnNameIdx + 1)))
{
int i = 0;
for (auto& dataRow : mData)
{
mRowNames[dataRow[mLabelParams.mRowNameIdx]] = i++;
}
}
}
void WriteCsv() const
{
std::ofstream file;
file.exceptions(std::ofstream::failbit | std::ofstream::badbit);
file.open(mPath, std::ios::binary | std::ios::trunc);
WriteCsv(file);
}
void WriteCsv(std::ostream &file) const
{
for (auto itr = mData.begin(); itr != mData.end(); ++itr)
{
for (auto itc = itr->begin(); itc != itr->end(); ++itc)
{
if (std::string::npos == itc->find(mSeparatorParams.mSeparator))
{
file << *itc;
}
else
{
file << '"' << *itc << '"';
}