-
Notifications
You must be signed in to change notification settings - Fork 122
/
LoadAscii2.cpp
860 lines (790 loc) · 32.1 KB
/
LoadAscii2.cpp
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
// Mantid Repository : https://github.com/mantidproject/mantid
//
// Copyright © 2018 ISIS Rutherford Appleton Laboratory UKRI,
// NScD Oak Ridge National Laboratory, European Spallation Source,
// Institut Laue - Langevin & CSNS, Institute of High Energy Physics, CAS
// SPDX - License - Identifier: GPL - 3.0 +
#include "MantidDataHandling/LoadAscii2.h"
#include "MantidAPI/Axis.h"
#include "MantidAPI/FileProperty.h"
#include "MantidAPI/NumericAxis.h"
#include "MantidAPI/RegisterFileLoader.h"
#include "MantidAPI/Run.h"
#include "MantidAPI/TableRow.h"
#include "MantidAPI/WorkspaceFactory.h"
#include "MantidDataObjects/TableWorkspace.h"
#include "MantidDataObjects/Workspace2D.h"
#include "MantidHistogramData/HistogramMath.h"
#include "MantidKernel/BoundedValidator.h"
#include "MantidKernel/ListValidator.h"
#include "MantidKernel/StringTokenizer.h"
#include "MantidKernel/UnitFactory.h"
#include "MantidKernel/VisibleWhenProperty.h"
// String utilities
#include <boost/algorithm/string.hpp>
#include <boost/regex.hpp>
#include <boost/tokenizer.hpp>
#include <fstream>
namespace Mantid {
namespace DataHandling {
DECLARE_FILELOADER_ALGORITHM(LoadAscii2)
using namespace Kernel;
using namespace API;
/// Empty constructor
LoadAscii2::LoadAscii2()
: m_columnSep(), m_separatorIndex(), m_comment(), m_baseCols(0), m_specNo(0), m_lastBins(0), m_curBins(0),
m_spectraStart(), m_spectrumIDcount(0), m_lineNo(0), m_spectra(), m_curSpectra(nullptr) {}
/**
* Return the confidence with with this algorithm can load the file
* @param descriptor A descriptor for the file
* @returns An integer specifying the confidence level. 0 indicates it will not
* be used
*/
int LoadAscii2::confidence(Kernel::FileDescriptor &descriptor) const {
const std::string &filePath = descriptor.filename();
const size_t filenameLength = filePath.size();
// Avoid some known file types that have different loaders
int confidence(0);
if (filenameLength > 12 ? (filePath.compare(filenameLength - 12, 12, "_runinfo.xml") == 0)
: false || filenameLength > 6 ? (filePath.compare(filenameLength - 6, 6, ".peaks") == 0)
: false || filenameLength > 10 ? (filePath.compare(filenameLength - 10, 10, ".integrate") == 0)
: false) {
confidence = 0;
} else if (descriptor.isAscii()) {
confidence = 10; // Low so that others may try
}
return confidence;
}
//--------------------------------------------------------------------------
// Protected methods
//--------------------------------------------------------------------------
/**
* Reads the data from the file. It is assumed that the provided file stream has
* its position
* set such that the first call to getline will be give the first line of data
* @param file :: A reference to a file stream
* @returns A pointer to a new workspace
*/
API::Workspace_sptr LoadAscii2::readData(std::ifstream &file) {
// it's probably more stirct versus version 1, but then this is a format
// change and we don't want any bad data getting into the workspace
// there is still flexibility, but the format should just make more sense in
// general
// if the file appears to be a table workspace then read it as such
auto ws = readTable(file);
if (ws) {
return ws;
}
m_baseCols = 0;
m_specNo = 0;
m_lastBins = 0;
m_curBins = 0;
m_spectraStart = true;
m_spectrumIDcount = 0;
m_spectra.clear();
m_curSpectra = std::make_unique<DataObjects::Histogram1D>(HistogramData::Histogram::XMode::Points,
HistogramData::Histogram::YMode::Counts);
std::string line;
std::list<std::string> columns;
setcolumns(file, line, columns);
while (getline(file, line)) {
std::string templine = line;
m_lineNo++;
boost::trim(templine);
if (templine.empty()) {
// the line is empty, treat as a break before a new spectra
newSpectra();
} else if (!skipLine(templine)) {
parseLine(templine, columns);
}
}
newSpectra();
const size_t numSpectra = m_spectra.size();
MatrixWorkspace_sptr localWorkspace;
try {
localWorkspace = WorkspaceFactory::Instance().create("Workspace2D", numSpectra, m_lastBins, m_lastBins);
} catch (std::exception &e) {
std::ostringstream msg;
msg << "Failed to create a Workspace2D from the data found in this file. "
"Error: "
<< e.what();
throw std::runtime_error(msg.str());
}
try {
writeToWorkspace(localWorkspace, numSpectra);
} catch (std::exception &e) {
std::ostringstream msg;
msg << "Failed to write read data into the output Workspace2D. Error: " << e.what();
throw std::runtime_error(msg.str());
}
m_curSpectra.reset();
return localWorkspace;
}
/// Attempts to read a table workspace from the file.
/// Failing early if the format does not match.
/// @param file the file handle to load from
/// @returns a populated table workspace or an empty shared pointer
API::Workspace_sptr LoadAscii2::readTable(std::ifstream &file) {
DataObjects::TableWorkspace_sptr ws;
// We need to see two rows commented out
// the first with column names
// the second with column types
// Then we need data, with the same number of columns as the first two lines
try {
size_t colNames = 0;
size_t colTypes = 0;
std::string line;
std::list<std::string> names;
std::list<std::string> types;
std::list<std::string> data;
while (getline(file, line)) {
boost::trim(line);
std::list<std::string> columns;
if (!line.empty()) {
// if line starts with a comment
if (line.at(0) == m_comment.at(0)) {
// remove the comment character
line.erase(0, 1);
size_t lineCols = this->splitIntoColumns(columns, line);
if (colNames == 0) {
colNames = lineCols;
names = columns;
continue;
}
if (colTypes == 0) {
colTypes = lineCols;
types = columns;
continue;
}
}
if (colTypes != colNames) {
// no point going further, the types and names differ in quantity
break;
}
size_t colData = this->splitIntoColumns(data, line);
if (colNames > 0 && colNames == colTypes && colTypes == colData) {
// we seem to have a table workspace
// if we have no already created a workspace
if (!ws) {
ws = std::make_shared<DataObjects::TableWorkspace>();
// create the columns
auto itName = names.begin();
auto itTypes = types.begin();
for (size_t i = 0; i < colNames; i++) {
std::string name = *itName;
std::string type = *itTypes;
// trim the strings
boost::trim(name);
boost::trim(type);
ws->addColumn(std::move(type), std::move(name));
itName++;
itTypes++;
}
}
// add the data
TableRow row = ws->appendRow();
auto itTypes = types.begin();
for (auto itData = data.begin(); itData != data.end(); itData++) {
// direct assignment only works for strings, we ill need to handle
// the other data types here
std::string type = *itTypes;
boost::trim(type);
if (type == "str") {
row << *itData;
} else if (type == "int") {
int num = boost::lexical_cast<int>(*itData);
row << num;
} else if (type == "uint") {
uint32_t num = boost::lexical_cast<uint32_t>(*itData);
row << num;
} else if (type == "long64") {
auto num = boost::lexical_cast<int64_t>(*itData);
row << num;
} else if (type == "size_t") {
size_t num = boost::lexical_cast<size_t>(*itData);
row << num;
} else if (type == "float") {
float num = boost::lexical_cast<float>(*itData);
row << num;
} else if (type == "double") {
double num = boost::lexical_cast<double>(*itData);
row << num;
} else if (type == "bool") {
bool val = (itData->at(0) == 't');
row << val;
} else if (type == "V3D") {
V3D val;
std::stringstream ss(*itData);
val.readPrinted(ss);
row << val;
} else {
throw std::runtime_error("unknown column data type " + type);
}
itTypes++;
}
}
}
}
// if the file does not have more than rowsToCheck, it will
// stop
// and raise the EndOfFile, this may cause problems for small workspaces.
// In this case clear the flag
if (file.eof()) {
file.clear(file.eofbit);
}
} catch (std::exception &ex) {
// log and squash the error, so we can still try to load the file as a
// matrix workspace
g_log.warning() << "Error while trying to read ascii file as table, "
"continuing to load as matrix workspace.\n"
<< ex.what() << "\n";
// clear any workspace that we started loading
ws.reset();
}
// Seek the file pointer back to the start.
file.seekg(0, std::ios::beg);
return ws;
}
/**
* Check the start of the file for the first data set, then set the number of
* columns that hsould be expected thereafter
* @param[in] line : The current line of data
* @param[in] columns : the columns of values in the current line of data
*/
void LoadAscii2::parseLine(const std::string &line, std::list<std::string> &columns) {
if (std::isdigit(line.at(0)) || line.at(0) == '-' || line.at(0) == '+') {
const int cols = splitIntoColumns(columns, line);
if (cols > 4 || cols < 0) {
// there were more separators than there should have been, which isn't
// right, or something went rather wrong
throw std::runtime_error("Line " + std::to_string(m_lineNo) +
": Sets of values must have between 1 and 3 delimiters");
} else if (cols == 1) {
// a size of 1 is a spectra ID as long as there are no alphabetic
// characters in it. Signifies the start of a new spectra if it wasn't
// preceeded with a blank line
newSpectra();
// at this point both vectors should be the same size (or the ID counter
// should be 0, but as we're here then that's out the window),
if (m_spectra.size() == m_spectrumIDcount) {
m_spectrumIDcount++;
} else {
// if not then they've ommitted IDs in the the file previously and just
// decided to include one (which is wrong and confuses everything)
throw std::runtime_error("Line " + std::to_string(m_lineNo) +
": Inconsistent inclusion of spectra IDs. All spectra must have "
"IDs or all spectra must not have IDs. "
"Check for blank lines, as they symbolize the end of one spectra "
"and the start of another. Also check for spectra IDs with no "
"associated bins.");
}
const std::string singleNumber = columns.front();
try {
m_curSpectra->setSpectrumNo(boost::lexical_cast<int>(singleNumber));
} catch (boost::bad_lexical_cast &) {
// the single column number is not the spectrum ID, maybe it is the
// spectrum axis value
try {
m_spectrumAxis.emplace_back(boost::lexical_cast<double>(singleNumber));
} catch (boost::bad_lexical_cast &) {
throw std::runtime_error("Unable to read as spectrum ID (int) nor as "
"spectrum axis value (double)" +
singleNumber);
}
}
} else {
inconsistantIDCheck();
checkLineColumns(cols);
addToCurrentSpectra(columns);
}
} else if (badLine(line)) {
throw std::runtime_error("Line " + std::to_string(m_lineNo) +
": Unexpected character found at beginning of line. Lines must either "
"be a single integer, a list of numeric values, blank, or a text line "
"beginning with the specified comment indicator: " +
m_comment + ".");
} else {
// strictly speaking this should never be hit, but just being sure
throw std::runtime_error("Line " + std::to_string(m_lineNo) +
": Unknown format at line. Lines must either be a single integer, a "
"list of numeric values, blank, or a text line beginning with the "
"specified comment indicator: " +
m_comment + ".");
}
}
/**
* Construct the workspace
* @param[out] localWorkspace : the workspace beign constructed
* @param[in] numSpectra : The number of spectra found in the file
*/
void LoadAscii2::writeToWorkspace(API::MatrixWorkspace_sptr &localWorkspace, const size_t &numSpectra) const {
try {
localWorkspace->getAxis(0)->unit() = UnitFactory::Instance().create(getProperty("Unit"));
} catch (Exception::NotFoundError &) {
// Asked for dimensionless workspace (obviously not in unit factory)
}
for (size_t i = 0; i < numSpectra; ++i) {
localWorkspace->setSharedX(i, m_spectra[i].sharedX());
localWorkspace->setSharedY(i, m_spectra[i].sharedY());
// if E or DX are ommitted they're implicitly initalised as 0
if (m_baseCols == 4 || m_baseCols == 3) {
// E in file
localWorkspace->setSharedE(i, m_spectra[i].sharedE());
}
// DX could be NULL
localWorkspace->setSharedDx(i, m_spectra[i].sharedDx());
if (m_spectrumIDcount != 0) {
localWorkspace->getSpectrum(i).setSpectrumNo(m_spectra[i].getSpectrumNo());
} else {
localWorkspace->getSpectrum(i).setSpectrumNo(static_cast<specnum_t>(i) + 1);
}
if (!m_spectrumAxis.empty()) {
localWorkspace->replaceAxis(1, std::make_unique<NumericAxis>(m_spectrumAxis));
}
}
}
/**
* Check the start of the file for the first data set, then set the number of
* columns that should be expected thereafter
* This will also place the file marker at the first spectrum No or data line,
* ignoring any header information at the moment.
* @param[in] file : The file stream
* @param[in] line : The current line of data
* @param[in] columns : the columns of values in the current line of data
*/
void LoadAscii2::setcolumns(std::ifstream &file, std::string &line, std::list<std::string> &columns) {
m_lineNo = 0;
std::vector<double> values;
// processheader will also look for a base number of columns, to save time
// here if possible
// but if the user specifies a number of lines to skip that check won't happen
// in processheader
processHeader(file);
if (m_baseCols == 0 || m_baseCols > 4 || m_baseCols < 2) {
// first find the first data set and set that as the template for the number
// of data columns we expect from this file
while (getline(file, line) && (m_baseCols == 0 || m_baseCols > 4 || m_baseCols < 2)) {
// std::string line = line;
boost::trim(line);
if (!line.empty()) {
if (std::isdigit(line.at(0)) || line.at(0) == '-' || line.at(0) == '+') {
const int cols = splitIntoColumns(columns, line);
// we might have the first set of values but there can't be more than
// 3 commas if it is
// int values = std::count(line.begin(), line.end(), ',');
if (cols > 4 || cols < 1) {
// there were more separators than there should have been, which
// isn't right, or something went rather wrong
throw std::runtime_error("Sets of values must have between 1 and 3 delimiters. Found " +
std::to_string(cols) + ".");
} else if (cols != 1) {
try {
fillInputValues(values, columns);
} catch (boost::bad_lexical_cast &) {
continue;
}
// a size of 1 is most likely a spectra ID so ignore it, a value of
// 2, 3 or 4 is a valid data set
m_baseCols = cols;
}
}
}
}
// make sure some valid data has been found to set the amount of columns,
// and the file isn't at EOF
if (m_baseCols > 4 || m_baseCols < 2 || file.eof()) {
throw std::runtime_error("No valid data in file, check separator "
"settings or number of columns per bin.");
}
// start from the top again, this time filling in the list
file.seekg(0, std::ios_base::beg);
for (size_t i = 0; i < m_lineNo; i++) {
getline(file, line);
}
}
}
/**
* Process the header information. This implementation just skips it entirely.
* @param file :: A reference to the file stream
*/
void LoadAscii2::processHeader(std::ifstream &file) {
// Most files will have some sort of header. If we've haven't been told how
// many lines to
// skip then try and guess
int numToSkip = getProperty("SkipNumLines");
if (numToSkip == EMPTY_INT()) {
size_t numCols = 0;
const size_t rowsToMatch(5);
// Have a guess where the data starts. Basically say, when we have say
// "rowsToMatch" lines of pure numbers
// in a row then the line that started block is the top of the data
size_t matchingRows = 0;
int validRows = 0;
size_t blankRows = 0;
int row = 0;
std::string line;
std::vector<double> values;
while (getline(file, line) && matchingRows < rowsToMatch) {
++row;
boost::trim(line);
std::list<std::string> columns;
size_t lineCols = 0;
if (!line.empty()) {
if (badLine(line)) {
matchingRows = 0;
validRows = 0;
continue;
}
// a skipped line is a valid non-data line this shouldn't be counted as
// a matching line
// but neither should it reset the matching counter
if (skipLine(line, true)) {
++validRows;
continue;
}
if (std::isdigit(line.at(0)) || line.at(0) == '-' || line.at(0) == '+') {
lineCols = this->splitIntoColumns(columns, line);
// we might have the first set of values but there can't be more than
// 3 delimiters if it is
if (lineCols > 4 || lineCols < 1) {
// there were more separators than there should have been,
// which isn't right, or something went rather wrong
matchingRows = 0;
validRows = 0;
continue;
} else if (lineCols != 1) {
try {
fillInputValues(values, columns);
} catch (boost::bad_lexical_cast &) {
matchingRows = 0;
validRows = 0;
continue;
}
// a size of 1 is most likely a spectra ID so ignore it, a value of
// 2, 3 or 4 is a valid data set
}
} else {
// line wasn't valid
matchingRows = 0;
validRows = 0;
continue;
}
} else {
// an empty line is legitimate but make sure there aren't too many in
// sucession as we need to see data
++matchingRows;
++validRows;
++blankRows;
if (blankRows >= rowsToMatch) {
matchingRows = 1;
validRows = 1;
}
continue;
}
if (numCols == 0 && lineCols != 1) {
numCols = lineCols;
}
// to reduce the chance of finding problems later,
// the concurrent data should also have the same nubmer of columns
// if the data has a different number of columns to the previous lines
// start the coutner again assuming those previous lines were header info
if (lineCols == numCols || lineCols == 1) {
// line is valid increment the counter
++matchingRows;
++validRows;
} else {
numCols = lineCols;
matchingRows = 1;
validRows = 1;
}
}
// if the file does not have more than rowsToMatch + skipped lines, it will
// stop
// and raise the EndOfFile, this may cause problems for small workspaces.
// In this case clear the flag
if (file.eof()) {
file.clear(file.eofbit);
}
// save some time in setcolumns as we've found the base columns
if (numCols > 4 || numCols < 2) {
throw std::runtime_error("No valid data in file, check separator "
"settings or number of columns per bin.");
}
m_baseCols = numCols;
// Seek the file pointer back to the start.
// NOTE: Originally had this as finding the stream position of the data and
// then moving the file pointer
// back to the start of the data. This worked when a file was read on the
// same platform it was written
// but failed when read on a different one due to underlying differences in
// the stream translation.
file.seekg(0, std::ios::beg);
// We've read the header plus a number of validRows
numToSkip = row - validRows;
}
m_lineNo = 0;
std::string line;
while (m_lineNo < static_cast<size_t>(numToSkip) && getline(file, line)) {
++m_lineNo;
}
g_log.information() << "Skipped " << numToSkip << " line(s) of header information()\n";
}
/**
* Check if the file has been found to inconsistently include spectra IDs
* @param[in] columns : the columns of values in the current line of data
*/
void LoadAscii2::addToCurrentSpectra(std::list<std::string> &columns) {
std::vector<double> values(m_baseCols, 0.);
m_spectraStart = false;
fillInputValues(values, columns);
// add X and Y
auto histo = m_curSpectra->histogram();
histo.resize(histo.size() + 1);
histo.mutableX().back() = values[0];
histo.mutableY().back() = values[1];
// check for E and DX
switch (m_baseCols) {
// if only 2 columns X and Y in file, E = 0 is implicit when constructing
// workspace, omit DX
case 3: {
// E in file, include it, omit DX
histo.mutableE().back() = values[2];
break;
}
case 4: {
// E and DX in file, include both
histo.mutableE().back() = values[2];
m_curDx.emplace_back(values[3]);
break;
}
}
m_curSpectra->setHistogram(histo);
m_curBins++;
}
/**
* Check if the file has been found to inconsistently include spectra IDs
* @param[in] cols : the number of columns in the current line of data
*/
void LoadAscii2::checkLineColumns(const size_t &cols) const {
// a size of 2, 3 or 4 is a valid data set, but first see if it's the same as
// the first observed one
if (m_baseCols != cols) {
throw std::runtime_error("Number of data columns not consistent throughout file");
}
}
/**
* Check if the file has been found to incosistantly include spectra IDs
*/
void LoadAscii2::inconsistantIDCheck() const {
// we need to do a check regarding spectra ids before doing anything else
// is this the first bin in the spectra? if not this check has already been
// done for this spectra
// If the ID vector is completly empty then it's ok we're assigning them later
// if there are equal or less IDs than there are spectra, then there's been no
// ID assigned to this spectra and there should be
if (m_spectraStart && m_spectrumIDcount != 0 && !(m_spectra.size() < m_spectrumIDcount)) {
throw std::runtime_error("Inconsistent inclusion of spectra IDs. All "
"spectra must have IDs or all spectra must not "
"have IDs."
" Check for blank lines, as they symbolize the "
"end of one spectra and the start of another.");
}
}
/**
* Check if the file has been found to incosistantly include spectra IDs
*/
void LoadAscii2::newSpectra() {
if (!m_spectraStart) {
if (m_lastBins == 0) {
m_lastBins = m_curBins;
m_curBins = 0;
} else if (m_lastBins == m_curBins) {
m_curBins = 0;
} else {
throw std::runtime_error("Number of bins per spectra not consistant.");
}
if (m_curSpectra) {
size_t specSize = m_curSpectra->size();
if (specSize > 0 && specSize == m_lastBins) {
if (m_curSpectra->x().size() == m_curDx.size())
m_curSpectra->setPointStandardDeviations(std::move(m_curDx));
m_spectra.emplace_back(*m_curSpectra);
}
m_curSpectra.reset();
}
m_curSpectra = std::make_unique<DataObjects::Histogram1D>(HistogramData::Histogram::XMode::Points,
HistogramData::Histogram::YMode::Counts);
m_curDx.clear();
m_spectraStart = true;
}
}
/**
* Return true if the line is to be skipped.
* @param[in] line :: The line to be checked
* @param[in] header :: Flag for if this is header material
* @return True if the line should be skipped
*/
bool LoadAscii2::skipLine(const std::string &line, bool header) const {
// Comments are skipped, Empty actually means something and shouldn't be
// skipped
// just checking the comment's first character should be ok as comment
// characters can't be numeric at all, so they can't really be confused
return ((line.empty() && header) || line.at(0) == m_comment.at(0));
}
/**
* Return true if the line doesn't start with a valid character.
* @param[in] line :: The line to be checked
* @return :: True if the line doesn't start with a valid character.
*/
bool LoadAscii2::badLine(const std::string &line) const {
// Empty or comment
return (!(std::isdigit(line.at(0)) || line.at(0) == '-' || line.at(0) == '+') && line.at(0) != m_comment.at(0));
}
/**
* Split the data into columns based on the input separator
* @param[out] columns :: A reference to a list to store the column data
* @param[in] str :: The input string
* @returns The number of columns
*/
int LoadAscii2::splitIntoColumns(std::list<std::string> &columns, const std::string &str) const {
boost::split(columns, str, boost::is_any_of(m_columnSep), boost::token_compress_on);
return static_cast<int>(columns.size());
}
/**
* Fill the given vector with the data values. Its size is assumed to be correct
* @param[out] values :: The data vector fill
* @param[in] columns :: The list of strings denoting columns
*/
void LoadAscii2::fillInputValues(std::vector<double> &values, const std::list<std::string> &columns) const {
values.resize(columns.size());
int i = 0;
for (auto value : columns) {
boost::trim(value);
boost::to_lower(value);
if (value == "nan" || value == "1.#qnan") // ignores nans (not a number) and
// replaces them with a nan
{
double nan = std::numeric_limits<double>::quiet_NaN(); //(0.0/0.0);
values[i] = nan;
} else {
values[i] = boost::lexical_cast<double>(value);
}
++i;
}
}
//--------------------------------------------------------------------------
// Private methods
//--------------------------------------------------------------------------
/// Initialisation method.
void LoadAscii2::init() {
const std::vector<std::string> exts{".dat", ".txt", ".csv", ""};
declareProperty(std::make_unique<FileProperty>("Filename", "", FileProperty::Load, exts),
"The name of the text file to read, including its full or "
"relative path. The file extension must be .txt, .dat, or "
".csv");
declareProperty(std::make_unique<WorkspaceProperty<Workspace>>("OutputWorkspace", "", Direction::Output),
"The name of the workspace that will be created, "
"filled with the read-in data and stored in the [[Analysis "
"Data Service]].");
const int numSpacers = 7;
std::string spacers[numSpacers][2] = {
{"Automatic", ",\t:; "}, {"CSV", ","}, {"Tab", "\t"}, {"Space", " "}, {"Colon", ":"}, {"SemiColon", ";"},
{"UserDefined", "UserDefined"}};
// For the ListValidator
std::array<std::string, numSpacers> sepOptions;
int sepOptionsIndex = 0;
for (const auto &spacer : spacers) {
const auto &option = spacer[0];
m_separatorIndex.insert(std::pair<std::string, std::string>(option, spacer[1]));
sepOptions[sepOptionsIndex++] = option;
}
declareProperty("Separator", "Automatic", std::make_shared<StringListValidator>(sepOptions),
"The separator between data columns in the data file. The "
"possible values are \"CSV\", \"Tab\", "
"\"Space\", \"SemiColon\", \"Colon\" or a user defined "
"value. (default: Automatic selection from comma,"
" tab, space, semicolon or colon.).");
declareProperty(std::make_unique<PropertyWithValue<std::string>>("CustomSeparator", "", Direction::Input),
"If present, will override any specified choice given to Separator.");
setPropertySettings("CustomSeparator",
std::make_unique<VisibleWhenProperty>("Separator", IS_EQUAL_TO, "UserDefined"));
declareProperty("CommentIndicator", "#",
"Character(s) found front of "
"comment lines. Cannot contain "
"numeric characters");
std::vector<std::string> units = UnitFactory::Instance().getKeys();
units.insert(units.begin(), "Dimensionless");
declareProperty("Unit", "Energy", std::make_shared<StringListValidator>(units),
"The unit to assign to the X axis (anything known to the "
"[[Unit Factory]] or \"Dimensionless\")");
auto mustBePosInt = std::make_shared<BoundedValidator<int>>();
mustBePosInt->setLower(0);
declareProperty("SkipNumLines", EMPTY_INT(), mustBePosInt,
"If given, skip this number of lines at the start of the file.");
}
/**
* Executes the algorithm.
*/
void LoadAscii2::exec() {
m_lineNo = 0;
std::string filename = getProperty("Filename");
std::ifstream file(filename.c_str());
if (!file) {
g_log.error("Unable to open file: " + filename);
throw Exception::FileError("Unable to open file: ", filename);
}
std::string sepOption = getProperty("Separator");
m_columnSep = m_separatorIndex[sepOption];
std::string choice = getPropertyValue("Separator");
std::string custom = getPropertyValue("CustomSeparator");
std::string sep;
// If the custom separator property is not empty, then we use that under any
// circumstance.
if (!custom.empty()) {
sep = custom;
}
// Else if the separator drop down choice is not UserDefined then we use that.
else if (choice != "UserDefined") {
auto it = m_separatorIndex.find(choice);
sep = it->second;
}
// If we still have nothing, then we are forced to use a default.
if (sep.empty()) {
g_log.notice() << "\"UserDefined\" has been selected, but no custom "
"separator has been entered."
" Using default instead.\n";
sep = ",";
}
m_columnSep = sep;
// e + and - are included as they're part of the scientific notation
if (!boost::regex_match(m_columnSep.begin(), m_columnSep.end(), boost::regex("[^0-9e+-]+", boost::regex::perl))) {
throw std::invalid_argument("Separators cannot contain numeric characters, "
"plus signs, hyphens or 'e'");
}
std::string tempcomment = getProperty("CommentIndicator");
if (!boost::regex_match(tempcomment.begin(), tempcomment.end(),
boost::regex("[^0-9e" + m_columnSep + "+-]+", boost::regex::perl))) {
throw std::invalid_argument("Comment markers cannot contain numeric "
"characters, plus signs, hyphens,"
" 'e' or the selected separator character");
}
m_comment = tempcomment;
// Process the header information.
// processHeader(file);
// Read the data
API::Workspace_sptr rd;
try {
rd = readData(file);
} catch (std::exception &e) {
g_log.error() << "Failed to read as ASCII this file: '" << filename << ", error description: " << e.what() << '\n';
throw std::runtime_error("Failed to recognize this file as an ASCII file, "
"cannot continue.");
}
MatrixWorkspace_sptr outputWS = std::dynamic_pointer_cast<MatrixWorkspace>(rd);
if (outputWS) {
outputWS->mutableRun().addProperty("Filename", filename);
}
setProperty("OutputWorkspace", rd);
}
} // namespace DataHandling
} // namespace Mantid