-
Notifications
You must be signed in to change notification settings - Fork 13
/
Copy pathregression_test.cpp
1323 lines (1046 loc) · 45.6 KB
/
regression_test.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
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
/* SpecUtils: a library to parse, save, and manipulate gamma spectrum data files.
Copyright 2018 National Technology & Engineering Solutions of Sandia, LLC
(NTESS). Under the terms of Contract DE-NA0003525 with NTESS, the U.S.
Government retains certain rights in this software.
For questions contact William Johnson via email at [email protected], or
alternative emails of [email protected], or [email protected].
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "SpecUtils_config.h"
#include <chrono>
#include <string>
#include <vector>
#include <iomanip>
#include <fstream>
#include <sstream>
#include <assert.h>
#include <iostream>
#include <algorithm>
#include "SpecUtils/SpecFile.h"
#include "SpecUtils/DateTime.h"
#include "SpecUtils/ParseUtils.h"
#include "SpecUtils/StringAlgo.h"
#include "SpecUtils/Filesystem.h"
#if( !SpecUtils_ENABLE_EQUALITY_CHECKS )
#error SpecUtils_ENABLE_EQUALITY_CHECKS must be enabled to compile regression_test
#endif
using namespace std;
//g_truth_n42_dirname: name of the sub-directory that truth N42 files will be
// stored in.
const string g_truth_n42_dirname = "truth_n42s";
//g_automated_mode: specifies whether being ran in an automated mode, or with
// user interaction.
bool g_automated_mode = false;
//g_sub_test_dir: specifies directory containing file types to be tested. All
// files if its empty.
string g_sub_test_dir = "";
//g_parse_time_filename: the name of the file written to the test base directory
// that stores the parse times for files. Not added to GIT.
const string g_parse_time_filename = "parsetimes.txt";
//open_spec_file(): uses the OS X 'open' command to open the spectrum file
// with InterSpec running on localport:8080.
void open_spec_file( const std::string &p );
//open_spec_file_in_textmate(): : uses the OS X 'open' command to open the
// spectrum file in textmate
void open_spec_file_in_textmate( const std::string &p );
//open_directory(): uses OS X 'open' command to open a finder window for the
// specified directory; if a file is passed in, its parent directory is opened.
void open_directory( const std::string &p );
//handle_no_truth_files(): interactively creates truth files, based on prompting
// user what actions should be taken (so they can decide it a truth file should
// be created or not).
void handle_no_truth_files( const string basedir );
//FixableErrors: types of errors that are non-fatal for parsing that might be
// expected to change over time, and hence you might want the truth level
// information to be updated.
enum FixableErrors
{
UuidError,
NumFixableErrors
};//enum FixableErrors
//get_compare_error_type(): searches the what() given by the exception thrown
// by MeasurmentInfo::equal_enough() to determine error type. Returns
// NumFixableErrors if it wasnt recognized or is not fixable.
FixableErrors get_compare_error_type( const string &msg );
//check_files_with_truth_n42(): check files that have a cooresponding truth n42
// file, to be sure that the original and truth n42 files parse to similar
// results using the 'equal_enough(...)' test.
void check_files_with_truth_n42( const string basedir );
//check_serialization_to_n42(): for test files (that have truth N42 files) this
// function tests that the oringal file can be read in, written out to a 2011
// N42, and then read back in and ensured its equal_enough() to the original.
void check_serialization_to_n42( const string basedir );
/** Checks the oeprator= to make sure copies are complete. */
void check_equality_operator( const string basedir );
//add_truth_n42(): adds a truth n42 file for the SpecUtils::SpecFile and path
// passed in. Will fail if a truth n42 file already exists, unless force is
// specified to be true. Checks the created n42 file to be sure it can be read
// back in and pass the 'equal_enough(...)' test, otherwise wont add truth n42
// file. Will add resulting added file (and possibly directory) to GIT.
// Returns true if the truth N42 file was created.
bool add_truth_n42( const SpecUtils::SpecFile &m, const std::string &p, const bool force );
//check_parse_time(): compares the parse times of files with truth n42 files
// against previous parse times. Parses the file 10 times and takes the
// minimum CPU time run as the parse time.
void check_parse_time( const string basedir );
//url_encode(): encodes a string appropriately to be passed as a URL argument.
string url_encode( const string &value );
//print_summary(): prints a reasonably brief summary to the provided stream.
void print_summary( const SpecUtils::SpecFile &info, std::ostream &out );
//print_one_line_summary(): prints a single line summary to the provided stream.
void print_one_line_summary( const SpecUtils::Measurement &info, std::ostream &out );
//candidate_test_files(): return all candidate files, regardless if they have a
// matching truth_n42.
vector<std::string> candidate_test_files( const string basedir );
//candidates_with_truth_n42_files(): returns only candidate files that have
// truth information as well.
vector<std::string> candidates_with_truth_n42_files( const string basedir );
//truth_n42_files(): return all truth_n42 files.
vector<std::string> truth_n42_files( const string basedir );
//candidates_without_truth_n42_files(): return files that do not have truthfiles
vector<std::string> candidates_without_truth_n42_files( const string basedir );
int main( int argc, char **argv )
{
//TODO: add test that ensures serializing to N42 and back again pass
// equal_enough(...) test.
//test_base_directory: the directory where the test file structure is based.
#if( !defined(WIN32) )
string test_base_directory = "/Users/wcjohns/rad_ana/SpectrumFileFormats/file_format_test_spectra";
#else
string test_base_directory = "Z:\\wcjohns\\rad_ana\\InterSpec\\testing\\SpectrumFileFormats\\file_format_test_spectra";
#endif
g_automated_mode = false;
g_sub_test_dir = "";
vector<string> actions;
// Do a very minimal command-line argument parser
try
{
for( int i = 1; i < argc; ++i )
{
const string arg = argv[i];
auto is_short_opt = []( const string &arg, const char test ) -> bool {
return ((arg.size() > 1) && ((arg[0] == '-') || (arg[0] == '/'))
&& (arg[1] == test) && ((arg.size() == 2) || (arg[2] == '=')) );
};
auto is_long_opt = []( const string &arg, const string &test ) -> bool {
return (((arg.size() >= (2+test.size()))
&& (arg[0] == '-') && (arg[1] == '-')
&& (arg.substr(2,test.size()) == test)
&& ((arg.size() == (2+test.size()))
|| (arg[2+test.size()] == '=')))
|| ((arg.size() >= (1+test.size())) //Windows specify option using '/' character instead of '--'
&& (arg[0] == '/')
&& SpecUtils::iequals_ascii(arg.substr(1,test.size()), test) //For Windows, allow to be case insensitive
&& ((arg.size() == (1+test.size()))
|| (arg[1+test.size()] == '=')))
);
};
auto get_arg_str_val = [&i,argv,argc,arg]() -> string {
const auto pos = arg.find("=");
if( pos != string::npos )
return arg.substr(pos+1);
if( (i+1) >= argc )
throw runtime_error( "No value specified for argument '" + arg + "'" );
string val = SpecUtils::trim_copy( argv[i+1] );
assert( !SpecUtils::istarts_with(val, "-") );
i += 1; //advance the argument position, so we dont try and interpret this value as an argument
cout << "Arg value: '" << val << "'" << endl;
return val;
};//auto get_arg_str_val()
auto get_arg_bool_val = [=]() -> bool {
using SpecUtils::iequals_ascii;
const string val = get_arg_str_val();
if( iequals_ascii(val,"0") || iequals_ascii(val,"false") || iequals_ascii(val,"no") )
return false;
else if( iequals_ascii(val,"1") || iequals_ascii(val,"true") || iequals_ascii(val,"yes") )
return true;
throw runtime_error( "Invalid boolean value '" + val + "'" );
return false;
};//get_arg_bool_val(...)
if( (arg == "-h") || (arg == "--help") )
{
cout << "Available options:\n"
"\thelp,h\t"
"produce help message\n"
"\tbatch,b\t"
"Run in non-interactive automated test mode.\n"
"\tbasedir,d\t"
"Directory where the test files are located.\n"
"\tsubdir,s\t"
"Sub-directory in 'basedir' of files to test.\n"
"action,a\t"
"Action to perform. Either 'n42test', 'regression' (or equivalently 'test'),\n"
"\t\t'addfiles', 'timing', or 'equality'. If blank defaults to 'test' if in\n"
"\t\tautomated mode, or 'n42test', 'addfiles', 'test', 'timing', 'equality' otherwise."
<< endl;
return EXIT_SUCCESS;
}else if( is_long_opt(arg, "batch") || is_short_opt(arg, 'b') )
{
g_automated_mode = get_arg_bool_val();
}else if( is_long_opt(arg, "basedir") || is_short_opt(arg, 'd') )
{
test_base_directory = get_arg_str_val();
}else if( is_long_opt(arg, "subdir") || is_short_opt(arg, 's') )
{
g_sub_test_dir = get_arg_str_val();
}else if( is_long_opt(arg, "action") || is_short_opt(arg, 'a') )
{
string arg = get_arg_str_val();
// We'll allow specifying a CSV list of values, like `--action=A,b,c,d`
vector<string> vals;
SpecUtils::split( vals, arg, "," );
actions.insert( end(actions), begin(vals), end(vals) );
// Or user could do something like `--action A b c d`
while( (i+1) < argc )
{
if( (argv[i+1][0] == '-') || (argv[i+1][0] == '/') )
break;
actions.push_back( argv[i+1] );
i += 1;
}//while( (i+1) < argc )
}else
{
throw runtime_error( "Unknown arg '" + arg + "'" );
}
}//for( int i = 1; i < argc; ++i )
}catch( std::exception &e )
{
cerr << "Error parsing command line arguments: " << e.what() << endl;
return EXIT_FAILURE;
}//try / catch to parse command line options
if( !SpecUtils::is_directory( test_base_directory ) )
{
cerr << "Base directory '" << test_base_directory << "' is not a valid "
<< "directory\n";
return EXIT_FAILURE;
}//if( base directory is invalid )
cout << "File base directory: '" << test_base_directory << "'\n";
if( g_automated_mode )
cout << "Testing in automated mode\n";
else
cout << "Testing in interactive mode\n";
if( !g_sub_test_dir.empty() )
{
test_base_directory
= SpecUtils::append_path( test_base_directory, g_sub_test_dir );
if( !SpecUtils::is_directory(test_base_directory) )
{
cerr << "Test sub directory '" << g_sub_test_dir << "' is not a valid"
<< " directory\n";
return EXIT_FAILURE;
}//if( sub directory is invalid )
cout << "Only testing files in the '" << g_sub_test_dir
<< "' subdirectory\n";
}//if( !g_sub_test_dir.empty() )
if( actions.empty() )
{
if( g_automated_mode )
actions.push_back( "test" );
else
actions = vector<string>{ "addfiles", "test", "timing", "n42test", "equality" };
}//if( vm.count("action") ) / else
for( string action : actions )
{
if( action == "n42test" )
check_serialization_to_n42( test_base_directory );
else if( action == "regression" || action == "test" )
check_files_with_truth_n42( test_base_directory );
else if( action == "addfiles" )
handle_no_truth_files( test_base_directory );
else if( action == "timing" )
check_parse_time( test_base_directory );
else if( action == "equality" )
check_equality_operator( test_base_directory );
else
{
cerr << "Invalid action type '" << action << "', valid options are "
<< "'n42test', 'regression', 'test', 'addfiles', 'timing', or blank\n";
return EXIT_FAILURE;
}
}//for( string action : actions )
return EXIT_SUCCESS;
}//int main( int argc, char **argv )
void open_spec_file( const std::string &p )
{
const string command = "open http://localhost:8080/?specfilename="
+ url_encode( p );
system( command.c_str() );
//The following wine comand crashes Peak Easy, but would be nice.
// command = "wine '/Users/wcjohns/Desktop/triage_spectra/PeakEasy 4.74/PeakEasy 4.74.exe' '" + path + "' &"
// system( command.c_str() );
}//void open_spec_file( const path &p )
void open_spec_file_in_textmate( const std::string &p )
{
//const string command = "open -a TextMate '" + p.string<string>() + "'";
const string command = "/usr/local/bin/code '" + p + "'";
system( command.c_str() );
}//void open_spec_file_in_textmate( const std::string &p )
void open_directory( const std::string &p )
{
string command = "open '";
if( !SpecUtils::is_file(p) )
command += p + "'";
else
command += SpecUtils::parent_path(p) + "'";
system( command.c_str() );
}//void open_directory( const std::string &p )
void check_parse_time( const string basedir )
{
const int ntimes_parse = 10;
map<std::string,double> cpu_parse_times, wall_parse_times;
const vector<std::string> with_truth = candidates_with_truth_n42_files( basedir );
const SpecUtils::time_point_t start_time = std::chrono::time_point_cast<std::chrono::microseconds>(std::chrono::system_clock::now());
for( const std::string &fpath : with_truth )
{
const string extention = SpecUtils::file_extension(fpath);
for( int i = 0; i < ntimes_parse; ++i )
{
SpecUtils::SpecFile info;
const double orig_wall_time = SpecUtils::get_wall_time();
const double orig_cpu_time = SpecUtils::get_cpu_time();
const bool parsed = info.load_file( fpath, SpecUtils::ParserType::Auto, extention );
const double final_cpu_time = SpecUtils::get_cpu_time();
const double final_wall_time = SpecUtils::get_wall_time();
if( parsed && orig_cpu_time > 0.0 && final_cpu_time > 0.0 )
{
double cpu_dt = final_cpu_time - orig_cpu_time;
double wall_dt = final_wall_time - orig_wall_time;
const map<string,double>::const_iterator pos = cpu_parse_times.find( fpath );
if( pos != cpu_parse_times.end() && (pos->second < cpu_dt) )
{
cpu_dt = pos->second;
wall_dt = wall_parse_times[pos->first];
}
cpu_parse_times[fpath] = cpu_dt;
wall_parse_times[fpath] = wall_dt;
}//if( parsed && orig_cpu_time > 0.0 && final_cpu_time > 0.0 )
}//for( int i = 0; i < ntimes_parse; ++i )
}//for( const string &fpath : with_truth )
string prevtimestr;
map<string,double> previous_cpu_parse_times, previous_wall_parse_times;
const string timingname
= SpecUtils::append_path( basedir, g_parse_time_filename );
{//begin read parsetimes
ifstream parsetimes( timingname.c_str(), ios::in | ios::binary );
if( parsetimes.is_open() && parsetimes.good() )
{
string filename;
SpecUtils::safe_get_line( parsetimes, prevtimestr );
while( SpecUtils::safe_get_line( parsetimes, filename ) )
{
if( filename.size() == 0 )
continue;
string times;
SpecUtils::safe_get_line( parsetimes, times );
double cputime, walltime;
const int n = sscanf( times.c_str(), "%lf %lf", &cputime, &walltime );
if( n != 2 )
{
cerr << "Error reading times for file '" << filename << "'\n"
<< "Stopping parsing timing file.\n";
break;
}//if( n != 2 )
previous_cpu_parse_times[filename] = cputime;
previous_wall_parse_times[filename] = walltime;
}//while( SpecUtils::safeGetline( parsetimes, line ) )
}//if( parsetimes.is_open() && parsetimes.good() )
}//end read parsetimes
//print comparison
double prev_cpu_total = 0.0, prev_wall_total = 0.0;
double current_cpu_total = 0.0, current_wall_total = 0.0;
bool previous_had_all = true;
cout << "Previous parse time: " << prevtimestr << endl;
for( map<string,double>::iterator i = cpu_parse_times.begin();
i != cpu_parse_times.end(); ++i )
{
const double cputime = i->second;
const double walltime = wall_parse_times[i->first];
current_cpu_total += cputime;
current_wall_total +=walltime;
string name = SpecUtils::filename(i->first);
if( name.size() > 30 )
name = name.substr( 0, 27 ) + "...";
cout << std::setw(31) << std::left << name << ": {cpu: "
<< setprecision(6) << std::fixed << cputime << ", wall: "
<< setprecision(6) << walltime << "}"
<< ", size: " << (SpecUtils::file_size(i->first) / 1024) << " kb\n";
if( previous_cpu_parse_times.count(i->first) )
{
prev_cpu_total += previous_cpu_parse_times[i->first];
prev_wall_total += previous_wall_parse_times[i->first];
cout << " previous : {cpu: "
<< setprecision(6) << previous_cpu_parse_times[i->first]
<< ", wall: "
<< setprecision(6) << previous_wall_parse_times[i->first] << "}\n";
}else
{
previous_had_all = false;
cout << " no previous \n";
}
cout << "\n";
}//for( loop over parse times )
cout << "Current total : {cpu: " << setprecision(6) << current_cpu_total
<< ", wall: " << setprecision(6) << prev_wall_total << "}\n";
if( previous_had_all )
cout << "Previous total : {cpu: " << setprecision(6) << prev_cpu_total
<< ", wall: " << setprecision(6) << prev_wall_total << "}\n\n";
else
cout << "Did not have previous timings for all the files\n\n";
//Decide if we should save the current results.
char action = (g_automated_mode ? 'n' : '\0');
while( action != 'y' && action != 'n' )
{
cout << "Would you like to save these latest timings? y/n\n";
cin >> action;
}//while( user hasnt entered valid answer )
if( action == 'y' )
{
ofstream file( timingname.c_str(), ios::out | ios::binary );
if( file.is_open() )
{
file << SpecUtils::to_extended_iso_string( start_time ) << endl;
for( map<string,double>::iterator i = cpu_parse_times.begin();
i != cpu_parse_times.end(); ++i )
{
file << i->first << endl << i->second
<< " " << wall_parse_times[i->first] << endl;
}
cout << "Saved timings to '" << timingname << "'" << endl;
}else
{
cerr << "Failed to open '" << timingname << "' for writing times\n";
}
}//if( action == 'y' )
}//void compare_parse_time( const string basedir )
FixableErrors get_compare_error_type( const string &msg )
{
if( SpecUtils::icontains( msg, "UUID of LHS" ) )
return UuidError;
return NumFixableErrors;
}//FixableErrors get_compare_error_type( const string &msg )
void check_files_with_truth_n42( const string basedir )
{
int initial = 0, initial_parsed = 0, failed_original_parsed = 0;
int failed_truth_parsed = 0, initial_with_truth = 0, passed_tests = 0;
int failed_tests = 0, updated_truths = 0, truths_failed_to_update = 0;
const vector<string> with_truth = candidates_with_truth_n42_files( basedir );
map<string,double> parse_times;
for( size_t file_index = 0; file_index < with_truth.size(); ++file_index )
{
const string &fpath = with_truth[file_index];
++initial;
const string filename = SpecUtils::filename(fpath);
const string originalpath = fpath;
const string originalext = SpecUtils::file_extension(fpath);
//A little hack to only look at certain files when debugging; insert part of the filename
// into 'files_interested_in' and re-compile.
set<string> files_interested_in, files_to_skip;
//files_interested_in.insert( "T10011_CS01C_D20070418_T181528_O0019_U.n42" );
bool interested_in = files_interested_in.empty();
for( const string &namesubstr : files_interested_in )
interested_in |= (filename.find(namesubstr) != string::npos);
//files_to_skip.insert( "some_filename_to_skip.n42" );
for( const auto &namesubstr : files_to_skip )
interested_in &= (filename.find(namesubstr) == string::npos);
if( !interested_in )
{
cerr << "Warning: skipping '" << filename << "' as requested in check_files_with_truth_n42\n";
continue;
}
SpecUtils::SpecFile original;
const bool originalstatus
= original.load_file( originalpath, SpecUtils::ParserType::Auto, originalext );
if( !originalstatus )
{
++failed_original_parsed;
cerr << "Failed to parse original file " << fpath << "\n\tskipping; type 'c' and enter to continue.\n\n";
char awk = (g_automated_mode ? 'c' : 'n');
while( awk != 'c' )
cin >> awk;
continue;
}
++initial_parsed;
const string tpath = SpecUtils::append_path( SpecUtils::append_path( SpecUtils::parent_path(fpath), g_truth_n42_dirname ), (filename + ".n42") );
if( !SpecUtils::is_file(tpath) )
{
cerr << "Fatal error: " << fpath << " doesnt have truth file at "
<< tpath << "\n\n";
exit( EXIT_FAILURE );
}
SpecUtils::SpecFile truth;
const bool truthstat = truth.load_file( tpath, SpecUtils::ParserType::N42_2012, "" );
if( !truthstat )
{
++failed_truth_parsed;
cerr << "Failed to parse truth file '" << tpath << "'\n\tskipping.\n\n";
continue;
}
++initial_with_truth;
truth.set_filename( original.filename() );
try
{
SpecUtils::SpecFile::equal_enough( original, truth );
++passed_tests;
}catch( std::exception &e )
{
++failed_tests;
cerr << "(on file " << file_index+1 << " of " << with_truth.size() << " )" << endl;
const string description = e.what();
vector<string> errors;
SpecUtils::split(errors, e.what(), "\n\r");
cerr << "\n" << fpath << "\nfailed comparison with previous parsing:\n";
for( const string &err : errors )
cerr << "\t" << err << endl;
cerr << "\n\t\t(Current parse is LHS, previous parse is RHS)\n"
<< "\n\tWhat would like to do?"
<< "\n";
const FixableErrors errortype = get_compare_error_type( description );
char action = (g_automated_mode ? 'i' : '\0');
while( (action != 'i') && (action != 'u') )
{
cout << "\ti: ignore\n"
<< "\to: open original file\n"
<< "\tt: open truth n42\n"
<< "\td: open contiaing directory\n"
<< "\tp: print summary of current parsing\n"
<< "\tq: print summary of truth\n"
<< "\tu: update truth\n";
if( errortype != NumFixableErrors )
cout << "\ts: set new error value to old parsing and try again\n";
cin >> action;
switch( action )
{
case 'i': break;
case 'o': open_spec_file( fpath ); break;
case 't': open_spec_file( tpath ); break;
case 'd': open_directory( fpath ); break;
case 'p': print_summary( original, cout ); break;
case 'q': print_summary( truth, cout ); break;
case 'u':
if( add_truth_n42( original, fpath, true ) )
{
++updated_truths;
cout << "\nUpdated truth info file.\n\n";
}else
{
++truths_failed_to_update;
cout << "\nFailed to updated truth info file.\n\n";
}
break;
case 's':
{
try
{
switch( errortype )
{
case UuidError:
truth.set_uuid( original.uuid() );
break;
case NumFixableErrors:
assert( 0 );
break;
}//switch( errortype )
SpecUtils::SpecFile::equal_enough( original, truth );
cout << "\nFixing the issue allowed the comparison test to pass."
<< "\nWould you like to update the truth level information?"
<< " (y/n)\n";
cin >> action;
if( action == 'y' )
{
if( add_truth_n42( original, fpath, true ) )
{
++updated_truths;
cout << "\nUpdated truth info file.\n\n";
}else
{
++truths_failed_to_update;
cout << "\nFailed to updated truth info file.\n\n";
}
action = 'u';
}//if( action == 'y' )
}catch( std::exception &e )
{
cout << "\nAfter fixing error, there was another error: \n\t"
<< e.what() << "\nNot updating truth information.\n\n";
}
break;
}//case 's':
default: break;
}//switch( action )
}//while( action != 'i' && action != 'u' )
}//try / catch
}//for( const string &path : with_truth )
cout << "Of the " << initial << " initial test files " << initial_parsed
<< " were parsable (" << failed_original_parsed << " failed).\n"
<< failed_truth_parsed << " of the truth N42 files failed to parse.\n"
<< "Of the " << initial_with_truth << " parsible original files with "
<< "valid truth N42 files: \n"
<< "\t" << passed_tests << " passed comparison\n"
<< "\t" << failed_tests << " failed comaprison, with "
<< updated_truths << " truth N42 files updated.\n";
if( truths_failed_to_update )
cerr << truths_failed_to_update << " truth n42 files failed to update!\n";
}//void check_files_with_truth_n42( const string basedir )
void check_serialization_to_n42( const string basedir )
{
size_t ninitial = 0, nOrigFileFailParse = 0,
nFailToSerialize = 0, nSerializedFileFailParse = 0,
npassed = 0, nfailed = 0;
vector<string> failedcompare;
const string tempdir = SpecUtils::temp_dir();
const vector<string> with_truth = candidates_with_truth_n42_files( basedir );
for( const string &fpath : with_truth )
{
++ninitial;
const string filename = SpecUtils::filename(fpath);
const string originalpath = fpath;
const string originalext = SpecUtils::file_extension(fpath);
SpecUtils::SpecFile info;
bool status = info.load_file( originalpath, SpecUtils::ParserType::Auto, originalext );
if( !status )
{
++nOrigFileFailParse;
cerr << "N42 Serialization Test: Failed to parse input file " << fpath
<< "\n\n";
continue;
}//if( !status )
const string tempname = SpecUtils::temp_file_name( filename, tempdir );
{//Begin codeblock to serialize to temporary file
ofstream output( tempname.c_str() );
if( !output )
{
++nFailToSerialize;
cerr << "N42 Serialization Test: Couldnt open temporary file "
<< tempname << "\n\n";
SpecUtils::remove_file( tempname.c_str() );
continue;
}
status = info.write_2012_N42( output );
if( !status )
{
++nFailToSerialize;
cerr << "N42 Serialization Test: Couldnt serialize " << fpath
<< " to temp file " << tempname << "\n\n";
SpecUtils::remove_file( tempname.c_str() );
continue;
}//if( !status )
}//End codeblock to serialize to temporary file
SpecUtils::SpecFile reread;
status = reread.load_file( tempname.c_str(), SpecUtils::ParserType::N42_2012, "" );
if( !status )
{
++nSerializedFileFailParse;
cerr << "N42 Serialization Test: Couldnt parse serialized N42 file for "
<< fpath << "\n\n";
SpecUtils::remove_file( tempname.c_str() );
continue;
}//if( !status )
reread.set_filename( info.filename() );
try
{
SpecUtils::SpecFile::equal_enough( info, reread );
++npassed;
}catch( std::exception &e )
{
const string error_msg = e.what();
++nfailed;
failedcompare.push_back( fpath );
cerr << "N42 Serialization Test: comparison test for " << fpath
<< " failed with error:\n\t" << error_msg << "\n"
<< "\t(LHS is original parse, RHS is re-ad back in)\n\n";
if( SpecUtils::contains(error_msg, " SpecUtils::SpecFile: Number of remarks in LHS") )
{
for( const string r : info.remarks() )
cout << "\t\tLHS remark: '" << r << "'" << endl;
for( const string r : reread.remarks() )
cout << "\t\tRHS remark: '" << r << "'" << endl;
}
}//try / catch
SpecUtils::remove_file( tempname.c_str() );
}//for( const string &fpath : with_truth )
cout << "N42 Serialization Test Results:\n"
<< "\tNumber of input files: " << ninitial << "\n"
<< "\tNumber of input files that failed to parse: " << nOrigFileFailParse
<< "\n\tNumber of files that failed to serialize to N42: "
<< nFailToSerialize
<< "\n\tNumber of serialed files that couldnt be parsed: "
<< nSerializedFileFailParse
<< "\n\tNumber of files that failed comparison: " << nfailed
<< "\n\tNumber of files that passed comparison: " << npassed
<< "\n\n";
if( failedcompare.size() )
{
cout << "Files failing comparison:\n";
for( const string &p : failedcompare )
cout << "\t'" << p << "'" << endl;
cout << endl << endl;
}
if( !g_automated_mode && (nFailToSerialize || nSerializedFileFailParse || nfailed) )
{
char dummy;
cout << "There was an error, enter 'x' to exit the app, or any other key"
<< " to continue.\n";
cin >> dummy;
if( dummy == 'x' )
exit( EXIT_FAILURE );
}//if( !g_automated_mode )
}//void check_serialization_to_n42( const string basedir )
void check_equality_operator( const string basedir )
{
size_t ninitial = 0, nOrigFileFailParse = 0,
npassed = 0, nfailed = 0;
vector<string> failedcompare;
// We'll only test on files with a truth-level N42 file to make sure we only
// check files known to be good spectrum files.
const vector<string> with_truth = candidates_with_truth_n42_files( basedir );
for( const string &fpath : with_truth )
{
++ninitial;
const string filename = SpecUtils::filename(fpath);
const string originalpath = fpath;
const string originalext = SpecUtils::file_extension(fpath);
SpecUtils::SpecFile info;
bool status = info.load_file( originalpath, SpecUtils::ParserType::Auto, originalext );
if( !status )
{
++nOrigFileFailParse;
cerr << "Equality Operator Test: Failed to parse input file " << fpath
<< "\n\n";
continue;
}//if( !status )
SpecUtils::SpecFile info_copy;
info_copy = info;
try
{
SpecUtils::SpecFile::equal_enough( info, info_copy );
++npassed;
}catch( std::exception &e )
{
const string error_msg = e.what();
++nfailed;
failedcompare.push_back( fpath );
cerr << "Equality Operator Test: comparison test for " << fpath
<< " failed with error:\n\t" << error_msg << "\n"
<< "\t(LHS is original parse, RHS is assigned copy)\n\n";
}//try / catch
}//for( const string &fpath : with_truth )
cout << "Equality Operator Test Results:\n"
<< "\tNumber of input files: " << ninitial << "\n"
<< "\tNumber of input files that failed to parse: " << nOrigFileFailParse
<< "\n\tNumber of files that failed comparison: " << nfailed
<< "\n\tNumber of files that passed comparison: " << npassed
<< "\n\n";
if( failedcompare.size() )
{
cout << "Files failing operator= comparison:\n";
for( const string &p : failedcompare )
cout << "\t" << p << endl;
cout << endl << endl;
}
if( !g_automated_mode && nfailed )
{
char dummy;
cout << "There was an error, enter 'x' to exit the app, or any other key"
<< " to continue.\n";
cin >> dummy;
if( dummy == 'x' )
exit( EXIT_FAILURE );
}//if( !g_automated_mode )
}//void check_equality_operator( const string basedir )
bool add_truth_n42( const SpecUtils::SpecFile &info, const string &p,
const bool force )
{
const string parentdir = SpecUtils::parent_path(p);
const string truthdir = SpecUtils::append_path(parentdir, g_truth_n42_dirname);
const string truth_n42 = SpecUtils::append_path(truthdir, (SpecUtils::filename(p) + ".n42"));
string old_n42;
const bool prevexist = SpecUtils::is_file( truth_n42 );
if( !force && prevexist )
{
cerr << "File " << truth_n42 << " already exits, not re-creating\n";
return false;
}if( prevexist )
{
old_n42 = truth_n42 + ".prev";
SpecUtils::rename_file( truth_n42, old_n42 );
}
try
{
if( !SpecUtils::is_directory( truthdir ) )
{
try
{
SpecUtils::create_directory( truthdir );
const string command = "git add '" + truthdir + "'";
const int val = system( command.c_str() );
if( val != 0 )
cerr << "\n\nThere may have been an issue adding " << truthdir
<< " to the GIT repository. Return code " << val << "\n";
}catch( std::exception &e )
{
throw runtime_error( "Couldnt create directory " + truthdir + ", so skipping file" );
}
}//if( !SpecUtils::is_directory( truthdir ) )
{//begin write file
ofstream output( truth_n42.c_str() );
if( !output )
throw runtime_error( "Couldnt create file " + truth_n42 + ", so skipping file" );
const bool status = info.write_2012_N42( output );