forked from DaehwanKimLab/centrifuge
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pat.cpp
1783 lines (1702 loc) · 46.9 KB
/
pat.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
/*
* Copyright 2011, Ben Langmead <[email protected]>
*
* This file is part of Bowtie 2.
*
* Bowtie 2 is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Bowtie 2 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Bowtie 2. If not, see <http://www.gnu.org/licenses/>.
*/
#include <cmath>
#include <iostream>
#include <string>
#include <stdexcept>
#include "sstring.h"
#include "pat.h"
#include "filebuf.h"
#include "formats.h"
#ifdef USE_SRA
#include "tinythread.h"
#include <ncbi-vdb/NGS.hpp>
#include <ngs/ErrorMsg.hpp>
#include <ngs/ReadCollection.hpp>
#include <ngs/ReadIterator.hpp>
#include <ngs/Read.hpp>
#endif
using namespace std;
/**
* Return a new dynamically allocated PatternSource for the given
* format, using the given list of strings as the filenames to read
* from or as the sequences themselves (i.e. if -c was used).
*/
PatternSource* PatternSource::patsrcFromStrings(
const PatternParams& p,
const EList<string>& qs,
int nthreads)
{
switch(p.format) {
case FASTA: return new FastaPatternSource(qs, p);
case FASTA_CONT: return new FastaContinuousPatternSource(qs, p);
case RAW: return new RawPatternSource(qs, p);
case FASTQ: return new FastqPatternSource(qs, p);
case TAB_MATE5: return new TabbedPatternSource(qs, p, false);
case TAB_MATE6: return new TabbedPatternSource(qs, p, true);
case CMDLINE: return new VectorPatternSource(qs, p);
case QSEQ: return new QseqPatternSource(qs, p);
#ifdef USE_SRA
case SRA_FASTA:
case SRA_FASTQ: return new SRAPatternSource(qs, p, nthreads);
#endif
default: {
cerr << "Internal error; bad patsrc format: " << p.format << endl;
throw 1;
}
}
}
/**
* The main member function for dispensing patterns.
*
* Returns true iff a pair was parsed succesfully.
*/
bool PatternSource::nextReadPair(
Read& ra,
Read& rb,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done,
bool& paired,
bool fixName)
{
// nextPatternImpl does the reading from the ultimate source;
// it is implemented in concrete subclasses
success = done = paired = false;
nextReadPairImpl(ra, rb, rdid, endid, success, done, paired);
if(success) {
// Construct reversed versions of fw and rc seqs/quals
ra.finalize();
if(!rb.empty()) {
rb.finalize();
}
// Fill in the random-seed field using a combination of
// information from the user-specified seed and the read
// sequence, qualities, and name
ra.seed = genRandSeed(ra.patFw, ra.qual, ra.name, seed_);
if(!rb.empty()) {
rb.seed = genRandSeed(rb.patFw, rb.qual, rb.name, seed_);
}
}
return success;
}
/**
* The main member function for dispensing patterns.
*/
bool PatternSource::nextRead(
Read& r,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done)
{
// nextPatternImpl does the reading from the ultimate source;
// it is implemented in concrete subclasses
nextReadImpl(r, rdid, endid, success, done);
if(success) {
// Construct the reversed versions of the fw and rc seqs
// and quals
r.finalize();
// Fill in the random-seed field using a combination of
// information from the user-specified seed and the read
// sequence, qualities, and name
r.seed = genRandSeed(r.patFw, r.qual, r.name, seed_);
}
return success;
}
/**
* Get the next paired or unpaired read from the wrapped
* PairedPatternSource.
*/
bool WrappedPatternSourcePerThread::nextReadPair(
bool& success,
bool& done,
bool& paired,
bool fixName)
{
PatternSourcePerThread::nextReadPair(success, done, paired, fixName);
ASSERT_ONLY(TReadId lastRdId = rdid_);
buf1_.reset();
buf2_.reset();
patsrc_.nextReadPair(buf1_, buf2_, rdid_, endid_, success, done, paired, fixName);
assert(!success || rdid_ != lastRdId);
return success;
}
/**
* The main member function for dispensing pairs of reads or
* singleton reads. Returns true iff ra and rb contain a new
* pair; returns false if ra contains a new unpaired read.
*/
bool PairedSoloPatternSource::nextReadPair(
Read& ra,
Read& rb,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done,
bool& paired,
bool fixName)
{
uint32_t cur = cur_;
success = false;
while(cur < src_->size()) {
// Patterns from srca_[cur_] are unpaired
do {
(*src_)[cur]->nextReadPair(
ra, rb, rdid, endid, success, done, paired, fixName);
} while(!success && !done);
if(!success) {
assert(done);
// If patFw is empty, that's our signal that the
// input dried up
lock();
if(cur + 1 > cur_) cur_++;
cur = cur_;
unlock();
continue; // on to next pair of PatternSources
}
assert(success);
ra.seed = genRandSeed(ra.patFw, ra.qual, ra.name, seed_);
if(!rb.empty()) {
rb.seed = genRandSeed(rb.patFw, rb.qual, rb.name, seed_);
if(fixName) {
ra.fixMateName(1);
rb.fixMateName(2);
}
}
ra.rdid = rdid;
ra.endid = endid;
if(!rb.empty()) {
rb.rdid = rdid;
rb.endid = endid+1;
}
ra.mate = 1;
rb.mate = 2;
return true; // paired
}
assert_leq(cur, src_->size());
done = (cur == src_->size());
return false;
}
/**
* The main member function for dispensing pairs of reads or
* singleton reads. Returns true iff ra and rb contain a new
* pair; returns false if ra contains a new unpaired read.
*/
bool PairedDualPatternSource::nextReadPair(
Read& ra,
Read& rb,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done,
bool& paired,
bool fixName)
{
// 'cur' indexes the current pair of PatternSources
uint32_t cur;
{
lock();
cur = cur_;
unlock();
}
success = false;
done = true;
while(cur < srca_->size()) {
if((*srcb_)[cur] == NULL) {
paired = false;
// Patterns from srca_ are unpaired
do {
(*srca_)[cur]->nextRead(ra, rdid, endid, success, done);
} while(!success && !done);
if(!success) {
assert(done);
lock();
if(cur + 1 > cur_) cur_++;
cur = cur_; // Move on to next PatternSource
unlock();
continue; // on to next pair of PatternSources
}
ra.rdid = rdid;
ra.endid = endid;
ra.mate = 0;
return success;
} else {
paired = true;
// Patterns from srca_[cur_] and srcb_[cur_] are paired
TReadId rdid_a = 0, endid_a = 0;
TReadId rdid_b = 0, endid_b = 0;
bool success_a = false, done_a = false;
bool success_b = false, done_b = false;
// Lock to ensure that this thread gets parallel reads
// in the two mate files
lock();
do {
(*srca_)[cur]->nextRead(ra, rdid_a, endid_a, success_a, done_a);
} while(!success_a && !done_a);
do {
(*srcb_)[cur]->nextRead(rb, rdid_b, endid_b, success_b, done_b);
} while(!success_b && !done_b);
if(!success_a && success_b) {
cerr << "Error, fewer reads in file specified with -1 than in file specified with -2" << endl;
throw 1;
} else if(!success_a) {
assert(done_a && done_b);
if(cur + 1 > cur_) cur_++;
cur = cur_; // Move on to next PatternSource
unlock();
continue; // on to next pair of PatternSources
} else if(!success_b) {
cerr << "Error, fewer reads in file specified with -2 than in file specified with -1" << endl;
throw 1;
}
assert_eq(rdid_a, rdid_b);
//assert_eq(endid_a+1, endid_b);
assert_eq(success_a, success_b);
unlock();
if(fixName) {
ra.fixMateName(1);
rb.fixMateName(2);
}
rdid = rdid_a;
endid = endid_a;
success = success_a;
done = done_a;
ra.rdid = rdid;
ra.endid = endid;
if(!rb.empty()) {
rb.rdid = rdid;
rb.endid = endid+1;
}
ra.mate = 1;
rb.mate = 2;
return success;
}
}
return success;
}
/**
* Return the number of reads attempted.
*/
pair<TReadId, TReadId> PairedDualPatternSource::readCnt() const {
uint64_t rets = 0llu, retp = 0llu;
for(size_t i = 0; i < srca_->size(); i++) {
if((*srcb_)[i] == NULL) {
rets += (*srca_)[i]->readCnt();
} else {
assert_eq((*srca_)[i]->readCnt(), (*srcb_)[i]->readCnt());
retp += (*srca_)[i]->readCnt();
}
}
return make_pair(rets, retp);
}
/**
* Given the values for all of the various arguments used to specify
* the read and quality input, create a list of pattern sources to
* dispense them.
*/
PairedPatternSource* PairedPatternSource::setupPatternSources(
const EList<string>& si, // singles, from argv
const EList<string>& m1, // mate1's, from -1 arg
const EList<string>& m2, // mate2's, from -2 arg
const EList<string>& m12, // both mates on each line, from --12 arg
#ifdef USE_SRA
const EList<string>& sra_accs,
#endif
const EList<string>& q, // qualities associated with singles
const EList<string>& q1, // qualities associated with m1
const EList<string>& q2, // qualities associated with m2
const PatternParams& p, // read-in parameters
int nthreads,
bool verbose) // be talkative?
{
EList<PatternSource*>* a = new EList<PatternSource*>();
EList<PatternSource*>* b = new EList<PatternSource*>();
EList<PatternSource*>* ab = new EList<PatternSource*>();
// Create list of pattern sources for paired reads appearing
// interleaved in a single file
for(size_t i = 0; i < m12.size(); i++) {
const EList<string>* qs = &m12;
EList<string> tmp;
if(p.fileParallel) {
// Feed query files one to each PatternSource
qs = &tmp;
tmp.push_back(m12[i]);
assert_eq(1, tmp.size());
}
ab->push_back(PatternSource::patsrcFromStrings(p, *qs, nthreads));
if(!p.fileParallel) {
break;
}
}
#ifdef USE_SRA
for(size_t i = 0; i < sra_accs.size(); i++) {
const EList<string>* qs = &sra_accs;
EList<string> tmp;
if(p.fileParallel) {
// Feed query files one to each PatternSource
qs = &tmp;
tmp.push_back(sra_accs[i]);
assert_eq(1, tmp.size());
}
ab->push_back(PatternSource::patsrcFromStrings(p, *qs, nthreads));
if(!p.fileParallel) {
break;
}
}
#endif
// Create list of pattern sources for paired reads
for(size_t i = 0; i < m1.size(); i++) {
const EList<string>* qs = &m1;
EList<string> tmpSeq;
EList<string> tmpQual;
if(p.fileParallel) {
// Feed query files one to each PatternSource
qs = &tmpSeq;
tmpSeq.push_back(m1[i]);
assert_eq(1, tmpSeq.size());
}
a->push_back(PatternSource::patsrcFromStrings(p, *qs, nthreads));
if(!p.fileParallel) {
break;
}
}
// Create list of pattern sources for paired reads
for(size_t i = 0; i < m2.size(); i++) {
const EList<string>* qs = &m2;
EList<string> tmpSeq;
EList<string> tmpQual;
if(p.fileParallel) {
// Feed query files one to each PatternSource
qs = &tmpSeq;
tmpSeq.push_back(m2[i]);
assert_eq(1, tmpSeq.size());
}
b->push_back(PatternSource::patsrcFromStrings(p, *qs, nthreads));
if(!p.fileParallel) {
break;
}
}
// All mates/mate files must be paired
assert_eq(a->size(), b->size());
// Create list of pattern sources for the unpaired reads
for(size_t i = 0; i < si.size(); i++) {
const EList<string>* qs = &si;
PatternSource* patsrc = NULL;
EList<string> tmpSeq;
EList<string> tmpQual;
if(p.fileParallel) {
// Feed query files one to each PatternSource
qs = &tmpSeq;
tmpSeq.push_back(si[i]);
assert_eq(1, tmpSeq.size());
}
patsrc = PatternSource::patsrcFromStrings(p, *qs, nthreads);
assert(patsrc != NULL);
a->push_back(patsrc);
b->push_back(NULL);
if(!p.fileParallel) {
break;
}
}
PairedPatternSource *patsrc = NULL;
#ifdef USE_SRA
if(m12.size() > 0 || sra_accs.size() > 0) {
#else
if(m12.size() > 0) {
#endif
patsrc = new PairedSoloPatternSource(ab, p);
for(size_t i = 0; i < a->size(); i++) delete (*a)[i];
for(size_t i = 0; i < b->size(); i++) delete (*b)[i];
delete a; delete b;
} else {
patsrc = new PairedDualPatternSource(a, b, p);
for(size_t i = 0; i < ab->size(); i++) delete (*ab)[i];
delete ab;
}
return patsrc;
}
VectorPatternSource::VectorPatternSource(
const EList<string>& v,
const PatternParams& p) :
PatternSource(p),
cur_(p.skip),
skip_(p.skip),
paired_(false),
v_(),
quals_()
{
for(size_t i = 0; i < v.size(); i++) {
EList<string> ss;
tokenize(v[i], ":", ss, 2);
assert_gt(ss.size(), 0);
assert_leq(ss.size(), 2);
// Initialize s
string s = ss[0];
int mytrim5 = gTrim5;
if(gColor && s.length() > 1) {
// This may be a primer character. If so, keep it in the
// 'primer' field of the read buf and parse the rest of the
// read without it.
int c = toupper(s[0]);
if(asc2dnacat[c] > 0) {
// First char is a DNA char
int c2 = toupper(s[1]);
// Second char is a color char
if(asc2colcat[c2] > 0) {
mytrim5 += 2; // trim primer and first color
}
}
}
if(gColor) {
// Convert '0'-'3' to 'A'-'T'
for(size_t i = 0; i < s.length(); i++) {
if(s[i] >= '0' && s[i] <= '4') {
s[i] = "ACGTN"[(int)s[i] - '0'];
}
if(s[i] == '.') s[i] = 'N';
}
}
if(s.length() <= (size_t)(gTrim3 + mytrim5)) {
// Entire read is trimmed away
s.clear();
} else {
// Trim on 5' (high-quality) end
if(mytrim5 > 0) {
s.erase(0, mytrim5);
}
// Trim on 3' (low-quality) end
if(gTrim3 > 0) {
s.erase(s.length()-gTrim3);
}
}
// Initialize vq
string vq;
if(ss.size() == 2) {
vq = ss[1];
}
// Trim qualities
if(vq.length() > (size_t)(gTrim3 + mytrim5)) {
// Trim on 5' (high-quality) end
if(mytrim5 > 0) {
vq.erase(0, mytrim5);
}
// Trim on 3' (low-quality) end
if(gTrim3 > 0) {
vq.erase(vq.length()-gTrim3);
}
}
// Pad quals with Is if necessary; this shouldn't happen
while(vq.length() < s.length()) {
vq.push_back('I');
}
// Truncate quals to match length of read if necessary;
// this shouldn't happen
if(vq.length() > s.length()) {
vq.erase(s.length());
}
assert_eq(vq.length(), s.length());
v_.expand();
v_.back().installChars(s);
quals_.push_back(BTString(vq));
trimmed3_.push_back(gTrim3);
trimmed5_.push_back(mytrim5);
ostringstream os;
os << (names_.size());
names_.push_back(BTString(os.str()));
}
assert_eq(v_.size(), quals_.size());
}
bool VectorPatternSource::nextReadImpl(
Read& r,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done)
{
// Let Strings begin at the beginning of the respective bufs
r.reset();
lock();
if(cur_ >= v_.size()) {
unlock();
// Clear all the Strings, as a signal to the caller that
// we're out of reads
r.reset();
success = false;
done = true;
assert(r.empty());
return false;
}
// Copy v_*, quals_* strings into the respective Strings
r.color = gColor;
r.patFw = v_[cur_];
r.qual = quals_[cur_];
r.trimmed3 = trimmed3_[cur_];
r.trimmed5 = trimmed5_[cur_];
ostringstream os;
os << cur_;
r.name = os.str();
cur_++;
done = cur_ == v_.size();
rdid = endid = readCnt_;
readCnt_++;
unlock();
success = true;
return true;
}
/**
* This is unused, but implementation is given for completeness.
*/
bool VectorPatternSource::nextReadPairImpl(
Read& ra,
Read& rb,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done,
bool& paired)
{
// Let Strings begin at the beginning of the respective bufs
ra.reset();
rb.reset();
paired = true;
if(!paired_) {
paired_ = true;
cur_ <<= 1;
}
lock();
if(cur_ >= v_.size()-1) {
unlock();
// Clear all the Strings, as a signal to the caller that
// we're out of reads
ra.reset();
rb.reset();
assert(ra.empty());
assert(rb.empty());
success = false;
done = true;
return false;
}
// Copy v_*, quals_* strings into the respective Strings
ra.patFw = v_[cur_];
ra.qual = quals_[cur_];
ra.trimmed3 = trimmed3_[cur_];
ra.trimmed5 = trimmed5_[cur_];
cur_++;
rb.patFw = v_[cur_];
rb.qual = quals_[cur_];
rb.trimmed3 = trimmed3_[cur_];
rb.trimmed5 = trimmed5_[cur_];
ostringstream os;
os << readCnt_;
ra.name = os.str();
rb.name = os.str();
ra.color = rb.color = gColor;
cur_++;
done = cur_ >= v_.size()-1;
rdid = endid = readCnt_;
readCnt_++;
unlock();
success = true;
return true;
}
/**
* Parse a single quality string from fb and store qualities in r.
* Assume the next character obtained via fb.get() is the first
* character of the quality string. When returning, the next
* character returned by fb.peek() or fb.get() should be the first
* character of the following line.
*/
int parseQuals(
Read& r,
FileBuf& fb,
int firstc,
int readLen,
int trim3,
int trim5,
bool intQuals,
bool phred64,
bool solexa64)
{
int c = firstc;
assert(c != '\n' && c != '\r');
r.qual.clear();
if (intQuals) {
while (c != '\r' && c != '\n' && c != -1) {
bool neg = false;
int num = 0;
while(!isspace(c) && !fb.eof()) {
if(c == '-') {
neg = true;
assert_eq(num, 0);
} else {
if(!isdigit(c)) {
char buf[2048];
cerr << "Warning: could not parse quality line:" << endl;
fb.getPastNewline();
cerr << fb.copyLastN(buf);
buf[2047] = '\0';
cerr << buf;
throw 1;
}
assert(isdigit(c));
num *= 10;
num += (c - '0');
}
c = fb.get();
}
if(neg) num = 0;
// Phred-33 ASCII encode it and add it to the back of the
// quality string
r.qual.append('!' + num);
// Skip over next stretch of whitespace
while(c != '\r' && c != '\n' && isspace(c) && !fb.eof()) {
c = fb.get();
}
}
} else {
while (c != '\r' && c != '\n' && c != -1) {
r.qual.append(charToPhred33(c, solexa64, phred64));
c = fb.get();
while(c != '\r' && c != '\n' && isspace(c) && !fb.eof()) {
c = fb.get();
}
}
}
if ((int)r.qual.length() < readLen-1 ||
((int)r.qual.length() < readLen && !r.color))
{
tooFewQualities(r.name);
}
r.qual.trimEnd(trim3);
if(r.qual.length()-trim5 < r.patFw.length()) {
assert(gColor && r.primer != -1);
assert_gt(trim5, 0);
trim5--;
}
r.qual.trimBegin(trim5);
if(r.qual.length() <= 0) return 0;
assert_eq(r.qual.length(), r.patFw.length());
while(fb.peek() == '\n' || fb.peek() == '\r') fb.get();
return (int)r.qual.length();
}
/// Read another pattern from a FASTA input file
bool FastaPatternSource::read(
Read& r,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done)
{
int c, qc = 0;
success = true;
done = false;
assert(fb_.isOpen());
r.reset();
r.color = gColor;
// Pick off the first carat
c = fb_.get();
if(c < 0) {
bail(r); success = false; done = true; return success;
}
while(c == '#' || c == ';' || c == '\r' || c == '\n') {
c = fb_.peekUptoNewline();
fb_.resetLastN();
c = fb_.get();
}
assert_eq(1, fb_.lastNLen());
// Pick off the first carat
if(first_) {
if(c != '>') {
cerr << "Error: reads file does not look like a FASTA file" << endl;
throw 1;
}
first_ = false;
}
assert_eq('>', c);
c = fb_.get(); // get next char after '>'
// Read to the end of the id line, sticking everything after the '>'
// into *name
//bool warning = false;
while(true) {
if(c < 0 || qc < 0) {
bail(r); success = false; done = true; return success;
}
if(c == '\n' || c == '\r') {
// Break at end of line, after consuming all \r's, \n's
while(c == '\n' || c == '\r') {
if(fb_.peek() == '>') {
// Empty sequence
break;
}
c = fb_.get();
if(c < 0 || qc < 0) {
bail(r); success = false; done = true; return success;
}
}
break;
}
r.name.append(c);
if(fb_.peek() == '>') {
// Empty sequence
break;
}
c = fb_.get();
}
if(c == '>') {
// Empty sequences!
cerr << "Warning: skipping empty FASTA read with name '" << r.name << "'" << endl;
fb_.resetLastN();
rdid = endid = readCnt_;
readCnt_++;
success = true; done = false; return success;
}
assert_neq('>', c);
// _in now points just past the first character of a sequence
// line, and c holds the first character
int begin = 0;
int mytrim5 = gTrim5;
if(gColor) {
// This is the primer character, keep it in the
// 'primer' field of the read buf and keep parsing
c = toupper(c);
if(asc2dnacat[c] > 0) {
// First char is a DNA char
int c2 = toupper(fb_.peek());
if(asc2colcat[c2] > 0) {
// Second char is a color char
r.primer = c;
r.trimc = c2;
mytrim5 += 2;
}
}
if(c < 0) {
bail(r); success = false; done = true; return success;
}
}
while(c != '>' && c >= 0) {
if(gColor) {
if(c >= '0' && c <= '4') c = "ACGTN"[(int)c - '0'];
if(c == '.') c = 'N';
}
if(asc2dnacat[c] > 0 && begin++ >= mytrim5) {
r.patFw.append(asc2dna[c]);
r.qual.append('I');
}
if(fb_.peek() == '>') break;
c = fb_.get();
}
r.patFw.trimEnd(gTrim3);
r.qual.trimEnd(gTrim3);
r.trimmed3 = gTrim3;
r.trimmed5 = mytrim5;
// Set up a default name if one hasn't been set
if(r.name.empty()) {
char cbuf[20];
itoa10<TReadId>(readCnt_, cbuf);
r.name.install(cbuf);
}
assert_gt(r.name.length(), 0);
r.readOrigBuf.install(fb_.lastN(), fb_.lastNLen());
fb_.resetLastN();
rdid = endid = readCnt_;
readCnt_++;
return success;
}
/// Read another pattern from a FASTQ input file
bool FastqPatternSource::read(
Read& r,
TReadId& rdid,
TReadId& endid,
bool& success,
bool& done)
{
int c;
int dstLen = 0;
success = true;
done = false;
r.reset();
r.color = gColor;
r.fuzzy = fuzzy_;
// Pick off the first at
if(first_) {
c = fb_.get();
if(c != '@') {
c = getOverNewline(fb_);
if(c < 0) {
bail(r); success = false; done = true; return success;
}
}
if(c != '@') {
cerr << "Error: reads file does not look like a FASTQ file" << endl;
throw 1;
}
assert_eq('@', c);
first_ = false;
}
// Read to the end of the id line, sticking everything after the '@'
// into *name
while(true) {
c = fb_.get();
if(c < 0) {
bail(r); success = false; done = true; return success;
}
if(c == '\n' || c == '\r') {
// Break at end of line, after consuming all \r's, \n's
while(c == '\n' || c == '\r') {
c = fb_.get();
if(c < 0) {
bail(r); success = false; done = true; return success;
}
}
break;
}
r.name.append(c);
}
// fb_ now points just past the first character of a
// sequence line, and c holds the first character
int charsRead = 0;
BTDnaString *sbuf = &r.patFw;
int dstLens[] = {0, 0, 0, 0};
int *dstLenCur = &dstLens[0];
int mytrim5 = gTrim5;
int altBufIdx = 0;
if(gColor && c != '+') {
// This may be a primer character. If so, keep it in the
// 'primer' field of the read buf and parse the rest of the
// read without it.
c = toupper(c);
if(asc2dnacat[c] > 0) {
// First char is a DNA char
int c2 = toupper(fb_.peek());
// Second char is a color char
if(asc2colcat[c2] > 0) {
r.primer = c;
r.trimc = c2;
mytrim5 += 2; // trim primer and first color
}
}
if(c < 0) {
bail(r); success = false; done = true; return success;
}
}
int trim5 = 0;
if(c != '+') {
trim5 = mytrim5;
while(c != '+') {
// Convert color numbers to letters if necessary
if(c == '.') c = 'N';
if(gColor) {
if(c >= '0' && c <= '4') c = "ACGTN"[(int)c - '0'];
}
if(fuzzy_ && c == '-') c = 'A';
if(isalpha(c)) {
// If it's past the 5'-end trim point
if(charsRead >= trim5) {
sbuf->append(asc2dna[c]);
(*dstLenCur)++;
}
charsRead++;
} else if(fuzzy_ && c == ' ') {
trim5 = 0; // disable 5' trimming for now
if(charsRead == 0) {
c = fb_.get();
continue;
}
charsRead = 0;
if(altBufIdx >= 3) {
cerr << "At most 3 alternate sequence strings permitted; offending read: " << r.name << endl;
throw 1;
}
// Move on to the next alternate-sequence buffer
sbuf = &r.altPatFw[altBufIdx++];
dstLenCur = &dstLens[altBufIdx];
}
c = fb_.get();
if(c < 0) {
bail(r); success = false; done = true; return success;
}
}
dstLen = dstLens[0];
charsRead = dstLen + mytrim5;
}
// Trim from 3' end
if(gTrim3 > 0) {
if((int)r.patFw.length() > gTrim3) {
r.patFw.resize(r.patFw.length() - gTrim3);
dstLen -= gTrim3;
assert_eq((int)r.patFw.length(), dstLen);
} else {
// Trimmed the whole read; we won't be using this read,
// but we proceed anyway so that fb_ is advanced
// properly
r.patFw.clear();
dstLen = 0;
}
}
assert_eq('+', c);
// Chew up the optional name on the '+' line
ASSERT_ONLY(int pk =) peekToEndOfLine(fb_);
if(charsRead == 0) {
assert_eq('@', pk);
fb_.get();
fb_.resetLastN();
rdid = endid = readCnt_;
readCnt_++;
return success;
}
// Now read the qualities
if (intQuals_) {
assert(!fuzzy_);
int qualsRead = 0;
char buf[4096];