File: bedFile.h

package info (click to toggle)
bedtools 2.27.1%2Bdfsg-4
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 54,804 kB
  • sloc: cpp: 38,072; sh: 7,307; makefile: 2,241; python: 163
file content (1343 lines) | stat: -rw-r--r-- 44,266 bytes parent folder | download | duplicates (2)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
/*****************************************************************************
  bedFile.h

  (c) 2009 - Aaron Quinlan
  Hall Laboratory
  Department of Biochemistry and Molecular Genetics
  University of Virginia
  aaronquinlan@gmail.com

  Licensed under the GNU General Public License 2.0 license.
******************************************************************************/
#ifndef BEDFILE_H
#define BEDFILE_H

// "local" includes
#include "gzstream.h"
#include "lineFileUtilities.h"
#include "fileType.h"

// standard includes
#include <vector>
#include <map>
#include <set>
#include <string>
#include <iostream>
#include <fstream>
#include <sstream>
#include <cstring>
#include <algorithm>
#include <limits.h>
#include <stdint.h>
#include <cstdio>
//#include <tr1/unordered_map>  // Experimental.
using namespace std;


//*************************************************
// Data type tydedef
//*************************************************
typedef uint32_t CHRPOS;
typedef uint16_t BINLEVEL;
typedef uint32_t BIN;
typedef uint16_t USHORT;
typedef uint32_t UINT;

//*************************************************
// Genome binning constants
//*************************************************
const BIN      _numBins   = 37450;
const BINLEVEL _binLevels = 7;

// bins range in size from 16kb to 512Mb
// Bin  0          spans 512Mbp,   # Level 1
// Bins 1-8        span 64Mbp,     # Level 2
// Bins 9-72       span 8Mbp,      # Level 3
// Bins 73-584     span 1Mbp       # Level 4
// Bins 585-4680   span 128Kbp     # Level 5
// Bins 4681-37449 span 16Kbp      # Level 6
const BIN _binOffsetsExtended[] = {32678+4096+512+64+8+1, 4096+512+64+8+1, 512+64+8+1, 64+8+1, 8+1, 1, 0};
//const BIN _binOffsetsExtended[] = {4096+512+64+8+1, 4096+512+64+8+1, 512+64+8+1, 64+8+1, 8+1, 1, 0};

const USHORT _binFirstShift = 14;       /* How much to shift to get to finest bin. */
const USHORT _binNextShift  = 3;        /* How much to shift to get to next larger bin. */


//*************************************************
// Common data structures
//*************************************************

struct DEPTH {
    UINT starts;
    UINT ends;
};


/*
    Structure for regular BED records
*/
struct BED {

    // Regular BED fields
    string chrom;
    CHRPOS start;
    CHRPOS end;
    string name;
    string score;
    string strand;
    // all of the original fields in the record
    vector<string> fields;
    // indices of the "other" fields
    vector<uint16_t> other_idxs;
    // is this a zero length feature: i.e., start == end
    bool   zeroLength;
    double weight;

public:
    // constructors

    // Null
    BED()
    : chrom(""),
      start(0),
      end(0),
      name(""),
      score(""),
      strand(""),
      fields(),
      other_idxs(),
      zeroLength(false),
      weight(0.0)
    {}

    // BED3
    BED(string chrom, CHRPOS start, CHRPOS end)
    : chrom(chrom),
      start(start),
      end(end),
      name(""),
      score(""),
      strand(""),
      fields(),
      other_idxs(),
      zeroLength(false),
      weight(0.0)
    {}

    // BED4
    BED(string chrom, CHRPOS start, CHRPOS end, string strand)
    : chrom(chrom),
      start(start),
      end(end),
      name(""),
      score(""),
      strand(strand),
      fields(),
      other_idxs(),
      zeroLength(false),
      weight(0.0)
    {}

    // BED6
    BED(string chrom, CHRPOS start, CHRPOS end, string name,
        string score, string strand)
    : chrom(chrom),
      start(start),
      end(end),
      name(name),
      score(score),
      strand(strand),
      fields(),
      other_idxs(),
      zeroLength(false),
      weight(0.0)
    {}

    // BEDALL
    BED(string chrom, CHRPOS start, CHRPOS end, string name,
        string score, string strand, vector<string> fields, 
        vector<uint16_t> other_idxs)
    : chrom(chrom),
      start(start),
      end(end),
      name(name),
      score(score),
      strand(strand),
      fields(fields),
      other_idxs(other_idxs),
      zeroLength(false),
      weight(0.0)
    {}
    
    int size() const {
        return end-start;
    }

}; // BED


/*
    Structure for each end of a paired BED record
    mate points to the other end.
*/
struct MATE {
    BED bed;
    int lineNum;
    MATE *mate;
};


/*
    Structure for regular BED COVERAGE records
*/
struct BEDCOV {

    string chrom;
    
    // Regular BED fields
    CHRPOS start;
    CHRPOS end;
    string name;
    string score;
    string strand;

    // all of the original fields in the record
    vector<string> fields;
    // indices of the "other" fields
    vector<uint16_t> other_idxs;
    // is this a zero length feature: i.e., start == end
    bool   zeroLength;
    
    // Additional fields specific to computing coverage
    map<unsigned int, DEPTH> depthMap;
    unsigned int count;
    CHRPOS minOverlapStart;
    
    
    public:
    // constructors
    // Null
    BEDCOV()
    : chrom(""),
      start(0),
      end(0),
      name(""),
      score(""),
      strand(""),
      fields(),
      other_idxs(),
      zeroLength(false),
      depthMap(),
      count(0),
      minOverlapStart(0)
    {}
};


/*
    Structure for BED COVERAGE records having lists of
    multiple coverages
*/
struct BEDCOVLIST {

    // Regular BED fields
    string chrom;
    CHRPOS start;
    CHRPOS end;
    string name;
    string score;
    string strand;

    // all of the original fields in the record
    vector<string> fields;
    // indices of the "other" fields
    vector<uint16_t> other_idxs;
    // is this a zero length feature: i.e., start == end
    bool   zeroLength;

    // Additional fields specific to computing coverage
    vector< map<unsigned int, DEPTH> > depthMapList;
    vector<unsigned int> counts;
    vector<CHRPOS> minOverlapStarts;
    
    
    public:
    // constructors
    // Null
    BEDCOVLIST()
    : chrom(""),
      start(0),
      end(0),
      name(""),
      score(""),
      strand(""),
      fields(),
      other_idxs(),
      zeroLength(false),
      depthMapList(),
      counts(0),
      minOverlapStarts(0)
    {}
};


// enum to flag the state of a given line in a BED file.
enum BedLineStatus
{
    BED_INVALID = -1,
    BED_HEADER  = 0,
    BED_BLANK   = 1,
    BED_VALID   = 2
};

// enum to indicate the type of file we are dealing with
enum FileType
{
    BED_FILETYPE,
    GFF_FILETYPE,
    VCF_FILETYPE
};

//*************************************************
// Data structure typedefs
//*************************************************
typedef vector<BED>    bedVector;
typedef vector<BEDCOV> bedCovVector;
typedef vector<MATE> mateVector;
typedef vector<BEDCOVLIST> bedCovListVector;

typedef map<BIN, bedVector> binsToBeds;
typedef map<BIN, bedCovVector> binsToBedCovs;
typedef map<BIN, mateVector> binsToMates;
typedef map<BIN, bedCovListVector> binsToBedCovLists;

typedef map<string, binsToBeds>    masterBedMap;
typedef map<string, binsToBedCovs> masterBedCovMap;
typedef map<string, binsToMates> masterMateMap;
typedef map<string, binsToBedCovLists> masterBedCovListMap;
typedef map<string, bedVector>     masterBedMapNoBin;


// return the genome "bin" for a feature with this start and end
inline
BIN getBin(CHRPOS start, CHRPOS end) {
    --end;
    start >>= _binFirstShift;
    end   >>= _binFirstShift;

    for (short i = 0; i < _binLevels; ++i) {
        if (start == end) return _binOffsetsExtended[i] + start;
        start >>= _binNextShift;
        end   >>= _binNextShift;
    }
    cerr << "start " << start << ", end " << end 
         << " out of range in findBin (max is 512M)" 
         << endl;
    return 0;
}

/****************************************************
// isInteger(s): Tests if string s is a valid integer
*****************************************************/
inline bool isInteger(const std::string& s) {
    int len = s.length();
    for (int i = 0; i < len; i++) {
        if (!std::isdigit(s[i])) return false;
    }
    return true;
}


// return the amount of overlap between two features.  Negative if none and the
// number of negative bases is the distance between the two.
inline
int overlaps(CHRPOS aS, CHRPOS aE, CHRPOS bS, CHRPOS bE) {
    return min(aE, bE) - max(aS, bS);
}

// is A after (to the right of) B?
inline
bool after(const BED &a, const BED &b) {
    return (a.start >= b.end);
}


// Ancillary functions
void splitBedIntoBlocks(const BED &bed, bedVector &bedBlocks);


// BED Sorting Methods
bool sortByChrom(const BED &a, const BED &b);
bool sortByStart(const BED &a, const BED &b);
bool sortBySizeAsc(const BED &a, const BED &b);
bool sortBySizeDesc(const BED &a, const BED &b);
bool sortByScoreAsc(const BED &a, const BED &b);
bool sortByScoreDesc(const BED &a, const BED &b);
bool byChromThenStart(BED const &a, BED const &b);



//************************************************
// BedFile Class methods and elements
//************************************************
class BedFile {

public:

    // Constructor
    BedFile(string &);
    BedFile(void);

    // Destructor
    ~BedFile(void);

    /********* File management ********/
    // Open a BED file for reading (creates an istream pointer)
    void Open(void);

    // Close an opened BED file.
    void Close(void);

    // are the any intervals left in the file?
    bool Empty(void);

    // Rewind the pointer back to the beginning of the file
    void Rewind(void);

    // Jump to a specific byte in the file
    void Seek(unsigned long offset);

    // dump the header, which is collected as part of Open()
    void PrintHeader(void);

    // Get the next BED entry in an opened BED file.
    bool GetNextBed (BED &bed, bool forceSorted = false);
    
    // Returns the next MERGED (i.e., non-overlapping) interval in 
    // an opened BED file
    // NOTE: assumes input file is sorted by chrom then start
    bool GetNextMergedBed(BED &merged_bed);

    // load a BED file into a map keyed by chrom, then bin. value is 
    // vector of BEDs
    void loadBedFileIntoMap();
    void loadBedFileIntoMergedMap();

    // load a BED entry into and existing map
    void addBEDIntoMap(BED bedEntry);

    // load a BED file into a map keyed by chrom, then bin. value is 
    // vector of BEDCOVs
    void loadBedCovFileIntoMap();

    // load a BED file into a map keyed by chrom, then bin. value is 
    // vector of BEDCOVLISTs
    void loadBedCovListFileIntoMap();

    // load a BED file into a map keyed by chrom. value is vector of BEDs
    void loadBedFileIntoMapNoBin();

    // load a BED file into a vector of BEDs
    void loadBedFileIntoVector();

    // load a BED file into a vector ordered in decreasing order by size
    void assignWeightsBasedOnSize();

    BED * sizeWeightedSearch(double val);

    // Given a chrom, start, end and strand for a single feature,
    // search for all overlapping features in another BED file.
    // Searches through each relevant genome bin on the same chromosome
    // as the single feature. Note: Adapted from kent source "binKeeperFind"
    void allHits(string chrom, CHRPOS start, CHRPOS end, string strand, 
                 vector<BED> &hits, bool sameStrand, bool diffStrand, 
                 float overlapFraction, bool reciprocal);

    // return true if at least one overlap was found.  otherwise, return false.
    bool anyHits(string chrom, CHRPOS start, CHRPOS end, string strand,
                bool sameStrand, bool diffStrand, float overlapFraction, bool reciprocal);


    // Given a chrom, start, end and strand for a single feature,
    // increment a the number of hits for each feature in B file
    // that the feature overlaps
    void countHits(const BED &a, bool sameStrand = false, 
                   bool diffStrand = false, bool countsOnly = false);

    // same as above, but has special logic that processes a set of
    // BED "blocks" from a single entry so as to avoid over-counting
    // each "block" of a single BAM/BED12 as distinct coverage.  That is,
    // if one read has four block, we only want to count the coverage as
    // coming from one read, not four.
    void countSplitHits(const vector<BED> &bedBlock, bool sameStrand = false, 
                        bool diffStrand = false, bool countsOnly = false);

    // Given a chrom, start, end and strand for a single feature,
    // increment a the number of hits for each feature in B file
    // that the feature overlaps
    void countListHits(const BED &a, int index, 
                       bool sameStrand, bool diffStrand);
    
    
    // return the total length of all the intervals in the file.
    // use with GetNextBed()
    unsigned long getTotalLength(void);

    // return the total _flattened_ length of all the intervals in the file.
    // use with GetNextMergedBed()
    unsigned long getTotalFlattenedLength(void);
    

    // the bedfile with which this instance is associated
    string bedFile;
    unsigned int bedType;  // 3-6, 12 for BED
                           // 9 for GFF
    bool isBed12;          // is it file of true blocked BED12 records?
    bool isZeroBased;

    // Main data structures used by BEDTools
    masterBedCovMap      bedCovMap;
    masterBedCovListMap  bedCovListMap;
    masterBedMap         bedMap;
    bedVector            bedList;
    masterBedMapNoBin    bedMapNoBin;
    
    BedLineStatus _status;
    int _lineNum;

private:

    // data
    bool _isGff;
    bool _isVcf;
    bool _typeIsKnown;        // do we know the type?   (i.e., BED, GFF, VCF)
    FileType   _fileType;     // what is the file type? (BED? GFF? VCF?)
    istream   *_bedStream;
    string _bedLine;

    BED _nullBed;
    string _header;
    bool _firstLine;
    vector<string> _bedFields;
    unsigned int _numFields;
    int _merged_start;
    int _merged_end;
    string _merged_chrom;
    int _prev_start;
    string _prev_chrom;
    unsigned long _total_length;
    unsigned long _total_flattened_length;

    void setZeroBased(bool zeroBased);
    void setGff (bool isGff);
    void setVcf (bool isVcf);
    void setFileType (FileType type);
    void setBedType (int colNums);
    void setBed12 (bool isBed12);

    /************ Private utilities ***********************/
    void GetHeader(void);

    /******************************************************
    Private definitions to circumvent linker issues with
    templated member functions.
    *******************************************************/

    /*
        parseLine: converts a lineVector into either BED or BEDCOV (templated, hence in header to avoid linker issues.)
    */
    template <typename T>
    inline BedLineStatus parseLine (T &bed, const vector<string> &fields) {
        
        // clear out the data from the last line.
        bed = _nullBed;
        // bail out if we have a blank line
        if (_numFields == 0) {
            return BED_BLANK;
        }
        // bail out if we have a comment line
        if ( (fields[0].find("#")       == 0) ||
             (fields[0].find("browser") == 0) ||
             (fields[0].find("track")   == 0) 
           )
        {
            return BED_HEADER;
        }

        if (_numFields >= 3) {
            // line parsing for all lines after the first non-header line
            if (_typeIsKnown == true) {
                switch(_fileType) {
                    case BED_FILETYPE:
                        if (parseBedLine(bed, fields) == true) 
                            return BED_VALID;
                    case VCF_FILETYPE:
                        if (parseVcfLine(bed, fields) == true)
                        {
                            return BED_VALID;
                        }
                    case GFF_FILETYPE:
                        if (parseGffLine(bed, fields) == true) 
                                return BED_VALID;
                    default:
                        printf("ERROR: file type encountered. Exiting\n");
                        exit(1);
                }
            }
            // line parsing for first non-header line: figure out file contents
            else {
                // it's BED format if columns 2 and 3 are integers
                if (isInteger(fields[1]) && isInteger(fields[2])) {
                    setGff(false);
                    setZeroBased(true);
                    setFileType(BED_FILETYPE);
                    // we now expect numFields columns in each line
                    setBedType(_numFields);
                    
                    // test to see if the file has true blocked BED12 records
                    if (_numFields == 12) {
                        int cdsStart = atoi(fields[6].c_str());
                        int cdsEnd   = atoi(fields[7].c_str());
                        int numExons = atoi(fields[9].c_str());

                        if (cdsStart > 0 && cdsEnd > 0&& numExons > 0 &&
                            fields[10].find(",") == 0 &&
                            fields[11].find(",") == 0)
                        {
                            setBed12(true);
                        }
                        else setBed12(false);
                    }
                    if (parseBedLine(bed, fields) == true) 
                        return BED_VALID;
                }
                // it's VCF, assuming the second column is numeric and 
                // there are at least 8 fields.
                else if (isInteger(fields[1]) && _numFields >= 8) {
                    setGff(false);
                    setVcf(true);
                    setZeroBased(false);
                    setFileType(VCF_FILETYPE);
                    // we now expect numFields columns in each line
                    setBedType(_numFields);
                    if (parseVcfLine(bed, fields) == true) 
                        return BED_VALID;
                }
                // it's GFF, assuming columns columns 4 and 5 are numeric 
                // and we have 9 fields total.
                else if ((_numFields >= 8) && 
                          isInteger(fields[3]) && 
                          isInteger(fields[4])) 
                {
                    setGff(true);
                    setZeroBased(false);
                    setFileType(GFF_FILETYPE);
                    // we now expect numFields columns in each line
                    setBedType(_numFields);
                    if (parseGffLine(bed, fields) == true) 
                    {
                        return BED_VALID;
                    }
                }
                else {
                    cerr << "Unexpected file format.  "
                         << "Please use tab-delimited BED, GFF, or VCF. " 
                         << "Perhaps you have non-integer starts or ends "
                         << "at line " 
                         << _lineNum 
                         << "?" 
                         << endl;
                    exit(1);
                }
            }
        }
        else {
            cerr << "It looks as though you have less than 3 columns at line: " 
                 << _lineNum 
                 << ".  Are you sure your files are tab-delimited?" 
                 << endl;
            exit(1);
        }
        // default
        return BED_INVALID;
    }


    /*
        parseBedLine: converts a lineVector into either BED or BEDCOV (templated, hence in header to avoid linker issues.)
    */
    template <typename T>
    inline bool parseBedLine (T &bed, const vector<string> &fields) 
    {
        // process as long as the number of fields in this
        // line matches what we expect for this file.
        if (_numFields == this->bedType) {
            bed.fields = fields;
            bed.chrom = fields[0];
            int i;
            i = atoi(fields[1].c_str());
            if (i<0) {
                 cerr << "Error: malformed BED entry at line " 
                      << _lineNum 
                      << ". Start Coordinate detected that is < 0. Exiting." 
                      << endl;
                 exit(1);
            }
            bed.start = (CHRPOS)i;
            i = atoi(fields[2].c_str());
            if (i<0) {
                cerr << "Error: malformed BED entry at line " 
                     << _lineNum 
                     << ". End Coordinate detected that is < 0. Exiting." 
                     << endl;
                exit(1);
            }
            bed.end = (CHRPOS)i;
            
            // handle starts == end (e.g., insertions in reference genome)
            if (bed.start == bed.end) {
                bed.start--;
                bed.end++;
                bed.zeroLength = true;
            }
            
            if (this->bedType == 4) {
                bed.name = fields[3];
            }
            else if (this->bedType == 5) {
                bed.name = fields[3];
                bed.score = fields[4];
            }
            else if (this->bedType == 6) {
                bed.name = fields[3];
                bed.score = fields[4];
                bed.strand = fields[5];
            }
            else if (this->bedType > 6) {
                bed.name = fields[3];
                bed.score = fields[4];
                bed.strand = fields[5];
                for (unsigned int i = 6; i < fields.size(); ++i) {
                    bed.other_idxs.push_back(i);
                }
            }
            else if (this->bedType != 3) {
                cerr << "Error: unexpected number of fields at line: " 
                     << _lineNum
                     << ".  Verify that your files are TAB-delimited. "     
                     << "Exiting..." 
                     << endl;
                exit(1);
            }

            // sanity checks.
            if (bed.start <= bed.end) {
                return true;
            }
            else {
                cerr << "Error: malformed BED entry at line " 
                     << _lineNum 
                     << ". Start was greater than end. Exiting." 
                     << endl;
                exit(1);
            }
        }
        else if (_numFields == 1) {
            cerr << "Only one BED field detected: " 
                 << _lineNum 
                 << ".  Verify that your files are TAB-delimited.  Exiting..." 
                 << endl;
            exit(1);
        }
        else if ((_numFields != this->bedType) && (_numFields != 0)) {
            cerr << "Differing number of BED fields encountered at line: " 
                 << _lineNum 
                 << ".  Exiting..." 
                 << endl;
            exit(1);
        }
        else if ((_numFields < 3) && (_numFields != 0)) {
            cerr << "TAB delimited BED file with at least 3 fields"
                 << " (chrom, start, end) is required at line: "
                 << _lineNum 
                 << ".  Exiting..." 
                 << endl;
            exit(1);
        }
        return false;
    }


    /*
        parseVcfLine: converts a lineVector into either BED or BEDCOV (templated, hence in header to avoid linker issues.)
    */
    template <typename T>
    inline bool parseVcfLine (T &bed, const vector<string> &fields) 
    {
        if (_numFields >= this->bedType) {
            bed.fields = fields;
            bed.chrom  = fields[0];
            // VCF is one-based
            bed.start  = atoi(fields[1].c_str()) - 1;  
            // VCF 4.0 stores the size of the affected REF allele.
            bed.end    = bed.start + fields[3].size(); 
            bed.strand = "+";
            // construct the name from the ref and alt alleles.
            // if it's an annotated variant, add the rsId as well.
            bed.name   = fields[3] + "/" + fields[4];
            if (fields[2] != ".") {
                bed.name += "_" + fields[2];
            }

            if (this->bedType > 2) {
                for (unsigned int i = 2; i < _numFields; ++i)
                    bed.other_idxs.push_back(i);
            }

            if ((bed.start <= bed.end) && (bed.start >= 0) && ((bed.end) >= 0)) {
                return true;
            }
            else if (bed.start > bed.end) {
                cerr << "Error: malformed VCF entry at line " 
                    << _lineNum 
                    << ". Start was greater than end. Exiting." 
                    << endl;
                exit(1);
            }
            else if ( (bed.start < 0) || ((bed.end) < 0) ) {
                cerr << "Error: malformed VCF entry at line " 
                     << _lineNum << ". Coordinate detected that is < 0. "
                     << "Exiting." 
                     << endl;
                exit(1);
            }
        }
        else if (_numFields == 1) {
            cerr << "Only one VCF field detected: " 
                 << _lineNum 
                 << ".  Verify that your files are TAB-delimited. "
                 << "Exiting..." 
                 << endl;
            exit(1);
        }
        else if ((_numFields != this->bedType) && (_numFields != 0)) {
            cerr << "Differing number of VCF fields encountered at line: " 
                 << _lineNum 
                 << ".  Exiting..." 
                 << endl;
            exit(1);
        }
        else if ((_numFields < 2) && (_numFields != 0)) {
            cerr << "TAB delimited VCF file with at least 2 fields "
                 << "(chrom, pos) is required at line: "
                 << _lineNum 
                 << ".  Exiting..." 
                 << endl;
            exit(1);
        }
        return false;
    }



    /*
        parseGffLine: converts a lineVector into either BED or BEDCOV (templated, hence in header to avoid linker issues.)
    */
    template <typename T>
    inline bool parseGffLine (T &bed, const vector<string> &fields) 
    {
        if (_numFields == this->bedType) {
            bed.fields = fields;
            if (this->bedType >= 8 && _isGff) {
                bed.chrom = fields[0];
                if (isInteger(fields[3]))
                    bed.start  = atoi(fields[3].c_str());
                if (isInteger(fields[4]))
                    bed.end  = atoi(fields[4].c_str());
                bed.name   = fields[2];
                bed.score  = fields[5];
                bed.strand = fields[6].c_str();
                // add GFF "source". unused in BED
                bed.other_idxs.push_back(1); 
                // add GFF "fname". unused in BED
                bed.other_idxs.push_back(7);  
                // handle the optional 9th field.
                if (this->bedType == 9)
                    // add GFF "group". unused in BED
                    bed.other_idxs.push_back(8); 
                bed.start--;
            }
            else {
                cerr << "Error: unexpected number of fields at line: " 
                    << _lineNum 
                    << ".  Verify that your files are TAB-delimited and that "
                    << "your GFF file has 8 or 9 fields.  Exiting..." 
                    << endl;
                exit(1);
            }
            if (bed.start > bed.end) {
                cerr << "Error: malformed GFF entry at line " 
                     << _lineNum 
                     << ". Start was greater than end. Exiting." 
                     << endl;
                exit(1);
            }
            if ( (bed.start < 0) || ((bed.end) < 0) ) {
                cerr << "Error: malformed GFF entry at line " 
                     << _lineNum 
                     << ". Coordinate detected that is < 1. Exiting." 
                     << endl;
                exit(1);
            }
            return true;
        }
        else if (_numFields == 1) {
            cerr << "Only one GFF field detected: " 
                 << _lineNum 
                 << ".  Verify that your files are TAB-delimited.  Exiting..." 
                 << endl;
            exit(1);
        }
        else if ((_numFields != this->bedType) && (_numFields != 0)) {
            cerr << "Differing number of GFF fields encountered at line: " 
                 << _lineNum 
                 << ".  Exiting..." 
                 << endl;
            exit(1);
        }
        else if ((_numFields < 8) && (_numFields != 0)) {
            cerr << "TAB delimited GFF file with 8 or 9 fields is required"
                 << " at line: "
                 << _lineNum 
                 << ".  Exiting..." 
                 << endl;
            exit(1);
        }
        return false;
    }


public:

    /*
        reportBedTab

        Writes the _original_ BED entry with a TAB
        at the end of the line.
        Works for BED3 - BED6.
    */
    template <typename T>
    inline void reportBedTab(const T &bed) {
        // if it is azeroLength feature, we need to
        // correct the start and end coords to what they were
        // in the original file
        CHRPOS start = bed.start;
        CHRPOS end   = bed.end;
        if (bed.zeroLength) {
            if (_isGff == false)
                start++;
            end--;
        }
        
        // BED
        if (_isGff == false && _isVcf == false) {
            if (this->bedType == 3) {
                printf ("%s\t%d\t%d\t", bed.chrom.c_str(), start, end);
            }
            else if (this->bedType == 4) {
                printf ("%s\t%d\t%d\t%s\t", 
                    bed.chrom.c_str(), start, end, bed.name.c_str());
            }
            else if (this->bedType == 5) {
                printf ("%s\t%d\t%d\t%s\t%s\t", 
                    bed.chrom.c_str(), start, end, 
                    bed.name.c_str(), bed.score.c_str());
            }
            else if (this->bedType == 6) {
                printf ("%s\t%d\t%d\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), start, end, 
                    bed.name.c_str(), bed.score.c_str(), bed.strand.c_str());
            }
            else if (this->bedType > 6) {
                printf ("%s\t%d\t%d\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), start, end, bed.name.c_str(),
                    bed.score.c_str(), bed.strand.c_str());
                
                vector<uint16_t>::const_iterator 
                    othIt  = bed.other_idxs.begin();
                vector<uint16_t>::const_iterator 
                    othEnd = bed.other_idxs.end();
                for ( ; othIt != othEnd; ++othIt) {
                    printf("%s\t", bed.fields[*othIt].c_str());
                }
            }
        }
        // VCF
        else if (_isGff == false && _isVcf == true) {
            printf ("%s\t%d\t", bed.chrom.c_str(), start+1);

            vector<uint16_t>::const_iterator othIt  = bed.other_idxs.begin();
            vector<uint16_t>::const_iterator othEnd = bed.other_idxs.end();
            for ( ; othIt != othEnd; ++othIt) {
                printf("%s\t", bed.fields[*othIt].c_str());
            }
        }
        // GFF
        else if (_isGff == true) {
            // "GFF-8"
            if (this->bedType == 8) {
                printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end, bed.score.c_str(), 
                    bed.strand.c_str(), bed.fields[bed.other_idxs[1]].c_str());
            }
            // "GFF-9"
            else if (this->bedType == 9) {
                printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end,
                    bed.score.c_str(), bed.strand.c_str(),
                    bed.fields[bed.other_idxs[1]].c_str(), 
                    bed.fields[bed.other_idxs[2]].c_str());
            }
        }
    }



    /*
        reportToFileBedNewLine

        Writes the _original_ BED entry with a NEWLINE
        at the end of the line.
        Works for BED3 - BED6.
    */
    template <typename T>
    inline void reportToFileBedNewLine(FILE* out,const T &bed) {
        
        // if it is azeroLength feature, we need to
        // correct the start and end coords to what they were
        // in the original file
        CHRPOS start = bed.start;
        CHRPOS end   = bed.end;
        if (bed.zeroLength) {
            if (_isGff == false)
                start++;
            end--;
        }
        //BED
        if (_isGff == false && _isVcf == false) {
            if (this->bedType == 3) {
                fprintf(out,"%s\t%d\t%d\n", bed.chrom.c_str(), start, end);
            }
            else if (this->bedType == 4) {
                fprintf(out,"%s\t%d\t%d\t%s\n", 
                    bed.chrom.c_str(), start, end, bed.name.c_str());
            }
            else if (this->bedType == 5) {
                fprintf(out,"%s\t%d\t%d\t%s\t%s\n", 
                    bed.chrom.c_str(), start, end, 
                    bed.name.c_str(), bed.score.c_str());
            }
            else if (this->bedType == 6) {
                fprintf(out,"%s\t%d\t%d\t%s\t%s\t%s\n", 
                    bed.chrom.c_str(), start, end, bed.name.c_str(),
                    bed.score.c_str(), bed.strand.c_str());
            }
            else if (this->bedType > 6) {
                fprintf(out,"%s\t%d\t%d\t%s\t%s\t%s", 
                    bed.chrom.c_str(), start, end, bed.name.c_str(),
                    bed.score.c_str(), bed.strand.c_str());

                vector<uint16_t>::const_iterator 
                    othIt  = bed.other_idxs.begin();
                vector<uint16_t>::const_iterator 
                    othEnd = bed.other_idxs.end();
                for ( ; othIt != othEnd; ++othIt) {
                    fprintf(out,"\t%s", bed.fields[*othIt].c_str());
                }
                fprintf(out,"\n");
            }
        }
        // VCF
        else if (_isGff == false && _isVcf == true) {
            fprintf(out,"%s\t%d", bed.chrom.c_str(), start+1);

            vector<uint16_t>::const_iterator othIt  = bed.other_idxs.begin();
            vector<uint16_t>::const_iterator othEnd = bed.other_idxs.end();
            for ( ; othIt != othEnd; ++othIt) {
                fprintf(out,"\t%s", bed.fields[*othIt].c_str());
            }
            fprintf(out,"\n");
        }
        // GFF
        else if (_isGff == true) {
            // "GFF-8"
            if (this->bedType == 8) {
                fprintf (out,"%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\n", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end,
                    bed.score.c_str(), bed.strand.c_str(),
                    bed.fields[bed.other_idxs[1]].c_str());
            }
            // "GFF-9"
            else if (this->bedType == 9) {
                fprintf (out,"%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end,
                    bed.score.c_str(), bed.strand.c_str(),
                    bed.fields[bed.other_idxs[1]].c_str(), 
                    bed.fields[bed.other_idxs[2]].c_str());
            }
        }
    }

    /* specialized version of reportBedNewLine printing to stdout */
     template <typename T>
     inline void reportBedNewLine(const T &bed) {
     reportToFileBedNewLine(stdout,bed);
     }

    /*
        reportBedRangeNewLine

        Writes a custom start->end for a BED entry
        with a NEWLINE at the end of the line.

        Works for BED3 - BED6.
    */
    template <typename T>
    inline void reportBedRangeTab(const T &bed, CHRPOS start, CHRPOS end) {
        // if it is azeroLength feature, we need to
        // correct the start and end coords to what they were
        // in the original file
        if (bed.zeroLength) {
            start = bed.start + 1;
            end   = bed.end - 1;
        }
        // BED
        if (_isGff == false && _isVcf == false) {
            if (this->bedType == 3) {
                printf ("%s\t%d\t%d\t", bed.chrom.c_str(), start, end);
            }
            else if (this->bedType == 4) {
                printf ("%s\t%d\t%d\t%s\t", 
                    bed.chrom.c_str(), start, end, bed.name.c_str());
            }
            else if (this->bedType == 5) {
                printf ("%s\t%d\t%d\t%s\t%s\t", 
                    bed.chrom.c_str(), start, end, 
                    bed.name.c_str(), bed.score.c_str());
            }
            else if (this->bedType == 6) {
                printf ("%s\t%d\t%d\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), start, end, bed.name.c_str(),
                    bed.score.c_str(), bed.strand.c_str());
            }
            else if (this->bedType > 6) {
                printf ("%s\t%d\t%d\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), start, end, bed.name.c_str(),
                    bed.score.c_str(), bed.strand.c_str());
                
                vector<uint16_t>::const_iterator 
                    othIt  = bed.other_idxs.begin();
                vector<uint16_t>::const_iterator 
                    othEnd = bed.other_idxs.end();
                for ( ; othIt != othEnd; ++othIt) {
                    printf("%s\t", bed.fields[*othIt].c_str());
                }
            }
        }
        // VCF
        else if (_isGff == false && _isVcf == true) {
            printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
            vector<uint16_t>::const_iterator othIt  = bed.other_idxs.begin();
            vector<uint16_t>::const_iterator othEnd = bed.other_idxs.end();
            for ( ; othIt != othEnd; ++othIt) {
                printf("%s\t", bed.fields[*othIt].c_str());
            }
        }
        // GFF
        else if (_isGff == true) {
            // "GFF-8"
            if (this->bedType == 8) {
                printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end,
                    bed.score.c_str(), bed.strand.c_str(),
                    bed.fields[bed.other_idxs[1]].c_str());
            }
            // "GFF-9"
            else if (this->bedType == 9) {
                printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end,
                    bed.score.c_str(), bed.strand.c_str(),
                    bed.fields[bed.other_idxs[1]].c_str(), 
                    bed.fields[bed.other_idxs[2]].c_str());
            }
        }
    }



    /*
        reportBedRangeTab

        Writes a custom start->end for a BED entry
        with a TAB at the end of the line.

        Works for BED3 - BED6.
    */
    template <typename T>
    inline void reportBedRangeNewLine(const T &bed, CHRPOS start, CHRPOS end) {
        
        // if it is azeroLength feature, we need to
        // correct the start and end coords to what they were
        // in the original file
        if (bed.zeroLength) {
            start = bed.start + 1;
            end   = bed.end - 1;
        }
        // BED
        if (_isGff == false && _isVcf == false) {
            if (this->bedType == 3) {
                printf ("%s\t%d\t%d\n", bed.chrom.c_str(), start, end);
            }
            else if (this->bedType == 4) {
                printf ("%s\t%d\t%d\t%s\n", 
                    bed.chrom.c_str(), start, end, bed.name.c_str());
            }
            else if (this->bedType == 5) {
                printf ("%s\t%d\t%d\t%s\t%s\n", 
                    bed.chrom.c_str(), start, end, 
                    bed.name.c_str(), bed.score.c_str());
            }
            else if (this->bedType == 6) {
                printf ("%s\t%d\t%d\t%s\t%s\t%s\n", 
                    bed.chrom.c_str(), start, end, bed.name.c_str(),
                    bed.score.c_str(), bed.strand.c_str());
            }
            else if (this->bedType > 6) {
                printf ("%s\t%d\t%d\t%s\t%s\t%s", 
                    bed.chrom.c_str(), start, end, bed.name.c_str(),
                    bed.score.c_str(), bed.strand.c_str());

                vector<uint16_t>::const_iterator 
                    othIt  = bed.other_idxs.begin();
                vector<uint16_t>::const_iterator 
                    othEnd = bed.other_idxs.end();
                for ( ; othIt != othEnd; ++othIt) {
                    printf("\t%s", bed.fields[*othIt].c_str());
                }
                printf("\n");
            }
        }
        // VCF
        else if (_isGff == false && _isVcf == true) {
            printf ("%s\t%d", bed.chrom.c_str(), bed.start+1);
            vector<uint16_t>::const_iterator othIt  = bed.other_idxs.begin();
            vector<uint16_t>::const_iterator othEnd = bed.other_idxs.end();
            for ( ; othIt != othEnd; ++othIt) {
                printf("\t%s", bed.fields[*othIt].c_str());
            }
            printf("\n");
        }
        // GFF
        else if (_isGff == true) {
            // "GFF-8"
            if (this->bedType == 8) {
                printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\n", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end,
                    bed.score.c_str(), bed.strand.c_str(),                                          bed.fields[bed.other_idxs[1]].c_str());
            }
            // "GFF-9"
            else if (this->bedType == 9) {
                printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", 
                    bed.chrom.c_str(), bed.fields[bed.other_idxs[0]].c_str(),
                    bed.name.c_str(), start+1, end,
                    bed.score.c_str(), bed.strand.c_str(),
                    bed.fields[bed.other_idxs[1]].c_str(), 
                    bed.fields[bed.other_idxs[2]].c_str());
            }
        }
    }


    /*
        reportNullBedTab
    */
    void reportNullBedTab() {

        if (_isGff == false && _isVcf == false) {
            if (this->bedType == 3) {
                printf (".\t-1\t-1\t");
            }
            else if (this->bedType == 4) {
                printf (".\t-1\t-1\t.\t");
            }
            else if (this->bedType == 5) {
                printf (".\t-1\t-1\t.\t-1\t");
            }
            else if (this->bedType == 6) {
                printf (".\t-1\t-1\t.\t-1\t.\t");
            }
            else if (this->bedType > 6) {
                printf (".\t-1\t-1\t.\t-1\t.\t");
                for (unsigned int i = 6; i < this->bedType; ++i) {
                    printf(".\t");
                }
            }
        }
        else if (_isGff == true && _isVcf == false) {
            if (this->bedType == 8) {
                printf (".\t.\t.\t-1\t-1\t-1\t.\t.\t");
            }
            else if (this->bedType == 9) {
                printf (".\t.\t.\t-1\t-1\t-1\t.\t.\t.\t");
            }
        }
    }


    /*
        reportNullBedTab
    */
    void reportNullBedNewLine() {

        if (_isGff == false && _isVcf == false) {
            if (this->bedType == 3) {
                printf (".\t-1\t-1\n");
            }
            else if (this->bedType == 4) {
                printf (".\t-1\t-1\t.\n");
            }
            else if (this->bedType == 5) {
                printf (".\t-1\t-1\t.\t-1\n");
            }
            else if (this->bedType == 6) {
                printf (".\t-1\t-1\t.\t-1\t.\n");
            }
            else if (this->bedType > 6) {
                printf (".\t-1\t-1\t.\t-1\t.");
                for (unsigned int i = 6; i < this->bedType; ++i) {
                    printf("\t.");
                }
                printf("\n");
            }
        }
        else if (_isGff == true && _isVcf == false) {
            if (this->bedType == 8) {
                printf (".\t.\t.\t-1\t-1\t-1\t.\t.\n");
            }
            else if (this->bedType == 9) {
                printf (".\t.\t.\t-1\t-1\t-1\t.\t.\t.\n");
            }
        }
    }


};

#endif /* BEDFILE_H */