This file is indexed.

/usr/include/vcflib/BedReader.h is in libvcflib-dev 1.0.0~rc1+dfsg1-3.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
#ifndef BEDREADER_H
#define BEDREADER_H

#include <iostream>
#include <fstream>
#include <string>
#include <vector>
#include <deque>
#include <map>
#include <iterator>
#include <algorithm>
#include "IntervalTree.h"
#include "split.h"

using namespace std;

string strip(string const& str, char const* separators = " \t") {
    string::size_type const first = str.find_first_not_of(separators);
    return (first == string::npos) ? string()
        : str.substr(first, str.find_last_not_of(separators) - first + 1);
}

void parseRegion(
    string& region,
    string& startSeq,
    int& startPos,
    int& stopPos) {

    size_t foundFirstColon = region.find(":");

    // we only have a single string, use the whole sequence as the target
    if (foundFirstColon == string::npos) {
        startSeq = region;
        startPos = 0;
        stopPos = -1;
    } else {
        startSeq = region.substr(0, foundFirstColon);
        string sep = "..";
        size_t foundRangeSep = region.find(sep, foundFirstColon);
        if (foundRangeSep == string::npos) {
            sep = "-";
            foundRangeSep = region.find("-", foundFirstColon);
        }
        if (foundRangeSep == string::npos) {
            startPos = atoi(region.substr(foundFirstColon + 1).c_str());
            // differ from bamtools in this regard, in that we process only
            // the specified position if a range isn't given
            stopPos = startPos + 1;
        } else {
            startPos = atoi(region.substr(foundFirstColon + 1, foundRangeSep - foundFirstColon).c_str());
            // if we have range sep specified, but no second number, read to the end of sequence
            if (foundRangeSep + sep.size() != region.size()) {
                stopPos = atoi(region.substr(foundRangeSep + sep.size()).c_str()); // end-exclusive, bed-format
            } else {
                //stopPos = reference.sequenceLength(startSeq);
                stopPos = -1;
            }
        }
    }
}

// stores the posiitional information of a bed target entry
class BedTarget {

public:

    string seq;  // sequence name
    int left;    // left position
    int right;   // right position, adjusted to 0-base
    string desc; // descriptive information, target name typically

    BedTarget(string s) {
        parseRegion(s, seq, left, right); 
    }

    BedTarget(string s, int l, int r, string d = "")
        : seq(s)
        , left(l)
        , right(r)
        , desc(d)
    { }

};


class BedReader {

    bool _isOpen;
    ifstream file;

public:

    bool isOpen(void) { return _isOpen; }

    vector<BedTarget> targets;
    map<string, IntervalTree<BedTarget*> > intervals; // intervals by reference sequence

    vector<BedTarget> entries(void) {

        vector<BedTarget> entries;

        if (!isOpen()) {
            cerr << "bed targets file is not open" << endl;
            exit(1);
        }

        string line;
        while (std::getline(file, line)) {
            vector<string> fields = split(line, " \t");
            BedTarget entry(strip(fields[0]),
                            atoi(strip(fields[1]).c_str()),
                            atoi(strip(fields[2]).c_str()),
                            (fields.size() >= 4) ? strip(fields[3]) : "");
            entries.push_back(entry);
        }

        return entries;

    }

    vector<BedTarget*> targetsContained(BedTarget& target) {
        vector<Interval<BedTarget*> > results;
        intervals[target.seq].findContained(target.left, target.right, results);
        vector<BedTarget*> contained;
        for (vector<Interval<BedTarget*> >::iterator r = results.begin(); r != results.end(); ++r) {
            contained.push_back(r->value);
        }
        return contained;
    }

    vector<BedTarget*> targetsOverlapping(BedTarget& target) {
        vector<Interval<BedTarget*> > results;
        intervals[target.seq].findOverlapping(target.left, target.right, results);
        vector<BedTarget*> overlapping;
        for (vector<Interval<BedTarget*> >::iterator r = results.begin(); r != results.end(); ++r) {
            overlapping.push_back(r->value);
        }
        return overlapping;
    }

BedReader(void)
	: _isOpen(false)
    { }

BedReader(string& fname)
	: _isOpen(false) {
        open(fname);
    }

    void addTargets(vector<BedTarget>& targets) {
        map<string, vector<Interval<BedTarget*> > > intervalsBySeq;
        for (vector<BedTarget>::iterator t = targets.begin(); t != targets.end(); ++t) {
            intervalsBySeq[t->seq].push_back(Interval<BedTarget*>(1 + t->left, t->right, &*t));
        }
        for (map<string, vector<Interval<BedTarget*> > >::iterator s = intervalsBySeq.begin(); s != intervalsBySeq.end(); ++s) {
            intervals[s->first] = IntervalTree<BedTarget*>(s->second);
        }
    }

    void open(const string& fname) {
        file.open(fname.c_str());
        _isOpen = true;
        targets = entries();
        map<string, vector<Interval<BedTarget*> > > intervalsBySeq;
        for (vector<BedTarget>::iterator t = targets.begin(); t != targets.end(); ++t) {
            intervalsBySeq[t->seq].push_back(Interval<BedTarget*>(1 + t->left, t->right, &*t));
        }
        for (map<string, vector<Interval<BedTarget*> > >::iterator s = intervalsBySeq.begin(); s != intervalsBySeq.end(); ++s) {
            intervals[s->first] = IntervalTree<BedTarget*>(s->second);
        }
    }

};

#endif