1 // ***************************************************************************
2 // bamtools_count.cpp (c) 2010 Derek Barnett, Erik Garrison
3 // Marth Lab, Department of Biology, Boston College
4 // All rights reserved.
5 // ---------------------------------------------------------------------------
6 // Last modified: 3 September 2010
7 // ---------------------------------------------------------------------------
8 // Prints alignment count for BAM file(s)
9 // ***************************************************************************
15 #include "bamtools_count.h"
16 #include "bamtools_options.h"
17 #include "bamtools_utilities.h"
18 #include "BamReader.h"
19 #include "BamMultiReader.h"
22 using namespace BamTools;
24 // ---------------------------------------------
25 // CountSettings implementation
27 struct CountTool::CountSettings {
34 vector<string> InputFiles;
44 // ---------------------------------------------
45 // CountTool implementation
47 CountTool::CountTool(void)
49 , m_settings(new CountSettings)
51 // set program details
52 Options::SetProgramInfo("bamtools count", "prints number of alignments in BAM file(s)", "[-in <filename> -in <filename> ...] [-region <REGION>]");
55 OptionGroup* IO_Opts = Options::CreateOptionGroup("Input & Output");
56 Options::AddValueOption("-in", "BAM filename", "the input BAM file(s)", "", m_settings->HasInput, m_settings->InputFiles, IO_Opts, Options::StandardIn());
57 Options::AddValueOption("-region", "REGION", "genomic region. Index file is recommended for better performance, and is used automatically if it exists. See \'bamtools help index\' for more details on creating one", "", m_settings->HasRegion, m_settings->Region, IO_Opts);
60 CountTool::~CountTool(void) {
65 int CountTool::Help(void) {
66 Options::DisplayHelp();
70 int CountTool::Run(int argc, char* argv[]) {
72 // parse command line arguments
73 Options::Parse(argc, argv, 1);
75 // if no '-in' args supplied, default to stdin
76 if ( !m_settings->HasInput )
77 m_settings->InputFiles.push_back(Options::StandardIn());
79 // open reader without index
80 BamMultiReader reader;
81 if (!reader.Open(m_settings->InputFiles, false, true)) {
82 cerr << "ERROR: Could not open input BAM file(s)... Aborting." << endl;
88 int alignmentCount(0);
90 // if no region specified, count entire file
91 if ( !m_settings->HasRegion ) {
92 while ( reader.GetNextAlignmentCore(al) )
96 // otherwise attempt to use region as constraint
99 // if region string parses OK
101 if ( Utilities::ParseRegionString(m_settings->Region, reader, region) ) {
103 // attempt to re-open reader with index files
105 bool openedOK = reader.Open(m_settings->InputFiles, true, true );
109 cerr << "ERROR: Could not open input BAM file(s)... Aborting." << endl;
113 // if index data available, we can use SetRegion
114 if ( reader.IsIndexLoaded() ) {
116 // attempt to use SetRegion(), if failed report error
117 if ( !reader.SetRegion(region.LeftRefID, region.LeftPosition, region.RightRefID, region.RightPosition) ) {
118 cerr << "ERROR: Region requested, but could not set BamReader region to REGION: " << m_settings->Region << " Aborting." << endl;
123 // everything checks out, just iterate through specified region, counting alignments
124 while ( reader.GetNextAlignmentCore(al) )
128 // no index data available, we have to iterate through until we
129 // find overlapping alignments
131 while( reader.GetNextAlignmentCore(al) ) {
132 if ( (al.RefID >= region.LeftRefID) && ( (al.Position + al.Length) >= region.LeftPosition ) &&
133 (al.RefID <= region.RightRefID) && ( al.Position <= region.RightPosition) )
141 // error parsing REGION string
143 cerr << "ERROR: Could not parse REGION - " << m_settings->Region << endl;
144 cerr << "Be sure REGION is in valid format (see README) and that coordinates are valid for selected references" << endl;
151 cout << alignmentCount << endl;