Support tabix index for collections

src/main/java/genepi/riskscore/io/csv/TabixTableReader.java

@@ -0,0 +1,114 @@
+package genepi.riskscore.io.csv;
+
+import genepi.io.FileUtil;
+import genepi.io.table.reader.AbstractTableReader;
+import genepi.io.table.reader.CsvTableReader;
+import genepi.io.text.LineReader;
+import genepi.riskscore.io.dbsnp.DbSnpReader;
+import htsjdk.tribble.readers.TabixReader;
+
+import java.io.DataInputStream;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Vector;
+
+public class TabixTableReader extends AbstractTableReader  {
+
+	private List<String> headerLines = new Vector<String>();
+
+	private String[] columns = null;
+
+	private Map<String, Integer> index = new HashMap<String, Integer>();
+
+	private String[] row = null;
+
+	private TabixReader tabixReader;
+
+	private TabixReader.Iterator iterator;
+
+	private int lineNumber = 0;
+
+	public TabixTableReader(String filename, String chromosome) throws IOException {
+		this(filename, chromosome, 0, Integer.MAX_VALUE);
+	}
+
+
+	public TabixTableReader(String filename, String chromosome, int start, int end) throws IOException {
+		LineReader reader = new LineReader(openTxtOrGzipStream(filename));
+		while(reader.next()) {
+			if (reader.get().startsWith("#")) {
+				headerLines.add(reader.get());
+			} else{
+				columns = reader.get().split("\t");
+				for (int i = 0 ; i < columns.length; i++){
+					index.put(columns[i], i);
+				}
+				break;
+			}
+		}
+		reader.close();
+
+		tabixReader = new TabixReader(filename);
+		iterator = tabixReader.query(chromosome, start, end);
+	}
+
+	public List<String> getHeader() {
+		return headerLines;
+	}
+
+	@Override
+	public String[] getColumns() {
+		return columns;
+	}
+
+	@Override
+	public boolean next() {
+		String line = null;
+		try {
+			line = iterator.next();
+		} catch (IOException e) {
+			throw new RuntimeException(e);
+		}
+		if (line == null) {
+			row = null;
+			return false;
+		}
+		row = line.split("\t", -1);
+		lineNumber++;
+		if (row.length != columns.length){
+			throw new RuntimeException("Different number of columns in line " + lineNumber + ": " + line);
+		}
+		return true;
+	}
+
+	@Override
+	public int getColumnIndex(String column) {
+		return index.get(column);
+	}
+
+	@Override
+	public String[] getRow() {
+		return row;
+	}
+
+	@Override
+	public void close() {
+		tabixReader.close();
+	}
+
+	@Override
+	public boolean hasColumn(String column) {
+		return index.containsKey(column);
+	}
+
+	private static DataInputStream openTxtOrGzipStream(String filename) throws IOException {
+		FileInputStream inputStream = new FileInputStream(filename);
+		InputStream in2 = FileUtil.decompressStream(inputStream);
+		return new DataInputStream(in2);
+	}
+
+}

src/main/java/genepi/riskscore/io/scores/MergedRiskScoreCollection.java

@@ -1,9 +1,11 @@
 package genepi.riskscore.io.scores;
 
+import genepi.io.table.reader.ITableReader;
 import genepi.riskscore.io.Chunk;
 import genepi.riskscore.io.RiskScoreFile;
 import genepi.riskscore.io.VariantFile;
 import genepi.riskscore.io.csv.CsvWithHeaderTableReader;
+import genepi.riskscore.io.csv.TabixTableReader;
 import genepi.riskscore.io.formats.RiskScoreFormatFactory.RiskScoreFormat;
 import genepi.riskscore.model.ReferenceVariant;
 import genepi.riskscore.model.RiskScoreSummary;
@@ -34,6 +36,8 @@ public class MergedRiskScoreCollection implements IRiskScoreCollection {
 
 	public static String META_EXTENSION = ".info";
 
+	public static String INDEX_EXTENSION = ".tbi";
+
 	public static  String COLUMN_CHROMOSOME = "chr_name";
 
 	public static  String COLUMN_POSITION = "chr_position";
@@ -88,8 +92,10 @@ public void buildIndex(String chromosome, Chunk chunk, String dbsnp, String prox
 		}
 		readerMeta.close();
 
-
-		CsvWithHeaderTableReader reader = new CsvWithHeaderTableReader(filename, '\t');
+		if (chunk == null){
+			chunk = new Chunk();
+		}
+		TabixTableReader reader = new TabixTableReader(filename, chromosome, chunk.getStart(), chunk.getEnd());
 		String[] columns = reader.getColumns();
 
 		numberRiskScores = columns.length - COLUMNS.size();
@@ -114,19 +120,6 @@ public void buildIndex(String chromosome, Chunk chunk, String dbsnp, String prox
 
 			String _chromosome = reader.getString(COLUMN_CHROMOSOME);
 			int position = reader.getInteger(COLUMN_POSITION);
-			if (!_chromosome.equals(chromosome)){
-				continue;
-			}
-			if (chunk != null) {
-				if (position < chunk.getStart()) {
-					continue;
-				}
-
-				if (position > chunk.getEnd()) {
-					break;
-				}
-			}
-
 			String otherAllele = reader.getString(COLUMN_OTHER_ALLELE);
 			String effectAllele = reader.getString(COLUMN_EFFECT_ALLELE);