Add additional errors when passed zipped VCFs, add PRECISE/IMPRECISE …

…flags to header

README.md

@@ -8,7 +8,7 @@
 
 JASMINE: Jointly Accurate Sv Merging with Intersample Network Edges
 
-Version 1.1.1
+Version 1.1.2
 
 This tool is used to merge structural variants (SVs) across samples.  Each sample has a number of SV calls, consisting of position information (chromosome, start, end, length), type and strand information, and a number of other values.  Jasmine represents the set of all SVs across samples as a network, and uses a modified minimum spanning forest algorithm to determine the best way of merging the variants such that each merged variants represents a set of analogous variants occurring in different samples.
 

src/Settings.java

@@ -78,12 +78,12 @@ public class Settings {
 	static void usage()
 	{
 		System.out.println();
-		System.out.println("Jasmine version 1.1.1");
+		System.out.println("Jasmine version 1.1.2");
 		System.out.println("Usage: jasmine [args]");
 		System.out.println("  Example: jasmine file_list=filelist.txt out_file=out.vcf");
 		System.out.println();
 		System.out.println("Required args:");
-		System.out.println("  file_list (String) - a file listing paths to all variant files to use (on separate lines)");
+		System.out.println("  file_list (String) - a file listing paths to unzipped VCF files to merge (on separate lines)");
 		System.out.println("  out_file  (String) - the name of the file to output the merged variants to");
 		System.out.println();
 		System.out.println("Optional args:");

src/VariantInput.java

@@ -60,6 +60,10 @@ public static TreeMap<String, ArrayList<Variant>> readAllFiles(String fileList)
 	 */
 	private static TreeMap<String, ArrayList<Variant>> getSingleList(String filename, int sample) throws Exception
 	{
+		if(filename.endsWith(".gz"))
+		{
+			System.err.println("Warning: " + filename + " ends with .gz, but (b)gzipped VCFs are not accepted");
+		}
 		Scanner input = new Scanner(new FileInputStream(new File(filename)));
 		ArrayList<Variant> allVariants = new ArrayList<Variant>();
 		HashSet<String> ids = new HashSet<String>();
@@ -74,6 +78,10 @@ private static TreeMap<String, ArrayList<Variant>> getSingleList(String filename
 			{
 				continue;
 			}
+			if(line.length() >=2 && line.charAt(0) == 31 && (line.charAt(1) == 65533 || line.charAt(1) == 139))
+			{
+				throw new Exception(filename + " is a gzipped file, but only unzipped VCFs are accepted");
+			}
 			VcfEntry entry = VcfEntry.fromLine(line);
 			if(!previouslyMergedSamples.containsKey(sample))
 			{

src/VariantOutput.java

@@ -93,6 +93,9 @@ else if(line.startsWith("#"))
 						header.addInfoField("AVG_LEN", "1", "String", "Average length for variants merged into this one");
 						header.addInfoField("END", "1", "String", "The end position of the variant");
 						header.addInfoField("SVLEN", "1", "String", "The length (in bp) of the variant");
+						header.addInfoField("PRECISE", "0", "Flag", "Precise structural variation");
+						header.addInfoField("IMPRECISE", "0", "Flag", "Imprecise structural variation");
+
 						if(Settings.ALLOW_INTRASAMPLE)
 						{
 							header.addInfoField("ALLVARS_EXT", ".", "String", "A comma-separated of all variants supporting this call");

src/VcfEntry.java

@@ -46,6 +46,10 @@ public VcfEntry(String line) throws Exception
 	{
 		originalLine = line;
 		tabTokens = line.split("\t");
+		if(line.length() >=2 && line.charAt(0) == 31 && (line.charAt(1) == 65533 || line.charAt(1) == 139))
+		{
+			throw new Exception("Trying to read a gzipped file, but only unzipped VCFs are accepted");
+		}
 		if(tabTokens.length < 8)
 		{
 			throw new Exception("VCF line had too few entries: "