Fix #653 (#672)

* added checking for AbstractFeatureReader.BLOCK_COMPRESSED_EXTENSIONS in TribbleIndexedFeatureReader

* fixing WFIterator checking of compressed file

* isGZIPPath deprecation

* added test for new functionality

* fixing URL encoding

* added no-remote test file with spaces

src/main/java/htsjdk/tribble/TribbleIndexedFeatureReader.java

@@ -33,10 +33,12 @@
 import htsjdk.tribble.util.ParsingUtils;
 
 import java.io.BufferedInputStream;
+import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
 import java.net.URI;
 import java.net.URISyntaxException;
+import java.net.URLEncoder;
 import java.util.ArrayList;
 import java.util.Iterator;
 import java.util.List;
@@ -217,7 +219,7 @@ private void readHeader() throws IOException {
         PositionalBufferedStream pbs = null;
         try {
             is = ParsingUtils.openInputStream(path);
-            if (isGZIPPath(path)) {
+            if (hasBlockCompressedExtension(new URI(URLEncoder.encode(path, "UTF-8")))) {
                 // TODO -- warning I don't think this can work, the buffered input stream screws up position
                 is = new GZIPInputStream(new BufferedInputStream(is));
             }
@@ -273,7 +275,11 @@ private void readHeader() throws IOException {
         return new WFIterator();
     }
 
+    /**
+     * @deprecated use {@link #hasBlockCompressedExtension(String)} instead
+     */
     //Visible for testing
+    @Deprecated
     static boolean isGZIPPath(final String path) {
         if (path.toLowerCase().endsWith(".gz")) {
             return true;
@@ -310,7 +316,7 @@ public WFIterator() throws IOException {
             final InputStream inputStream = ParsingUtils.openInputStream(path);
 
             final PositionalBufferedStream pbs;
-            if (isGZIPPath(path)) {
+            if (hasBlockCompressedExtension(path)) {
                 // Gzipped -- we need to buffer the GZIPInputStream methods as this class makes read() calls,
                 // and seekableStream does not support single byte reads
                 final InputStream is = new GZIPInputStream(new BufferedInputStream(inputStream, 512000));

src/test/java/htsjdk/tribble/TribbleIndexFeatureReaderTest.java

@@ -64,7 +64,9 @@ public void testGZExtension(final String testString, final boolean expected) thr
     public Object[][] createFeatureFileStrings() {
         return new Object[][]{
                 {TestUtils.DATA_DIR + "test.vcf", 5},
-                {TestUtils.DATA_DIR + "test.vcf.gz", 5}
+                {TestUtils.DATA_DIR + "test.vcf.gz", 5},
+                {TestUtils.DATA_DIR + "test.vcf.bgz", 5},
+                {TestUtils.DATA_DIR + "test with spaces.vcf", 5}
         };
     }
 

src/test/resources/htsjdk/tribble/test with spaces.vcf

@@ -0,0 +1,24 @@
+##fileformat=VCFv4.1
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=file:///seq/references/1000GenomesPilot-NCBI36.fasta
+##contig=<ID=20,length=62435964,assembly=B36,md5=f126cdf8a6e0c7f379d618ff66beb2da,species="Homo sapiens",taxonomy=x>
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+20	14370	rs6054257	G	A	29	PASS	NS=3;DP=14;AF=0.5;DB;H2	GT:GQ:DP:HQ	0|0:48:1:51,51	1|0:48:8:51,51	1/1:43:5:.,.
+20	17330	.	T	A	3	q10	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|0:49:3:58,50	0|1:3:5:65,3	0/0:41:3
+20	1110696	rs6040355	A	G,T	67	PASS	NS=2;DP=10;AF=0.333,0.667;AA=T;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2|1:2:0:18,2	2/2:35:4
+20	1230237	.	T	.	47	PASS	NS=3;DP=13;AA=T	GT:GQ:DP:HQ	0|0:54:7:56,60	0|0:48:4:51,51	0/0:61:2
+20	1234567	microsat1	GTC	G,GTCT	50	PASS	NS=3;DP=9;AA=G	GT:GQ:DP	0/1:35:4	0/2:17:2	1/1:40:3