Merge pull request #57 from 4dn-dcic/0.3.6

0.3.6
4dn-dcic · Apr 30, 2018 · 07bcab0 · 07bcab0
2 parents e32ff38 + dfd49e2
commit 07bcab0
Show file tree

Hide file tree

Showing 56 changed files with 746 additions and 32 deletions.
diff --git a/.travis.yml b/.travis.yml
@@ -14,8 +14,10 @@ matrix:
       - sudo python setup.py install
       - python test/test.py
       - python test/test_oldindex.py
+      - python test/test_oldindex2.py
       - source test/test_c.sh  # valgrind test is applied when VALGRIND_TEST_ON=1
       - source test/test_c_oldindex.sh  # test for old index
+      - source test/test_c_oldindex2.sh  # test for old index
     - language: c
       sudo: required
       compiler: gcc

diff --git a/README.md b/README.md
@@ -639,6 +639,9 @@ ulimit -n 2000
 
 ## Version history
 
+### 0.3.6
+* Line count (`pairix -n`) integer overflow issue has been fixed. The index structure has changed. The index generated by the previous versions (0.2.5~0.3.3, 0.3.4~0.3.5) can be auto-detected and used as well (backward compatible).
+
 ### 0.3.5
 * Backward compatibility is added - The index generated by the previous version (0.2.5 ~ 0.3.3) can now be auto-detected and used by Pairix.
 

diff --git a/VERSION.txt b/VERSION.txt
@@ -1 +1 @@
-0.3.5
+0.3.6
diff --git a/samples/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz.px2 b/samples/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz.px2
diff --git a/samples/4dn.bsorted.chr21_22_only.pairs.gz.px2 b/samples/4dn.bsorted.chr21_22_only.pairs.gz.px2
diff --git a/samples/SRR1171591.variants.snp.vqsr.p.vcf.gz.px2 b/samples/SRR1171591.variants.snp.vqsr.p.vcf.gz.px2
diff --git a/samples/merged_nodup.tab.chrblock_sorted.txt.gz.px2 b/samples/merged_nodup.tab.chrblock_sorted.txt.gz.px2
diff --git a/samples/merged_nodups.space.chrblock_sorted.subsample1.txt.gz.px2 b/samples/merged_nodups.space.chrblock_sorted.subsample1.txt.gz.px2
diff --git a/samples/merged_nodups.space.chrblock_sorted.subsample2.txt.gz.px2 b/samples/merged_nodups.space.chrblock_sorted.subsample2.txt.gz.px2
diff --git a/samples/merged_nodups.space.chrblock_sorted.subsample3.bsorted.ff.pairs.gz.px2 b/samples/merged_nodups.space.chrblock_sorted.subsample3.bsorted.ff.pairs.gz.px2
diff --git a/samples/merged_nodups.space.chrblock_sorted.subsample3.bsorted.nofrag.pairs.gz.px2 b/samples/merged_nodups.space.chrblock_sorted.subsample3.bsorted.nofrag.pairs.gz.px2
diff --git a/samples/merged_nodups.space.chrblock_sorted.subsample3.bsorted.pairs.gz.px2 b/samples/merged_nodups.space.chrblock_sorted.subsample3.bsorted.pairs.gz.px2
diff --git a/samples/merged_nodups.space.chrblock_sorted.subsample3.txt.gz.px2 b/samples/merged_nodups.space.chrblock_sorted.subsample3.txt.gz.px2
diff --git a/samples/mock.largechr.pairs.gz.px2 b/samples/mock.largechr.pairs.gz.px2
diff --git a/samples/old_index/SRR1171591.variants.snp.vqsr.p.vcf.gz.px2 b/samples/old_index/SRR1171591.variants.snp.vqsr.p.vcf.gz.px2
diff --git a/samples/old_index/merged_nodup.tab.chrblock_sorted.txt.gz.px2 b/samples/old_index/merged_nodup.tab.chrblock_sorted.txt.gz.px2
diff --git a/samples/old_index/merged_nodups.space.chrblock_sorted.subsample1.txt.gz.px2 b/samples/old_index/merged_nodups.space.chrblock_sorted.subsample1.txt.gz.px2
diff --git a/samples/old_index/merged_nodups.space.chrblock_sorted.subsample2.txt.gz.px2 b/samples/old_index/merged_nodups.space.chrblock_sorted.subsample2.txt.gz.px2
diff --git a/samples/old_index/test_4dn.pairs.gz.px2 b/samples/old_index/test_4dn.pairs.gz.px2
diff --git a/samples/old_index/test_juicer_shortform.bsorted.pairs.gz.px2 b/samples/old_index/test_juicer_shortform.bsorted.pairs.gz.px2
diff --git a/samples/old_index/test_merged_nodups.bsorted.pairs.gz.px2 b/samples/old_index/test_merged_nodups.bsorted.pairs.gz.px2
diff --git a/samples/old_index/test_merged_nodups.txt.bsorted.gz.px2 b/samples/old_index/test_merged_nodups.txt.bsorted.gz.px2
diff --git a/samples/old_index/test_old_merged_nodups.bsorted.pairs.gz.px2 b/samples/old_index/test_old_merged_nodups.bsorted.pairs.gz.px2
diff --git a/samples/old_index/test_old_merged_nodups.txt.bsorted.gz.px2 b/samples/old_index/test_old_merged_nodups.txt.bsorted.gz.px2
diff --git a/samples/old_index2/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz b/samples/old_index2/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz
diff --git a/samples/old_index2/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz.px2 b/samples/old_index2/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz.px2
diff --git a/samples/old_index2/4dn.bsorted.chr21_22_only.pairs.gz b/samples/old_index2/4dn.bsorted.chr21_22_only.pairs.gz
diff --git a/samples/old_index2/4dn.bsorted.chr21_22_only.pairs.gz.px2 b/samples/old_index2/4dn.bsorted.chr21_22_only.pairs.gz.px2
diff --git a/samples/old_index2/SRR1171591.variants.snp.vqsr.p.vcf.gz b/samples/old_index2/SRR1171591.variants.snp.vqsr.p.vcf.gz
diff --git a/samples/old_index2/SRR1171591.variants.snp.vqsr.p.vcf.gz.px2 b/samples/old_index2/SRR1171591.variants.snp.vqsr.p.vcf.gz.px2
diff --git a/samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz b/samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz
diff --git a/samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz.px2 b/samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz.px2
diff --git a/samples/old_index2/merged_nodups.space.chrblock_sorted.subsample1.txt.gz b/samples/old_index2/merged_nodups.space.chrblock_sorted.subsample1.txt.gz
diff --git a/samples/old_index2/merged_nodups.space.chrblock_sorted.subsample1.txt.gz.px2 b/samples/old_index2/merged_nodups.space.chrblock_sorted.subsample1.txt.gz.px2
diff --git a/samples/old_index2/mock.largechr.pairs.gz b/samples/old_index2/mock.largechr.pairs.gz
diff --git a/samples/old_index2/mock.largechr.pairs.gz.px2 b/samples/old_index2/mock.largechr.pairs.gz.px2
diff --git a/samples/old_index2/test_4dn.pairs.gz b/samples/old_index2/test_4dn.pairs.gz
diff --git a/samples/old_index2/test_4dn.pairs.gz.px2 b/samples/old_index2/test_4dn.pairs.gz.px2
diff --git a/samples/test_4dn.pairs.gz.px2 b/samples/test_4dn.pairs.gz.px2
diff --git a/samples/test_4dn_2.bsorted.pairs.gz.px2 b/samples/test_4dn_2.bsorted.pairs.gz.px2
diff --git a/samples/test_juicer_shortform.bsorted.pairs.gz.px2 b/samples/test_juicer_shortform.bsorted.pairs.gz.px2
diff --git a/samples/test_merged_nodups.bsorted.pairs.gz.px2 b/samples/test_merged_nodups.bsorted.pairs.gz.px2
diff --git a/samples/test_merged_nodups.txt.bsorted.gz.px2 b/samples/test_merged_nodups.txt.bsorted.gz.px2
diff --git a/samples/test_old_merged_nodups.bsorted.pairs.gz.px2 b/samples/test_old_merged_nodups.bsorted.pairs.gz.px2
diff --git a/samples/test_old_merged_nodups.txt.bsorted.gz.px2 b/samples/test_old_merged_nodups.txt.bsorted.gz.px2
diff --git a/src/index.c b/src/index.c
@@ -26,7 +26,8 @@
 int TAD_LIDX_SHIFT = TAD_LIDX_SHIFT_LARGE_CHR;
 int MAX_CHR = MAX_CHR_LARGE_CHR;
 
-#define MAGIC_NUMBER "PX2.003\1"
+#define MAGIC_NUMBER "PX2.004\1"
+#define OLD_MAGIC_NUMBER2 "PX2.003\1"  // magic number for older version of pairix (0.3.4 - 0.3.5)
 #define OLD_MAGIC_NUMBER "PX2.002\1"  // magic number for older version of pairix (up to 0.3.3)
 
 
@@ -56,7 +57,7 @@ struct __ti_index_t {
         khash_t(s) *tname;
         khash_t(i) **index;
         ti_lidx_t *index2;
-        int linecount;
+        uint64_t linecount;
 };
 
 struct __ti_iter_t {
@@ -490,9 +491,9 @@ void ti_index_save(const ti_index_t *idx, BGZF *fp)
 		bgzf_write(fp, bam_swap_endian_4p(&x), 4);
 	} else bgzf_write(fp, &idx->n, 4);
 	if (ti_is_be) {
-		uint32_t x = idx->linecount;
-		bgzf_write(fp, bam_swap_endian_4p(&x), 4);
-	} else bgzf_write(fp, &idx->linecount, 4);
+		uint64_t x = idx->linecount;
+		bgzf_write(fp, bam_swap_endian_8p(&x), 8);
+	} else bgzf_write(fp, &idx->linecount, 8);
 	assert(sizeof(ti_conf_t) == 40);
 	if (ti_is_be) { // write ti_conf_t;
 		uint32_t x[6];
@@ -574,19 +575,28 @@ static ti_index_t *ti_index_load_core(BGZF *fp)
 	}
 	bgzf_read(fp, magic, 8);
 	if (strncmp(magic, MAGIC_NUMBER, 8)) {
-            if (strncmp(magic, OLD_MAGIC_NUMBER, 8)) {
-		fprintf(stderr, "[ti_index_load] wrong magic number. Re-index if your index file was created by an earlier version of pairix.\n");
-		return 0;
-            } else {
+            if (strncmp(magic, OLD_MAGIC_NUMBER, 8)==0) {
                 TAD_LIDX_SHIFT = TAD_LIDX_SHIFT_ORIGINAL;
                 MAX_CHR = MAX_CHR_ORIGINAL; 
             }
+            else if(strncmp(magic, OLD_MAGIC_NUMBER2, 8)==0) {
+            }
+            else {
+		fprintf(stderr, "[ti_index_load] wrong magic number. Re-index if your index file was created by an earlier version of pairix.\n");
+		return 0;
+            }
 	}
 	idx = (ti_index_t*)calloc(1, sizeof(ti_index_t));
 	bgzf_read(fp, &idx->n, 4);
 	if (ti_is_be) bam_swap_endian_4p(&idx->n);
-	bgzf_read(fp, &idx->linecount, 4);
-	if (ti_is_be) bam_swap_endian_4p(&idx->linecount);
+        if(strncmp(magic, MAGIC_NUMBER, 8)==0) {
+      	    bgzf_read(fp, &idx->linecount, 8);
+	    if (ti_is_be) bam_swap_endian_8p(&idx->linecount);
+        }
+        else if(strncmp(magic, OLD_MAGIC_NUMBER2, 8)==0 || strncmp(magic, OLD_MAGIC_NUMBER, 8)==0) {
+            bgzf_read(fp, &idx->linecount, 4);
+            if (ti_is_be) bam_swap_endian_4p(&idx->linecount);
+        }
 	idx->tname = kh_init(s);
 	idx->index = (khash_t(i)**)calloc(idx->n, sizeof(void*));
 	idx->index2 = (ti_lidx_t*)calloc(idx->n, sizeof(ti_lidx_t));
@@ -845,9 +855,10 @@ int ti_parse_region(const ti_index_t *idx, const char *str, int *tid, int *begin
 // if 1d, begin2 and end2 will have value -1.
 // query string error: -1
 // region_split_character not matching error: -2
+// memory allocation error: -3
 int ti_parse_region2d(const ti_index_t *idx, const char *str, int *tid, int *begin, int *end, int *begin2, int *end2)
 {
-	char *s, *p, *sname;
+	char *s, *p, *sname, *tmp_s;
 	int i, l, k, h;
         int coord1s, coord1e, coord2s, coord2e, pos1s, pos2s;
         char region_split_character = ti_get_region_split_character(idx);
@@ -872,7 +883,9 @@ int ti_parse_region2d(const ti_index_t *idx, const char *str, int *tid, int *beg
           free(s); return (res);
         }
         if(i == k && dim == 2) { //1d query on 2d data : interprete query 'x' as 'x|x'
-          s = (char*)realloc(s, k*2+2);
+          tmp_s = (char*)realloc(s, k*2+2);
+          if(tmp_s) s = tmp_s;
+          else return(-3);  // memory alloc error
           strcpy(s+i+1, s);
           s[i] = region_split_character;
           k = k*2+1;
@@ -975,7 +988,7 @@ ti_iter_t ti_iter_first()
 }
 
 
-int get_linecount(const ti_index_t *idx)
+uint64_t get_linecount(const ti_index_t *idx)
 {
         return(idx->linecount);
 }

diff --git a/src/main.c b/src/main.c
@@ -5,6 +5,7 @@
 #include <sys/stat.h>
 #include <errno.h>
 #include <getopt.h>
+#include <inttypes.h>
 #include "bgzf.h"
 #include "pairix.h"
 #include "knetfile.h"
@@ -220,8 +221,7 @@ int main(int argc, char *argv[])
             fprintf(stderr, "[main] fail to load the index file.\n");
             return 1;
         }
-        int linecount = get_linecount(idx);
-        printf("%d\n", linecount);
+        printf("%"PRIu64"\n", get_linecount(idx));
         ti_index_destroy(idx);
         return 0;
     }

diff --git a/src/pairix.h b/src/pairix.h
@@ -28,7 +28,7 @@
 #ifndef __TABIDX_H
 #define __TABIDX_H
 
-#define PACKAGE_VERSION "0.3.5"
+#define PACKAGE_VERSION "0.3.6"
 
 #include <stdint.h>
 #include "kstring.h"
@@ -151,7 +151,7 @@ extern "C" {
 	const char **ti_seqname(const ti_index_t *idx, int *n);
 
         /* get linecount */
-        int get_linecount(const ti_index_t *idx);
+        uint64_t get_linecount(const ti_index_t *idx);
 
         /* get file offset
          * returns number of bgzf blocks spanning a sequence (pair) */

diff --git a/test/test.py b/test/test.py
@@ -253,10 +253,10 @@ def test_querys_2_bad_order(self):
         with warnings.catch_warnings(record=True) as w:
             warnings.simplefilter("always")
             # trigger a warning
-            it = self.pr.querys2D(query)
+            self.pr.querys2D(query)
             # verify some things about the warning
-            assert len(w) == 1
-            assert issubclass(w[-1].category, pypairix.PairixWarning)
+            self.assertEqual(len(w), 1)
+            self.assertTrue(issubclass(w[-1].category, pypairix.PairixWarning))
 
     def test_build_index_with_force_merged_nodups_tab(self):  ## recognizing custom set
         pypairix.build_index(TEST_FILE_2D, sc=2, bc=3, ec=3, sc2=6, bc2=7, ec2=7, force=1)
@@ -300,10 +300,10 @@ def test_query2_rev_fail(self):
         with warnings.catch_warnings(record=True) as w:
             warnings.simplefilter("always")
             # trigger a warning
-            it = self.pr.query2D(self.chrom, self.start, self.end, self.chrom2, self.start2, self.end2)
+            self.pr.query2D(self.chrom, self.start, self.end, self.chrom2, self.start2, self.end2)
             # verify some things about the warning
-            assert len(w) == 1
-            assert issubclass(w[-1].category, pypairix.PairixWarning)
+            self.assertEqual(len(w), 1)
+            self.assertTrue(issubclass(w[-1].category, pypairix.PairixWarning))
 
 
 ## 2D query on 2D indexed file with chromosomes using a 4DN pairs file

diff --git a/test/test_c.sh b/test/test_c.sh
@@ -1,3 +1,5 @@
+#!/bin/bash
+
 PATH=./bin:$PATH
 
 if [ $VALGRIND_TEST_ON -eq 1 ]; then

diff --git a/test/test_c_oldindex.sh b/test/test_c_oldindex.sh
@@ -1,3 +1,5 @@
+#!/bin/bash
+
 PATH=./bin:$PATH
 
 if [ $VALGRIND_TEST_ON -eq 1 ]; then

diff --git a/test/test_c_oldindex2.sh b/test/test_c_oldindex2.sh
@@ -0,0 +1,172 @@
+#!/bin/bash
+
+PATH=./bin:$PATH
+
+if [ $VALGRIND_TEST_ON -eq 1 ]; then
+  VALGRIND="valgrind --error-exitcode=42 --leak-check=full"
+else
+  VALGRIND=""
+fi
+
+## 2D
+echo "test 1"
+$VALGRIND pairix samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz '10:1-1000000|20' > log1
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="10" && $3>=1 && $3<=1000000 && $6=="20"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 1 failed"
+  return 1;
+fi
+
+echo "test 1b"
+$VALGRIND pairix -a samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz '10:1-1000000|20' > log1
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="10" && $3>=1 && $3<=1000000 && $6=="20"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 1b failed"
+  return 1;
+fi
+
+echo "test 1c"
+$VALGRIND pairix -a samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz '20|10:1-1000000' > log1
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="10" && $3>=1 && $3<=1000000 && $6=="20"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 1c failed"
+  return 1;
+fi
+
+echo "test 1d"
+$VALGRIND pairix samples/old_index2/test_4dn.pairs.gz 'chr22:50000000-60000000' > log1
+$VALGRIND pairix samples/old_index2/test_4dn.pairs.gz 'chr22:50000000-60000000|chr22:50000000-60000000' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 1d failed"
+  return 1;
+fi
+
+echo "test 1e"
+$VALGRIND pairix samples/old_index2/test_4dn.pairs.gz 'chrY:1-2000000' > log1
+$VALGRIND pairix samples/old_index2/test_4dn.pairs.gz 'chrY:1-2000000|chrY:1-2000000' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 1e failed"
+  return 1;
+fi
+
+echo "test 2"
+$VALGRIND pairix samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz '10:1-1000000|20:50000000-60000000' > log1
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="10" && $3>=1 && $3<=1000000 && $6=="20" && $7>=50000000 && $7<=60000000' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 2 failed"
+  return 1;
+fi
+
+echo "test 3"
+$VALGRIND pairix samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz '1:1-10000000|20:50000000-60000000' '3:5000000-9000000|X:70000000-90000000' > log1
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="1" && $3>=1 && $3<=10000000 && $6=="20" && $7>=50000000 && $7<=60000000' > log2
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="3" && $3>=5000000 && $3<=9000000 && $6=="X" && $7>=70000000 && $7<=90000000' >> log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 3 failed"
+  return 1;
+fi
+
+echo "test 4"
+$VALGRIND pairix samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz '*|1:0-100000' > log1
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$6=="1" && $7>=0 && $7<=100000' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 4 failed"
+  return 1;
+fi
+
+echo "test 5"
+$VALGRIND pairix samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz '1:0-100000|*' > log1
+gunzip -c samples/old_index2/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="1" && $3>=0 && $3<=100000' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 5 failed"
+  return 1;
+fi
+
+
+## 1D
+echo "test 6"
+$VALGRIND pairix samples/old_index2/SRR1171591.variants.snp.vqsr.p.vcf.gz chr10:1-4000000 > log1
+gunzip -c samples/old_index2/SRR1171591.variants.snp.vqsr.p.vcf.gz | awk '$1=="chr10" && $2>=1 && $2<=4000000' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 6 failed"
+  return 1;
+fi
+
+
+## 2D, space-delimited
+echo "test 7"
+$VALGRIND pairix samples/old_index2/merged_nodups.space.chrblock_sorted.subsample1.txt.gz '10:1-1000000|20' > log1
+gunzip -c samples/old_index2/merged_nodups.space.chrblock_sorted.subsample1.txt.gz | awk '$2=="10" && $3>=1 && $3<=1000000 && $6=="20"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 7 failed"
+  return 1;
+fi
+
+
+## preset for pairs.gz
+echo "test 8"
+$VALGRIND pairix samples/old_index2/test_4dn.pairs.gz 'chr10|chr20' > log1
+gunzip -c samples/old_index2/test_4dn.pairs.gz | awk '$2=="chr10" && $4=="chr20"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 8 failed"
+  return 1;
+fi
+
+## linecount
+echo "test linecount"
+$VALGRIND pairix -n samples/old_index2/test_4dn.pairs.gz > log1
+gunzip -c samples/old_index2/test_4dn.pairs.gz |wc -l | sed "s/ //g" > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "linecount test failed"
+  return 1;
+fi
+
+
+## bgzf block count (currently no auto test for the accuracy of the result)
+echo "test bgzf block count"
+$VALGRIND pairix -B samples/old_index2/test_4dn.pairs.gz
+
+## check triangle
+echo "test check triangle"
+$VALGRIND pairix -Y samples/old_index2/4dn.bsorted.chr21_22_only.pairs.gz
+$VALGRIND pairix -Y samples/old_index2/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz
+res=$(pairix -Y samples/old_index2/4dn.bsorted.chr21_22_only.nontriangle.pairs.gz)
+if [ "$res" != "The file is not a triangle." ]; then
+  echo "test check triangle failed"
+  return 1;
+fi
+
+echo "test check triangle #2"
+res=$(pairix -Y samples/old_index2/4dn.bsorted.chr21_22_only.pairs.gz)
+if [ "$res" != "The file is a triangle." ]; then
+  echo "test check triangle #2 failed"
+  return 1;
+fi
+
+
+# test large chromosome
+echo "test large chr"
+$VALGRIND pairix samples/old_index2/mock.largechr.pairs.gz 'chr21:800000000-900000000|chr22' > log1
+gunzip -c  samples/old_index2/mock.largechr.pairs.gz | awk '$2=="chr21" && $3>800000000 && $3<900000000 && $4=="chr22"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test large chromosome failed"
+  return 1;
+fi
+
+# test large chromosome
+echo "test large chr2"
+$VALGRIND pairix samples/old_index2/mock.largechr.pairs.gz 'chr22:800000000-997027270|chr22' > log1
+gunzip -c samples/old_index2/mock.largechr.pairs.gz | awk '$2=="chr22" && $3>=800000000 && $3<=997027270  && $4=="chr22"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test large chromosome2 failed"
+  return 1;
+fi
+
+# test large chromosome
+echo "test large chr3"
+$VALGRIND pairix samples/old_index2/mock.largechr.pairs.gz 'chr22:1073741820-1073741824|chr22' > log1
+gunzip -c samples/old_index2/mock.largechr.pairs.gz | awk '$2=="chr22" && $3>=1073741820 && $3<=1073741824 && $4=="chr22"' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test large chromosome3 failed"
+  return 1;
+fi
diff --git a/test/test_oldindex.py b/test/test_oldindex.py
@@ -245,10 +245,10 @@ def test_querys_2_bad_order(self):
         with warnings.catch_warnings(record=True) as w:
             warnings.simplefilter("always")
             # trigger a warning
-            it = self.pr.querys2D(query)
+            self.pr.querys2D(query)
             # verify some things about the warning
-            assert len(w) == 1
-            assert issubclass(w[-1].category, pypairix.PairixWarning)
+            self.assertEqual(len(w), 1)
+            self.assertTrue(issubclass(w[-1].category, pypairix.PairixWarning))
 
 
 ## 2D query on 2D indexed file with chromosomes input in reverse order
@@ -283,10 +283,10 @@ def test_query2_rev_fail(self):
         with warnings.catch_warnings(record=True) as w:
             warnings.simplefilter("always")
             # trigger a warning
-            it = self.pr.query2D(self.chrom, self.start, self.end, self.chrom2, self.start2, self.end2)
+            self.pr.query2D(self.chrom, self.start, self.end, self.chrom2, self.start2, self.end2)
             # verify some things about the warning
-            assert len(w) == 1
-            assert issubclass(w[-1].category, pypairix.PairixWarning)
+            self.assertEqual(len(w), 1)
+            self.assertTrue(issubclass(w[-1].category, pypairix.PairixWarning))
 
 
 ## 2D query on 2D indexed file with chromosomes using a 4DN pairs file