Merge pull request #46 from 4dn-dcic/0.2.9

0.2.9

VERSION.txt

@@ -1 +1 @@
-0.2.8
+0.2.9

src/index.c

@@ -854,10 +854,10 @@ 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, l*2+2);
+          s = (char*)realloc(s, k*2+2);
           strcpy(s+i+1, s);
           s[i] = region_split_character;
-          l = l*2+1;
+          k = k*2+1;
         }
 
         //2d query on 2d data

src/pairix.h

@@ -28,7 +28,7 @@
 #ifndef __TABIDX_H
 #define __TABIDX_H
 
-#define PACKAGE_VERSION "0.2.8"
+#define PACKAGE_VERSION "0.2.9"
 
 #include <stdint.h>
 #include "kstring.h"

test/test.py

@@ -88,7 +88,7 @@ def find_pairs_type(filename, delimiter='\t'):
         except AttributeError:
             pass
         fields = line.rstrip().split(delimiter)
-        if is_str(fields[2]) and is_str(fields[6]):
+        if len(fields)>=6 and is_str(fields[2]) and is_str(fields[6]):
             is_juicer = True
         if is_str(fields[2]) and is_str(fields[4]):
             is_4DN = True
@@ -119,6 +119,8 @@ def read_pairs(filename, file_type='undetermined', delimiter='\t'):
             line = line.decode('utf-8')
         except AttributeError:
             pass
+        if line.startswith('#'):
+            continue
         fields = line.rstrip().split(delimiter)
         if file_type == 'juicer':
             chrom1 = fields[1]
@@ -154,6 +156,14 @@ def get_result_2D(regions, chrom, start, end, chrom2, start2, end2):
     return retval
 
 
+def get_result_2D_4DN(regions, chrom, start, end, chrom2, start2, end2):
+    retval = []
+    for r in regions:
+        if r[1] == chrom and overlap1(r[2], r[2], start, end) and r[3] == chrom2 and overlap1(r[4], r[4], start2, end2):
+            retval.append(r)
+    return retval
+
+
 def build_it_result(it, f_type):
     """Build results using the pairix iterator based on the filetype"""
     if f_type == 'juicer':
@@ -389,6 +399,26 @@ def test_build_index_with_force_merged_nodups_with_no_preset(self):  ## recogniz
         self.assertEqual(self.result, pr2_result)
 
 
+## 1D query on 2D indexed file
+class PairixTest_1_on_2(unittest.TestCase):
+    f_type='4DN'
+    regions = read_pairs(TEST_FILE_2D_4DN_2, f_type)
+    chrom = 'chrY'
+    start = 1
+    end = 2000000
+    chrom2 = chrom
+    start2 = start
+    end2 = end
+    result = get_result_2D_4DN(regions, chrom, start, end, chrom2, 0, sys.maxsize)
+    pr = pypairix.open(TEST_FILE_2D_4DN_2)
+
+    def test_querys(self):
+        query = '{}:{}-{}'.format(self.chrom, self.start, self.end)
+        it = self.pr.querys2D(query)
+        pr_result = build_it_result(it, self.f_type)
+        self.assertEqual(self.result, pr_result)
+
+
 class PairixTestBlocknames(unittest.TestCase):
 
     def test_blocknames(self):

test/test_c.sh

@@ -30,6 +30,12 @@ if [ ! -z "$(diff log1 log2)" ]; then
   return 1;
 fi
 
+pairix samples/test_4dn.pairs.gz 'chrY:1-2000000' > log1
+pairix samples/test_4dn.pairs.gz 'chrY:1-2000000|chrY:1-2000000' > log2
+if [ ! -z "$(diff log1 log2)" ]; then
+  echo "test 1e failed"
+  return 1;
+fi
 
 pairix samples/merged_nodup.tab.chrblock_sorted.txt.gz '10:1-1000000|20:50000000-60000000' > log1
 gunzip -c samples/merged_nodup.tab.chrblock_sorted.txt.gz | awk '$2=="10" && $3>=1 && $3<=1000000 && $6=="20" && $7>=50000000 && $7<=60000000' > log2