X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=pysam.git;a=blobdiff_plain;f=tests%2Ftabix_test.py;h=2caa628660f74a4389a23bf8b09c8c9e55266dee;hp=207a59c6c125360655ac77192f43640903fc1c1d;hb=ca46ef4ba4a883c57cea62d5bf1bc021f1185109;hpb=d02fe5283ed7a93a2f76a5d6dc6e37b40c11b9b1

diff --git a/tests/tabix_test.py b/tests/tabix_test.py
index 207a59c..2caa628 100644
--- a/tests/tabix_test.py
+++ b/tests/tabix_test.py
@@ -127,7 +127,6 @@ class TestIteration( unittest.TestCase ):
                                  b.difference(a) ))
 
         for x, d in enumerate( zip( result, ref )):
-            
             self.assertEqual( d[0], d[1],
                               "unexpected results in pair %i: '%s', expected '%s'" % \
                                   (x, 
@@ -204,6 +203,17 @@ class TestIteration( unittest.TestCase ):
         header = list( self.tabix.header )
         self.assertEqual( ref, header )
 
+    def testReopening( self ):
+        '''test repeated opening of the same file.'''
+        def func1():
+            # opens any tabix file
+            inf = pysam.Tabixfile(self.filename)
+            return
+
+        for i in range(10000):
+            func1()
+
+
 class TestParser( unittest.TestCase ):
 
     filename = "example.gtf.gz" 
@@ -219,9 +229,16 @@ class TestParser( unittest.TestCase ):
             self.assertEqual( self.compare[x], list(r) )
             self.assertEqual( len(self.compare[x]), len(r) )
 
+            # test indexing
             for c in range(0,len(r)):
                 self.assertEqual( self.compare[x][c], r[c] )
 
+            # test slicing access
+            for c in range(0, len(r)-1):
+                for cc in range(c+1, len(r)):
+                    self.assertEqual( self.compare[x][c:cc],
+                                      r[c:cc] )
+
     def testWrite( self ):
         
         for x, r in enumerate(self.tabix.fetch( parser = pysam.asTuple() )):
@@ -250,10 +267,18 @@ class TestParser( unittest.TestCase ):
                 self.assertEqual( "\t".join(e), str(r) )
 
 class TestGTF( TestParser ):
+
     def testRead( self ):
 
         for x, r in enumerate(self.tabix.fetch( parser = pysam.asGTF() )):
-            self.assertEqual( "\t".join( self.compare[x]), str(r) )
+            c =  self.compare[x]
+            
+            self.assertEqual( len(c), len(r) )
+            self.assertEqual( "\t".join(c), str(r) )
+            self.assertTrue( r.gene_id.startswith("ENSG") )
+            if r.feature != "gene":
+                self.assertTrue( r.transcript_id.startswith("ENST") )
+            self.assertEqual( c[0], r.contig )
 
 class TestBed( unittest.TestCase ):
     filename = "example.bed.gz"
@@ -307,8 +332,8 @@ class TestVCF( TestParser ):
             c = self.compare[x]
             for y, field in enumerate( self.columns ):
                 if field == "pos":
-                    self.assertEqual( int(c[y])-1, getattr( r, field ) )
-                    self.assertEqual( int(c[y])-1, r.pos )
+                    self.assertEqual( int(c[y]) - 1, getattr( r, field ) )
+                    self.assertEqual( int(c[y]) - 1, r.pos )
                 else:
                     self.assertEqual( c[y], getattr( r, field ), 
                                       "mismatch in field %s: %s != %s" %\
@@ -323,12 +348,24 @@ class TestVCF( TestParser ):
         ncolumns = len(self.columns) 
 
         for x, r in enumerate(self.tabix.fetch( parser = pysam.asVCF() )):
+
             c = self.compare[x]
+
+            # check unmodified string
+            ref_string = "\t".join( c )
+            cmp_string = str(r)
+            self.assertEqual( ref_string, cmp_string )
+
+            # set fields and compare field-wise
             for y, field in enumerate( self.columns ):
                 if field == "pos":
-                    r.pos += 1
-                    self.assertEqual( int(c[y]), getattr( r, field ) )
-                    self.assertEqual( int(c[y]), r.pos )
+                    rpos = getattr( r, field )
+                    self.assertEqual( int(c[y]) - 1, rpos )
+                    self.assertEqual( int(c[y]) - 1, r.pos )
+                    # increment pos by 1
+                    setattr( r, field, rpos + 1 )
+                    self.assertEqual( getattr( r, field ), rpos + 1 )
+                    c[y] = str(int(c[y]) + 1 ) 
                 else:
                     setattr( r, field, "test_%i" % y)
                     c[y] = "test_%i" % y
@@ -342,7 +379,23 @@ class TestVCF( TestParser ):
                 c[ncolumns+y] = "test_%i" % y
                 r[y] = "test_%i" % y
                 self.assertEqual( c[ncolumns+y], r[y] )
+
+class TestVCF( TestParser ):
+
+    filename = "example.vcf40.gz"
+
+    def testOpening( self ):
+        while 1:
+            infile = pysam.Tabixfile( self.filename )
+            infile.close()
+
                 
+            # check strings
+            ref_string = "\t".join( c )
+            cmp_string = str(r)
+            
+            self.assertEqual( ref_string, cmp_string )
+
 if __name__ == "__main__":
 
     unittest.main()