Improvements to datatypes suggested by @nsoranzo

lib/galaxy/datatypes/binary.py

@@ -210,7 +210,7 @@ class Bam(Binary):
     @staticmethod
     def merge(split_files, output_file):
         """
-        Merges Bam files
+        Merges BAM files
 
         :param split_files: List of bam file paths to merge
         :param output_file: Write merged bam file to this location
@@ -232,7 +232,7 @@ class Bam(Binary):
             with open(os.devnull, 'w') as devnull:
                 subprocess.check_call(cmd, stderr=devnull, shell=False)
             needs_sorting = False
-        except Exception:
+        except subprocess.CalledProcessError:
             needs_sorting = True
         try:
             os.unlink(index_name)
@@ -242,10 +242,10 @@ class Bam(Binary):
 
     def groom_dataset_content(self, file_name):
         """
-        Ensures that the Bam file contents are sorted.  This function is called
+        Ensures that the BAM file contents are sorted.  This function is called
         on an output dataset after the content is initially generated.
         """
-        # Use pysam to sort the Bam file
+        # Use pysam to sort the BAM file
         # This command may also creates temporary files <out.prefix>.%d.bam when the
         # whole alignment cannot fit into memory.
         # do this in a unique temp directory, because of possible <out.prefix>.%d.bam temp files
@@ -254,7 +254,7 @@ class Bam(Binary):
             return
         tmp_dir = tempfile.mkdtemp()
         tmp_sorted_dataset_file_name_prefix = os.path.join(tmp_dir, 'sorted')
-        sorted_file_name = "%s.bam" % tmp_sorted_dataset_file_name_prefix  # samtools accepts a prefix, not a filename, it always adds .bam to the prefix
+        sorted_file_name = "%s.bam" % tmp_sorted_dataset_file_name_prefix
         slots = os.environ.get('GALAXY_SLOTS', 1)
         try:
             pysam.sort("-@%s" % slots, file_name, '-T', tmp_sorted_dataset_file_name_prefix, '-O', 'BAM', '-o', sorted_file_name)

lib/galaxy/datatypes/tabular.py

@@ -16,7 +16,6 @@ from cgi import escape
 from json import dumps
 
 import pysam
-import pysam.bcftools
 
 from galaxy import util
 from galaxy.datatypes import binary, data, metadata
@@ -740,7 +739,7 @@ class Vcf(BaseVcf):
     def sniff(self, filename):
         if is_gzip(filename):
             return False
-        return BaseVcf.sniff(self, filename)
+        return super(Vcf, self).sniff(filename)
 
 
 class VcfGz(BaseVcf, binary.Binary):
@@ -752,7 +751,7 @@ class VcfGz(BaseVcf, binary.Binary):
     def sniff(self, filename):
         if not is_gzip(filename):
             return False
-        return BaseVcf.sniff(self, filename)
+        return super(VcfGz, self).sniff(filename)
 
     def set_meta(self, dataset, **kwd):
         super(BaseVcf, self).set_meta(dataset, **kwd)

lib/galaxy/visualization/data_providers/genome.py

@@ -322,7 +322,7 @@ class TabixDataProvider(FilterableMixin, GenomeDataProvider):
 
     @contextmanager
     def open_data_file(self):
-        # We create a symlnk to the index file. This is
+        # We create a symlink to the index file. This is
         # required until https://github.com/pysam-developers/pysam/pull/586 is merged.
         if PYSAM_INDEX_SYMLINK_NECESSARY:
             fd, index_path = tempfile.mkstemp(suffix='.tbi')

test/unit/datatypes/util.py

@@ -9,12 +9,12 @@ from galaxy.util.hash_util import md5_hash_file
 
 
 @contextmanager
-def get_dataset(file, index_attr='bam_index', dataset_id=1, has_data=True):
+def get_dataset(filename, index_attr='bam_index', dataset_id=1, has_data=True):
     dataset = Bunch()
     dataset.has_data = lambda: True
     dataset.id = dataset_id
     dataset.metadata = Bunch()
-    with get_input_files(file) as input_files, get_tmp_path() as index_path:
+    with get_input_files(filename) as input_files, get_tmp_path() as index_path:
         dataset.file_name = input_files[0]
         index = Bunch()
         index.file_name = index_path
@@ -39,9 +39,9 @@ def get_input_files(*args):
     temp_dir = tempfile.mkdtemp()
     test_files = []
     try:
-        for file in args:
-            shutil.copy(get_test_fname(file), temp_dir)
-            test_files.append(os.path.join(temp_dir, file))
+        for filename in args:
+            shutil.copy(get_test_fname(filename), temp_dir)
+            test_files.append(os.path.join(temp_dir, filename))
         md5_sums = [md5_hash_file(f) for f in test_files]
         yield test_files
         new_md5_sums = [md5_hash_file(f) for f in test_files]