Display preview feature for Bam datatype

lib/galaxy/datatypes/binary.py

@@ -10,11 +10,14 @@
 import subprocess
 import tempfile
 import zipfile
+from json import dumps
 
 import pysam
 from bx.seq.twobit import TWOBIT_MAGIC_NUMBER, TWOBIT_MAGIC_NUMBER_SWAP, TWOBIT_MAGIC_SIZE
 
+from galaxy import util
 from galaxy.datatypes import metadata
+from galaxy.datatypes.tabular import Sam
 from galaxy.datatypes.metadata import DictParameter, ListParameter, MetadataElement, MetadataParameter
 from galaxy.util import FILENAME_VALID_CHARS, nice_size, sqlite, which
 from . import data, dataproviders
@@ -220,7 +223,7 @@ class GenericAsn1Binary( Binary ):
 
 
 @dataproviders.decorators.has_dataproviders
-class Bam( Binary ):
+class Bam( Binary, Sam ):
     """Class describing a BAM binary file"""
     edam_format = "format_2572"
     edam_data = "data_0863"
@@ -236,6 +239,9 @@ class Bam( Binary ):
     MetadataElement( name="reference_lengths", default=[], desc="Chromosome Lengths", param=MetadataParameter, readonly=True, visible=False, optional=True, no_value=[] )
     MetadataElement( name="bam_header", default={}, desc="Dictionary of BAM Headers", param=MetadataParameter, readonly=True, visible=False, optional=True, no_value={} )
 
+    def __init__(self, **kwd):
+        super( Bam, self ).__init__( **kwd )
+
     def _get_samtools_version( self ):
         version = '0.0.0'
         samtools_exec = which('samtools')
@@ -462,6 +468,52 @@ def to_archive(self, trans, dataset, name=""):
         file_paths.append(dataset.metadata.bam_index.file_name)
         return zip(file_paths, rel_paths)
 
+    def get_chunk(self, trans, dataset, offset=0, ck_size=None):
+        index_file = dataset.metadata.bam_index
+        with pysam.AlignmentFile(dataset.file_name, "rb", index_filename=index_file.file_name) as bamfile:
+            ck_size = 1000  # 1000 lines
+            ck_data = ""
+            line_number = 0
+            if offset == 0:
+                ck_data = bamfile.text
+            for line_number, alignment,  in enumerate(bamfile):
+                if line_number > offset and line_number <= (offset + ck_size):
+                    bamline = alignment.tostring(bamfile)
+                    # Galaxy display each tag as separate column because 'tostring()' funcition put spaces in between each tag of tags column. 
+                    # Below code will remove spaces between each tag. 
+                    bamline_modified = ('\t').join(bamline.split()[:11] + [('').join(bamline.split()[11:])])
+                    ck_data = ck_data +"\n" + bamline_modified
+                elif line_number > (offset + ck_size):
+                    break
+        last_read = offset + ck_size
+        return dumps( { 'ck_data': util.unicodify( ck_data ),
+                        'offset': last_read } )
+
+    def display_data( self, trans, dataset, preview=False, filename=None, to_ext=None, offset=None, ck_size=None, **kwd):
+        preview = util.string_as_bool( preview )
+        if offset is not None:
+            return self.get_chunk(trans, dataset, offset, ck_size)
+        elif to_ext or not preview:
+            return super( Bam, self ).display_data( trans, dataset, preview, filename, to_ext, **kwd )
+        else:
+            column_names = ''
+            if dataset.metadata.column_names:
+                column_names = dataset.metadata.column_names
+            elif hasattr(dataset.datatype, 'column_names'):
+                column_names = dataset.datatype.column_names
+            column_types = dataset.metadata.column_types
+            if not column_types:
+                column_types = []
+            column_number = dataset.metadata.columns
+            if column_number is None:
+                column_number = 1
+            return trans.fill_template( "/dataset/tabular_chunked.mako",
+                                        dataset=dataset,
+                                        chunk=self.get_chunk(trans, dataset, 0),
+                                        column_number=column_number,
+                                        column_names=column_names,
+                                        column_types=column_types )
+
     # ------------- Dataproviders
     # pipe through samtools view
     # ALSO: (as Sam)

lib/galaxy/datatypes/sniff.py

@@ -28,7 +28,6 @@
     is_bz2,
     is_gzip
 )
-from galaxy.datatypes.binary import Binary
 
 log = logging.getLogger(__name__)
 
@@ -478,7 +477,7 @@ def handle_uploaded_dataset_file( filename, datatypes_registry, ext='auto', is_m
         ext = guess_ext( filename, sniff_order=datatypes_registry.sniff_order, is_multi_byte=is_multi_byte )
 
     if check_binary( filename ):
-        if not Binary.is_ext_unsniffable(ext) and not datatypes_registry.get_datatype_by_extension( ext ).sniff( filename ):
+        if not galaxy.datatypes.binary.is_ext_unsniffable(ext) and not datatypes_registry.get_datatype_by_extension( ext ).sniff( filename ):
             raise InappropriateDatasetContentError( 'The binary uploaded file contains inappropriate content.' )
     elif check_html( filename ):
         raise InappropriateDatasetContentError( 'The uploaded file contains inappropriate HTML content.' )