From e88233af84d50822bc6328114e112165605e32fa Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Wed, 5 Jul 2017 15:12:07 +0200
Subject: [PATCH 01/17] Preview feature for Bam datatype

---
 lib/galaxy/datatypes/binary.py | 54 +++++++++++++++++++++++++++++++++-
 lib/galaxy/datatypes/sniff.py  |  3 +-
 2 files changed, 54 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 236d9ba3de2..684ed71e361 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -15,6 +15,7 @@ import pysam
 from bx.seq.twobit import TWOBIT_MAGIC_NUMBER, TWOBIT_MAGIC_NUMBER_SWAP, TWOBIT_MAGIC_SIZE
 
 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 +221,7 @@ Binary.register_unsniffable_binary_ext("asn1-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 +237,10 @@ 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):
+        """Initialize taxonomy datatype"""
+        super( Bam, self ).__init__( **kwd )
+
     def _get_samtools_version( self ):
         version = '0.0.0'
         samtools_exec = which('samtools')
@@ -462,6 +467,53 @@ class Bam( Binary ):
         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):
+        bamfile = pysam.AlignmentFile(dataset.file_name, "rb")
+        ck_size = 100 # 100 lines
+        ck_data=""
+        lineNumber=0
+        if(offset == 0):
+            ck_data = bamfile.text
+        for f in bamfile.fetch(until_eof=True):
+            lineNumber+=1
+            if (lineNumber > offset and lineNumber <= (offset + ck_size)):
+                bamline = f.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. 
+                bamlineModified = ('\t').join(bamline.split()[:11] + [('').join(bamline.split()[11:])])
+                ck_data=ck_data +"\n" + bamlineModified
+            elif (lineNumber > (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 = 'null'
+            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 = 'null'
+            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)
diff --git a/lib/galaxy/datatypes/sniff.py b/lib/galaxy/datatypes/sniff.py
index b2a82e9f8bf..2c46ba8380c 100644
--- a/lib/galaxy/datatypes/sniff.py
+++ b/lib/galaxy/datatypes/sniff.py
@@ -28,7 +28,6 @@ from galaxy.util.checkers import (
     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.' )

From 2005a9d685209789c95e5eb48d2a6c77d9703201 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Wed, 5 Jul 2017 15:17:00 +0200
Subject: [PATCH 02/17] Preview feature for Bam datatype. Final Changes

---
 lib/galaxy/datatypes/binary.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 684ed71e361..3e040349378 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -10,10 +10,12 @@ import struct
 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 bb67be81cd1c2043ecd1b1eb54942cbb5b52c828 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Wed, 5 Jul 2017 18:59:57 +0200
Subject: [PATCH 03/17] Updated based on the changes requested

---
 lib/galaxy/datatypes/binary.py | 40 ++++++++++++++++------------------
 1 file changed, 19 insertions(+), 21 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 3e040349378..abe050e5741 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -223,7 +223,7 @@ Binary.register_unsniffable_binary_ext("asn1-binary")
 
 
 @dataproviders.decorators.has_dataproviders
-class Bam( Binary , Sam):
+class Bam( Binary, Sam ):
     """Class describing a BAM binary file"""
     edam_format = "format_2572"
     edam_data = "data_0863"
@@ -240,7 +240,6 @@ class Bam( Binary , Sam):
     MetadataElement( name="bam_header", default={}, desc="Dictionary of BAM Headers", param=MetadataParameter, readonly=True, visible=False, optional=True, no_value={} )
 
     def __init__(self, **kwd):
-        """Initialize taxonomy datatype"""
         super( Bam, self ).__init__( **kwd )
 
     def _get_samtools_version( self ):
@@ -469,24 +468,23 @@ class Bam( Binary , Sam):
         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):
-        bamfile = pysam.AlignmentFile(dataset.file_name, "rb")
-        ck_size = 100 # 100 lines
-        ck_data=""
-        lineNumber=0
-        if(offset == 0):
-            ck_data = bamfile.text
-        for f in bamfile.fetch(until_eof=True):
-            lineNumber+=1
-            if (lineNumber > offset and lineNumber <= (offset + ck_size)):
-                bamline = f.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. 
-                bamlineModified = ('\t').join(bamline.split()[:11] + [('').join(bamline.split()[11:])])
-                ck_data=ck_data +"\n" + bamlineModified
-            elif (lineNumber > (offset + ck_size)):
-                break
+        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 } )
@@ -498,7 +496,7 @@ class Bam( Binary , Sam):
         elif to_ext or not preview:
             return super( Bam, self ).display_data( trans, dataset, preview, filename, to_ext, **kwd )
         else:
-            column_names = 'null'
+            column_names = ''
             if dataset.metadata.column_names:
                 column_names = dataset.metadata.column_names
             elif hasattr(dataset.datatype, 'column_names'):
@@ -508,7 +506,7 @@ class Bam( Binary , Sam):
                 column_types = []
             column_number = dataset.metadata.columns
             if column_number is None:
-                column_number = 'null'
+                column_number = 1
             return trans.fill_template( "/dataset/tabular_chunked.mako",
                                         dataset=dataset,
                                         chunk=self.get_chunk(trans, dataset, 0),

From 72c196f793aeb30ec00cf368e419bcdaecdbd514 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Thu, 6 Jul 2017 14:48:08 +0200
Subject: [PATCH 04/17] Accessing Bam file via seek() and tell()

---
 lib/galaxy/datatypes/binary.py | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index abe050e5741..c36c39cf8f3 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -468,31 +468,37 @@ class Bam( Binary, Sam ):
         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):
+    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
+        with pysam.AlignmentFile( dataset.file_name, "rb", index_filename=index_file.file_name ) as bamfile:
+            ck_size = 300  # 300 lines
             ck_data = ""
-            line_number = 0
+            last_read = 0
+            header_line_count = 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)
+                header_line_count = bamfile.text.count('\n')
+            else:
+                bamfile.seek( offset )
+            for line_number, alignment in enumerate( bamfile ) :
+                # return only Header lines if 'header_line_count' exceeds 'ck_size'
+                # FIXME: Can be problematic if bam has million lines of header
+                if ( line_number + header_line_count ) > ck_size:
+                    break
+                else:
+                    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:])])
+                    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
+                last_read = bamfile.tell()
         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)
+            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:
@@ -509,7 +515,7 @@ class Bam( Binary, Sam ):
                 column_number = 1
             return trans.fill_template( "/dataset/tabular_chunked.mako",
                                         dataset=dataset,
-                                        chunk=self.get_chunk(trans, dataset, 0),
+                                        chunk=self.get_chunk( trans, dataset, 0 ),
                                         column_number=column_number,
                                         column_names=column_names,
                                         column_types=column_types )

From c66298d62717c88cf4341ad1601176420b16f280 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Thu, 6 Jul 2017 15:43:56 +0200
Subject: [PATCH 05/17] travis test correction

---
 lib/galaxy/datatypes/binary.py | 6 +++---
 lib/galaxy/datatypes/sniff.py  | 3 ++-
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index c36c39cf8f3..b6276f0ac7f 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -487,10 +487,10 @@ class Bam( Binary, Sam ):
                     break
                 else:
                     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. 
+                    # 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
+                    ck_data = ck_data + "\n" + bamline_modified
                 last_read = bamfile.tell()
         return dumps( { 'ck_data': util.unicodify( ck_data ),
                         'offset': last_read } )
diff --git a/lib/galaxy/datatypes/sniff.py b/lib/galaxy/datatypes/sniff.py
index 2c46ba8380c..0d585a4ac80 100644
--- a/lib/galaxy/datatypes/sniff.py
+++ b/lib/galaxy/datatypes/sniff.py
@@ -17,6 +17,7 @@ from encodings import search_function as encodings_search_function
 from six import text_type
 
 from galaxy import util
+from galaxy import datatypes
 from galaxy.util import multi_byte
 from galaxy.util import (
     compression_utils,
@@ -477,7 +478,7 @@ 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 galaxy.datatypes.binary.is_ext_unsniffable(ext) and not datatypes_registry.get_datatype_by_extension( ext ).sniff( filename ):
+        if not datatypes.binary.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.' )

From 8c8aa8820fcc592c31693399660b87b04809b9da Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Wed, 5 Jul 2017 15:12:07 +0200
Subject: [PATCH 06/17] Preview feature for Bam datatype

---
 lib/galaxy/datatypes/binary.py | 54 +++++++++++++++++++++++++++++++++-
 lib/galaxy/datatypes/sniff.py  |  2 +-
 2 files changed, 54 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 236d9ba3de2..684ed71e361 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -15,6 +15,7 @@ import pysam
 from bx.seq.twobit import TWOBIT_MAGIC_NUMBER, TWOBIT_MAGIC_NUMBER_SWAP, TWOBIT_MAGIC_SIZE
 
 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 +221,7 @@ Binary.register_unsniffable_binary_ext("asn1-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 +237,10 @@ 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):
+        """Initialize taxonomy datatype"""
+        super( Bam, self ).__init__( **kwd )
+
     def _get_samtools_version( self ):
         version = '0.0.0'
         samtools_exec = which('samtools')
@@ -462,6 +467,53 @@ class Bam( Binary ):
         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):
+        bamfile = pysam.AlignmentFile(dataset.file_name, "rb")
+        ck_size = 100 # 100 lines
+        ck_data=""
+        lineNumber=0
+        if(offset == 0):
+            ck_data = bamfile.text
+        for f in bamfile.fetch(until_eof=True):
+            lineNumber+=1
+            if (lineNumber > offset and lineNumber <= (offset + ck_size)):
+                bamline = f.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. 
+                bamlineModified = ('\t').join(bamline.split()[:11] + [('').join(bamline.split()[11:])])
+                ck_data=ck_data +"\n" + bamlineModified
+            elif (lineNumber > (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 = 'null'
+            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 = 'null'
+            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)
diff --git a/lib/galaxy/datatypes/sniff.py b/lib/galaxy/datatypes/sniff.py
index 4e1aa31b223..bfa271d1ec4 100644
--- a/lib/galaxy/datatypes/sniff.py
+++ b/lib/galaxy/datatypes/sniff.py
@@ -487,7 +487,7 @@ 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.' )

From 3ddf819c83f881eee4b7ab19281926e1e64a58d3 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Wed, 5 Jul 2017 15:17:00 +0200
Subject: [PATCH 07/17] Preview feature for Bam datatype. Final Changes

---
 lib/galaxy/datatypes/binary.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 684ed71e361..3e040349378 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -10,10 +10,12 @@ import struct
 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 9a8c8b8a61b1ec09509cc9b2b7738eae5238e036 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Wed, 5 Jul 2017 18:59:57 +0200
Subject: [PATCH 08/17] Updated based on the changes requested

---
 lib/galaxy/datatypes/binary.py | 40 ++++++++++++++++------------------
 1 file changed, 19 insertions(+), 21 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 3e040349378..abe050e5741 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -223,7 +223,7 @@ Binary.register_unsniffable_binary_ext("asn1-binary")
 
 
 @dataproviders.decorators.has_dataproviders
-class Bam( Binary , Sam):
+class Bam( Binary, Sam ):
     """Class describing a BAM binary file"""
     edam_format = "format_2572"
     edam_data = "data_0863"
@@ -240,7 +240,6 @@ class Bam( Binary , Sam):
     MetadataElement( name="bam_header", default={}, desc="Dictionary of BAM Headers", param=MetadataParameter, readonly=True, visible=False, optional=True, no_value={} )
 
     def __init__(self, **kwd):
-        """Initialize taxonomy datatype"""
         super( Bam, self ).__init__( **kwd )
 
     def _get_samtools_version( self ):
@@ -469,24 +468,23 @@ class Bam( Binary , Sam):
         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):
-        bamfile = pysam.AlignmentFile(dataset.file_name, "rb")
-        ck_size = 100 # 100 lines
-        ck_data=""
-        lineNumber=0
-        if(offset == 0):
-            ck_data = bamfile.text
-        for f in bamfile.fetch(until_eof=True):
-            lineNumber+=1
-            if (lineNumber > offset and lineNumber <= (offset + ck_size)):
-                bamline = f.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. 
-                bamlineModified = ('\t').join(bamline.split()[:11] + [('').join(bamline.split()[11:])])
-                ck_data=ck_data +"\n" + bamlineModified
-            elif (lineNumber > (offset + ck_size)):
-                break
+        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 } )
@@ -498,7 +496,7 @@ class Bam( Binary , Sam):
         elif to_ext or not preview:
             return super( Bam, self ).display_data( trans, dataset, preview, filename, to_ext, **kwd )
         else:
-            column_names = 'null'
+            column_names = ''
             if dataset.metadata.column_names:
                 column_names = dataset.metadata.column_names
             elif hasattr(dataset.datatype, 'column_names'):
@@ -508,7 +506,7 @@ class Bam( Binary , Sam):
                 column_types = []
             column_number = dataset.metadata.columns
             if column_number is None:
-                column_number = 'null'
+                column_number = 1
             return trans.fill_template( "/dataset/tabular_chunked.mako",
                                         dataset=dataset,
                                         chunk=self.get_chunk(trans, dataset, 0),

From 731d1db4b23e2a75335f716a9c6f6d1b30938101 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Thu, 6 Jul 2017 14:48:08 +0200
Subject: [PATCH 09/17] Accessing Bam file via seek() and tell()

---
 lib/galaxy/datatypes/binary.py | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index abe050e5741..c36c39cf8f3 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -468,31 +468,37 @@ class Bam( Binary, Sam ):
         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):
+    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
+        with pysam.AlignmentFile( dataset.file_name, "rb", index_filename=index_file.file_name ) as bamfile:
+            ck_size = 300  # 300 lines
             ck_data = ""
-            line_number = 0
+            last_read = 0
+            header_line_count = 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)
+                header_line_count = bamfile.text.count('\n')
+            else:
+                bamfile.seek( offset )
+            for line_number, alignment in enumerate( bamfile ) :
+                # return only Header lines if 'header_line_count' exceeds 'ck_size'
+                # FIXME: Can be problematic if bam has million lines of header
+                if ( line_number + header_line_count ) > ck_size:
+                    break
+                else:
+                    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:])])
+                    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
+                last_read = bamfile.tell()
         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)
+            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:
@@ -509,7 +515,7 @@ class Bam( Binary, Sam ):
                 column_number = 1
             return trans.fill_template( "/dataset/tabular_chunked.mako",
                                         dataset=dataset,
-                                        chunk=self.get_chunk(trans, dataset, 0),
+                                        chunk=self.get_chunk( trans, dataset, 0 ),
                                         column_number=column_number,
                                         column_names=column_names,
                                         column_types=column_types )

From dac72950db3b64291c5c202b9db15fac3525de86 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Thu, 6 Jul 2017 15:43:56 +0200
Subject: [PATCH 10/17] travis test correction

---
 lib/galaxy/datatypes/binary.py | 6 +++---
 lib/galaxy/datatypes/sniff.py  | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index c36c39cf8f3..b6276f0ac7f 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -487,10 +487,10 @@ class Bam( Binary, Sam ):
                     break
                 else:
                     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. 
+                    # 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
+                    ck_data = ck_data + "\n" + bamline_modified
                 last_read = bamfile.tell()
         return dumps( { 'ck_data': util.unicodify( ck_data ),
                         'offset': last_read } )
diff --git a/lib/galaxy/datatypes/sniff.py b/lib/galaxy/datatypes/sniff.py
index bfa271d1ec4..08342cf876d 100644
--- a/lib/galaxy/datatypes/sniff.py
+++ b/lib/galaxy/datatypes/sniff.py
@@ -17,7 +17,7 @@ import zipfile
 from six import text_type
 
 from galaxy import util
-from galaxy.datatypes.binary import Binary
+from galaxy import datatypes
 from galaxy.util import (
     compression_utils,
     multi_byte,
@@ -487,7 +487,7 @@ 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 galaxy.datatypes.binary.is_ext_unsniffable(ext) and not datatypes_registry.get_datatype_by_extension( ext ).sniff( filename ):
+        if not datatypes.binary.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.' )

From 253d0c2d4f435a9778a636ff3a162d0fe0717854 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Thu, 6 Jul 2017 18:07:19 +0200
Subject: [PATCH 11/17] reordering import statements

---
 lib/galaxy/datatypes/binary.py | 2 +-
 lib/galaxy/datatypes/sniff.py  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index b6276f0ac7f..6ba1a198381 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -17,8 +17,8 @@ from bx.seq.twobit import TWOBIT_MAGIC_NUMBER, TWOBIT_MAGIC_NUMBER_SWAP, TWOBIT_
 
 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.datatypes.tabular import Sam
 from galaxy.util import FILENAME_VALID_CHARS, nice_size, sqlite, which
 from . import data, dataproviders
 
diff --git a/lib/galaxy/datatypes/sniff.py b/lib/galaxy/datatypes/sniff.py
index 08342cf876d..f20777b7c75 100644
--- a/lib/galaxy/datatypes/sniff.py
+++ b/lib/galaxy/datatypes/sniff.py
@@ -16,8 +16,8 @@ import zipfile
 
 from six import text_type
 
-from galaxy import util
 from galaxy import datatypes
+from galaxy import util
 from galaxy.util import (
     compression_utils,
     multi_byte,

From 3ddd05d56985360c31bd62ea78027fbfc34bb796 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Fri, 7 Jul 2017 13:35:17 +0200
Subject: [PATCH 12/17] Removing the SAM datatype for class Bam and resetting
 changes with sniff.py

---
 lib/galaxy/datatypes/binary.py | 9 +++++++--
 lib/galaxy/datatypes/sniff.py  | 4 ++--
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 6ba1a198381..aadf8f4d603 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -18,7 +18,6 @@ from bx.seq.twobit import TWOBIT_MAGIC_NUMBER, TWOBIT_MAGIC_NUMBER_SWAP, TWOBIT_
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes.metadata import DictParameter, ListParameter, MetadataElement, MetadataParameter
-from galaxy.datatypes.tabular import Sam
 from galaxy.util import FILENAME_VALID_CHARS, nice_size, sqlite, which
 from . import data, dataproviders
 
@@ -223,7 +222,7 @@ Binary.register_unsniffable_binary_ext("asn1-binary")
 
 
 @dataproviders.decorators.has_dataproviders
-class Bam( Binary, Sam ):
+class Bam( Binary ):
     """Class describing a BAM binary file"""
     edam_format = "format_2572"
     edam_data = "data_0863"
@@ -238,9 +237,13 @@ class Bam( Binary, Sam ):
     MetadataElement( name="reference_names", default=[], desc="Chromosome Names", param=MetadataParameter, readonly=True, visible=False, optional=True, no_value=[] )
     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={} )
+    MetadataElement( name="columns", default=0, desc="Number of columns", readonly=True, visible=False, no_value=0 )
+    MetadataElement( name="column_types", default=[], desc="Column types", param=metadata.ColumnTypesParameter, readonly=True, visible=False, no_value=[] )
+    MetadataElement( name="column_names", default=[], desc="Column names", readonly=True, visible=False, optional=True, no_value=[] )
 
     def __init__(self, **kwd):
         super( Bam, self ).__init__( **kwd )
+        self.column_names = ['QNAME', 'FLAG', 'RNAME', 'POS', 'MAPQ', 'CIGAR', 'MRNM', 'MPOS', 'ISIZE', 'SEQ', 'QUAL', 'OPT' ]
 
     def _get_samtools_version( self ):
         version = '0.0.0'
@@ -429,6 +432,8 @@ class Bam( Binary, Sam ):
             dataset.metadata.read_groups = [ read_group['ID'] for read_group in dataset.metadata.bam_header.get( 'RG', [] ) if 'ID' in read_group ]
             dataset.metadata.sort_order = dataset.metadata.bam_header.get( 'HD', {} ).get( 'SO', None )
             dataset.metadata.bam_version = dataset.metadata.bam_header.get( 'HD', {} ).get( 'VN', None )
+            dataset.metadata.columns = 12
+            dataset.metadata.column_types = ['str', 'int', 'str', 'int', 'int', 'str', 'str', 'int', 'int', 'str', 'str', 'str']
         except:
             # Per Dan, don't log here because doing so will cause datasets that
             # fail metadata to end in the error state
diff --git a/lib/galaxy/datatypes/sniff.py b/lib/galaxy/datatypes/sniff.py
index f20777b7c75..4e1aa31b223 100644
--- a/lib/galaxy/datatypes/sniff.py
+++ b/lib/galaxy/datatypes/sniff.py
@@ -16,8 +16,8 @@ import zipfile
 
 from six import text_type
 
-from galaxy import datatypes
 from galaxy import util
+from galaxy.datatypes.binary import Binary
 from galaxy.util import (
     compression_utils,
     multi_byte,
@@ -487,7 +487,7 @@ 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 datatypes.binary.Binary.is_ext_unsniffable(ext) and not datatypes_registry.get_datatype_by_extension( ext ).sniff( filename ):
+        if not 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.' )

From c476090bdef84b7781458ff7445451d35e0af46b Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Fri, 7 Jul 2017 16:20:32 +0200
Subject: [PATCH 13/17] setting default value for column_names, column_types
 and column Metadata

---
 lib/galaxy/datatypes/binary.py | 24 +++++++++---------------
 1 file changed, 9 insertions(+), 15 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index aadf8f4d603..11010eb965e 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -237,13 +237,11 @@ class Bam( Binary ):
     MetadataElement( name="reference_names", default=[], desc="Chromosome Names", param=MetadataParameter, readonly=True, visible=False, optional=True, no_value=[] )
     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={} )
-    MetadataElement( name="columns", default=0, desc="Number of columns", readonly=True, visible=False, no_value=0 )
-    MetadataElement( name="column_types", default=[], desc="Column types", param=metadata.ColumnTypesParameter, readonly=True, visible=False, no_value=[] )
-    MetadataElement( name="column_names", default=[], desc="Column names", readonly=True, visible=False, optional=True, no_value=[] )
-
-    def __init__(self, **kwd):
-        super( Bam, self ).__init__( **kwd )
-        self.column_names = ['QNAME', 'FLAG', 'RNAME', 'POS', 'MAPQ', 'CIGAR', 'MRNM', 'MPOS', 'ISIZE', 'SEQ', 'QUAL', 'OPT' ]
+    MetadataElement( name="columns", default=12, desc="Number of columns", readonly=True, visible=False, no_value=0 )
+    MetadataElement( name="column_types", default=['str', 'int', 'str', 'int', 'int', 'str', 'str', 'int', 'int', 'str', 'str', 'str'], desc="Column types", 
+                     param=metadata.ColumnTypesParameter, readonly=True, visible=False, no_value=[] )
+    MetadataElement( name="column_names", default=[ 'QNAME', 'FLAG', 'RNAME', 'POS', 'MAPQ', 'CIGAR', 'MRNM', 'MPOS', 'ISIZE', 'SEQ', 'QUAL', 'OPT' ], desc="Column names", 
+                    readonly=True, visible=False, optional=True, no_value=[] )
 
     def _get_samtools_version( self ):
         version = '0.0.0'
@@ -432,8 +430,6 @@ class Bam( Binary ):
             dataset.metadata.read_groups = [ read_group['ID'] for read_group in dataset.metadata.bam_header.get( 'RG', [] ) if 'ID' in read_group ]
             dataset.metadata.sort_order = dataset.metadata.bam_header.get( 'HD', {} ).get( 'SO', None )
             dataset.metadata.bam_version = dataset.metadata.bam_header.get( 'HD', {} ).get( 'VN', None )
-            dataset.metadata.columns = 12
-            dataset.metadata.column_types = ['str', 'int', 'str', 'int', 'int', 'str', 'str', 'int', 'int', 'str', 'str', 'str']
         except:
             # Per Dan, don't log here because doing so will cause datasets that
             # fail metadata to end in the error state
@@ -488,6 +484,7 @@ class Bam( Binary ):
             for line_number, alignment in enumerate( bamfile ) :
                 # return only Header lines if 'header_line_count' exceeds 'ck_size'
                 # FIXME: Can be problematic if bam has million lines of header
+                last_read = bamfile.tell()
                 if ( line_number + header_line_count ) > ck_size:
                     break
                 else:
@@ -496,7 +493,6 @@ class Bam( Binary ):
                     # 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
-                last_read = bamfile.tell()
         return dumps( { 'ck_data': util.unicodify( ck_data ),
                         'offset': last_read } )
 
@@ -507,11 +503,9 @@ class Bam( Binary ):
         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_names = dataset.metadata.column_names
+            if not column_names:
+                column_names = []
             column_types = dataset.metadata.column_types
             if not column_types:
                 column_types = []

From 8b3e492bad9257bd0f4c9ba3e78f1a88cc64bfe6 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Fri, 7 Jul 2017 16:47:16 +0200
Subject: [PATCH 14/17] Fix for travis test

---
 lib/galaxy/datatypes/binary.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 11010eb965e..a1715946693 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -238,10 +238,8 @@ 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={} )
     MetadataElement( name="columns", default=12, desc="Number of columns", readonly=True, visible=False, no_value=0 )
-    MetadataElement( name="column_types", default=['str', 'int', 'str', 'int', 'int', 'str', 'str', 'int', 'int', 'str', 'str', 'str'], desc="Column types", 
-                     param=metadata.ColumnTypesParameter, readonly=True, visible=False, no_value=[] )
-    MetadataElement( name="column_names", default=[ 'QNAME', 'FLAG', 'RNAME', 'POS', 'MAPQ', 'CIGAR', 'MRNM', 'MPOS', 'ISIZE', 'SEQ', 'QUAL', 'OPT' ], desc="Column names", 
-                    readonly=True, visible=False, optional=True, no_value=[] )
+    MetadataElement( name="column_types", default=['str', 'int', 'str', 'int', 'int', 'str', 'str', 'int', 'int', 'str', 'str', 'str'], desc="Column types", param=metadata.ColumnTypesParameter, readonly=True, visible=False, no_value=[] )
+    MetadataElement( name="column_names", default=[ 'QNAME', 'FLAG', 'RNAME', 'POS', 'MAPQ', 'CIGAR', 'MRNM', 'MPOS', 'ISIZE', 'SEQ', 'QUAL', 'OPT' ], desc="Column names", readonly=True, visible=False, optional=True, no_value=[] )
 
     def _get_samtools_version( self ):
         version = '0.0.0'

From 0cfdfbf275fda9072b521fa501ad1aaafdc87c8e Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Fri, 7 Jul 2017 17:09:16 +0200
Subject: [PATCH 15/17] replaced last_read with offset variable

---
 lib/galaxy/datatypes/binary.py | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index a1715946693..8c941864c7b 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -472,7 +472,6 @@ class Bam( Binary ):
         with pysam.AlignmentFile( dataset.file_name, "rb", index_filename=index_file.file_name ) as bamfile:
             ck_size = 300  # 300 lines
             ck_data = ""
-            last_read = 0
             header_line_count = 0
             if offset == 0:
                 ck_data = bamfile.text
@@ -482,7 +481,7 @@ class Bam( Binary ):
             for line_number, alignment in enumerate( bamfile ) :
                 # return only Header lines if 'header_line_count' exceeds 'ck_size'
                 # FIXME: Can be problematic if bam has million lines of header
-                last_read = bamfile.tell()
+                offset = bamfile.tell()
                 if ( line_number + header_line_count ) > ck_size:
                     break
                 else:
@@ -490,9 +489,9 @@ class Bam( Binary ):
                     # 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
+                    ck_data = "%s\n%s" % ( ck_data, bamline_modified )
         return dumps( { 'ck_data': util.unicodify( ck_data ),
-                        'offset': last_read } )
+                        'offset': offset } )
 
     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 )

From 90a0ab0398860cccf84a78dd293f62b44bb0bf71 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Mon, 10 Jul 2017 11:26:34 +0200
Subject: [PATCH 16/17] Replace '\t' to ' ' in  BAM headers

---
 lib/galaxy/datatypes/binary.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 8c941864c7b..0a0bbbf3229 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -474,7 +474,7 @@ class Bam( Binary ):
             ck_data = ""
             header_line_count = 0
             if offset == 0:
-                ck_data = bamfile.text
+                ck_data = bamfile.text.replace('\t',' ')
                 header_line_count = bamfile.text.count('\n')
             else:
                 bamfile.seek( offset )
@@ -486,9 +486,9 @@ class Bam( Binary ):
                     break
                 else:
                     bamline = alignment.tostring( bamfile )
-                    # Galaxy display each tag as separate column because 'tostring()' funcition put spaces in between each tag of tags column.
+                    # Galaxy display each tag as separate column because 'tostring()' funcition put tabs 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:]) ] )
+                    bamline_modified = ('\t').join( bamline.split()[:11] + [ (' ').join(bamline.split()[11:]) ] )
                     ck_data = "%s\n%s" % ( ck_data, bamline_modified )
         return dumps( { 'ck_data': util.unicodify( ck_data ),
                         'offset': offset } )

From b370a9cbaea3781d21c3d618cfa5521bdc5bea73 Mon Sep 17 00:00:00 2001
From: ashvark <ashvark@gmail.com>
Date: Mon, 10 Jul 2017 15:25:28 +0200
Subject: [PATCH 17/17] travis test fix

---
 lib/galaxy/datatypes/binary.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 0a0bbbf3229..57b1f5223ab 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -474,7 +474,7 @@ class Bam( Binary ):
             ck_data = ""
             header_line_count = 0
             if offset == 0:
-                ck_data = bamfile.text.replace('\t',' ')
+                ck_data = bamfile.text.replace('\t', ' ')
                 header_line_count = bamfile.text.count('\n')
             else:
                 bamfile.seek( offset )