From eeecf4103c78af2486618dd60f609af07b10db86 Mon Sep 17 00:00:00 2001
From: Eric Rasche <rasche.eric@yandex.ru>
Date: Tue, 5 May 2015 14:30:41 -0500
Subject: [PATCH 1/9] Include hmmer3 text format

---
 config/datatypes_conf.xml.sample |  2 ++
 lib/galaxy/datatypes/text.py     | 38 ++++++++++++++++++++++++++------
 2 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/config/datatypes_conf.xml.sample b/config/datatypes_conf.xml.sample
index 42b874b46cc..7aa7d5d2710 100644
--- a/config/datatypes_conf.xml.sample
+++ b/config/datatypes_conf.xml.sample
@@ -271,6 +271,8 @@
     <datatype extension="rdf" type="galaxy.datatypes.graph:Rdf" display_in_upload="true"/>
     <!-- Excel datatypes -->
     <datatype extension="xlsx" type="galaxy.datatypes.binary:Xlsx" display_in_upload="true" />
+    <!-- MSA Datatypes -->
+    <datatype extension="hmm" type="galaxy.datatypes.text:Hmmer3" display_in_upload="true" />
   </registration>
   <sniffers>
     <!--
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 7309e84afd0..8069a1f2daf 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -139,7 +139,7 @@ class Obo( Text ):
 
     def sniff( self, filename ):
         """
-            Try to guess the Obo filetype. 
+            Try to guess the Obo filetype.
             It usually starts with a "format-version:" string and has several stanzas which starts with "id:".
         """
         stanza = re.compile(r'^\[.*\]$')
@@ -158,7 +158,7 @@ class Obo( Text ):
 
 class Arff( Text ):
     """
-        An ARFF (Attribute-Relation File Format) file is an ASCII text file that describes a list of instances sharing a set of attributes. 
+        An ARFF (Attribute-Relation File Format) file is an ASCII text file that describes a list of instances sharing a set of attributes.
         http://weka.wikispaces.com/ARFF
     """
     file_ext = "arff"
@@ -179,7 +179,7 @@ class Arff( Text ):
 
     def sniff( self, filename ):
         """
-            Try to guess the Arff filetype. 
+            Try to guess the Arff filetype.
             It usually starts with a "format-version:" string and has several stanzas which starts with "id:".
         """
         with open( filename ) as handle:
@@ -318,7 +318,7 @@ class SnpSiftDbNSFP( Text ):
     composite_type = 'auto_primary_file'
     allow_datatype_change = False
     """
-    ## The dbNSFP file is a tabular file with 1 header line 
+    ## The dbNSFP file is a tabular file with 1 header line
     ## The first 4 columns are required to be: chrom	pos	ref	alt
     ## These match columns 1,2,4,5 of the VCF file
     ## SnpSift requires the file to be block-gzipped and the indexed with samtools tabix
@@ -335,14 +335,14 @@ class SnpSiftDbNSFP( Text ):
     def init_meta( self, dataset, copy_from=None ):
         Text.init_meta( self, dataset, copy_from=copy_from )
     def generate_primary_file( self, dataset = None ):
-        """ 
+        """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
         """
         self.regenerate_primary_file( dataset )
     def regenerate_primary_file(self,dataset):
         """
-        cannot do this until we are setting metadata 
+        cannot do this until we are setting metadata
         """
         annotations = "dbNSFP Annotations: %s\n" % ','.join(dataset.metadata.annotation)
         f = open(dataset.file_name,'a')
@@ -366,7 +366,7 @@ class SnpSiftDbNSFP( Text ):
                             lines = buf.splitlines()
                             headers = lines[0].split('\t')
                             dataset.metadata.annotation = headers[4:]
-                        except Exception,e:        
+                        except Exception,e:
                             log.warn("set_meta fname: %s  %s" % (fname,str(e)))
                         finally:
                             fh.close()
@@ -376,3 +376,27 @@ class SnpSiftDbNSFP( Text ):
         except Exception,e:
             log.warn("set_meta fname: %s  %s" % (dataset.file_name if dataset and dataset.file_name else 'Unkwown',str(e)))
 
+
+class Hmmer3( Text ):
+    file_ext = "hmm"
+
+    def set_peek(self, dataset, is_multi_byte=False):
+        if not dataset.dataset.purged:
+            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = "HMMER3 Database"
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disc'
+
+    def sniff(self, filename):
+        """HMMER3 files start with HMMER3/f
+        """
+        with open(filename, 'r') as handle:
+            return handle.read(8) == 'HMMER3/f'
+        return False
+
+    def display_peek(self, dataset):
+        try:
+            return dataset.peek
+        except:
+            return "HMMER3 database (%s)" % ( nice_size( dataset.get_size() ) )

From 7ef0d4e6eb48e4ee91a83a93753afa01597a6b6f Mon Sep 17 00:00:00 2001
From: Eric Rasche <rasche.eric@yandex.ru>
Date: Tue, 5 May 2015 14:42:25 -0500
Subject: [PATCH 2/9] Move msa datatypes into separate file

---
 config/datatypes_conf.xml.sample |  5 ++++-
 lib/galaxy/datatypes/msa.py      | 31 +++++++++++++++++++++++++++++++
 lib/galaxy/datatypes/registry.py |  1 +
 lib/galaxy/datatypes/text.py     | 25 -------------------------
 4 files changed, 36 insertions(+), 26 deletions(-)
 create mode 100644 lib/galaxy/datatypes/msa.py

diff --git a/config/datatypes_conf.xml.sample b/config/datatypes_conf.xml.sample
index 7aa7d5d2710..e1df494d3ed 100644
--- a/config/datatypes_conf.xml.sample
+++ b/config/datatypes_conf.xml.sample
@@ -272,7 +272,8 @@
     <!-- Excel datatypes -->
     <datatype extension="xlsx" type="galaxy.datatypes.binary:Xlsx" display_in_upload="true" />
     <!-- MSA Datatypes -->
-    <datatype extension="hmm" type="galaxy.datatypes.text:Hmmer3" display_in_upload="true" />
+    <datatype extension="hmm" type="galaxy.datatypes.msa:Hmmer3" display_in_upload="true" />
+    <datatype extension="stockholm" type="galaxy.datatypes.msa:Stockholm_1_0" display_in_upload="True" />
   </registration>
   <sniffers>
     <!--
@@ -335,6 +336,8 @@
     <sniffer type="galaxy.datatypes.images:Xpm"/>
     <sniffer type="galaxy.datatypes.images:Eps"/>
     <sniffer type="galaxy.datatypes.images:Rast"/>
+    <sniffer type="galaxy.datatypes.msa:Stockholm_1_0" />
+    <sniffer type="galaxy.datatypes.msa:Hmmer3" />
     <!--
     Keep this commented until the sniff method in the assembly.py
     module is fixed to not read the entire file.
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
new file mode 100644
index 00000000000..6f8bb178a52
--- /dev/null
+++ b/lib/galaxy/datatypes/msa.py
@@ -0,0 +1,31 @@
+from galaxy.datatypes.data import Text
+from galaxy.datatypes.data import get_file_peek
+from galaxy.datatypes.data import nice_size
+
+import logging
+log = logging.getLogger(__name__)
+
+
+class Hmmer3( Text ):
+    file_ext = "hmm"
+
+    def set_peek(self, dataset, is_multi_byte=False):
+        if not dataset.dataset.purged:
+            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = "HMMER3 Database"
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disc'
+
+    def sniff(self, filename):
+        """HMMER3 files start with HMMER3/f
+        """
+        with open(filename, 'r') as handle:
+            return handle.read(8) == 'HMMER3/f'
+        return False
+
+    def display_peek(self, dataset):
+        try:
+            return dataset.peek
+        except:
+            return "HMMER3 database (%s)" % ( nice_size( dataset.get_size() ) )
diff --git a/lib/galaxy/datatypes/registry.py b/lib/galaxy/datatypes/registry.py
index 856096292c4..d6211c89021 100644
--- a/lib/galaxy/datatypes/registry.py
+++ b/lib/galaxy/datatypes/registry.py
@@ -23,6 +23,7 @@ import assembly
 import ngsindex
 import graph
 import text
+import msa
 import galaxy.util
 from galaxy.util.odict import odict
 from display_applications.application import DisplayApplication
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 8069a1f2daf..a3e3efd1828 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -375,28 +375,3 @@ class SnpSiftDbNSFP( Text ):
             self.regenerate_primary_file(dataset)
         except Exception,e:
             log.warn("set_meta fname: %s  %s" % (dataset.file_name if dataset and dataset.file_name else 'Unkwown',str(e)))
-
-
-class Hmmer3( Text ):
-    file_ext = "hmm"
-
-    def set_peek(self, dataset, is_multi_byte=False):
-        if not dataset.dataset.purged:
-            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
-            dataset.blurb = "HMMER3 Database"
-        else:
-            dataset.peek = 'file does not exist'
-            dataset.blurb = 'file purged from disc'
-
-    def sniff(self, filename):
-        """HMMER3 files start with HMMER3/f
-        """
-        with open(filename, 'r') as handle:
-            return handle.read(8) == 'HMMER3/f'
-        return False
-
-    def display_peek(self, dataset):
-        try:
-            return dataset.peek
-        except:
-            return "HMMER3 database (%s)" % ( nice_size( dataset.get_size() ) )

From 92ff779f050e7e6f74c9da89784f8d4a7ad9c3e1 Mon Sep 17 00:00:00 2001
From: Bjoern Gruening <bjoern.gruening@gmail.com>
Date: Tue, 5 May 2015 14:46:02 -0500
Subject: [PATCH 3/9] Imported stockholm from @bgruening

---
 lib/galaxy/datatypes/msa.py | 105 ++++++++++++++++++++++++++++++++++++
 1 file changed, 105 insertions(+)

diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 6f8bb178a52..8ecbdf53ed5 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -1,11 +1,33 @@
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.data import get_file_peek
 from galaxy.datatypes.data import nice_size
+from galaxy.datatypes.metadata import MetadataElement
+import subprocess
+import os
+
 
 import logging
 log = logging.getLogger(__name__)
 
 
+def count_special_lines( word, filename, invert=False ):
+    """
+        searching for special 'words' using the grep tool
+        grep is used to speed up the searching and counting
+        The number of hits is returned.
+    """
+    try:
+        cmd = ["grep", "-c"]
+        if invert:
+            cmd.append('-v')
+        cmd.extend([word, filename])
+        out = subprocess.Popen(cmd, stdout=subprocess.PIPE)
+        return int(out.communicate()[0].split()[0])
+    except:
+        pass
+    return 0
+
+
 class Hmmer3( Text ):
     file_ext = "hmm"
 
@@ -29,3 +51,86 @@ class Hmmer3( Text ):
             return dataset.peek
         except:
             return "HMMER3 database (%s)" % ( nice_size( dataset.get_size() ) )
+
+
+class Stockholm_1_0( Text ):
+    file_ext = "stockholm"
+
+    MetadataElement( name="number_of_alignments", default=0, desc="Number of multiple alignments", readonly=True, visible=True, optional=True, no_value=0 )
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        if not dataset.dataset.purged:
+            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            if (dataset.metadata.number_of_models == 1):
+                dataset.blurb = "1 alignment"
+            else:
+                dataset.blurb = "%s alignments" % dataset.metadata.number_of_models
+            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disc'
+
+    def sniff( self, filename ):
+        if count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', filename) > 0:
+            return True
+        else:
+            return False
+
+    def set_meta( self, dataset, **kwd ):
+        """
+
+        Set the number of models in dataset.
+        """
+        dataset.metadata.number_of_models = count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', dataset.file_name)
+
+    def split( cls, input_datasets, subdir_generator_function, split_params):
+        """
+
+        Split the input files by model records.
+        """
+        if split_params is None:
+            return None
+
+        if len(input_datasets) > 1:
+            raise Exception("STOCKHOLM-file splitting does not support multiple files")
+        input_files = [ds.file_name for ds in input_datasets]
+
+        chunk_size = None
+        if split_params['split_mode'] == 'number_of_parts':
+            raise Exception('Split mode "%s" is currently not implemented for STOCKHOLM-files.' % split_params['split_mode'])
+        elif split_params['split_mode'] == 'to_size':
+            chunk_size = int(split_params['split_size'])
+        else:
+            raise Exception('Unsupported split mode %s' % split_params['split_mode'])
+
+        def _read_stockholm_records( filename ):
+            lines = []
+            with open(filename) as handle:
+                for line in handle:
+                    lines.append( line )
+                    if line.strip() == '//':
+                        yield lines
+                        lines = []
+
+        def _write_part_stockholm_file( accumulated_lines ):
+            part_dir = subdir_generator_function()
+            part_path = os.path.join( part_dir, os.path.basename( input_files[0] ) )
+            part_file = open( part_path, 'w' )
+            part_file.writelines( accumulated_lines )
+            part_file.close()
+
+        try:
+
+            stockholm_records = _read_stockholm_records( input_files[0] )
+            stockholm_lines_accumulated = []
+            for counter, stockholm_record in enumerate( stockholm_records, start=1):
+                stockholm_lines_accumulated.extend( stockholm_record )
+                if counter % chunk_size == 0:
+                    _write_part_stockholm_file( stockholm_lines_accumulated )
+                    stockholm_lines_accumulated = []
+            if stockholm_lines_accumulated:
+                _write_part_stockholm_file( stockholm_lines_accumulated )
+        except Exception, e:
+            log.error('Unable to split files: %s' % str(e))
+            raise
+    split = classmethod(split)

From c1840a46b55db4446f46b48a67c11db76a5a80f5 Mon Sep 17 00:00:00 2001
From: Eric Rasche <rasche.eric@yandex.ru>
Date: Tue, 5 May 2015 14:54:15 -0500
Subject: [PATCH 4/9] Bump version of hmm format

---
 config/datatypes_conf.xml.sample | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/config/datatypes_conf.xml.sample b/config/datatypes_conf.xml.sample
index e1df494d3ed..c25e052d4d9 100644
--- a/config/datatypes_conf.xml.sample
+++ b/config/datatypes_conf.xml.sample
@@ -272,7 +272,7 @@
     <!-- Excel datatypes -->
     <datatype extension="xlsx" type="galaxy.datatypes.binary:Xlsx" display_in_upload="true" />
     <!-- MSA Datatypes -->
-    <datatype extension="hmm" type="galaxy.datatypes.msa:Hmmer3" display_in_upload="true" />
+    <datatype extension="hmm3" type="galaxy.datatypes.msa:Hmmer3" display_in_upload="true" />
     <datatype extension="stockholm" type="galaxy.datatypes.msa:Stockholm_1_0" display_in_upload="True" />
   </registration>
   <sniffers>

From ec363b2b39dd7b98eb1afe0c97f741f2344cf445 Mon Sep 17 00:00:00 2001
From: Eric Rasche <rasche.eric@yandex.ru>
Date: Tue, 5 May 2015 15:03:41 -0500
Subject: [PATCH 5/9] Add in hmmer2 datatypes

---
 config/datatypes_conf.xml.sample |  2 ++
 lib/galaxy/datatypes/msa.py      | 29 +++++++++++++++++++++--------
 2 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/config/datatypes_conf.xml.sample b/config/datatypes_conf.xml.sample
index c25e052d4d9..369f24e33ad 100644
--- a/config/datatypes_conf.xml.sample
+++ b/config/datatypes_conf.xml.sample
@@ -272,6 +272,7 @@
     <!-- Excel datatypes -->
     <datatype extension="xlsx" type="galaxy.datatypes.binary:Xlsx" display_in_upload="true" />
     <!-- MSA Datatypes -->
+    <datatype extension="hmm2" type="galaxy.datatypes.msa:Hmmer2" display_in_upload="true" />
     <datatype extension="hmm3" type="galaxy.datatypes.msa:Hmmer3" display_in_upload="true" />
     <datatype extension="stockholm" type="galaxy.datatypes.msa:Stockholm_1_0" display_in_upload="True" />
   </registration>
@@ -337,6 +338,7 @@
     <sniffer type="galaxy.datatypes.images:Eps"/>
     <sniffer type="galaxy.datatypes.images:Rast"/>
     <sniffer type="galaxy.datatypes.msa:Stockholm_1_0" />
+    <sniffer type="galaxy.datatypes.msa:Hmmer2" />
     <sniffer type="galaxy.datatypes.msa:Hmmer3" />
     <!--
     Keep this commented until the sniff method in the assembly.py
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 8ecbdf53ed5..34cdf5268d1 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -28,17 +28,36 @@ def count_special_lines( word, filename, invert=False ):
     return 0
 
 
-class Hmmer3( Text ):
+class Hmmer( Text ):
     file_ext = "hmm"
 
     def set_peek(self, dataset, is_multi_byte=False):
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
-            dataset.blurb = "HMMER3 Database"
+            dataset.blurb = "HMMER Database"
         else:
             dataset.peek = 'file does not exist'
             dataset.blurb = 'file purged from disc'
 
+    def display_peek(self, dataset):
+        try:
+            return dataset.peek
+        except:
+            return "HMMER database (%s)" % ( nice_size( dataset.get_size() ) )
+
+
+class Hmmer2( Hmmer ):
+
+    def sniff(self, filename):
+        """HMMER2 files start with HMMER2.0
+        """
+        with open(filename, 'r') as handle:
+            return handle.read(8) == 'HMMER2.0'
+        return False
+
+
+class Hmmer3( Hmmer ):
+
     def sniff(self, filename):
         """HMMER3 files start with HMMER3/f
         """
@@ -46,12 +65,6 @@ class Hmmer3( Text ):
             return handle.read(8) == 'HMMER3/f'
         return False
 
-    def display_peek(self, dataset):
-        try:
-            return dataset.peek
-        except:
-            return "HMMER3 database (%s)" % ( nice_size( dataset.get_size() ) )
-
 
 class Stockholm_1_0( Text ):
     file_ext = "stockholm"

From 5037c4de031c72fac50be4ec3de63877dd5138f7 Mon Sep 17 00:00:00 2001
From: Eric Rasche <rasche.eric@yandex.ru>
Date: Tue, 5 May 2015 15:16:12 -0500
Subject: [PATCH 6/9] Refactor count_special

---
 lib/galaxy/datatypes/msa.py               | 24 +++--------------------
 lib/galaxy/datatypes/util/generic_util.py | 19 ++++++++++++++++++
 2 files changed, 22 insertions(+), 21 deletions(-)
 create mode 100644 lib/galaxy/datatypes/util/generic_util.py

diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 34cdf5268d1..8d8248c5bc5 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -2,7 +2,7 @@ from galaxy.datatypes.data import Text
 from galaxy.datatypes.data import get_file_peek
 from galaxy.datatypes.data import nice_size
 from galaxy.datatypes.metadata import MetadataElement
-import subprocess
+from galaxy.datatypes.util import generic_util
 import os
 
 
@@ -10,24 +10,6 @@ import logging
 log = logging.getLogger(__name__)
 
 
-def count_special_lines( word, filename, invert=False ):
-    """
-        searching for special 'words' using the grep tool
-        grep is used to speed up the searching and counting
-        The number of hits is returned.
-    """
-    try:
-        cmd = ["grep", "-c"]
-        if invert:
-            cmd.append('-v')
-        cmd.extend([word, filename])
-        out = subprocess.Popen(cmd, stdout=subprocess.PIPE)
-        return int(out.communicate()[0].split()[0])
-    except:
-        pass
-    return 0
-
-
 class Hmmer( Text ):
     file_ext = "hmm"
 
@@ -84,7 +66,7 @@ class Stockholm_1_0( Text ):
             dataset.blurb = 'file purged from disc'
 
     def sniff( self, filename ):
-        if count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', filename) > 0:
+        if generic_util.count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', filename) > 0:
             return True
         else:
             return False
@@ -94,7 +76,7 @@ class Stockholm_1_0( Text ):
 
         Set the number of models in dataset.
         """
-        dataset.metadata.number_of_models = count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', dataset.file_name)
+        dataset.metadata.number_of_models = generic_util.count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', dataset.file_name)
 
     def split( cls, input_datasets, subdir_generator_function, split_params):
         """
diff --git a/lib/galaxy/datatypes/util/generic_util.py b/lib/galaxy/datatypes/util/generic_util.py
new file mode 100644
index 00000000000..49bfd007a89
--- /dev/null
+++ b/lib/galaxy/datatypes/util/generic_util.py
@@ -0,0 +1,19 @@
+import subprocess
+
+
+def count_special_lines( word, filename, invert=False ):
+    """
+        searching for special 'words' using the grep tool
+        grep is used to speed up the searching and counting
+        The number of hits is returned.
+    """
+    try:
+        cmd = ["grep", "-c"]
+        if invert:
+            cmd.append('-v')
+        cmd.extend([word, filename])
+        out = subprocess.Popen(cmd, stdout=subprocess.PIPE)
+        return int(out.communicate()[0].split()[0])
+    except:
+        pass
+    return 0

From d1c1af3bff2fa8959c09cdd26523dcf9c0e839a7 Mon Sep 17 00:00:00 2001
From: Eric Rasche <rasche.eric@yandex.ru>
Date: Tue, 5 May 2015 15:16:29 -0500
Subject: [PATCH 7/9] Move ddatatypes upwards of images

---
 config/datatypes_conf.xml.sample | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/config/datatypes_conf.xml.sample b/config/datatypes_conf.xml.sample
index 369f24e33ad..ca29863d1c2 100644
--- a/config/datatypes_conf.xml.sample
+++ b/config/datatypes_conf.xml.sample
@@ -320,6 +320,8 @@
     <sniffer type="galaxy.datatypes.text:Ipynb"/>
     <sniffer type="galaxy.datatypes.text:Json"/>
     <sniffer type="galaxy.datatypes.sequence:RNADotPlotMatrix"/>
+    <sniffer type="galaxy.datatypes.msa:Hmmer2" />
+    <sniffer type="galaxy.datatypes.msa:Hmmer3" />
     <sniffer type="galaxy.datatypes.images:Jpg"/>
     <sniffer type="galaxy.datatypes.images:Png"/>
     <sniffer type="galaxy.datatypes.images:Tiff"/>
@@ -338,8 +340,6 @@
     <sniffer type="galaxy.datatypes.images:Eps"/>
     <sniffer type="galaxy.datatypes.images:Rast"/>
     <sniffer type="galaxy.datatypes.msa:Stockholm_1_0" />
-    <sniffer type="galaxy.datatypes.msa:Hmmer2" />
-    <sniffer type="galaxy.datatypes.msa:Hmmer3" />
     <!--
     Keep this commented until the sniff method in the assembly.py
     module is fixed to not read the entire file.

From 791785c1a52159e0d9ff44f5c252e6c3ea0325d4 Mon Sep 17 00:00:00 2001
From: Eric Rasche <rasche.eric@yandex.ru>
Date: Wed, 6 May 2015 09:56:41 -0500
Subject: [PATCH 8/9] Move stockholm as well

---
 config/datatypes_conf.xml.sample |  2 +-
 lib/galaxy/datatypes/msa.py      | 38 +++++++++++++++++++++++++++++++-
 2 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/config/datatypes_conf.xml.sample b/config/datatypes_conf.xml.sample
index ca29863d1c2..cf744de21bc 100644
--- a/config/datatypes_conf.xml.sample
+++ b/config/datatypes_conf.xml.sample
@@ -322,6 +322,7 @@
     <sniffer type="galaxy.datatypes.sequence:RNADotPlotMatrix"/>
     <sniffer type="galaxy.datatypes.msa:Hmmer2" />
     <sniffer type="galaxy.datatypes.msa:Hmmer3" />
+    <sniffer type="galaxy.datatypes.msa:Stockholm_1_0" />
     <sniffer type="galaxy.datatypes.images:Jpg"/>
     <sniffer type="galaxy.datatypes.images:Png"/>
     <sniffer type="galaxy.datatypes.images:Tiff"/>
@@ -339,7 +340,6 @@
     <sniffer type="galaxy.datatypes.images:Xpm"/>
     <sniffer type="galaxy.datatypes.images:Eps"/>
     <sniffer type="galaxy.datatypes.images:Rast"/>
-    <sniffer type="galaxy.datatypes.msa:Stockholm_1_0" />
     <!--
     Keep this commented until the sniff method in the assembly.py
     module is fixed to not read the entire file.
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 8d8248c5bc5..b001a959f12 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -1,4 +1,4 @@
-from galaxy.datatypes.data import Text
+from galaxy.datatypes.data import Text, Binary
 from galaxy.datatypes.data import get_file_peek
 from galaxy.datatypes.data import nice_size
 from galaxy.datatypes.metadata import MetadataElement
@@ -48,6 +48,42 @@ class Hmmer3( Hmmer ):
         return False
 
 
+class HmmerPress( Binary ):
+    """Class for hmmpress database files."""
+    file_ext = 'hmmpress'
+    allow_datatype_change = False
+    composite_type = 'basic'
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text."""
+        if not dataset.dataset.purged:
+            dataset.peek = "HMMER Binary database"
+            dataset.blurb = "HMMER Binary database"
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+    def display_peek( self, dataset ):
+        """Create HTML content, used for displaying peek."""
+        try:
+            return dataset.peek
+        except:
+            return "HMMER3 database (multiple files)"
+
+    def __init__(self, **kwd):
+        Binary.__init__(self, **kwd)
+        # Binary model
+        self.add_composite_file('model.hmm.h3m', is_binary=True)
+        # SSI index for binary model
+        self.add_composite_file('model.hmm.h3i', is_binary=True)
+        # Profiles (MSV part)
+        self.add_composite_file('model.hmm.h3f', is_binary=True)
+        # Profiles (remained)
+        self.add_composite_file('model.hmm.h3p', is_binary=True)
+
+Binary.register_unsniffable_binary_ext("hmmpress")
+
+
 class Stockholm_1_0( Text ):
     file_ext = "stockholm"
 

From b0b43919be7254e013d3abdccfc325a458adc2f7 Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Wed, 6 May 2015 19:26:55 -0400
Subject: [PATCH 9/9] Fix import problem with msa.py.

---
 lib/galaxy/datatypes/msa.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index b001a959f12..011de5a720f 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -1,4 +1,5 @@
-from galaxy.datatypes.data import Text, Binary
+from galaxy.datatypes.data import Text
+from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import get_file_peek
 from galaxy.datatypes.data import nice_size
 from galaxy.datatypes.metadata import MetadataElement