Merge pull request #12199 from gallardoalba/add_bref3

[21.05] Add bref3 datatype

lib/galaxy/config/sample/datatypes_conf.xml.sample

@@ -272,6 +272,7 @@
     <datatype extension="mzml" type="galaxy.datatypes.proteomics:MzML" mimetype="application/xml" display_in_upload="true"/>
     <datatype extension="nmrml" type="galaxy.datatypes.proteomics:NmrML" mimetype="application/xml" display_in_upload="true" description="nmrML is an open mark-up language for NMR data." description_url="http://nmrml.org/schema/"/>
     <datatype extension="meryldb" type="galaxy.datatypes.binary:Meryldb" subclass="true" display_in_upload="true" description="MerylDB is a tar.gz archive containing 64 binaries + 64 indexes." />
+    <datatype extension="bref3" type="galaxy.datatypes.binary:Bref3" display_in_upload="true" description="Bref3 format is a binary format for storing phased, non-missing genotypes for a list of samples. More information in https://faculty.washington.edu/browning/beagle/bref3.14May18.pdf" />
     <datatype extension="mgf" type="galaxy.datatypes.proteomics:Mgf" display_in_upload="true"/>
     <datatype extension="wiff" type="galaxy.datatypes.proteomics:Wiff" display_in_upload="true"/>
     <datatype extension="mzxml" type="galaxy.datatypes.proteomics:MzXML" mimetype="application/xml" display_in_upload="true"/>
@@ -935,6 +936,7 @@
     <sniffer type="galaxy.datatypes.binary:Fast5ArchiveBz2"/>
     <sniffer type="galaxy.datatypes.binary:Fast5Archive"/>
     <sniffer type="galaxy.datatypes.binary:Meryldb" />
+    <sniffer type="galaxy.datatypes.binary:Bref3" />
     <sniffer type="galaxy.datatypes.binary:PostgresqlArchive"/>
     <sniffer type="galaxy.datatypes.binary:ICM"/>
     <sniffer type="galaxy.datatypes.binary:Idat"/>

lib/galaxy/datatypes/binary.py

@@ -236,6 +236,33 @@ class Meryldb(CompressedArchive):
         return False
 
 
+class Bref3(Binary):
+    """Bref3 format is a binary format for storing phased, non-missing genotypes for a list of samples."""
+
+    file_ext = "bref3"
+
+    def __init__(self, **kwd):
+        super().__init__(**kwd)
+        self._magic = binascii.unhexlify("7a8874f400156272")
+
+    def sniff_prefix(self, sniff_prefix):
+        return sniff_prefix.startswith_bytes(self._magic)
+
+    def set_peek(self, dataset, is_multi_byte=False):
+        if not dataset.dataset.purged:
+            dataset.peek = "Binary bref3 file"
+            dataset.blurb = nice_size(dataset.get_size())
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+    def display_peek(self, dataset):
+        try:
+            return dataset.peek
+        except Exception:
+            return f"Binary bref3 file ({nice_size(dataset.get_size())})"
+
+
 class DynamicCompressedArchive(CompressedArchive):
 
     def matches_any(self, target_datatypes):