June 2010 - galaxy-commits - lists.galaxyproject.org

galaxy-dist commit 37f4420ba3fc: Bug fix for handling 'spaces to tab' for non-binary composite datatype files.
by commits-noreply＠bitbucket.org 08 Jun '10

08 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Dan Blankenberg <dan(a)bx.psu.edu> # Date 1275939260 14400 # Node ID 37f4420ba3fcf9eb0fd097cf812ad91cc2824f99 # Parent 7de1adaf5628e04e2da0d948f03d08cb5ce5d7f3 Bug fix for handling 'spaces to tab' for non-binary composite datatype files. Add upload tests for testing 'space to tab' when uploading composite and non-composite datatypes. --- a/test/functional/test_get_data.py +++ b/test/functional/test_get_data.py @@ -4,14 +4,16 @@ from galaxy.model.mapping import context from base.twilltestcase import TwillTestCase class UploadData( TwillTestCase ): - def test_0005_upload_file( self ): - """Test uploading 1.bed, NOT setting the file format""" + def test_0000_setup_upload_tests( self ): + """Configuring upload tests, setting admin_user""" self.logout() self.login( email='test(a)bx.psu.edu' ) global admin_user admin_user = sa_session.query( galaxy.model.User ) \ .filter( galaxy.model.User.table.c.email=='test(a)bx.psu.edu' ) \ .one() + def test_0005_upload_file( self ): + """Test uploading 1.bed, NOT setting the file format""" history = sa_session.query( galaxy.model.History ) \ .filter( and_( galaxy.model.History.table.c.deleted==False, galaxy.model.History.table.c.user_id==admin_user.id ) ) \ @@ -25,6 +27,21 @@ class UploadData( TwillTestCase ): self.verify_dataset_correctness( '1.bed', hid=str( hda.hid ) ) self.check_history_for_string( "<th>1.Chrom</th><th>2.Start</th><th>3.End</th>" ) self.delete_history( id=self.security.encode_id( history.id ) ) + def test_0006_upload_file( self ): + """Test uploading 1.bed.spaces, with space to tab selected, NOT setting the file format""" + history = sa_session.query( galaxy.model.History ) \ + .filter( and_( galaxy.model.History.table.c.deleted==False, + galaxy.model.History.table.c.user_id==admin_user.id ) ) \ + .order_by( desc( galaxy.model.History.table.c.create_time ) ) \ + .first() + self.upload_file( '1.bed.spaces', space_to_tab = True ) + hda = sa_session.query( galaxy.model.HistoryDatasetAssociation ) \ + .order_by( desc( galaxy.model.HistoryDatasetAssociation.table.c.create_time ) ) \ + .first() + assert hda is not None, "Problem retrieving hda from database" + self.verify_dataset_correctness( '1.bed', hid=str( hda.hid ) ) + self.check_history_for_string( "<th>1.Chrom</th><th>2.Start</th><th>3.End</th>" ) + self.delete_history( id=self.security.encode_id( history.id ) ) def test_0010_upload_file( self ): """Test uploading 4.bed.gz, manually setting the file format""" self.check_history_for_string( 'Your history is empty' ) @@ -174,15 +191,36 @@ class UploadData( TwillTestCase ): .order_by( desc( galaxy.model.History.table.c.create_time ) ) \ .first() # lped data types include a ped_file and a map_file ( which is binary ) - self.upload_composite_datatype_file( 'lped', ped_file='tinywga.ped', map_file='tinywga.map', base_name='rgenetics' ) + self.upload_file( None, ftype='lped', metadata = [ { 'name':'base_name', 'value':'rgenetics' } ], composite_data = [ { 'name':'ped_file', 'value':'tinywga.ped' }, { 'name':'map_file', 'value':'tinywga.map'} ] ) # Get the latest hid for testing hda = sa_session.query( galaxy.model.HistoryDatasetAssociation ) \ .order_by( desc( galaxy.model.HistoryDatasetAssociation.table.c.create_time ) ) \ .first() assert hda is not None, "Problem retrieving hda from database" # We'll test against the resulting ped file and map file for correctness - self.verify_composite_datatype_file_content( 'rgenetics.ped', str( hda.id ) ) - self.verify_composite_datatype_file_content( 'rgenetics.map', str( hda.id ) ) + self.verify_composite_datatype_file_content( 'tinywga.ped', str( hda.id ), base_name = 'rgenetics.ped' ) + self.verify_composite_datatype_file_content( 'tinywga.map', str( hda.id ), base_name = 'rgenetics.map' ) + self.check_history_for_string( "rgenetics" ) + self.delete_history( id=self.security.encode_id( history.id ) ) + def test_0056_upload_file( self ): + """Test uploading lped composite datatype file, manually setting the file format, and using space to tab on one file (tinywga.ped)""" + # Logged in as admin_user + self.check_history_for_string( 'Your history is empty' ) + history = sa_session.query( galaxy.model.History ) \ + .filter( and_( galaxy.model.History.table.c.deleted==False, + galaxy.model.History.table.c.user_id==admin_user.id ) ) \ + .order_by( desc( galaxy.model.History.table.c.create_time ) ) \ + .first() + # lped data types include a ped_file and a map_file ( which is binary ) + self.upload_file( None, ftype='lped', metadata = [ { 'name':'base_name', 'value':'rgenetics' } ], composite_data = [ { 'name':'ped_file', 'value':'tinywga.ped', 'space_to_tab':True }, { 'name':'map_file', 'value':'tinywga.map'} ] ) + # Get the latest hid for testing + hda = sa_session.query( galaxy.model.HistoryDatasetAssociation ) \ + .order_by( desc( galaxy.model.HistoryDatasetAssociation.table.c.create_time ) ) \ + .first() + assert hda is not None, "Problem retrieving hda from database" + # We'll test against the resulting ped file and map file for correctness + self.verify_composite_datatype_file_content( 'tinywga.ped.space_to_tab', str( hda.id ), base_name = 'rgenetics.ped' ) + self.verify_composite_datatype_file_content( 'tinywga.map', str( hda.id ), base_name = 'rgenetics.map' ) self.check_history_for_string( "rgenetics" ) self.delete_history( id=self.security.encode_id( history.id ) ) def test_0060_upload_file( self ): @@ -195,16 +233,16 @@ class UploadData( TwillTestCase ): .order_by( desc( galaxy.model.History.table.c.create_time ) ) \ .first() # pbed data types include a bim_file, a bed_file and a fam_file - self.upload_composite_datatype_file( 'pbed', bim_file='tinywga.bim', bed_file='tinywga.bed', fam_file='tinywga.fam', base_name='rgenetics' ) + self.upload_file( None, ftype='pbed', metadata = [ { 'name':'base_name', 'value':'rgenetics' } ], composite_data = [ { 'name':'bim_file', 'value':'tinywga.bim' }, { 'name':'bed_file', 'value':'tinywga.bed'}, { 'name':'fam_file', 'value':'tinywga.fam' } ] ) # Get the latest hid for testing hda = sa_session.query( galaxy.model.HistoryDatasetAssociation ) \ .order_by( desc( galaxy.model.HistoryDatasetAssociation.table.c.create_time ) ) \ .first() assert hda is not None, "Problem retrieving hda from database" # We'll test against the resulting ped file and map file for correctness - self.verify_composite_datatype_file_content( 'rgenetics.bim', str( hda.id ) ) - self.verify_composite_datatype_file_content( 'rgenetics.bed', str( hda.id ) ) - self.verify_composite_datatype_file_content( 'rgenetics.fam', str( hda.id ) ) + self.verify_composite_datatype_file_content( 'tinywga.bim', str( hda.id ), base_name = 'rgenetics.bim' ) + self.verify_composite_datatype_file_content( 'tinywga.bed', str( hda.id ), base_name = 'rgenetics.bed' ) + self.verify_composite_datatype_file_content( 'tinywga.fam', str( hda.id ), base_name = 'rgenetics.fam' ) self.check_history_for_string( "rgenetics" ) self.delete_history( id=self.security.encode_id( history.id ) ) def test_0065_upload_file( self ): --- /dev/null +++ b/test-data/tinywga.ped.space_to_tab @@ -0,0 +1,40 @@ +101 1 3 2 2 2 2 2 4 2 1 3 3 3 3 3 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 4 4 1 1 2 2 2 2 3 1 3 1 2 1 0 0 2 2 1 3 3 1 1 3 +101 2 0 0 2 1 2 2 4 2 1 3 3 3 3 3 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 4 4 1 1 2 2 2 2 3 1 3 1 2 1 3 3 2 2 1 3 3 1 1 3 +101 3 0 0 1 1 2 2 4 4 1 3 3 3 3 3 2 2 3 3 2 2 1 1 2 2 2 2 4 4 1 1 4 4 1 1 2 2 2 2 1 1 3 1 1 1 1 3 2 4 3 3 1 1 3 3 +105 1 3 2 2 2 2 2 4 2 3 3 3 3 3 1 2 2 3 3 1 1 3 3 2 2 2 2 2 2 3 3 4 4 1 1 2 2 2 2 3 1 1 1 2 1 0 0 2 2 1 1 3 3 1 1 +105 2 0 0 2 1 2 2 4 4 3 3 3 3 3 1 2 2 1 3 1 2 3 1 2 2 4 2 2 4 3 1 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +105 3 0 0 1 1 4 2 2 2 3 3 3 3 3 1 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 3 1 1 1 2 1 3 3 2 4 1 3 3 1 1 3 +112 1 3 2 1 2 4 2 2 2 3 3 1 1 1 1 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +112 2 0 0 2 1 2 2 2 2 3 3 1 1 1 1 2 2 3 3 1 1 3 3 2 2 2 2 2 2 3 3 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +112 3 0 0 1 1 4 2 4 2 3 3 1 3 3 1 2 2 1 3 2 2 1 1 2 2 4 2 4 4 1 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +117 1 3 2 2 2 2 2 4 2 3 3 3 3 3 3 4 2 1 1 2 2 1 1 2 2 4 2 2 4 3 1 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 2 1 1 3 3 1 1 +117 2 0 0 2 1 2 2 4 4 1 3 3 3 3 3 2 2 1 3 2 2 1 1 2 2 4 2 4 4 1 1 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +117 3 0 0 1 1 2 2 4 2 3 3 3 3 3 3 4 2 1 1 2 2 1 1 2 2 4 2 2 4 3 1 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +12 1 3 2 1 2 2 2 4 4 1 3 3 3 3 3 2 2 3 3 2 2 1 1 2 2 2 2 4 4 1 1 4 4 1 1 2 2 2 2 1 1 3 1 1 1 3 3 2 4 3 3 1 1 3 3 +12 2 0 0 2 1 2 2 4 4 1 3 3 3 3 3 2 2 3 3 2 2 1 1 2 2 2 2 4 4 1 1 4 4 1 1 2 2 2 2 1 1 3 1 1 1 3 3 2 4 3 3 1 1 3 3 +12 3 0 0 1 1 2 2 4 2 1 3 1 3 3 1 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 4 4 1 1 2 2 2 2 1 1 3 1 1 1 3 3 2 4 3 3 1 1 3 3 +13 1 3 2 1 2 4 2 4 2 1 3 3 3 3 1 2 2 3 3 2 2 1 1 2 2 2 2 4 4 1 1 3 4 1 1 2 2 4 2 1 1 3 1 1 1 3 3 2 4 3 3 1 1 3 3 +13 2 0 0 2 1 4 2 2 2 3 3 1 3 1 1 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 0 0 0 0 3 3 1 1 3 3 +13 3 0 0 1 1 2 2 4 4 1 3 3 3 3 3 2 2 1 3 1 2 3 1 2 2 2 2 2 4 3 1 4 4 3 1 2 2 2 2 1 1 3 1 1 1 3 3 2 2 3 3 1 1 3 3 +1334 1 10 11 1 2 2 2 4 2 3 3 1 3 3 1 2 2 1 3 1 2 3 1 4 2 4 2 2 4 3 1 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1334 10 0 0 1 1 4 2 4 2 3 3 1 3 3 1 2 2 1 3 2 2 1 1 4 2 4 2 4 4 1 1 3 4 1 1 2 2 4 2 3 1 1 1 2 1 3 3 2 4 1 3 3 1 1 3 +1334 11 0 0 2 1 2 2 2 2 3 3 1 1 1 1 2 2 3 3 1 1 3 3 2 2 2 2 2 2 3 3 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1334 12 0 0 1 1 4 2 2 2 3 3 1 3 1 1 2 2 3 3 2 2 1 1 2 2 4 2 4 4 1 1 3 4 1 1 2 2 4 2 3 1 1 1 2 1 3 3 2 4 1 3 3 1 1 3 +1334 13 0 0 2 1 4 2 4 2 3 3 1 3 3 1 4 2 1 3 2 2 1 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +1334 2 12 13 2 2 4 4 2 2 3 3 1 3 1 1 2 2 3 3 2 2 1 1 2 2 2 2 4 4 1 1 3 3 1 1 2 2 4 4 3 1 1 1 2 1 3 3 2 4 1 3 3 1 1 3 +1340 1 9 10 1 2 4 2 4 2 3 3 1 3 3 1 2 2 1 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 3 1 2 2 4 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1340 10 0 0 2 1 4 2 4 2 3 3 1 3 3 1 2 2 1 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 3 1 2 2 4 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1340 11 0 0 1 1 4 2 4 2 3 3 1 3 3 1 4 2 1 3 2 2 1 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +1340 12 0 0 2 1 2 2 4 2 3 3 1 3 3 1 2 2 1 3 1 2 3 1 4 2 4 2 2 4 3 1 4 4 1 1 4 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +1340 2 11 12 2 2 2 2 4 2 3 3 1 3 3 1 4 2 1 3 1 2 3 1 2 2 2 2 2 2 3 3 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +1340 9 0 0 1 1 4 4 2 2 3 3 1 1 1 1 2 2 3 3 2 2 1 1 2 2 2 2 4 4 1 1 3 3 1 1 2 2 4 4 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1341 1 11 12 1 1 2 2 4 2 3 3 1 3 3 1 2 2 1 3 1 2 3 1 4 2 4 2 2 4 3 1 4 4 1 1 0 0 2 2 1 1 1 1 1 1 3 3 2 2 1 1 3 3 1 1 +1341 11 0 0 1 1 2 2 2 2 3 3 1 1 1 1 2 2 3 3 1 1 3 3 2 2 2 2 2 2 3 3 4 4 1 1 4 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +1341 12 0 0 2 1 4 2 4 2 3 3 1 3 3 1 2 2 1 3 2 2 1 1 4 2 4 2 4 4 1 1 3 4 1 1 4 2 4 2 3 1 1 1 2 1 3 3 2 2 1 1 3 3 1 1 +1341 13 0 0 1 1 4 2 2 2 3 3 1 1 1 1 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1341 14 0 0 2 1 4 2 2 2 3 3 1 1 1 1 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1341 2 13 14 2 1 4 2 2 2 3 3 1 1 1 1 2 2 3 3 1 2 3 1 2 2 2 2 2 4 3 1 3 4 1 1 2 2 4 2 1 1 1 1 1 1 3 3 4 4 3 3 1 1 3 3 +1344 1 12 13 1 1 2 2 4 4 3 3 3 3 3 3 4 4 1 1 2 2 1 1 2 2 2 2 2 2 3 3 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 2 1 1 3 3 1 1 +1344 12 0 0 1 1 2 2 4 2 3 3 1 3 3 1 4 2 1 3 1 2 3 1 2 2 2 2 2 2 3 3 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +1344 13 0 0 2 1 2 2 4 2 3 3 1 3 3 1 4 2 1 3 1 2 3 1 2 2 2 2 2 2 3 3 4 4 1 1 2 2 2 2 1 1 1 1 1 1 3 3 2 4 1 3 3 1 1 3 +1345 12 0 0 1 1 4 2 4 2 3 3 3 3 3 1 2 2 1 3 2 2 1 1 4 2 4 2 4 4 1 1 3 4 1 1 4 2 4 2 3 1 1 1 2 1 3 3 2 2 1 1 3 3 1 1 --- /dev/null +++ b/test-data/1.bed.spaces @@ -0,0 +1,65 @@ +chr1 147962192 147962580 CCDS989.1_cds_0_0_chr1_147962193_r 0 - +chr1 147984545 147984630 CCDS990.1_cds_0_0_chr1_147984546_f 0 + +chr1 148078400 148078582 CCDS993.1_cds_0_0_chr1_148078401_r 0 - +chr1 148185136 148185276 CCDS996.1_cds_0_0_chr1_148185137_f 0 + +chr10 55251623 55253124 CCDS7248.1_cds_0_0_chr10_55251624_r 0 - +chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - +chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + +chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - +chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 + +chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - +chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + +chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - +chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - +chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + +chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - +chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 + +chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + +chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 - +chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + +chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - +chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - +chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + +chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - +chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 + +chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + +chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - +chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + +chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 - +chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + +chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 - +chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 + +chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - +chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - +chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + +chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 - +chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 + +chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 + +chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - +chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + +chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 - +chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + +chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - +chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 + +chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 - +chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + +chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - +chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + +chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 - +chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - +chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + +chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - +chr6 108722976 108723115 CCDS5067.1_cds_0_0_chr6_108722977_f 0 + +chr7 113660517 113660685 CCDS5760.1_cds_0_0_chr7_113660518_f 0 + +chr7 116512159 116512389 CCDS5771.1_cds_0_0_chr7_116512160_r 0 - +chr7 116714099 116714152 CCDS5773.1_cds_0_0_chr7_116714100_f 0 + +chr7 116945541 116945787 CCDS5774.1_cds_0_0_chr7_116945542_r 0 - +chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - +chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + +chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - +chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 + +chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 - +chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + +chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - +chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + +chrX 152694029 152694263 CCDS14736.1_cds_0_0_chrX_152694030_r 0 - --- a/lib/galaxy/datatypes/data.py +++ b/lib/galaxy/datatypes/data.py @@ -295,7 +295,7 @@ class Data( object ): def after_setting_metadata( self, dataset ): """This function is called on the dataset after metadata is set.""" dataset.clear_associated_files( metadata_safe = True ) - def __new_composite_file( self, name, optional = False, mimetype = None, description = None, substitute_name_with_metadata = None, is_binary = False, space_to_tab = True, **kwds ): + def __new_composite_file( self, name, optional = False, mimetype = None, description = None, substitute_name_with_metadata = None, is_binary = False, space_to_tab = False, **kwds ): kwds[ 'name' ] = name kwds[ 'optional' ] = optional kwds[ 'mimetype' ] = mimetype --- a/test/base/twilltestcase.py +++ b/test/base/twilltestcase.py @@ -143,7 +143,7 @@ class TwillTestCase( unittest.TestCase ) filename = os.path.join( *path ) file(filename, 'wt').write(buffer.getvalue()) - def upload_file( self, filename, ftype='auto', dbkey='unspecified (?)', metadata = None, composite_data = None ): + def upload_file( self, filename, ftype='auto', dbkey='unspecified (?)', space_to_tab = False, metadata = None, composite_data = None ): """Uploads a file""" self.visit_url( "%s/tool_runner?tool_id=upload1" % self.url ) try: @@ -156,9 +156,11 @@ class TwillTestCase( unittest.TestCase ) for i, composite_file in enumerate( composite_data ): filename = self.get_filename( composite_file.get( 'value' ) ) tc.formfile( "1", "files_%i|file_data" % i, filename ) + tc.fv( "1", "files_%i|space_to_tab" % i, composite_file.get( 'space_to_tab', False ) ) else: filename = self.get_filename( filename ) tc.formfile( "1", "file_data", filename ) + tc.fv( "1", "space_to_tab", space_to_tab ) tc.submit("runtool_btn") self.home() except AssertionError, err: @@ -196,60 +198,6 @@ class TwillTestCase( unittest.TestCase ) # Wait for upload processing to finish (TODO: this should be done in each test case instead) self.wait() - def upload_composite_datatype_file( self, ftype, ped_file='', map_file='', bim_file='', bed_file='', - fped_file='',fphe_file='',pphe_file='',fam_file='',pheno_file='',eset_file='',malist_file='', - affybatch_file='', dbkey='unspecified (?)', base_name='rgenetics' ): - """Tests uploading either of 2 different composite data types ( lped and pbed )""" - self.visit_url( "%s/tool_runner/index?tool_id=upload1" % self.url ) - # Handle refresh_on_change - self.refresh_form( "file_type", ftype ) - tc.fv( "1", "dbkey", dbkey ) - tc.fv( "1", "files_metadata|base_name", base_name ) - if ftype == 'lped': - # lped data types include a ped_file and a map_file - ped_file = self.get_filename( ped_file ) - tc.formfile( "1", "files_0|file_data", ped_file ) - map_file = self.get_filename( map_file ) - tc.formfile( "1", "files_1|file_data", map_file ) - elif ftype == 'pbed': - # pbed data types include a bim_file, a bed_file and a fam_file - bim_file = self.get_filename( bim_file ) - tc.formfile( "1", "files_0|file_data", bim_file ) - bed_file = self.get_filename( bed_file ) - tc.formfile( "1", "files_1|file_data", bed_file ) - fam_file = self.get_filename( fam_file ) - tc.formfile( "1", "files_2|file_data", fam_file ) - elif ftype == 'pphe': - # pphe data types include a phe_file - pphe_file = self.get_filename( pphe_file ) - tc.formfile( "1", "files_0|file_data", pphe_file ) - elif ftype == 'fped': - # fped data types include an fped_file only - fped_file = self.get_filename( fped_file ) - tc.formfile( "1", "files_0|file_data", fped_file ) - elif ftype == 'eset': - # eset data types include a eset_file, a pheno_file - eset_file = self.get_filename( eset_file ) - tc.formfile( "1", "files_0|file_data", eset_file ) - pheno_file = self.get_filename( pheno_file ) - tc.formfile( "1", "files_1|file_data", pheno_file ) - elif ftype == 'affybatch': - # affybatch data types include an affybatch_file, and a pheno_file - affybatch_file = self.get_filename( affybatch_file ) - tc.formfile( "1", "files_0|file_data", affybatch_file ) - pheno_file = self.get_filename( pheno_file ) - tc.formfile( "1", "files_1|file_data", pheno_file ) - else: - raise AssertionError, "Unsupported composite data type (%s) received, currently only %s data types are supported."\ - % (ftype,','.join(self.composite_extensions)) - tc.submit( "runtool_btn" ) - self.check_page_for_string( 'The following job has been succesfully added to the queue:' ) - check_str = base_name #'Uploaded Composite Dataset (%s)' % ftype - self.check_page_for_string( check_str ) - # Wait for upload processing to finish (TODO: this should be done in each test case instead) - self.wait() - self.check_history_for_string( check_str ) - # Functions associated with histories def check_history_for_errors( self ): """Raises an exception if there are errors in a history""" --- a/lib/galaxy/tools/parameters/grouping.py +++ b/lib/galaxy/tools/parameters/grouping.py @@ -241,8 +241,8 @@ class UploadDataset( Group ): name = context.get( 'NAME', None ) info = context.get( 'INFO', None ) warnings = [] - space_to_tab = False - if context.get( 'space_to_tab', None ) not in ["None", None]: + space_to_tab = False + if context.get( 'space_to_tab', None ) not in [ "None", None, False ]: space_to_tab = True file_bunch = get_data_file_filename( data_file, override_name = name, override_info = info ) if file_bunch.path and url_paste: @@ -261,7 +261,7 @@ class UploadDataset( Group ): name = context.get( 'NAME', None ) info = context.get( 'INFO', None ) space_to_tab = False - if context.get( 'space_to_tab', None ) not in ["None", None]: + if context.get( 'space_to_tab', None ) not in [ "None", None, False ]: space_to_tab = True warnings = [] file_bunch = get_data_file_filename( data_file, override_name = name, override_info = info ) --- a/tools/data_source/upload.py +++ b/tools/data_source/upload.py @@ -299,7 +299,7 @@ def add_composite_file( dataset, json_fi break elif dataset.composite_file_paths[value.name] is not None: if not value.is_binary: - if value.space_to_tab: + if dataset.composite_file_paths[ value.name ].get( 'space_to_tab', value.space_to_tab ): sniff.convert_newlines_sep2tabs( dataset.composite_file_paths[ value.name ][ 'path' ] ) else: sniff.convert_newlines( dataset.composite_file_paths[ value.name ][ 'path' ] )

1 0

galaxy-dist commit 5ba6a1d980ac: merged SAM indel filter tool commit
by commits-noreply＠bitbucket.org 08 Jun '10

08 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Kelly Vincent <kpvincent(a)bx.psu.edu> # Date 1275938865 14400 # Node ID 5ba6a1d980ac4d446478d8a4d054234d6342a979 # Parent 1ab9d6b0ddfc65bc6e58c77891c57ef99e1e12cb # Parent c3ced3ed4fee6e0bdb5acbc7bdc2518995f97e7a merged SAM indel filter tool commit

1 0

galaxy-dist commit 7de1adaf5628: Add SAM indel filter tool to tool_conf.xml.sample
by commits-noreply＠bitbucket.org 08 Jun '10

08 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Kelly Vincent <kpvincent(a)bx.psu.edu> # Date 1275939020 14400 # Node ID 7de1adaf5628e04e2da0d948f03d08cb5ce5d7f3 # Parent 5ba6a1d980ac4d446478d8a4d054234d6342a979 Add SAM indel filter tool to tool_conf.xml.sample --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -253,6 +253,7 @@ </section><section name="NGS: SAM Tools" id="samtools"><tool file="samtools/sam_bitwise_flag_filter.xml" /> + <tool file="samtools/sam_indel_filter.xml" /><tool file="samtools/sam2interval.xml" /><tool file="samtools/sam_to_bam.xml" /><tool file="samtools/sam_merge.xml" />

1 0

galaxy-dist commit c3ced3ed4fee: Adding SAM indel filter tool with test files
by commits-noreply＠bitbucket.org 08 Jun '10

08 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Kelly Vincent <kpvincent(a)bx.psu.edu> # Date 1275938612 14400 # Node ID c3ced3ed4fee6e0bdb5acbc7bdc2518995f97e7a # Parent f7cf88978f1f848b97c5da1bfe6e48aeb1930378 Adding SAM indel filter tool with test files --- /dev/null +++ b/test-data/sam_indel_filter_out1.sam @@ -0,0 +1,3 @@ +1378_28_770 89 chr11.nib:1-134452384 72131356 37 17M1I5M = 72131356 0 CACACTGTGACAGACAGCGCAGC 00/02!!0//1200210AA44/1 XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 +1378_69_800 16 chr11.nib:1-125234658 241 255 15M1D8M * 0 0 CGTGGCCGGCGGGCCGAAGGCAT IIIIIIIIIICCCCIII?IIIII +1378_72_1612 151 chrY.nib:1-124295114 190342418 37 19M1I3M = 190342418 0 TCTAACTTAGCCTCATAATAGCT /<<!"0/4//7//00/BC0121/ XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 --- /dev/null +++ b/tools/samtools/sam_indel_filter.xml @@ -0,0 +1,74 @@ +<tool id="sam_indel_filter" name="Filter SAM" version="1.0.0"> + <description>for indels</description> + <command interpreter="python"> + sam_indel_filter.py + --input=$input1 + --quality_threshold=$quality_threshold + --adjacent_bases=$adjacent_bases + --output=$out_file1 + </command> + <inputs> + <param format="sam" name="input1" type="data" label="Select dataset to filter" /> + <param name="quality_threshold" type="integer" value="40" label="Quality threshold for adjacent bases" help="You need to give the true value, not offset (see chart below), regardless of source FASTQ type" /> + <param name="adjacent_bases" type="integer" value="5" label="The number of adjacent bases to match on either side of the indel" help="If one side is shorter than this width, it will still match if the long-enough side matches" /> + </inputs> + <outputs> + <data format="sam" name="out_file1" /> + </outputs> + <tests> + <test> + <param name="input1" value="sam_indel_filter_in1.sam" ftype="sam"/> + <param name="quality_threshold" value="47"/> + <param name="adjacent_bases" value="2"/> + <output name="out_file1" file="sam_indel_filter_out1.sam" ftype="sam"/> + </test> + <test> + <param name="input1" value="sam_indel_filter_in1.sam" ftype="sam"/> + <param name="quality_threshold" value="62"/> + <param name="adjacent_bases" value="5"/> + <output name="out_file1" file="sam_indel_filter_out2.sam" ftype="sam"/> + </test> + </tests> + <help> + +**What it does** + +Allows extracting indels from SAM. Currently it can handle SAM with alignments with only one insertion or one deletion, and will throw an error if it encounters an alignment with more than one. It matches CIGAR strings (column 6 in the SAM file) like 5M3I5M or 4M2D10M, so there must be a match or mismatch of sufficient length on either side of the indel. + +----- + +**Example** + +Suppose you have the following:: + + r770 89 ref 116 37 17M1I5M = 72131356 0 CACACTGTGACAGACAGCGCAGC 00/02!!0//1200210AA44/1 XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 + r770 181 ref 116 0 24M = 72131356 0 TTGGTGCGCGCGGTTGAGGGTTGG $$(#%%#$%#%####$%%##$### + r1945 113 ref 181247988 0 23M 41710908 41710908 0 GAGAGAGAGAGAGAGAGAGAGAG PQRVUMNXYRPUXYXWXSOSZ]M XT:A:R CM:i:0 SM:i:0 AM:i:0 X0:i:163148 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 + r1945 177 ref 41710908 0 23M 190342418 181247988 0 AGAGAGAGAGAGAGAGAGAGAGA SQQWZYURVYWX]]YXTSY]]ZM XT:A:R CM:i:0 SM:i:0 AM:i:0 X0:i:163148 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 + r2363 115 ref 19671878 0 23M = 19671877 -1 AGAGAGAGAGAGAGAGAGAGTCT 77543:<55#"4!&=964518A> XT:A:R CM:i:2 SM:i:0 AM:i:0 X0:i:4 X1:i:137 XM:i:2 XO:i:0 XG:i:0 MD:Z:23 + r2363 179 ref 19671877 0 23M = 19671878 1 GAGAGAGAGAGAGAGAGAGAGTC LE7402DD34FL:27AKE>;432 XT:A:R CM:i:0 SM:i:0 AM:i:0 X0:i:265 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 + r3671 117 ref 190342418 0 24M = 190342418 0 CTGGCGTTCTCGGCGTGGATGGGT #####$$##$#%#%%###%$#$## + r3671 153 ref 190342418 37 16M1I6M = 190342418 0 TCTAACTTAGCCTCATAATAGCT /<<!"0///////00/!!0121/ XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 + r3824 117 ref 80324999 0 24M = 80324999 0 TCCAGTCGCGTTGTTAGGTTCGGA #$#$$$#####%##%%###**#+/ + r3824 153 ref 80324999 37 8M1I14M = 80324999 0 TTTAGCCCGAAATGCCTAGAGCA 4;6//11!"11100110////00 XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 + r4795 81 ref 26739130 0 23M 57401793 57401793 0 TGGCATTCCTGTAGGCAGAGAGG AZWWZS]!"QNXZ]VQ]]]/2]] XT:A:R CM:i:2 SM:i:0 AM:i:0 X0:i:3 X1:i:0 XM:i:2 XO:i:0 XG:i:0 MD:Z:23 + r4795 161 ref 57401793 37 23M 26739130 26739130 0 GATCACCCAGGTGATGTAACTCC ]WV]]]]WW]]]]]]]]]]PU]] XT:A:U CM:i:0 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 + r4800 16 ref 241 255 15M1D8M * 0 0 CGTGGCCGGCGGGCCGAAGGCAT IIIIIIIIIICCCCIII?IIIII + r5377 170 ref 59090793 37 23M 26739130 26739130 0 TATCAATAAGGTGATGTAACTCG ]WV]ABAWW]]]]]P]P//GU]] XT:A:U CM:i:0 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 + r5612 151 ref 190342418 37 19M1I3M = 190342418 0 TCTAACTTAGCCTCATAATAGCT /<<!"0/4//7//00/BC0121/ XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 + + +To select only alignments with indels, you need to determine the minimum quality you want the adjacent bases to have, as well as the number of adjacent bases to check. If you set the quality threshold to 47 and the number of bases to check to 2, you will get the following output:: + + r770 89 ref 116 37 17M1I5M = 72131356 0 CACACTGTGACAGACAGCGCAGC 00/02!!0//1200210AA44/1 XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 + r4800 16 ref 241 255 15M1D8M * 0 0 CGTGGCCGGCGGGCCGAAGGCAT IIIIIIIIIICCCCIII?IIIII + r5612 151 ref 190342418 37 19M1I3M = 190342418 0 TCTAACTTAGCCTCATAATAGCT /<<!"0/4//7//00/BC0121/ XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 + + +For more information on SAM, please consult the `SAM format description`__. + +.. __: http://www.ncbi.nlm.nih.gov/pubmed/19505943 + + + </help> +</tool> --- /dev/null +++ b/tools/samtools/sam_indel_filter.py @@ -0,0 +1,83 @@ +#!/usr/bin/env python + +""" +Allows user to filter out non-indels from SAM. + +usage: %prog [options] + -i, --input=i: Input SAM file to be filtered + -q, --quality_threshold=q: Minimum quality value for adjacent bases + -a, --adjacent_bases=a: Number of adjacent bases on each size to check qualities + -o, --output=o: Filtered output SAM file +""" + +import re, sys +from galaxy import eggs +import pkg_resources; pkg_resources.require( "bx-python" ) +from bx.cookbook import doc_optparse + + +def stop_err( msg ): + sys.stderr.write( '%s\n' % msg ) + sys.exit() + +def __main__(): + #Parse Command Line + options, args = doc_optparse.parse( __doc__ ) + # prep output file + output = open( options.output, 'wb' ) + # patterns + pat_indel = re.compile( '(?P<before_match>(\d+[MIDNSHP])*)(?P<lmatch>\d+)M(?P<ins_del_width>\d+)(?P<ins_del>[ID])(?P<rmatch>\d+)M' ) + pat_matches = re.compile( '\d+[MIDNSHP]' ) + qual_thresh = int( options.quality_threshold ) + adj_bases = int( options.adjacent_bases ) + # go through all lines in input file + for line in open( options.input, 'rb' ): + if line and not line.startswith( '#' ) and not line.startswith( '@' ) : + split_line = line.split( '\t' ) + cigar = split_line[5] + # find all possible matches, like 3M2D7M and 7M3I10M in 3M2D7M3I10M + cigar_copy = cigar[:] + matches = [] + while len( cigar_copy ) >= 6: # nMnInM or nMnDnM + m = pat_indel.match( cigar_copy ) + if not m: + break + else: + parts = m.groupdict() + parts[ 'start' ] = m.start() + matches.append( parts ) + cigar_copy = cigar_copy[ len( parts[ 'lmatch' ] ) : ] + # see if matches meet filter requirements + if len( matches ) == 1: + start = int( matches[0][ 'start' ] ) + left = int( matches[0][ 'lmatch' ] ) + right = int( matches[0][ 'rmatch' ] ) + if matches[0][ 'ins_del' ] == 'D': + middle = int( matches[0][ 'ins_del_width' ] ) + else: + middle = 0 + # if there are enough adjacent bases to check, then do so + if left >= adj_bases and right >= adj_bases: + qual = split_line[10] + left_bases = qual[ start : start + left + 1 ][ -adj_bases : ] + right_bases = qual[ start + left + middle : start + left + middle + right + 1 ][ : adj_bases ] + qual_thresh_met = True + for l in left_bases: + if ord( l ) < qual_thresh: + qual_thresh_met = False + break + if qual_thresh_met: + for r in right_bases: + if ord( r ) < qual_thresh: + qual_thresh_met = False + break + # if filter reqs met, output line + if qual_thresh_met: + output.write( line ) + # error if there are multiple indels + elif len( matches ) > 1: + stop_err( 'There is more than one indel present in the alignment:\n%s' % line ) + # close out file + output.close() + +if __name__=="__main__": __main__() --- /dev/null +++ b/test-data/sam_indel_filter_out2.sam @@ -0,0 +1,1 @@ +1378_69_800 16 chr11.nib:1-125234658 241 255 15M1D8M * 0 0 CGTGGCCGGCGGGCCGAAGGCAT IIIIIIIIIICCCCIII?IIIII --- /dev/null +++ b/test-data/sam_indel_filter_in1.sam @@ -0,0 +1,15 @@ +1378_28_770 89 chr11.nib:1-134452384 72131356 37 17M1I5M = 72131356 0 CACACTGTGACAGACAGCGCAGC 00/02!!0//1200210AA44/1 XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 +1378_28_770 181 chr11.nib:1-134452384 72131356 0 24M = 72131356 0 TTGGTGCGCGCGGTTGAGGGTTGG $$(#%%#$%#%####$%%##$### +1378_33_1945 113 chr2.nib:1-242951149 181247988 0 23M chr12.nib:1-132349534 41710908 0 GAGAGAGAGAGAGAGAGAGAGAG PQRVUMNXYRPUXYXWXSOSZ]M XT:A:R CM:i:0 SM:i:0 AM:i:0 X0:i:163148 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 +1378_33_1945 177 chr12.nib:1-132349534 41710908 0 23M chr2.nib:1-242951149 181247988 0 AGAGAGAGAGAGAGAGAGAGAGA SQQWZYURVYWX]]YXTSY]]ZM XT:A:R CM:i:0 SM:i:0 AM:i:0 X0:i:163148 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 +1378_35_263 115 chr16.nib:1-88827254 19671878 0 23M = 19671877 -1 AGAGAGAGAGAGAGAGAGAGTCT 77543:<55#"4!&=964518A> XT:A:R CM:i:2 SM:i:0 AM:i:0 X0:i:4 X1:i:137 XM:i:2 XO:i:0 XG:i:0 MD:Z:23 +1378_35_263 179 chr16.nib:1-88827254 19671877 0 23M = 19671878 1 GAGAGAGAGAGAGAGAGAGAGTC LE7402DD34FL:27AKE>;432 XT:A:R CM:i:0 SM:i:0 AM:i:0 X0:i:265 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 +1378_51_1671 117 chr2.nib:1-242951149 190342418 0 24M = 190342418 0 CTGGCGTTCTCGGCGTGGATGGGT #####$$##$#%#%%###%$#$## +1378_51_1671 153 chr2.nib:1-242951149 190342418 37 16M1I6M = 190342418 0 TCTAACTTAGCCTCATAATAGCT /<<!"0///////00/!!0121/ XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 +1378_56_324 117 chr2.nib:1-242951149 80324999 0 24M = 80324999 0 TCCAGTCGCGTTGTTAGGTTCGGA #$#$$$#####%##%%###**#+/ +1378_56_324 153 chr2.nib:1-242951149 80324999 37 8M1I14M = 80324999 0 TTTAGCCCGAAATGCCTAGAGCA 4;6//11!"11100110////00 XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22 +1378_67_1795 81 chr16.nib:1-88827254 26739130 0 23M chrY.nib:1-57772954 57401793 0 TGGCATTCCTGTAGGCAGAGAGG AZWWZS]!"QNXZ]VQ]]]/2]] XT:A:R CM:i:2 SM:i:0 AM:i:0 X0:i:3 X1:i:0 XM:i:2 XO:i:0 XG:i:0 MD:Z:23 +1378_67_1795 161 chrY.nib:1-57772954 57401793 37 23M chr16.nib:1-88827254 26739130 0 GATCACCCAGGTGATGTAACTCC ]WV]]]]WW]]]]]]]]]]PU]] XT:A:U CM:i:0 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 +1378_69_800 16 chr11.nib:1-125234658 241 255 15M1D8M * 0 0 CGTGGCCGGCGGGCCGAAGGCAT IIIIIIIIIICCCCIII?IIIII +1378_69_1777 170 chrX.nib:1-59090954 59090793 37 23M chr16.nib:1-88827254 26739130 0 TATCAATAAGGTGATGTAACTCG ]WV]ABAWW]]]]]P]P//GU]] XT:A:U CM:i:0 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:0 XO:i:0 XG:i:0 MD:Z:23 +1378_72_1612 151 chrY.nib:1-124295114 190342418 37 19M1I3M = 190342418 0 TCTAACTTAGCCTCATAATAGCT /<<!"0/4//7//00/BC0121/ XT:A:U CM:i:2 SM:i:37 AM:i:0 X0:i:1 X1:i:0 XM:i:1 XO:i:1 XG:i:1 MD:Z:22

1 0

galaxy-dist commit 1f70816084ae: Fix bug in 48ec25db21c3
by commits-noreply＠bitbucket.org 07 Jun '10

07 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Nate Coraor <nate(a)bx.psu.edu> # Date 1275924969 14400 # Node ID 1f70816084ae18122f3af9a5efb588f9ace6cd11 # Parent 2c99bd86765fc2665cfa6bea98b4ebae7fc3d6c8 Fix bug in 48ec25db21c3 --- a/lib/galaxy/web/controllers/page.py +++ b/lib/galaxy/web/controllers/page.py @@ -129,7 +129,7 @@ class HistoryDatasetAssociationSelection model_class = model.HistoryDatasetAssociation columns = [ ItemSelectionGrid.NameColumn( "Name", key="name", model_class=model.HistoryDatasetAssociation, filterable="advanced" ), - grids.IndividualTagsColumn( "Tags", "tags", model_class=model.HistoryDatasetAssociation, model.HistoryDatasetAssociationTagAssociation, filterable="advanced"), + grids.IndividualTagsColumn( "Tags", "tags", model.HistoryDatasetAssociation, model.HistoryDatasetAssociationTagAssociation, filterable="advanced"), grids.GridColumn( "Last Updated", key="update_time", format=time_ago ), # Columns that are valid for filtering but are not visible. grids.DeletedColumn( "Deleted", key="deleted", visible=False, filterable="advanced" ),

1 0

galaxy-dist commit 1ab9d6b0ddfc: Yet another fix fo creating the history link on the library dataset information page - since it is possible to have an hda that does not have an associated history, we need to handle it.
by commits-noreply＠bitbucket.org 07 Jun '10

07 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Greg Von Kuster <greg(a)bx.psu.edu> # Date 1275930847 14400 # Node ID 1ab9d6b0ddfc65bc6e58c77891c57ef99e1e12cb # Parent f415eee0950c78ccf103bde9d4adc8a853e55a1e Yet another fix fo creating the history link on the library dataset information page - since it is possible to have an hda that does not have an associated history, we need to handle it. --- a/templates/library/common/ldda_info.mako +++ b/templates/library/common/ldda_info.mako @@ -149,20 +149,17 @@ %for hda in associated_hdas: <tr><td> - <% - hda_hist = trans.sa_session.query( trans.model.History ).get( hda.history_id ) - %> - %if hda_hist: - <a target="_blank" href="${h.url_for( controller='history', action='view', id=trans.security.encode_id( hda_hist.id ) )}">${hda_hist.get_display_name()}</a> + %if hda.history: + <a target="_blank" href="${h.url_for( controller='history', action='view', id=trans.security.encode_id( hda.history_id ) )}">${hda.history.get_display_name()}</a> %else: - error getting history + no history %endif </td><td>${hda.get_display_name()}</td><td>${time_ago( hda.update_time )}</td><td> - %if hda_hist and hda_hist.user: - ${hda_hist.user.email} + %if hda.history and hda.history.user: + ${hda.history.user.email} %else: anonymous %endif

1 0

galaxy-dist commit ada54c10540a: Bugfix for 4fb747f317d0, open tar file as stream
by commits-noreply＠bitbucket.org 07 Jun '10

07 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Nate Coraor <nate(a)bx.psu.edu> # Date 1275926267 14400 # Node ID ada54c10540ae10f308a1f2e8683bcbe779057f1 # Parent 1f70816084ae18122f3af9a5efb588f9ace6cd11 Bugfix for 4fb747f317d0, open tar file as stream --- a/lib/galaxy/web/controllers/library_common.py +++ b/lib/galaxy/web/controllers/library_common.py @@ -1382,7 +1382,7 @@ class LibraryCommon( BaseController ): archive.add = lambda x, y: archive.write( x, y.encode('CP437') ) elif action == 'tgz': if trans.app.config.upstream_gzip: - archive = util.streamball.StreamBall( 'w' ) + archive = util.streamball.StreamBall( 'w|' ) outext = 'tar' else: archive = util.streamball.StreamBall( 'w|gz' )

1 0

galaxy-dist commit f415eee0950c: Being extremely cautious when displaying history atibutes associated with an hda in the library dataset info page.
by commits-noreply＠bitbucket.org 07 Jun '10

07 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Greg Von Kuster <greg(a)bx.psu.edu> # Date 1275929498 14400 # Node ID f415eee0950c78ccf103bde9d4adc8a853e55a1e # Parent ada54c10540ae10f308a1f2e8683bcbe779057f1 Being extremely cautious when displaying history atibutes associated with an hda in the library dataset info page. --- a/templates/library/common/ldda_info.mako +++ b/templates/library/common/ldda_info.mako @@ -148,12 +148,21 @@ </thead> %for hda in associated_hdas: <tr> - <td><a target="_blank" href="${h.url_for( controller='history', action='view', id=trans.security.encode_id( hda.history_id ) )}">${hda.history.get_display_name()}</a></td> + <td> + <% + hda_hist = trans.sa_session.query( trans.model.History ).get( hda.history_id ) + %> + %if hda_hist: + <a target="_blank" href="${h.url_for( controller='history', action='view', id=trans.security.encode_id( hda_hist.id ) )}">${hda_hist.get_display_name()}</a> + %else: + error getting history + %endif + </td><td>${hda.get_display_name()}</td><td>${time_ago( hda.update_time )}</td><td> - %if hda.history.user: - ${hda.history.user.email} + %if hda_hist and hda_hist.user: + ${hda_hist.user.email} %else: anonymous %endif

1 0

galaxy-dist commit 4fb747f317d0: When using gzip compression in the upstream proxy, do not gzip compress library tar.gz or zip archives. bz2 then remains as the only compression perfomed in Galaxy itself.
by commits-noreply＠bitbucket.org 07 Jun '10

07 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Nate Coraor <nate(a)bx.psu.edu> # Date 1275924249 14400 # Node ID 4fb747f317d0b2c36ffb5fbf4b815caf4cb6ace1 # Parent 48ec25db21c3bd76b52bcd68a1301f777eea280e When using gzip compression in the upstream proxy, do not gzip compress library tar.gz or zip archives. bz2 then remains as the only compression perfomed in Galaxy itself. --- a/templates/library/common/common.mako +++ b/templates/library/common/common.mako @@ -382,15 +382,15 @@ # This condition should not contain an else clause because the user is not authorized # to manage dataset permissions unless the default action is 'manage_permissions' %endif - %if 'bz2' in comptypes: - <option value="tbz" + %if 'gz' in comptypes: + <option value="tgz" %if default_action == 'download': selected %endif> - >Download as a .tar.bz2 file</option> + >Download as a .tar.gz file</option> %endif - %if 'gz' in comptypes: - <option value="tgz">Download as a .tar.gz file</option> + %if 'bz2' in comptypes: + <option value="tbz">Download as a .tar.bz2 file</option> %endif %if 'zip' in comptypes: <option value="zip">Download as a .zip file</option> --- a/lib/galaxy/web/controllers/library_common.py +++ b/lib/galaxy/web/controllers/library_common.py @@ -1364,14 +1364,22 @@ class LibraryCommon( BaseController ): # Can't use mkstemp - the file must not exist first tmpd = tempfile.mkdtemp() tmpf = os.path.join( tmpd, 'library_download.' + action ) - if ziptype == '64': + if ziptype == '64' and trans.app.config.upstream_gzip: + archive = zipfile.ZipFile( tmpf, 'w', zipfile.ZIP_STORED, True ) + elif ziptype == '64': archive = zipfile.ZipFile( tmpf, 'w', zipfile.ZIP_DEFLATED, True ) + elif trans.app.config.upstream_gzip: + archive = zipfile.ZipFile( tmpf, 'w', zipfile.ZIP_STORED ) else: archive = zipfile.ZipFile( tmpf, 'w', zipfile.ZIP_DEFLATED ) archive.add = lambda x, y: archive.write( x, y.encode('CP437') ) elif action == 'tgz': - archive = util.streamball.StreamBall( 'w|gz' ) - outext = 'tgz' + if trans.app.config.upstream_gzip: + archive = util.streamball.StreamBall( 'w' ) + outext = 'tar' + else: + archive = util.streamball.StreamBall( 'w|gz' ) + outext = 'tgz' elif action == 'tbz': archive = util.streamball.StreamBall( 'w|bz2' ) outext = 'tbz2' --- a/lib/galaxy/config.py +++ b/lib/galaxy/config.py @@ -99,6 +99,7 @@ class Configuration( object ): raise ConfigurationError( "user_library_import_dir specified in config (%s) does not exist" % self.user_library_import_dir ) self.allow_library_path_paste = kwargs.get( 'allow_library_path_paste', False ) # Configuration options for taking advantage of nginx features + self.upstream_gzip = string_as_bool( kwargs.get( 'upstream_gzip', False ) ) self.apache_xsendfile = kwargs.get( 'apache_xsendfile', False ) self.nginx_x_accel_redirect_base = kwargs.get( 'nginx_x_accel_redirect_base', False ) self.nginx_x_archive_files_base = kwargs.get( 'nginx_x_archive_files_base', False ) --- a/templates/library/common/browse_library.mako +++ b/templates/library/common/browse_library.mako @@ -507,12 +507,16 @@ TIP: Multiple compression options are available for downloading library datasets: </p><ul style="padding-left: 1em; list-style-type: disc;"> + %if 'gz' in comptypes: + <li>gzip: Compression is fastest and yields a larger file, making it more suitable for fast network connections. + %if trans.app.config.upstream_gzip: + NOTE: The file you receive will be an uncompressed .tar file - this is because the Galaxy server compresses it and your browser decompresses it on the fly. + %endif + </li> + %endif %if 'bz2' in comptypes: <li>bzip2: Compression takes the most time but is better for slower network connections (that transfer slower than the rate of compression) since the resulting file size is smallest.</li> %endif - %if 'gz' in comptypes: - <li>gzip: Compression is faster and yields a larger file, making it more suitable for fast network connections.</li> - %endif %if 'zip' in comptypes: <li>ZIP: Not recommended but is provided as an option for those on Windows without WinZip (since WinZip can read .bz2 and .gz files).</li> %endif

1 0

galaxy-dist commit 2c99bd86765f: Add RGENETICS section label to main tool conf
by commits-noreply＠bitbucket.org 07 Jun '10

07 Jun '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Nate Coraor <nate(a)bx.psu.edu> # Date 1275924412 14400 # Node ID 2c99bd86765fc2665cfa6bea98b4ebae7fc3d6c8 # Parent f08dff0dd4ac92c5d9b75792c2c5c38eb280e81b Add RGENETICS section label to main tool conf --- a/tool_conf.xml.main +++ b/tool_conf.xml.main @@ -333,6 +333,7 @@ <tool file="genetrack/genetrack_indexer.xml" /><tool file="genetrack/genetrack_peak_prediction.xml" /></section> + <label text="RGENETICS" id="rgenetics" /><section name="SNP/WGA: Data; Filters" id="rgdat"><label text="Data: Import and upload" id="rgimport" /><tool file="data_source/upload.xml"/>

1 0