opensource/galaxy
3
0
Fork 0
mirror of https://github.com/galaxyproject/galaxy.git synced 2026-09-24 16:30:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Better approach to altering initial content of output dataset if necessary. The upload tool will now call the data type's groom_output_dataset() method ( a better name than before_setting_metadata since it is not related to metadata ). This will now also run on the cluster.

Browse Source
This commit is contained in:
Greg Von Kuster
2009-12-08 11:46:13 -05:00
parent 7051ce7dd5
commit cf83cecb0b
20 changed files with 38 additions and 224 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/galaxy/datatypes/binary.py
+27 -48
View File
@@ -17,9 +17,6 @@ unsniffable_binary_formats = [ 'ab1', 'scf' ]
class Binary( data.Data ):
"""Binary data"""
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
"""Set the peek and blurb text"""
if not dataset.dataset.purged:
@@ -36,9 +33,6 @@ class Ab1( Binary ):
"""Class describing an ab1 binary sequence file"""
file_ext = "ab1"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
export_url = "/history_add_to?" + urlencode( {'history_id':dataset.history_id,'ext':'ab1','name':'ab1 sequence','info':'Sequence file','dbkey':dataset.dbkey} )
@@ -58,39 +52,32 @@ class Bam( Binary ):
file_ext = "bam"
MetadataElement( name="bam_index", desc="BAM Index File", param=metadata.FileParameter, readonly=True, no_value=None, visible=False, optional=True )
def before_setting_metadata( self, dataset ):
""" Ensures that the Bam file contents are sorted. This function is called on the dataset before set_meta() is called."""
sorted = False
try:
index_file = dataset.metadata.bam_index
except:
index_file = None
if index_file:
# If an index file already exists on disk, then the data must have previously been sorted
# since samtools requires a sorted Bam file in order to create an index.
sorted = os.path.exists( index_file.file_name )
if not sorted:
# Use samtools to sort the Bam file
tmp_dir = tempfile.gettempdir()
# Create a symlink from the temporary directory to the dataset file so that samtools can mess with it.
tmp_dataset_file_name = os.path.join( tmp_dir, os.path.basename( dataset.file_name ) )
# Here tmp_dataset_file_name looks something like /tmp/dataset_XX.dat
os.symlink( dataset.file_name, tmp_dataset_file_name )
# Sort alignments by leftmost coordinates. File <out.prefix>.bam will be created.
# TODO: This command may also create temporary files <out.prefix>.%d.bam when the
# whole alignment cannot be fitted into memory ( controlled by option -m ). We're
# not handling this case here.
tmp_sorted_dataset_file = tempfile.NamedTemporaryFile( prefix=tmp_dataset_file_name )
tmp_sorted_dataset_file_name = tmp_sorted_dataset_file.name
tmp_sorted_dataset_file.close()
command = "samtools sort %s %s 2>/dev/null" % ( tmp_dataset_file_name, tmp_sorted_dataset_file_name )
proc = subprocess.Popen( args=command, shell=True )
proc.wait()
tmp_sorted_bam_file_name = '%s.bam' % tmp_sorted_dataset_file_name
# Move tmp_sorted_bam_file_name to our output dataset location
shutil.move( tmp_sorted_bam_file_name, dataset.file_name )
# Remove all remaining temporary files
os.unlink( tmp_dataset_file_name )
def groom_dataset_content( self, file_name ):
"""
Ensures that the Bam file contents are sorted. This function is called
on an output dataset after the content is initially generated.
"""
# Use samtools to sort the Bam file
tmp_dir = tempfile.gettempdir()
# Create a symlink from the temporary directory to the dataset file so that samtools can mess with it.
tmp_dataset_file_name = os.path.join( tmp_dir, os.path.basename( file_name ) )
# Here tmp_dataset_file_name looks something like /tmp/dataset_XX.dat
os.symlink( file_name, tmp_dataset_file_name )
# Sort alignments by leftmost coordinates. File <out.prefix>.bam will be created.
# TODO: This command may also create temporary files <out.prefix>.%d.bam when the
# whole alignment cannot be fitted into memory ( controlled by option -m ). We're
# not handling this case here.
tmp_sorted_dataset_file = tempfile.NamedTemporaryFile( prefix=tmp_dataset_file_name )
tmp_sorted_dataset_file_name = tmp_sorted_dataset_file.name
tmp_sorted_dataset_file.close()
command = "samtools sort %s %s 2>/dev/null" % ( tmp_dataset_file_name, tmp_sorted_dataset_file_name )
proc = subprocess.Popen( args=command, shell=True )
proc.wait()
tmp_sorted_bam_file_name = '%s.bam' % tmp_sorted_dataset_file_name
# Move tmp_sorted_bam_file_name to our output dataset location
shutil.move( tmp_sorted_bam_file_name, file_name )
# Remove all remaining temporary files
os.unlink( tmp_dataset_file_name )
def init_meta( self, dataset, copy_from=None ):
Binary.init_meta( self, dataset, copy_from=copy_from )
def set_meta( self, dataset, overwrite = True, **kwd ):
@@ -151,9 +138,6 @@ class Binseq( Binary ):
"""Class describing a zip archive of binary sequence files"""
file_ext = "binseq.zip"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
zip_file = zipfile.ZipFile( dataset.file_name, "r" )
@@ -176,9 +160,6 @@ class Scf( Binary ):
"""Class describing an scf binary sequence file"""
file_ext = "scf"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
export_url = "/history_add_to?" + urlencode({'history_id':dataset.history_id,'ext':'scf','name':'scf sequence','info':'Sequence file','dbkey':dataset.dbkey})
@@ -196,11 +177,9 @@ class Scf( Binary ):
class Sff( Binary ):
""" Standard Flowgram Format (SFF) """
file_ext = "sff"
def __init__( self, **kwd ):
Binary.__init__( self, **kwd )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff( self, filename ):
# The first 4 bytes of any sff file is '.sff', and the file is binary. For details
# about the format, see http://www.ncbi.nlm.nih.gov/Traces/trace.cgi?cmd=show&f=formats&m=doc&s=format
lib/galaxy/datatypes/chrominfo.py
-3
View File
@@ -12,6 +12,3 @@ class ChromInfo( Tabular ):
MetadataElement( name="chrom", default=1, desc="Chrom column", param=metadata.ColumnParameter )
MetadataElement( name="length", default=2, desc="Length column", param=metadata.ColumnParameter )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
lib/galaxy/datatypes/coverage.py
+1 -4
View File
@@ -28,10 +28,7 @@ class LastzCoverage( Tabular ):
MetadataElement( name="forwardCol", default=3, desc="Forward or aggregate read column", param=metadata.ColumnParameter )
MetadataElement( name="reverseCol", desc="Optional reverse read column", param=metadata.ColumnParameter, optional=True, no_value=0 )
MetadataElement( name="columns", default=3, desc="Number of columns", readonly=True, visible=False )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def get_track_window(self, dataset, data, start, end):
"""
Assumes we have a numpy file.
lib/galaxy/datatypes/data.py
+3 -6
View File
@@ -84,6 +84,9 @@ class Data( object ):
except OSError, e:
log.exception('%s reading a file that does not exist %s' % (self.__class__.__name__, dataset.file_name))
return ''
def groom_dataset_content( self, file_name ):
"""This function is called on an output dataset file after the content is initially generated."""
pass
def init_meta( self, dataset, copy_from=None ):
# Metadata should be left mostly uninitialized. Dataset will
# handle returning default values when metadata is not set.
@@ -256,9 +259,6 @@ class Data( object ):
if return_output:
return converted_dataset
return "The file conversion of %s on data %s has been added to the Queue." % (converter.name, original_dataset.hid)
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is set."""
pass
def after_setting_metadata( self, dataset ):
"""This function is called on the dataset after metadata is set."""
dataset.clear_associated_files( metadata_safe = True )
@@ -346,9 +346,6 @@ class Text( Data ):
def get_mime(self):
"""Returns the mime type of the datatype"""
return 'text/plain'
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is set."""
pass
def set_meta( self, dataset, **kwd ):
"""
Set the number of lines of data in dataset,
lib/galaxy/datatypes/genetics.py
-64
View File
@@ -47,9 +47,6 @@ class GenomeGraphs(Interval):
self.add_display_app ( 'ucsc', 'display at UCSC', 'as_ucsc_display_file', 'ucsc_links' )
def as_ucsc_display_file( self, dataset, **kwd ):
return open( dataset.file_name )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, overwrite = True, **kwd ):
i = 0
for i, line in enumerate( file ( dataset.file_name ) ):
@@ -205,9 +202,6 @@ class rgTabList(Tabular):
"""Initialize featurelistt datatype"""
Tabular.__init__( self, **kwd )
self.column_names = []
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def make_html_table( self, dataset, skipchars=[] ):
"""Create HTML table, used for displaying peek"""
out = ['<table cellspacing="0" cellpadding="3">']
@@ -246,9 +240,6 @@ class rgSampleList(rgTabList):
self.column_names[0] = 'FID'
self.column_names[1] = 'IID'
# this is what Plink wants as at 2009
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff(self,filename):
"""
"""
@@ -273,9 +264,6 @@ class rgFeatureList( rgTabList ):
rgTabList.__init__( self, **kwd )
for i,s in enumerate(['#FeatureId', 'Chr', 'Genpos', 'Mappos']):
self.column_names[i] = s
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Rgenetics(Html):
"""
@@ -329,9 +317,6 @@ class Rgenetics(Html):
f.write("\n".join( rval ))
f.write('\n')
f.close()
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, **kwd ):
"""
for lped/pbed eg
@@ -373,9 +358,6 @@ class SNPMatrix(Rgenetics):
"""
file_ext="snpmatrix"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
dataset.peek = "Binary RGenetics file"
@@ -405,9 +387,6 @@ class Lped(Rgenetics):
Rgenetics.__init__(self, **kwd)
self.add_composite_file( '%s.ped', description = 'Pedigree File', substitute_name_with_metadata = 'base_name', is_binary = True )
self.add_composite_file( '%s.map', description = 'Map File', substitute_name_with_metadata = 'base_name', is_binary = True )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Pphe(Rgenetics):
"""
@@ -418,9 +397,6 @@ class Pphe(Rgenetics):
def __init__( self, **kwd ):
Rgenetics.__init__(self, **kwd)
self.add_composite_file( '%s.pphe', description = 'Plink Phenotype File', substitute_name_with_metadata = 'base_name' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Lmap(Rgenetics):
"""
@@ -428,10 +404,6 @@ class Lmap(Rgenetics):
"""
file_ext="lmap"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Fphe(Rgenetics):
"""
fake class to distinguish different species of Rgenetics data collections
@@ -441,9 +413,6 @@ class Fphe(Rgenetics):
def __init__( self, **kwd ):
Rgenetics.__init__(self, **kwd)
self.add_composite_file( '%s.fphe', description = 'FBAT Phenotype File', substitute_name_with_metadata = 'base_name' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Phe(Rgenetics):
"""
@@ -454,9 +423,6 @@ class Phe(Rgenetics):
def __init__( self, **kwd ):
Rgenetics.__init__(self, **kwd)
self.add_composite_file( '%s.phe', description = 'Phenotype File', substitute_name_with_metadata = 'base_name' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Fped(Rgenetics):
"""
@@ -467,9 +433,6 @@ class Fped(Rgenetics):
def __init__( self, **kwd ):
Rgenetics.__init__(self, **kwd)
self.add_composite_file( '%s.fped', description = 'FBAT format pedfile', substitute_name_with_metadata = 'base_name' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Pbed(Rgenetics):
"""
@@ -482,9 +445,6 @@ class Pbed(Rgenetics):
self.add_composite_file( '%s.bim', substitute_name_with_metadata = 'base_name', is_binary = True )
self.add_composite_file( '%s.bed', substitute_name_with_metadata = 'base_name', is_binary = True )
self.add_composite_file( '%s.fam', substitute_name_with_metadata = 'base_name', is_binary = True )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Eigenstratgeno(Rgenetics):
"""
@@ -497,9 +457,6 @@ class Eigenstratgeno(Rgenetics):
self.add_composite_file( '%s.eigenstratgeno', substitute_name_with_metadata = 'base_name', is_binary = True )
self.add_composite_file( '%s.ind', substitute_name_with_metadata = 'base_name', is_binary = True )
self.add_composite_file( '%s.map', substitute_name_with_metadata = 'base_name', is_binary = True )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Eigenstratpca(Rgenetics):
"""
@@ -510,27 +467,18 @@ class Eigenstratpca(Rgenetics):
def __init__( self, **kwd ):
Rgenetics.__init__(self, **kwd)
self.add_composite_file( '%s.eigenstratpca', description = 'Eigenstrat PCA file', substitute_name_with_metadata = 'base_name' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Snptest(Rgenetics):
"""
fake class to distinguish different species of Rgenetics data collections
"""
file_ext="snptest"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Pheno(Tabular):
"""
base class for pheno files
"""
file_ext = 'pheno'
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class RexpBase( Html ):
"""
@@ -698,9 +646,6 @@ class RexpBase( Html ):
f.write("\n".join( rval ))
f.write('\n')
f.close()
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def init_meta( self, dataset, copy_from=None ):
"""Add metadata elements"""
if copy_from:
@@ -789,9 +734,6 @@ class Affybatch( RexpBase ):
RexpBase.__init__(self, **kwd)
self.add_composite_file( '%s.affybatch', description = 'AffyBatch R object saved to file',
substitute_name_with_metadata = 'base_name', is_binary=True )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Eset( RexpBase ):
"""derived class for BioC data structures in Galaxy """
@@ -801,9 +743,6 @@ class Eset( RexpBase ):
RexpBase.__init__(self, **kwd)
self.add_composite_file( '%s.eset', description = 'ESet R object saved to file',
substitute_name_with_metadata = 'base_name', is_binary = True )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class MAlist( RexpBase ):
"""derived class for BioC data structures in Galaxy """
@@ -813,9 +752,6 @@ class MAlist( RexpBase ):
RexpBase.__init__(self, **kwd)
self.add_composite_file( '%s.malist', description = 'MAlist R object saved to file',
substitute_name_with_metadata = 'base_name', is_binary = True )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
if __name__ == '__main__':
import doctest, sys
lib/galaxy/datatypes/images.py
+2 -12
View File
@@ -15,9 +15,6 @@ log = logging.getLogger(__name__)
class Image( data.Data ):
"""Class describing an image"""
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
dataset.peek = 'Image in %s format' % dataset.extension
@@ -54,9 +51,6 @@ class Gmaj( data.Data ):
"""Class describing a GMAJ Applet"""
file_ext = "gmaj.zip"
copy_safe_peek = False
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
if hasattr( dataset, 'history_id' ):
@@ -108,9 +102,7 @@ class Gmaj( data.Data ):
class Html( data.Text ):
"""Class describing an html file"""
file_ext = "html"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
dataset.peek = "HTML file"
@@ -145,9 +137,7 @@ class Laj( data.Text ):
"""Class describing a LAJ Applet"""
file_ext = "laj"
copy_safe_peek = False
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
if not dataset.dataset.purged:
if hasattr( dataset, 'history_id' ):
lib/galaxy/datatypes/interval.py
-18
View File
@@ -75,9 +75,6 @@ class Interval( Tabular ):
else:
dataset.peek = 'file does not exist'
dataset.blurb = 'file purged from disk'
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, overwrite = True, first_line_is_header = False, **kwd ):
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = 0 )
@@ -343,9 +340,6 @@ class Bed( Interval ):
MetadataElement( name="columns", default=3, desc="Number of columns", readonly=True, visible=False )
###do we need to repeat these? they are the same as should be inherited from interval type
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, overwrite = True, **kwd ):
"""Sets the metadata information for datasets previously determined to be in bed format."""
i = 0
@@ -504,9 +498,6 @@ class Gff( Tabular ):
"""Initialize datatype, by adding GBrowse display app"""
Tabular.__init__(self, **kwd)
self.add_display_app ( 'c_elegans', 'display in Wormbase', 'as_gbrowse_display_file', 'gbrowse_links' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, overwrite = True, **kwd ):
i = 0
for i, line in enumerate( file ( dataset.file_name ) ):
@@ -644,9 +635,6 @@ class Gff3( Gff ):
def __init__(self, **kwd):
"""Initialize datatype, by adding GBrowse display app"""
Gff.__init__(self, **kwd)
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, overwrite = True, **kwd ):
i = 0
for i, line in enumerate( file ( dataset.file_name ) ):
@@ -810,9 +798,6 @@ class Wiggle( Tabular ):
return ret_val
def make_html_table( self, dataset ):
return Tabular.make_html_table( self, dataset, skipchars=['track', '#'] )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, overwrite = True, **kwd ):
i = 0
for i, line in enumerate( file ( dataset.file_name ) ):
@@ -904,9 +889,6 @@ class CustomTrack ( Tabular ):
"""Initialize interval datatype, by adding UCSC display app"""
Tabular.__init__(self, **kwd)
self.add_display_app ( 'ucsc', 'display at UCSC', 'as_ucsc_display_file', 'ucsc_links' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, overwrite = True, **kwd ):
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = 1 )
def display_peek( self, dataset ):
lib/galaxy/datatypes/qualityscore.py
+1 -12
View File
@@ -15,9 +15,6 @@ class QualityScoreSOLiD ( data.Text ):
"""
file_ext = "qualsolid"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff( self, filename ):
"""
>>> fname = get_test_fname( 'sequence.fasta' )
@@ -67,9 +64,6 @@ class QualityScore454 ( data.Text ):
"""
file_ext = "qual454"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff( self, filename ):
"""
>>> fname = get_test_fname( 'sequence.fasta' )
@@ -108,9 +102,4 @@ class QualityScoreSolexa ( data.Text ):
until we know more about quality score formats
"""
file_ext = "qualsolexa"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
lib/galaxy/datatypes/sequence.py
-29
View File
@@ -21,9 +21,6 @@ class Sequence( data.Text ):
"""Add metadata elements"""
MetadataElement( name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0 )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, **kwd ):
"""
Set the number of sequences and the number of data lines in dataset.
@@ -59,17 +56,10 @@ class Alignment( data.Text ):
"""Add metadata elements"""
MetadataElement( name="species", desc="Species", default=[], param=metadata.SelectParameter, multiple=True, readonly=True, no_value=None )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
class Fasta( Sequence ):
"""Class representing a FASTA sequence"""
file_ext = "fasta"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff( self, filename ):
"""
Determines whether the file is in fasta format
@@ -122,9 +112,6 @@ class csFasta( Sequence ):
""" Class representing the SOLID Color-Space sequence ( csfasta ) """
file_ext = "csfasta"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff( self, filename ):
"""
Color-space sequence:
@@ -166,9 +153,6 @@ class Fastq ( Sequence ):
"""Class representing a generic FASTQ sequence"""
file_ext = "fastq"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_meta( self, dataset, **kwd ):
"""
Set the number of sequences and the number of data lines
@@ -220,10 +204,6 @@ class FastqSanger( Fastq ):
"""Class representing a FASTQ sequence ( the Sanger variant )"""
file_ext = "fastqsanger"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
try:
from galaxy import eggs
import pkg_resources; pkg_resources.require( "bx-python" )
@@ -316,9 +296,6 @@ class Maf( Alignment ):
MetadataElement( name="species_chromosomes", desc="Species Chromosomes", param=metadata.FileParameter, readonly=True, no_value=None, visible=False, optional=True )
MetadataElement( name="maf_index", desc="MAF Index File", param=metadata.FileParameter, readonly=True, no_value=None, visible=False, optional=True )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def init_meta( self, dataset, copy_from=None ):
Alignment.init_meta( self, dataset, copy_from=copy_from )
def set_meta( self, dataset, overwrite = True, **kwd ):
@@ -425,9 +402,6 @@ class Axt( data.Text ):
file_ext = "axt"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff( self, filename ):
"""
Determines whether the file is in axt format
@@ -480,9 +454,6 @@ class Lav( data.Text ):
# here simply for backward compatibility ( although it is still in the datatypes registry ). Subclassing
# from data.Text eliminates managing metadata elements inherited from the Alignemnt class.
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def sniff( self, filename ):
"""
Determines whether the file is in lav format
lib/galaxy/datatypes/tabular.py
-9
View File
@@ -23,9 +23,6 @@ class Tabular( data.Text ):
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=[] )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def init_meta( self, dataset, copy_from=None ):
data.Text.init_meta( self, dataset, copy_from=copy_from )
def set_meta( self, dataset, overwrite = True, skip = None, **kwd ):
@@ -227,9 +224,6 @@ class Taxonomy( Tabular ):
'Superorder', 'Order', 'Suborder', 'Superfamily', 'Family', 'Subfamily',
'Tribe', 'Subtribe', 'Genus', 'Subgenus', 'Species', 'Subspecies'
]
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def make_html_table( self, dataset, skipchars=[] ):
"""Create HTML table, used for displaying peek"""
out = ['<table cellspacing="0" cellpadding="3">']
@@ -259,9 +253,6 @@ class Sam( Tabular ):
self.column_names = ['QNAME', 'FLAG', 'RNAME', 'POS', 'MAPQ', 'CIGAR',
'MRNM', 'MPOS', 'ISIZE', 'SEQ', 'QUAL', 'OPT'
]
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def make_html_table( self, dataset, skipchars=[] ):
"""Create HTML table, used for displaying peek"""
out = ['<table cellspacing="0" cellpadding="3">']
lib/galaxy/datatypes/tracks.py
-3
View File
@@ -23,9 +23,6 @@ class GeneTrack( tabular.Tabular ):
def __init__(self, **kwargs):
super( GeneTrack, self ).__init__( **kwargs )
self.add_display_app( 'genetrack', 'View in', '', 'genetrack_link' )
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def get_display_links( self, dataset, type, app, base_url, target_frame='galaxy_main', **kwd ):
return data.Data.get_display_links( self, dataset, type, app, base_url, target_frame=target_frame, **kwd )
def genetrack_link( self, hda, type, app, base_url ):
lib/galaxy/datatypes/xml.py
-3
View File
@@ -11,9 +11,6 @@ class BlastXml( data.Text ):
"""NCBI Blast XML Output data"""
file_ext = "blastxml"
def before_setting_metadata( self, dataset ):
"""This function is called on the dataset before metadata is edited."""
pass
def set_peek( self, dataset, is_multi_byte=False ):
"""Set the peek and blurb text"""
if not dataset.dataset.purged:
lib/galaxy/jobs/__init__.py
-1
View File
@@ -537,7 +537,6 @@ class JobWrapper( object ):
#it would be quicker to just copy the metadata from the originating output dataset,
#but somewhat trickier (need to recurse up the copied_from tree), for now we'll call set_meta()
if not self.external_output_metadata.external_metadata_set_successfully( dataset, self.sa_session ):
dataset.datatype.before_setting_metadata( dataset )
# Only set metadata values if they are missing...
dataset.set_meta( overwrite = False )
else:
lib/galaxy/tools/__init__.py
-3
View File
@@ -1418,7 +1418,6 @@ class Tool:
if data.extension != data_type:
data = app.datatypes_registry.change_datatype( data, data_type )
elif not isinstance( data.datatype, datatypes.interval.Bed ) and isinstance( data.datatype, datatypes.interval.Interval ):
data.datatype.before_setting_metadata( data )
data.set_meta()
if data.missing_meta():
data = app.datatypes_registry.change_datatype( data, 'tabular' )
@@ -1473,7 +1472,6 @@ class Tool:
self.sa_session.flush()
child_dataset.set_size()
child_dataset.name = "Secondary Dataset (%s)" % ( designation )
child_dataset.datatype.before_setting_metadata( child_dataset )
child_dataset.init_meta()
child_dataset.set_meta()
child_dataset.set_peek()
@@ -1533,7 +1531,6 @@ class Tool:
primary_data.set_size()
primary_data.name = outdata.name
primary_data.info = outdata.info
primary_dataset.datatype.before_setting_metadata( primary_dataset )
primary_data.init_meta( copy_from=outdata )
primary_data.dbkey = dbkey
primary_data.set_meta()
lib/galaxy/web/controllers/library.py
-2
View File
@@ -487,7 +487,6 @@ class Library( BaseController ):
if name not in [ 'name', 'info', 'dbkey' ]:
if spec.get( 'default' ):
setattr( ldda.metadata, name, spec.unwrap( spec.get( 'default' ) ) )
ldda.datatype.before_setting_metadata( ldda )
ldda.datatype.set_meta( ldda )
ldda.datatype.after_setting_metadata( ldda )
trans.sa_session.flush()
@@ -521,7 +520,6 @@ class Library( BaseController ):
msg=msg,
messagetype=messagetype )
if trans.app.security_agent.can_modify_library_item( user, roles, ldda ):
ldda.datatype.before_setting_metadata( ldda )
if "dbkey" in ldda.datatype.metadata_spec and not ldda.metadata.dbkey:
# Copy dbkey into metadata, for backwards compatability
# This looks like it does nothing, but getting the dbkey
lib/galaxy/web/controllers/library_admin.py
-2
View File
@@ -493,7 +493,6 @@ class LibraryAdmin( BaseController ):
if name not in [ 'name', 'info', 'dbkey' ]:
if spec.get( 'default' ):
setattr( ldda.metadata, name, spec.unwrap( spec.get( 'default' ) ) )
ldda.datatype.before_setting_metadata( ldda )
ldda.datatype.set_meta( ldda )
ldda.datatype.after_setting_metadata( ldda )
trans.sa_session.flush()
@@ -517,7 +516,6 @@ class LibraryAdmin( BaseController ):
widgets=widgets,
msg=msg,
messagetype=messagetype )
ldda.datatype.before_setting_metadata( ldda )
if "dbkey" in ldda.datatype.metadata_spec and not ldda.metadata.dbkey:
# Copy dbkey into metadata, for backwards compatability
# This looks like it does nothing, but getting the dbkey
lib/galaxy/web/controllers/root.py
-3
View File
@@ -321,7 +321,6 @@ class RootController( BaseController ):
trans.app.datatypes_registry.set_external_metadata_tool.tool_action.execute( trans.app.datatypes_registry.set_external_metadata_tool, trans, incoming = { 'input1':data } )
else:
msg = 'Attributes updated'
data.datatype.before_setting_metadata( data )
data.set_meta()
data.datatype.after_setting_metadata( data )
trans.sa_session.flush()
@@ -346,7 +345,6 @@ class RootController( BaseController ):
trans.sa_session.refresh( data.dataset )
else:
return trans.show_error_message( "You are not authorized to change this dataset's permissions" )
data.datatype.before_setting_metadata( data )
if "dbkey" in data.datatype.metadata_spec and not data.metadata.dbkey:
# Copy dbkey into metadata, for backwards compatability
# This looks like it does nothing, but getting the dbkey
@@ -521,7 +519,6 @@ class RootController( BaseController ):
data_file.close()
data.state = data.states.OK
data.set_size()
data.datatype.before_setting_metadata( data )
data.init_meta()
data.set_meta()
trans.sa_session.flush()
tools/data_source/hbvar_filter.py
-1
View File
@@ -46,7 +46,6 @@ def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=No
fp.close()
#Set meta data, format file to be valid interval type
if isinstance(data.datatype, datatypes.interval.Interval):
data.datatype.before_setting_metadata( data )
data.set_meta(first_line_is_header=True)
#check for missing meta data, if all there, comment first line and process file
if not data.missing_meta():
tools/data_source/upload.py
+4
View File
@@ -10,6 +10,7 @@ from galaxy import eggs
import galaxy.model
from galaxy.datatypes import sniff
from galaxy.datatypes.binary import *
from galaxy.datatypes.registry import Registry
from galaxy import util
from galaxy.util.json import *
@@ -264,6 +265,9 @@ def add_file( dataset, json_file, output_path ):
name = dataset.name,
line_count = line_count )
json_file.write( to_json_string( info ) + "\n" )
# Groom the dataset content if necessary
datatype = Registry().get_datatype_by_extension( ext )
datatype.groom_dataset_content( output_path )
def add_composite_file( dataset, json_file, output_path, files_path ):
if dataset.composite_files:
tools/maf/maf_to_bed_code.py
-1
View File
@@ -45,7 +45,6 @@ def exec_after_process(app, inp_data, out_data, param_dict, tool, stdout, stderr
newdata.info = "The requested file is missing from the system."
newdata.state = newdata.states.ERROR
newdata.dbkey = dbkey
newdata.datatype.before_setting_metadata( newdata )
newdata.init_meta()
newdata.set_meta()
newdata.set_peek()