mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-21 13:50:20 +08:00
Enhanced upload to handle certain binary and zip files. Cleaned up the upload config. Added 4 new data types: ab1, scf, binseq.zip and txtseq.zip. Added Regional Variation section to tool_conf.xml.main.
This commit is contained in:
Greg Von Kuster
@@ -10,6 +10,66 @@ import zipfile
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
class Ab1( data.Data ):
|
||||
"""Class describing an ab1 binary sequence file"""
|
||||
file_ext = "ab1"
|
||||
def set_peek( self, dataset ):
|
||||
export_url = "/history_add_to?"+urlencode({'history_id':dataset.history_id,'ext':'ab1','name':'ab1 sequence','info':'Sequence file','dbkey':dataset.dbkey})
|
||||
dataset.peek = "Binary ab1 sequence file (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
dataset.blurb = "Binary ab1 sequence file"
|
||||
def display_peek(self, dataset):
|
||||
try:
|
||||
return dataset.peek
|
||||
except:
|
||||
return "Binary ab1 sequence file (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
|
||||
class Scf( data.Data ):
|
||||
"""Class describing an scf binary sequence file"""
|
||||
file_ext = "scf"
|
||||
def set_peek( self, dataset ):
|
||||
export_url = "/history_add_to?"+urlencode({'history_id':dataset.history_id,'ext':'scf','name':'scf sequence','info':'Sequence file','dbkey':dataset.dbkey})
|
||||
dataset.peek = "Binary scf sequence file (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
dataset.blurb = "Binary scf sequence file"
|
||||
def display_peek(self, dataset):
|
||||
try:
|
||||
return dataset.peek
|
||||
except:
|
||||
return "Binary scf sequence file (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
|
||||
class Binseq( data.Data ):
|
||||
"""Class describing a zip archive of binary sequence files"""
|
||||
file_ext = "binseq.zip"
|
||||
def set_peek( self, dataset ):
|
||||
zip_file = zipfile.ZipFile( dataset.file_name, "r" )
|
||||
num_files = len( zip_file.namelist() )
|
||||
dataset.peek = "Binary sequence file archive (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
dataset.blurb = 'Zip archive of %s binary sequence files' % ( str( num_files ) )
|
||||
def display_peek(self, dataset):
|
||||
try:
|
||||
return dataset.peek
|
||||
except:
|
||||
return "Binary sequence file archive (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
def get_mime(self):
|
||||
"""Returns the mime type of the datatype"""
|
||||
return 'application/zip'
|
||||
|
||||
class Txtseq( data.Data ):
|
||||
"""Class describing a zip archive of text sequence files"""
|
||||
file_ext = "txtseq.zip"
|
||||
def set_peek( self, dataset ):
|
||||
zip_file = zipfile.ZipFile( dataset.file_name, "r" )
|
||||
num_files = len( zip_file.namelist() )
|
||||
dataset.peek = "Text sequence file archive (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
dataset.blurb = 'Zip archive of %s text sequence files' % ( str( num_files ) )
|
||||
def display_peek(self, dataset):
|
||||
try:
|
||||
return dataset.peek
|
||||
except:
|
||||
return "Text sequence file archive (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
def get_mime(self):
|
||||
"""Returns the mime type of the datatype"""
|
||||
return 'application/zip'
|
||||
|
||||
class Image( data.Data ):
|
||||
"""Class describing an image"""
|
||||
def set_peek( self, dataset ):
|
||||
@@ -19,11 +79,9 @@ class Image( data.Data ):
|
||||
class Gmaj( data.Data ):
|
||||
"""Class describing a GMAJ Applet"""
|
||||
file_ext = "gmaj.zip"
|
||||
|
||||
def set_peek( self, dataset ):
|
||||
dataset.peek = "<p align=\"center\"><applet code=\"edu.psu.bx.gmaj.MajApplet.class\" archive=\"/static/gmaj/gmaj.jar\" width=\"200\" height=\"30\" align=\"middle\"> <param name=bundle value=\"display?id="+str(dataset.id)+"&tofile=yes&toext=.zip\"> <param name=buttonlabel value=\"Launch GMAJ\"><param name=nobutton value=\"false\"><param name=urlpause value=\"100\"><param name=debug value=\"false\"><i>Your browser is not responding to the <applet> tag.</i></applet></p>"
|
||||
dataset.blurb = 'GMAJ Multiple Alignment Viewer'
|
||||
|
||||
def display_peek(self, dataset):
|
||||
try:
|
||||
return dataset.peek
|
||||
@@ -54,15 +112,12 @@ class Gmaj( data.Data ):
|
||||
class Html( data.Text ):
|
||||
"""Class describing an html file"""
|
||||
file_ext = "html"
|
||||
|
||||
def set_peek( self, dataset ):
|
||||
dataset.peek = "HTML file (%s)" % ( data.nice_size( dataset.get_size() ) )
|
||||
dataset.blurb = data.nice_size( dataset.get_size() )
|
||||
|
||||
def get_mime(self):
|
||||
"""Returns the mime type of the datatype"""
|
||||
return 'text/html'
|
||||
|
||||
def sniff( self, filename ):
|
||||
"""
|
||||
Determines wether the file is in html format
|
||||
@@ -86,7 +141,6 @@ class Html( data.Text ):
|
||||
class Laj( data.Text ):
|
||||
"""Class describing a LAJ Applet"""
|
||||
file_ext = "laj"
|
||||
|
||||
def set_peek( self, dataset ):
|
||||
export_url = "/history_add_to?"+urlencode({'history_id':dataset.history_id,'ext':'lav','name':'LAJ Output','info':'Added by LAJ','dbkey':dataset.dbkey})
|
||||
dataset.peek = "<p align=\"center\"><applet code=\"edu.psu.cse.bio.laj.LajApplet.class\" archive=\"static/laj/laj.jar\" width=\"200\" height=\"30\"><param name=buttonlabel value=\"Launch LAJ\"><param name=title value=\"LAJ in Galaxy\"><param name=posturl value=\""+export_url+"\"><param name=alignfile1 value=\"display?id="+str(dataset.id)+"\"><param name=noseq value=\"true\"></applet></p>"
|
||||
@@ -96,4 +150,3 @@ class Laj( data.Text ):
|
||||
return dataset.peek
|
||||
except:
|
||||
return "peek unavailable"
|
||||
|
||||
|
||||
@@ -37,44 +37,42 @@ class Registry( object ):
|
||||
#default values
|
||||
if len(self.datatypes_by_extension) < 1:
|
||||
self.datatypes_by_extension = {
|
||||
'data' : data.Data(),
|
||||
'bed' : interval.Bed(),
|
||||
'txt' : data.Text(),
|
||||
'interval' : interval.Interval(),
|
||||
'tabular' : tabular.Tabular(),
|
||||
'png' : images.Image(),
|
||||
'pdf' : images.Image(),
|
||||
'fasta' : sequence.Fasta(),
|
||||
'maf' : sequence.Maf(),
|
||||
'axt' : sequence.Axt(),
|
||||
'gff' : interval.Gff(),
|
||||
'gff3' : interval.Gff3(),
|
||||
'wig' : interval.Wiggle(),
|
||||
'gmaj.zip' : images.Gmaj(),
|
||||
'laj' : images.Laj(),
|
||||
'lav' : sequence.Lav(),
|
||||
'html' : images.Html(),
|
||||
'customtrack' : interval.CustomTrack()
|
||||
'ab1' : images.Ab1(),
|
||||
'axt' : sequence.Axt(),
|
||||
'bed' : interval.Bed(),
|
||||
'binseq.zip' : images.Binseq(),
|
||||
'customtrack' : interval.CustomTrack(),
|
||||
'fasta' : sequence.Fasta(),
|
||||
'gff' : interval.Gff(),
|
||||
'gff3' : interval.Gff3(),
|
||||
'interval' : interval.Interval(),
|
||||
'laj' : images.Laj(),
|
||||
'lav' : sequence.Lav(),
|
||||
'maf' : sequence.Maf(),
|
||||
'scf' : images.Scf(),
|
||||
'tabular' : tabular.Tabular(),
|
||||
'txt' : data.Text(),
|
||||
'txtseq.zip' : images.Txtseq(),
|
||||
'wig' : interval.Wiggle()
|
||||
}
|
||||
self.mimetypes_by_extension = {
|
||||
'data' : 'application/octet-stream',
|
||||
'bed' : 'text/plain',
|
||||
'txt' : 'text/plain',
|
||||
'interval' : 'text/plain',
|
||||
'tabular' : 'text/plain',
|
||||
'png' : 'image/png',
|
||||
'pdf' : 'application/pdf',
|
||||
'fasta' : 'text/plain',
|
||||
'maf' : 'text/plain',
|
||||
'axt' : 'text/plain',
|
||||
'gff' : 'text/plain',
|
||||
'gff3' : 'text/plain',
|
||||
'wig' : 'text/plain',
|
||||
'gmaj.zip' : 'application/zip',
|
||||
'laj' : 'text/plain',
|
||||
'lav' : 'text/plain',
|
||||
'html' : 'text/html',
|
||||
'customtrack' : 'text/plain'
|
||||
'ab1' : 'application/octet-stream',
|
||||
'axt' : 'text/plain',
|
||||
'bed' : 'text/plain',
|
||||
'binseq.zip' : 'application/zip',
|
||||
'customtrack' : 'text/plain',
|
||||
'fasta' : 'text/plain',
|
||||
'gff' : 'text/plain',
|
||||
'gff3' : 'text/plain',
|
||||
'interval' : 'text/plain',
|
||||
'laj' : 'text/plain',
|
||||
'lav' : 'text/plain',
|
||||
'maf' : 'text/plain',
|
||||
'scf' : 'application/octet-stream',
|
||||
'tabular' : 'text/plain',
|
||||
'txt' : 'text/plain',
|
||||
'txtseq.zip' : 'application/zip',
|
||||
'wig' : 'text/plain'
|
||||
}
|
||||
"""
|
||||
The order in which we attempt to determine data types is critical
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import os, shutil, urllib, StringIO, re
|
||||
import os, shutil, urllib, StringIO, re, gzip, tempfile, shutil, zipfile
|
||||
from galaxy import datatypes, jobs
|
||||
from galaxy.datatypes import sniff
|
||||
from galaxy import model, util
|
||||
@@ -9,10 +9,9 @@ import logging
|
||||
log = logging.getLogger( __name__ )
|
||||
|
||||
class UploadToolAction( object ):
|
||||
"""
|
||||
Action for uploading files
|
||||
"""
|
||||
empty = False
|
||||
# Action for uploading files
|
||||
def __init__( self ):
|
||||
self.empty = False
|
||||
|
||||
def execute( self, tool, trans, incoming={} ):
|
||||
data_file = incoming['file_data']
|
||||
@@ -21,44 +20,36 @@ class UploadToolAction( object ):
|
||||
url_paste = incoming['url_paste']
|
||||
space_to_tab = False
|
||||
if 'space_to_tab' in incoming:
|
||||
if incoming['space_to_tab'] not in ["None", None]:
|
||||
if incoming['space_to_tab'] not in ["None", None]:
|
||||
space_to_tab = True
|
||||
info = "uploaded file"
|
||||
temp_name = ""
|
||||
data_list = []
|
||||
self.empty = False
|
||||
if 'filename' in dir(data_file):
|
||||
|
||||
if 'filename' in dir( data_file ):
|
||||
try:
|
||||
file_name = data_file.filename
|
||||
file_name = file_name.split('\\')[-1]
|
||||
file_name = file_name.split('/')[-1]
|
||||
data_list.append( self.add_file(trans, data_file.file, file_name, file_type, dbkey, "uploaded file",space_to_tab=space_to_tab) )
|
||||
except BadFileException:
|
||||
return self.upload_empty( trans, "Error", "attempted to upload an empty or inappropriate file")
|
||||
except:
|
||||
pass
|
||||
|
||||
file_name = file_name.split( '\\' )[-1]
|
||||
file_name = file_name.split( '/' )[-1]
|
||||
data_list.append( self.add_file( trans, data_file.file, file_name, file_type, dbkey, space_to_tab=space_to_tab ) )
|
||||
except BadFileException, e:
|
||||
return self.upload_empty( trans, "Error:", str( e ) )
|
||||
if url_paste not in [None, ""]:
|
||||
if url_paste[0:7].lower() == "http://" or url_paste[0:6].lower() == "ftp://" :
|
||||
url_paste = url_paste.replace("\r","").split("\n")
|
||||
if url_paste[0:7].lower() == "http://" or url_paste[0:6].lower() == "ftp://":
|
||||
url_paste = url_paste.replace( "\r","" ).split("\n")
|
||||
for line in url_paste:
|
||||
try:
|
||||
data_list.append( self.add_file(trans, urllib.urlopen(line), line, file_type, dbkey, "uploaded url",space_to_tab=space_to_tab) )
|
||||
except BadFileException:
|
||||
return self.upload_empty( trans, "Error", "attempted to upload an empty or inappropriate file")
|
||||
except:
|
||||
pass
|
||||
data_list.append( self.add_file( trans, urllib.urlopen( line ), line, file_type, dbkey, info="uploaded url", space_to_tab=space_to_tab ) )
|
||||
except BadFileException, e:
|
||||
return self.upload_empty( trans, "Error:", str( e ) )
|
||||
else:
|
||||
try:
|
||||
data_list.append( self.add_file(trans, StringIO.StringIO(url_paste), 'Pasted Entry', file_type, dbkey, "pasted entry",space_to_tab=space_to_tab) )
|
||||
except BadFileException:
|
||||
return self.upload_empty( trans, "Error", "attempted to upload an empty or inappropriate file" )
|
||||
except:
|
||||
pass
|
||||
data_list.append( self.add_file( trans, StringIO.StringIO( url_paste ), 'Pasted Entry', file_type, dbkey, info="pasted entry", space_to_tab=space_to_tab ) )
|
||||
except BadFileException, e:
|
||||
return self.upload_empty( trans, "Error:", str( e ) )
|
||||
if self.empty:
|
||||
return self.upload_empty(trans, "Empty file error:", "attempted to upload an empty file")
|
||||
elif len(data_list)<1:
|
||||
return self.upload_empty(trans, "No data error:","either you pasted no data, the url you specified is invalid, or you have not specified a file")
|
||||
return self.upload_empty( trans, "Empty file error:", "you attempted to upload an empty file." )
|
||||
elif len( data_list ) < 1:
|
||||
return self.upload_empty( trans, "No data error:","either you pasted no data, the url you specified is invalid, or you have not specified a file." )
|
||||
return dict( output=data_list[0] )
|
||||
|
||||
def upload_empty(self, trans, err_code, err_msg):
|
||||
@@ -73,33 +64,84 @@ class UploadToolAction( object ):
|
||||
trans.app.model.flush()
|
||||
return dict( output=data )
|
||||
|
||||
def add_file(self, trans, file_obj, file_name, file_type, dbkey, info, space_to_tab = False ):
|
||||
temp_name = sniff.stream_to_file(file_obj)
|
||||
def add_file( self, trans, file_obj, file_name, file_type, dbkey, info=None, space_to_tab=False ):
|
||||
data_type = None
|
||||
temp_name = sniff.stream_to_file( file_obj )
|
||||
|
||||
# See if we have an empty file
|
||||
if not os.path.getsize( temp_name ) > 0:
|
||||
raise BadFileException( "you attempted to upload an empty file." )
|
||||
|
||||
# See if we have a gzipped file, which, if it passes our restrictions, we'll decompress on the fly.
|
||||
is_gzipped, is_valid = self.check_gzip( temp_name )
|
||||
if is_gzipped and not is_valid:
|
||||
raise BadFileException( "you attempted to upload an inappropriate file." )
|
||||
elif is_gzipped and is_valid:
|
||||
#We need to decompress the temp_name file
|
||||
CHUNK_SIZE = 2**20 # 1Mb
|
||||
fd, uncompressed = tempfile.mkstemp()
|
||||
gzipped_file = gzip.GzipFile( temp_name )
|
||||
while 1:
|
||||
try:
|
||||
chunk = gzipped_file.read( CHUNK_SIZE )
|
||||
except IOError:
|
||||
uncompressed.close()
|
||||
raise BadFileException( 'problem decompressing gzipped data.' )
|
||||
if not chunk:
|
||||
break
|
||||
os.write( fd, chunk )
|
||||
os.close( fd )
|
||||
gzipped_file.close()
|
||||
# Replace the gzipped file with the decompressed file
|
||||
shutil.move( uncompressed, temp_name )
|
||||
file_name = file_name.rstrip( '.gz' )
|
||||
data_type = 'gzip'
|
||||
|
||||
try:
|
||||
# Check against undesireable file data:
|
||||
if self.check_html( temp_name ) or self.check_binary( temp_name ):
|
||||
self.empty = True
|
||||
except:
|
||||
#User is attempting to upload a non-text file, but for some reason check_binary didn't work...
|
||||
self.empty = True
|
||||
if not data_type:
|
||||
# See if we have a zip archive
|
||||
is_zipped, is_valid, test_ext = self.check_zip( temp_name )
|
||||
if is_zipped and not is_valid:
|
||||
raise BadFileException( "you attempted to upload an inappropriate file." )
|
||||
elif is_zipped and is_valid:
|
||||
# Currently, we force specific tools to handle this case. We also require the user
|
||||
# to manually set the incoming file_type
|
||||
if ( test_ext == 'ab1' or test_ext == 'scf' ) and file_type != 'binseq.zip':
|
||||
raise BadFileException( "Invalid 'File Format' for archive consisting of binary files - use 'Binseq.zip'." )
|
||||
elif test_ext == 'txt' and file_type != 'txtseq.zip':
|
||||
raise BadFileException( "Invalid 'File Format' for archive consisting of text files - use 'Txtseq.zip'." )
|
||||
if not ( file_type == 'binseq.zip' or file_type == 'txtseq.zip' ):
|
||||
raise BadFileException( "you must manually set the 'File Format' to either 'Binseq.zip' or 'Txtseq.zip' when uploading zip files." )
|
||||
data_type = 'zip'
|
||||
ext = file_type
|
||||
|
||||
if not data_type:
|
||||
if self.check_binary( temp_name ):
|
||||
ext = file_name.split( "." )[1].strip().lower()
|
||||
if not( ext == 'ab1' or ext == 'scf' ):
|
||||
raise BadFileException( "you attempted to upload an inappropriate file." )
|
||||
if ext == 'ab1' and file_type != 'ab1':
|
||||
raise BadFileException( "you must manually set the 'File Format' to 'Ab1' when uploading ab1 files." )
|
||||
elif ext == 'scf' and file_type != 'scf':
|
||||
raise BadFileException( "you must manually set the 'File Format' to 'Scf' when uploading scf files." )
|
||||
data_type = 'binary'
|
||||
|
||||
if self.empty:
|
||||
raise BadFileException( "attempted to upload an empty or inappropriate file" )
|
||||
|
||||
"""
|
||||
NOTE: the following will keep binary and zip files (e.g., gmaj.zip) from being correctly sniffed, but
|
||||
the files can be uploaded (they'll be sniffed as 'txt'). This should restrict some unwanted behavior.
|
||||
"""
|
||||
sniff.convert_newlines(temp_name)
|
||||
|
||||
if space_to_tab:
|
||||
sniff.sep2tabs(temp_name)
|
||||
|
||||
if file_type == 'auto':
|
||||
ext = sniff.guess_ext(temp_name)
|
||||
else:
|
||||
ext = file_type
|
||||
if not data_type:
|
||||
# We must have a text file
|
||||
if self.check_html( temp_name ):
|
||||
raise BadFileException( "you attempted to upload an inappropriate file." )
|
||||
|
||||
if data_type != 'binary' and data_type != 'zip':
|
||||
sniff.convert_newlines( temp_name )
|
||||
if space_to_tab:
|
||||
sniff.sep2tabs( temp_name )
|
||||
if file_type == 'auto':
|
||||
ext = sniff.guess_ext( temp_name )
|
||||
else:
|
||||
ext = file_type
|
||||
data_type = ext
|
||||
|
||||
if info is None:
|
||||
info = 'uploaded %s file' %data_type
|
||||
|
||||
data = trans.app.model.Dataset()
|
||||
data.name = file_name
|
||||
@@ -119,37 +161,72 @@ class UploadToolAction( object ):
|
||||
data.add_validation_error(
|
||||
model.ValidationError( message=str( error ), err_type=error.__class__.__name__, attributes=util.object_to_string( error.__dict__ ) ) )
|
||||
"""
|
||||
if data.has_data():
|
||||
if data.missing_meta():
|
||||
data.datatype.set_meta(data)
|
||||
dbkey_to_store = dbkey
|
||||
if type(dbkey_to_store) == type([]):
|
||||
dbkey_to_store = dbkey[0]
|
||||
trans.history.add_dataset( data, genome_build=dbkey_to_store )
|
||||
trans.app.model.flush()
|
||||
trans.log_event("Added dataset %d to history %d" %(data.id, trans.history.id), tool_id="upload")
|
||||
else:
|
||||
self.empty = True
|
||||
if data.missing_meta():
|
||||
data.datatype.set_meta( data )
|
||||
dbkey_to_store = dbkey
|
||||
if type( dbkey_to_store ) == type( [] ):
|
||||
dbkey_to_store = dbkey[0]
|
||||
trans.history.add_dataset( data, genome_build=dbkey_to_store )
|
||||
trans.app.model.flush()
|
||||
trans.log_event( "Added dataset %d to history %d" %( data.id, trans.history.id ), tool_id="upload" )
|
||||
return data
|
||||
|
||||
def check_html( self, temp_name ):
|
||||
temp = open(temp_name, "U")
|
||||
def check_gzip( self, temp_name ):
|
||||
temp = open( temp_name, "U" )
|
||||
magic_check = temp.read( 2 )
|
||||
temp.close()
|
||||
if magic_check != datatypes.data.gzip_magic:
|
||||
return ( False, False )
|
||||
CHUNK_SIZE = 2**15 # 32Kb
|
||||
gzipped_file = gzip.GzipFile( temp_name )
|
||||
chunk = gzipped_file.read( CHUNK_SIZE )
|
||||
gzipped_file.close()
|
||||
if self.check_html( temp_name, chunk=chunk ) or self.check_binary( temp_name, chunk=chunk ):
|
||||
return( True, False )
|
||||
return ( True, True )
|
||||
|
||||
def check_zip( self, temp_name ):
|
||||
if not zipfile.is_zipfile( temp_name ):
|
||||
return ( False, False, None )
|
||||
zip_file = zipfile.ZipFile( temp_name, "r" )
|
||||
# Make sure the archive consists of valid files. The current rules are:
|
||||
# 1. Archives can only include .ab1, .scf or .txt files
|
||||
# 2. All file extensions within an archive must be the same
|
||||
name = zip_file.namelist()[0]
|
||||
test_ext = name.split( "." )[1].strip().lower()
|
||||
if not ( test_ext == 'scf' or test_ext == 'ab1' or test_ext == 'txt' ):
|
||||
return ( True, False, test_ext )
|
||||
for name in zip_file.namelist():
|
||||
ext = name.split( "." )[1].strip().lower()
|
||||
if ext != test_ext:
|
||||
return ( True, False, test_ext )
|
||||
return ( True, True, test_ext )
|
||||
|
||||
def check_html( self, temp_name, chunk=None ):
|
||||
if chunk is None:
|
||||
temp = open(temp_name, "U")
|
||||
else:
|
||||
temp = chunk
|
||||
regexp = re.compile( "<([A-Z][A-Z0-9]*)[^>]*>", re.I )
|
||||
lineno = 0
|
||||
for line in temp:
|
||||
lineno += 1
|
||||
matches = regexp.search( line )
|
||||
if matches:
|
||||
temp.close()
|
||||
if chunk is None:
|
||||
temp.close()
|
||||
return True
|
||||
if lineno > 100:
|
||||
# We should be able to detmine an HTML file within 100 lines.
|
||||
break
|
||||
temp.close()
|
||||
if chunk is None:
|
||||
temp.close()
|
||||
return False
|
||||
|
||||
def check_binary( self, temp_name ):
|
||||
temp = open( temp_name, "U" )
|
||||
def check_binary( self, temp_name, chunk=None ):
|
||||
if chunk is None:
|
||||
temp = open( temp_name, "U" )
|
||||
else:
|
||||
temp = chunk
|
||||
lineno = 0
|
||||
for line in temp:
|
||||
lineno += 1
|
||||
@@ -157,11 +234,13 @@ class UploadToolAction( object ):
|
||||
if line:
|
||||
for char in line:
|
||||
if ord( char ) > 128:
|
||||
temp.close()
|
||||
if chunk is None:
|
||||
temp.close()
|
||||
return True
|
||||
if lineno > 100:
|
||||
break
|
||||
temp.close()
|
||||
if chunk is None:
|
||||
temp.close()
|
||||
return False
|
||||
|
||||
class BadFileException( Exception ):
|
||||
|
||||
@@ -113,6 +113,14 @@
|
||||
<!-- <tool file="data_source/show_in_ucsc.xml" /> -->
|
||||
<tool file="visualization/build_ucsc_custom_track.xml" />
|
||||
</section>
|
||||
<section name="Regional Variation" id="regVar">
|
||||
<tool file="regVariation/windowSplitter.xml" />
|
||||
<tool file="regVariation/featureCounter.xml" />
|
||||
<tool file="regVariation/quality_filter.xml" />
|
||||
<tool file="regVariation/maf_cpg_filter.xml" />
|
||||
<tool file="regVariation/getIndels_2way.xml" />
|
||||
<tool file="regVariation/getIndels_3way.xml" />
|
||||
</section>
|
||||
<section name="Evolution: HyPhy" id="hyphy">
|
||||
<tool file="hyphy/hyphy_branch_lengths_wrapper.xml" />
|
||||
<tool file="hyphy/hyphy_nj_tree_wrapper.xml" />
|
||||
|
||||
@@ -17,9 +17,30 @@
|
||||
<param name="dbkey" type="genomebuild" label="Genome" />
|
||||
</inputs>
|
||||
<help>
|
||||
|
||||
**Auto-detect**
|
||||
|
||||
The system will attempt to detect AXT, FASTA, Gff, HTML, LAV, Maf, Wiggle, BED and Interval (BED with headers) formats. Other formats will be set to generic text files. If your file is not detected properly as one of the known formats, it most likely means that it has some format problems (e.g., different number of columns on different rows). You can still coerce the system to set your data to the format you think it should be (please send us a note if you see a case when a valid format is not detected).
|
||||
The system will attempt to detect AXT, FASTA, Gff, HTML, LAV, Maf, Tabular, Wiggle, BED and Interval (BED with headers) formats. If your file is not detected properly as one of the known formats, it most likely means that it has some format problems (e.g., different number of columns on different rows). You can still coerce the system to set your data to the format you think it should be (please send us a note if you see a case when a valid format is not detected). You can also upload valid files that are compressed (gzipped), which will automatically be decompressed upon upload.
|
||||
|
||||
-----
|
||||
|
||||
**Ab1**
|
||||
|
||||
A binary sequence file in 'ab1' format with a '.ab1' file extension. You must manually select this 'File Format' when uploading the file.
|
||||
|
||||
-----
|
||||
|
||||
**AXT**
|
||||
|
||||
blastz pairwise alignment format. Each alignment block in an axt file contains three lines: a summary line and 2 sequence lines. Blocks are separated from one another by blank lines. The summary line contains chromosomal position and size information about the alignment. It consists of 9 required fields.
|
||||
|
||||
-----
|
||||
|
||||
**Binseq.zip**
|
||||
|
||||
A zipped archive consisting of binary sequence files in either 'ab1' or 'scf' format. All files in this archive must have the same file extension which is one of '.ab1' or '.scf'. You must manually select this 'File Format' when uploading the file.
|
||||
|
||||
-----
|
||||
|
||||
**BED**
|
||||
|
||||
@@ -50,32 +71,6 @@ The system will attempt to detect AXT, FASTA, Gff, HTML, LAV, Maf, Wiggle, BED a
|
||||
|
||||
-----
|
||||
|
||||
**Genomic Intervals**
|
||||
|
||||
- Tab delimited format (tabular)
|
||||
- File must start with definition line in the following format (columns may be in any order).::
|
||||
|
||||
#CHROM START END STRAND
|
||||
|
||||
- CHROM - The name of the chromosome (e.g. chr3, chrY, chr2_random) or contig (e.g. ctgY1).
|
||||
- START - The starting position of the feature in the chromosome or contig. The first base in a chromosome is numbered 0.
|
||||
- END - The ending position of the feature in the chromosome or contig. The chromEnd base is not included in the display of the feature. For example, the first 100 bases of a chromosome are defined as chromStart=0, chromEnd=100, and span the bases numbered 0-99.
|
||||
- STRAND - Defines the strand - either '+' or '-'.
|
||||
|
||||
- Example::
|
||||
|
||||
#CHROM START END STRAND NAME COMMENT
|
||||
chr1 10 100 + exon myExon
|
||||
chrX 1000 10050 - gene myGene
|
||||
|
||||
-----
|
||||
|
||||
**AXT**
|
||||
|
||||
blastz pairwise alignment format. Each alignment block in an axt file contains three lines: a summary line and 2 sequence lines. Blocks are separated from one another by blank lines. The summary line contains chromosomal position and size information about the alignment. It consists of 9 required fields.
|
||||
|
||||
-----
|
||||
|
||||
**FASTA**
|
||||
|
||||
A sequence in FASTA format consists of a single-line description, followed by lines of sequence data. The first character of the description line is a greater-than (">") symbol in the first column. All lines should be shorter than 80 charcters::
|
||||
@@ -101,6 +96,26 @@ The GFF3 format addresses the most common extensions to GFF, while preserving ba
|
||||
|
||||
-----
|
||||
|
||||
**Interval (Genomic Intervals)**
|
||||
|
||||
- Tab delimited format (tabular)
|
||||
- File must start with definition line in the following format (columns may be in any order).::
|
||||
|
||||
#CHROM START END STRAND
|
||||
|
||||
- CHROM - The name of the chromosome (e.g. chr3, chrY, chr2_random) or contig (e.g. ctgY1).
|
||||
- START - The starting position of the feature in the chromosome or contig. The first base in a chromosome is numbered 0.
|
||||
- END - The ending position of the feature in the chromosome or contig. The chromEnd base is not included in the display of the feature. For example, the first 100 bases of a chromosome are defined as chromStart=0, chromEnd=100, and span the bases numbered 0-99.
|
||||
- STRAND - Defines the strand - either '+' or '-'.
|
||||
|
||||
- Example::
|
||||
|
||||
#CHROM START END STRAND NAME COMMENT
|
||||
chr1 10 100 + exon myExon
|
||||
chrX 1000 10050 - gene myGene
|
||||
|
||||
-----
|
||||
|
||||
**Lav**
|
||||
|
||||
Lav is the primary output format for BLASTZ. The first line of a .lav file begins with #:lav..
|
||||
@@ -113,18 +128,30 @@ TBA and multiz multiple alignment format. The first line of a .maf file begins
|
||||
|
||||
-----
|
||||
|
||||
**Wiggle**
|
||||
**Scf**
|
||||
|
||||
The .wig format is line-oriented. Wiggle data is preceeded by a track definition line, which adds a number of options for controlling the default display of this track.
|
||||
A binary sequence file in 'scf' format with a '.scf' file extension. You must manually select this 'File Format' when uploading the file.
|
||||
|
||||
-----
|
||||
|
||||
**Tab delimited**
|
||||
**Tabular (tab delimited)**
|
||||
|
||||
Any data in tab delimited format (tabular)
|
||||
|
||||
-----
|
||||
|
||||
**Txtseq.zip**
|
||||
|
||||
A zipped archive consisting of flat text sequence files. All files in this archive must have the same file extension of '.txt'. You must manually select this 'File Format' when uploading the file.
|
||||
|
||||
-----
|
||||
|
||||
**Wig**
|
||||
|
||||
The wiggle format is line-oriented. Wiggle data is preceeded by a track definition line, which adds a number of options for controlling the default display of this track.
|
||||
|
||||
-----
|
||||
|
||||
**Other text type**
|
||||
|
||||
Any text file
|
||||
|
||||
+58
-53
@@ -105,73 +105,78 @@ static_style_dir = %(here)s/static/june_2007_style/blue
|
||||
|
||||
[galaxy:datatypes]
|
||||
|
||||
data = galaxy.datatypes.data:Data,application/octet-stream
|
||||
bed = galaxy.datatypes.interval:Bed
|
||||
txt = galaxy.datatypes.data:Text
|
||||
interval = galaxy.datatypes.interval:Interval
|
||||
tabular = galaxy.datatypes.tabular:Tabular
|
||||
png = galaxy.datatypes.images:Image,image/png
|
||||
pdf = galaxy.datatypes.images:Image,application/pdf
|
||||
gif = galaxy.datatypes.images:Image,image/gif
|
||||
jpg = galaxy.datatypes.images:Image,image/jpeg
|
||||
fasta = galaxy.datatypes.sequence:Fasta
|
||||
maf = galaxy.datatypes.sequence:Maf
|
||||
ab1 = galaxy.datatypes.images:Ab1,application/octet-stream
|
||||
axt = galaxy.datatypes.sequence:Axt
|
||||
bed = galaxy.datatypes.interval:Bed
|
||||
binseq.zip = galaxy.datatypes.images:Binseq,application/zip
|
||||
customtrack = galaxy.datatypes.interval:CustomTrack
|
||||
data = galaxy.datatypes.data:Data,application/octet-stream
|
||||
fasta = galaxy.datatypes.sequence:Fasta
|
||||
gbrowsetrack = galaxy.datatypes.interval:GBrowseTrack
|
||||
gff = galaxy.datatypes.interval:Gff
|
||||
gff3 = galaxy.datatypes.interval:Gff3
|
||||
wig = galaxy.datatypes.interval:Wiggle
|
||||
gif = galaxy.datatypes.images:Image,image/gif
|
||||
gmaj.zip = galaxy.datatypes.images:Gmaj,application/zip
|
||||
html = galaxy.datatypes.images:Html,text/html
|
||||
interval = galaxy.datatypes.interval:Interval
|
||||
jpg = galaxy.datatypes.images:Image,image/jpeg
|
||||
laj = galaxy.datatypes.images:Laj
|
||||
lav = galaxy.datatypes.sequence:Lav
|
||||
html = galaxy.datatypes.images:Html,text/html
|
||||
customtrack = galaxy.datatypes.interval:CustomTrack
|
||||
maf = galaxy.datatypes.sequence:Maf
|
||||
pdf = galaxy.datatypes.images:Image,application/pdf
|
||||
png = galaxy.datatypes.images:Image,image/png
|
||||
scf = galaxy.datatypes.images:Scf,application/octet-stream
|
||||
tabular = galaxy.datatypes.tabular:Tabular
|
||||
txt = galaxy.datatypes.data:Text
|
||||
txtseq.zip = galaxy.datatypes.images:Txtseq,application/zip
|
||||
wig = galaxy.datatypes.interval:Wiggle
|
||||
#EMBOSS TOOLS
|
||||
match = galaxy.datatypes.data:Text
|
||||
genbank = galaxy.datatypes.data:Text
|
||||
motif = galaxy.datatypes.data:Text
|
||||
acedb = galaxy.datatypes.data:Text
|
||||
nexus = galaxy.datatypes.data:Text
|
||||
fitch = galaxy.datatypes.data:Text
|
||||
meganon = galaxy.datatypes.data:Text
|
||||
codata = galaxy.datatypes.data:Text
|
||||
dbmotif = galaxy.datatypes.data:Text
|
||||
table = galaxy.datatypes.data:Text
|
||||
pir = galaxy.datatypes.data:Text
|
||||
ig = galaxy.datatypes.data:Text
|
||||
seqtable = galaxy.datatypes.data:Text
|
||||
clustal = galaxy.datatypes.data:Text
|
||||
gcg = galaxy.datatypes.data:Text
|
||||
hennig86 = galaxy.datatypes.data:Text
|
||||
excel = galaxy.datatypes.data:Text
|
||||
asn1 = galaxy.datatypes.data:Text
|
||||
regions = galaxy.datatypes.data:Text
|
||||
simple = galaxy.datatypes.data:Text
|
||||
score = galaxy.datatypes.data:Text
|
||||
msf = galaxy.datatypes.data:Text
|
||||
selex = galaxy.datatypes.data:Text
|
||||
tagseq = galaxy.datatypes.data:Text
|
||||
clustal = galaxy.datatypes.data:Text
|
||||
codata = galaxy.datatypes.data:Text
|
||||
diffseq = galaxy.datatypes.data:Text
|
||||
dbmotif = galaxy.datatypes.data:Text
|
||||
embl = galaxy.datatypes.data:Text
|
||||
excel = galaxy.datatypes.data:Text
|
||||
feattable = galaxy.datatypes.data:Text
|
||||
fitch = galaxy.datatypes.data:Text
|
||||
gcg = galaxy.datatypes.data:Text
|
||||
genbank = galaxy.datatypes.data:Text
|
||||
hennig86 = galaxy.datatypes.data:Text
|
||||
ig = galaxy.datatypes.data:Text
|
||||
jackknifer = galaxy.datatypes.data:Text
|
||||
jackknifernon = galaxy.datatypes.data:Text
|
||||
markx0 = galaxy.datatypes.data:Text
|
||||
markx1 = galaxy.datatypes.data:Text
|
||||
markx10 = galaxy.datatypes.data:Text
|
||||
markx2 = galaxy.datatypes.data:Text
|
||||
markx3 = galaxy.datatypes.data:Text
|
||||
match = galaxy.datatypes.data:Text
|
||||
mega = galaxy.datatypes.data:Text
|
||||
meganon = galaxy.datatypes.data:Text
|
||||
motif = galaxy.datatypes.data:Text
|
||||
msf = galaxy.datatypes.data:Text
|
||||
nametable = galaxy.datatypes.data:Text
|
||||
ncbi = galaxy.datatypes.data:Text
|
||||
nexus = galaxy.datatypes.data:Text
|
||||
nexusnon = galaxy.datatypes.data:Text
|
||||
pair = galaxy.datatypes.data:Text
|
||||
phylip = galaxy.datatypes.data:Text
|
||||
phylipnon = galaxy.datatypes.data:Text
|
||||
pir = galaxy.datatypes.data:Text
|
||||
regions = galaxy.datatypes.data:Text
|
||||
score = galaxy.datatypes.data:Text
|
||||
selex = galaxy.datatypes.data:Text
|
||||
seqtable = galaxy.datatypes.data:Text
|
||||
simple = galaxy.datatypes.data:Text
|
||||
srs = galaxy.datatypes.data:Text
|
||||
srspair = galaxy.datatypes.data:Text
|
||||
staden = galaxy.datatypes.data:Text
|
||||
strider = galaxy.datatypes.data:Text
|
||||
markx10 = galaxy.datatypes.data:Text
|
||||
pair = galaxy.datatypes.data:Text
|
||||
markx1 = galaxy.datatypes.data:Text
|
||||
markx0 = galaxy.datatypes.data:Text
|
||||
markx3 = galaxy.datatypes.data:Text
|
||||
markx2 = galaxy.datatypes.data:Text
|
||||
jackknifer = galaxy.datatypes.data:Text
|
||||
ncbi = galaxy.datatypes.data:Text
|
||||
mega = galaxy.datatypes.data:Text
|
||||
feattable = galaxy.datatypes.data:Text
|
||||
phylip = galaxy.datatypes.data:Text
|
||||
diffseq = galaxy.datatypes.data:Text
|
||||
srs = galaxy.datatypes.data:Text
|
||||
jackknifernon = galaxy.datatypes.data:Text
|
||||
swiss = galaxy.datatypes.data:Text
|
||||
phylipnon = galaxy.datatypes.data:Text
|
||||
nexusnon = galaxy.datatypes.data:Text
|
||||
nametable = galaxy.datatypes.data:Text
|
||||
table = galaxy.datatypes.data:Text
|
||||
tagseq = galaxy.datatypes.data:Text
|
||||
|
||||
# ---- Data Type Sniff Order --------------------------------------------------
|
||||
|
||||
|
||||
Reference in New Issue
Block a user