def check_file_content_for_html_and_images( file_path ):
message = ''
if checkers.check_html( file_path ):
message = 'The file "%s" contains HTML content.\n' % str( file_path )
elif checkers.check_image( file_path ):
message = 'The file "%s" contains image content.\n' % str( file_path )
return message
def check_file_content_for_html_and_images(file_path):
message = ''
if checkers.check_html(file_path):
message = 'The file "%s" contains HTML content.\n' % str(file_path)
elif checkers.check_image(file_path):
message = 'The file "%s" contains image content.\n' % str(file_path)
return message
def handle_uploaded_dataset_file(filename,
datatypes_registry,
ext='auto',
is_multi_byte=False):
is_valid, ext = handle_compressed_file(filename,
datatypes_registry,
ext=ext)
if not is_valid:
raise InappropriateDatasetContentError(
'The compressed uploaded file contains inappropriate content.')
if ext in AUTO_DETECT_EXTENSIONS:
ext = guess_ext(filename,
sniff_order=datatypes_registry.sniff_order,
is_multi_byte=is_multi_byte)
if check_binary(filename):
if not Binary.is_ext_unsniffable(
ext) and not datatypes_registry.get_datatype_by_extension(
ext).sniff(filename):
raise InappropriateDatasetContentError(
'The binary uploaded file contains inappropriate content.')
elif check_html(filename):
raise InappropriateDatasetContentError(
'The uploaded file contains inappropriate HTML content.')
return ext
def __check_file_content( self, file_path ):
message = ''
if checkers.check_html( file_path ):
message = 'The file "%s" contains HTML content.\n' % str( file_path )
elif checkers.check_image( file_path ):
message = 'The file "%s" contains image content.\n' % str( file_path )
return message
def __check_file_content(self, file_path):
message = ''
if checkers.check_html(file_path):
message = 'The file "%s" contains HTML content.\n' % str(file_path)
elif checkers.check_image(file_path):
message = 'The file "%s" contains image content.\n' % str(
file_path)
return message
def handle_uploaded_dataset_file( filename, datatypes_registry, ext = 'auto', is_multi_byte = False ):
is_valid, ext = handle_compressed_file( filename, datatypes_registry, ext = ext )
if not is_valid:
raise InappropriateDatasetContentError, 'The compressed uploaded file contains inappropriate content.'
if ext in AUTO_DETECT_EXTENSIONS:
ext = guess_ext( filename, sniff_order = datatypes_registry.sniff_order, is_multi_byte=is_multi_byte )
if check_binary( filename ):
if not Binary.is_ext_unsniffable(ext) and not datatypes_registry.get_datatype_by_extension( ext ).sniff( filename ):
raise InappropriateDatasetContentError, 'The binary uploaded file contains inappropriate content.'
elif check_html( filename ):
raise InappropriateDatasetContentError, 'The uploaded file contains inappropriate HTML content.'
return ext
def is_data_index_sample_file(file_path):
"""
Attempt to determine if a .sample file is appropriate for copying to ~/tool-data when
a tool shed repository is being installed into a Galaxy instance.
"""
# Currently most data index files are tabular, so check that first. We'll assume that
# if the file is tabular, it's ok to copy.
if is_column_based(file_path):
return True
# If the file is any of the following, don't copy it.
if checkers.check_html(file_path):
return False
if checkers.check_image(file_path):
return False
if checkers.check_binary(name=file_path):
return False
if checkers.is_bz2(file_path):
return False
if checkers.is_gzip(file_path):
return False
if checkers.check_zip(file_path):
return False
# Default to copying the file if none of the above are true.
return True
def is_data_index_sample_file(file_path):
"""
Attempt to determine if a .sample file is appropriate for copying to ~/tool-data when
a tool shed repository is being installed into a Galaxy instance.
"""
# Currently most data index files are tabular, so check that first. We'll assume that
# if the file is tabular, it's ok to copy.
if is_column_based(file_path):
return True
# If the file is any of the following, don't copy it.
if checkers.check_html(file_path):
return False
if checkers.check_image(file_path):
return False
if checkers.check_binary(name=file_path):
return False
if checkers.is_bz2(file_path):
return False
if checkers.is_gzip(file_path):
return False
if checkers.check_zip(file_path):
return False
# Default to copying the file if none of the above are true.
return True
# We have a binary dataset, but it is not Bam, Sff or Pdf
data_type = 'binary'
# binary_ok = False
parts = dataset.name.split( "." )
if len( parts ) > 1:
ext = parts[-1].strip().lower()
if not Binary.is_ext_unsniffable(ext):
file_err( 'The uploaded binary file contains inappropriate content', dataset, json_file )
return
elif Binary.is_ext_unsniffable(ext) and dataset.file_type != ext:
err_msg = "You must manually set the 'File Format' to '%s' when uploading %s files." % ( ext.capitalize(), ext )
file_err( err_msg, dataset, json_file )
return
if not data_type:
# We must have a text file
if check_html( dataset.path ):
file_err( 'The uploaded file contains inappropriate HTML content', dataset, json_file )
return
if data_type != 'binary':
if link_data_only == 'copy_files':
if dataset.type in ( 'server_dir', 'path_paste' ) and data_type not in [ 'gzip', 'bz2', 'zip' ]:
in_place = False
# Convert universal line endings to Posix line endings, but allow the user to turn it off,
# so that is becomes possible to upload gzip, bz2 or zip files with binary data without
# corrupting the content of those files.
if dataset.to_posix_lines:
tmpdir = output_adjacent_tmpdir( output_path )
tmp_prefix = 'data_id_%s_convert_' % dataset.dataset_id
if dataset.space_to_tab:
line_count, converted_path = sniff.convert_newlines_sep2tabs( dataset.path, in_place=in_place, tmp_dir=tmpdir, tmp_prefix=tmp_prefix )
else:
if len(parts) > 1:
ext = parts[-1].strip().lower()
if not Binary.is_ext_unsniffable(ext):
file_err(
'The uploaded binary file contains inappropriate content',
dataset, json_file)
return
elif Binary.is_ext_unsniffable(
ext) and dataset.file_type != ext:
err_msg = "You must manually set the 'File Format' to '%s' when uploading %s files." % (
ext.capitalize(), ext)
file_err(err_msg, dataset, json_file)
return
if not data_type:
# We must have a text file
if check_html(dataset.path):
file_err(
'The uploaded file contains inappropriate HTML content',
dataset, json_file)
return
if data_type != 'binary':
if link_data_only == 'copy_files':
if dataset.type in ('server_dir',
'path_paste') and data_type not in [
'gzip', 'bz2', 'zip'
]:
in_place = False
# Convert universal line endings to Posix line endings, but allow the user to turn it off,
# so that is becomes possible to upload gzip, bz2 or zip files with binary data without
# corrupting the content of those files.
if dataset.to_posix_lines:
