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 __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 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
dataset.path = temp_name
# See if we have an empty file
if not os.path.exists( dataset.path ):
file_err( 'Uploaded temporary file (%s) does not exist.' % dataset.path, dataset, json_file )
return
if not os.path.getsize( dataset.path ) > 0:
file_err( 'The uploaded file is empty', dataset, json_file )
return
if not dataset.type == 'url':
# Already set is_multi_byte above if type == 'url'
try:
dataset.is_multi_byte = util.is_multi_byte( codecs.open( dataset.path, 'r', 'utf-8' ).read( 100 ) )
except UnicodeDecodeError, e:
dataset.is_multi_byte = False
# Is dataset an image?
image = check_image( dataset.path )
if image:
if not PIL:
image = None
# get_image_ext() returns None if nor a supported Image type
ext = get_image_ext( dataset.path, image )
data_type = ext
# Is dataset content multi-byte?
elif dataset.is_multi_byte:
data_type = 'multi-byte char'
ext = sniff.guess_ext( dataset.path, is_multi_byte=True )
# Is dataset content supported sniffable binary?
else:
# FIXME: This ignores the declared sniff order in datatype_conf.xml
# resulting in improper behavior
type_info = Binary.is_sniffable_binary( dataset.path )
if not os.path.exists(dataset.path):
file_err('Uploaded temporary file (%s) does not exist.' % dataset.path,
dataset, json_file)
return
if not os.path.getsize(dataset.path) > 0:
file_err('The uploaded file is empty', dataset, json_file)
return
if not dataset.type == 'url':
# Already set is_multi_byte above if type == 'url'
try:
dataset.is_multi_byte = util.is_multi_byte(
codecs.open(dataset.path, 'r', 'utf-8').read(100))
except UnicodeDecodeError, e:
dataset.is_multi_byte = False
# Is dataset an image?
image = check_image(dataset.path)
if image:
if not PIL:
image = None
# get_image_ext() returns None if nor a supported Image type
ext = get_image_ext(dataset.path, image)
data_type = ext
# Is dataset content multi-byte?
elif dataset.is_multi_byte:
data_type = 'multi-byte char'
ext = sniff.guess_ext(dataset.path, is_multi_byte=True)
# Is dataset content supported sniffable binary?
else:
# FIXME: This ignores the declared sniff order in datatype_conf.xml
# resulting in improper behavior
type_info = Binary.is_sniffable_binary(dataset.path)
