def update(self, data, make_backup=True, **kwargs):
"""
Update database with features in `data`.
data : str, iterable, FeatureDB instance
If FeatureDB, all data will be used. If string, assume it's
a filename of a GFF or GTF file. Otherwise, assume it's an
iterable of Feature objects. The classes in gffutils.iterators may
be helpful in this case.
make_backup : bool
If True, and the database you're about to update is a file on disk,
makes a copy of the existing database and saves it with a .bak
extension.
Notes
-----
Other kwargs are used in the same way as in gffutils.create_db; see the
help for that function for details.
Returns
-------
FeatureDB with updated features.
"""
from gffutils import create
from gffutils import iterators
if make_backup:
if isinstance(self.dbfn, six.string_types):
shutil.copy2(self.dbfn, self.dbfn + '.bak')
# get iterator-specific kwargs
_iterator_kwargs = {}
for k, v in kwargs.items():
if k in constants._iterator_kwargs:
_iterator_kwargs[k] = v
# Handle all sorts of input
data = iterators.DataIterator(data, **_iterator_kwargs)
if self.dialect['fmt'] == 'gtf':
if 'id_spec' not in kwargs:
kwargs['id_spec'] = {
'gene': 'gene_id', 'transcript': 'transcript_id'}
db = create._GTFDBCreator(
data=data, dbfn=self.dbfn, dialect=self.dialect, **kwargs)
elif self.dialect['fmt'] == 'gff3':
if 'id_spec' not in kwargs:
kwargs['id_spec'] = 'ID'
db = create._GFFDBCreator(
data=data, dbfn=self.dbfn, dialect=self.dialect, **kwargs)
else:
raise ValueError
db._populate_from_lines(data)
db._update_relations()
db._finalize()
return db
def update(self, data, make_backup=True, **kwargs):
"""
Update database with features in `data`.
data : str, iterable, FeatureDB instance
If FeatureDB, all data will be used. If string, assume it's
a filename of a GFF or GTF file. Otherwise, assume it's an
iterable of Feature objects. The classes in gffutils.iterators may
be helpful in this case.
make_backup : bool
If True, and the database you're about to update is a file on disk,
makes a copy of the existing database and saves it with a .bak
extension.
Notes
-----
Other kwargs are used in the same way as in gffutils.create_db; see the
help for that function for details.
Returns
-------
FeatureDB with updated features.
"""
from gffutils import create
from gffutils import iterators
if make_backup:
if isinstance(self.dbfn, six.string_types):
shutil.copy2(self.dbfn, self.dbfn + '.bak')
# get iterator-specific kwargs
_iterator_kwargs = {}
for k, v in kwargs.items():
if k in constants._iterator_kwargs:
_iterator_kwargs[k] = v
# Handle all sorts of input
data = iterators.DataIterator(data, **_iterator_kwargs)
if self.dialect['fmt'] == 'gtf':
if 'id_spec' not in kwargs:
kwargs['id_spec'] = {
'gene': 'gene_id', 'transcript': 'transcript_id'}
db = create._GTFDBCreator(
data=data, dbfn=self.dbfn, dialect=self.dialect, **kwargs)
elif self.dialect['fmt'] == 'gff3':
if 'id_spec' not in kwargs:
kwargs['id_spec'] = 'ID'
db = create._GFFDBCreator(
data=data, dbfn=self.dbfn, dialect=self.dialect, **kwargs)
else:
raise ValueError
db._populate_from_lines(data)
db._update_relations()
db._finalize()
return db
def update(self, features, make_backup=True, **kwargs):
"""
Update database with features.
features : str, iterable, FeatureDB instance
If FeatureDB, all features will be used. If string, assume it's
a filename of a GFF or GTF file. Otherwise, assume it's an
iterable of Feature objects. The classes in gffutils.iterators may
be helpful in this case.
make_backup : bool
If True, and the database you're about to update is a file on disk,
makes a copy of the existing database and saves it with a .bak
extension.
Remaining kwargs are passed to create_db.
"""
from gffutils import create
if make_backup:
if isinstance(self.dbfn, six.string_types):
shutil.copy2(self.dbfn, self.dbfn + '.bak')
# No matter what `features` came in as, convert to gffutils.Feature
# instances. Since the tricky part -- attribute strings -- have been
# parsed into dicts in a Feature, we no longer have to worry about
# that. This also allows GTF features to be used to update a GFF
# database, or vice versa.
if isinstance(features, six.string_types):
indb = create.create_db(features, intermediate, **kwargs)
features = indb.all_features()
if isinstance(features, FeatureDB):
features = features.all_features()
if self.dialect['fmt'] == 'gtf':
if 'id_spec' not in kwargs:
kwargs['id_spec'] = {
'gene': 'gene_id', 'transcript': 'transcript_id'}
db = create._GTFDBCreator(
data=features, dbfn=self.dbfn, dialect=self.dialect, **kwargs)
elif self.dialect['fmt'] == 'gff3':
if 'id_spec' not in kwargs:
kwargs['id_spec'] = 'ID'
db = create._GFFDBCreator(
data=features, dbfn=self.dbfn, dialect=self.dialect, **kwargs)
else:
raise ValueError
db._populate_from_lines(features)
db._update_relations()
db._finalize()
