Skip to content

Commit

Permalink
Removing the deprecated online bits of Bio.GenBank (replaced by Bio.E…
Browse files Browse the repository at this point in the history 
…ntrez)
  • Loading branch information
Peter Cock committed Mar 4, 2010
1 parent ff19d79 commit 4f7d50c
Show file tree
Hide file tree
Showing 2 changed files with 3 additions and 169 deletions.
168 changes: 1 addition & 167 deletions Bio/GenBank/__init__.py
View file
Expand Up @@ -24,24 +24,13 @@
ErrorFeatureParser Catch errors caused during parsing.
FeatureParser Parse GenBank data in SeqRecord and SeqFeature objects.
RecordParser Parse GenBank data into a Record object.
NCBIDictionary Access GenBank using a dictionary interface (DEPRECATED).
_BaseGenBankConsumer A base class for GenBank consumer that implements
some helpful functions that are in common between
consumers.
_FeatureConsumer Create SeqFeature objects from info generated by
the Scanner
_RecordConsumer Create a GenBank record object from Scanner info.
_PrintingConsumer A debugging consumer.
Exceptions:
ParserFailureError Exception indicating a failure in the parser (ie.
scanner or consumer)
LocationParserError Exception indiciating a problem with the spark based
location parser.
Functions:
search_for Do a query against GenBank (DEPRECATED).
download_many Download many GenBank records (DEPRECATED).
17-MAR-2009: added wgs, wgs_scafld for GenBank whole genome shotgun master records.
These are GenBank files that summarize the content of a project, and provide lists of
Expand Down Expand Up @@ -1308,158 +1297,3 @@ def record_end(self, content):
self._add_feature()


class NCBIDictionary:
"""Access GenBank using a read-only dictionary interface (DEPRECATED).
This object is deprecated and will be removed in a future release of
Biopython. Please use Bio.Entrez instead as described in the tutorial.
"""
VALID_DATABASES = ['nucleotide', 'protein', 'genome']
VALID_FORMATS = ['genbank', 'fasta']
def __init__(self, database, format, parser = None):
"""Initialize an NCBI dictionary to retrieve sequences.
Create a new Dictionary to access GenBank. Valid values for
database are 'nucleotide' and 'protein'.
Valid values for format are 'genbank' (for nucleotide genbank and
protein genpept) and 'fasta'.
dely and retmax are old options kept only for compatibility -- do not
bother to set them.
parser is an optional parser object
to change the results into another form. If unspecified, then
the raw contents of the file will be returned.
"""
import warnings
warnings.warn("Bio.GenBank.NCBIDictionary has been deprecated, and will be"\
" removed in a future release of Biopython. Please use"\
" Bio.Entrez instead which is described in the tutorial.",
DeprecationWarning)

self.parser = parser
if database not in self.__class__.VALID_DATABASES:
raise ValueError("Invalid database %s, should be one of %s" %
(database, self.__class__.VALID_DATABASES))
if format not in self.__class__.VALID_FORMATS:
raise ValueError("Invalid format %s, should be one of %s" %
(format, self.__class__.VALID_FORMATS))

if format=="genbank": format = "gb"
self.db = database
self.format = format

def __len__(self):
raise NotImplementedError("GenBank contains lots of entries")
def clear(self):
raise NotImplementedError("This is a read-only dictionary")
def __setitem__(self, key, item):
raise NotImplementedError("This is a read-only dictionary")
def update(self):
raise NotImplementedError("This is a read-only dictionary")
def copy(self):
raise NotImplementedError("You don't need to do this...")
def keys(self):
raise NotImplementedError("You don't really want to do this...")
def items(self):
raise NotImplementedError("You don't really want to do this...")
def values(self):
raise NotImplementedError("You don't really want to do this...")

def has_key(self, id):
"""S.has_key(id) -> bool"""
try:
self[id]
except KeyError:
return 0
return 1

def get(self, id, failobj=None):
try:
return self[id]
except KeyError:
return failobj

def __getitem__(self, id):
"""Return the GenBank entry specified by the GenBank ID.
Raises a KeyError if there's an error.
"""
handle = Entrez.efetch(db = self.db, id = id, rettype = self.format)
# Parse the record if a parser was passed in.
if self.parser is not None:
return self.parser.parse(handle)
return handle.read()

def search_for(search, database='nucleotide',
reldate=None, mindate=None, maxdate=None,
start_id = 0, max_ids = 50000000):
"""Do an online search at the NCBI, returns a list of IDs (DEPRECATED).
This function is deprecated and will be removed in a future release of
Biopython. Please use Bio.Entrez instead as described in the tutorial.
Search GenBank and return a list of the GenBank identifiers (gi's)
that match the criteria. search is the search string used to
search the database. Valid values for database are
'nucleotide', 'protein', 'popset' and 'genome'. reldate is
the number of dates prior to the current date to restrict the
search. mindate and maxdate are the dates to restrict the search,
e.g. 2002/12/20. start_id is the number to begin retrieval on.
max_ids specifies the maximum number of id's to retrieve.
"""
import warnings
warnings.warn("Bio.GenBank.search_for has been deprecated, and will be"\
" removed in a future release of Biopython. Please use"\
" Bio.Entrez instead which is described in the tutorial.",
DeprecationWarning)

# mindate and maxdate are NCBI parameters in "YYYY/MM/DD" format
# (and both should be supplied or neither)
# relate is an NCBI parameter for "within N days"

#Following date checking from Bio/EUtils/Datatypes.py,
import re
_date_re_match = re.compile(r"\d{4}(/\d\d(/\d\d)?)?$").match
errinfo = None
if mindate is not None and _date_re_match(mindate) is None:
errinfo = ("mindate", mindate)
elif maxdate is not None and _date_re_match(maxdate) is None:
errinfo = ("maxdate", maxdate)
if errinfo:
raise TypeError(
"%s is not in YYYY/MM/DD format (month and "
"day are optional): %r" % errinfo)

#Bio.Entrez can now ignore None arguments automatically
handle = Entrez.esearch(database, search, retmode="xml",
retstart=start_id, retmax=max_ids,
mindate=mindate, maxdate=maxdate,
reldate=reldate)
return Entrez.read(handle)["IdList"]

def download_many(ids, database = 'nucleotide'):
"""Download multiple NCBI GenBank records, returned as a handle (DEPRECATED).
This function is deprecated and will be removed in a future release of
Biopython. Please use Bio.Entrez instead as described in the tutorial.
Download many records from GenBank. ids is a list of gis or
accessions.
"""
import warnings
warnings.warn("Bio.GenBank.download_many has been deprecated, and will be"\
" removed in a future release of Biopython. Please use"\
" Bio.Entrez instead which is described in the tutorial.",
DeprecationWarning)

if database in ['nucleotide']:
format = 'gb'
elif database in ['protein']:
format = 'gp'
else:
raise ValueError("Unexpected database: %s" % database)
#TODO - Batch the queries?
result_handle = Entrez.efetch(database,
id=",".join(ids),
retmode = "text",
rettype = format)
return cStringIO.StringIO(result_handle.read())
4 changes: 2 additions & 2 deletions DEPRECATED
View file
Expand Up @@ -178,8 +178,8 @@ for the output of MetaTool 3.5 which is now obsolete.
Bio.GenBank
===========
The online functionality (search_for, download_many, and NCBIDictionary) was
declared obsolete in Release 1.48, and deprecated in Release 1.50.
Please use Bio.Entrez instead.
declared obsolete in Release 1.48, deprecated in Release 1.50, and removed
in Release 1.54. Please use Bio.Entrez instead.

Bio.PubMed
==========
Expand Down

0 comments on commit 4f7d50c

Please sign in to comment.