def validate(self):
infile = SegmentedFile.fileopen( self.mFilenameSegments )
last_nid = None
found = set()
nfound, nunknown, nduplicate = 0, 0, 0
for line in infile:
ninput += 1
nid = line[:line.index("\t")]
if nid != last_nid:
if nid in found:
nduplicates += 1
self.warn("duplicate nid: %i in file %s" % (nid, filename))
if nid not in tokens:
nunknown += 1
self.warn("unknown nid: %i in file %s" % (nid, filename))
found.add(nid)
nfound += 1
last_nid = nid
noutput += 1
missing = set(self.mFasta.getTokens()).difference( found )
if len(missing) > 0:
self.warn( "the following nids were missing: %s" % str(missing) )
self.info( "merging: ninput=%i, noutput=%i, nfound=%i, nmissing=%i, nduplicate=%i, nunknown=%i" %\
(ninput, noutput, nfound, len(missing), nduplicate, nunknown ) )
return len(missing) == 0 and nduplicate == 0 and nunknown == 0
def validate(self):
"""merge runs from parallel computations.
Note: duplicated code with AddaSegments - can be merged.
returns true if merging was succecss.
"""
infiles = self.getPartialResults()
last_nid = None
found = set()
nfound, nunknown, nduplicate = 0, 0, 0
infile = SegmentedFile.fileopen( self.mFilenameGraph )
for line in infile:
ninput += 1
nid = line[:line.index("\t")]
if nid != last_nid:
if nid in found:
nduplicates += 1
self.warn("duplicate nid: %i in file %s" % (nid, filename))
if nid not in tokens:
nunknown += 1
self.warn("unknown nid: %i in file %s" % (nid, filename))
found.add(nid)
nfound += 1
last_nid = nid
noutput += 1
missing = set(self.mFasta.getTokens()).difference( found )
if len(missing) > 0:
self.warn( "the following nids were missing: %s" % str(missing) )
self.info( "merging: ninput=%i, noutput=%i, nfound=%i, nmissing=%i, nduplicate=%i, nunknown=%i" %\
(ninput, noutput, nfound, len(missing), nduplicate, nunknown ) )
return len(missing) == 0 and nduplicate == 0 and nunknown == 0
def validate(self):
infile = SegmentedFile.fileopen(self.mFilenameSegments)
last_nid = None
found = set()
nfound, nunknown, nduplicate = 0, 0, 0
for line in infile:
ninput += 1
nid = line[:line.index("\t")]
if nid != last_nid:
if nid in found:
nduplicates += 1
self.warn("duplicate nid: %i in file %s" % (nid, filename))
if nid not in tokens:
nunknown += 1
self.warn("unknown nid: %i in file %s" % (nid, filename))
found.add(nid)
nfound += 1
last_nid = nid
noutput += 1
missing = set(self.mFasta.getTokens()).difference(found)
if len(missing) > 0:
self.warn("the following nids were missing: %s" % str(missing))
self.info( "merging: ninput=%i, noutput=%i, nfound=%i, nmissing=%i, nduplicate=%i, nunknown=%i" %\
(ninput, noutput, nfound, len(missing), nduplicate, nunknown ) )
return len(missing) == 0 and nduplicate == 0 and nunknown == 0
