if not out:
# if file can't be opened use stdout
out = sys.stdout
n_sequence[fastafile] = 0
n_match[fastafile] = 0
n_notmatch[fastafile] = 0
n_file += 1
while fasta.next():
n_sequence[fastafile] += 1
n_total += 1
if fasta.id in idlist or not idlist:
# desired selected sequences
fasta.trimDocByRegex(trim)
seqlen = len(fasta.seq)
if args.minlen and seqlen < args.minlen:
# skip sequences shorter than minimum length, if specified
continue
out.write('{}\n'.format(fasta.format(linelen=args.linelen)))
n_written += 1
n_match[fastafile] += 1
if fasta.id in n_found:
n_found[fasta.id] += 1
else:
n_found[fasta.id] = 1
else:
# not selected sequence
fasta = Fasta()
fasta.fh = cl.fasta_file
trimre = re.compile(trim)
# initialize counters
base_total = 0
base_current = 0
n_out = 0
n_seq = 0
n_current = 0
while fasta.next():
if trimre: fasta.trimDocByRegex(trimre)
if not n_seq or base_current + fasta.length() > maxbases:
# if number of bases would be greater than cutoff after adding the new sequence
# close current output file, open new
# report statistics for old file
# reset current file counters
try:
# prevents error on first pass - file is not yet open
outfile.close()
print(' ', base_current, 'bases/amino acids', end=' ')
print('in', n_current, 'sequences', end=' ')
print('written to', outfilename)
except NameError:
pass