def merge(split_files, output_file):
"""Merging multiple MIRA files is non-trivial and may not be possible..."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no MIRA, %r, to merge into %s" \
% (split_files, output_file))
raise NotImplementedError("Merging MIRA Assembly Files has not been implemented")
def merge(split_files, output_file):
"""Merging multiple MIRA files is non-trivial and may not be possible..."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no MIRA, %r, to merge into %s" \
% (split_files, output_file))
raise NotImplementedError(
"Merging MIRA Assembly Files has not been implemented")
def merge(split_files, output_file):
"""
Merging fps files requires merging the header manually.
We take the header from the first file.
"""
if len(split_files) == 1:
# For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("No fps files given, %r, to merge into %s" %
(split_files, output_file))
with open(output_file, "w") as out:
first = True
for filename in split_files:
with open(filename) as handle:
for line in handle:
if line.startswith('#'):
if first:
out.write(line)
else:
# line is no header and not a comment, we assume the first header is written to out and we set 'first' to False
first = False
out.write(line)
def merge(split_files, output_file):
"""
Merging CML files.
"""
if len(split_files) == 1:
# For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no CML files, %r, to merge into %s" %
(split_files, output_file))
with open(output_file, "w") as out:
for filename in split_files:
with open(filename) as handle:
header = handle.readline()
if not header:
raise ValueError("CML file %s was empty" % filename)
if not header.lstrip().startswith('<?xml version="1.0"?>'):
out.write(header)
raise ValueError("%s is not a valid XML file!" %
filename)
line = handle.readline()
header += line
if not line.lstrip().startswith(
'<cml xmlns="http://www.xml-cml.org/schema'):
out.write(header)
raise ValueError("%s is not a CML file!" % filename)
molecule_found = False
for line in handle.readlines():
# We found two required header lines, the next line should start with <molecule >
if line.lstrip().startswith('</cml>'):
continue
if line.lstrip().startswith('<molecule'):
molecule_found = True
if molecule_found:
out.write(line)
out.write("</cml>\n")
def merge(split_files, output_file):
"""Merging multiple XML files is non-trivial and must be done in subclasses."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no BLAST XML files, %r, to merge into %s" \
% (split_files, output_file))
out = open(output_file, "w")
h = None
for f in split_files:
if not os.path.isfile(f):
log.warning("BLAST XML file %s missing, retry in 1s..." % f)
sleep(1)
if not os.path.isfile(f):
log.error("BLAST XML file %s missing" % f)
raise ValueError("BLAST XML file %s missing" % f)
h = open(f)
header = h.readline()
if not header:
out.close()
h.close()
#Retry, could be transient error with networked file system...
log.warning("BLAST XML file %s empty, retry in 1s..." % f)
sleep(1)
h = open(f)
header = h.readline()
if not header:
log.error("BLAST XML file %s was empty" % f)
raise ValueError("BLAST XML file %s was empty" % f)
if header.strip() != '<?xml version="1.0"?>':
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not an XML file!" % f)
line = h.readline()
header += line
if line.strip() not in [
'<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">',
'<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "NCBI_BlastOutput.dtd">'
]:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file!" % f)
while True:
line = h.readline()
if not line:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("BLAST XML file %s ended prematurely" % f)
header += line
if "<Iteration>" in line:
break
if len(header) > 10000:
#Something has gone wrong, don't load too much into memory!
#Write what we have to the merged file for diagnostics
out.write(header)
out.close()
h.close()
raise ValueError(
"BLAST XML file %s has too long a header!" % f)
if "<BlastOutput>" not in header:
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file:\n%s\n..." %
(f, header))
if f == split_files[0]:
out.write(header)
old_header = header
elif old_header[:300] != header[:300]:
#Enough to check <BlastOutput_program> and <BlastOutput_version> match
out.close()
h.close()
raise ValueError("BLAST XML headers don't match for %s and %s - have:\n%s\n...\n\nAnd:\n%s\n...\n" \
% (split_files[0], f, old_header[:300], header[:300]))
else:
out.write(" <Iteration>\n")
for line in h:
if "</BlastOutput_iterations>" in line:
break
#TODO - Increment <Iteration_iter-num> and if required automatic query names
#like <Iteration_query-ID>Query_3</Iteration_query-ID> to be increasing?
out.write(line)
h.close()
out.write(" </BlastOutput_iterations>\n")
out.write("</BlastOutput>\n")
out.close()
def merge(split_files, output_file):
"""Merging multiple XML files is non-trivial and must be done in subclasses."""
if len(split_files) == 1:
#For one file only, use base class method (move/copy)
return Text.merge(split_files, output_file)
if not split_files:
raise ValueError("Given no BLAST XML files, %r, to merge into %s" \
% (split_files, output_file))
out = open(output_file, "w")
h = None
for f in split_files:
if not os.path.isfile(f):
log.warning("BLAST XML file %s missing, retry in 1s..." % f)
sleep(1)
if not os.path.isfile(f):
log.error("BLAST XML file %s missing" % f)
raise ValueError("BLAST XML file %s missing" % f)
h = open(f)
body = False
header = h.readline()
if not header:
out.close()
h.close()
#Retry, could be transient error with networked file system...
log.warning("BLAST XML file %s empty, retry in 1s..." % f)
sleep(1)
h = open(f)
header = h.readline()
if not header:
log.error("BLAST XML file %s was empty" % f)
raise ValueError("BLAST XML file %s was empty" % f)
if header.strip() != '<?xml version="1.0"?>':
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not an XML file!" % f)
line = h.readline()
header += line
if line.strip() not in ['<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">',
'<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "NCBI_BlastOutput.dtd">']:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file!" % f)
while True:
line = h.readline()
if not line:
out.write(header) #for diagnosis
out.close()
h.close()
raise ValueError("BLAST XML file %s ended prematurely" % f)
header += line
if "<Iteration>" in line:
break
if len(header) > 10000:
#Something has gone wrong, don't load too much into memory!
#Write what we have to the merged file for diagnostics
out.write(header)
out.close()
h.close()
raise ValueError("BLAST XML file %s has too long a header!" % f)
if "<BlastOutput>" not in header:
out.close()
h.close()
raise ValueError("%s is not a BLAST XML file:\n%s\n..." % (f, header))
if f == split_files[0]:
out.write(header)
old_header = header
elif old_header[:300] != header[:300]:
#Enough to check <BlastOutput_program> and <BlastOutput_version> match
out.close()
h.close()
raise ValueError("BLAST XML headers don't match for %s and %s - have:\n%s\n...\n\nAnd:\n%s\n...\n" \
% (split_files[0], f, old_header[:300], header[:300]))
else:
out.write(" <Iteration>\n")
for line in h:
if "</BlastOutput_iterations>" in line:
break
#TODO - Increment <Iteration_iter-num> and if required automatic query names
#like <Iteration_query-ID>Query_3</Iteration_query-ID> to be increasing?
out.write(line)
h.close()
out.write(" </BlastOutput_iterations>\n")
out.write("</BlastOutput>\n")
out.close()
