def _create_mapping_stats_gmap_report(self):
"""
Creates and returns a Mapping Stats gmap report
"""
from pbreports.report.mapping_stats import to_report
from test_pbreports_report_mapping_stats import _GMAP_DATA_DIR as datadir
log.info('Creating Mapping Stats gmap report using datadir {d}'.format(
d=datadir))
_to_p = lambda x: os.path.join(datadir, x)
filtered_regions_fofn = _to_p('filtered_regions.fofn')
filtered_summary = _to_p('filtered_summary.csv')
input_fofn = _to_p('input.fofn')
aligned_reads_cmph5 = _to_p('aligned_reads.cmp.h5')
mode = "external"
report_json = 'mapping_report.json'
output_json = os.path.join(self._output_dir, 'mapping_report.json')
bas_files = fofn_to_files(input_fofn)
region_files = fofn_to_files(filtered_regions_fofn)
report = to_report(bas_files,
region_files,
aligned_reads_cmph5,
report_json,
self._output_dir,
filter_summary_csv=filtered_summary,
mode=mode)
pformat(report.to_dict())
report.write_json(output_json)
return self._deserialize_report(output_json)
def main(argv=sys.argv):
"""Main point of entry"""
p = get_parser()
# the first arg with be the exe name
args = p.parse_args(argv[1:])
fofn = args.fofn
cmp_h5 = args.cmp_h5
movie_files = fofn_to_files(fofn)
output_csv = args.output_csv
external_mode = args.external
if args.debug:
setup_log(log, level=logging.DEBUG)
else:
log.addHandler(logging.NullHandler())
log.debug(args)
started_at = time.time()
try:
rcode = run(cmp_h5, movie_files, output_csv,
external_mode=external_mode)
except Exception as e:
rcode = -1
log.error(e, exc_info=True)
sys.stderr.write(str(e) + "\n")
run_time = time.time() - started_at
_d = dict(f=os.path.basename(__file__), x=rcode, s=run_time, v=__version__)
log.info(
"completed {f} v{v} with exit code {x} in {s:.2f} sec.".format(**_d))
return rcode
def fofn_to_chunks(fofn):
files = fofn_to_files(fofn)
chunks = []
for i, f in enumerate(files):
chunk_id = "chunk-{i}".format(i=i)
_d = {Constants.CHUNK_KEY_FOFN: f}
p = PipelineChunk(chunk_id, **_d)
chunks.append(p)
return chunks
def _args_chunk_fofn(args):
fofn_files = fofn_to_files(args.input_fofn)
log.info("read in fofn with {n} files.".format(n=len(fofn_files)))
chunks = CU.write_grouped_fofn_chunks(fofn_files, args.max_total_chunks,
args.output_dir,
args.chunk_report_json)
log.debug("Converted {x} Fofn into {n} chunks. Write chunks to {f}".format(
n=len(chunks), f=args.chunk_report_json, x=len(fofn_files)))
return 0
def fofn_to_chunks(fofn):
files = fofn_to_files(fofn)
chunks = []
for i, f in enumerate(files):
chunk_id = "chunk-{i}".format(i=i)
_d = {Constants.CHUNK_KEY_FOFN: f}
p = PipelineChunk(chunk_id, **_d)
chunks.append(p)
return chunks
def _create_reads_of_insert_report(self):
"""
Creates and returns a Reads of Insert report.
"""
from pbreports.report.reads_of_insert import to_report
from test_pbreports_report_reads_of_insert import _DATA_DIR as datadir
log.info('Creating reads_of_insert report using datadir {d}'.format(
d=datadir))
bas_files = fofn_to_files(os.path.join(datadir,
'reads_of_insert.fofn'))
output_json = os.path.join(self._output_dir, 'reads_of_insert.json')
report = to_report(bas_files, self._output_dir)
pformat(report.to_dict())
report.write_json(output_json)
return self._deserialize_report(output_json)
def _create_overview_report(self):
"""
Creates and returns an Overview report
"""
from pbreports.report.overview import run
from test_pbreports_report_overview import _DATA_DIR as datadir
log.info(
'Creating Overview report using datadir {d}'.format(d=datadir))
input_name = 'input.fofn'
input_fofn = os.path.join(datadir, input_name)
bas_files = fofn_to_files(input_fofn)
report_json = 'overview.json'
output_json = os.path.join(self._output_dir, report_json)
report = run(bas_files)
pformat(report.to_dict())
report.write_json(output_json)
return self._deserialize_report(output_json)
def gather_fofn(input_files, output_file, skip_empty=True):
"""
This should be better spec'ed and impose a tighter constraint on the FOFN
:param input_files: List of file paths
:param output_file: File Path
:param skip_empty: Ignore empty files
:return: Output file
:rtype: str
"""
all_files = []
for input_file in input_files:
file_names = fofn_to_files(input_file)
all_files.extend(file_names)
with open(output_file, 'w') as f:
f.write("\n".join(all_files))
return output_file
def gather_fofn(input_files, output_file, skip_empty=True):
"""
This should be better spec'ed and impose a tighter constraint on the FOFN
:param input_files: List of file paths
:param output_file: File Path
:param skip_empty: Ignore empty files
:return: Output file
:rtype: str
"""
all_files = []
for input_file in input_files:
file_names = fofn_to_files(input_file)
all_files.extend(file_names)
with open(output_file, 'w') as f:
f.write("\n".join(all_files))
return output_file
def nchunk_fofn(input_file, max_chunks):
input_files = fofn_to_files(input_file)
nchunks = min(len(input_files), max_chunks)
return nchunks
def _fofn_to_metadata(path):
files = fofn_to_files(path)
return DatasetMetadata(len(files), len(files))
def _fofn_to_metadata(path):
files = fofn_to_files(path)
return DatasetMetadata(len(files), len(files))
def nchunk_fofn(input_file, max_chunks):
input_files = fofn_to_files(input_file)
nchunks = min(len(input_files), max_chunks)
return nchunks
def _args_chunk_fofn(args):
fofn_files = fofn_to_files(args.input_fofn)
log.info("read in fofn with {n} files.".format(n=len(fofn_files)))
chunks = CU.write_grouped_fofn_chunks(fofn_files, args.max_total_chunks, args.output_dir, args.chunk_report_json)
log.debug("Converted {x} Fofn into {n} chunks. Write chunks to {f}".format(n=len(chunks), f=args.chunk_report_json, x=len(fofn_files)))
return 0
