def compress_dataset_files(dataset_data, ext_python_modules_home, max_threads, log):
log.info("\n== Compressing corrected reads (with gzip)")
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
compressed_reads_filenames = []
for reads_file in value:
if not os.path.isfile(reads_file):
support.error('something went wrong and file with corrected reads (' + reads_file + ') is missing!', log)
to_compress.append(reads_file)
compressed_reads_filenames.append(reads_file + ".gz")
reads_library[key] = compressed_reads_filenames
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([pigz_path, '-f', '-7', '-p', str(max_threads), reads_file], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(delayed(support.sys_call)(['gzip', '-f', '-7', reads_file]) for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def compress_dataset_files(dataset_data, ext_python_modules_home, max_threads, log):
log.info("\n== Compressing corrected reads (with gzip)")
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
compressed_reads_filenames = []
for reads_file in value:
if not os.path.isfile(reads_file):
support.error('something went wrong and file with corrected reads (' + reads_file + ') is missing!', log)
to_compress.append(reads_file)
compressed_reads_filenames.append(reads_file + ".gz")
reads_library[key] = compressed_reads_filenames
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([pigz_path, '-f', '-7', '-p', str(max_threads), reads_file], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(delayed(support.sys_call)(['gzip', '-f', '-7', reads_file]) for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def move_dataset_files(dataset_data,
dst,
ext_python_modules_home,
max_threads,
log,
gzip=False):
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
moved_reads_files = []
for reads_file in value:
dst_filename = os.path.join(dst,
os.path.basename(reads_file))
# TODO: fix problem with files with the same basenames in Hammer binary!
if not os.path.isfile(reads_file):
if (not gzip and os.path.isfile(dst_filename)) or (
gzip and os.path.isfile(dst_filename + '.gz')):
support.warning(
'file with corrected reads (' + reads_file +
') is the same in several libraries', log)
if gzip:
dst_filename += '.gz'
else:
support.error(
'something went wrong and file with corrected reads ('
+ reads_file + ') is missing!', log)
else:
shutil.move(reads_file, dst_filename)
if gzip:
to_compress.append(dst_filename)
dst_filename += '.gz'
moved_reads_files.append(dst_filename)
reads_library[key] = moved_reads_files
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([
pigz_path, '-f', '-7', '-p',
str(max_threads), reads_file
], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(
delayed(support.sys_call)(['gzip', '-f', '-7', reads_file])
for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def move_dataset_files(dataset_data, dst, ext_python_modules_home, max_threads, log, gzip=False):
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith('reads'):
moved_reads_files = []
for reads_file in value:
dst_filename = os.path.join(dst, os.path.basename(reads_file))
# TODO: fix problem with files with the same basenames in Hammer binary!
if not os.path.isfile(reads_file):
if (not gzip and os.path.isfile(dst_filename)) or (gzip and os.path.isfile(dst_filename + '.gz')):
support.warning('file with corrected reads (' + reads_file + ') is the same in several libraries', log)
if gzip:
dst_filename += '.gz'
else:
support.error('something went wrong and file with corrected reads (' + reads_file + ') is missing!', log)
else:
shutil.move(reads_file, dst_filename)
if gzip:
to_compress.append(dst_filename)
dst_filename += '.gz'
moved_reads_files.append(dst_filename)
reads_library[key] = moved_reads_files
if len(to_compress):
pigz_path = support.which('pigz')
if pigz_path:
for reads_file in to_compress:
support.sys_call([pigz_path, '-f', '-7', '-p', str(max_threads), reads_file], log)
else:
addsitedir(ext_python_modules_home)
if sys.version.startswith('2.'):
from joblib2 import Parallel, delayed
elif sys.version.startswith('3.'):
from joblib3 import Parallel, delayed
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(delayed(support.sys_call)(['gzip', '-f', '-7', reads_file]) for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
def compress_dataset_files(input_file, ext_python_modules_home, max_threads,
log, not_used_yaml_file, output_dir, gzip_output):
addsitedir(ext_python_modules_home)
if sys.version.startswith("2."):
import pyyaml2 as pyyaml
from joblib2 import Parallel, delayed
elif sys.version.startswith("3."):
import pyyaml3 as pyyaml
from joblib3 import Parallel, delayed
dataset_data = pyyaml.load(open(input_file))
remove_not_corrected_reads(output_dir)
is_changed = False
if gzip_output:
is_changed = True
pigz_path = support.which("pigz")
if pigz_path:
compressor = "pigz"
else:
compressor = "gzip"
log.info("\n== Compressing corrected reads (with %s)" % compressor)
to_compress = []
for reads_library in dataset_data:
for key, value in reads_library.items():
if key.endswith("reads"):
compressed_reads_filenames = []
for reads_file in value:
compressed_reads_filenames.append(reads_file + ".gz")
to_compress.append(reads_file)
reads_library[key] = compressed_reads_filenames
if len(to_compress):
for reads_file in to_compress:
if not isfile(reads_file):
support.error(
"something went wrong and file with corrected reads (%s) is missing!"
% reads_file, log)
if pigz_path:
for reads_file in to_compress:
support.sys_call([
pigz_path, "-f", "-7", "-p",
str(max_threads), reads_file
], log)
else:
n_jobs = min(len(to_compress), max_threads)
outputs = Parallel(n_jobs=n_jobs)(
delayed(support.sys_call)(["gzip", "-f", "-7", reads_file])
for reads_file in to_compress)
for output in outputs:
if output:
log.info(output)
if not_used_yaml_file != "":
is_changed = True
not_used_dataset_data = pyyaml.load(open(not_used_yaml_file))
dataset_data += not_used_dataset_data
if is_changed:
with open(input_file, 'w') as f:
pyyaml.dump(dataset_data,
f,
default_flow_style=False,
default_style='"',
width=float("inf"))
