def test_wait_for_file(self):
"""wait_for_file should go to sleep if file is not present."""
# wait_for_file has a debug/test mode, in which it raises an exception
# instead of going to sleep
# should not raise anything on valid file
try:
wait_for_file("/tmp/denoiser_utils_dummy.tmp", test_mode=True)
except RuntimeWarning:
self.fail("wait_for_file fails on valid file")
# but should raise on file not present
self.assertRaises(RuntimeWarning, wait_for_file, "/foo/bar/baz", test_mode=True)
def test_wait_for_file(self):
"""wait_for_file should go to sleep if file is not present."""
#wait_for_file has a debug/test mode, in which it raises an exception
# instead of going to sleep
# should not raise anything on valid file
try:
wait_for_file("/tmp/denoiser_utils_dummy.tmp", test_mode=True)
except RuntimeWarning:
self.fail("wait_for_file fails on valid file")
#but should raise on file not present
self.assertRaises(RuntimeWarning, wait_for_file, "/foo/bar/baz",
test_mode=True)
def preprocess_on_cluster(sff_fps,
log_fp,
fasta_fp=None,
out_fp="/tmp/",
squeeze=False,
verbose=False,
primer=STANDARD_BACTERIAL_PRIMER):
"""Call preprocess via cluster_jobs_script on the cluster.
sff_fps: List of paths to flowgram files.
log_fp: path to log file
fasta_fp: Path to fasta file, formatted as from split_libraries.py.
This files is used to filter the flowgrams in sff_fps. Only reads in
fasta_fp are pulled from sff_fps.
out_fp: path to output directory
verbose: a binary verbose flag
squeeze: a flag that controls if sequences are squeezed before phase I.
Squeezing means consecutive identical nucs are collapsed to one.
primer: The primer sequences of the amplification process. This seq will be
removed from all reads during the preprocessing
"""
qiime_config = load_qiime_config()
python_bin = qiime_config['python_exe_fp']
cmd = "%s %s/denoiser_preprocess.py -i %s -l %s -o %s" %\
(python_bin, get_qiime_scripts_dir(), ",".join(sff_fps), log_fp, out_fp)
if (fasta_fp):
cmd += " -f %s" % fasta_fp
if (squeeze):
cmd += " -s"
if verbose:
cmd += " -v"
if primer:
cmd += " -p %s" % primer
submit_jobs([cmd], "pp_" + make_tmp_name(6))
wait_for_file(out_fp + "/prefix_mapping.txt", 10)
def preprocess_on_cluster(sff_fps, log_fp, fasta_fp=None, out_fp="/tmp/",
squeeze=False, verbose=False,
primer=STANDARD_BACTERIAL_PRIMER):
"""Call preprocess via cluster_jobs_script on the cluster.
sff_fps: List of paths to flowgram files.
log_fp: path to log file
fasta_fp: Path to fasta file, formatted as from split_libraries.py.
This files is used to filter the flowgrams in sff_fps. Only reads in
fasta_fp are pulled from sff_fps.
out_fp: path to output directory
verbose: a binary verbose flag
squeeze: a flag that controls if sequences are squeezed before phase I.
Squeezing means consecutive identical nucs are collapsed to one.
primer: The primer sequences of the amplification process. This seq will be
removed from all reads during the preprocessing
"""
qiime_config = load_qiime_config()
python_bin = qiime_config['python_exe_fp']
cmd = "%s %s/denoiser_preprocess.py -i %s -l %s -o %s" %\
(python_bin, get_qiime_scripts_dir(),
",".join(sff_fps), log_fp, out_fp)
if (fasta_fp):
cmd += " -f %s" % fasta_fp
if(squeeze):
cmd += " -s"
if verbose:
cmd += " -v"
if primer:
cmd += " -p %s" % primer
submit_jobs([cmd], "pp_" + make_tmp_name(6))
wait_for_file(out_fp + "/prefix_mapping.txt", 10)
