def test_create_bc_report(self):
"""Create a demultiplex report and upload it to gdocs
"""
# Parse the config
config_file = os.path.join(self.data_dir, "post_process.yaml")
self.config = load_config(config_file)
# Loop over the runs
for name in self.runname:
print "\nProcessing %s" % name
fc_name, fc_date = get_flowcell_info(name)
analysisdir = os.path.join(self.workdir, name)
assert create_report_on_gdocs(fc_date, fc_name, self.run_info_file, {"work": analysisdir, "flowcell": analysisdir}, self.config), "Report creation failed"
def create_report_on_gdocs(*args):
[fc_date, fc_name, run_info_yaml, dirs, config] = args
return sequencing_report.create_report_on_gdocs(fc_date,fc_name,run_info_yaml,dirs,config)
def main(run_id, config_file, run_info_file=None, dryrun=False):
assert run_id, \
"No run id was specified"
assert os.path.exists(config_file), \
"The configuration file, {}, could not be found".format(config_file)
config = load_config(config_file)
assert "gdocs_upload" in config, \
"The configuration file, {}, has no section specifying the Google docs details".format(config_file)
analysis_cfg = config.get("analysis", {})
if "store_dir" in analysis_cfg:
archive_dir = os.path.join(analysis_cfg["store_dir"], run_id)
else:
archive_dir = os.getcwd()
analysis_dir = None
if "base_dir" in analysis_cfg:
analysis_dir = os.path.join(analysis_cfg["base_dir"], run_id)
if analysis_dir is None or not os.path.exists(analysis_dir):
analysis_dir = tempfile.mkdtemp()
dirs = {
"work": os.path.normpath(analysis_dir),
"flowcell": os.path.normpath(archive_dir)
}
assert os.path.exists(dirs["flowcell"]), \
"The flowcell directory, {}, could not be found".format(dirs["flowcell"])
assert os.path.exists(dirs["work"]), \
"The work directory, {}, could not be found".format(dirs["work"])
if run_info_file is None:
run_info_file = os.path.join(dirs["flowcell"], "run_info.yaml")
if not os.path.exists(run_info_file):
# Locate the samplesheet and convert to yaml
samplesheet = _find_samplesheet(dirs["flowcell"])
assert samplesheet, \
"Could not locate samplesheet in {}, aborting..".format(dirs["flowcell"])
fh, run_info_file = tempfile.mkstemp()
os.close(fh)
run_info_file = ssheet.csv2yaml(samplesheet, run_info_file)
assert os.path.exists(run_info_file), \
"The run info configuration file, {}, could not be found".format(run_info_file)
fc_name, fc_date = fc.get_flowcell_info(dirs["flowcell"])
# If we have no bc_metrics files in the workdir, we may be looking at a Casava run.
# In that case, attempt to parse the Demultiplex_Stats.htm file and create bc_metrics files
metric_files = glob.glob(
os.path.join(dirs["work"], "*_barcode", "*bc[_.]metrics")) + glob.glob(
os.path.join(dirs["work"], "*bc[_.]metrics"))
if len(metric_files) == 0:
casava_report = _find_casava_report(dirs["flowcell"])
assert len(casava_report) > 0, \
"Could not locate CASAVA demultiplex report in {}, aborting..".format(dirs["flowcell"])
metric_files = _casava_report_to_metrics(run_info_file, casava_report,
dirs)
assert len(metric_files) > 0, \
"Could not locate or create required metric files, aborting.."
print(
"A report will be created on Google Docs based on the demultiplexed data in {}"
.format(dirs["work"]))
print("The configuration file is {0} and the run info file is {1}".format(
config_file, run_info_file))
print("The run was started on {0} and has flowcell id {1}".format(
fc_date, fc_name))
if not dryrun:
create_report_on_gdocs(fc_date, fc_name, run_info_file, dirs, config)
else:
print("DRY-RUN: nothing uploaded")
def main(run_id, config_file, run_info_file=None, dryrun=False):
assert run_id, \
"No run id was specified"
assert os.path.exists(config_file), \
"The configuration file, {}, could not be found".format(config_file)
config = load_config(config_file)
assert "gdocs_upload" in config, \
"The configuration file, {}, has no section specifying the Google docs details".format(config_file)
analysis_cfg = config.get("analysis",{})
if "store_dir" in analysis_cfg:
archive_dir = os.path.join(analysis_cfg["store_dir"], run_id)
else:
archive_dir = os.getcwd()
analysis_dir = None
if "base_dir" in analysis_cfg:
analysis_dir = os.path.join(analysis_cfg["base_dir"], run_id)
if analysis_dir is None or not os.path.exists(analysis_dir):
analysis_dir = tempfile.mkdtemp()
dirs = {"work": os.path.normpath(analysis_dir),
"flowcell": os.path.normpath(archive_dir)}
assert os.path.exists(dirs["flowcell"]), \
"The flowcell directory, {}, could not be found".format(dirs["flowcell"])
assert os.path.exists(dirs["work"]), \
"The work directory, {}, could not be found".format(dirs["work"])
if run_info_file is None:
run_info_file = os.path.join(dirs["flowcell"], "run_info.yaml")
if not os.path.exists(run_info_file):
# Locate the samplesheet and convert to yaml
samplesheet = _find_samplesheet(dirs["flowcell"])
assert samplesheet, \
"Could not locate samplesheet in {}, aborting..".format(dirs["flowcell"])
fh, run_info_file = tempfile.mkstemp()
os.close(fh)
run_info_file = ssheet.csv2yaml(samplesheet,run_info_file)
assert os.path.exists(run_info_file), \
"The run info configuration file, {}, could not be found".format(run_info_file)
fc_name, fc_date = fc.get_flowcell_info(dirs["flowcell"])
# If we have no bc_metrics files in the workdir, we may be looking at a Casava run.
# In that case, attempt to parse the Demultiplex_Stats.htm file and create bc_metrics files
metric_files = glob.glob(os.path.join(dirs["work"], "*_barcode", "*bc[_.]metrics")) + glob.glob(os.path.join(dirs["work"], "*bc[_.]metrics"))
if len(metric_files) == 0:
casava_report = _find_casava_report(dirs["flowcell"])
assert len(casava_report) > 0, \
"Could not locate CASAVA demultiplex report in {}, aborting..".format(dirs["flowcell"])
metric_files = _casava_report_to_metrics(run_info_file, casava_report, dirs)
assert len(metric_files) > 0, \
"Could not locate or create required metric files, aborting.."
print("A report will be created on Google Docs based on the demultiplexed data in {}".format(dirs["work"]))
print("The configuration file is {0} and the run info file is {1}".format(config_file, run_info_file))
print("The run was started on {0} and has flowcell id {1}".format(fc_date, fc_name))
if not dryrun:
create_report_on_gdocs(fc_date, fc_name, run_info_file, dirs, config)
else:
print("DRY-RUN: nothing uploaded")
def create_report_on_gdocs(*args):
[fc_date, fc_name, run_info_yaml, dirs, config] = args
return sequencing_report.create_report_on_gdocs(fc_date, fc_name, run_info_yaml, dirs, config)
