def __init__(self, dirn, data_format=None, qc_dir="qc", regex_pattern=None, version=None):
"""Create a new QCReporter instance
Arguments:
dirn: top-level directory for the run
data_format: (optional) set format of files to acquire
qc_dir: (optional) name of qc subdirectory holding QC
outputs relative to the top-level (default is 'qc')
version: (optional) version of the QC reporter (default
is the version of the bcftbx package)
"""
# Basic information
self.__dirn = os.path.abspath(dirn)
self.__data_format = data_format
self.__qc_dir = os.path.join(self.__dirn, qc_dir)
# Version
if version is None:
self.__version = "bcftbx-%s" % get_version()
else:
self.__version = version
if not os.path.isdir(self.__qc_dir):
raise QCReporterError, "QC dir %s not found" % self.qc_dir
# Run and experiment names
# Assume that the experiment name is the current dir and the
# run name is the parent directory
self.__name = self.__dirn.split(os.sep)[-1]
self.__run = self.__dirn.split(os.sep)[-2]
self.__report_base_name = "%s_report" % os.path.basename(self.qc_dir)
self.__report_name = "%s_report.%s.%s" % (os.path.basename(self.qc_dir), self.__name, self.__run)
# List of samples
self.__samples = []
# Regexp pattern for selecting sample subset
self.__regex_pattern = regex_pattern
# HTML document
self.__html = self.__init_html()
#######################################################################
if __name__ == "__main__":
# Initialise
max_concurrent_jobs = 4
poll_interval = 30
max_total_jobs = 0
script = None
data_dirs = []
input_type = "solid"
email_addr = None
ge_queue = None
runner_type = "ge"
# Set up command line parser
p = argparse.ArgumentParser(version="%(prog)s "+get_version(),
description=
"Execute SCRIPT on data in each directory "
"DIR. By default the SCRIPT is executed on "
"each CSFASTA/QUAL file pair found in DIR, "
"as 'SCRIPT CSFASTA QUAL'. Use the --input "
"option to run SCRIPT on different types of "
"data (e.g. FASTQ files). SCRIPT can be a "
"quoted string to include command line "
"options (e.g. 'run_solid2fastq.sh --gzip').")
# Basic options
group = p.add_argument_group("Basic Options")
group.add_argument('--limit',action='store',dest='max_concurrent_jobs',
type=int,default=max_concurrent_jobs,
help="queue no more than MAX_CONCURRENT_JOBS at one "
#source_encoding = 'utf-8-sig' # The master toctree document. master_doc = 'index' # General information about the project. project = u'genomics-bcftbx' copyright = u'2015, Peter Briggs' # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the # built documents. # # The short X.Y version. from bcftbx import get_version version = get_version() # The full version, including alpha/beta/rc tags. release = get_version() # The language for content autogenerated by Sphinx. Refer to documentation # for a list of supported languages. #language = None # There are two options for replacing |today|: either, you set today to some # non-false value, then it is used: #today = '' # Else, today_fmt is used as the format for a strftime call. #today_fmt = '%B %d, %Y' # List of patterns, relative to source directory, that match files and # directories to ignore when looking for source files.
#source_encoding = 'utf-8-sig' # The master toctree document. master_doc = 'index' # General information about the project. project = u'genomics-bcftbx' copyright = u'2015, Peter Briggs' # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the # built documents. # # The short X.Y version. from bcftbx import get_version version = get_version() # The full version, including alpha/beta/rc tags. release = get_version() # The language for content autogenerated by Sphinx. Refer to documentation # for a list of supported languages. #language = None # There are two options for replacing |today|: either, you set today to some # non-false value, then it is used: #today = '' # Else, today_fmt is used as the format for a strftime call. #today_fmt = '%B %d, %Y' # List of patterns, relative to source directory, that match files and # directories to ignore when looking for source files.
if __name__ == "__main__":
# Initialise
max_concurrent_jobs = 4
poll_interval = 30
max_total_jobs = 0
script = None
data_dirs = []
input_type = "solid"
email_addr = None
ge_queue = None
runner_type = "ge"
# Set up command line parser
p = optparse.OptionParser(usage="%prog [options] SCRIPT DIR [ DIR ...]",
version="%prog "+get_version(),
description=
"Execute SCRIPT on data in each directory DIR. By default "
"the SCRIPT is executed on each CSFASTA/QUAL file pair "
"found in DIR, as 'SCRIPT CSFASTA QUAL'. Use the --input "
"option to run SCRIPT on different types of data (e.g. "
"FASTQ files). SCRIPT can be a quoted string to include "
"command line options (e.g. 'run_solid2fastq.sh --gzip').")
# Basic options
group = optparse.OptionGroup(p,"Basic Options")
group.add_option('--limit',action='store',dest='max_concurrent_jobs',type='int',
default=max_concurrent_jobs,
help="queue no more than MAX_CONCURRENT_JOBS at one time (default %s)"
% max_concurrent_jobs)
group.add_option('--input',action='store',dest='input_type',default=input_type,
