def main():
parser = argparse.ArgumentParser(description=DESCRIPTION,
epilog=EPILOG,
formatter_class=ParagraphFormatter)
utils.add_db_arguments(parser)
utils.add_tokenizer_argument(parser)
utils.add_query_arguments(parser)
parser.add_argument('parent',
help=PARENT_LABEL_HELP,
metavar='PARENT_LABEL')
parser.add_argument('child', help=CHILD_LABEL_HELP, metavar='CHILD_LABEL')
parser.add_argument('unrelated',
help=UNRELATED_LABEL_HELP,
metavar='UNRELATED_LABEL')
parser.add_argument('max_works',
help=MAX_WORKS_HELP,
metavar='MAXIMUM',
type=int)
parser.add_argument('output_dir',
help=OUTPUT_DIR_HELP,
metavar='DIRECTORY')
args = parser.parse_args()
catalogue = utils.get_catalogue(args)
data_store = utils.get_data_store(args)
tokenizer = utils.get_tokenizer(args)
try:
test = taclextra.paternity.PaternityTest(data_store, catalogue,
tokenizer, args.parent,
args.child, args.unrelated,
args.max_works,
args.output_dir)
test.process()
except Exception as e:
parser.error(e)
def generate_supplied_diff_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to run a diff query using
the supplied results sets."""
parser = subparsers.add_parser(
'sdiff', description=constants.SUPPLIED_DIFF_DESCRIPTION,
epilog=constants.SUPPLIED_DIFF_EPILOG,
formatter_class=ParagraphFormatter, help=constants.SUPPLIED_DIFF_HELP)
parser.set_defaults(func=supplied_diff)
utils.add_common_arguments(parser)
utils.add_tokenizer_argument(parser)
utils.add_db_arguments(parser, True)
utils.add_supplied_query_arguments(parser)
def generate_supplied_diff_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to run a diff query using
the supplied results sets."""
parser = subparsers.add_parser(
'sdiff',
description=constants.SUPPLIED_DIFF_DESCRIPTION,
epilog=constants.SUPPLIED_DIFF_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.SUPPLIED_DIFF_HELP)
parser.set_defaults(func=supplied_diff)
utils.add_common_arguments(parser)
utils.add_tokenizer_argument(parser)
utils.add_db_arguments(parser, True)
utils.add_supplied_query_arguments(parser)
def main():
parser = argparse.ArgumentParser(description=DESCRIPTION)
utils.add_db_arguments(parser)
utils.add_tokenizer_argument(parser)
utils.add_query_arguments(parser)
parser.add_argument('output', help=HELP_OUTPUT, metavar='DIRECTORY')
args = parser.parse_args()
data_store = utils.get_data_store(args)
catalogue = utils.get_catalogue(args)
tokenizer = utils.get_tokenizer(args)
output_dir = os.path.abspath(args.output)
reporter = lifetime.LifetimeReporter(data_store, catalogue, tokenizer,
output_dir)
reporter.process()
def generate_normalise_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate a normalised
corpus from an unnormalised corpus."""
parser = subparsers.add_parser(
'normalise', description=constants.NORMALISE_DESCRIPTION,
epilog=constants.NORMALISE_EPILOG, formatter_class=ParagraphFormatter,
help=constants.NORMALISE_HELP)
parser.set_defaults(func=normalise_corpus)
utils.add_tokenizer_argument(parser)
utils.add_common_arguments(parser)
parser.add_argument('corpus', help=constants.NORMALISE_CORPUS_HELP,
metavar='CORPUS')
parser.add_argument('mapping', help=constants.NORMALISE_MAPPING_HELP,
metavar='MAPPING')
parser.add_argument('output', help=constants.NORMALISE_OUTPUT_HELP,
metavar='OUTPUT')
def generate_lifetime_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make a lifetime report."""
parser = subparsers.add_parser(
'lifetime', description=constants.LIFETIME_DESCRIPTION,
epilog=constants.LIFETIME_EPILOG, formatter_class=ParagraphFormatter,
help=constants.LIFETIME_HELP)
parser.set_defaults(func=lifetime_report)
utils.add_tokenizer_argument(parser)
utils.add_common_arguments(parser)
utils.add_query_arguments(parser)
parser.add_argument('results', help=constants.LIFETIME_RESULTS_HELP,
metavar='RESULTS')
parser.add_argument('label', help=constants.LIFETIME_LABEL_HELP,
metavar='LABEL')
parser.add_argument('output', help=constants.REPORT_OUTPUT_HELP,
metavar='OUTPUT')
def generate_normalise_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate a normalised
corpus from an unnormalised corpus."""
parser = subparsers.add_parser('normalise',
description=constants.NORMALISE_DESCRIPTION,
epilog=constants.NORMALISE_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.NORMALISE_HELP)
parser.set_defaults(func=normalise_corpus)
utils.add_tokenizer_argument(parser)
utils.add_common_arguments(parser)
parser.add_argument('corpus',
help=constants.NORMALISE_CORPUS_HELP,
metavar='CORPUS')
parser.add_argument('mapping',
help=constants.NORMALISE_MAPPING_HELP,
metavar='MAPPING')
parser.add_argument('output',
help=constants.NORMALISE_OUTPUT_HELP,
metavar='OUTPUT')
def generate_lifetime_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make a lifetime report."""
parser = subparsers.add_parser('lifetime',
description=constants.LIFETIME_DESCRIPTION,
epilog=constants.LIFETIME_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.LIFETIME_HELP)
parser.set_defaults(func=lifetime_report)
utils.add_tokenizer_argument(parser)
utils.add_common_arguments(parser)
utils.add_query_arguments(parser)
parser.add_argument('results',
help=constants.LIFETIME_RESULTS_HELP,
metavar='RESULTS')
parser.add_argument('label',
help=constants.LIFETIME_LABEL_HELP,
metavar='LABEL')
parser.add_argument('output',
help=constants.REPORT_OUTPUT_HELP,
metavar='OUTPUT')
def generate_results_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to manipulate CSV
results data."""
parser = subparsers.add_parser(
'results', description=constants.RESULTS_DESCRIPTION,
epilog=constants.RESULTS_EPILOG, formatter_class=ParagraphFormatter,
help=constants.RESULTS_HELP)
utils.add_common_arguments(parser)
parser.set_defaults(func=results)
be_group = parser.add_argument_group('bifurcated extend')
be_group.add_argument('-b', '--bifurcated-extend',
dest='bifurcated_extend', metavar='CORPUS',
help=constants.RESULTS_BIFURCATED_EXTEND_HELP)
be_group.add_argument('--max-be-count', dest='bifurcated_extend_size',
help=constants.RESULTS_BIFURCATED_EXTEND_MAX_HELP,
metavar='COUNT', type=int)
normalise_group = parser.add_argument_group('denormalise')
normalise_group.add_argument(
'--denormalise', dest='denormalise_mapping',
help=constants.RESULTS_DENORMALISE_MAPPING_HELP, metavar='MAPPING')
normalise_group.add_argument(
'--denormalised-corpus', dest='denormalised_corpus',
help=constants.RESULTS_DENORMALISE_CORPUS_HELP, metavar='CORPUS')
parser.add_argument('-e', '--extend', dest='extend',
help=constants.RESULTS_EXTEND_HELP, metavar='CORPUS')
parser.add_argument('--excise', help=constants.RESULTS_EXCISE_HELP,
metavar='NGRAM', type=str)
parser.add_argument('-l', '--label', dest='label',
help=constants.RESULTS_LABEL_HELP, metavar='LABEL')
parser.add_argument('--min-count', dest='min_count',
help=constants.RESULTS_MINIMUM_COUNT_HELP,
metavar='COUNT', type=int)
parser.add_argument('--max-count', dest='max_count',
help=constants.RESULTS_MAXIMUM_COUNT_HELP,
metavar='COUNT', type=int)
parser.add_argument('--min-count-work', dest='min_count_work',
help=constants.RESULTS_MINIMUM_COUNT_WORK_HELP,
metavar='COUNT', type=int)
parser.add_argument('--max-count-work', dest='max_count_work',
help=constants.RESULTS_MAXIMUM_COUNT_WORK_HELP,
metavar='COUNT', type=int)
parser.add_argument('--min-size', dest='min_size',
help=constants.RESULTS_MINIMUM_SIZE_HELP,
metavar='SIZE', type=int)
parser.add_argument('--max-size', dest='max_size',
help=constants.RESULTS_MAXIMUM_SIZE_HELP,
metavar='SIZE', type=int)
parser.add_argument('--min-works', dest='min_works',
help=constants.RESULTS_MINIMUM_WORK_HELP,
metavar='COUNT', type=int)
parser.add_argument('--max-works', dest='max_works',
help=constants.RESULTS_MAXIMUM_WORK_HELP,
metavar='COUNT', type=int)
parser.add_argument('--ngrams', dest='ngrams',
help=constants.RESULTS_NGRAMS_HELP, metavar='NGRAMS')
parser.add_argument('--reciprocal', action='store_true',
help=constants.RESULTS_RECIPROCAL_HELP)
parser.add_argument('--reduce', action='store_true',
help=constants.RESULTS_REDUCE_HELP)
parser.add_argument('--relabel', help=constants.RESULTS_RELABEL_HELP,
metavar='CATALOGUE')
parser.add_argument('--remove', help=constants.RESULTS_REMOVE_HELP,
metavar='LABEL', type=str)
parser.add_argument('--sort', action='store_true',
help=constants.RESULTS_SORT_HELP)
utils.add_tokenizer_argument(parser)
parser.add_argument('-z', '--zero-fill', dest='zero_fill',
help=constants.RESULTS_ZERO_FILL_HELP,
metavar='CORPUS')
parser.add_argument('results', help=constants.RESULTS_RESULTS_HELP,
metavar='RESULTS')
unsafe_group = parser.add_argument_group(
constants.RESULTS_UNSAFE_GROUP_TITLE,
constants.RESULTS_UNSAFE_GROUP_DESCRIPTION)
unsafe_group.add_argument('--add-label-count', action='store_true',
help=constants.RESULTS_ADD_LABEL_COUNT_HELP)
unsafe_group.add_argument('--add-label-work-count', action='store_true',
help=constants.RESULTS_ADD_LABEL_WORK_COUNT_HELP)
unsafe_group.add_argument('--collapse-witnesses', action='store_true',
help=constants.RESULTS_COLLAPSE_WITNESSES_HELP)
unsafe_group.add_argument('--group-by-ngram', dest='group_by_ngram',
help=constants.RESULTS_GROUP_BY_NGRAM_HELP,
metavar='CATALOGUE')
unsafe_group.add_argument('--group-by-witness', action='store_true',
help=constants.RESULTS_GROUP_BY_WITNESS_HELP)
def generate_results_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to manipulate CSV
results data."""
parser = subparsers.add_parser('results',
description=constants.RESULTS_DESCRIPTION,
epilog=constants.RESULTS_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.RESULTS_HELP)
utils.add_common_arguments(parser)
parser.set_defaults(func=results)
be_group = parser.add_argument_group('bifurcated extend')
be_group.add_argument('-b',
'--bifurcated-extend',
dest='bifurcated_extend',
metavar='CORPUS',
help=constants.RESULTS_BIFURCATED_EXTEND_HELP)
be_group.add_argument('--max-be-count',
dest='bifurcated_extend_size',
help=constants.RESULTS_BIFURCATED_EXTEND_MAX_HELP,
metavar='COUNT',
type=int)
normalise_group = parser.add_argument_group('denormalise')
normalise_group.add_argument(
'--denormalise',
dest='denormalise_mapping',
help=constants.RESULTS_DENORMALISE_MAPPING_HELP,
metavar='MAPPING')
normalise_group.add_argument(
'--denormalised-corpus',
dest='denormalised_corpus',
help=constants.RESULTS_DENORMALISE_CORPUS_HELP,
metavar='CORPUS')
parser.add_argument('-e',
'--extend',
dest='extend',
help=constants.RESULTS_EXTEND_HELP,
metavar='CORPUS')
parser.add_argument('--excise',
help=constants.RESULTS_EXCISE_HELP,
metavar='NGRAM',
type=str)
parser.add_argument('-l',
'--label',
dest='label',
help=constants.RESULTS_LABEL_HELP,
metavar='LABEL')
parser.add_argument('--min-count',
dest='min_count',
help=constants.RESULTS_MINIMUM_COUNT_HELP,
metavar='COUNT',
type=int)
parser.add_argument('--max-count',
dest='max_count',
help=constants.RESULTS_MAXIMUM_COUNT_HELP,
metavar='COUNT',
type=int)
parser.add_argument('--min-count-work',
dest='min_count_work',
help=constants.RESULTS_MINIMUM_COUNT_WORK_HELP,
metavar='COUNT',
type=int)
parser.add_argument('--max-count-work',
dest='max_count_work',
help=constants.RESULTS_MAXIMUM_COUNT_WORK_HELP,
metavar='COUNT',
type=int)
parser.add_argument('--min-size',
dest='min_size',
help=constants.RESULTS_MINIMUM_SIZE_HELP,
metavar='SIZE',
type=int)
parser.add_argument('--max-size',
dest='max_size',
help=constants.RESULTS_MAXIMUM_SIZE_HELP,
metavar='SIZE',
type=int)
parser.add_argument('--min-works',
dest='min_works',
help=constants.RESULTS_MINIMUM_WORK_HELP,
metavar='COUNT',
type=int)
parser.add_argument('--max-works',
dest='max_works',
help=constants.RESULTS_MAXIMUM_WORK_HELP,
metavar='COUNT',
type=int)
parser.add_argument('--ngrams',
dest='ngrams',
help=constants.RESULTS_NGRAMS_HELP,
metavar='NGRAMS')
parser.add_argument('--reciprocal',
action='store_true',
help=constants.RESULTS_RECIPROCAL_HELP)
parser.add_argument('--reduce',
action='store_true',
help=constants.RESULTS_REDUCE_HELP)
parser.add_argument('--relabel',
help=constants.RESULTS_RELABEL_HELP,
metavar='CATALOGUE')
parser.add_argument('--remove',
help=constants.RESULTS_REMOVE_HELP,
metavar='LABEL',
type=str)
parser.add_argument('--sort',
action='store_true',
help=constants.RESULTS_SORT_HELP)
utils.add_tokenizer_argument(parser)
parser.add_argument('-z',
'--zero-fill',
dest='zero_fill',
help=constants.RESULTS_ZERO_FILL_HELP,
metavar='CORPUS')
parser.add_argument('results',
help=constants.RESULTS_RESULTS_HELP,
metavar='RESULTS')
unsafe_group = parser.add_argument_group(
constants.RESULTS_UNSAFE_GROUP_TITLE,
constants.RESULTS_UNSAFE_GROUP_DESCRIPTION)
unsafe_group.add_argument('--add-label-count',
action='store_true',
help=constants.RESULTS_ADD_LABEL_COUNT_HELP)
unsafe_group.add_argument('--add-label-work-count',
action='store_true',
help=constants.RESULTS_ADD_LABEL_WORK_COUNT_HELP)
unsafe_group.add_argument('--collapse-witnesses',
action='store_true',
help=constants.RESULTS_COLLAPSE_WITNESSES_HELP)
unsafe_group.add_argument('--group-by-ngram',
dest='group_by_ngram',
help=constants.RESULTS_GROUP_BY_NGRAM_HELP,
metavar='CATALOGUE')
unsafe_group.add_argument('--group-by-witness',
action='store_true',
help=constants.RESULTS_GROUP_BY_WITNESS_HELP)