def generate_ngrams_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to add n-grams data
to the data store."""
parser = subparsers.add_parser('ngrams',
description=constants.NGRAMS_DESCRIPTION,
epilog=constants.NGRAMS_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.NGRAMS_HELP)
parser.set_defaults(func=generate_ngrams)
utils.add_common_arguments(parser)
parser.add_argument('-c',
'--catalogue',
dest='catalogue',
help=constants.NGRAMS_CATALOGUE_HELP,
metavar='CATALOGUE')
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
parser.add_argument('min_size',
help=constants.NGRAMS_MINIMUM_HELP,
metavar='MINIMUM',
type=int)
parser.add_argument('max_size',
help=constants.NGRAMS_MAXIMUM_HELP,
metavar='MAXIMUM',
type=int)
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_counts_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make a counts
query."""
parser = subparsers.add_parser(
'counts', description=constants.COUNTS_DESCRIPTION,
epilog=constants.COUNTS_EPILOG, formatter_class=ParagraphFormatter,
help=constants.COUNTS_HELP)
parser.set_defaults(func=ngram_counts)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_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 generate_intersect_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make an
intersection query."""
parser = subparsers.add_parser(
'intersect', description=constants.INTERSECT_DESCRIPTION,
epilog=constants.INTERSECT_EPILOG, formatter_class=ParagraphFormatter,
help=constants.INTERSECT_HELP)
parser.set_defaults(func=ngram_intersection)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
def generate_supplied_intersect_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to run an intersect query
using the supplied results sets."""
parser = subparsers.add_parser(
'sintersect', description=constants.SUPPLIED_INTERSECT_DESCRIPTION,
epilog=constants.SUPPLIED_INTERSECT_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.SUPPLIED_INTERSECT_HELP)
parser.set_defaults(func=supplied_intersect)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser, True)
utils.add_supplied_query_arguments(parser)
def generate_supplied_intersect_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to run an intersect query
using the supplied results sets."""
parser = subparsers.add_parser(
'sintersect',
description=constants.SUPPLIED_INTERSECT_DESCRIPTION,
epilog=constants.SUPPLIED_INTERSECT_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.SUPPLIED_INTERSECT_HELP)
parser.set_defaults(func=supplied_intersect)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser, True)
utils.add_supplied_query_arguments(parser)
def generate_intersect_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make an
intersection query."""
parser = subparsers.add_parser('intersect',
description=constants.INTERSECT_DESCRIPTION,
epilog=constants.INTERSECT_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.INTERSECT_HELP)
parser.set_defaults(func=ngram_intersection)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
def generate_counts_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make a counts
query."""
parser = subparsers.add_parser('counts',
description=constants.COUNTS_DESCRIPTION,
epilog=constants.COUNTS_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.COUNTS_HELP)
parser.set_defaults(func=ngram_counts)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_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 generate_parser():
"""Return a parser for the command."""
parser = argparse.ArgumentParser(description=JITC_DESCRIPTION,
epilog=JITC_EPILOG,
formatter_class=ParagraphFormatter)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
parser.add_argument('label', help=JITC_LABEL_HELP, metavar='LABEL')
parser.add_argument('output',
help=constants.REPORT_OUTPUT_HELP,
metavar='OUTPUT')
return parser
def generate_search_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate search
results for a set of n-grams."""
parser = subparsers.add_parser(
'search', description=constants.SEARCH_DESCRIPTION,
epilog=constants.SEARCH_EPILOG, formatter_class=ParagraphFormatter,
help=constants.SEARCH_HELP)
parser.set_defaults(func=search_texts)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
parser.add_argument('ngrams', help=constants.SEARCH_NGRAMS_HELP,
nargs='*', metavar='NGRAMS')
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_diff_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make a diff
query."""
parser = subparsers.add_parser(
'diff', description=constants.DIFF_DESCRIPTION,
epilog=constants.DIFF_EPILOG, formatter_class=ParagraphFormatter,
help=constants.DIFF_HELP)
parser.set_defaults(func=ngram_diff)
group = parser.add_mutually_exclusive_group()
group.add_argument('-a', '--asymmetric', help=constants.ASYMMETRIC_HELP,
metavar='LABEL')
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
def generate_search_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate search
results for a set of n-grams."""
parser = subparsers.add_parser('search',
description=constants.SEARCH_DESCRIPTION,
epilog=constants.SEARCH_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.SEARCH_HELP)
parser.set_defaults(func=search_texts)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
parser.add_argument('ngrams',
help=constants.SEARCH_NGRAMS_HELP,
nargs='*',
metavar='NGRAMS')
def generate_diff_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to make a diff
query."""
parser = subparsers.add_parser('diff',
description=constants.DIFF_DESCRIPTION,
epilog=constants.DIFF_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.DIFF_HELP)
parser.set_defaults(func=ngram_diff)
group = parser.add_mutually_exclusive_group()
group.add_argument('-a',
'--asymmetric',
help=constants.ASYMMETRIC_HELP,
metavar='LABEL')
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
def generate_ngrams_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to add n-grams data
to the data store."""
parser = subparsers.add_parser(
'ngrams', description=constants.NGRAMS_DESCRIPTION,
epilog=constants.NGRAMS_EPILOG, formatter_class=ParagraphFormatter,
help=constants.NGRAMS_HELP)
parser.set_defaults(func=generate_ngrams)
utils.add_common_arguments(parser)
parser.add_argument('-c', '--catalogue', dest='catalogue',
help=constants.NGRAMS_CATALOGUE_HELP,
metavar='CATALOGUE')
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
parser.add_argument('min_size', help=constants.NGRAMS_MINIMUM_HELP,
metavar='MINIMUM', type=int)
parser.add_argument('max_size', help=constants.NGRAMS_MAXIMUM_HELP,
metavar='MAXIMUM', type=int)
def generate_query_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to send SQL to the data
store and return the results."""
parser = subparsers.add_parser('query',
description=constants.QUERY_DESCRIPTION,
formatter_class=ParagraphFormatter,
help=constants.QUERY_HELP)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser, True)
parser.add_argument('-q',
'--query',
help=constants.QUERY_QUERY_HELP,
metavar='QUERY',
required=True)
parser.add_argument('-p',
'--parameters',
help=constants.QUERY_PARAMETERS_HELP,
metavar='PARAMETER',
nargs='*')
parser.set_defaults(func=query_data_store)
def main():
parser = argparse.ArgumentParser(description=DESCRIPTION,
epilog=EPILOG,
formatter_class=ParagraphFormatter)
parser.add_argument('--min_size',
default=1,
help=MINIMUM_HELP,
metavar='MINIMUM',
type=int)
parser.add_argument('--max_size',
default=10,
help=MAXIMUM_HELP,
metavar='MAXIMUM',
type=int)
utils.add_common_arguments(parser)
utils.add_db_arguments(parser)
utils.add_corpus_arguments(parser)
utils.add_query_arguments(parser)
parser.add_argument('output_dir',
help='Path to output directory',
metavar='DIRECTORY')
parser.add_argument('tracker_path',
help='Path to tracking file',
metavar='TRACKING')
args = parser.parse_args()
logger = logging.getLogger('taclextra')
if hasattr(args, 'verbose'):
utils.configure_logging(args.verbose, logger)
corpus = utils.get_corpus(args)
if args.db == 'memory':
data_store = None
else:
data_store = utils.get_data_store(args)
tokenizer = utils.get_tokenizer(args)
catalogue = utils.get_catalogue(args)
pi = paired_intersector.PairedIntersector(data_store, corpus, tokenizer,
catalogue, args.output_dir,
args.tracker_path, args.min_size,
args.max_size)
pi.intersect_all()
