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_statistics_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate statistics
from a set of results."""
parser = subparsers.add_parser(
'stats', description=constants.STATISTICS_DESCRIPTION,
formatter_class=ParagraphFormatter, help=constants.STATISTICS_HELP)
parser.set_defaults(func=generate_statistics)
utils.add_common_arguments(parser)
utils.add_corpus_arguments(parser)
parser.add_argument('results', help=constants.STATISTICS_RESULTS_HELP,
metavar='RESULTS')
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_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_statistics_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate statistics
from a set of results."""
parser = subparsers.add_parser(
'stats',
description=constants.STATISTICS_DESCRIPTION,
formatter_class=ParagraphFormatter,
help=constants.STATISTICS_HELP)
parser.set_defaults(func=generate_statistics)
utils.add_common_arguments(parser)
utils.add_corpus_arguments(parser)
parser.add_argument('results',
help=constants.STATISTICS_RESULTS_HELP,
metavar='RESULTS')
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 generate_split_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate new corpus
files by splitting existing ones."""
parser = subparsers.add_parser('split',
description=constants.SPLIT_DESCRIPTION,
epilog=constants.SPLIT_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.SPLIT_HELP)
parser.set_defaults(func=split_texts)
utils.add_corpus_arguments(parser)
parser.add_argument('splits',
help=constants.SPLIT_CONF_HELP,
nargs="+",
metavar='CONF')
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_align_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate aligned
sequences from a set of results."""
parser = subparsers.add_parser(
'align', description=constants.ALIGN_DESCRIPTION,
epilog=constants.ALIGN_EPILOG,
formatter_class=ParagraphFormatter, help=constants.ALIGN_HELP)
parser.set_defaults(func=align_results)
utils.add_common_arguments(parser)
parser.add_argument('-m', '--minimum', default=20,
help=constants.ALIGN_MINIMUM_SIZE_HELP, type=int)
utils.add_corpus_arguments(parser)
parser.add_argument('output', help=constants.ALIGN_OUTPUT_HELP,
metavar='OUTPUT')
parser.add_argument('results', help=constants.RESULTS_RESULTS_HELP,
metavar='RESULTS')
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_excise_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to excise n-grams from
witnesses."""
parser = subparsers.add_parser(
'excise', description=constants.EXCISE_DESCRIPTION,
help=constants.EXCISE_HELP)
parser.set_defaults(func=excise)
utils.add_common_arguments(parser)
parser.add_argument('ngrams', metavar='NGRAMS',
help=constants.EXCISE_NGRAMS_HELP)
parser.add_argument('replacement', metavar='REPLACEMENT',
help=constants.EXCISE_REPLACEMENT_HELP)
parser.add_argument('output', metavar='OUTPUT',
help=constants.EXCISE_OUTPUT_HELP)
utils.add_corpus_arguments(parser)
parser.add_argument('works', metavar='WORK',
help=constants.EXCISE_WORKS_HELP, nargs='+')
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 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()
def generate_align_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate aligned
sequences from a set of results."""
parser = subparsers.add_parser('align',
description=constants.ALIGN_DESCRIPTION,
epilog=constants.ALIGN_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.ALIGN_HELP)
parser.set_defaults(func=align_results)
utils.add_common_arguments(parser)
parser.add_argument('-m',
'--minimum',
default=20,
help=constants.ALIGN_MINIMUM_SIZE_HELP,
type=int)
utils.add_corpus_arguments(parser)
parser.add_argument('output',
help=constants.ALIGN_OUTPUT_HELP,
metavar='OUTPUT')
parser.add_argument('results',
help=constants.RESULTS_RESULTS_HELP,
metavar='RESULTS')
def generate_excise_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to excise n-grams from
witnesses."""
parser = subparsers.add_parser('excise',
description=constants.EXCISE_DESCRIPTION,
help=constants.EXCISE_HELP)
parser.set_defaults(func=excise)
utils.add_common_arguments(parser)
parser.add_argument('ngrams',
metavar='NGRAMS',
help=constants.EXCISE_NGRAMS_HELP)
parser.add_argument('replacement',
metavar='REPLACEMENT',
help=constants.EXCISE_REPLACEMENT_HELP)
parser.add_argument('output',
metavar='OUTPUT',
help=constants.EXCISE_OUTPUT_HELP)
utils.add_corpus_arguments(parser)
parser.add_argument('works',
metavar='WORK',
help=constants.EXCISE_WORKS_HELP,
nargs='+')
def generate_highlight_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to highlight a witness'
text with its matches in a result."""
parser = subparsers.add_parser(
'highlight', description=constants.HIGHLIGHT_DESCRIPTION,
epilog=constants.HIGHLIGHT_EPILOG, formatter_class=ParagraphFormatter,
help=constants.HIGHLIGHT_HELP)
parser.set_defaults(func=highlight_text)
utils.add_common_arguments(parser)
parser.add_argument('-m', '--minus-ngrams', metavar='NGRAMS',
help=constants.HIGHLIGHT_MINUS_NGRAMS_HELP)
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument('-n', '--ngrams', action='append', metavar='NGRAMS',
help=constants.HIGHLIGHT_NGRAMS_HELP)
group.add_argument('-r', '--results', metavar='RESULTS',
help=constants.HIGHLIGHT_RESULTS_HELP)
parser.add_argument('-l', '--label', action='append', metavar='LABEL',
help=constants.HIGHLIGHT_LABEL_HELP)
utils.add_corpus_arguments(parser)
parser.add_argument('base_name', help=constants.HIGHLIGHT_BASE_NAME_HELP,
metavar='BASE_NAME')
parser.add_argument('output', metavar='OUTPUT',
help=constants.REPORT_OUTPUT_HELP)
def generate_highlight_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to highlight a witness'
text with its matches in a result."""
parser = subparsers.add_parser('highlight',
description=constants.HIGHLIGHT_DESCRIPTION,
epilog=constants.HIGHLIGHT_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.HIGHLIGHT_HELP)
parser.set_defaults(func=highlight_text)
utils.add_common_arguments(parser)
parser.add_argument('-m',
'--minus-ngrams',
metavar='NGRAMS',
help=constants.HIGHLIGHT_MINUS_NGRAMS_HELP)
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument('-n',
'--ngrams',
action='append',
metavar='NGRAMS',
help=constants.HIGHLIGHT_NGRAMS_HELP)
group.add_argument('-r',
'--results',
metavar='RESULTS',
help=constants.HIGHLIGHT_RESULTS_HELP)
parser.add_argument('-l',
'--label',
action='append',
metavar='LABEL',
help=constants.HIGHLIGHT_LABEL_HELP)
utils.add_corpus_arguments(parser)
parser.add_argument('base_name',
help=constants.HIGHLIGHT_BASE_NAME_HELP,
metavar='BASE_NAME')
parser.add_argument('output',
metavar='OUTPUT',
help=constants.REPORT_OUTPUT_HELP)
