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_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_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_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_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_strip_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to process prepared files
for use with the tacl ngrams command."""
parser = subparsers.add_parser(
'strip', description=constants.STRIP_DESCRIPTION,
epilog=constants.STRIP_EPILOG, formatter_class=ParagraphFormatter,
help=constants.STRIP_HELP)
parser.set_defaults(func=strip_files)
utils.add_common_arguments(parser)
parser.add_argument('input', help=constants.STRIP_INPUT_HELP,
metavar='INPUT')
parser.add_argument('output', help=constants.STRIP_OUTPUT_HELP,
metavar='OUTPUT')
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_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_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_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_catalogue_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate and save
a catalogue file."""
parser = subparsers.add_parser(
'catalogue', description=constants.CATALOGUE_DESCRIPTION,
epilog=constants.CATALOGUE_EPILOG,
formatter_class=ParagraphFormatter, help=constants.CATALOGUE_HELP)
utils.add_common_arguments(parser)
parser.set_defaults(func=generate_catalogue)
parser.add_argument('corpus', help=constants.DB_CORPUS_HELP,
metavar='CORPUS')
utils.add_query_arguments(parser)
parser.add_argument('-l', '--label', default='',
help=constants.CATALOGUE_LABEL_HELP)
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_common_arguments(parser)
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_strip_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to process prepared files
for use with the tacl ngrams command."""
parser = subparsers.add_parser('strip',
description=constants.STRIP_DESCRIPTION,
epilog=constants.STRIP_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.STRIP_HELP)
parser.set_defaults(func=strip_files)
utils.add_common_arguments(parser)
parser.add_argument('input',
help=constants.STRIP_INPUT_HELP,
metavar='INPUT')
parser.add_argument('output',
help=constants.STRIP_OUTPUT_HELP,
metavar='OUTPUT')
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_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_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_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_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_catalogue_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to generate and save
a catalogue file."""
parser = subparsers.add_parser('catalogue',
description=constants.CATALOGUE_DESCRIPTION,
epilog=constants.CATALOGUE_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.CATALOGUE_HELP)
utils.add_common_arguments(parser)
parser.set_defaults(func=generate_catalogue)
parser.add_argument('corpus',
help=constants.DB_CORPUS_HELP,
metavar='CORPUS')
utils.add_query_arguments(parser)
parser.add_argument('-l',
'--label',
default='',
help=constants.CATALOGUE_LABEL_HELP)
def generate_prepare_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to prepare source XML
files for stripping."""
parser = subparsers.add_parser(
'prepare', description=constants.PREPARE_DESCRIPTION,
epilog=constants.PREPARE_EPILOG, formatter_class=ParagraphFormatter,
help=constants.PREPARE_HELP)
parser.set_defaults(func=prepare_xml)
utils.add_common_arguments(parser)
parser.add_argument('-s', '--source', dest='source',
choices=constants.TEI_SOURCE_CHOICES,
default=constants.TEI_SOURCE_CBETA_GITHUB,
help=constants.PREPARE_SOURCE_HELP,
metavar='SOURCE')
parser.add_argument('input', help=constants.PREPARE_INPUT_HELP,
metavar='INPUT')
parser.add_argument('output', help=constants.PREPARE_OUTPUT_HELP,
metavar='OUTPUT')
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_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 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 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_prepare_subparser(subparsers):
"""Adds a sub-command parser to `subparsers` to prepare source XML
files for stripping."""
parser = subparsers.add_parser('prepare',
description=constants.PREPARE_DESCRIPTION,
epilog=constants.PREPARE_EPILOG,
formatter_class=ParagraphFormatter,
help=constants.PREPARE_HELP)
parser.set_defaults(func=prepare_xml)
utils.add_common_arguments(parser)
parser.add_argument('-s',
'--source',
dest='source',
choices=constants.TEI_SOURCE_CHOICES,
default=constants.TEI_SOURCE_CBETA_GITHUB,
help=constants.PREPARE_SOURCE_HELP,
metavar='SOURCE')
parser.add_argument('input',
help=constants.PREPARE_INPUT_HELP,
metavar='INPUT')
parser.add_argument('output',
help=constants.PREPARE_OUTPUT_HELP,
metavar='OUTPUT')
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)
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)