qurator-spk/page2tsv
1
0
Fork 0
mirror of https://github.com/qurator-spk/page2tsv.git synced 2025-10-30 16:14:13 +01:00
Code Issues Releases Wiki Activity

add tsv2tsv tool;make easy re-processing of tsv files possible

Browse source
This commit is contained in:
Kai Labusch 2024-11-12 14:46:00 +01:00
parent 438b10e407
commit ef8244a466
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
qurator/tsvtools/cli.py
View file

@ -257,7 +257,9 @@ def unicode_normalize(text, normalization_map=None, use_combining_characters=Tru
@click.command() @click.command()
@click.argument('tsv-in-file', type=click.Path(exists=True), required=True, nargs=1) @click.argument('tsv-in-file', type=click.Path(exists=True), required=True, nargs=1)
@click.option('--tsv-out-file', type=click.Path(), default=None, help="Write modified TSV to this file.") @click.option('--tsv-out-file', type=click.Path(), default=None, help="Write modified TSV to this file.")
@click.option('--ner-rest-endpoint', type=str, default=None, help="") @click.option('--ner-rest-endpoint', type=str, default=None, help="REST endpoint of sbb_ner service. "
"See https://github.com/qurator-spk/sbb_ner "
"for details.")
@click.option('--noproxy', type=bool, is_flag=True, help='disable proxy. default: enabled.') @click.option('--noproxy', type=bool, is_flag=True, help='disable proxy. default: enabled.')
@click.option('--num-tokens', type=bool, is_flag=True, help='Print number of tokens in input/output file.') @click.option('--num-tokens', type=bool, is_flag=True, help='Print number of tokens in input/output file.')
@click.option('--sentence-count', type=bool, is_flag=True, help='Print sentence count in input/output file.') @click.option('--sentence-count', type=bool, is_flag=True, help='Print sentence count in input/output file.')