sporada/nopaque
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git synced 2024-12-25 10:54:18 +00:00
Code Issues Projects Releases Wiki Activity

Fix corpus building process for vrt files without entities

Browse Source
This commit is contained in:
Patrick Jentsch 2022-11-25 10:46:46 +01:00
parent aff85f2145
commit f8d4b601f7
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
app/converters/vrt.py
View File

@ -97,7 +97,7 @@ def normalize_vrt_file(input_file, output_file):
multi_line_tag_definition = False multi_line_tag_definition = False
continue continue
pos_attrs = line.rstrip('\n').split('\t') pos_attrs = line.rstrip('\n').split('\t')
if not has_ent_as_s_attr: if not has_ent_as_s_attr and len(pos_attrs) > 4:
if pos_attrs[4].lower() in ['null', 'none']: if pos_attrs[4].lower() in ['null', 'none']:
if current_ent: if current_ent:
output_vrt += '</ent>\n' output_vrt += '</ent>\n'