qurator-spk/page2tsv
1
0
Fork 0
mirror of https://github.com/qurator-spk/page2tsv.git synced 2025-06-09 11:29:55 +02:00
Code Issues Releases Wiki Activity

fix alto2tsv bug

Browse source
This commit is contained in:
Kai Labusch 2023-11-10 17:28:30 +01:00
parent eb750752c6
commit 2f7d01c7cd
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

@ -148,7 +148,9 @@ def alto2tsv(alto_xml_file, tsv_out_file, purpose, image_url, ner_rest_endpoint,
for region_idx, region in alto_iterate_textblocks(alto_xml_file):
for line, line_id, l_left, l_right, l_top, l_bottom in alto_iterate_lines(region):
for line, _, l_left, l_right, l_top, l_bottom in alto_iterate_lines(region):
line_id = len(line_info)
line_info.append((len(urls), l_left, l_right, l_top, l_bottom, line_id))