qurator-spk/page2tsv
1
0
Fork 0
mirror of https://github.com/qurator-spk/page2tsv.git synced 2025-10-31 00:24:13 +01:00
Code Issues Releases Wiki Activity

fix line shift

Browse source
This commit is contained in:
Kai 2021-03-10 16:08:39 +01:00
parent 6ffba183ab
commit 243c7b48c6
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tsvtools/cli.py
View file

@ -138,7 +138,7 @@ def page2tsv(page_xml_file, tsv_out_file, purpose, image_url, ner_rest_endpoint,
left, right, top, bottom = min(x_points), max(x_points), min(y_points), max(y_points)
tsv.append((rgn_number, len(line_info), left + (right - left) / 2.0, text,
tsv.append((rgn_number, len(line_info)-1, left + (right - left) / 2.0, text,
len(urls), left, right, top, bottom))
line_info = pd.DataFrame(line_info, columns=['url_id', 'left', 'right', 'top', 'bottom', 'conf'])