From f8d4b601f7f37ab3f9b342cdb438d15984a739ff Mon Sep 17 00:00:00 2001
From: Patrick Jentsch <p.jentsch@uni-bielefeld.de>
Date: Fri, 25 Nov 2022 10:46:46 +0100
Subject: [PATCH] Fix corpus building process for vrt files without entities
---
app/converters/vrt.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/converters/vrt.py b/app/converters/vrt.py
index 4c4a613e..08fa82c9 100644
--- a/app/converters/vrt.py
+++ b/app/converters/vrt.py
@@ -97,7 +97,7 @@ def normalize_vrt_file(input_file, output_file):
multi_line_tag_definition = False
continue
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 current_ent:
output_vrt += '</ent>\n'
--
GitLab