aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--fatcat_covid19/transform.py2
1 files changed, 1 insertions, 1 deletions
diff --git a/fatcat_covid19/transform.py b/fatcat_covid19/transform.py
index 338b3e8..7e1a47f 100644
--- a/fatcat_covid19/transform.py
+++ b/fatcat_covid19/transform.py
@@ -81,7 +81,7 @@ def fulltext_to_elasticsearch(row, force_bool=True):
# hack to (partially) clean up common JATS abstract display case
if a.get('mimetype') == 'application/xml+jats':
- for tag in ('p', 'jats', 'jats:p', 'jats:title'):
+ for tag in ('p', 'b', 'i', 'br', 'jats', 'jats:p', 'jats:title'):
a['content'] = a['content'].replace('<{}>'.format(tag), '')
a['content'] = a['content'].replace('</{}>'.format(tag), '')
# ugh, double encoding happens