[fix] do highlight replacement at once

Highlights all search queries in search result in one go.

Fixes the case where search query contains word from highlight HTML code,
which causes broken HTML to appear in search results.

Closes #3057
This commit is contained in:
allixx 2023-12-19 11:21:54 +03:00 committed by Markus Heiser
parent 8c73aa772b
commit e4cf0a7d4f
2 changed files with 7 additions and 4 deletions

View file

@ -290,10 +290,8 @@ def highlight_content(content, query):
if len(qs) > 0:
queries.extend(re.findall(regex_highlight_cjk(qs), content, flags=re.I | re.U))
if len(queries) > 0:
for q in set(queries):
content = re.sub(
regex_highlight_cjk(q), f'<span class="highlight">{q}</span>'.replace('\\', r'\\'), content
)
regex = re.compile("|".join(map(regex_highlight_cjk, queries)))
return regex.sub(lambda match: f'<span class="highlight">{match.group(0)}</span>'.replace('\\', r'\\'), content)
return content

View file

@ -57,6 +57,11 @@ class TestWebUtils(SearxTestCase):
]
),
),
(
'a class',
'a string with class.',
'<span class="highlight">a</span> string with <span class="highlight">class</span>.',
),
)
for query, content, expected in data:
self.assertEqual(webutils.highlight_content(content, query), expected)