Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix : Belga-Archive API : Search highlighted text is not showing properly with boolean operators [SDBELGA-736] #434

Merged
merged 4 commits into from
Aug 2, 2023
Merged

Fix : Belga-Archive API : Search highlighted text is not showing properly with boolean operators [SDBELGA-736] #434

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ecee090
update regex for boolean operators
devketanpro Aug 2, 2023
b777cc6
add unit testcases
devketanpro Aug 2, 2023
8c0e561
fix black
devketanpro Aug 2, 2023
e0255cd
fix testcases
devketanpro Aug 2, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion server/belga/search_providers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,7 +336,7 @@ def get_search_text(self, query):
return searchText

def set_highlight(self, search_text, docs):
search_text = "|".join(search_text.split())
search_text = "|".join(re.escape(term.strip()) for term in search_text.split())
fields = ("body_html", "headline", "slugline")
for doc in docs:
for field in fields:
Expand Down
2 changes: 1 addition & 1 deletion server/tests/fixtures/belga-360archive-search.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
"name": "",
"credit": "BELGA",
"topic": "Belga 360 slugline",
"headLine": "Lorem ipsum dolor sit amet, consectetur adipiscing elit.",
"headLine": "(Lorem ipsum) dolor sit amet, consectetur adipiscing elit.",
"keywords": ["BRIEF", "#CORONAVIRUS", "SPORTS", "INTERNET"],
"authors": [
{
Expand Down
25 changes: 22 additions & 3 deletions server/tests/search_providers/belga_360_archive_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,7 +173,8 @@ def test_format_list_item(self):
self.assertEqual(item["guid"], guid)
self.assertEqual(item["extra"]["city"], "Bruxelles")
self.assertEqual(
item["headline"], "Lorem ipsum dolor sit amet, consectetur adipiscing elit."
item["headline"],
"(Lorem ipsum) dolor sit amet, consectetur adipiscing elit.",
)
self.assertEqual(item["name"], "")
self.assertEqual(item["slugline"], "Belga 360 slugline")
Expand Down Expand Up @@ -400,7 +401,7 @@ def test_get_highlighted_text(self):
{
"headline": [
(
'<span class="es-highlight">Lorem</span> <span class="es-highlight">ipsum</span> dolor '
'(<span class="es-highlight">Lorem</span> <span class="es-highlight">ipsum</span>) dolor '
"sit amet, consectetur adipiscing elit."
)
]
Expand All @@ -415,7 +416,25 @@ def test_get_highlighted_text(self):
{
"headline": [
(
'<span class="es-highlight">Lorem</span> <span class="es-highlight">ipsum</span> dolor '
'(<span class="es-highlight">Lorem</span> <span class="es-highlight">ipsum</span>) dolor '
"sit amet, consectetur adipiscing elit."
)
]
},
)

query["query"]["filtered"]["query"]["query_string"][
"query"
] = "(Lorem ipsum)"
items = self.provider.find(query)
highlighted_item = items[0]

self.assertEqual(
highlighted_item["es_highlight"],
{
"headline": [
(
'<span class="es-highlight">(Lorem</span> <span class="es-highlight">ipsum)</span> dolor '
"sit amet, consectetur adipiscing elit."
)
]
Expand Down