Skip to content

Add match phrase tests to Wikipedia track #782

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

Merged
kderusso merged 4 commits into from
Jun 6, 2025
Merged

Add match phrase tests to Wikipedia track #782

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
918e0f4
Add match phrase tests to Wikipedia track
kderusso Jun 4, 2025
4c9f6bb
Fix typo
kderusso Jun 4, 2025
0e7e428
Add match_phrase support to track.py
kderusso Jun 5, 2025
6cedd2c
PR feedback
kderusso Jun 6, 2025
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
14 changes: 14 additions & 0 deletions wikipedia/challenges/common/esql-full-text-functions.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,20 @@
"time-period": {{ standalone_search_time_period | default(300) | int }},
"warmup-time-period": {{ standalone_search_warmup_time_period | default(10) | int }}
},
{
"name": "standalone-esql-match-phrase-search",
"operation": "query-esql-match-phrase-search",
"clients": {{ standalone_search_clients | default(20) | int }},
"time-period": {{ standalone_search_time_period | default(300) | int }},
"warmup-time-period": {{ initial_indexing_bulk_warmup_time_period | default(40) | int }}
},
{
"name": "standalone-query-match-phrase-search",
"operation": "query-match-phrase-search",
"clients": {{ standalone_search_clients | default(20) | int }},
"time-period": {{ standalone_search_time_period | default(300) | int }},
"warmup-time-period": {{ standalone_search_warmup_time_period | default(10) | int }}
},
{
"name": "standalone-esql-qstr-search",
"operation": "query-esql-qstr-search",
Expand Down
16 changes: 16 additions & 0 deletions wikipedia/operations/default.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,6 +172,22 @@
"size" : {{ query_string_search_page_size | default(20) | int }},
"search-fields" : "{{ query_string_search_fields | default("*") }}"
},
{
"name": "query-match-phrase-search",
"operation-type": "search",
"param-source": "query-search",
"query-type": "match_phrase",
"size" : {{ query_string_search_page_size | default(20) | int }},
"search-fields" : "{{ query_string_search_fields | default("*") }}"
},
{
"name": "query-esql-match-phrase-search",
"operation-type": "esql",
"param-source": "esql-search",
"query-type": "match_phrase",
"size" : {{ query_string_search_page_size | default(20) | int }},
"search-fields" : "{{ query_string_search_fields | default("*") }}"
},
{
"name": "query-kql-search",
"operation-type": "search",
Expand Down
6 changes: 5 additions & 1 deletion wikipedia/track.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,6 +234,8 @@ def params(self):
query_body = f'KQL("{ self._search_fields }:{ query }")'
elif self._query_type == "term":
query_body = f'TERM(title, "{ query }") OR TERM(content, "{ query }")'
elif self._query_type == "match_phrase":
query_body = f'MATCH_PHRASE(title, "{ query }") OR MATCH_PHRASE(content, "{ query }")'
else:
raise ValueError("Unknown query type: " + self._query_type)

Expand Down Expand Up @@ -261,11 +263,13 @@ def params(self):
elif self._query_type == "kql":
query_body = {"kql": {"query": f'{ self._params["search-fields"] }:"{ query }"'}}
elif self._query_type == "match":
query_body = {"match": {"content": query}}
query_body = {"bool": {"should": [{"match": {"title": query}}, {"match": {"content": query}}]}}
elif self._query_type == "multi_match":
query_body = {"bool": {"should": [{"match": {"title": query}}, {"match": {"content": query}}]}}
elif self._query_type == "term":
query_body = {"bool": {"should": [{"term": {"title": query}}, {"term": {"content": query}}]}}
elif self._query_type == "match_phrase":
query_body = {"bool": {"should": [{"match_phrase": {"title": query}}, {"match_phrase": {"content": query}}]}}
else:
raise ValueError("Unknown query type: " + self._query_type)

Expand Down
Loading