Feature/mx 1604 wikidata extract multiple orgs (#223)

# PR Context
A total search results is required for frontend operations to show
proper pagination. This PR implements an additional function to get just
the total count. Further context in mex-backend related PR comment:
robert-koch-institut/mex-backend#91 (comment)

# Added
- get count of found wikidata organizations

CHANGELOG.md

@@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- get count of found wikidata organizations
+
 ### Changes
 
 ### Deprecated

mex/common/wikidata/extract.py

@@ -46,6 +46,42 @@ def search_organization_by_label(
     return _get_organization_details(wd_item_id)
 
 
+def get_count_of_found_organizations_by_label(
+    item_label: str,
+    lang: TextLanguage,
+) -> int:
+    """Get total count of searched organizations in wikidata.
+
+    Args:
+        item_label: Item title or label to be counted
+        lang: language of the label. Example: en, de
+
+    Returns:
+        count of found organizations
+    """
+    connector = WikidataQueryServiceConnector.get()
+    item_label = item_label.replace('"', "")
+    query_string_new = (
+        "SELECT (COUNT(distinct ?item) AS ?count) "
+        "WHERE { "
+        "SERVICE wikibase:mwapi { "
+        'bd:serviceParam wikibase:api "EntitySearch" . '
+        'bd:serviceParam wikibase:endpoint "www.wikidata.org" . '
+        f'bd:serviceParam mwapi:search "{item_label}" . '
+        f'bd:serviceParam mwapi:language "{lang}" . '
+        "?item wikibase:apiOutputItem mwapi:item . "
+        "?num wikibase:apiOrdinal true . "
+        "} "
+        "?item (wdt:P31/wdt:P8225*/wdt:P279*) wd:Q43229. "
+        'SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en,de". } '  # noqa: E501
+        "} "
+        "ORDER BY ASC(?num) "
+    )
+
+    result = connector.get_data_by_query(query_string_new)
+    return int(result[0]["count"]["value"])
+
+
 def search_organizations_by_label(
     item_label: str,
     offset: int,

tests/wikidata/test_extract.py

@@ -12,6 +12,7 @@
 )
 from mex.common.wikidata.extract import (
     _get_organization_details,
+    get_count_of_found_organizations_by_label,
     search_organization_by_label,
     search_organizations_by_label,
 )
@@ -49,6 +50,16 @@ def test_search_organizations_by_label() -> None:
     assert search_result[0].labels.model_dump() == labels
 
 
+@pytest.mark.integration
+def test_get_count_of_found_organizations_by_label() -> None:
+    total_found_orgs = get_count_of_found_organizations_by_label(
+        item_label='Robert Koch Institute"',
+        lang=TextLanguage.EN,
+    )
+
+    assert total_found_orgs == 3
+
+
 @pytest.mark.integration
 def test_search_organization_by_label_for_none() -> None:
     """Test if None is returned when multiple organizations are found."""
@@ -392,6 +403,38 @@ def mocked_item_details_response() -> Any:
     assert search_result[0].model_dump() == expected_organization
 
 
+@pytest.mark.usefixtures(
+    "mocked_session_wikidata_query_service", "mocked_session_wikidata_api"
+)
+def test_get_count_of_found_organizations_by_label_mocked(
+    monkeypatch: MonkeyPatch,
+) -> None:
+    expected_query_response = [
+        {
+            "count": {
+                "datatype": "http://www.w3.org/2001/XMLSchema#integer",
+                "type": "literal",
+                "value": "3",
+            }
+        }
+    ]
+
+    def mocked_query_response() -> list[dict[str, dict[str, str]]]:
+        return expected_query_response
+
+    monkeypatch.setattr(
+        WikidataQueryServiceConnector,
+        "get_data_by_query",
+        lambda self, _: mocked_query_response(),
+    )
+
+    search_result = get_count_of_found_organizations_by_label(
+        item_label="TEST", lang=TextLanguage.EN
+    )
+
+    assert search_result == 3
+
+
 @pytest.mark.integration
 def test_get_organization_details() -> None:
     expected = {