(backend) handle title extension

Find returns titles with a language extension
ex:
{ title.fr: "rapport d'activité" }
instead of
{ "title": "rapport d'activité" }

Signed-off-by: charles <[email protected]>
This commit is contained in:
charles
2026-03-17 16:51:17 +01:00
parent 34a890c8d9
commit 79bff98f4b
4 changed files with 154 additions and 5 deletions
+50 -5
View File
@@ -8,7 +8,6 @@ from functools import cache
from django.conf import settings
from django.contrib.auth.models import AnonymousUser
from django.core.exceptions import ImproperlyConfigured
from django.db.models import Subquery
from django.utils.module_loading import import_string
import requests
@@ -193,7 +192,7 @@ class BaseDocumentIndexer(ABC):
Returns ids of the documents
Args:
q (str): Text search content.
q (str): user query.
token (str): OIDC Authentication token.
visited (list, optional):
List of ids of active public documents with LinkTrace
@@ -202,7 +201,7 @@ class BaseDocumentIndexer(ABC):
The number of results to return.
Defaults to 50 if not specified.
path (str, optional):
The path to filter documents.
The parent path to search descendants of.
"""
nb_results = nb_results or self.search_limit
results = self.search_query(
@@ -229,11 +228,57 @@ class BaseDocumentIndexer(ABC):
"""
class SearchIndexer(BaseDocumentIndexer):
class FindDocumentIndexer(BaseDocumentIndexer):
"""
Document indexer that pushes documents to La Suite Find app.
Document indexer that indexes and searches documents with La Suite Find app.
"""
# pylint: disable=too-many-arguments,too-many-positional-arguments
def search(self, q, token, visited=(), nb_results=None, path=None):
"""format Find search results"""
search_results = super().search(q, token, visited, nb_results, path)
return [
{
**hit["_source"],
"id": hit["_id"],
"title": self.get_title(hit["_source"]),
}
for hit in search_results
]
@staticmethod
def get_title(source):
"""
Find returns the titles with an extension depending on the language.
This function extracts the title in a generic way.
Handles multiple cases:
- Localized title fields like "title.<some_extension>"
- Fallback to plain "title" field if localized version not found
- Returns empty string if no title field exists
Args:
source (dict): The _source dictionary from a search hit
Returns:
str: The extracted title or empty string if not found
Example:
>>> get_title({"title.fr": "Bonjour", "id": 1})
"Bonjour"
>>> get_title({"title": "Hello", "id": 1})
"Hello"
>>> get_title({"id": 1})
""
"""
titles = utils.get_value_by_pattern(source, r"^title\.")
for title in titles:
if title:
return title
if "title" in source:
return source["title"]
return ""
def serialize_document(self, document, accesses):
"""
Convert a Document to the JSON format expected by La Suite Find.
@@ -633,3 +633,51 @@ def test_services_search_indexers_search_nb_results(mock_post, indexer_settings)
assert args[0] == indexer_settings.SEARCH_INDEXER_QUERY_URL
assert kwargs.get("json")["nb_results"] == 109
def test_search_indexer_get_title_with_localized_field():
"""Test extracting title from localized title field."""
source = {"title.extension": "Bonjour", "id": 1, "content": "test"}
result = SearchIndexer.get_title(source)
assert result == "Bonjour"
def test_search_indexer_get_title_with_multiple_localized_fields():
"""Test that first matching localized title is returned."""
source = {"title.extension": "Bonjour", "title.en": "Hello", "id": 1}
result = SearchIndexer.get_title(source)
assert result in ["Bonjour", "Hello"]
def test_search_indexer_get_title_fallback_to_plain_title():
"""Test fallback to plain 'title' field when no localized field exists."""
source = {"title": "Hello World", "id": 1}
result = SearchIndexer.get_title(source)
assert result == "Hello World"
def test_search_indexer_get_title_no_title_field():
"""Test that empty string is returned when no title field exists."""
source = {"id": 1, "content": "test"}
result = SearchIndexer.get_title(source)
assert result == ""
def test_search_indexer_get_title_with_empty_localized_title():
"""Test that fallback works when localized title is empty."""
source = {"title.extension": "", "title": "Fallback Title", "id": 1}
result = SearchIndexer.get_title(source)
assert result == "Fallback Title"
def test_search_indexer_get_title_with_multiple_extension():
"""Test extracting title from title field with multiple extensions."""
source = {"title.extension_1.extension_2": "Bonjour", "id": 1, "content": "test"}
result = SearchIndexer.get_title(source)
assert result == "Bonjour"
+35
View File
@@ -205,3 +205,38 @@ def test_utils_users_sharing_documents_with_empty_result():
cached_data = cache.get(cache_key)
assert cached_data == {}
def test_utils_get_value_by_pattern_matching_key():
"""Test extracting value from a dictionary with a matching key pattern."""
data = {"title.extension": "Bonjour", "id": 1, "content": "test"}
result = utils.get_value_by_pattern(data, r"^title\.")
assert set(result) == {"Bonjour"}
def test_utils_get_value_by_pattern_multiple_matches():
"""Test that all matching keys are returned."""
data = {"title.extension_1": "Bonjour", "title.extension_2": "Hello", "id": 1}
result = utils.get_value_by_pattern(data, r"^title\.")
assert set(result) == {
"Bonjour",
"Hello",
}
def test_utils_get_value_by_pattern_multiple_extensions():
"""Test that all matching keys are returned."""
data = {"title.extension_1.extension_2": "Bonjour", "id": 1}
result = utils.get_value_by_pattern(data, r"^title\.")
assert set(result) == {"Bonjour"}
def test_utils_get_value_by_pattern_no_match():
"""Test that empty list is returned when no key matches the pattern."""
data = {"name": "Test", "id": 1}
result = utils.get_value_by_pattern(data, r"^title\.")
assert result == []
+21
View File
@@ -18,6 +18,27 @@ from core import enums, models
logger = logging.getLogger(__name__)
def get_value_by_pattern(data, pattern):
"""
Get all values from keys matching a regex pattern in a dictionary.
Args:
data (dict): Source dictionary to search
pattern (str): Regex pattern to match against keys
Returns:
list: List of values for all matching keys, empty list if no matches
Example:
>>> get_value_by_pattern({"title.fr": "Bonjour", "id": 1}, r"^title\\.")
["Bonjour"]
>>> get_value_by_pattern({"title.fr": "Bonjour", "title.en": "Hello"}, r"^title\\.")
["Bonjour", "Hello"]
"""
regex = re.compile(pattern)
return [value for key, value in data.items() if regex.match(key)]
def get_ancestor_to_descendants_map(paths, steplen):
"""
Given a list of document paths, return a mapping of ancestor_path -> set of descendant_paths.