diff --git a/core/elasticsearch/__init__.py b/core/elasticsearch/__init__.py index efdc28c6..f12e30bb 100644 --- a/core/elasticsearch/__init__.py +++ b/core/elasticsearch/__init__.py @@ -30,125 +30,113 @@ SMART_FIELDS = [ "title.ngram^3", "title.phonetic", "title.auto^4", - "name.sat^6", - "title.sat^4", ] def process_query(query: str = "", request: Request | None = None): - if not (query := query.strip()): + """ + Perform a lenient, typo‑tolerant, multi‑index search. + + * Full‑text with fuzziness for spelling mistakes + * `bool_prefix` for edge‑ngram autocomplete / “icontains” + """ + if not query: raise ValueError(_("no search term provided.")) - sat_match = Q( - "multi_match", - query=query, - type="phrase_prefix", - fields=[f for f in SMART_FIELDS if ".sat" in f], - ) - - fuzzy_match = Q( - "multi_match", - query=query, - fields=SMART_FIELDS, - fuzziness="AUTO", - operator="and", - ) - - prefix_match = Q( - "multi_match", - query=query, - fields=[f for f in SMART_FIELDS if f.endswith(".auto")], - type="bool_prefix", - ) - - combined = Q( - "bool", - should=[sat_match, fuzzy_match, prefix_match], - minimum_should_match=1, - ) - - functions = [ - { - "filter": Q("prefix", **{"name.raw": query.lower()}), - "weight": 5, - }, - { - "gauss": { - "sales_rank": { - "origin": 100, - "scale": 500, - "offset": 0, - "decay": 0.3, - } - }, - "weight": 3, - }, - ] - - boosted = Q( - "function_score", - query=combined, - boost_mode="sum", - score_mode="sum", - functions=functions, - ) - - search = ( - Search(index=["products", "categories", "brands", "posts"]) - .query(boosted) - .extra(size=100) - ) - + query = query.strip() try: - response = search.execute() - except NotFoundError: - raise Http404 - - results = {"products": [], "categories": [], "brands": [], "posts": []} - for hit in response.hits: - obj_uuid = getattr(hit, "uuid", None) or hit.meta.id - obj_name = getattr(hit, "name", None) or getattr(hit, "title", None) or "N/A" - raw_slug = getattr(hit, "slug", None) or "" - obj_slug = ( - raw_slug or slugify(obj_name) - if hit.meta.index in {"brands", "categories"} - else raw_slug + q = Q( + "bool", + should=[ + Q( + "multi_match", + query=query, + fields=SMART_FIELDS, + fuzziness="AUTO", + operator="and", + ), + Q( + "multi_match", + query=query, + fields=[f for f in SMART_FIELDS if f.endswith(".auto")], + type="bool_prefix", + ), + ], + minimum_should_match=1, ) - image_url = None - idx = hit.meta.index - if request: - if idx == "products": + functions = [ + { + "gauss": { + "sales_rank": { + "origin": 100, + "scale": 500, + "offset": 0, + "decay": 0.3, + } + }, + "weight": 3, + }, + ] + + boosted = Q( + "function_score", + query=q, + boost_mode="sum", + score_mode="sum", + functions=functions, + ) + + search = ( + Search(index=["products", "categories", "brands", "posts"]) + .query(boosted) + .extra(size=100) + ) + response = search.execute() + + results: dict = {"products": [], "categories": [], "brands": [], "posts": []} + for hit in response.hits: + obj_uuid = getattr(hit, "uuid", None) or hit.meta.id + obj_name = ( + getattr(hit, "name", None) or getattr(hit, "title", None) or "N/A" + ) + obj_slug = "" + raw_slug = getattr(hit, "slug", None) + if raw_slug: + obj_slug = raw_slug + elif hit.meta.index == "brands": + obj_slug = slugify(obj_name) + elif hit.meta.index == "categories": + obj_slug = slugify(f"{obj_name}") + + image_url = None + idx = hit.meta.index + if idx == "products" and request: prod = get_object_or_404(Product, uuid=obj_uuid) first = prod.images.order_by("priority").first() - image_url = ( - request.build_absolute_uri(first.image.url) - if first and first.image - else None - ) - if idx == "brands": + if first and first.image: + image_url = request.build_absolute_uri(first.image.url) + elif idx == "brands" and request: brand = get_object_or_404(Brand, uuid=obj_uuid) - image_url = ( - request.build_absolute_uri(brand.small_logo.url) - if brand.small_logo - else None - ) - if idx == "categories": + if brand.small_logo: + image_url = request.build_absolute_uri(brand.small_logo.url) + elif idx == "categories" and request: cat = get_object_or_404(Category, uuid=obj_uuid) - image_url = ( - request.build_absolute_uri(cat.image.url) if cat.image else None - ) + if cat.image: + image_url = request.build_absolute_uri(cat.image.url) - results[idx].append( - { - "uuid": str(obj_uuid), - "name": obj_name, - "slug": obj_slug, - "image": image_url, - } - ) + results[idx].append( + { + "uuid": str(obj_uuid), + "name": obj_name, + "slug": obj_slug, + "image": image_url, + } + ) - return results + return results + except NotFoundError: + raise Http404 LANGUAGE_ANALYZER_MAP = {