api: Remove visit_types field in origins endpoint responses

The recent addition of the visit_types field in origins endpoint responses
significantly degraded the performance of the HTTP requests as visit types
info are fetched on the backend side by sending requests to elasticsearch
for each origin in a page.

It has been observed by an endpoint client (OpenAIRE) that requests could
fail by returning read timeout errors related to elasticsearch not responding
in time when fetching visit types info.

So revert the addition of that field in order to significantly speedup response
time as requests to elasticsearch will no longer be made by the backend.

swh/web/api/views/origin.py

@@ -30,13 +30,17 @@ DOC_RETURN_ORIGIN = """
             :http:get:`/api/1/raw-extrinsic-metadata/swhid/(target)/authorities/`
             to get the list of metadata authorities providing extrinsic metadata
             on this origin (and, indirectly, to the origin's extrinsic metadata itself)
-        :>json array visit_types: set of visit types for that origin
         :>json boolean has_visits: indicates if Software Heritage made at least one full
             visit of the origin
 """
 
+
 DOC_RETURN_ORIGIN_ARRAY = DOC_RETURN_ORIGIN.replace(":>json", ":>jsonarr")
 
+DOC_RETURN_ORIGIN += (
+    "        :>json array visit_types: set of visit types for that origin"
+)
+
 DOC_RETURN_ORIGIN_VISIT = """
         :>json string date: ISO8601/RFC3339 representation of the visit date (in UTC)
         :>json str origin: the origin canonical url
@@ -82,6 +86,7 @@ def api_origins(request: Request):
         :query int origin_count: The maximum number of origins to return
             (default to 100, cannot exceed 10000)
 
+
         {return_origin_array}
 
         {common_headers}
@@ -105,6 +110,7 @@ def api_origins(request: Request):
     limit = min(int(request.query_params.get("origin_count", "100")), 10000)
 
     page_result = archive.lookup_origins(page_token, limit)
+
     origins = [enrich_origin(o, request=request) for o in page_result.results]
     next_page_token = page_result.next_page_token
 

swh/web/utils/archive.py

@@ -192,10 +192,11 @@ def lookup_content_license(q):
     return converters.from_swh(lic, hashess={"id"})
 
 
-def _origin_info(origin: Origin) -> OriginInfo:
+def _origin_info(origin: Origin, with_visit_types: bool = True) -> OriginInfo:
     origin_dict = origin.to_dict()
-    origin_data = search.origin_get(origin.url) or {}
-    origin_dict["visit_types"] = list(origin_data.get("visit_types", []))
+    if with_visit_types:
+        origin_data = search.origin_get(origin.url) or {}
+        origin_dict["visit_types"] = list(origin_data.get("visit_types", []))
     return converters.from_origin(origin_dict)
 
 
@@ -253,7 +254,7 @@ def lookup_origins(
     """
     page = storage.origin_list(page_token=page_token, limit=limit)
     return PagedResult(
-        [_origin_info(o) for o in page.results],
+        [_origin_info(o, with_visit_types=False) for o in page.results],
         next_page_token=page.next_page_token,
     )