Record source-attribution provenance instead of inferring it from the name shape (Maestro 966066e3) (#202)

Co-authored-by: orchestrator-agent <20+orchestrator-agent@code.cubecraftcreations.com>

migrations/0020_site_name_from_page.sql

@@ -0,0 +1,41 @@
+-- 0020_site_name_from_page: recipes.site_name now holds only the name a
+-- recipe page gives its site (its publisher's name or og:site_name), and is
+-- null when the page names none; a client is credited with the link's host
+-- only when dinners.SourceOf finds the link safe to show. Before this, a
+-- page naming no site was stored under the host of the URL it was served
+-- from, which may carry a personal token, and nothing recorded which a
+-- stored name was. A stored name that could be a host is cleared here, so
+-- every stored name is one a page gave: one with no space (a host has
+-- none) that is dotted or holds a colon — a host name or an IP address —
+-- or that appears in the recipe's own link, as a dotless host does. This
+-- clears every name the read rule before it withheld, and more: a site
+-- that names itself as a domain, such as "Food.com", or by a word its link
+-- spells, such as "Delish" on delish.com, loses its stored name until its
+-- recipe is fetched again, and is credited by its link's host meanwhile
+-- when the link is safe.
+--
+-- Idea job results stored before sources were made safe hold the grounded
+-- recipe's site name and link as they were stored, and are cleared the
+-- same way: an idea's stored site name is shown as it stands. The ideas
+-- array is rebuilt from a plain scan of json_each, which yields its
+-- elements in array order, so the ideas keep their order (sqlc's parser
+-- refuses an ORDER BY inside json_group_array).
+
+UPDATE recipes SET site_name = NULL
+WHERE instr(site_name, ' ') = 0
+	AND (site_name GLOB '*[.:]*' OR instr(lower(source_url), lower(site_name)) > 0);
+
+UPDATE jobs SET result = json_set(result, '$.ideas', (
+	SELECT json_group_array(
+		CASE
+			WHEN instr(json_extract(idea.value, '$.site_name'), ' ') = 0
+				AND (json_extract(idea.value, '$.site_name') GLOB '*[.:]*'
+					OR instr(lower(json_extract(idea.value, '$.source_url')), lower(json_extract(idea.value, '$.site_name'))) > 0)
+			THEN json_set(idea.value, '$.site_name', json('null'))
+			ELSE json(idea.value)
+		END
+	)
+	FROM json_each(jobs.result, '$.ideas') AS idea
+))
+WHERE kind IN ('ideas_from_ingredients', 'quick_ideas')
+	AND json_type(result, '$.ideas') = 'array';