; lib/blogimport/source.sx
; Live source adapter — Q-M4 RESOLVED: import via the blog INTERNAL-DATA QUERY
; surface (decoupled), not direct Postgres. Reuses the existing query contracts
; (blog/queries.sx: post-by-id/post-by-slug/posts-by-ids) and keeps the importer in
; the SX/host world (plans/migration/data-migration.md §7 recommended default).
;
; TRANSPORT SEAM (hexagonal, like every other subsystem): a `fetch-fn` port is
; INJECTED. Contract:
;     (fetch-fn query-name params-dict) -> response-data
; In production `fetch-fn` is the host's HMAC-signed fetch_data wrapper
; (GET /internal/data/{query}); in tests it's a mock. The importer never knows how
; the bytes arrive.
;
; RESPONSE CONTRACT (one published-post row), the blog `get-post-by-*` data handler:
;   {:uuid|:id  :slug :title :status :visibility :tags :authors :lexical}
;   :lexical is the Ghost body as a JSON STRING (the Post.lexical DB column) — parsed
;   here with dream-json-parse into the SX dict shape blogimport/lex-blocks expects.
;   (If a handler returns :lexical already-structured, it is used as-is.)
;
; REQUIRED BLOG-SIDE ADDITION (the one gap): blog/queries.sx exposes fetch-by-id/slug
; but NO enumeration query. The corpus (Q-D2 = every published post) needs a
; `published-posts` query returning the published ids/slugs (Python: list_posts(
; status="published"), blog/bp/blog/ghost_db.py:102). Flagged for the blog app; mocked
; in tests. Until it exists, callers can pass an explicit id list to backfill-ids!.

(define blogimport/dep-json-parse dream-json-parse)

; --- lexical field -> SX dict (string from DB column, or already structured) -----
(define
  blogimport/parse-lexical
  (fn (lx)
    (cond
      ((equal? lx nil) {:root {:children (list)}})
      ((string? lx) (blogimport/dep-json-parse lx))
      (else lx))))

; --- service post-row -> importer `post` dict -----------------------------------
(define
  blogimport/parse-row
  (fn (row)
    {:id (or (get row :uuid) (get row :id))
     :slug (or (get row :slug) "")
     :title (or (get row :title) "")
     :status (or (get row :status) "")
     :visibility (or (get row :visibility) "")
     :tags (or (get row :tags) (list))
     :authors (or (get row :authors) (list))
     :lexical (blogimport/parse-lexical (get row :lexical))}))

; --- fetch one post via an internal-data query ----------------------------------
(define
  blogimport/fetch-post
  (fn (fetch-fn query params)
    (blogimport/parse-row (fetch-fn query params))))

; --- enumerate published post ids (needs the `published-posts` query) -----------
(define
  blogimport/published-ids
  (fn (fetch-fn) (fetch-fn "published-posts" {})))

; --- fetch all published posts as importer `post` dicts -------------------------
(define
  blogimport/source-posts
  (fn (fetch-fn)
    (map
      (fn (id) (blogimport/fetch-post fetch-fn "post-by-id" {:id id}))
      (blogimport/published-ids fetch-fn))))

; --- fetch an explicit id list (fallback before the enumeration query lands) ----
(define
  blogimport/source-posts-by-ids
  (fn (fetch-fn ids)
    (map (fn (id) (blogimport/fetch-post fetch-fn "post-by-id" {:id id})) ids)))

; --- end-to-end drivers ---------------------------------------------------------
; backfill = enumerate -> fetch -> genesis-import (idempotent). Re-runnable as the
; one-way DB->persist sync (data-migration.md Strategy 1).
(define
  blogimport/backfill!
  (fn (b fetch-fn at)
    (blogimport/import-all! b (blogimport/source-posts fetch-fn) at)))

(define
  blogimport/backfill-ids!
  (fn (b fetch-fn ids at)
    (blogimport/import-all! b (blogimport/source-posts-by-ids fetch-fn ids) at)))

; sync-verify = enumerate -> fetch -> shadow-diff the persisted streams at rest.
(define
  blogimport/sync-verify
  (fn (b fetch-fn)
    (blogimport/verify-all b (blogimport/source-posts fetch-fn))))