feat(ingest): country-focused seeding (collect domestic CN products)

Add a market-focused seeding path so the catalogue can be built from
domestic products rather than the English-heavy global default:

- adapter.fetch_by_country(country): OFF search filtered by
  countries_tags_en, sorted by unique_scans_n (most-scanned first),
  de-duplicated across pages since OFF popularity ordering is unstable.
- is_cn_gs1(code): True for GS1-China company prefixes (690-699),
  i.e. genuinely domestic items vs. imports merely sold in China.
- seed_off --country <slug> [--domestic-only] [--page-size/--max-pages]:
  e.g. 'seed_off --country china --domestic-only' loads only 69x
  barcodes.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

ingestion/opengoods/adapters/openfoodfacts.py

@@ -157,6 +157,60 @@ class OpenFoodFactsAdapter:
             if reached_old or len(products) < page_size:
                 return
 
+    def fetch_by_country(
+        self,
+        country: str,
+        *,
+        page_size: int = 100,
+        max_pages: int = 10,
+        sort_by: str = "unique_scans_n",
+    ) -> Iterator[dict]:
+        """Yield products sold in ``country`` (an OFF ``countries_tags_en`` slug).
+
+        Used to seed a market-specific catalogue (e.g. ``china``). Results are
+        sorted by ``sort_by`` (default ``unique_scans_n`` so the most-scanned,
+        best-known products come first) and de-duplicated across pages, since
+        OFF's popularity ordering is not stable between page requests.
+        """
+        seen: set[str] = set()
+        for page in range(1, max_pages + 1):
+            resp = self._get(
+                _SEARCH_URL,
+                params={
+                    "fields": _SEARCH_FIELDS,
+                    "countries_tags_en": country,
+                    "sort_by": sort_by,
+                    "page": page,
+                    "page_size": page_size,
+                },
+            )
+            products = resp.json().get("products") or []
+            if not products:
+                return
+            new_on_page = 0
+            for prod in products:
+                code = str(prod.get("code") or "")
+                if code and code in seen:
+                    continue
+                if code:
+                    seen.add(code)
+                new_on_page += 1
+                yield prod
+            if len(products) < page_size or new_on_page == 0:
+                return
+
+
+def is_cn_gs1(code: str | None) -> bool:
+    """Return True for a GS1 China company prefix (barcodes starting 690-699).
+
+    These identify products registered with GS1 China, i.e. genuinely domestic
+    items, as opposed to imported goods merely tagged as sold in China.
+    """
+    if not code:
+        return False
+    code = code.strip()
+    return len(code) >= 3 and code[:2] == "69" and code[2].isdigit()
+
 
 def read_dump(path: str | Path) -> Iterator[dict]:
     """Yield raw product records from an OFF JSONL dump file.