Merge branch 'replay-json-pages' into dev-test

backend/btrixcloud/colls.py

@@ -351,8 +351,10 @@ async def get_collection_out(
                 coll_id, is_seed=True, page_size=25
             )
             result["pages"] = pages
+            public = "public/" if public_or_unlisted_only else ""
             result["pagesQuery"] = (
-                get_origin(headers) + f"/api/orgs/{org.id}/collections/{coll_id}/pages"
+                get_origin(headers)
+                + f"/api/orgs/{org.id}/collections/{coll_id}/{public}pages"
             )
 
         thumbnail = result.get("thumbnail")
@@ -539,9 +541,17 @@ async def get_collection_search_values(self, org: Organization):
         names = [name for name in names if name]
         return {"names": names}
 
-    async def get_collection_crawl_ids(self, coll_id: UUID) -> List[str]:
-        """Return list of crawl ids in collection"""
+    async def get_collection_crawl_ids(
+        self, coll_id: UUID, public_or_unlisted_only=False
+    ) -> List[str]:
+        """Return list of crawl ids in collection, including only public collections"""
         crawl_ids = []
+        if public_or_unlisted_only:
+            try:
+                await self.get_collection_raw(coll_id, public_or_unlisted_only)
+            except HTTPException:
+                return []
+
         async for crawl_raw in self.crawls.find(
             {"collectionIds": coll_id}, projection=["_id"]
         ):

backend/btrixcloud/pages.py

@@ -670,14 +670,17 @@ async def list_collection_pages(
         page: int = 1,
         sort_by: Optional[str] = None,
         sort_direction: Optional[int] = -1,
+        public_or_unlisted_only=False,
     ) -> Tuple[Union[List[PageOut], List[PageOutWithSingleQA]], int]:
         """List all pages in collection, with optional filtering"""
         # pylint: disable=duplicate-code, too-many-locals, too-many-branches, too-many-statements
         # Zero-index page for query
         page = page - 1
         skip = page_size * page
 
-        crawl_ids = await self.coll_ops.get_collection_crawl_ids(coll_id)
+        crawl_ids = await self.coll_ops.get_collection_crawl_ids(
+            coll_id, public_or_unlisted_only
+        )
 
         query: dict[str, object] = {
             "crawl_id": {"$in": crawl_ids},
@@ -886,6 +889,7 @@ def init_pages_api(
 
     org_viewer_dep = org_ops.org_viewer_dep
     org_crawl_dep = org_ops.org_crawl_dep
+    org_public = org_ops.org_public
 
     @app.post(
         "/orgs/{oid}/crawls/all/pages/reAdd",
@@ -1092,6 +1096,41 @@ async def get_crawl_pages_list(
         )
         return paginated_format(pages, total, page, pageSize)
 
+    @app.get(
+        "/orgs/{oid}/collections/{coll_id}/public/pages",
+        tags=["pages", "collections"],
+        response_model=PaginatedPageOutResponse,
+    )
+    async def get_public_collection_pages_list(
+        coll_id: UUID,
+        org: Organization = Depends(org_public),
+        url: Optional[str] = None,
+        urlPrefix: Optional[str] = None,
+        ts: Optional[datetime] = None,
+        isSeed: Optional[bool] = None,
+        depth: Optional[int] = None,
+        pageSize: int = DEFAULT_PAGE_SIZE,
+        page: int = 1,
+        sortBy: Optional[str] = None,
+        sortDirection: Optional[int] = -1,
+    ):
+        """Retrieve paginated list of pages in collection"""
+        pages, total = await ops.list_collection_pages(
+            coll_id=coll_id,
+            org=org,
+            url=url,
+            url_prefix=urlPrefix,
+            ts=ts,
+            is_seed=isSeed,
+            depth=depth,
+            page_size=pageSize,
+            page=page,
+            sort_by=sortBy,
+            sort_direction=sortDirection,
+            public_or_unlisted_only=True,
+        )
+        return paginated_format(pages, total, page, pageSize)
+
     @app.get(
         "/orgs/{oid}/collections/{coll_id}/pages",
         tags=["pages", "collections"],

backend/test/test_collections.py

@@ -84,6 +84,10 @@ def test_create_collection(
     assert data["pageCount"] > 0
     assert data["uniquePageCount"] > 0
     assert data["totalSize"] > 0
+    assert (
+        data["pagesQuery"]
+        == f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/pages"
+    )
     modified = data["modified"]
     assert modified
     assert modified.endswith("Z")
@@ -413,6 +417,10 @@ def test_collection_public(crawler_auth_headers, default_org_id):
         f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/public/replay.json",
         headers=crawler_auth_headers,
     )
+    assert (
+        r.json()["pagesQuery"]
+        == f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/public/pages"
+    )
     assert r.status_code == 200
     assert r.headers["Access-Control-Allow-Origin"] == "*"
     assert r.headers["Access-Control-Allow-Headers"] == "*"