Use canned query title, produce valid Atom

Closes #12, closes #6
simonw · May 28, 2020 · 64de6b0 · 64de6b0
1 parent df98a6c
commit 64de6b0
Show file tree

Hide file tree

Showing 3 changed files with 83 additions and 13 deletions.
diff --git a/README.md b/README.md
@@ -53,3 +53,33 @@ limit
 ```
 
 You can try this query by [pasting it in here](https://www.niche-museums.com/browse) - then click the `.atom` link to see it as an Atom feed.
+
+## Using a canned query
+
+Datasette's [canned query mechanism](https://datasette.readthedocs.io/en/stable/sql_queries.html#canned-queries) is a useful way to configure feeds. If a canned query definition has a `title` that will be used as the title of the Atom feed.
+
+Here's an example, defined using a `metadata.yaml` file:
+
+```yaml
+databases:
+  browse:
+    queries:
+      feed:
+        title: Niche Museums
+        sql: |-
+          select
+            'tag:niche-museums.com,' || substr(created, 0, 11) || ':' || id as atom_id,
+            name as atom_title,
+            created as atom_updated,
+            'https://www.niche-museums.com/browse/museums/' || id as atom_link,
+            coalesce(
+              '<img src="' || photo_url || '?w=800&amp;h=400&amp;fit=crop&amp;auto=compress">',
+              ''
+            ) || '<p>' || description || '</p>' as atom_content_html
+          from
+            museums
+          order by
+            created desc
+          limit
+            15
+```
diff --git a/datasette_atom/__init__.py b/datasette_atom/__init__.py
@@ -12,10 +12,11 @@ def register_output_renderer():
     return {"extension": "atom", "render": render_atom, "can_render": can_render_atom}
 
 
-def render_atom(args, data, view_name):
+def render_atom(
+    datasette, request, sql, columns, rows, database, table, query_name, view_name, data
+):
     from datasette.views.base import DatasetteError
 
-    columns = set(data["columns"])
     if not REQUIRED_COLUMNS.issubset(columns):
         raise DatasetteError(
             "SQL query must return columns {}".format(", ".join(REQUIRED_COLUMNS)),
@@ -27,17 +28,25 @@ def render_atom(args, data, view_name):
         version=__version__,
         uri="https://github.com/simonw/datasette",
     )
-    sql = data["query"]["sql"]
-    fg.id(data["database"] + "/" + hashlib.sha256(sql.encode("utf8")).hexdigest())
-    fg.updated(max(row["atom_updated"] for row in data["rows"]))
-    title = args.get("_feed_title", sql)
-    if data.get("table"):
-        title += "/" + data["table"]
+    fg.id(request.url)
+    fg.link(href=request.url, rel="self")
+    fg.updated(max(row["atom_updated"] for row in rows))
+    title = request.args.get("_feed_title", sql)
+    if table:
+        title += "/" + table
     if data.get("human_description_en"):
         title += ": " + data["human_description_en"]
+    # If this is a canned query the configured title for that over-rides all others
+    if query_name:
+        try:
+            title = datasette.metadata(database=database)["queries"][query_name][
+                "title"
+            ]
+        except (KeyError, TypeError):
+            pass
     fg.title(title)
     # And the rows
-    for row in reversed(data["rows"]):
+    for row in reversed(rows):
         entry = fg.add_entry()
         entry.id(str(row["atom_id"]))
         if "atom_content_html" in columns:
@@ -67,7 +76,7 @@ def render_atom(args, data, view_name):
 
 
 def can_render_atom(columns):
-    return {"atom_id", "atom_title", "atom_updated"}.issubset(columns)
+    return REQUIRED_COLUMNS.issubset(columns)
 
 
 def clean(html):

diff --git a/tests/test_atom.py b/tests/test_atom.py
@@ -7,7 +7,7 @@
 EXPECTED_ATOM = """
 <?xml version='1.0' encoding='UTF-8'?>
 <feed xmlns="http://www.w3.org/2005/Atom">
-  <id>:memory:/d765251b024da6156f346354d5ca573b2c8717bc71d82d2e1a2fdd55b9a44215</id>
+  <id>http://localhost/:memory:.atom?sql=%0A++++select%0A++++++++1+as+atom_id%2C%0A++++++++123+as+atom_title%2C%0A++++++++%272019-10-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27blah+%3Cb%3EBold%3C%2Fb%3E%27+as+atom_content%2C%0A++++++++%27Author%27+as+atom_author_name%2C%0A++++++++%27https%3A%2F%2Fwww.example.com%2F%27+as+atom_author_uri%0A++++union+select%0A++++++++%27atom-id-2%27+as+atom_id%2C%0A++++++++%27title+2%27+as+atom_title%2C%0A++++++++%272019-09-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27blah%27+as+atom_content%2C%0A++++++++null+as+atom_author_name%2C%0A++++++++null+as+atom_author_uri%3B%0A++++</id>
   <title>
     select
         1 as atom_id,
@@ -25,6 +25,7 @@
         null as atom_author_uri;
     </title>
   <updated>2019-10-23T21:32:12-07:00</updated>
+  <link href="http://localhost/:memory:.atom?sql=%0A++++select%0A++++++++1+as+atom_id%2C%0A++++++++123+as+atom_title%2C%0A++++++++%272019-10-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27blah+%3Cb%3EBold%3C%2Fb%3E%27+as+atom_content%2C%0A++++++++%27Author%27+as+atom_author_name%2C%0A++++++++%27https%3A%2F%2Fwww.example.com%2F%27+as+atom_author_uri%0A++++union+select%0A++++++++%27atom-id-2%27+as+atom_id%2C%0A++++++++%27title+2%27+as+atom_title%2C%0A++++++++%272019-09-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27blah%27+as+atom_content%2C%0A++++++++null+as+atom_author_name%2C%0A++++++++null+as+atom_author_uri%3B%0A++++" rel="self"/>
   <generator uri="https://github.com/simonw/datasette" version="{version}">Datasette</generator>
   <entry>
     <id>1</id>
@@ -48,7 +49,7 @@
 EXPECTED_ATOM_WITH_LINK = """
 <?xml version='1.0' encoding='UTF-8'?>
 <feed xmlns="http://www.w3.org/2005/Atom">
-  <id>:memory:/652f6714d6b9efa3657b50fe0ae8cbac13ccefb2ecbdbafe527c6f6fe97556da</id>
+  <id>http://localhost/:memory:.atom?sql=%0A++++select%0A++++++++%27atom-id%27+as+atom_id%2C%0A++++++++%27title%27+as+atom_title%2C%0A++++++++%272019-10-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27https%3A%2F%2Fwww.niche-museums.com%2F%27+as+atom_link%2C%0A++++++++%27blah%27+as+atom_content%3B%0A++++</id>
   <title>
     select
         'atom-id' as atom_id,
@@ -58,6 +59,7 @@
         'blah' as atom_content;
     </title>
   <updated>2019-10-23T21:32:12-07:00</updated>
+  <link href="http://localhost/:memory:.atom?sql=%0A++++select%0A++++++++%27atom-id%27+as+atom_id%2C%0A++++++++%27title%27+as+atom_title%2C%0A++++++++%272019-10-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27https%3A%2F%2Fwww.niche-museums.com%2F%27+as+atom_link%2C%0A++++++++%27blah%27+as+atom_content%3B%0A++++" rel="self"/>
   <generator uri="https://github.com/simonw/datasette" version="{version}">Datasette</generator>
   <entry>
     <id>atom-id</id>
@@ -72,7 +74,7 @@
 EXPECTED_ATOM_WITH_HTML = """
 <?xml version='1.0' encoding='UTF-8'?>
 <feed xmlns="http://www.w3.org/2005/Atom">
-  <id>:memory:/beb5a312c0daa591d04d7dfb5a79eb8bbbcd6f84ebe90cf0345ed8c24bb2ff22</id>
+  <id>http://localhost/:memory:.atom?sql=%0A++++select%0A++++++++%27atom-id%27+as+atom_id%2C%0A++++++++%27title%27+as+atom_title%2C%0A++++++++%272019-10-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27https%3A%2F%2Fwww.niche-museums.com%2F%27+as+atom_link%2C%0A++++++++%27%3Ch2%3Eblah%3C%2Fh2%3E%3Cscript%3Ealert%28%22bad%22%29%3C%2Fscript%3E%27+as+atom_content_html%3B%0A++++</id>
   <title>
     select
         'atom-id' as atom_id,
@@ -82,6 +84,7 @@
         '&lt;h2&gt;blah&lt;/h2&gt;&lt;script&gt;alert("bad")&lt;/script&gt;' as atom_content_html;
     </title>
   <updated>2019-10-23T21:32:12-07:00</updated>
+  <link href="http://localhost/:memory:.atom?sql=%0A++++select%0A++++++++%27atom-id%27+as+atom_id%2C%0A++++++++%27title%27+as+atom_title%2C%0A++++++++%272019-10-23T21%3A32%3A12-07%3A00%27+as+atom_updated%2C%0A++++++++%27https%3A%2F%2Fwww.niche-museums.com%2F%27+as+atom_link%2C%0A++++++++%27%3Ch2%3Eblah%3C%2Fh2%3E%3Cscript%3Ealert%28%22bad%22%29%3C%2Fscript%3E%27+as+atom_content_html%3B%0A++++" rel="self"/>
   <generator uri="https://github.com/simonw/datasette" version="{version}">Datasette</generator>
   <entry>
     <id>atom-id</id>
@@ -208,3 +211,31 @@ async def test_atom_link_only_shown_for_correct_queries():
         )
     assert b'<a href="/:memory:.json' in response.content
     assert b'<a href="/:memory:.atom' not in response.content
+
+
+@pytest.mark.asyncio
+async def test_atom_from_titled_canned_query():
+    sql = """
+    select
+        'atom-id' as atom_id,
+        'title' as atom_title,
+        '2019-10-23T21:32:12-07:00' as atom_updated,
+        'https://www.niche-museums.com/' as atom_link,
+        'blah' as atom_content;
+    """
+    app = Datasette(
+        [],
+        immutables=[],
+        memory=True,
+        metadata={
+            "databases": {
+                ":memory:": {"queries": {"feed": {"sql": sql, "title": "My atom feed"}}}
+            }
+        },
+    ).app()
+    async with httpx.AsyncClient(app=app) as client:
+        response = await client.get("http://localhost/:memory:/feed.atom")
+    assert 200 == response.status_code
+    assert "application/xml; charset=utf-8" == response.headers["content-type"]
+    xml = response.content.decode("utf-8")
+    assert "<title>My atom feed</title>" in xml