?_facet_size=100 parameter, closes #1332

datasette/facets.py

@@ -101,6 +101,14 @@ class Facet:
         # [('_foo', 'bar'), ('_foo', '2'), ('empty', '')]
         return urllib.parse.parse_qsl(self.request.query_string, keep_blank_values=True)
 
+    def get_facet_size(self):
+        facet_size = self.ds.setting("default_facet_size")
+        max_returned_rows = self.ds.setting("max_returned_rows")
+        custom_facet_size = self.request.args.get("_facet_size")
+        if custom_facet_size and custom_facet_size.isdigit():
+            facet_size = int(custom_facet_size)
+        return min(facet_size, max_returned_rows)
+
     async def suggest(self):
         return []
 
@@ -136,7 +144,7 @@ class ColumnFacet(Facet):
     async def suggest(self):
         row_count = await self.get_row_count()
         columns = await self.get_columns(self.sql, self.params)
-        facet_size = self.ds.setting("default_facet_size")
+        facet_size = self.get_facet_size()
         suggested_facets = []
         already_enabled = [c["config"]["simple"] for c in self.get_configs()]
         for column in columns:
@@ -186,7 +194,7 @@ class ColumnFacet(Facet):
 
         qs_pairs = self.get_querystring_pairs()
 
-        facet_size = self.ds.setting("default_facet_size")
+        facet_size = self.get_facet_size()
         for source_and_config in self.get_configs():
             config = source_and_config["config"]
             source = source_and_config["source"]
@@ -338,7 +346,7 @@ class ArrayFacet(Facet):
         facet_results = {}
         facets_timed_out = []
 
-        facet_size = self.ds.setting("default_facet_size")
+        facet_size = self.get_facet_size()
         for source_and_config in self.get_configs():
             config = source_and_config["config"]
             source = source_and_config["source"]
@@ -449,7 +457,7 @@ class DateFacet(Facet):
         facet_results = {}
         facets_timed_out = []
         args = dict(self.get_querystring_pairs())
-        facet_size = self.ds.setting("default_facet_size")
+        facet_size = self.get_facet_size()
         for source_and_config in self.get_configs():
             config = source_and_config["config"]
             source = source_and_config["source"]

docs/facets.rst

@@ -84,6 +84,8 @@ This works for both the HTML interface and the ``.json`` view. When enabled, fac
 
 If Datasette detects that a column is a foreign key, the ``"label"`` property will be automatically derived from the detected label column on the referenced table.
 
+The default number of facet results returned is 30, controlled by the :ref:`setting_default_facet_size` setting. You can increase this on an individual page by adding ``?_facet_size=100`` to the query string, up to a maximum of :ref:`setting_max_returned_rows` (which defaults to 1000).
+
 Facets in metadata.json
 -----------------------
 

docs/json_api.rst

@@ -371,6 +371,12 @@ Special table arguments
     Pagination by continuation token - pass the token that was returned in the
     ``"next"`` property by the previous page.
 
+``?_facet=column``
+    Facet by column. Can be applied multiple times, see :ref:`facets`. Only works on the default JSON output, not on any of the custom shapes.
+
+``?_facet_size=100``
+    Increase the number of facet results returned for each facet.
+
 ``?_trace=1``
     Turns on tracing for this page: SQL queries executed during the request will
     be gathered and included in the response, either in a new ``"_traces"`` key

docs/plugin_hooks.rst

@@ -619,6 +619,7 @@ Each Facet subclass implements a new type of facet operation. The class should l
             # using self.sql and self.params as the starting point
             facet_results = {}
             facets_timed_out = []
+            facet_size = self.get_facet_size()
             # Do some calculations here...
             for column in columns_selected_for_facet:
                 try:

tests/test_facets.py

@@ -347,3 +347,55 @@ async def test_json_array_with_blanks_and_nulls():
             "toggle_url": "http://localhost/test_json_array/foo.json?_facet_array=json_column",
         }
     ]
+
+
+@pytest.mark.asyncio
+async def test_facet_size():
+    ds = Datasette([], memory=True, config={"max_returned_rows": 50})
+    db = ds.add_database(Database(ds, memory_name="test_facet_size"))
+    await db.execute_write(
+        "create table neighbourhoods(city text, neighbourhood text)", block=True
+    )
+    for i in range(1, 51):
+        for j in range(1, 4):
+            await db.execute_write(
+                "insert into neighbourhoods (city, neighbourhood) values (?, ?)",
+                ["City {}".format(i), "Neighbourhood {}".format(j)],
+                block=True,
+            )
+    response = await ds.client.get("/test_facet_size/neighbourhoods.json")
+    data = response.json()
+    assert data["suggested_facets"] == [
+        {
+            "name": "neighbourhood",
+            "toggle_url": "http://localhost/test_facet_size/neighbourhoods.json?_facet=neighbourhood",
+        }
+    ]
+    # Bump up _facet_size= to suggest city too
+    response2 = await ds.client.get(
+        "/test_facet_size/neighbourhoods.json?_facet_size=50"
+    )
+    data2 = response2.json()
+    assert sorted(data2["suggested_facets"], key=lambda f: f["name"]) == [
+        {
+            "name": "city",
+            "toggle_url": "http://localhost/test_facet_size/neighbourhoods.json?_facet_size=50&_facet=city",
+        },
+        {
+            "name": "neighbourhood",
+            "toggle_url": "http://localhost/test_facet_size/neighbourhoods.json?_facet_size=50&_facet=neighbourhood",
+        },
+    ]
+    # Facet by city should return expected number of results
+    response3 = await ds.client.get(
+        "/test_facet_size/neighbourhoods.json?_facet_size=50&_facet=city"
+    )
+    data3 = response3.json()
+    assert len(data3["facet_results"]["city"]["results"]) == 50
+    # Reduce max_returned_rows and check that it's respected
+    ds._settings["max_returned_rows"] = 20
+    response4 = await ds.client.get(
+        "/test_facet_size/neighbourhoods.json?_facet_size=50&_facet=city"
+    )
+    data4 = response4.json()
+    assert len(data4["facet_results"]["city"]["results"]) == 20