#1017

opteryx/components/binder.py

@@ -82,8 +82,12 @@
 from opteryx.exceptions import DatabaseError
 from opteryx.exceptions import FunctionNotFoundError
 from opteryx.exceptions import UnexpectedDatasetReferenceError
-from opteryx.functions.v2 import FUNCTIONS
+
+# from opteryx.functions.v2 import FUNCTIONS
+from opteryx.functions import FUNCTIONS
 from opteryx.managers.expression import NodeType
+from opteryx.operators.aggregate_node import AGGREGATORS
+from opteryx.samples import calculated
 
 CAMEL_TO_SNAKE = re.compile(r"(?<!^)(?=[A-Z])")
 logger = get_logger()
@@ -100,7 +104,7 @@ def inner_binder(node, relations):
         return node
 
     node_type = node.node_type
-    if node_type & NodeType.IDENTIFIER == NodeType.IDENTIFIER:
+    if node_type == NodeType.IDENTIFIER:
         column = None
         found_source_relation = relations.get(node.source)
 
@@ -146,15 +150,22 @@ def inner_binder(node, relations):
 
         # add values to the node to indicate the source of this data
         node.schema_column = column
-    if (node_type & NodeType.FUNCTION == NodeType.FUNCTION) or (
-        node_type & NodeType.AGGREGATOR == NodeType.AGGREGATOR
-    ):
+    if node_type == NodeType.FUNCTION:
         # we're just going to bind the function into the node
         func = FUNCTIONS.get(node.value)
         if not func:
-            suggest = FUNCTIONS.suggest(node.value)
+            # v1:
+            from opteryx.utils import fuzzy_search
+
+            suggest = fuzzy_search(node.value, FUNCTIONS.keys() + AGGREGATORS.keys())
+            # v2: suggest = FUNCTIONS.suggest(node.value)
             raise FunctionNotFoundError(function=node.value, suggestion=suggest)
         node.function = func
+    if node_type == NodeType.AGGREGATOR:
+        # We don't suggest because if it wasn't found as an aggregation, it's
+        # assumed to be a function
+        agg = AGGREGATORS.get(node.value)
+        node.function = agg
 
     # Now recurse and do this again for all the sub parts of the evaluation plan
     if node.left:
@@ -263,7 +274,7 @@ def merge_dicts(*dicts):
             return merged_dict
 
         if context is None:
-            context = {}
+            context = {"schemas": {"$calculated": calculated.schema}}
 
         # Recursively visit children
         children = graph.ingoing_edges(node)

opteryx/components/logical_planner.py

@@ -246,10 +246,7 @@ def inner_query_planner(ast_branch):
             inner_plan.add_edge(previous_step_id, step_id)
 
     # projection
-    _projection = [clause for clause in _projection if clause not in _aggregates]
-    if not _projection == [] and not (
-        len(_projection) == 1 and _projection[0].node_type == NodeType.WILDCARD
-    ):
+    if not (len(_projection) == 1 and _projection[0].node_type == NodeType.WILDCARD):
         project_step = LogicalPlanNode(node_type=LogicalPlanStepType.Project)
         project_step.columns = _projection
         previous_step_id, step_id = step_id, random_string()

opteryx/connectors/sample_data.py

@@ -27,6 +27,7 @@
 
 WELL_KNOWN_DATASETS = {
     "$astronauts": samples.astronauts,
+    "$calculated": None,
     "$no_table": samples.no_table,
     "$planets": samples.planets,
     "$satellites": samples.satellites,
@@ -39,7 +40,7 @@ def suggest(dataset):
     """
     from opteryx.utils import fuzzy_search
 
-    known_datasets = (k for k in WELL_KNOWN_DATASETS if k != "$no_table")
+    known_datasets = (k for k in WELL_KNOWN_DATASETS if k not in ("$no_table", "$calculated"))
     suggestion = fuzzy_search(dataset, known_datasets)
     if suggestion is not None:
         return (

opteryx/samples/__init__.py

@@ -10,9 +10,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import datetime
-
 import opteryx.samples.astronaut_data as astronauts
+import opteryx.samples.calculated_data as calculated
 import opteryx.samples.no_table_data as no_table
 import opteryx.samples.planet_data as planets
 import opteryx.samples.satellite_data as satellites

opteryx/samples/calculated_data.py

@@ -0,0 +1,26 @@
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+calculated
+---------
+
+This is used as the source relation for calculated values.
+"""
+from orso.schema import RelationSchema
+
+
+def read(*args):
+    return None
+
+
+schema = RelationSchema(name="$calculated", columns=[])