def build(cls, strengthening_constraint: Graph) -> 'Intelligence':
all_uids: Set[str] = set()
selected: Dict[str, Set[Union[Node,
str]]] = collections.defaultdict(set)
not_selected: Dict[str, Set[Union[Node,
str]]] = collections.defaultdict(set)
for tag in strengthening_constraint.iter_tags():
# Tags correspond to SelectConst invocations
# Format is (SELECTED/NOT_SELECTED)@(val)@(uid)
# Values are guaranteed to be strings in the RLang domain.
selected_bool, value, uid = tag.split('@')
selected_bool = selected_bool == "SELECTED"
all_uids.add(uid)
if selected_bool:
selected[uid].add(value)
else:
not_selected[uid].add(value)
for tagged_edge in strengthening_constraint.iter_tagged_edges():
# Tagged edges should be self edges for the RLang domain.
# Format is (SELECTED/NOT_SELECTED)@(uid)
node = tagged_edge.src
selected_bool, uid = tagged_edge.tag.split('@')
selected_bool = selected_bool == "SELECTED"
all_uids.add(uid)
if selected_bool:
selected[uid].add(node)
else:
not_selected[uid].add(node)
return Intelligence(all_uids=all_uids,
selected=selected,
not_selected=not_selected)
def extract_paths(graph: Graph, input_entities: List[Entity],
output_entity: Entity):
path_dict: Dict[Entity, List[Path]] = {ent: [] for ent in input_entities}
for node in itertools.chain(*(graph.iter_nodes(entity=ent)
for ent in input_entities)):
# Find all the paths from node to an output node, without any other input or output nodes in between.
# An entry is the set of visited nodes, the current node to explore, and the current set of edges.
entry: Tuple[Set[Node], Node, List[Edge]] = ({node}, node, [])
worklist = collections.deque([entry])
paths: List[Path] = []
while len(worklist) > 0:
visited, cur_node, edges = worklist.popleft()
for edge in graph.iter_edges(src=cur_node):
dst = edge.dst
if dst in visited or dst.entity in input_entities:
continue
if dst.entity is output_entity:
paths.append((visited | {dst}, edges + [edge]))
else:
worklist.append((visited | {dst}, dst, edges + [edge]))
path_dict[node.entity].extend(paths)
return path_dict
def equality_transitive_closure(graph: Graph,
equality_label: int,
join_nodes: Optional[Set[Node]] = None,
valid_combinations: Optional[Set[int]] = None):
worklist = collections.deque(
e for e in graph.iter_edges(label=equality_label))
seen_edges = set(worklist)
while len(worklist) > 0:
edge_item = worklist.popleft()
added = set()
if join_nodes is None or edge_item.src in join_nodes:
for e in graph.iter_edges(dst=edge_item.src):
if valid_combinations is None or e.label in valid_combinations:
added.add(Edge(e.src, edge_item.dst, e.label))
if join_nodes is None or edge_item.dst in join_nodes:
for e in graph.iter_edges(src=edge_item.dst):
if valid_combinations is None or e.label in valid_combinations:
added.add(Edge(edge_item.src, e.dst, e.label))
added -= seen_edges
if len(added) > 0:
graph.add_nodes_and_edges(edges=added)
for e in added:
if e.label == equality_label:
worklist.append(e)
seen_edges.add(e)
def get_strengthening_constraint(self, input_graph: Graph) -> Graph:
strengthened_input_graph = Graph()
for constraint in self.constraints.values():
strengthened_input_graph.merge(
constraint.get_strengthening_constraint(input_graph))
return strengthened_input_graph
def _get_canonical_query_plans(self,
sequence: List[str],
transformation: Transformation) -> Dict[Skeleton, Set[QueryPlan]]:
meta_plan = self._meta_plans[transformation]
blueprint_item_lists = self._get_blueprint_item_lists(sequence,
meta_plan,
_d=len(sequence))
canonical_transformation = meta_plan.canonical_transformations[len(sequence)]
mapping = next(canonical_transformation.get_subgraph_mappings(transformation))
skeletons_to_plans: Dict[Skeleton, Set[QueryPlan]] = collections.defaultdict(set)
for blueprint_item_list in blueprint_item_lists:
# Breakdown the overall transformation in terms of the unit plans contained in the blueprint items.
# Store the connections between them as a graph mapping.
connections = GraphMapping()
connections.update(mapping)
graph = Graph()
for item in blueprint_item_list:
graph.merge(item.unit.transformation)
connections = connections.apply_mapping(item.canonical_mapping, only_keys=True)
if item.border_mapping:
connections.update(item.border_mapping)
connections = connections.apply_mapping(connections, only_values=True)
# Assemble the query plan
query_plan = QueryPlan(transformation,
units=[item.unit.transformation for item in blueprint_item_list],
all_connections=connections,
strengthenings=[item.unit.strengthenings[component_name]
for component_name, item in zip(sequence, blueprint_item_list)])
# Obtain the skeletons for which this query plan would work.
# External inputs are negative integers. See gauss.synthesis.skeleton for details.
ent_to_idx = {ent: -idx for idx, ent in enumerate(transformation.get_input_entities(), 1)}
possible_arg_ints_lists = []
for component_name, (idx, item) in zip(sequence, enumerate(blueprint_item_list, 1)):
# Get the mapped entities to the inputs of this unit's transformation, and look up their idx values.
arg_ints = [ent_to_idx[connections.m_ent[ent]] for ent in item.unit.transformation.get_input_entities()]
# Get all the permutations as well.
arg_ints_list = [arg_num_mapping.apply_list(arg_ints)
for arg_num_mapping in item.unit.component_entries[component_name].argument_mappings]
possible_arg_ints_lists.append(arg_ints_list)
ent_to_idx[item.unit.transformation.get_output_entity()] = idx
# The skeletons are then simply the all the combinations
for arg_ints_list in itertools.product(*possible_arg_ints_lists):
skeleton = Skeleton(list(zip(sequence, arg_ints_list)))
skeletons_to_plans[skeleton].add(query_plan)
return skeletons_to_plans
def _get_explanation_expr_str(
graph: Graph, node: Node, node_label_dict: Dict[int, str],
edge_label_dict: Dict[int, str]) -> Optional[str]:
args = collections.defaultdict(list)
for edge in graph.iter_edges(dst=node):
label = edge_label_dict[edge.label]
if label.startswith("CUM") or label == "COLUMN" or label == "ROW":
continue
if node_label_dict[edge.src.label] == "INTERM":
args[label].append(
_get_explanation_expr_str(graph, edge.src, node_label_dict,
edge_label_dict))
else:
args[label].append(str(edge.src.value))
if len(args) == 0:
return None
if "EQUAL" in args:
return args["EQUAL"][0]
key = next(iter(args.keys()))
arg_str = ", ".join(args[key])
return f"({key.upper()}({arg_str}))"
def _adapt_query_plan(self, plan: QueryPlan, query: Query):
# The given plan is assumed to be a canonical query plan.
# Also, the transformation in plan should be the same as the transformation in query. This should be
# guaranteed by construction of the query plan.
# Create a fresh copy of the plan where the transformation is the actual subgraph.
adapted_plan = plan.deepcopy().adapt(new_transformation=query.subgraph,
mapping_old_to_new=query.mapping)
equality_label = self._domain.get_equality_edge_label()
if equality_label is None:
return None
# Propagate known values amongst the nodes with the equality edge
influence: Dict[Node, Set[Node]] = collections.defaultdict(set)
for k, v in adapted_plan.all_connections.m_node.items():
influence[v].add(k)
seen = set()
worklist = collections.deque(adapted_plan.transformation.iter_nodes())
while len(worklist) > 0:
node = worklist.popleft()
if node in seen:
continue
seen.add(node)
if node.value is SYMBOLIC_VALUE:
continue
# Connected nodes inherit the value
for n in influence[node]:
if n.value is SYMBOLIC_VALUE:
n.value = node.value
worklist.append(n)
# Equality edges with src and dst as node also propagate the values
for unit in adapted_plan.units:
for e in unit.iter_edges(src=node, label=equality_label):
if e.dst.value is SYMBOLIC_VALUE:
e.dst.value = node.value
worklist.append(e.dst)
for e in unit.iter_edges(dst=node, label=equality_label):
if e.src.value is SYMBOLIC_VALUE:
e.src.value = node.value
worklist.append(e.src)
# We may have wrecked the internal data-structures of the unit transformations by changing values directly.
# Create shallow copies which force a rebuild
adapted_plan.units = [Transformation.build_from_graph(Graph.from_nodes_and_edges(unit.get_all_nodes(),
unit.get_all_edges()),
unit.get_input_entities(),
unit.get_output_entity())
for unit in adapted_plan.units]
return adapted_plan
def create_symbolic_copy(graph: Graph) -> Tuple[Graph, GraphMapping]:
mapping = GraphMapping()
for entity in graph.iter_entities():
mapping.m_ent[entity] = Entity(value=SYMBOLIC_VALUE)
for node in graph.iter_nodes():
mapping.m_node[node] = Node(label=node.label,
entity=mapping.m_ent[node.entity],
value=SYMBOLIC_VALUE)
new_graph = Graph.from_nodes_and_edges(nodes=set(mapping.m_node.values()),
edges={
Edge(src=mapping.m_node[e.src],
dst=mapping.m_node[e.dst],
label=e.label)
for e in graph.iter_edges()
})
return new_graph, mapping
def get_strengthening_constraint(self, input_graph: Graph) -> Graph:
common_tags = None
common_edges = None
common_tagged_edges = None
for plan, partial_mappings in self._checks.items():
strengthening, s_mapping = plan.strengthenings[self.depth]
s_edges = strengthening.get_all_edges()
s_tagged_edges = set(strengthening.iter_tagged_edges())
plan_tags = set(strengthening.iter_tags())
plan_tagged_edges = None
plan_edges = None
for partial_mapping in partial_mappings:
mapping_wrt_inp_graph = partial_mapping.apply_mapping(
s_mapping, only_keys=True)
for m in strengthening.get_subgraph_mappings(
input_graph, partial_mapping=mapping_wrt_inp_graph):
if plan_tagged_edges is None:
plan_tagged_edges = {
TaggedEdge(m.m_node[e.src], m.m_node[e.dst], e.tag)
for e in s_tagged_edges
}
plan_edges = {
Edge(m.m_node[e.src], m.m_node[e.dst], e.label)
for e in s_edges
}
else:
plan_tagged_edges.intersection_update(
TaggedEdge(m.m_node[e.src], m.m_node[e.dst], e.tag)
for e in s_tagged_edges)
plan_edges.intersection_update(
Edge(m.m_node[e.src], m.m_node[e.dst], e.label)
for e in s_edges)
if common_tags is None:
common_tags = plan_tags or set()
common_tagged_edges = plan_tagged_edges or set()
common_edges = plan_edges or set()
else:
common_tags.intersection_update(plan_tags or set())
common_tagged_edges.intersection_update(plan_tagged_edges
or set())
common_edges.intersection_update(plan_edges or set())
nodes = {e.src for e in common_tagged_edges}
nodes.update(e.dst for e in common_tagged_edges)
nodes.update(e.src for e in common_edges)
nodes.update(e.dst for e in common_edges)
result = Graph.from_nodes_and_edges(nodes=nodes, edges=common_edges)
result.add_tagged_edges(common_tagged_edges)
result.add_tags(common_tags)
return result
def test_1(self):
from gauss.graphs.python.subgraph import _get_candidate_mappings
g1 = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n2 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g1.add_node(n1)
g1.add_node(n2)
g1.add_edge(Edge(n1, n2, 0))
g2 = Graph()
n3 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g2.add_node(n3)
m1 = _get_candidate_mappings(g2, g1)
m2 = _get_candidate_mappings(g1, g2)
self.assertIsNotNone(m1)
self.assertIsNone(m2)
self.assertIn(n3, m1.m_node)
self.assertSetEqual({n1}, m1.m_node[n3])
def _extract_unit_plans(self, component_name: str, witness_entry: WitnessEntry):
graph = witness_entry.graph
input_entities = witness_entry.get_input_entities()
output_entity = witness_entry.get_output_entity()
placeholder_dict = {}
# A placeholder node can represent any node belonging to an entity.
# This helps coalesce equivalent query plans.
for ent in itertools.chain(input_entities, [output_entity]):
placeholder_dict[ent] = PlaceholderNode(entity=ent)
path_dict: Dict[Entity, List[Path]] = extract_paths(graph, input_entities, output_entity)
# Find queries by taking exactly one path, and placeholder nodes for the
# input entities not present in the path.
for path_ent, paths in path_dict.items():
remaining_entities = [ent for ent in input_entities if ent is not path_ent]
for path in paths:
path_nodes, path_edges = path
nodes = list(path_nodes) + [placeholder_dict[ent] for ent in remaining_entities]
edges = path_edges
# Get the corresponding subgraph.
subgraph = Graph.from_nodes_and_edges(nodes=set(nodes), edges=set(edges))
self._record_unit_meta_query_plan(component_name, subgraph, input_entities, output_entity)
# Include empty transformations to help with evolution (the second stage).
# An empty transformation plays the role of a *wildcard* plan, that is, any transformation is valid.
# We add all empty transformations with input nodes spanning all distinct input node types
# (including placeholders) and the output being the placeholder node.
label_canonical_node: Dict[Entity, Dict[int, Node]] = collections.defaultdict(dict)
for ent in input_entities:
for node in graph.iter_nodes(entity=ent):
label_canonical_node[ent][node.label] = node
canonical_nodes: List[List[Node]] = [list(v.values()) for v in label_canonical_node.values()]
canonical_nodes.append([placeholder_dict[output_entity]])
for subgraph_nodes in itertools.product(*canonical_nodes):
subgraph = Graph.from_nodes_and_edges(nodes=subgraph_nodes, edges=[])
self._record_unit_meta_query_plan(component_name, subgraph, input_entities, output_entity,
empty=True)
def _get_involved_nodes(graph: Graph, node: Node, node_label_dict: Dict[int,
str],
edge_label_dict: Dict[int, str]) -> Set[Node]:
result = set()
for edge in graph.iter_edges(dst=node):
label = edge_label_dict[edge.label]
if label.startswith("CUM") or label == "COLUMN" or label == "ROW":
continue
result.add(edge.src)
result.update(
_get_involved_nodes(graph, edge.src, node_label_dict,
edge_label_dict))
return result
def prepare_solution(self, output: Any, output_graph: Graph) -> Solution:
if self.problem.input_names is not None:
int_to_names: Dict[int, str] = {
-idx: name
for idx, name in enumerate(self.problem.input_names, 1)
}
else:
int_to_names: Dict[int, str] = {
-idx: f"inp{idx}"
for idx in range(1,
len(self.problem.inputs) + 1)
}
int_to_names[self.skeleton.length] = self.problem.output_name
graph = Graph()
for g in self.graphs:
graph.merge(g)
# Perform transitive closure w.r.t the nodes corresponding to the intermediate outputs
# and take the induced subgraph containing all nodes except those
if self.skeleton.length > 1:
join_nodes = set.union(*(set(self.int_to_graph[i].iter_nodes())
for i in range(1, self.skeleton.length)))
self.domain.perform_transitive_closure(graph,
join_nodes=join_nodes)
graph = graph.induced_subgraph(keep_nodes=set(graph.iter_nodes()) -
join_nodes)
return self.domain.prepare_solution(
self.problem.inputs,
output,
graph,
self.problem.graph_inputs,
output_graph,
self.enumeration_items,
arguments=[arg_ints for (comp_name, arg_ints) in self.skeleton],
int_to_names=int_to_names,
int_to_obj=self.int_to_val)
def test_4(self):
from gauss.graphs.python.subgraph import _get_candidate_mappings
query = Graph()
n11 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n12 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n13 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
query.add_node(n11)
query.add_node(n12)
query.add_node(n13)
query.add_edge(Edge(n11, n12, 0))
query.add_edge(Edge(n11, n13, 1))
graph = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n2 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n3 = Node(label=3, entity=DEFAULT_ENTITY,
value=SYMBOLIC_VALUE) # 3, not 2
n4 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n5 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n6 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n7 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
graph.add_node(n1)
graph.add_node(n2)
graph.add_node(n3)
graph.add_node(n4)
graph.add_node(n5)
graph.add_node(n6)
graph.add_node(n7)
graph.add_edge(Edge(n1, n2, 0))
graph.add_edge(Edge(n1, n3, 1))
graph.add_edge(Edge(n4, n5, 0))
graph.add_edge(Edge(n4, n6, 1))
graph.add_edge(Edge(n4, n7, 1))
m = _get_candidate_mappings(query, graph)
self.assertIsNotNone(m)
def test_3(self):
g1 = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=10)
n2 = Node(label=0, entity=DEFAULT_ENTITY, value=20)
n3 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n4 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n5 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n6 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g1.add_node(n1)
g1.add_node(n2)
g1.add_node(n3)
g1.add_node(n4)
g1.add_node(n5)
g1.add_node(n6)
g1.add_edge(Edge(n1, n3, 0))
g1.add_edge(Edge(n3, n5, 1))
g1.add_edge(Edge(n2, n4, 0))
g1.add_edge(Edge(n4, n6, 1))
g2 = Graph()
n21 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n22 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n23 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g2.add_node(n21)
g2.add_node(n22)
g2.add_node(n23)
g2.add_edge(Edge(n21, n22, 0))
g2.add_edge(Edge(n22, n23, 1))
mappings_21 = list(g2.get_subgraph_mappings(g1))
self.assertEqual(2, len(mappings_21))
g3 = Graph()
n31 = Node(label=0, entity=DEFAULT_ENTITY, value=10)
n32 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n33 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g3.add_node(n31)
g3.add_node(n32)
g3.add_node(n33)
g3.add_edge(Edge(n31, n32, 0))
g3.add_edge(Edge(n32, n33, 1))
mappings_31 = list(g3.get_subgraph_mappings(g1))
self.assertEqual(1, len(mappings_31))
def _solve_for_skeleton_recursive(
self,
problem: SynthesisProblem,
skeleton: Skeleton,
query_plans: QueryPlans,
context: SolverContext,
_depth: int = 0) -> Iterator[Tuple[Any, Graph]]:
domain = self._domain
component_name, arg_ints = skeleton[_depth]
inputs, g_inputs = context.get_arguments(depth=_depth)
inp_entities = [
next(iter(g_inp.iter_entities())) for g_inp in g_inputs
]
inp_graph = Graph()
for g_inp in g_inputs:
inp_graph.merge(g_inp)
# Get the strengthening constraint for this depth.
# Specifically, for every query, get the intersection of the strengthenings of all the query plans for that
# query at this particular depth. Then take the union of all of these.
# In other words, this strengthening constraint is a graph containing the nodes, edges, tags and tagged edges
# that must be satisfied by the graph containing the inputs, that is `inp_graph` in this context.
# This constraint can then be used by the `enumerate` procedure to speed up the search.
strengthening_constraint: Graph = context.waypoints[
_depth].get_strengthening_constraint(inp_graph)
enumeration_item: EnumerationItem
for enumeration_item in domain.enumerate(
component_name=component_name,
inputs=inputs,
g_inputs=g_inputs,
constants=problem.constants,
strengthening_constraint=strengthening_constraint):
output = enumeration_item.output
c_graph = enumeration_item.graph
o_graph = enumeration_item.o_graph
# for g in g_inputs:
# assert set(g.iter_nodes()).issubset(set(c_graph.iter_nodes()))
if problem.timeout is not None and time.time(
) - self._time_start > problem.timeout:
raise TimeoutError("Exceeded time limit.")
out_entity = next(iter(o_graph.iter_entities()))
c_graph.add_node(PlaceholderNode(entity=out_entity))
c_graph = Transformation.build_from_graph(
c_graph, input_entities=inp_entities, output_entity=out_entity)
# Check if the returned graph is consistent with the query plans.
if not context.check_validity(c_graph, depth=_depth):
continue
# Prepare for the next round.
context.step(output=output,
graph=c_graph,
output_graph=o_graph,
enumeration_item=enumeration_item,
depth=_depth)
if _depth == skeleton.length - 1:
# This was the last component, prepare the program and return it along with the final output and graph.
yield output, o_graph
else:
# Move on to the next component.
yield from self._solve_for_skeleton_recursive(problem,
skeleton,
query_plans,
context,
_depth=_depth +
1)
def test_5(self):
# Stress-tests the intelligence of back-tracking
query = Graph()
n11 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n12 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n13 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n14 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n15 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n16 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
query.add_node(n11)
query.add_node(n12)
query.add_node(n13)
query.add_node(n14)
query.add_node(n15)
query.add_node(n16)
query.add_edge(Edge(n13, n15, 0))
query.add_edge(Edge(n13, n15, 1))
query.add_edge(Edge(n14, n16, 0))
query.add_edge(Edge(n14, n16, 1))
graph = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n2 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n3 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n4 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n5 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n6 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n7 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n8 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n9 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n10 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
graph.add_node(n1)
graph.add_node(n2)
graph.add_node(n3)
graph.add_node(n4)
graph.add_node(n5)
graph.add_node(n6)
graph.add_node(n7)
graph.add_node(n8)
graph.add_node(n9)
graph.add_node(n10)
graph.add_edge(Edge(n3, n5, 0))
graph.add_edge(Edge(n3, n6, 1))
graph.add_edge(Edge(n4, n5, 1))
graph.add_edge(Edge(n4, n6, 0))
mappings = list(
query.get_subgraph_mappings(
graph, _worklist_order=[n11, n12, n13, n14, n15, n16]))
self.assertEqual(0, len(mappings))
def test_4(self):
query = Graph()
n11 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n12 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n13 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
query.add_node(n11)
query.add_node(n12)
query.add_node(n13)
query.add_edge(Edge(n11, n12, 0))
query.add_edge(Edge(n11, n13, 1))
graph = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n2 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n3 = Node(label=3, entity=DEFAULT_ENTITY,
value=SYMBOLIC_VALUE) # 3, not 2
n4 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n5 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n6 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n7 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
graph.add_node(n1)
graph.add_node(n2)
graph.add_node(n3)
graph.add_node(n4)
graph.add_node(n5)
graph.add_node(n6)
graph.add_node(n7)
graph.add_edge(Edge(n1, n2, 0))
graph.add_edge(Edge(n1, n3, 1))
graph.add_edge(Edge(n4, n5, 0))
graph.add_edge(Edge(n4, n6, 1))
graph.add_edge(Edge(n4, n7, 1))
mappings = list(query.get_subgraph_mappings(graph))
self.assertEqual(2, len(mappings))
def _evolve_meta_plan(self,
plan: MetaQueryPlan,
depth: int,
nlabel_to_unit_plan: Dict[int, Set[UnitMetaPlan]]):
# Replace an input node of plan with the output of a unit meta-plan (contained in nlabel_to_meta_plan).
# Thus we extend an existing plan with the output of exactly one component, thus increasing the program
# depth by exactly one.
plan_transformation: Transformation = plan.canonical_transformations[depth - 1]
all_input_nodes: Set[Node] = set(plan_transformation.get_input_nodes())
for inp_node in all_input_nodes:
# Even if it is a placeholder node, it can only be extended via the empty transform. This makes sense
# as no matter what the extension is, it will never "influence" the final output, as there is no path
# between a placeholder node and the output node. This helps reduce the size of the collection of
# meta query-plans by a large margin.
remaining_inputs = all_input_nodes - {inp_node}
for extender in nlabel_to_unit_plan[int(inp_node.label)]:
# We can map the other inputs to the inputs of the extender plan. They can also be distinct
# inputs of their own. The total number of inputs should, however, be less than max_inputs.
# For the remaining inputs, if they are a placeholder node, they can be mapped to *any* of the
# input nodes of the extender plan, regardless of the label.
nlabel_to_inp_node: Dict[int, Set[Node]] = collections.defaultdict(set)
extender_inputs: Set[Node] = set(extender.transformation.get_input_nodes())
# Guaranteed to be a single output node by construction.
extender_output: Node = next(extender.transformation.get_output_nodes())
for inp in extender_inputs:
nlabel_to_inp_node[inp.label].add(inp)
nlabel_to_inp_node[extender_output.label].add(extender_output)
mapping_possibilities: Dict[Node, Set[Node]] = {inp_node: {extender_output}}
for inp in remaining_inputs:
if inp.label == PLACEHOLDER_LABEL:
mapping_possibilities[inp] = extender_inputs | {extender_output, inp}
else:
mapping_possibilities[inp] = nlabel_to_inp_node[inp.label] | {inp}
node_list = list(all_input_nodes)
for border_node_mapping in itertools.product(*[mapping_possibilities[n] for n in node_list]):
border_node_mapping: Dict[Node, Node] = dict(zip(node_list, border_node_mapping))
border_mapping = GraphMapping(m_ent={k.entity: v.entity for k, v in border_node_mapping.items()},
m_node=border_node_mapping.copy())
# Create a deepcopy of the extender for safety
copied_extender, copy_mapping = extender.deepcopy()
copied_extender_inputs: Set[Node] = set(copied_extender.transformation.get_input_nodes())
copied_extender_output: Node = next(copied_extender.transformation.get_output_nodes())
border_mapping = border_mapping.apply_mapping(copy_mapping, only_values=True)
assert border_mapping.m_node != border_node_mapping
# The new inputs are the inputs of extender, plus the nodes of the current plan
# which were not bound to any of the inputs of extender.
# We also decide the order of the nodes/entities right now.
new_input_nodes: List[Node] = []
for inp in plan_transformation.get_input_nodes():
mapped = border_mapping.m_node[inp]
if mapped is inp:
new_input_nodes.append(inp)
elif mapped is copied_extender_output:
new_input_nodes.extend(i for i in copied_extender.transformation.get_input_nodes()
if i not in new_input_nodes)
elif mapped not in new_input_nodes:
assert mapped in copied_extender_inputs
new_input_nodes.append(mapped)
new_input_entities = [n.entity for n in new_input_nodes]
# Every entity is associated with one node so the following should hold true.
assert len(new_input_entities) == len(set(new_input_entities))
if len(new_input_entities) > self._config.max_inputs:
continue
new_output_entity = plan_transformation.get_output_entity()
# Obtain the transformation by establishing common edges between the node pairs in
# border_node_mapping, taking the transitive closure w.r.t equality, and finally the
# induced subgraph by removing the input nodes of the current plan.
joint_graph = Graph.from_graph(copied_extender.transformation)
joint_graph.merge(plan_transformation)
final_border_mapping = GraphMapping()
for k, v in border_mapping.m_node.items():
if k is not v:
final_border_mapping.m_node[k] = v
final_border_mapping.m_ent[k.entity] = v.entity
for edge in plan_transformation.iter_edges(src=k):
joint_graph.add_edge(Edge(v, edge.dst, edge.label))
for edge in plan_transformation.iter_edges(dst=k):
joint_graph.add_edge(Edge(edge.src, v, edge.label))
join_nodes: Set[Node] = set(all_input_nodes)
join_nodes.difference_update(new_input_nodes)
join_nodes.add(copied_extender_output)
self._domain.perform_transitive_closure(joint_graph, join_nodes=join_nodes)
keep_nodes = set(joint_graph.iter_nodes())
keep_nodes.difference_update(join_nodes)
new_transformation_subgraph = joint_graph.induced_subgraph(keep_nodes=keep_nodes)
new_transformation = Transformation.build_from_graph(new_transformation_subgraph,
input_entities=new_input_entities,
output_entity=new_output_entity)
# Record the transformation and how it was obtained.
if new_transformation not in self._meta_plans:
# The transformation was never seen before.
blueprint = collections.defaultdict(lambda: collections.defaultdict(list))
meta_plan = MetaQueryPlan(transformation=new_transformation.deepcopy()[0],
blueprint=blueprint)
self._meta_plans[new_transformation] = meta_plan
else:
meta_plan = self._meta_plans[new_transformation]
if depth not in meta_plan.canonical_transformations:
copy, mapping = new_transformation.deepcopy()
meta_plan.canonical_transformations[depth] = copy
# mapping = mapping.slice(nodes=set(copied_extender.transformation.iter_nodes()))
mapping = mapping.reverse()
else:
canonical = meta_plan.canonical_transformations[depth]
mapping = next(new_transformation.get_subgraph_mappings(canonical))
# mapping = mapping.slice(nodes=set(copied_extender.transformation.iter_nodes()))
mapping = mapping.reverse()
bp_item = MetaQueryPlan.BlueprintItem(depth=depth,
unit=copied_extender,
canonical_mapping=mapping,
sub_plan=plan,
border_mapping=final_border_mapping)
for c in copied_extender.component_entries:
meta_plan.blueprint[depth][c].append(bp_item)
def test_3(self):
from gauss.graphs.python.subgraph import _get_candidate_mappings
g1 = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=10)
n2 = Node(label=0, entity=DEFAULT_ENTITY, value=20)
n3 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n4 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n5 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n6 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g1.add_node(n1)
g1.add_node(n2)
g1.add_node(n3)
g1.add_node(n4)
g1.add_node(n5)
g1.add_node(n6)
g1.add_edge(Edge(n1, n3, 0))
g1.add_edge(Edge(n3, n5, 1))
g1.add_edge(Edge(n2, n4, 0))
g1.add_edge(Edge(n4, n6, 1))
g2 = Graph()
n21 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n22 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n23 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g2.add_node(n21)
g2.add_node(n22)
g2.add_node(n23)
g2.add_edge(Edge(n21, n22, 0))
g2.add_edge(Edge(n22, n23, 1))
m21 = _get_candidate_mappings(g2, g1)
self.assertIsNotNone(m21)
self.assertSetEqual({n1, n2}, m21.m_node[n21])
self.assertSetEqual({n3, n4}, m21.m_node[n22])
self.assertSetEqual({n5, n6}, m21.m_node[n23])
g3 = Graph()
n31 = Node(label=0, entity=DEFAULT_ENTITY, value=10)
n32 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n33 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g3.add_node(n31)
g3.add_node(n32)
g3.add_node(n33)
g3.add_edge(Edge(n31, n32, 0))
g3.add_edge(Edge(n32, n33, 1))
m31 = _get_candidate_mappings(g3, g1)
self.assertIsNotNone(m31)
self.assertSetEqual({n1}, m31.m_node[n31])
self.assertSetEqual({n3}, m31.m_node[n32])
self.assertSetEqual({n5}, m31.m_node[n33])
g4 = Graph()
n41 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n42 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n43 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g4.add_node(n41)
g4.add_node(n42)
g4.add_node(n43)
g4.add_edge(Edge(n41, n42, 0))
g4.add_edge(Edge(n42, n43, 1))
m41 = _get_candidate_mappings(g4, g1, GraphMapping(m_node={n41: n1}))
self.assertIsNotNone(m41)
self.assertSetEqual({n1}, m41.m_node[n41])
self.assertSetEqual({n3}, m41.m_node[n42])
self.assertSetEqual({n5}, m41.m_node[n43])
def test_greatest_common_universal_subgraph_1(self):
g1 = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n2 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n3 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n4 = Node(label=3, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g1.add_nodes_and_edges(nodes=[n1, n2, n3, n4])
g1.add_tags(["TAG_1", "TAG_2"])
g1.add_tagged_edges(
[TaggedEdge(n2, n2, "TAG_L1"),
TaggedEdge(n3, n3, "TAG_L2")])
# Linear chain from n1 to n2 and n2 to n3 and n3 to n4
g1.add_edge(Edge(src=n1, dst=n2, label=10))
g1.add_edge(Edge(src=n2, dst=n3, label=11))
g1.add_edge(Edge(src=n3, dst=n4, label=12))
g2 = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n2 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n3 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n4 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n5 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n6 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n7 = Node(label=2, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n8 = Node(label=3, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g2.add_nodes_and_edges(nodes=[n1, n2, n3, n4, n5, n6, n7, n8])
g2.add_tags(["TAG_2", "TAG_3"])
g2.add_tagged_edges(
[TaggedEdge(n2, n2, "TAG_L1"),
TaggedEdge(n3, n3, "TAG_L2")])
# Only one of label=2 has an edge to a label=3
g2.add_edge(Edge(src=n1, dst=n2, label=10))
g2.add_edge(Edge(src=n2, dst=n3, label=11))
g2.add_edge(Edge(src=n2, dst=n4, label=11))
g2.add_edge(Edge(src=n2, dst=n5, label=11))
g2.add_edge(Edge(src=n2, dst=n6, label=11))
g2.add_edge(Edge(src=n2, dst=n7, label=11))
g2.add_edge(Edge(src=n7, dst=n8, label=12))
query = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
n2 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
query.add_nodes_and_edges(nodes=[n1, n2])
query.add_edge(Edge(n1, n2, 10))
supergraph, mapping = query.get_greatest_common_universal_supergraph(
[g1])
# We expect the supergraph to be equivalent to g1
self.assertEqual(3, supergraph.get_num_edges())
self.assertEqual(4, supergraph.get_num_nodes())
self.assertSetEqual({0, 1, 2, 3},
{n.label
for n in supergraph.iter_nodes()})
self.assertSetEqual({10, 11, 12},
{e.label
for e in supergraph.iter_edges()})
self.assertSetEqual({"TAG_1", "TAG_2"}, set(supergraph.iter_tags()))
self.assertEqual({"TAG_L1", "TAG_L2"},
{e.tag
for e in supergraph.iter_tagged_edges()})
for node in mapping.m_node:
self.assertIn(node, query.get_all_nodes())
supergraph, mapping = query.get_greatest_common_universal_supergraph(
[g1, g2])
# We expect the supergraph to be the linear chain 0 to 1 and 1 to 2
self.assertEqual(2, supergraph.get_num_edges())
self.assertEqual(3, supergraph.get_num_nodes())
self.assertSetEqual({0, 1, 2},
{n.label
for n in supergraph.iter_nodes()})
self.assertSetEqual({10, 11},
{e.label
for e in supergraph.iter_edges()})
self.assertSetEqual({"TAG_2"}, set(supergraph.iter_tags()))
self.assertEqual({"TAG_L1"},
{e.tag
for e in supergraph.iter_tagged_edges()})
for node in mapping.m_node:
self.assertIn(node, query.get_all_nodes())
def build(cls, domain: SynthesisDomain, config: EngineConfig, witness_set: WitnessSet) -> 'QueryPlanner':
q_planner = QueryPlanner(domain=domain, config=config)
logger_color = logger.opt(colors=True)
# ---------------------------------------------------------------------------------------------------------- #
# Stage 1 : Build unit plans
# ---------------------------------------------------------------------------------------------------------- #
logger.debug("Extracting meta query-plans of length 1 from individual components...")
for component_name in domain.get_available_components():
for witness_entry in witness_set.entries[component_name]:
q_planner._extract_unit_plans(component_name, witness_entry)
# Log some information for post-mortem analysis if necessary
# Total plans found.
logger_color.debug(f"Found <green>{len(q_planner._unit_plans)}</green> unit plans in total.")
# Plans found per component.
components_to_units: Dict[str, List[UnitMetaPlan]] = collections.defaultdict(list)
for unit in q_planner._unit_plans.values():
for c in unit.component_entries:
components_to_units[c].append(unit)
with logutils.temporary_add(f"{config.path}/logs/query_planner/unit_plans.log",
level="TRACE",
only_sink=True) as logger_:
logger_ = logger_.opt(raw=True)
for component_name, units in components_to_units.items():
logger_color.debug(f"Found <green>{len(units)}</green> unit plans from "
f"<blue>{component_name}</blue>.")
logger_.opt(colors=True).debug(f"Found <green>{len(units)}</green> unit plans from "
f"<blue>{component_name}</blue>.")
for unit in units:
logger_.trace(f"Component: {component_name}\n")
logger_.trace("-----------------\n")
logger_.trace("Transformation\n")
logger_.trace("-----------------\n")
logger_.trace(unit.transformation.to_str(domain))
logger_.trace("\n-----------------\n")
logger_.trace("Argument Mappings\n")
logger_.trace("-----------------\n")
logger_.trace(unit.component_entries[component_name].argument_mappings)
logger_.trace("\n========xxx========\n\n")
# ---------------------------------------------------------------------------------------------------------- #
# Stage 2 : Strengthen Unit Plans
# ---------------------------------------------------------------------------------------------------------- #
logger_color.debug("Strengthening Unit Plans...")
for unit_plan in debug_iter(list(q_planner._unit_plans.values()), desc='Strengthening Unit Plans'):
query: Transformation = unit_plan.transformation
for component_name in unit_plan.component_entries.keys():
# The witness set examples are guaranteed to have a placeholder node for each entity,
# so the use of placeholder nodes in transformations should not cause issues.
if unit_plan.empty:
strengthened, mapping = query.deepcopy()
strengthened = Graph.from_graph(strengthened)
else:
examples: List[Transformation] = witness_set.get_transformations(component_name)
strengthened, mapping = query.get_greatest_common_universal_supergraph(examples)
inp_entities = set(query.get_input_entities())
m_reverse = mapping.reverse()
keep_nodes = [n for n in strengthened.iter_nodes()
if m_reverse.m_ent.get(n.entity, None) in inp_entities]
strengthened = strengthened.induced_subgraph(keep_nodes=keep_nodes)
unit_plan.strengthenings[component_name] = (strengthened, mapping)
logger_color.debug(f"Strengthened <green>{len(q_planner._unit_plans)}</green> unit plans.")
# ---------------------------------------------------------------------------------------------------------- #
# Stage 3 : Combining unit plans to obtain query plans upto max-depth
# Note that these are not explicitly constructed. Rather, a recursive formulation is established
# to construct the query plans quickly during test-time.
# ---------------------------------------------------------------------------------------------------------- #
# Initialize the meta-plans from these unit plans
logger.debug("Initializing meta-plans from unit-plans...")
for transformation, unit_plan in q_planner._unit_plans.items():
q_planner._meta_plans[transformation] = MetaQueryPlan.initialize_from_unit_plan(unit_plan.deepcopy()[0])
logger_color.debug(f"Evolving meta query-plans upto a maximum length of "
f"<blue>{config.max_length}</blue>")
# Setup a mapping from the label of the output node of transformations
# to the meta plan for that transformation. This helps in quickly finding
# appropriate unit plans to extend a plan with.
nlabel_to_unit_plan: Dict[int, Set[UnitMetaPlan]] = collections.defaultdict(set)
for transformation, unit_plan in q_planner._unit_plans.items():
# Guaranteed to be a single node with that entity.
output_node = next(transformation.get_output_nodes())
nlabel_to_unit_plan[output_node.label].add(unit_plan)
# At every depth, the worklist will be the set of query plans with an entry for depth-1 in the blueprint.
worklist: Set[MetaQueryPlan] = set(q_planner._meta_plans.values())
for depth in range(2, config.max_length + 1):
for unit in worklist:
q_planner._evolve_meta_plan(unit, depth, nlabel_to_unit_plan)
worklist = {plan for plan in q_planner._meta_plans.values() if depth in plan.blueprint}
logger_color.debug(f"Found <green>{len(worklist)}</green> transformations in total "
f"at depth <blue>{depth}</blue>.")
if len(worklist) == 0:
break
logger_color.debug(f"Found <green>{len(q_planner._meta_plans)}</green> transformations and meta "
f"query plans in total with <blue>max_depth={config.max_length}</blue>.")
# TODO : Log the transformations to a file.
# ---------------------------------------------------------------------------------------------------------- #
# Stage 4 : Setup auxiliary data-structures
# ---------------------------------------------------------------------------------------------------------- #
# Flattened blue-print items enable access to all the items agnostic of the component name.
for plan in q_planner._meta_plans.values():
plan.blueprint_items = collections.defaultdict(set)
for depth, bp_dict in plan.blueprint.items():
for items_list in bp_dict.values():
plan.blueprint_items[depth].update(items_list)
# Sequence tries help in quickly computing candidate sequences given a synthesis problem.
logger_color.debug("Constructing Sequence Tries...")
q_planner._compute_sequence_tries()
logger_color.debug(f"Sequence Tries constructed for every depth.")
return q_planner
def init(self):
domain = PandasLiteSynthesisDomain()
replay = {k: iter(v) for k, v in self.replay_map.items()}
graph = Graph()
g_inputs = self._g_inputs = [
self._convert_inp_to_graph(inp) for inp in self.inputs
]
int_to_val = {-idx: inp for idx, inp in enumerate(self.inputs, 1)}
int_to_graph = {-idx: g_inp for idx, g_inp in enumerate(g_inputs, 1)}
# Run the generators to extract the programs and graphs for each component call.
# Merge the individual graphs into the master graph.
call_strs: List[str] = []
for idx, (component_name, arg_ints) in enumerate(self.skeleton, 1):
c_inputs = [int_to_val[i] for i in arg_ints]
g_c_inputs = [int_to_graph[i] for i in arg_ints]
output, program, c_graph, output_graph = next(
domain.enumerate(component_name,
c_inputs,
g_c_inputs,
replay=replay))
int_to_val[idx] = output
int_to_graph[idx] = output_graph
call_strs.append(program)
graph.merge(c_graph)
# Check that the final output is equivalent to the original output specified in the benchmark.
assert domain.check_equivalent(self.output, int_to_val[self.skeleton.length]), \
f"Generated output inconsistent with specified output in Pandas benchmark {self.b_id}"
# Retrofit the value of the output entity to the original output
cur_out_entity = next(ent for ent in graph.iter_entities()
if ent.value is int_to_val[self.skeleton.length])
cur_out_entity.value = self.output
# Perform transitive closure w.r.t the nodes corresponding to the intermediate outputs
# and take the induced subgraph containing all nodes except those
if self.skeleton.length > 1:
join_nodes = set.union(*(set(int_to_graph[i].iter_nodes())
for i in range(1, self.skeleton.length)))
domain.perform_transitive_closure(graph, join_nodes=join_nodes)
intent_graph = graph.induced_subgraph(
keep_nodes=set(graph.iter_nodes()) - join_nodes)
else:
intent_graph = graph
self._graph = intent_graph
# Also construct the string representation of the ground-truth program.
program_list: List[str] = []
for depth, (call_str,
(component_name,
arg_ints)) in enumerate(zip(call_strs, self.skeleton), 1):
arg_strs = [f"inp{-i}" if i < 0 else f"v{i}" for i in arg_ints]
call_str = call_str.format(**{
f"inp{idx}": arg_str
for idx, arg_str in enumerate(arg_strs, 1)
})
if depth == self.skeleton.length:
program_list.append(call_str)
else:
program_list.append(f"v{depth} = {call_str}")
self.program = "\n".join(program_list)
def extract_queries(
problem: SynthesisProblem) -> Dict[Transformation, List[Query]]:
# Stage 1 : Get all paths from one of the input nodes to an output node without any input/output node in between.
graph = problem.graph
inputs = problem.inputs
output = problem.output
entities = list(graph.iter_entities())
input_entities = [
next(ent for ent in entities if ent.value is inp) for inp in inputs
]
output_entity = next(ent for ent in entities if ent.value is output)
arg_numbering = {ent: idx for idx, ent in enumerate(input_entities)}
placeholder_dict = {}
# A placeholder node can represent any node belonging to an entity.
# This helps coalesce equivalent query plans.
for ent in itertools.chain(input_entities, [output_entity]):
placeholder_dict[ent] = PlaceholderNode(entity=ent)
path_dict: Dict[Entity,
List[Path]] = extract_paths(graph, input_entities,
output_entity)
canonical_transformations: Dict[Transformation, Transformation] = {}
# Only keep one transformation for a set of nodes as satisfying that query means satisfying all the others.
seen: Set[Tuple[Transformation, FrozenSet[Node]]] = set()
queries: Dict[Transformation, List[Query]] = collections.defaultdict(list)
set_input_entities = set(input_entities)
# Find queries by taking exactly one path, and placeholder nodes for the
# input entities not present in the path.
for path_ent, paths in path_dict.items():
remaining_entities = [
ent for ent in set_input_entities if ent is not path_ent
]
for path in paths:
path_nodes, path_edges = path
nodes = list(path_nodes) + [
placeholder_dict[ent] for ent in remaining_entities
]
edges = path_edges
# Get the corresponding subgraph.
subgraph = Graph.from_nodes_and_edges(nodes=set(nodes),
edges=set(edges))
subgraph_transformation = Transformation.build_from_graph(
subgraph,
input_entities=input_entities,
output_entity=output_entity)
# Compute the symbolic counter-part to group subgraphs together by the underlying transformation.
symbolic_copy, mapping = create_symbolic_copy(subgraph)
mapped_input_entities = [mapping.m_ent[i] for i in input_entities]
mapped_output_entity = mapping.m_ent[output_entity]
transformation = Transformation.build_from_graph(
symbolic_copy,
input_entities=mapped_input_entities,
output_entity=mapped_output_entity)
# Check if the transformation was seen before
if transformation not in canonical_transformations:
canonical_transformations[transformation] = transformation
seen.add((transformation,
frozenset(n for n in subgraph.iter_nodes()
if n.entity in set_input_entities)))
mapping = mapping.reverse()
arg_number_mapping = ArgumentNumberMapping({
idx: arg_numbering[mapping.m_ent[ent]]
for idx, ent in enumerate(mapped_input_entities)
})
# We need a mapping from transformation to the subgraph.
queries[transformation].append(
Query(transformation=transformation,
subgraph=subgraph_transformation,
mapping=mapping,
arg_number_mapping=arg_number_mapping))
else:
canonical = canonical_transformations[transformation]
key = (transformation,
frozenset(n for n in subgraph.iter_nodes()
if n.entity in set_input_entities))
# Check if the transformation was seen before with the same input nodes. If yes, continue. This is
# because if a graph satisfies the already seen transformation for these input nodes, it will satisfy
# this one as well. So no point in checking it.
if key in seen:
continue
seen.add(key)
# We need a mapping from the canonical transformation to the subgraph.
mapping = next(canonical.get_subgraph_mappings(
transformation)).apply_mapping(mapping.reverse())
arg_number_mapping = ArgumentNumberMapping({
idx: arg_numbering[mapping.m_ent[ent]]
for idx, ent in enumerate(canonical.get_input_entities())
})
queries[canonical].append(
Query(transformation=canonical,
subgraph=subgraph_transformation,
mapping=mapping,
arg_number_mapping=arg_number_mapping))
return queries
def test_2(self):
g1 = Graph()
n1 = Node(label=0, entity=DEFAULT_ENTITY, value=10)
n2 = Node(label=1, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g1.add_node(n1)
g1.add_node(n2)
g1.add_edge(Edge(n1, n2, 0))
g2 = Graph()
n3 = Node(label=0, entity=DEFAULT_ENTITY, value=SYMBOLIC_VALUE)
g2.add_node(n3)
g3 = Graph()
n4 = Node(label=0, entity=DEFAULT_ENTITY, value=20)
g3.add_node(n4)
mappings_21 = list(g2.get_subgraph_mappings(g1))
mappings_31 = list(g3.get_subgraph_mappings(g1))
self.assertEqual(1, len(mappings_21))
self.assertEqual(mappings_21[0].m_node[n3], n1)
self.assertEqual(mappings_21[0].m_ent[n3.entity], n1.entity)
self.assertEqual(0, len(mappings_31))