fix bug add testcases

Author: TomHodson

src/python/qubed/set_operations.py

@@ -75,7 +75,11 @@ def node_intersection(
         return QEnum_intersection(A, B)
 
     if isinstance(A.values, WildcardGroup) and isinstance(B.values, WildcardGroup):
-        return A, ValuesMetadata(WildcardGroup(), {}), B
+        return (
+            ValuesMetadata(QEnum([]), {}),
+            ValuesMetadata(WildcardGroup(), {}),
+            ValuesMetadata(QEnum([]), {}),
+        )
 
     # If A is a wildcard matcher then the intersection is everything
     # just_A is still *
@@ -92,7 +96,7 @@ def node_intersection(
     )
 
 
-def operation(A: Qube, B: Qube, operation_type: SetOperation, node_type) -> Qube:
+def operation(A: Qube, B: Qube, operation_type: SetOperation, node_type) -> Qube | None:
     assert A.key == B.key, (
         "The two Qube root nodes must have the same key to perform set operations,"
         f"would usually be two root nodes. They have {A.key} and {B.key} respectively"
@@ -118,6 +122,18 @@ def operation(A: Qube, B: Qube, operation_type: SetOperation, node_type) -> Qube
         output = list(_operation(key, A_nodes, B_nodes, operation_type, node_type))
         new_children.extend(output)
 
+    # print(f"operation {operation_type}: {A}, {B} {new_children = }")
+    # print(f"{A.children = }")
+    # print(f"{B.children = }")
+    # print(f"{new_children = }")
+
+    # If there are now no children as a result of the operation, return nothing.
+    if (A.children or B.children) and not new_children:
+        if A.key == "root":
+            return A.replace(children=())
+        else:
+            return None
+
     # Whenever we modify children we should recompress them
     # But since `operation` is already recursive, we only need to compress this level not all levels
     # Hence we use the non-recursive _compress method
@@ -161,7 +177,14 @@ def _operation(
                         values=intersection.values,
                         metadata=intersection.metadata,
                     )
-                    yield operation(new_node_a, new_node_b, operation_type, node_type)
+                    # print(f"{node_a = }")
+                    # print(f"{node_b = }")
+                    # print(f"{intersection.values =}")
+                    result = operation(
+                        new_node_a, new_node_b, operation_type, node_type
+                    )
+                    if result is not None:
+                        yield result
 
     # Now we've removed all the intersections we can yield the just_A and just_B parts if needed
     if keep_just_A:

src/python/qubed/value_types.py

@@ -119,6 +119,9 @@ def __len__(self):
     def __iter__(self):
         return ["*"]
 
+    def __bool__(self):
+        return True
+
     @classmethod
     def from_strings(cls, values: Iterable[str]) -> Sequence[ValueGroup]:
         return [WildcardGroup()]

src/rust/lib.rs

@@ -3,6 +3,8 @@
 // #![allow(unused_variables)]
 
 
+use std::collections::HashMap;
+
 use pyo3::prelude::*;
 use pyo3::wrap_pyfunction;
 use pyo3::types::{PyDict, PyInt, PyList, PyString};
@@ -18,6 +20,47 @@ fn rust(m: &Bound<'_, PyModule>) -> PyResult<()> {
     Ok(())
 }
 
+#[derive(Debug, Copy, Clone, PartialEq, PartialOrd, Ord, Eq, Hash)]
+struct NodeId(usize);
+
+#[derive(Debug, Copy, Clone, PartialEq, PartialOrd, Ord, Eq, Hash)]
+struct StringId(usize);
+
+struct Node {
+    key: StringId,
+    metadata: HashMap<StringId, Vec<String>>,
+    parent: NodeId,
+    values: Vec<String>,
+    children: HashMap<StringId, Vec<NodeId>>,
+}
+
+
+
+struct Qube {
+    root: NodeId,
+    nodes: Vec<Node>,
+    strings: Vec<String>,
+}
+
+use std::ops;
+
+impl ops::Index<StringId> for Qube {
+    type Output = str;
+
+    fn index(&self, index: StringId) -> &str {
+        &self.strings[index.0]
+    }
+
+}
+
+impl ops::Index<NodeId> for Qube {
+    type Output = Node;
+
+    fn index(&self, index: NodeId) -> &Node {
+        &self.nodes[index.0]
+    }
+
+}
 
 // use rsfdb::listiterator::KeyValueLevel;
 // use rsfdb::request::Request;

tests/test_set_operations.py

@@ -1,6 +1,95 @@
 from qubed import Qube
 
 
+def set_operation_testcase(testcase):
+    q1 = Qube.from_tree(testcase["q1"])
+    q2 = Qube.from_tree(testcase["q2"])
+    assert q1 | q2 == Qube.from_tree(testcase["union"])
+    assert q1 & q2 == Qube.from_tree(testcase["intersection"])
+    assert q1 - q2 == Qube.from_tree(testcase["q1 - q2"])
+
+
+# These are a bunch of testcases where q1 and q2 are specified and then their union/intersection/difference are checked
+# Generate them with code like:
+# q1 = Qube.from_tree("root, frequency=*, levtype=*, param=*, levelist=*, domain=a/b/c/d")
+# q2 = Qube.from_tree("root, frequency=*, levtype=*, param=*, domain=a/b/c/d")
+
+# test = {
+# "q1": str(q1),
+# "q2": str(q2),
+# "union": str(q1 | q2),
+# "intersection": str(q1 & q2),
+# "q1 - q2": str(q1 - q2),
+# }
+# BUT MANUALLY CHECK THE OUTPUT BEFORE ADDING IT AS A TEST CASE!
+
+
+testcases = [
+    # Simplest case, only leaves differ
+    {
+        "q1": "root, a=1, b=1, c=1",
+        "q2": "root, a=1, b=1, c=2",
+        "union": "root, a=1, b=1, c=1/2",
+        "intersection": "root",
+        "q1 - q2": "root",
+    },
+    # Some overlap but also each tree has unique items
+    {
+        "q1": "root, a=1, b=1, c=1/2/3",
+        "q2": "root, a=1, b=1, c=2/3/4",
+        "union": "root, a=1, b=1, c=1/2/3/4",
+        "intersection": "root, a=1, b=1, c=2/3",
+        "q1 - q2": "root",
+    },
+    # Overlap at two levels
+    {
+        "q1": "root, a=1, b=1/2, c=1/2/3",
+        "q2": "root, a=1, b=2/3, c=2/3/4",
+        "union": """
+        root, a=1
+        ├── b=1, c=1/2/3
+        ├── b=2, c=1/2/3/4
+        └── b=3, c=2/3/4
+    """,
+        "intersection": "root, a=1, b=2, c=2/3",
+        "q1 - q2": "root",
+    },
+    # Check that we can merge even if the divergence point is higher
+    {
+        "q1": "root, a=1, b=1, c=1",
+        "q2": "root, a=2, b=1, c=1",
+        "union": "root, a=1/2, b=1, c=1",
+        "intersection": "root",
+        "q1 - q2": "root, a=1, b=1, c=1",
+    },
+    # Two equal qubes
+    {
+        "q1": "root, a=1, b=1, c=1",
+        "q2": "root, a=1, b=1, c=1",
+        "union": "root, a=1, b=1, c=1",
+        "intersection": "root, a=1, b=1, c=1",
+        "q1 - q2": "root",
+    },
+    # With wildcards
+    {
+        "q1": "root, frequency=*, levtype=*, param=*, levelist=*, domain=a/b/c/d",
+        "q2": "root, frequency=*, levtype=*, param=*, domain=a/b/c/d",
+        "union": """
+        root, frequency=*, levtype=*, param=*
+        ├── domain=a/b/c/d
+        └── levelist=*, domain=a/b/c/d
+    """,
+        "intersection": "root",
+        "q1 - q2": "root",
+    },
+]
+
+
+def test_cases():
+    for case in testcases:
+        set_operation_testcase(case)
+
+
 def test_leaf_conservation():
     q = Qube.from_dict(
         {

tests/test_wildcard.py

@@ -34,3 +34,16 @@ def test_intersection():
             },
         }
     )
+
+
+def test_wildcard_union():
+    q1 = Qube.from_tree(
+        "root, frequency=*, levtype=*, param=*, levelist=*, domain=a/b/c/d"
+    )
+    q2 = Qube.from_tree("root, frequency=*, levtype=*, param=*, domain=a/b/c/d")
+    expected = Qube.from_tree("""
+    root, frequency=*, levtype=*, param=*
+    ├── domain=a/b/c/d
+    └── levelist=*, domain=a/b/c/d
+    """)
+    assert (q1 | q2) == expected