Add DataTree.match_names to match node names

pydata · Sep 7, 2024 · 7ff801d · 7ff801d
1 parent 25debff
commit 7ff801d
Show file tree

Hide file tree

Showing 2 changed files with 65 additions and 0 deletions.
diff --git a/xarray/core/datatree.py b/xarray/core/datatree.py
@@ -1349,6 +1349,50 @@ def match(self, pattern: str) -> DataTree:
         }
         return DataTree.from_dict(matching_nodes, name=self.root.name)
 
+    def match_names(self, names: Iterable[str]) -> DataTree:
+        """
+        Filter nodes by name.
+
+        Parameters
+        ----------
+        names: Iterable[str]
+            The list of node names to retain.
+
+        Returns
+        -------
+        DataTree
+
+        See Also
+        --------
+        match
+        filter
+        pipe
+        map_over_subtree
+
+        Examples
+        --------
+        >>> dt = DataTree.from_dict(
+        ...     {
+        ...         "/a/A": None,
+        ...         "/a/B": None,
+        ...         "/a/C": None,
+        ...         "/C/D": None,
+        ...         "/E/F": None,
+        ...     }
+        ... )
+        >>> dt.match_names(["A", "C"])
+        DataTree('None', parent=None)
+        ├── DataTree('a')
+        │   └── DataTree('A')
+        │   └── DataTree('C')
+        └── DataTree('C')
+        """
+        names = set(names)
+        matching_nodes = {
+            node.path: node.ds for node in self.subtree if node.name in names
+        }
+        return DataTree.from_dict(matching_nodes, name=self.root.name)
+
     def map_over_subtree(
         self,
         func: Callable,

diff --git a/xarray/tests/test_datatree.py b/xarray/tests/test_datatree.py
@@ -1025,6 +1025,27 @@ def test_match(self):
         )
         assert_identical(result, expected)
 
+    def test_match_names(self):
+        # TODO is this example going to cause problems with case sensitivity?
+        dt: DataTree = DataTree.from_dict(
+            {
+                "/a/A": None,
+                "/a/B": None,
+                "/a/C": None,
+                "/C/D": None,
+                "/E/F": None,
+            }
+        )
+        result = dt.match_names(["A", "C"])
+        expected = DataTree.from_dict(
+            {
+                "/a/A": None,
+                "/a/C": None,
+                "/C": None,
+            }
+        )
+        assert_identical(result, expected)
+
     def test_filter(self):
         simpsons: DataTree = DataTree.from_dict(
             d={