perf: use rglob("type.raw") to find systems instead of find * and then find type.raw. 10x accelarate

Author: OutisLi

deepmd/common.py

@@ -202,7 +202,7 @@ def expand_sys_str(root_dir: Union[str, Path]) -> list[str]:
         list of string pointing to system directories
     """
     root_dir = DPPath(root_dir)
-    matches = [str(d) for d in root_dir.rglob("*") if (d / "type.raw").is_file()]
+    matches = [str(p.parent) for p in root_dir.rglob("type.raw") if p.is_file()]
     if (root_dir / "type.raw").is_file():
         matches.append(str(root_dir))
     return matches

deepmd/utils/path.py

@@ -157,6 +157,11 @@ def mkdir(self, parents: bool = False, exist_ok: bool = False) -> None:
             If true, no error will be raised if the target directory already exists.
         """
 
+    @property
+    @abstractmethod
+    def parent(self) -> "DPPath":
+        """Return the parent path."""
+
 
 class DPOSPath(DPPath):
     """The OS path class to data system (DeepmdData) for real directories.
@@ -267,6 +272,11 @@ def name(self) -> str:
         """Name of the path."""
         return self.path.name
 
+    @property
+    def parent(self) -> "DPPath":
+        """Return the parent path."""
+        return type(self)(self.path.parent, mode=self.mode)
+
     def mkdir(self, parents: bool = False, exist_ok: bool = False) -> None:
         """Make directory.
 
@@ -469,6 +479,14 @@ def name(self) -> str:
         """Name of the path."""
         return self._name.split("/")[-1]
 
+    @property
+    def parent(self) -> "DPPath":
+        """Return the parent path."""
+        parent_name = "/".join(self._name.split("/")[:-1])
+        if not parent_name:
+            parent_name = "/"
+        return type(self)(f"{self.root_path}#{parent_name}", mode=self.mode)
+
     def mkdir(self, parents: bool = False, exist_ok: bool = False) -> None:
         """Make directory.