Merge pull request #243 from scipp/transforms

Improve and simplify loading of transformation chains

src/scippnexus/__init__.py

@@ -18,8 +18,26 @@
     create_class,
     create_field,
 )
-from .field import Attrs, Field
+from .field import Attrs, DependsOn, Field
 from .file import File
 from ._load import load
 from .nexus_classes import *
-from .nxtransformations import compute_positions, zip_pixel_offsets
+from .nxtransformations import compute_positions, zip_pixel_offsets, TransformationChain
+
+__all__ = [
+    'Attrs',
+    'DependsOn',
+    'Field',
+    'File',
+    'Group',
+    'NXobject',
+    'NexusStructureError',
+    'TransformationChain',
+    'base_definitions',
+    'compute_positions',
+    'create_class',
+    'create_field',
+    'load',
+    'typing',
+    'zip_pixel_offsets',
+]

src/scippnexus/base.py

@@ -409,16 +409,13 @@ def isclass(x):
         # For a time-dependent transformation in NXtransformations, an NXlog may
         # take the place of the `value` field. In this case, we need to read the
         # properties of the NXlog group to make the actual transformation.
-        from .nxtransformations import maybe_resolve, maybe_transformation
+        from .nxtransformations import maybe_transformation, parse_depends_on_chain
 
-        if (
-            isinstance(dg, sc.DataGroup)
-            and (depends_on := dg.get('depends_on')) is not None
-        ):
-            if (resolved := maybe_resolve(self['depends_on'], depends_on)) is not None:
-                dg['resolved_depends_on'] = resolved
+        if isinstance(dg, sc.DataGroup) and 'depends_on' in dg:
+            if (chain := parse_depends_on_chain(self, dg['depends_on'])) is not None:
+                dg['depends_on'] = chain
 
-        return maybe_transformation(self, value=dg, sel=sel)
+        return maybe_transformation(self, value=dg)
 
     def _warn_fallback(self, e: Exception) -> None:
         msg = (

src/scippnexus/field.py

@@ -24,14 +24,22 @@
     from .base import Group
 
 
-def depends_on_to_relative_path(depends_on: str, parent_path: str) -> str:
-    """Replace depends_on paths with relative paths.
+@dataclass
+class DependsOn:
+    """
+    Represents a depends_on reference in a NeXus file.
+
+    The parent (the full path within the NeXus file) is stored, as the value may be
+    relative or absolute, so having the path available after loading is essential.
+    """
+
+    parent: str
+    value: str
 
-    After loading we will generally not have the same root so absolute paths
-    cannot be resolved after loading."""
-    if depends_on.startswith('/'):
-        return posixpath.relpath(depends_on, parent_path)
-    return depends_on
+    def absolute_path(self) -> str | None:
+        if self.value == '.':
+            return None
+        return posixpath.normpath(posixpath.join(self.parent, self.value))
 
 
 def _is_time(obj):
@@ -161,7 +169,7 @@ def __getitem__(self, select: ScippIndex) -> Any | sc.Variable:
         # If the variable is empty, return early
         if np.prod(shape) == 0:
             variable = self._maybe_datetime(variable)
-            return maybe_transformation(self, value=variable, sel=select)
+            return maybe_transformation(self, value=variable)
 
         if self.dtype == sc.DType.string:
             try:
@@ -170,10 +178,8 @@ def __getitem__(self, select: ScippIndex) -> Any | sc.Variable:
                 strings = self.dataset.asstr(encoding='latin-1')[index]
                 _warn_latin1_decode(self.dataset, strings, str(e))
             variable.values = np.asarray(strings).flatten()
-            if self.dataset.name.endswith('depends_on') and variable.ndim == 0:
-                variable.value = depends_on_to_relative_path(
-                    variable.value, self.dataset.parent.name
-                )
+            if self.dataset.name.endswith('/depends_on') and variable.ndim == 0:
+                return DependsOn(parent=self.dataset.parent.name, value=variable.value)
         elif variable.values.flags["C_CONTIGUOUS"]:
             # On versions of h5py prior to 3.2, a TypeError occurs in some cases
             # where h5py cannot broadcast data with e.g. shape (20, 1) to a buffer
@@ -199,7 +205,7 @@ def __getitem__(self, select: ScippIndex) -> Any | sc.Variable:
             else:
                 return variable.value
         variable = self._maybe_datetime(variable)
-        return maybe_transformation(self, value=variable, sel=select)
+        return maybe_transformation(self, value=variable)
 
     def _maybe_datetime(self, variable: sc.Variable) -> sc.Variable:
         if _is_time(variable):