Add check_virtual_sources_exist

tomoscan/io.py

@@ -127,3 +127,36 @@ def isErrno(e, errno):
     """
     # Because e.__cause__ is None for chained exceptions
     return "errno = {}".format(errno) in "".join(traceback.format_exc())
+
+def check_virtual_sources_exist(fname, data_path):
+    """
+    Check that a virtual dataset points to actual data.
+
+    Parameters
+    ----------
+    fname: str
+        HDF5 file path
+    data_path: str
+        Path within the HDF5 file
+
+    Returns
+    --------
+    res: bool
+        Whether the virtual dataset points to actual data.
+    """
+    with HDF5File(fname, "r") as f:
+        if data_path not in f:
+            print("No dataset %s in file %s" % (data_path, fname))
+            return False
+        dptr = f[data_path]
+        if not dptr.is_virtual:
+            return True
+        for vsource in dptr.virtual_sources():
+            vsource_fname = os.path.join(os.path.dirname(dptr.file.filename), vsource.file_name)
+            if not os.path.isfile(vsource_fname):
+                print("No such file: %s" % vsource_fname)
+                return False
+            elif not check_virtual_sources_exist(vsource_fname, vsource.dset_name):
+                print("Error with virtual source %s" % vsource_fname)
+                return False
+    return True