Refactor offline

This refactoring includes some slicing and performance improvement attempts.

The slicing is still experimental and has some flaws:

• fancy indexing over thousands of elements might be horrible slow, eg f.events.tracks[idx_list, 0] where idx_list is a huge list of indices
• trivial problem of iterating: for track in f.evens.tracks does not stop after the last element
• meaningless indexing: f.events[5][23][420] is simply f.events[420] since the index/slice is not chained but overwritten when propagated. We need custom checks whether it makes sense
  • events are flat lists, so [x][y] does not make sense, it should throw an error
  • f.events[5:23][4] should effectively be the same as f.events[9] due to chaining of slice/index

km3io/tools.py

@@ -47,7 +47,7 @@ class Branch:
 
         if subbranchmaps is not None:
             for mapper in subbranchmaps:
-                subbranch = Branch(self._tree,
+                subbranch = self.__class__(self._tree,
                                    mapper=mapper,
                                    index=self._index)
                 self._subbranches.append(subbranch)
@@ -74,10 +74,6 @@ class Branch:
     def keys(self):
         return self._keymap.keys()
 
-    @cached_property
-    def usr(self):
-        return Usr(self._mapper, self._branch, index=self._index)
-
     def __getattribute__(self, attr):
         if attr.startswith("_"):  # let all private and magic methods pass
             return object.__getattribute__(self, attr)
@@ -134,104 +130,6 @@ class Branch:
                                                's' if length > 1 else '')
 
 
-class Usr:
-    """Helper class to access AAObject `usr` stuff"""
-    def __init__(self, mapper, branch, index=None):
-        self._mapper = mapper
-        self._name = mapper.name
-        self._index = index
-        self._branch = branch
-        self._usr_names = []
-        self._usr_idx_lookup = {}
-
-        self._usr_key = 'usr' if mapper.flat else mapper.key + '.usr'
-
-        self._initialise()
-
-    def _initialise(self):
-        try:
-            self._branch[self._usr_key]
-            # This will raise a KeyError in old aanet files
-            # which has a different strucuter and key (usr_data)
-            # We do not support those (yet)
-        except (KeyError, IndexError):
-            print("The `usr` fields could not be parsed for the '{}' branch.".
-                  format(self._name))
-            return
-
-        if self._mapper.flat:
-            self._initialise_flat()
-
-    def _initialise_flat(self):
-        # Here, we assume that every event has the same names in the same order
-        # to massively increase the performance. This needs triple check if
-        # it's always the case.
-        self._usr_names = [
-            n.decode("utf-8")
-            for n in self._branch[self._usr_key + '_names'].lazyarray(
-                basketcache=BASKET_CACHE)[0]
-        ]
-        self._usr_idx_lookup = {
-            name: index
-            for index, name in enumerate(self._usr_names)
-        }
-
-        data = self._branch[self._usr_key].lazyarray(basketcache=BASKET_CACHE)
-
-        if self._index is not None:
-            data = data[self._index]
-
-        self._usr_data = data
-
-        for name in self._usr_names:
-            setattr(self, name, self[name])
-
-    # def _initialise_nested(self):
-    #     self._usr_names = [
-    #         n.decode("utf-8") for n in self.branch['usr_names'].lazyarray(
-    #             # TODO this will be fixed soon in uproot,
-    #             # see https://github.com/scikit-hep/uproot/issues/465
-    #             uproot.asgenobj(
-    #                 uproot.SimpleArray(uproot.STLVector(uproot.STLString())),
-    #                 self.branch['usr_names']._context, 6),
-    #             basketcache=BASKET_CACHE)[0]
-    #     ]
-
-    def __getitem__(self, item):
-        if self._mapper.flat:
-            return self.__getitem_flat__(item)
-        return self.__getitem_nested__(item)
-
-    def __getitem_flat__(self, item):
-        if self._index is not None:
-            return self._usr_data[self._index][:, self._usr_idx_lookup[item]]
-        else:
-            return self._usr_data[:, self._usr_idx_lookup[item]]
-
-    def __getitem_nested__(self, item):
-        data = self._branch[self._usr_key + '_names'].lazyarray(
-            # TODO this will be fixed soon in uproot,
-            # see https://github.com/scikit-hep/uproot/issues/465
-            uproot.asgenobj(
-                uproot.SimpleArray(uproot.STLVector(uproot.STLString())),
-                self._branch[self._usr_key + '_names']._context, 6),
-            basketcache=BASKET_CACHE)
-        if self._index is None:
-            return data
-        else:
-            return data[self._index]
-
-    def keys(self):
-        return self._usr_names
-
-    def __str__(self):
-        entries = []
-        for name in self.keys():
-            entries.append("{}: {}".format(name, self[name]))
-        return '\n'.join(entries)
-
-    def __repr__(self):
-        return "<{}[{}]>".format(self.__class__.__name__, self._name)
 
 
 def _to_num(value):