Merge pull request #169 from CornellNLP/storage-abstraction

Storage abstraction

.pre-commit-config.yaml

@@ -9,4 +9,3 @@ repos:
     rev: 22.3.0
     hooks:
       - id: black
-        language_version: python3.9

convokit/model/convoKitMeta.py

@@ -2,9 +2,11 @@
     from collections.abc import MutableMapping
 except:
     from collections import MutableMapping
+from numpy import isin
 from convokit.util import warn
 from .convoKitIndex import ConvoKitIndex
 import json
+from typing import Union
 
 # See reference: https://stackoverflow.com/questions/7760916/correct-usage-of-a-getter-setter-for-dictionary-values
 
@@ -14,12 +16,30 @@ class ConvoKitMeta(MutableMapping, dict):
     ConvoKitMeta is a dictlike object that stores the metadata attributes of a corpus component
     """
 
-    def __init__(self, convokit_index, obj_type):
+    def __init__(self, owner, convokit_index, obj_type):
+        self.owner = owner  # Corpus or CorpusComponent
         self.index: ConvoKitIndex = convokit_index
         self.obj_type = obj_type
 
+        self._get_storage().initialize_data_for_component("meta", self.storage_key)
+
+    @property
+    def storage_key(self) -> str:
+        return f"{self.obj_type}_{self.owner.id}"
+
     def __getitem__(self, item):
-        return dict.__getitem__(self, item)
+        return self._get_storage().get_data("meta", self.storage_key, item)
+
+    def _get_storage(self):
+        # special case for Corpus meta since that's the only time owner is not a CorpusComponent
+        # since cannot directly import Corpus to check the type (circular import), as a proxy we
+        # check for the obj_type attribute which is common to all CorpusComponent but not
+        # present in Corpus
+        if not hasattr(self.owner, "obj_type"):
+            return self.owner.storage
+        # self.owner -> CorpusComponent
+        # self.owner.owner -> Corpus that owns the CorpusComponent (only Corpus has direct pointer to storage)
+        return self.owner.owner.storage
 
     @staticmethod
     def _check_type_and_update_index(index, obj_type, key, value):
@@ -45,12 +65,12 @@ def __setitem__(self, key, value):
 
         if self.index.type_check:
             ConvoKitMeta._check_type_and_update_index(self.index, self.obj_type, key, value)
-        dict.__setitem__(self, key, value)
+        self._get_storage().update_data("meta", self.storage_key, key, value)
 
     def __delitem__(self, key):
         if self.obj_type == "corpus":
-            dict.__delitem__(self, key)
             self.index.del_from_index(self.obj_type, key)
+            self._get_storage().delete_data("meta", self.storage_key, key)
         else:
             if self.index.lock_metadata_deletion[self.obj_type]:
                 warn(
@@ -62,19 +82,36 @@ def __delitem__(self, key):
                     )
                 )
             else:
-                dict.__delitem__(self, key)
+                self._get_storage().delete_data("meta", self.storage_key, key)
 
     def __iter__(self):
-        return dict.__iter__(self)
+        return self._get_storage().get_data("meta", self.storage_key).__iter__()
 
     def __len__(self):
-        return dict.__len__(self)
+        return self._get_storage().get_data("meta", self.storage_key).__len__()
 
     def __contains__(self, x):
-        return dict.__contains__(self, x)
+        return self._get_storage().get_data("meta", self.storage_key).__contains__(x)
+
+    def __repr__(self) -> str:
+        return "ConvoKitMeta(" + self.to_dict().__repr__() + ")"
 
     def to_dict(self):
-        return self.__dict__
+        return dict(self._get_storage().get_data("meta", self.storage_key))
+
+    def reinitialize_from(self, other: Union["ConvoKitMeta", dict]):
+        """
+        Reinitialize this ConvoKitMeta instance with the data from other
+        """
+        if isinstance(other, ConvoKitMeta):
+            other = {k: v for k, v in other.to_dict().items()}
+        elif not isinstance(other, dict):
+            raise TypeError(
+                "ConvoKitMeta can only be reinitialized from a dict instance or another ConvoKitMeta"
+            )
+        self._get_storage().initialize_data_for_component(
+            "meta", self.storage_key, overwrite=True, initial_value=other
+        )
 
 
 _basic_types = {type(0), type(1.0), type("str"), type(True)}  # cannot include lists or dicts