handle pickling differently

dedupeio · Jun 27, 2024 · 9271305 · 9271305
1 parent 0c6b65c
commit 9271305
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 25 deletions.
diff --git a/parseratorvariable/__init__.py b/parseratorvariable/__init__.py
@@ -40,16 +40,6 @@ def __init__(
         else:
             self._string_comparison = affineGap
 
-        # setting up some information for pickling this variable
-        self._definition = {
-            "field": field,
-            "tagger": tagger,
-            "block_parts": block_parts,
-            "crf": crf,
-            "log_file": log_file,
-        }
-        self._definition.update(**kwargs)
-
         self.variable_types, self.variable_parts = comparisons(self.components)
 
         self.n_type_indicators = len(self.variable_types) - 1
@@ -62,8 +52,7 @@ def __init__(
         fields = self.fields(field)
 
         self.higher_vars = [
-            DerivedType(variable, field_type)
-            for variable, field_type in fields
+            DerivedType(variable, field_type) for variable, field_type in fields
         ]
 
         self.log_file = log_file
@@ -100,12 +89,6 @@ def tag(self, field, *args):
 
         return result
 
-    def __getstate__(self):
-        return self._definition.copy()
-
-    def __setstate__(self, d):
-        self.__init__(**d)
-
     def comparator(self, field_1, field_2):
         distances = numpy.zeros(self.expanded_size)
         i = 0
@@ -167,7 +150,8 @@ def fields(self, field):
         fields += [(part, "Derived") for part in self.variable_parts]
 
         fields += [
-            ("%s: Not Missing" % (part,), "Not Missing") for part in self.variable_parts
+            ("{}: Not Missing".format(part), "Not Missing")
+            for part in self.variable_parts
         ]
 
         fields += [("full string", "String")]

diff --git a/parseratorvariable/predicates.py b/parseratorvariable/predicates.py
@@ -2,12 +2,12 @@
 from probableparsing import RepeatedLabelError
 
 
-class PartialIndex(object):
+class PartialIndex:
     def __init__(self, *args, **kwargs):
         self.part = kwargs.pop("part")
         self.tag = kwargs.pop("tag")
-        super(PartialIndex, self).__init__(*args, **kwargs)
-        self.__name__ = "(%s, %s, %s)" % (self.threshold, self.field, self.part)
+        super().__init__(*args, **kwargs)
+        self.__name__ = "({}, {}, {})".format(self.threshold, self.field, self.part)
 
     def preprocess(self, doc):
         try:
@@ -16,7 +16,7 @@ def preprocess(self, doc):
             part = ""
         else:
             part = tags.get(self.part, "")
-        return super(PartialIndex, self).preprocess(part)
+        return super().preprocess(part)
 
 
 class PLCPredicate(PartialIndex, predicates.LevenshteinCanopyPredicate):
@@ -48,7 +48,7 @@ class PartialString(predicates.StringPredicate):
 
     def __init__(self, func, field, part, tag):
         self.func = func
-        self.__name__ = "(%s, %s, %s)" % (func.__name__, field, part)
+        self.__name__ = "({}, {}, {})".format(func.__name__, field, part)
         self.field = field
         self.part = part
         self.tag = tag
@@ -65,4 +65,4 @@ def __call__(self, record, **kwargs):
         else:
             part = tags.get(self.part, "")
 
-        return super(PartialString, self).__call__({self.field: part})
+        return super().__call__({self.field: part})