Relax the checking of cross-type column matching on demand

And ensure that both columns have the same set of attributes and follow the same protocol before actually using it — i.e. do not simply imply it as given.

Author: Sergey Vasilyev

data_diff/hashdiff_tables.py

@@ -3,7 +3,6 @@
 import logging
 from collections import defaultdict
 from typing import Iterator
-from operator import attrgetter
 
 import attrs
 
@@ -82,7 +81,7 @@ def __attrs_post_init__(self):
         if self.bisection_factor < 2:
             raise ValueError("Must have at least two segments per iteration (i.e. bisection_factor >= 2)")
 
-    def _validate_and_adjust_columns(self, table1, table2):
+    def _validate_and_adjust_columns(self, table1, table2, *, strict: bool = True):
         for c1, c2 in safezip(table1.relevant_columns, table2.relevant_columns):
             if c1 not in table1._schema:
                 raise ValueError(f"Column '{c1}' not found in schema for table {table1}")
@@ -92,23 +91,23 @@ def _validate_and_adjust_columns(self, table1, table2):
             # Update schemas to minimal mutual precision
             col1 = table1._schema[c1]
             col2 = table2._schema[c2]
-            if isinstance(col1, PrecisionType):
-                if not isinstance(col2, PrecisionType):
+            if isinstance(col1, PrecisionType) and isinstance(col2, PrecisionType):
+                if strict and not isinstance(col2, PrecisionType):
                     raise TypeError(f"Incompatible types for column '{c1}':  {col1} <-> {col2}")
 
-                lowest = min(col1, col2, key=attrgetter("precision"))
+                lowest = min(col1, col2, key=lambda col: col.precision)
 
                 if col1.precision != col2.precision:
                     logger.warning(f"Using reduced precision {lowest} for column '{c1}'. Types={col1}, {col2}")
 
                 table1._schema[c1] = attrs.evolve(col1, precision=lowest.precision, rounds=lowest.rounds)
                 table2._schema[c2] = attrs.evolve(col2, precision=lowest.precision, rounds=lowest.rounds)
 
-            elif isinstance(col1, (NumericType, Boolean)):
-                if not isinstance(col2, (NumericType, Boolean)):
+            elif isinstance(col1, (NumericType, Boolean)) and isinstance(col2, (NumericType, Boolean)):
+                if strict and not isinstance(col2, (NumericType, Boolean)):
                     raise TypeError(f"Incompatible types for column '{c1}':  {col1} <-> {col2}")
 
-                lowest = min(col1, col2, key=attrgetter("precision"))
+                lowest = min(col1, col2, key=lambda col: col.precision)
 
                 if col1.precision != col2.precision:
                     logger.warning(f"Using reduced precision {lowest} for column '{c1}'. Types={col1}, {col2}")
@@ -119,11 +118,11 @@ def _validate_and_adjust_columns(self, table1, table2):
                     table2._schema[c2] = attrs.evolve(col2, precision=lowest.precision)
 
             elif isinstance(col1, ColType_UUID):
-                if not isinstance(col2, ColType_UUID):
+                if strict and not isinstance(col2, ColType_UUID):
                     raise TypeError(f"Incompatible types for column '{c1}':  {col1} <-> {col2}")
 
             elif isinstance(col1, StringType):
-                if not isinstance(col2, StringType):
+                if strict and not isinstance(col2, StringType):
                     raise TypeError(f"Incompatible types for column '{c1}':  {col1} <-> {col2}")
 
         for t in [table1, table2]: