removed old, unused code

Author: datsom1

db_diff/__init__.py

@@ -17,6 +17,18 @@
 
 __version__ = "1.0.0"
 
+def _generate_hash_key(row):
+    """
+    Generate a hash key for a row.
+    
+    Args:
+        row: Row data dictionary
+        
+    Returns:
+        Hash key as a string
+    """
+    return xxhash.xxh64(json.dumps(row, sort_keys=True).encode("utf8")).hexdigest()
+
 def load_csv(fp, key=None, dialect=None):
     """
     Load a CSV file into a dictionary keyed by the given column or hash.
@@ -45,7 +57,7 @@ def load_csv(fp, key=None, dialect=None):
     if key:
         keyfn = lambda r: r[key]
     else:
-        keyfn = lambda r: xxhash.xxh64(json.dumps(r, sort_keys=True).encode("utf8")).hexdigest()
+        keyfn = _generate_hash_key
     return {keyfn(r): r for r in rows}
 
 def load_json(fp, key=None):
@@ -79,7 +91,7 @@ def load_json(fp, key=None):
     if key:
         keyfn = lambda r: r.get(key, str(id(r)))
     else:
-        keyfn = lambda r: xxhash.xxh64(json.dumps(r, sort_keys=True).encode("utf8")).hexdigest()
+        keyfn = _generate_hash_key
 
     return {keyfn(r): _simplify_json_row(r, common_keys) for r in raw_list}
 
@@ -108,6 +120,31 @@ def _simplify_json_row(r, common_keys):
 
     return result
 
+def _determine_columns_to_compare(prev_columns, curr_columns, fields=None, ignorefields=None):
+    """
+    Determine which columns to compare based on fields and ignorefields.
+    
+    Args:
+        prev_columns: Set of column names from previous data
+        curr_columns: Set of column names from current data
+        fields: List of specific fields to compare (optional)
+        ignorefields: List of fields to ignore in comparison (optional)
+        
+    Returns:
+        Tuple of (compare_columns, ignore_columns)
+    """
+    if fields:
+        compare_columns = set(fields)
+    elif ignorefields:
+        compare_columns = prev_columns | curr_columns
+        compare_columns -= set(ignorefields)
+    else:
+        compare_columns = prev_columns | curr_columns
+        
+    ignore_columns = (prev_columns | curr_columns) - compare_columns
+    
+    return compare_columns, ignore_columns
+
 def compare(previous, current, show_unchanged=False, fields=None, ignorefields=None):
     """
     Compare two dictionaries of rows and return a diff summary.
@@ -143,18 +180,12 @@ def compare(previous, current, show_unchanged=False, fields=None, ignorefields=N
     current_columns = set(next(iter(current.values())).keys())
 
     # Apply fields/ignorefields filtering
-    if fields:
-        compare_columns = set(fields)
-    elif ignorefields:
-        compare_columns = previous_columns | current_columns
-        compare_columns -= set(ignorefields)
-    else:
-        compare_columns = previous_columns | current_columns
+    compare_columns, ignore_columns = _determine_columns_to_compare(previous_columns, current_columns, fields, ignorefields)
 
     # Adjust columns_added/removed based on compare_columns
     result["columns_added"] = [c for c in current_columns if c not in previous_columns and c in compare_columns]
     result["columns_removed"] = [c for c in previous_columns if c not in current_columns and c in compare_columns]
-    ignore_columns = (previous_columns | current_columns) - compare_columns
+    #ignore_columns = (previous_columns | current_columns) - compare_columns
 
     # Have any rows been removed or added?
     removed = [id for id in previous if id not in current]
@@ -249,12 +280,7 @@ def streaming_compare_csv(prev_path, curr_path, key, compare_columns=None, ignor
             curr_columns = set(reader2.fieldnames)
 
             # Determine columns to compare
-            if compare_columns:
-                compare_columns = set(compare_columns)
-            elif ignorefields:
-                compare_columns = (prev_columns | curr_columns) - set(ignorefields)
-            else:
-                compare_columns = prev_columns | curr_columns
+            compare_columns, _ = _determine_columns_to_compare(prev_columns, curr_columns, compare_columns, ignorefields)
 
             result["columns_added"] = [c for c in curr_columns if c not in prev_columns and c in compare_columns]
             result["columns_removed"] = [c for c in prev_columns if c not in curr_columns and c in compare_columns]
@@ -298,15 +324,13 @@ def streaming_compare_csv(prev_path, curr_path, key, compare_columns=None, ignor
 
     return result
 
-def human_text(result, key=None, current=None, extras=None):
+def human_text(result, key=None):
     """
     Render the diff result as a human-readable string.
     
     Args:
         result: Diff result dictionary
         key: Name of the key column (optional)
-        current: Current data dictionary (optional)
-        extras: Extra fields to display (optional)
         
     Returns:
         Formatted string with diff information
@@ -345,10 +369,6 @@ def human_text(result, key=None, current=None, extras=None):
             block.append(f"  {key}: {details['key']}")
             for field, (prev_value, current_value) in details["changes"].items():
                 block.append(f'    {field}: "{prev_value}" => "{current_value}"')
-            if extras and current:
-                current_item = current.get(details["key"])
-                if current_item:
-                    block.append(human_extras(current_item, extras))
             block.append("")
             change_blocks.append("\n".join(block))
             if details.get("unchanged"):
@@ -369,8 +389,6 @@ def human_text(result, key=None, current=None, extras=None):
         rows = []
         for row in result["added"]:
             to_append = human_row(row, prefix="  ")
-            if extras:
-                to_append += "\n" + human_extras(row, extras)
             rows.append(to_append)
         summary.append("\n\n".join(rows))
         summary.append("")
@@ -384,8 +402,6 @@ def human_text(result, key=None, current=None, extras=None):
         rows = []
         for row in result["removed"]:
             to_append = human_row(row, prefix="  ")
-            if extras:
-                to_append += "\n" + human_extras(row, extras)
             rows.append(to_append)
         summary.append("\n\n".join(rows))
         summary.append("")
@@ -404,22 +420,3 @@ def human_row(row, prefix=""):
         Formatted string representation of the row
     """
     return "\n".join(f"{prefix}{key}: {value}" for key, value in row.items())
-
-def human_extras(row, extras):
-    """
-    Render extra fields for a row.
-    
-    Args:
-        row: Row data dictionary
-        extras: List of (key, format) tuples
-        
-    Returns:
-        Formatted string with extra information
-    """
-    bits = ["  extras:"]
-    for key, fmt in extras:
-        try:
-            bits.append(f"    {key}: {fmt.format(**row)}")
-        except (KeyError, ValueError) as e:
-            bits.append(f"    {key}: <error formatting: {str(e)}>")
-    return "\n".join(bits)

db_diff/cli.py

@@ -5,8 +5,8 @@
 """
 
 import click
-import json as std_json
-import time as time_module
+import json
+import time
 import os
 import datetime
 import csv
@@ -47,7 +47,7 @@ def sniff_key_column(filename, input_format, encoding="utf-8"):
     try:
         if input_format == "json":
             with open(filename, encoding=encoding) as f:
-                data = std_json.load(f)
+                data = json.load(f)
                 if isinstance(data, list) and data:
                     return list(data[0].keys())[0]
         else:
@@ -173,13 +173,13 @@ def generate_output_filename(previous, current, output_file, output_path, timest
     "--fields",
     type=str,
     default=None,
-    help="Comma-separated list of fields to compare (all others ignored). Mutually exclusive with --ignorefields. (example: --fields=Id,Name,Age__c,Email__c).",
+    help="Comma-separated list of fields to compare (all others ignored). Mutually exclusive with --ignorefields. (example: --fields=Id,Name,Age,Email).",
 )
 @click.option(
     "--ignorefields",
     type=str,
     default=None,
-    help="Comma-separated list of fields to ignore during comparison. Mutually exclusive with --fields. (example: --ignorefields=LastModifiedDate,SystemModstamp).",
+    help="Comma-separated list of fields to ignore. Mutually exclusive with --fields. (example: --ignorefields=LastModifiedDate,SystemModstamp).",
 )
 @click.option(
     "--showunchanged",
@@ -263,7 +263,7 @@ def cli(
         try:
             if detected_format == "json":
                 with open(previous, encoding=encoding) as f:
-                    data = std_json.load(f)
+                    data = json.load(f)
                     if isinstance(data, list) and data:
                         click.echo("Available fields:")
                         for field in sorted(data[0].keys()):
@@ -307,7 +307,7 @@ def cli(
     ignorefields_set = set(f.strip() for f in ignorefields.split(",")) if ignorefields else None
 
     # Always measure time
-    start = time_module.time()
+    start = time.time()
 
     try:
         # --- Streaming logic ---
@@ -325,8 +325,6 @@ def cli(
                 encoding=encoding,
                 dialect=DIALECTS.get(detected_format, "excel"),
             )
-            # For human_text, we need current_data for extras (if used)
-            current_data = None
         else:
             click.echo("Loading previous data...")
             previous_data = load(previous, key, detected_format, encoding)
@@ -347,15 +345,15 @@ def cli(
 
         # Generate output
         if output == "json":
-            print(std_json.dumps(diff, indent=4))
+            print(json.dumps(diff, indent=4))
             click.echo("Finished. Output printed as JSON to terminal.")
         elif output == "jsonfile":
             with open(output_file, "w", encoding=encoding) as f:
-                f.write(std_json.dumps(diff, indent=4))
+                f.write(json.dumps(diff, indent=4))
             click.echo(f"Finished. Output saved to file: {output_file}")
         else:
             print(
-                human_text(diff, key, current=current_data)
+                human_text(diff, key)
             )
             click.echo("Finished. Output printed in readable format to terminal.")
 
@@ -367,7 +365,7 @@ def cli(
         raise click.ClickException(str(e))
 
     # Always display the elapsed time
-    end = time_module.time()
+    end = time.time()
     click.echo(f"\nElapsed time: {end - start:.3f} seconds")
 
     # Display summary statistics