csv_diff_compare_files_with_primary_key_tracking.py

1import io
2from csv_diff import load_csv, compare
3
4# Define the CSV data as file-like objects
5previous_csv = io.StringIO("""id,name,age
61,Cleo,4
72,Pancakes,2""")
8
9current_csv = io.StringIO("""id,name,age
101,Cleo,5
113,Bailey,1""")
12
13# Load the CSV data into dictionaries, specifying the primary key
14# The primary key is used to track changes to the same row
15diff = compare(
16    load_csv(previous_csv, key="id"),
17    load_csv(current_csv, key="id")
18)
19
20# The result is a dictionary containing 'added', 'removed', and 'changed'
21print(diff)
22
23# Example output:
24# {
25#     'added': [{'id': '3', 'name': 'Bailey', 'age': '1'}],
26#     'removed': [{'id': '2', 'name': 'Pancakes', 'age': '2'}],
27#     'changed': [{'id': '1', 'changes': {'age': ['4', '5']}}],
28#     'columns_added': [],
29#     'columns_removed': []
30# }