Сравнение двух CSV-расшифровок по ID: как найти добавленные, удалённые и изменённые реплики

import csv
fields = ["replica_id", "speaker", "timecode", "text"]
def read(path):
    result = {}
    with open(path, encoding="utf-8-sig", newline="") as f:
        reader = csv.DictReader(f)
        if reader.fieldnames != fields:
            raise ValueError("Заголовки: " + path)
        for row in reader:
            if None in row or any(v is None for v in row.values()):
                raise ValueError("Число полей: " + path)
            key = row["replica_id"]
            if not key or key in result:
                raise ValueError("Пустой или повторный ID: " + path)
            result[key] = row
    return result
old, new = read("before.csv"), read("after.csv")
changes = []
for key in sorted(set(old) | set(new)):
    if key not in old:
        changes.append([key, "added", "", "", new[key]["text"]])
    elif key not in new:
        changes.append([key, "removed", "", old[key]["text"], ""])
    else:
        for field in fields[1:]:
            if old[key][field] != new[key][field]:
                changes.append([key, "changed", field,
                                old[key][field], new[key][field]])
with open("changes.csv", "x", encoding="utf-8", newline="") as f:
    writer = csv.writer(f)
    writer.writerow(["replica_id", "status", "field", "before", "after"])
    writer.writerows(changes)
print("Строк отчёта:", len(changes))