| 12345678910111213141516171819202122232425262728293031323334353637383940414243 |
- #!/usr/bin/env python3
- import csv
- import sys
- from collections import OrderedDict
- from decimal import Decimal
- INPUT_HEADER = ["日期", "姓名", "类别", "金额"]
- SUMMARY_HEADER = ["姓名", "报销总额"]
- def main():
- if len(sys.argv) != 4:
- raise SystemExit("usage: summarize.py INPUT_CSV SUMMARY_CSV OVER_500_CSV")
- input_path, summary_path, filtered_path = sys.argv[1:]
- with open(input_path, encoding="utf-8-sig", newline="") as source:
- reader = csv.DictReader(source)
- if reader.fieldnames != INPUT_HEADER:
- raise ValueError("unexpected input columns")
- rows = list(reader)
- totals = OrderedDict()
- for row in rows:
- name = row["姓名"]
- totals[name] = totals.get(name, Decimal("0")) + Decimal(row["金额"])
- with open(summary_path, "w", encoding="utf-8", newline="") as output:
- writer = csv.writer(output)
- writer.writerow(SUMMARY_HEADER)
- for name, total in totals.items():
- writer.writerow([name, f"{total:.2f}"])
- with open(filtered_path, "w", encoding="utf-8", newline="") as output:
- writer = csv.writer(output)
- writer.writerow(INPUT_HEADER)
- for row in rows:
- if Decimal(row["金额"]) > Decimal("500"):
- writer.writerow([row[column] for column in INPUT_HEADER])
- if __name__ == "__main__":
- main()
|