Files
Card-data-sorting/expenses/csv_parsers/idemitsu.py

68 lines
2.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
from __future__ import annotations
import csv
import hashlib
from datetime import datetime
from typing import Iterable
from .base import CSVParserBase, ExpenseRow
class IdemitsuParser(CSVParserBase):
source = 'idemitsu'
def detect(self, header_line: str) -> bool:
return '出光' in header_line or '' in header_line
def parse(self, lines: Iterable[str]) -> list[ExpenseRow]:
rows: list[ExpenseRow] = []
reader = csv.reader(lines)
last_row_index: int | None = None
for columns in reader:
if not columns:
continue
head = columns[0].strip()
if head in ('カード名称', 'お支払日', '今回ご請求額'):
continue
if head == '利用日':
continue
if not head:
if last_row_index is not None:
extra_desc = columns[1].strip() if len(columns) > 1 else ''
extra_note = columns[6].strip() if len(columns) > 6 else ''
if extra_desc:
rows[last_row_index].description += f' {extra_desc}'
if extra_note:
if rows[last_row_index].note:
rows[last_row_index].note += f' {extra_note}'
else:
rows[last_row_index].note = extra_note
continue
if len(columns) < 6:
continue
try:
use_date = datetime.strptime(head, '%Y/%m/%d').date()
except ValueError:
continue
description = columns[1].strip()
amount_text = columns[5].replace(',', '').strip()
note = columns[6].strip() if len(columns) > 6 else ''
try:
amount = int(amount_text)
except ValueError:
continue
raw = f"{use_date.isoformat()}|{description}|{amount}|{note}|{self.source}"
source_hash = hashlib.sha256(raw.encode('utf-8')).hexdigest()
rows.append(
ExpenseRow(
use_date=use_date,
description=description,
amount=amount,
note=note,
source=self.source,
source_hash=source_hash,
)
)
last_row_index = len(rows) - 1
return rows