msmoney2squirrel.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# EDIT HERE!
OUTPUT_DIR = '/tmp/'

# --- From: http://docs.python.org/library/csv.html
# --- BEGIN
import csv, codecs, cStringIO

class UTF8Recoder:
    """
    Iterator that reads an encoded stream and reencodes the input to UTF-8
    """
    def __init__(self, f, encoding):
        self.reader = codecs.getreader(encoding)(f)

    def __iter__(self):
        return self

    def next(self):
        return self.reader.next().encode("utf-8")

class UnicodeReader:
    """
    A CSV reader which will iterate over lines in the CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        f = UTF8Recoder(f, encoding)
        self.reader = csv.reader(f, dialect=dialect, **kwds)

    def next(self):
        row = self.reader.next()
        return [unicode(s, "utf-8") for s in row]

    def __iter__(self):
        return self

class UnicodeWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([s.encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)
# --- END

import sys

def main():
    if len(sys.argv) <= 1:
        print "filename not specified."
        sys.exit()
    reader = UnicodeReader(file(sys.argv[1], 'rU'), encoding='cp932')

    # Ultrasoft MoneyLink emits:
    # [0] 番号
    # [1] 日付
    # [2] 資産
    # [3] 摘要
    # [4] 照合
    # [5] 金額
    # [6] 費目
    # [7] 内訳
    # [8] 備考
    data = {}
    for row in reader:
        account = row[2]
        if account == u'資産':
            continue
        if not account in data:
            data[account] = [
                # [u'日付',u'説明',u'合計',u'メモ',u'カテゴリ']
                ]
        if not row[3]:
            row[3] = row[7]
        data[account].append([
                row[1], row[3], row[5], row[8], row[6] + ' : ' + row[7]
                ])
    for account in data.keys():
        filename = OUTPUT_DIR + account + '.csv'
        writer = UnicodeWriter(file(filename, 'w'), encoding='utf-8')
        writer.writerows(data[account])
        print filename+' created.'

if __name__ == "__main__":
    main()