def test_extract_(tmpdir):
csv_path = path.join(tmpdir, "微信支付账单(20200830-20200906).csv")
with open(csv_path, "w", encoding="utf-8", newline="") as f:
f.write("\n" * 16)
writer = csv.writer(f)
writer.writerow(
"交易时间,交易类型,交易对方,商品,收/支,金额(元),支付方式,当前状态,交易单号,商户单号,备注".split(","))
writer.writerow([
"2020-09-06 23:19:24",
"零钱充值",
"招商银行(1111)",
"/",
"/",
"¥1.00",
"招商银行(1111)",
"充值完成",
233,
"/",
"/",
])
file = cache._FileMemo(csv_path)
importer: WechatImporter = get_importer("examples/wechat.import")
entries = importer.extract(file)
assert len(entries) == 1
txn = entries[0]
assert [x.account == importer.account
for x in txn.postings] == [True, False]
assert [x.units for x in txn.postings] == [
Amount(Decimal(1), "CNY"),
Amount(Decimal(-1), "CNY"),
]
assert txn.postings[1].account == "Assets:Bank:CMB:C1111"
def test_cache_head_obeys_explict_utf8_encoding_avoids_chardet_exception(self):
emoji_header = 'asciiHeader1,🍏Header1,asciiHeader2'.encode('utf-8')
with mock.patch('builtins.open',
mock.mock_open(read_data=emoji_header)):
try:
function_return = cache._FileMemo('anyFile').head(encoding='utf-8')
except UnicodeDecodeError:
self.fail("Failed to decode emoji")
def test_match(self, filename):
"""\
DATE,TYPE,REF #,DESCRIPTION,FEES,AMOUNT,BALANCE
2014-04-14,BUY,14167001,BOUGHT +CSKO 50 @98.35,7.95,-4925.45,25674.63
2014-05-08,BUY,12040838,BOUGHT +HOOL 121 @79.11,7.95,-9580.26,16094.37
2014-05-11,BUY,41579908,BOUGHT +MSFX 104 @64.39,7.95,-6704.51,9389.86
2014-05-22,DIV,54857517,ORDINARY DIVIDEND~HOOL,0,28.56,9418.42
"""
importer = SimpleTestImporter([
'Filename: .*te?mp.*', 'MimeType: text/', 'Contents:\n.*DATE,TYPE'
])
file = cache._FileMemo(filename)
self.assertTrue(importer.identify(file))
importer = SimpleTestImporter(
['Filename: .*te?mp.*', 'MimeType: text/xml'])
file = cache._FileMemo(filename)
self.assertFalse(importer.identify(file))
def test_importer_methods(self):
# Kind of a dumb test, but for consistency we just test everything.
memo = cache._FileMemo('/tmp/test')
imp = importer.ImporterProtocol()
self.assertIsInstance(imp.FLAG, str)
self.assertFalse(imp.identify(memo))
self.assertFalse(imp.extract(memo))
self.assertFalse(imp.file_account(memo))
self.assertFalse(imp.file_date(memo))
self.assertFalse(imp.file_name(memo))
def test_cache(self):
with tempfile.NamedTemporaryFile() as tmpfile:
shutil.copy(__file__, tmpfile.name)
wrap = cache._FileMemo(tmpfile.name)
# Check attributes.
self.assertEqual(tmpfile.name, wrap.name)
# Check that caching works.
converter = mock.MagicMock(return_value='abc')
self.assertEqual('abc', wrap.convert(converter))
self.assertEqual('abc', wrap.convert(converter))
self.assertEqual('abc', wrap.convert(converter))
self.assertEqual(1, converter.call_count)
def test_match(self, filename):
"""\
DATE,TYPE,REF #,DESCRIPTION,FEES,AMOUNT,BALANCE
2014-04-14,BUY,14167001,BOUGHT +CSKO 50 @98.35,7.95,-4925.45,25674.63
2014-05-08,BUY,12040838,BOUGHT +HOOL 121 @79.11,7.95,-9580.26,16094.37
"""
importer = fileonly.Importer(matchers=[
('filename', 'te?mp'), ('mime', 'text/'),
('content', 'DATE,TYPE,REF #,DESCRIPTION,FEES,AMOUNT')
],
filing='Assets:BofA:Checking',
prefix='bofa')
file = cache._FileMemo(filename)
self.assertTrue(importer.identify(file))
assert importer.file_name(file).startswith('bofa.')
def test_match(self, filename):
"""\
DATE,TYPE,REF #,DESCRIPTION,FEES,AMOUNT,BALANCE
2014-04-14,BUY,14167001,BOUGHT +CSKO 50 @98.35,7.95,-4925.45,25674.63
2014-05-08,BUY,12040838,BOUGHT +HOOL 121 @79.11,7.95,-9580.26,16094.37
"""
importer = fileonly.Importer([
'Filename: .*te?mp.*', 'MimeType: text/plain',
'Contents: .*DATE,TYPE,REF #,DESCRIPTION,FEES,AMOUNT'
],
'Assets:BofA:Checking',
basename='bofa')
file = cache._FileMemo(filename)
self.assertTrue(importer.identify(file))
self.assertEqual('bofa', importer.file_name(file))
def test_cache_head_and_contents(self):
with tempfile.NamedTemporaryFile() as tmpfile:
shutil.copy(__file__, tmpfile.name)
wrap = cache._FileMemo(tmpfile.name)
contents = wrap.convert(cache.contents)
self.assertIsInstance(contents, str)
self.assertGreater(len(contents), 128)
contents2 = wrap.contents()
self.assertEqual(contents, contents2)
head = wrap.convert(cache.head(128))
self.assertIsInstance(head, str)
self.assertEqual(128, len(head))
mimetype = wrap.convert(cache.mimetype)
self.assertRegex(mimetype, r'text/(x-(python|c\+\+)|plain)')
def main():
parser = CsvParser()
parser.add_argument('-o',
'--output',
default=None,
help="Output file path (For single file input only)")
parser.add_argument(
'-d',
'--directory',
default=".",
help="Export to an existing directory. Default in current directory.")
# parser.add_argument('-f', '--format',
# help="""Default value depends on --type argument.
# HangSeng: 11s58s35s25s24s
# MPower: 11s12s78s46s
# This is the number of bytes expected for each field. For
# example, for HangSeng, we expect Date(11), Title(58),
# Deposit(35), Withdraw(25), and Balance(24).
# Default value is set based on my statements. If it
# doesn't work as expected, use `--verbose` option and
# adjust format string until an aligned table is printed
# out.""")
parser.add_argument('-t',
'--type',
help="""Type of PDF.
Available types: HangSeng, MPower, DBS.""")
parser.add_argument('-v',
'--verbose',
default=False,
action="store_true",
help="More details.")
parser.add_argument('file',
nargs='+',
help='One or more PDF eStatements to process.')
args = parser.parse_args()
if args.output and len(args.file) > 1:
sys.exit(
"Output option can only be set with single file input. To export multiple files, use -d option."
)
for stmt in args.file:
print("Processing: {}".format(stmt))
if args.type.lower() == 'hangseng':
allrecords = HangSengSavingsImporter("Dummy:Account:Name",
"Dummy",
debug=args.verbose).extract(
_FileMemo(stmt))
elif args.type.lower() == 'mpower':
allrecords = MPowerMasterImporter("Dummy:Account:Name",
"Dummy",
debug=args.verbose).extract(
_FileMemo(stmt))
elif args.type.lower() == 'dbs':
allrecords = DBSImporter("Dummy:Account:Name",
"Dummy",
debug=args.verbose).extract(
_FileMemo(stmt))
output_path = args.output if args.output else path.join(
args.directory,
path.splitext(path.basename(stmt))[0] + ".csv")
print("Exporting to {}".format(output_path))
with open(output_path, mode='w') as csv_file:
csv_writer = csv.writer(csv_file,
delimiter=',',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
if args.type.lower() == 'hangseng':
csv_writer.writerow(["date", "title", "amount"])
for txn in allrecords:
csv_writer.writerow([
txn.date.isoformat(), txn.payee,
txn.postings[0].units.number
])
elif args.type.lower() == 'mpower':
csv_writer.writerow(
["trans_date", "post_date", "activity", "amount"])
for txn in allrecords:
csv_writer.writerow([
txn.meta['txn_date'],
txn.date.isoformat(), txn.narration,
txn.postings[0].units.number
])
elif args.type.lower() == 'dbs':
csv_writer.writerow(
["trans_date", "post_date", "description", "amount"])
for txn in allrecords:
csv_writer.writerow([
txn.meta['txn_date'],
txn.date.isoformat(), txn.narration,
txn.postings[0].units.number
])
return 0