1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
|
# -*- coding: utf-8 -*-
import locale
import itertools
import csv
import re
from datetime import datetime
from contextlib import contextmanager
from ofxstatement.parser import StatementParser
from ofxstatement.plugin import Plugin
from ofxstatement.statement import Statement, StatementLine, generate_transaction_id
def take(iterable, n):
"""Return first n items of the iterable as a list."""
return list(itertools.islice(iterable, n))
def drop(iterable, n):
"""Drop first n items of the iterable and return result as a list."""
return list(itertools.islice(iterable, n, None))
def head(iterable):
"""Return first element of the iterable."""
return take(iterable, 1)[0]
@contextmanager
def scoped_setlocale(category, loc=None):
"""Scoped version of locale.setlocale()"""
orig = locale.getlocale(category)
try:
yield locale.setlocale(category, loc)
finally:
locale.setlocale(category, orig)
def atof(string, loc=None):
"""Locale aware atof function for our parser."""
with scoped_setlocale(locale.LC_NUMERIC, loc):
return locale.atof(string)
#
# Yeah, maybe CsvStatementParser is the right way to do it but we have some custom logic here
# that doesn't fit it nicely.
#
class AlfaBankStatementParser(StatementParser):
bank_id = 'AlfaBank'
date_format = '%d.%m.%y'
def __init__(self, fin, encoding=None, locale=None, brief=False):
self.locale = locale
self.encoding = encoding
self.brief = brief
with open(fin, 'r', encoding=self.encoding) as f:
self.lines = f.readlines()
self.validate()
self.statement = self.parse_statement()
@property
def reader(self):
return csv.reader(self.lines, delimiter=';')
@property
def header(self):
return head(self.reader)
@property
def rows(self):
return drop(self.reader, 1)
def validate(self):
"""
Validate to ensure csv has the same header we expect.
"""
expected = [
u"Тип счёта",
u"Номер счета",
u"Валюта",
u"Дата операции",
u"Референс проводки",
u"Описание операции",
u"Приход",
u"Расход",
u""
]
actual = self.header
if expected != actual:
msg = "\n".join([
"Header template doesn't match:",
"expected: %s" % expected,
"actual : %s" % actual
])
raise ValueError(msg)
def parse_statement(self):
"""
Parse statement object.
"""
account_ids = set()
for row in self.rows:
account_id = row[1]
account_ids.add(account_id)
if len(account_ids) < 1:
raise ValueError("No accounts found: %s" % account_ids)
if len(account_ids) > 1:
raise ValueError("More than one account found: %s" % account_ids)
currency_ids = set()
for row in self.rows:
currency_id = row[2]
currency_ids.add(currency_id)
if len(currency_ids) < 1:
raise ValueError("No currency found: %s" % currency_ids)
if len(currency_ids) > 1:
raise ValueError("More than one currency found: %s" % currency_ids)
return Statement(
bank_id=self.bank_id,
account_id=head(account_ids),
currency=head(currency_ids),
)
def split_records(self):
for row in self.rows:
yield row
def parse_record(self, row):
account_name, account_id, currency, date, refnum, description, debit, credit = take(row, 8)
stmt_line = StatementLine()
stmt_line.date = datetime.strptime(date, self.date_format)
stmt_line.memo = description
stmt_line.refnum = refnum
debit = atof(debit, self.locale)
credit = atof(credit, self.locale)
assert (debit > 0) ^ (credit > 0)
if debit > 0:
stmt_line.amount = debit
elif credit > 0:
stmt_line.amount = -1 * credit
else:
stmt_line.amount = 0.0
#
# Looks like AlfaBank formats description for card transactions so it includes the actual purchase date
# within e.g.
#
# 123456++++++7890 12312312\111\NOVOSIBIRSK\CHITAI GOROD 10.01.16 08.01.16 617.00 RUR
#
# we cleanup it (optionally) by leaving only the actual description part i.e.
#
# 12312312\111\NOVOSIBIRSK\CHITAI GOROD
#
if refnum.startswith("CRD"):
m = re.match('([0-9+]+) +(.+) +([0-9]{2}\.[0-9]{2}\.[0-9]{2}) ([0-9]{2}\.[0-9]{2}\.[0-9]{2}) +([0-9]+\.[0-9]+) +([^ ]+)', stmt_line.memo)
if m:
card_id, card_memo, _, card_date, card_amount, card_currency = m.groups()
if self.brief:
stmt_line.memo = card_memo
stmt_line.date_user = datetime.strptime(card_date, self.date_format)
stmt_line.id = generate_transaction_id(stmt_line)
return stmt_line
def parse_bool(value):
if value in ('True', 'true', '1'):
return True
if value in ('False', 'false', '0'):
return False
raise ValueError("Can't parse boolean value: %s" % value)
class AlfaBankPlugin(Plugin):
def get_parser(self, fin):
kwargs = {
'locale': 'ru_RU',
'encoding': 'cp1251',
}
if self.settings:
if 'brief' in self.settings:
kwargs['brief'] = parse_bool(self.settings.get('brief'))
if 'encoding' in self.settings:
kwargs['encoding'] = self.settings.get('encoding')
if 'locale' in self.settings:
kwargs['locale'] = self.settings.get('locale')
return AlfaBankStatementParser(fin, **kwargs)
|
