Files
@ e764f3d0ef05
Branch filter:
Location: NPO-Accounting/conservancy_beancount/conservancy_beancount/reconcile/statement_reconciler.py
e764f3d0ef05
29.6 KiB
text/x-python
reconcile: Factor out the output formatting
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 | """Compare a bank CSV statement with the books.
This tool takes an AMEX or First Republic CSV statement file and compares it
line-by-line with the Beancount books to make sure that everything matches. This
is designed for situations where transactions are entered into the books
directly, rather than being imported from a statement after the fact.
The reconciler will attempt to match transactions based on date, amount, check
number and payee, but is forgiving to differences in dates, the absensce of
check number and inexact matches on payee. Matches are ranked, so where there is
only one decent match for an amount/date this is accepted, but if there are
multiple similar candidates it will refuse to guess.
The reconciler will also attempt to identify where a single statement entry has
been split out into multiple Beancount postings, such as a single bank transfer
representing health insurance for multiple employees.
Run it like this:
$ statement_reconciler \
--beancount-file 2021.beancount \
--account Liabilities:CreditCard:AMEX \
--csv-statement ~/svn/2021-09-10_AMEX_activity.csv \
--bank-statement ~/svn/2021-09-10_AMEX_activity.pdf
Background:
Regular Beancount users often write automated importers to create bookkeeping
entries direct from a bank statement or similar. That combines data entry and
reconciliation in one step. Conservancy uses a different approach; they manually
entering transactions and reconciling them later on. This workflow is helpful in
cases like writing checks (see below). This is the workflow implented by this
tool.
That said, this tool *is* still somewhat like an importer in that it needs to
extract transaction details from a third-party statement. Instead of creating
directives, it just checks to see that similar directives are already
present. This is a bit like diff-ing a statement with the books (though we're
only interested in the presence of lines, not so much their order).
Paper checks are entered into the books when written (a.k.a. "posted"), but may
not be cashed until months later sometimes causing reconciliation differences
that live beyond a month. It's worth noting that there are really two dates here
- the posting date and the cleared date. Beancount only allows us to model one,
which is why carrying these reconciliation differences between months feels a
bit awkward.
Problems in scope:
- errors in the books take hours to find during reconciliation, requiring
manually comparing statements and the books and are succeptible to mistakes,
such as not noticing when there are two payments for the same amount on the
statement, but not in the books (as Bradley likes to quote, "you're entering
a world of pain")
- adding statement/reconciliation metadata to books is/was manual and prone to
mistakes
- jumping to an individual transaction in a large ledger isn't trivial - Emacs
grep mode is the current best option
- not all staff use Emacs
- auditors would prefer Bradley didn't perform reconciliation, ideally not
Rosanne either
- reconciliation reports are created by hand when there are mismatches
Other related problems we're not dealing with here:
- after updates to the books files, beancount must be restarted to reflect
updates
- updates also invalidate the cache meaning restart takes several minutes
- balance checks are manually updated in
svn/Financial/Ledger/sanity-check-balances.yaml
- transactions are entered manually and reconciled after the fact, but
importing from statements may be useful in some cases
Current issue:
- entry_point seems to swallow errors, meaning you get a fairly unhelpful
message if there's an unhandled error
Future possibilities:
- allow the reconciler to respect manually-applied metadata - not clear how
this would work exactly
- allow interactive matching where the user can specifiy a match
- consider combining this with helper.py into one more complete tool that both
reconciles and summarises the unreconciled transactions
"""
import argparse
import collections
import copy
import csv
import datetime
import decimal
import io
import itertools
import logging
import os
import re
import sys
from typing import Dict, List, Optional, Sequence, Tuple, TextIO
from beancount import loader
from beancount.query.query import run_query
from colorama import Fore, Style # type: ignore
from .. import cliutil
from .. import config as configmod
if not sys.warnoptions:
import warnings
# Disable annoying warning from thefuzz prompting for a C extension. The
# current pure-Python implementation isn't a bottleneck for us.
warnings.filterwarnings('ignore', category=UserWarning, module='thefuzz.fuzz')
from thefuzz import fuzz # type: ignore
PROGNAME = 'reconcile-statement'
logger = logging.getLogger(__name__)
# Get some interesting feedback on call to RT with this:
# logger.setLevel(logging.DEBUG)
# logger.addHandler(logging.StreamHandler())
JUNK_WORDS = [
'software',
'freedom',
'conservancy',
'conse',
'payment',
'echeck',
'bill',
'debit',
'wire',
'credit',
"int'l",
"in.l",
'llc',
'online',
'donation',
'usd',
'inc',
]
JUNK_WORDS_RES = [re.compile(word, re.IGNORECASE) for word in JUNK_WORDS]
ZERO_RE = re.compile('^0+')
FULL_MATCH_THRESHOLD = 0.8
PARTIAL_MATCH_THRESHOLD = 0.4
def remove_duplicate_words(text: str) -> str:
unique_words = []
known_words = set()
for word in text.split():
if word.lower() not in known_words:
unique_words.append(word)
known_words.add(word.lower())
return ' '.join(unique_words)
def remove_payee_junk(payee: str) -> str:
"""Clean up payee field to improve quality of fuzzy matching.
It turns out that bank statement "description" fields are
difficult to fuzzy match on because they're long and
noisey. Truncating them (see standardize_XXX_record fns) and
removing the common junk helps significantly.
"""
for r in JUNK_WORDS_RES:
payee = r.sub('', payee)
payee = ZERO_RE.sub('', payee)
payee = payee.replace(' - ', ' ')
payee = re.sub(r'\.0\.\d+', ' ', payee)
payee = payee.replace('.0', ' ')
payee = payee.replace('/', ' ')
payee = re.sub(re.escape('.com'), ' ', payee, flags=re.IGNORECASE)
payee = re.sub(re.escape('.net'), ' ', payee, flags=re.IGNORECASE)
payee = payee.replace('*', ' ')
payee = ' '.join([i for i in payee.split(' ') if len(i) > 2])
payee = payee.replace('-', ' ')
payee = remove_duplicate_words(payee)
payee.strip()
return payee
def parse_amount(amount: str) -> decimal.Decimal:
"""Parse amounts and handle comma separators as seen in some FR statements."""
return decimal.Decimal(amount.replace('$', '').replace(',', ''))
def validate_amex_csv(sample: str) -> None:
required_cols = {'Date', 'Amount', 'Description', 'Card Member'}
reader = csv.DictReader(io.StringIO(sample))
if reader.fieldnames and not required_cols.issubset(reader.fieldnames):
sys.exit(f"This AMEX CSV doesn't seem to have the columns we're expecting, including: {', '.join(required_cols)}. Please use an unmodified statement direct from the institution.")
def standardize_amex_record(row: Dict, line: int) -> Dict:
"""Turn an AMEX CSV row into a standard dict format representing a transaction."""
# NOTE: Statement doesn't seem to give us a running balance or a final total.
return {
'date': datetime.datetime.strptime(row['Date'], '%m/%d/%Y').date(),
'amount': -1 * parse_amount(row['Amount']),
# Descriptions have too much noise, so taking just the start
# significantly assists the fuzzy matching.
'payee': remove_payee_junk(row['Description'] or '')[:20],
'check_id': '',
'line': line,
}
def read_amex_csv(f: TextIO) -> list:
reader = csv.DictReader(f)
# The reader.line_num is the source line number, not the spreadsheet row
# number due to multi-line records.
return sort_records([standardize_amex_record(row, i) for i, row in enumerate(reader, 2)])
def validate_fr_csv(sample: str) -> None:
# No column headers in FR statements
reader = csv.reader(io.StringIO(sample))
next(reader) # First row is previous statement ending balance
row = next(reader)
date = None
try:
date = datetime.datetime.strptime(row[1], '%m/%d/%Y')
except ValueError:
pass
amount_found = '$' in row[4] and '$' in row[5]
if len(row) != 6 or not date or not amount_found:
sys.exit("This First Republic CSV doesn't seem to have the 6 columns we're expecting, including a date in column 2 and an amount in columns 5 and 6. Please use an unmodified statement direct from the institution.")
def standardize_fr_record(line, row):
record = {
'date': datetime.datetime.strptime(row[1], '%m/%d/%Y').date(),
'amount': parse_amount(row[4]),
'payee': remove_payee_junk(row[3] or '')[:20],
'check_id': row[2].replace('CHECK ', '') if 'CHECK ' in row[2] else '',
'line': line,
}
return record
def read_fr_csv(f: TextIO) -> list:
reader = csv.reader(f)
# The reader.line_num is the source line number, not the spreadsheet row
# number due to multi-line records.
return sort_records(
standardize_fr_record(i, row) for i, row in enumerate(reader, 1)
if len(row) == 6 and row[2] not in {'LAST STATEMENT', 'THIS STATEMENT'}
)
def standardize_beancount_record(row) -> Dict: # type: ignore[no-untyped-def]
"""Turn a Beancount query result row into a standard dict representing a transaction."""
return {
'date': row.date,
'amount': row.number_cost_position,
'payee': remove_payee_junk(f'{row.payee or ""} {row.entity or ""} {row.narration or ""}'),
'check_id': str(row.check_id or ''),
'filename': row.filename,
'line': row.line,
'bank_statement': row.bank_statement,
}
def format_record(record: dict) -> str:
"""Generate output lines for a standard 1:1 match."""
if record['payee'] and record['check_id']:
output = f"{record['date'].isoformat()}: {record['amount']:11,.2f} {record['payee'][:25]} #{record['check_id']}".ljust(59)
elif record['payee']:
output = f"{record['date'].isoformat()}: {record['amount']:11,.2f} {record['payee'][:35]}".ljust(59)
else:
output = f"{record['date'].isoformat()}: {record['amount']:11,.2f} #{record['check_id']}".ljust(59)
return output
def format_multirecord(r1s: List[dict], r2s: List[dict], note: str) -> List[list]:
"""Generates output lines for one statement:multiple books transaction match."""
assert len(r1s) == 1
assert len(r2s) > 1
match_output = []
match_output.append([r1s[0]['date'], f'{format_record(r1s[0])} → {format_record(r2s[0])} ✓ Matched{note}'])
for r2 in r2s[1:]:
match_output.append([r1s[0]['date'], f'{r1s[0]["date"].isoformat()}: ↳ → {format_record(r2)} ✓ Matched{note}'])
return match_output
def sort_records(records: List) -> List:
return sorted(records, key=lambda x: (x['date'], x['amount']))
def first_word_exact_match(a: str, b: str) -> float:
"""Score a payee match based first word.
We get a whole lot of good matches this way. Helps in the
situation where the first word or two of a transaction description
is useful and the rest is garbage.
"""
if len(a) == 0 or len(b) == 0:
return 0.0
first_a = a.split()[0].strip()
first_b = b.split()[0].strip()
if first_a.casefold() == first_b.casefold():
return min(1.0, 0.2 * len(first_a))
else:
return 0.0
def payee_match(a: str, b: str) -> float:
"""Score a match between two payees."""
fuzzy_match = float(fuzz.token_set_ratio(a, b) / 100.00)
first_word_match = first_word_exact_match(a, b)
return max(fuzzy_match, first_word_match)
def records_match(r1: Dict, r2: Dict) -> Tuple[float, List[str]]:
"""Do these records represent the same transaction?"""
date_score = date_proximity(r1['date'], r2['date'])
if r1['date'] == r2['date']:
date_message = ''
elif date_score > 0.0:
diff = abs((r1['date'] - r2['date']).days)
date_message = f'+/- {diff} days'
else:
date_message = 'date mismatch'
if r1['amount'] == r2['amount']:
amount_score, amount_message = 2.0, ''
else:
amount_score, amount_message = 0.0, 'amount mismatch'
# We never consider payee if there's a check_id in the books.
check_message = ''
payee_message = ''
# Sometimes we get unrelated numbers in the statement column with check-ids,
# so we can't match based on the existence of a statement check-id.
if r2['check_id']:
payee_score = 0.0
if r1['check_id'] and r2['check_id'] and r1['check_id'] == r2['check_id']:
check_score = 1.0
else:
check_message = 'check-id mismatch'
check_score = 0.0
else:
check_score = 0.0
payee_score = payee_match(r1['payee'], r2['payee'])
if payee_score > FULL_MATCH_THRESHOLD:
payee_message = ''
elif payee_score > PARTIAL_MATCH_THRESHOLD:
payee_message = 'partial payee match'
else:
payee_message = 'payee mismatch'
overall_score = (date_score + amount_score + check_score + payee_score) / 4
overall_message = [m for m in [date_message, amount_message, check_message, payee_message] if m]
return overall_score, overall_message
def match_statement_and_books(statement_trans: List[Dict], books_trans: List[Dict]) -> Tuple[List[Tuple[List, List, List]], List[Dict], List[Dict]]:
"""Match transactions between the statement and books.
If matched, the books transaction is marked off so that it can
only be matched once. Some transactions will be matched, some will
be on the statement but not the books and some on the books but
not the statement.
Passes through any unmatched transactions.
Currently we use the same matching logic for all types of
statements. It's conceivable that you could have special cases to
accurately match some types of statements, but that would be more
work to maintain and test.
"""
matches = []
remaining_books_trans = []
remaining_statement_trans = []
for r1 in statement_trans:
best_match_score = 0.0
best_match_index = None
best_match_note = []
matches_found = 0
for i, r2 in enumerate(books_trans):
score, note = records_match(r1, r2)
if score >= 0.5 and score >= best_match_score:
matches_found += 1
best_match_score = score
best_match_index = i
best_match_note = note
if best_match_score > 0.5 and matches_found == 1 and 'check-id mismatch' not in best_match_note or best_match_score > 0.8:
matches.append(([r1], [books_trans[best_match_index]], best_match_note))
# Don't try to make a second match against this books entry.
if best_match_index is not None:
del books_trans[best_match_index]
else:
remaining_statement_trans.append(r1)
for r2 in books_trans:
remaining_books_trans.append(r2)
return matches, remaining_statement_trans, remaining_books_trans
def subset_match(statement_trans: List[dict], books_trans: List[dict]) -> Tuple[List[Tuple[List, List, List]], List[Dict], List[Dict]]:
"""Match single statement transactions with multiple books transactions.
Works similarly to match_statement_and_books in that it returns a
list of matches and lists of remaining statement and books
transactions.
"""
matches = []
remaining_books_trans = []
remaining_statement_trans = []
groups = itertools.groupby(books_trans, key=lambda x: (x['date'], x['payee']))
for _, group in groups:
best_match_score = 0.0
best_match_index = None
best_match_note = []
matches_found = 0
group_items = list(group)
total = sum(x['amount'] for x in group_items)
r2 = copy.copy(group_items[0])
r2['amount'] = total
for i, r1 in enumerate(statement_trans):
score, note = records_match(r1, r2)
if score >= 0.5 and score >= best_match_score:
matches_found += 1
best_match_score = score
best_match_index = i
best_match_note = note
if best_match_score > 0.5 and matches_found == 1 and 'check-id mismatch' not in best_match_note or best_match_score > 0.8:
matches.append(([statement_trans[best_match_index]], group_items, best_match_note))
if best_match_index is not None:
del statement_trans[best_match_index]
else:
remaining_books_trans.append(r2)
for r1 in statement_trans:
remaining_statement_trans.append(r1)
return matches, remaining_statement_trans, remaining_books_trans
# TODO: Return list of tuples (instead of list of lists).
def format_matches(matches: List, csv_statement: str, show_reconciled_matches: bool) -> List[List]:
"""Produce a list of body output lines from the given matches.
The first column is a date so we can re-sort the list to put the
missing entries in the right place. The second column is the text
output.
"""
match_output = []
for r1s, r2s, note in matches:
note = ', '.join(note)
note = ': ' + note if note else note
if r1s and r2s:
if show_reconciled_matches or not all(x['bank_statement'] for x in r2s):
if len(r2s) == 1:
entry = [r1s[0]['date'], f'{format_record(r1s[0])} → {format_record(r2s[0])} ✓ Matched{note}']
if 'payee mismatch' in note:
entry[1] = Fore.YELLOW + Style.BRIGHT + entry[1] + Style.RESET_ALL
match_output.append(entry)
else:
match_output.extend(format_multirecord(r1s, r2s, note))
elif r1s:
match_output.append([r1s[0]['date'], Fore.RED + Style.BRIGHT + f'{format_record(r1s[0])} → {" ":^59} ✗ NOT IN BOOKS ({os.path.basename(csv_statement)}:{r1s[0]["line"]})' + Style.RESET_ALL])
else:
match_output.append([r2s[0]['date'], Fore.RED + Style.BRIGHT + f'{" ":^59} → {format_record(r2s[0])} ✗ NOT ON STATEMENT ({os.path.basename(r2s[0]["filename"])}:{r2s[0]["line"]})' + Style.RESET_ALL])
return match_output
def date_proximity(d1: datetime.date, d2: datetime.date) -> float:
"""Scores two days based on how close they are together."""
ZERO_CUTOFF = 60 # Score will be zero for this many days apart.
diff = abs(int((d1 - d2).days))
if diff >= ZERO_CUTOFF:
return 0.0
else:
return 1.0 - (diff / ZERO_CUTOFF)
def metadata_for_match(match: Tuple[List, List, List], statement_filename: str, csv_filename: str) -> List[Tuple[str, int, str]]:
"""Returns the bank-statement metadata that should be applied for a match."""
# TODO: Our data structure would allow multiple statement entries
# for a match, but would this ever make sense? Probably not.
statement_filename = get_repo_relative_path(statement_filename)
csv_filename = get_repo_relative_path(csv_filename)
metadata = []
statement_entries, books_entries, _ = match
for books_entry in books_entries:
for statement_entry in statement_entries:
if not books_entry['bank_statement']:
metadata.append((books_entry['filename'], books_entry['line'], f' bank-statement: "{statement_filename}"'))
metadata.append((books_entry['filename'], books_entry['line'], f' bank-statement-csv: "{csv_filename}:{statement_entry["line"]}"'))
return metadata
def write_metadata_to_books(metadata_to_apply: List[Tuple[str, int, str]]) -> None:
"""Insert reconciliation metadata in the books files.
Takes a list of edits to make as tuples of form (filename, lineno, metadata):
[
('2021/main.beancount', 4245, ' bank-statement: statement.pdf'),
('2021/main.beancount', 1057, ' bank-statement: statement.pdf'),
('2021/payroll.beancount', 257, ' bank-statement: statement.pdf'),
...,
]
Beancount doesn't provide any infrastructure for programmatically
updating the books, only appending in the case of importers. So
we're on our own here.
"""
file_contents: dict[str, list] = {}
file_offsets: dict[str, int] = collections.defaultdict(int)
# Load each books file into memory and insert the relevant metadata lines.
# Line numbers change as we do this, so we keep track of the offset for each
# file. Changes must be sorted by line number first or else the offsets will
# break because we're jumping around making edits.
for filename, line, metadata in sorted(metadata_to_apply):
if filename not in file_contents:
with open(filename, 'r') as f:
file_contents[filename] = f.readlines()
# Insert is inefficient, but fast enough for now in practise.
file_contents[filename].insert(line + file_offsets[filename], metadata.rstrip() + '\n')
file_offsets[filename] += 1
# Writes each updated file back to disk.
for filename, contents in file_contents.items():
with open(filename, 'w') as f:
f.writelines(contents)
print(f'Wrote {filename}.')
def get_repo_relative_path(path: str) -> str:
"""Chop off the unique per-person CONSERVANCY_REPOSITORY.
CSV and PDF statement metadata should be relative to
CONSERVANCY_REPOSITORY ie. without regards to exactly where on
your computer all the files live.
"""
return os.path.relpath(path, start=os.getenv('CONSERVANCY_REPOSITORY'))
def parse_path(path: str) -> str:
"""Validate that a file exists for use in argparse."""
if not os.path.exists(path):
raise argparse.ArgumentTypeError(f'File {path} does not exist.')
return path
def parse_repo_relative_path(path: str) -> str:
"""Validate that a file exists and is within $CONSERVANCY_REPOSITORY.
For use with argparse.
"""
if not os.path.exists(path):
raise argparse.ArgumentTypeError(f'File {path} does not exist.')
repo = os.getenv('CONSERVANCY_REPOSITORY')
if not repo:
raise argparse.ArgumentTypeError('$CONSERVANCY_REPOSITORY is not set.')
if not path.startswith(repo):
raise argparse.ArgumentTypeError(f'File {path} does not share a common prefix with $CONSERVANCY_REPOSITORY {repo}.')
return path
def parse_decimal_with_separator(number_text: str) -> decimal.Decimal:
"""decimal.Decimal can't parse numbers with thousands separator."""
number_text = number_text.replace(',', '')
return decimal.Decimal(number_text)
def parse_arguments(argv: List[str]) -> argparse.Namespace:
parser = argparse.ArgumentParser(prog=PROGNAME, description='Reconciliation helper')
cliutil.add_version_argument(parser)
cliutil.add_loglevel_argument(parser)
parser.add_argument('--beancount-file', required=True, type=parse_path)
parser.add_argument('--csv-statement', required=True, type=parse_repo_relative_path)
parser.add_argument('--bank-statement', required=True, type=parse_repo_relative_path)
parser.add_argument('--account', required=True, help='eg. Liabilities:CreditCard:AMEX')
# parser.add_argument('--report-group-regex')
parser.add_argument('--show-reconciled-matches', action='store_true')
parser.add_argument('--non-interactive', action='store_true', help="Don't prompt to write to the books") # parser.add_argument('--statement-balance', type=parse_decimal_with_separator, required=True, help="A.K.A \"cleared balance\" taken from the end of the period on the PDF statement. Required because CSV statements don't include final or running totals")
args = parser.parse_args(args=argv)
return args
def totals(matches: List[Tuple[List, List, List]]) -> Tuple[decimal.Decimal, decimal.Decimal, decimal.Decimal]:
"""Calculate the totals of transactions matched/not-matched."""
total_matched = decimal.Decimal(0)
total_missing_from_books = decimal.Decimal(0)
total_missing_from_statement = decimal.Decimal(0)
for statement_entries, books_entries, _ in matches:
if statement_entries and books_entries:
total_matched += sum(c['amount'] for c in statement_entries)
elif statement_entries:
total_missing_from_books += sum(c['amount'] for c in statement_entries)
else:
total_missing_from_statement += sum(c['amount'] for c in books_entries)
return total_matched, total_missing_from_books, total_missing_from_statement
def process_unmatched(statement_trans: List[dict], books_trans: List[dict]) -> List[Tuple[List, List, List]]:
"""Format the remaining unmatched transactions to be added to one single list of matches."""
matches: List[Tuple[List, List, List]] = []
for r1 in statement_trans:
matches.append(([r1], [], ['no match']))
for r2 in books_trans:
matches.append(([], [r2], ['no match']))
return matches
def format_output(matches, begin_date, end_date, csv_statement, show_reconciled_matches) -> str:
with io.StringIO() as out:
match_output = format_matches(matches, csv_statement, show_reconciled_matches)
_, total_missing_from_books, total_missing_from_statement = totals(matches)
print('-' * 155, file=out)
statement_heading = f'Statement transactions {begin_date} to {end_date}'
print(f'{statement_heading:<52} {"Books transactions":<58} Notes', file=out)
print('-' * 155, file=out)
for _, output in sorted(match_output, key=lambda x: x[0]):
print(output, file=out)
print('-' * 155, file=out)
print(f'Sub-total not on statement: {total_missing_from_statement:12,.2f}', file=out)
print(f'Sub-total not in books: {total_missing_from_books:12,.2f}', file=out)
print(f'Total: {total_missing_from_statement + total_missing_from_books:12,.2f}', file=out)
print('-' * 155, file=out)
return out.getvalue()
def main(arglist: Optional[Sequence[str]] = None,
stdout: TextIO = sys.stdout,
stderr: TextIO = sys.stderr,
config: Optional[configmod.Config] = None,
) -> int:
args = parse_arguments(arglist)
cliutil.set_loglevel(logger, args.loglevel)
if config is None:
config = configmod.Config()
config.load_file()
# Validate and normalise the statement into our standard
# transaction data structure.
if 'AMEX' in args.account:
validate_csv = validate_amex_csv
read_csv = read_amex_csv
else:
validate_csv = validate_fr_csv
read_csv = read_fr_csv
with open(args.csv_statement) as f:
sample = f.read(200)
# Validate should return true/false and a message.
validate_csv(sample)
f.seek(0)
# TODO: Needs a custom read_transactions_from_csv for each of AMEX and
# FR since AMEX has a header row and FR doesn't.
statement_trans = read_csv(f)
# Dates are taken from the beginning/end of the statement.
begin_date = statement_trans[0]['date']
end_date = statement_trans[-1]['date']
# Query for the Beancount books data for this above period.
#
# There are pros and cons for using Beancount's in-memory entries
# list directly and also for using Beancount Query Language (BQL)
# to get a list of transactions? Using BQL because it's
# convenient, but we don't have access to the full transaction
# entry objects. Feels a bit strange that these approaches are so
# disconnected.
#
# beancount.query.query_compile.compile() and
# beancount.query.query_execute.filter_entries() look useful in this respect,
# but I'm not clear on how to use compile(). An example would help.
entries, _, options = loader.load_file(args.beancount_file)
# String concatenation looks bad, but there's no SQL injection possible here
# because BQL can't write back to the Beancount files. I hope!
query = f'SELECT filename, META("lineno") AS line, META("bank-statement") AS bank_statement, date, number(cost(position)), payee, ENTRY_META("entity") as entity, ANY_META("check-id") as check_id, narration where account = "{args.account}" and date >= {begin_date} and date <= {end_date}'
_, result_rows = run_query(entries, options, query)
books_trans = sort_records([standardize_beancount_record(row) for row in result_rows])
# Apply two passes of matching, one for standard matches and one
# for subset matches.
matches, remaining_statement_trans, remaining_books_trans = match_statement_and_books(statement_trans, books_trans)
subset_matches, remaining_statement_trans, remaining_books_trans = subset_match(
remaining_statement_trans, remaining_books_trans)
matches.extend(subset_matches)
# Add the remaining unmatched to make one big list of matches, successful or not.
unmatched = process_unmatched(remaining_statement_trans, remaining_books_trans)
matches.extend(unmatched)
# Print out results of our matching.
print(format_output(matches, begin_date, end_date, args.csv_statement, args.show_reconciled_matches))
# Write statement metadata back to the books.
metadata_to_apply = []
for match in matches:
metadata_to_apply.extend(metadata_for_match(match, args.bank_statement, args.csv_statement))
if metadata_to_apply and not args.non_interactive:
print('Mark matched transactions as reconciled in the books? (y/N) ', end='')
if input().lower() == 'y':
write_metadata_to_books(metadata_to_apply)
entry_point = cliutil.make_entry_point(__name__, PROGNAME)
if __name__ == '__main__':
exit(entry_point())
|