Files
@ efe9bd88550d
Branch filter:
Location: NPO-Accounting/conservancy_beancount/conservancy_beancount/reports/ledger.py
efe9bd88550d
20.5 KiB
text/x-python
ledger: Change default report dates.
The old defaults were optimized for the audit report.
The new defaults provide more helpful ad hoc reports.
The latter will be run more often and more quickly, so it's
worth optimizing the defaults for them.
The old defaults were optimized for the audit report.
The new defaults provide more helpful ad hoc reports.
The latter will be run more often and more quickly, so it's
worth optimizing the defaults for them.
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 | """ledger.py - General ledger report from Beancount
This tool produces a spreadsheet that shows postings in Beancount, organized
by account.
Specify the date range you want to report with the ``--begin`` and ``--end``
options.
Select the accounts you want to report with the ``--account`` option. You can
specify this option multiple times. The report will include at least one sheet
for each account you specify. Subaccounts will be reported on that sheet as
well.
Select the postings you want to report by passing metadata search terms in
``name=value`` format.
Run ``ledger-report --help`` for abbreviations and other options.
Examples
--------
Report all activity related to a given project::
ledger-report project=NAME
Get all Assets postings for a given month to help with reconciliation::
ledger-report -a Assets -b 2018-05-01 -e 2018-06-01
"""
# Copyright © 2020 Brett Smith
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
import argparse
import collections
import datetime
import enum
import itertools
import operator
import logging
import sys
from typing import (
Callable,
Dict,
Iterable,
Iterator,
List,
Mapping,
Optional,
Sequence,
TextIO,
Tuple,
)
from pathlib import Path
import odf.table # type:ignore[import]
from beancount.parser import printer as bc_printer
from . import core
from .. import books
from .. import cliutil
from .. import config as configmod
from .. import data
from .. import ranges
from .. import rtutil
PostTally = List[Tuple[int, data.Account]]
PROGNAME = 'ledger-report'
logger = logging.getLogger('conservancy_beancount.reports.ledger')
class LedgerODS(core.BaseODS[data.Posting, data.Account]):
CORE_COLUMNS: Sequence[str] = [
'Date',
data.Metadata.human_name('entity'),
'Description',
'Original Amount',
'Booked Amount',
]
ACCOUNT_COLUMNS: Dict[str, Sequence[str]] = collections.OrderedDict([
('Income', ['project', 'rt-id', 'receipt', 'income-type']),
('Expenses', ['project', 'rt-id', 'receipt', 'approval', 'expense-allocation']),
('Equity', ['rt-id']),
('Assets:Receivable', ['project', 'rt-id', 'invoice', 'approval', 'contract', 'purchase-order']),
('Liabilities:Payable', ['project', 'rt-id', 'invoice', 'approval', 'contract', 'purchase-order']),
('Assets:PayPal', ['rt-id', 'paypal-id', 'receipt', 'approval']),
('Assets', ['rt-id', 'receipt', 'approval', 'bank-statement']),
('Liabilities', ['rt-id', 'receipt', 'approval', 'bank-statement']),
])
COLUMN_STYLES: Mapping[str, str] = {
'Date': '',
'Description': 'col_1_75',
data.Metadata.human_name('paypal-id'): 'col_1_5',
}
# Excel 2003 was limited to 65,536 rows per worksheet.
# While we can probably count on all our users supporting more modern
# formats (Excel 2007 supports over 1 million rows per worksheet),
# keeping the default limit conservative seems good to avoid running into
# other limits (like the number of hyperlinks per worksheet), plus just
# better for human organization and readability.
SHEET_SIZE = 65000
def __init__(self,
start_date: datetime.date,
stop_date: datetime.date,
sheet_names: Optional[Sequence[str]]=None,
rt_wrapper: Optional[rtutil.RT]=None,
sheet_size: Optional[int]=None,
) -> None:
if sheet_names is None:
sheet_names = list(self.ACCOUNT_COLUMNS)
if sheet_size is None:
sheet_size = self.SHEET_SIZE
super().__init__(rt_wrapper)
self.date_range = ranges.DateRange(start_date, stop_date)
self.required_sheet_names = sheet_names
self.sheet_size = sheet_size
@classmethod
def _group_tally(
cls,
tally_by_account: PostTally,
key: Callable[[data.Account], Optional[str]],
) -> Dict[str, PostTally]:
retval: Dict[str, PostTally] = collections.defaultdict(list)
for count, account in tally_by_account:
item_key = key(account)
if item_key is not None:
retval[item_key].append((count, account))
return retval
@classmethod
def _split_sheet(
cls,
tally_by_account: PostTally,
sheet_size: int,
sheet_name: str,
) -> Iterator[str]:
total = 0
for index, (count, account) in enumerate(tally_by_account):
total += count
if total > sheet_size:
break
else:
# All the accounts fit in this sheet.
yield sheet_name
return
if index == 0 and len(tally_by_account) == 1:
# With one account, we can't split any further, so warn and stop.
logger.warning(
"%s has %s rows, over size %s",
account, f'{count:,g}', f'{sheet_size:,g}',
)
yield sheet_name
return
group_func = operator.methodcaller('root_part', sheet_name.count(':') + 2)
maybe_split = cls._group_tally(tally_by_account[:index], group_func)
must_split = cls._group_tally(tally_by_account[index:], group_func)
for subkey, must_split_tally in sorted(must_split.items()):
split_names = cls._split_sheet(
maybe_split.get(subkey, []) + must_split_tally, sheet_size, subkey,
)
# We must be willing to split out at least as many sheets as there
# are accounts that didn't fit. Do that first.
yield from itertools.islice(split_names, len(must_split_tally))
# After that, we can be in one of two cases:
# 1. There is no next sheet. All the accounts, including the
# maybe_splits and must_splits, fit on planned subsheets.
# Update state to note we don't need a sheet for them anymore.
# 2. The next sheet is named `subkey`, and is planned to include
# all of our maybe_split accounts. However, we don't need to
# yield that sheet name, because those accounts already fit in
# the sheet we're planning, and it would be a needless split.
next_sheet_name = next(split_names, None)
if next_sheet_name is None:
maybe_split.pop(subkey, None)
else:
assert next_sheet_name == subkey
assert not any(split_names)
if maybe_split:
yield sheet_name
@classmethod
def plan_sheets(
cls,
tally_by_account: Mapping[data.Account, int],
base_sheets: Sequence[str],
sheet_size: int,
) -> Sequence[str]:
sorted_tally: PostTally = [
(count, account)
for account, count in tally_by_account.items()
]
sorted_tally.sort()
split_tally = cls._group_tally(
sorted_tally,
operator.methodcaller('is_under', *base_sheets),
)
return [
sheet_name
for key in base_sheets
for sheet_name in cls._split_sheet(split_tally[key], sheet_size, key)
]
@staticmethod
def _sort_and_filter_accounts(
accounts: Iterable[data.Account],
order: Sequence[str],
) -> Iterator[Tuple[int, data.Account]]:
index_map = {s: ii for ii, s in enumerate(order)}
retval: Mapping[int, List[data.Account]] = collections.defaultdict(list)
for account in accounts:
acct_key = account.is_under(*order)
if acct_key is not None:
retval[index_map[acct_key]].append(account)
for key in sorted(retval):
acct_list = retval[key]
acct_list.sort()
for account in acct_list:
yield key, account
def section_key(self, row: data.Posting) -> data.Account:
return row.account
def start_sheet(self, sheet_name: str) -> None:
self.use_sheet(sheet_name.replace(':', ' '))
columns_key = data.Account(sheet_name).is_under(*self.ACCOUNT_COLUMNS)
# columns_key must not be None because ACCOUNT_COLUMNS has an entry
# for all five root accounts.
assert columns_key is not None
self.metadata_columns = self.ACCOUNT_COLUMNS[columns_key]
self.sheet_columns: Sequence[str] = [
*self.CORE_COLUMNS,
*(data.Metadata.human_name(meta_key) for meta_key in self.metadata_columns),
]
for col_name in self.sheet_columns:
self.sheet.addElement(odf.table.TableColumn(
stylename=self.COLUMN_STYLES.get(col_name, 'col_1_25'),
))
self.add_row(*(
self.string_cell(col_name, stylename=self.style_bold)
for col_name in self.sheet_columns
))
self.lock_first_row()
def _report_section_balance(self, key: data.Account, date_key: str) -> None:
uses_opening = key.is_under('Assets', 'Equity', 'Liabilities')
if date_key == 'start':
if not uses_opening:
return
date = self.date_range.start
description = "Opening Balance"
else:
date = self.date_range.stop
description = "Ending Balance" if uses_opening else "Period Total"
balance = self.norm_func(
self.account_groups[key].balance_at_cost_by_date(date)
)
self.add_row(
self.date_cell(date, stylename=self.merge_styles(
self.style_bold, self.style_date,
)),
odf.table.TableCell(),
self.string_cell(description, stylename=self.style_bold),
odf.table.TableCell(),
self.balance_cell(balance, stylename=self.style_bold),
)
def start_section(self, key: data.Account) -> None:
self.add_row()
self.add_row(
odf.table.TableCell(),
self.string_cell(
f"{key} Ledger"
f" From {self.date_range.start.isoformat()}"
f" To {self.date_range.stop.isoformat()}",
stylename=self.style_bold,
numbercolumnsspanned=len(self.sheet_columns) - 1,
),
)
self.norm_func = core.normalize_amount_func(key)
self._report_section_balance(key, 'start')
def end_section(self, key: data.Account) -> None:
self._report_section_balance(key, 'stop')
def write_row(self, row: data.Posting) -> None:
if row.meta.date not in self.date_range:
return
elif row.cost is None:
amount_cell = odf.table.TableCell()
else:
amount_cell = self.currency_cell(self.norm_func(row.units))
self.add_row(
self.date_cell(row.meta.date),
self.string_cell(row.meta.get('entity') or ''),
self.string_cell(row.meta.txn.narration),
amount_cell,
self.currency_cell(self.norm_func(row.at_cost())),
*(self.meta_links_cell(row.meta.report_links(key))
if key in data.LINK_METADATA
else self.string_cell(row.meta.get(key, ''))
for key in self.metadata_columns),
)
def _combined_balance_row(self,
date: datetime.date,
balance_accounts: Sequence[str],
) -> None:
balance = -sum((
related.balance_at_cost_by_date(date)
for account, related in self.account_groups.items()
if account.is_under(*balance_accounts)
), core.MutableBalance())
self.add_row(
self.string_cell(
f"Balance as of {date.isoformat()}",
stylename=self.merge_styles(self.style_bold, self.style_endtext),
),
self.balance_cell(balance, stylename=self.style_bold),
)
def write_balance_sheet(self) -> None:
balance_accounts = ['Equity', 'Income', 'Expenses']
# FIXME: This is a hack to exclude non-project Equity accounts from
# project reports.
if balance_accounts[0] not in self.required_sheet_names:
balance_accounts[0] = 'Equity:Funds'
self.use_sheet("Balance")
column_style = self.replace_child(
self.document.automaticstyles, odf.style.Style, name='col_3',
)
column_style.setAttribute('family', 'table-column')
column_style.addElement(odf.style.TableColumnProperties(columnwidth='3in'))
for _ in range(2):
self.sheet.addElement(odf.table.TableColumn(stylename=column_style))
self.add_row(
self.string_cell("Account", stylename=self.style_bold),
self.string_cell("Balance", stylename=self.style_bold),
)
self.lock_first_row()
self.add_row()
self.add_row(self.string_cell(
f"Ledger From {self.date_range.start.isoformat()}"
f" To {self.date_range.stop.isoformat()}",
stylename=self.merge_styles(self.style_centertext, self.style_bold),
numbercolumnsspanned=2,
))
self.add_row()
self._combined_balance_row(self.date_range.start, balance_accounts)
for _, account in self._sort_and_filter_accounts(
self.account_groups, balance_accounts,
):
related = self.account_groups[account]
# start_bal - stop_bal == -(stop_bal - start_bal)
balance = related.balance_at_cost_by_date(self.date_range.start)
balance -= related.balance_at_cost_by_date(self.date_range.stop)
if not balance.is_zero():
self.add_row(
self.string_cell(account, stylename=self.style_endtext),
self.balance_cell(balance),
)
self._combined_balance_row(self.date_range.stop, balance_accounts)
def write(self, rows: Iterable[data.Posting]) -> None:
self.account_groups = dict(core.RelatedPostings.group_by_account(rows))
self.write_balance_sheet()
tally_by_account_iter = (
(account, sum(1 for post in related if post.meta.date in self.date_range))
for account, related in self.account_groups.items()
)
tally_by_account = {
account: count
for account, count in tally_by_account_iter
if count
}
sheet_names = self.plan_sheets(
tally_by_account, self.required_sheet_names, self.sheet_size,
)
using_sheet_index = -1
for sheet_index, account in self._sort_and_filter_accounts(
tally_by_account, sheet_names,
):
while using_sheet_index < sheet_index:
using_sheet_index += 1
self.start_sheet(sheet_names[using_sheet_index])
super().write(self.account_groups[account])
for index in range(using_sheet_index + 1, len(sheet_names)):
self.start_sheet(sheet_names[index])
class ReturnFlag(enum.IntFlag):
LOAD_ERRORS = 1
NOTHING_TO_REPORT = 8
def parse_arguments(arglist: Optional[Sequence[str]]=None) -> argparse.Namespace:
parser = argparse.ArgumentParser(prog=PROGNAME)
cliutil.add_version_argument(parser)
parser.add_argument(
'--begin', '--start', '-b',
dest='start_date',
metavar='DATE',
type=cliutil.date_arg,
help="""Date to start reporting entries, inclusive, in YYYY-MM-DD format.
The default is one year ago.
""")
parser.add_argument(
'--end', '--stop', '-e',
dest='stop_date',
metavar='DATE',
type=cliutil.date_arg,
help="""Date to stop reporting entries, exclusive, in YYYY-MM-DD format.
The default is a year after the start date, or 30 days from today if the start
date was also not specified.
""")
parser.add_argument(
'--account', '-a',
dest='sheet_names',
metavar='ACCOUNT',
action='append',
help="""Show this account in the report. You can specify this option
multiple times. If not specified, the default set adapts to your search
criteria.
""")
parser.add_argument(
'--sheet-size', '--size',
metavar='SIZE',
type=int,
default=LedgerODS.SHEET_SIZE,
help="""Try to limit sheets to this many rows. The report will
automatically create new sheets to make this happen. When that's not possible,
it will issue a warning.
""")
parser.add_argument(
'--output-file', '-O',
metavar='PATH',
type=Path,
help="""Write the report to this file, or stdout when PATH is `-`.
The default is stdout for the balance and outgoing reports, and a generated
filename for other reports.
""")
cliutil.add_loglevel_argument(parser)
parser.add_argument(
'search_terms',
metavar='FILTER',
type=cliutil.SearchTerm.arg_parser('project', 'rt-id'),
nargs=argparse.ZERO_OR_MORE,
help="""Report on postings that match this criteria. The format is
NAME=TERM. TERM is a link or word that must exist in a posting's NAME
metadata to match. A single ticket number is a shortcut for
`rt-id=rt:NUMBER`. Any other word is a shortcut for `project=TERM`.
""")
args = parser.parse_args(arglist)
if args.sheet_names is None:
if any(term.meta_key == 'project' for term in args.search_terms):
args.sheet_names = ['Income', 'Expenses', 'Assets:Receivable', 'Liabilities:Payable']
else:
args.sheet_names = list(LedgerODS.ACCOUNT_COLUMNS)
return args
def diff_year(date: datetime.date, diff: int) -> datetime.date:
new_year = date.year + diff
try:
return date.replace(year=new_year)
except ValueError:
# The original date is Feb 29, which doesn't exist in the new year.
if diff < 0:
return datetime.date(new_year, 2, 28)
else:
return datetime.date(new_year, 3, 1)
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()
today = datetime.date.today()
if args.start_date is None:
args.start_date = diff_year(today, -1)
if args.stop_date is None:
args.stop_date = today + datetime.timedelta(days=30)
elif args.stop_date is None:
args.stop_date = diff_year(args.start_date, 1)
returncode = 0
books_loader = config.books_loader()
if books_loader is None:
entries, load_errors, _ = books.Loader.load_none(config.config_file_path())
else:
entries, load_errors, _ = books_loader.load_fy_range(args.start_date, args.stop_date)
for error in load_errors:
bc_printer.print_error(error, file=stderr)
returncode |= ReturnFlag.LOAD_ERRORS
postings = data.Posting.from_entries(entries)
for search_term in args.search_terms:
postings = search_term.filter_postings(postings)
rt_wrapper = config.rt_wrapper()
if rt_wrapper is None:
logger.warning("could not initialize RT client; spreadsheet links will be broken")
report = LedgerODS(
args.start_date,
args.stop_date,
args.sheet_names,
rt_wrapper,
args.sheet_size,
)
report.write(postings)
if not report.account_groups:
logger.warning("no matching postings found to report")
returncode |= ReturnFlag.NOTHING_TO_REPORT
if args.output_file is None:
out_dir_path = config.repository_path() or Path()
args.output_file = out_dir_path / 'LedgerReport_{}_{}.ods'.format(
args.start_date.isoformat(), args.stop_date.isoformat(),
)
logger.info("Writing report to %s", args.output_file)
ods_file = cliutil.bytes_output(args.output_file, stdout)
report.save_file(ods_file)
return 0 if returncode == 0 else 16 + returncode
entry_point = cliutil.make_entry_point(__name__, PROGNAME)
if __name__ == '__main__':
exit(entry_point())
|