- 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

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

# 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+')

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)

        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'])

            payee_message = ''

            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.