TODO/ISSUES:

 - AMEX statement doesn't provide bank balance or running total

"""

import argparse

import collections

import copy

import csv

import datetime

import decimal

import io

import logging

import os

import re

import sys

from typing import Callable, Dict, List, Tuple, TextIO

from beancount import loader

from beancount.query.query import run_query

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

logger = logging.getLogger()

logger.setLevel(logging.DEBUG)

# Console logging.

    """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,

    }

    else:

def sort_records(records: List) -> List:

    return sorted(records, key=lambda x: (x['date'], x['amount']))

def first_word_exact_match(a, b):

    if len(a) == 0 or len(b) == 0:

        return 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))

def match_statement_and_books(statement_trans: list, books_trans: list):

    """

    Runs through all the statement transactions to find a matching transaction

    in the books. If found, 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.

    """

    matches = []

    remaining_statement_trans = []

    for r1 in statement_trans:

        best_match_score = 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:

            if best_match_score <= 0.8:

                best_match_note.append('only one decent match')

            matches.append(([r1], [books_trans[best_match_index]], best_match_note))

            del books_trans[best_match_index]

        else:

    for r2 in books_trans:

def format_matches(matches, csv_statement: str, show_reconciled_matches):

    match_output = []

    for r1, r2, note in matches:

        note = ', '.join(note)

        note = ': ' + note if note else note

        if r1 and r2:

        elif r1:

        else:

    return match_output

def date_proximity(d1, d2):

    diff = abs((d1 - d2).days)

    if diff > 60:

        return 0

    else:

        return 1.0 - (diff / 60.0)

def metadata_for_match(match, statement_filename, csv_filename):

    # Can we really ever have multiple statement entries? Probably not.

    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 main(args):

    # TODO: Should put in a sanity check to make sure the statement you're feeding

    # in matches the account you've provided.

    # TODO: Can we open the files first, then pass the streams on to the rest of the program?

    if 'AMEX' in args.account:

        standardize_statement_record = standardize_amex_record

    else:

        standardize_statement_record = standardize_fr_record

    with open(args.csv_statement) as f:

    books_balance_reconciled_query = f"""SELECT sum(COST(position)) AS aa WHERE account = "{args.account}"

        AND date <= {end_date.isoformat()} AND META('bank-statement') != NULL"""

    result_types, result_rows = run_query(entries, options, books_balance_reconciled_query, numberify=True)

    books_balance_reconciled = result_rows[0][0] if result_rows else 0

    # 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_types, result_rows = run_query(entries, options, query)

    books_trans = sort_records([standardize_beancount_record(row) for row in result_rows])

    total_matched, total_missing_from_books, total_missing_from_statement = totals(matches)

    out = io.StringIO()

    print('-' * 155)

    print(f'{"Statement transaction":<52}            {"Books transaction":<58}   Notes')

    print('-' * 155)

    for _, output in sorted(match_output):

        print(output)

    print('-' * 155)

    print(f'Statement period {begin_date} to {end_date}')

    print(f'Statement/cleared balance:    {args.statement_balance:12,.2f}    (as provided by you)')

import tempfile

import textwrap

from conservancy_beancount.reconcile.statement_reconciler import (

    match_statement_and_books,

    remove_payee_junk,

    date_proximity,

    remove_duplicate_words,

    payee_match,

    metadata_for_match,

    write_metadata_to_books,

    totals,

)

# These data structures represent individual transactions as taken from the

# statement ("S") or the books ("B").

# Statement transaction examples.

S1 = {

    'date': datetime.date(2022, 1, 1),

    'amount': decimal.Decimal('10.00'),

    'payee': 'Patreon         / Patreon   / 123456/ ST-A1B2C3D4G5H6       /',

    'check_id': '',

    'line': 222,

    'amount': decimal.Decimal('20.00'),

    'payee': 'BT*LINODE           PHILADELPHIA        P',

    'check_id': '',

    'line': 333,

}

S3 = {

    'date': datetime.date(2022, 1, 3),

    'amount': decimal.Decimal('30.00'),

    'payee': 'USPS PO 4067540039 0PORTLAND            OR',

    'check_id': '',

    'line': 444,

}

# Books transaction examples.

B1 = {

    'date': datetime.date(2022, 1, 1),

    'amount': decimal.Decimal('10.00'),

    'payee': 'Patreon',

    'check_id': '',

    'filename': '2022/imports.beancount',

    'line': 777,

    'bank_statement': '',

}

B2 = {

    'line': 999,

    'bank_statement': "Financial/Bank-Statements/AMEX/2022-01-12_AMEX_statement.pdf"

}

B3_unmatched_check_id = {

    'date': datetime.date(2022, 1, 3),

    'amount': decimal.Decimal('30.00'),

    'payee': 'USPS',

    'check_id': '1234',

    'filename': '2022/main.beancount',

    'line': 999,

    'bank_statement': "Financial/Bank-Statements/AMEX/2022-01-12_AMEX_statement.pdf"

}

def test_one_exact_match():

    statement = [S1]

    books = [B1]

        # Match, match, notes.

        #

        # The matches are a list so we can implement subset-sum matching where

        # multiple books transactions may match to a single statement

        # transaction.

def test_multiple_exact_matches():

    statement = [S1, S2]

    books = [B1, B2]

def test_one_mismatch():

    statement = [S1]

    books = []

def test_multiple_mismatches():

    statement = [S1]

    books = [B2]

def test_next_day_matches():

    statement = [S3]

    books = [B3_next_day]

def test_next_week_matches():

    statement = [S3]

    books = [B3_next_week]

def test_incorrect_amount_does_not_match():

    statement = [S3]

    books = [B3_mismatch_amount]

def test_payee_mismatch_ok_when_only_one_that_amount_and_date():

    statement = [S3]

    books = [B3_payee_mismatch_1]

def test_payee_mismatch_not_ok_when_multiple_that_amount_and_date():

    statement = [S3]

    books = [B3_payee_mismatch_1, B3_payee_mismatch_2]

    match = match_statement_and_books(statement, books)

def test_remove_payee_junk():

    assert remove_payee_junk('WIDGETSRUS INC PAYMENT 1') == 'WIDGETSRUS'

    assert remove_payee_junk('0000010017') == '10017'

def test_date_proximity():

    assert date_proximity(datetime.date(2021, 8, 23), datetime.date(2021, 8, 23)) == 1.0

    assert date_proximity(datetime.date(2021, 8, 23), datetime.date(2021, 8, 23) - datetime.timedelta(days=30)) == 0.5

    assert date_proximity(datetime.date(2021, 8, 23), datetime.date(2021, 8, 23) - datetime.timedelta(days=60)) == 0.0

def test_remove_duplicate_words():

    assert remove_duplicate_words('Hi Foo Kow FOO') == 'Hi Foo Kow'

def test_totals():

    assert totals([

        ([S1], [B1], []),

        ([S2], [], []),

        ([], [B3_next_day], []),

    ]) == (decimal.Decimal('10'), decimal.Decimal('20'), decimal.Decimal('30'))

def test_payee_not_considered_if_check_id_present():

    # These records match aside from check-id.

    statement = [S3]

    books = [B3_unmatched_check_id]