consors-report.py: Add

diff --git a/consors-report.py b/consors-report.py
new file mode 100755 (executable)
index 0000000..8601bf2
--- /dev/null
+++ b/consors-report.py
@@ -0,0 +1,97 @@
+#!/usr/bin/python3
+
+import argparse
+import collections
+import itertools
+import re
+from collections import namedtuple
+from pathlib import Path
+from typing import Iterable
+
+Entry = namedtuple('Entry', ['category', 'date', 'valuta', 'who', 'iban', 'bic', 'type', 'desc', 'value'])
+
+CATEGORIES = {
+    'Gehalt/Steuern': re.compile('Gehalt/Rente|RED HAT|Finanzamt|FK Guenzburg', re.I),
+    'Wohnung': re.compile('Telekom|hands4home|Goetzfried|Green Planet Energy|Beitragsservice.*Rundfunk', re.I),
+    'Medizin': re.compile(r'Apotheke|MVZ|\bmed\b|ZAB Abrechnung|Caika|HNOeins|PVS|'
+                          r'BFS Health|Streifeneder|(Drescher.*Lung)|(Debeka.*Überweisung)', re.I),
+    'Versicherung': re.compile('(debeka|DKV|Versicherung|Alte Leipziger).*Lastschrift', re.I),
+    'Transport': re.compile('DB Vertrieb|Deutsche Bahn|Nextbike', re.I),
+    'Lebensmittel': re.compile('BIOS|Wolf|Ruta|Rewe', re.I),
+    'Eigentumswohnungen': re.compile('Rechnung Darl.-Leistung|Semmelweis', re.I),
+    'Hobby/Sport': re.compile('Holstein|Mrs. Sporty|Kieser|DJK', re.I),
+    'Sparen': re.compile('Bausparkasse Mainz AG|FIL Fondsbank|MIG GmbH|Netfonds AG', re.I),
+    'Spenden': re.compile('Spende|Signal Foundation|nebenan.de|(paypal.*Sabine.Hossenf)|'
+                          'Patreon|Umwelthilfe|Foerderer|(Aktion Tier.*Mensch)', re.I),
+}
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description='Read Consorsbank CSV and generate report')
+    parser.add_argument('-d', '--date', metavar='REGEX', default='.', help='date filter regex')
+    parser.add_argument('-s', '--summary', action='store_true', help='only show category sums')
+    parser.add_argument('csv', type=Path, nargs='+', help='CSV files to parse')
+    return parser.parse_args()
+
+
+def get_category(item: str) -> str:
+    for category, pattern in CATEGORIES.items():
+        if pattern.search(item):
+            return category
+    return 'Sonstiges'
+
+
+def parse_entry(line: str) -> Entry:
+    fields = [f.strip() for f in line.strip().split(';')]
+    # last field is the value, parse as float
+    value = float(fields.pop().replace('.', '').replace(',', '.'))
+    # match on who, IBAN, type, or desc
+    category = get_category(fields[2] + fields[3] + fields[5] + fields[6])
+    return Entry._make([category, *fields, value])
+
+
+def parse_csv(path: Path, date_filter: str) -> Iterable[Entry]:
+    filter_re = re.compile(date_filter, re.I)
+
+    def filter_entry(entry: Entry):
+        # ignore from/to Tagesgeldkonto
+        if entry.iban == 'DE13760300800853589101':
+            return None
+        return filter_re.search(entry.date)
+
+    with path.open() as f:
+        # first line is the column headers, chop it off
+        entries = map(parse_entry, f.readlines()[1:])
+        return filter(filter_entry, entries)
+
+
+def main():
+    args = parse_args()
+
+    entries = itertools.chain.from_iterable(map(lambda p: parse_csv(p, args.date), args.csv))
+    by_category = collections.defaultdict(lambda: [])
+    category_sum = collections.defaultdict(lambda: 0.0)
+    balance = 0.0
+    for e in entries:
+        by_category[e.category].append(e)
+        category_sum[e.category] += e.value
+        balance += e.value
+
+    if args.summary:
+        for cat in sorted(by_category):
+            print(f'| {category_sum[cat]:>8.2f} | {cat:20} |')
+        print('|----------|----------------------|')
+        print(f'| {balance:>8.2f} | {"Saldo":20} |')
+
+    else:
+        for cat in sorted(by_category):
+            print(f'## {cat}: {category_sum[cat]:.2f}\n')
+            for entry in by_category[cat]:
+                print(f'| {entry.date:7} | {entry.value:>7.2f} | _{entry.type}_ - {entry.who} - {entry.desc} |')
+            print()
+
+        print(f'## Saldo: {balance:.2f}')
+
+
+if __name__ == '__main__':
+    main()