config.yml

# Define the tesseract language
language: deu

# Enable https
https: false

results_as_json: false

# Where the receipts are stored
# Receipts should be simple text files
receipts_path: "data/txt"

# Market names roughly ordered by likelihood.
# Can contain market locations for fuzzy parsing
markets:
  
  Colruyt:
    - colruyt
    - Colruyt
  
  Delhaize:
    - Delhaize
    - delhaize
  
  Penny:
    - penny markt
    - penny
    - p e n n y
    - m a r k t gmbh
  
  REWE:
    - rewe
  
  Real:
    - real
 
  Netto:
    - netto-online
  
  Kaiser's:
    - kaiser
    - kaiserswerther straße 270
  
  Aldi:
    - aldi
    - friedrichstr 128—133
  
  Lidl:
    - lidl
  
  Edeka:
    - edeka
  
  Drogerie:
    - drogerie
  
  Kodi:
    - kodi
  
  Getraenke:
    - Getraenke Tempel
  
  Tanken:
    - shell
    - esso station
    - aral
    - total tankstelle
    - RK Tankstellen
  
  Migros:
    - genossenschaft migros

sum_keys:
  - summe
  - gesamtbetrag
  - gesantbetrag
  - gesamt
  - total
  - sum
  - zwischensumme
  - bar
  - te betalen
  - rockgeld
  - rusckgeld
  - rückgeld

ignore_keys:
  - mwst
  - kg x
  - stkx
  - stk

sum_format: '\d+(\.\s?|,\s?|[^a-zA-Z\d])\d{2}'

item_format: '([a-zA-Z].+)\s(-|)((\d|\d{2}),(\d{2}|\d{3}))\s'
item_format_metro: '[0-9]\s(.*?)\d.()((\d|\d{2})(\,|\.)\d{2})\s([A|a]|[B|b])'

date_format: '((\d{2}\.\d{2}\.\d{2,4})|(\d{2,4}\/\d{2}\/\d{2})|(\d{2}\/\d{2}\/\d{4}))'