gpn23-recipes/fruehstueck.py

import json
import sys
from pathlib import Path
from datetime import timedelta
import re
import os
from tqdm import tqdm
import csv
from collections import defaultdict

from config import *


def grams(ingredient):
    conversion = None
    for c in ingredient["conversions"]:
        if c["unit"] in ["g / Gramm", "g"]:
            conversion = c
    if conversion:
        return conversion.get('amount')


def allergens_for_step_ingredients(step):
    l = []
    for ingredient in step["ingredients"]:
        if not ingredient.get("food"):
            raise ValueError("No food in ingredient")
            continue
        i_grams = grams(ingredient)
        i_name = ingredient["food"]["name"]
        i_description = ingredient["food"]["description"]

        if match := re.search(r"^Allergene: (.*)$", i_description, re.MULTILINE):
            i_allergens = match.group(1)
        else:
            i_allergens = "❗ keine Allergene hinterlegt"

        l.append((i_grams, i_name, i_allergens))

    return l


def allergens_for_recipe(recipe):
    l = []
    for step in recipe["steps"]:
        l += allergens_for_step_ingredients(step)
    return l


def link(recipe):
    return f"{TANDOOR_URL + "/view/recipe/" + str(recipe["id"])}"

def wiki_link(recipe):
    wiki_slug = recipe["name"]
    wiki_slug = re.sub(" ", "_", wiki_slug)
    return f"{WIKI_URL + WIKI_ARTICLE_PREFIX + wiki_slug}"


def decruft_ingredient(i_name: str):
    i_name = i_name.replace(" (trocken)", "")
    i_name = i_name.replace(" (frisch)", "")
    i_name = i_name.replace(" (TK)", "")
    i_name = i_name.replace(" (Dose)", "")
    i_name = i_name.replace(" (getrocknet)", "")
    return i_name


def aggregate_zutaten(data):
    result = defaultdict(int)
    for grams, item in data:
        result[item] += grams
    return [(g, n) for n, g in result.items()]


def main():

    Path("fruehstueck.csv").unlink(missing_ok=True)

    recipes = []
    for json_file in os.listdir(OUTDIR_JSON):
        with open(os.path.join(OUTDIR_JSON, json_file), "r", encoding="utf-8") as f:
            data = json.load(f)
        recipes.append(data)
    recipes.sort(key=lambda r: r["name"])

    # filter "Frühstück"
    recipes = [r for r in recipes if any(k["name"] == "Fr\u00fchst\u00fcck" for k in r["keywords"])]

    with open("fruehstueck.csv", "w", newline="") as f:
        fwriter = csv.writer(f, delimiter=';', quotechar='"', quoting=csv.QUOTE_MINIMAL, lineterminator="\n")
        fwriter.writerow(["title", "url", "isVegan", "ingredients", "comment"])

        for recipe in recipes:
            zutaten = []
            for i_grams, i_name, i_allergens in allergens_for_recipe(recipe):
                if i_grams is None:
                    i_grams = 0

                zn = decruft_ingredient(i_name)
                if i_allergens != "(keine)":
                    i_allergens = i_allergens.replace("⁉\ufe0f", "\\faExclamationTriangle")
                    zn += f" (\\Alg{{{i_allergens}}})"

                zutaten.append((i_grams, zn))

            zutaten = aggregate_zutaten(zutaten)
            zutaten.sort(key=lambda z: z[0], reverse=True)

            fwriter.writerow([
                recipe["name"],
                wiki_link(recipe),
                1,  # XXX hardcoded
                ", ".join(z[1] for z in zutaten),
                ""
            ])


if __name__ == "__main__":
    main()