recipeparser

import glob
import re

from pathlib import Path
from typing import List
from urllib.parse import unquote

from PIL import Image


def parse_list(lst: list):
    return [item[2:] for item in lst.strip().splitlines()]

def parse_content(content: str):
    if content.lstrip().startswith("-"):
        return parse_list(content)
    else:
        # ignore cross-links
        content = re.sub("\[\[.+?\]\]", "", content)

        paragraphs = content.split("\n\n")
        return list(process_paragraphs(paragraphs))

def find_categories(regex, content):
    result = {}
    cats = re.finditer(regex, content, re.M)
    for cat in cats:
        title, content = cat.groups()
        title = title.lower()
        parsed_content = parse_content(content)
        result[title] = parsed_content
    return result   

def process_pictures(md: str):
    regex = r"!\[(.*)\]\((.+)\)"
    pictures = re.findall(regex, md)
    result_dict = {}

    for picture in pictures:
        image_name, image_file = picture[0], unquote(picture[1])
        goal_path = Path(f"assets/images/{image_file}")
        result_dict[image_name] = image_file
        if goal_path.is_file():
            continue

        image = Image.open(f"../content/recipes/attachments/{image_file}")
        image.thumbnail((500, 500), Image.ANTIALIAS)
        image.save(goal_path)        
    return result_dict  

def process_paragraphs(paragraphs: List):
    for par in paragraphs:
        pictures = process_pictures(par)
        if pictures:
            yield pictures
        elif par:
            yield par

def process_tagfile(md: str):
    regex = r'## (.+)\n((?: *-.*\n)+)'
    return find_categories(regex, md)

def process_recipe(md: str):
    """processes recipe in markdown-format into a dict
    
    # = title (parse title: str)
    ## = part (parse content: lines below)
    """
    result = find_categories(r'## (.*)\n([^#]*)', md)
    result["title"], result["title_image_title"], result["title_image"] = re.search(r'^# (.*)$(?:\n?!\[(.*)\]\((.+)\))?', md, re.M).groups()
    result["tags"] = re.findall(r'#([\w/!]+)', md)
    result["pictures"] = process_pictures(md)

    return result


if __name__ == "__main__":
    from pprint import pprint
    for filename in glob.glob("../content/recipes/*.md"):
        with open(filename, "r") as fi:
            pprint(process_recipe(fi.read()))