TransformCSV2JSON

import json
import csv
import re

character = "../personajes/characters.csv"
comic = "../personajes/comics.csv"
relation = "../personajes/charactersToComics.csv"


def sanitize(input: str):
    return input.encode('ascii', 'ignore').decode()


def process_comic(comic):
    match = re.search(r"\((\d+)\)", comic['title'])
    if match:
        comic['year'] = match.group(1)
    comic['title'] = re.split(r"\(.*?\)", comic['title'])[0].strip()
    return comic


if __name__ == "__main__":
    characters = None
    with open(character, 'r') as f:
        characters = [{sanitize(k): sanitize(v) for k, v in row.items()}
                      for row in csv.DictReader(f, skipinitialspace=True)]
    characters = {character['characterID']: character for character in characters}
    comics = None
    with open(comic, 'r') as f:
        comics = [{sanitize(k): sanitize(v) for k, v in row.items()}
                  for row in csv.DictReader(f, skipinitialspace=True)]
    comics = {comic['comicID']: process_comic(comic) for comic in comics}
    relations = None
    with open(relation, 'r') as f:
        relations = [[sanitize(v) for k, v in row.items()]
                     for row in csv.DictReader(f, skipinitialspace=True)]
    for comicRef, characterRef in relations:
        if 'characters' not in comics[comicRef]:
            comics[comicRef]['characters'] = set()
        comics[comicRef]['characters'].add(
            characters[characterRef]['name'])
        if 'comics' not in characters[characterRef]:
            characters[characterRef]['comics'] = list()
        characters[characterRef]['comics'].append({
            'title': comics[comicRef]['title'],
            'issueNumber': comics[comicRef]['issueNumber']
            })
    comics = list(comics.values())
    characters = list(characters.values())
    for comic in comics:
        if 'characters' in comic:
            comic['characters'] = list(comic['characters'])
        del comic['comicID']
    for character in characters:
        character['comics'] = list(character['comics'])
        del character['characterID']
    with open('../files/JSON/characters.json', 'w') as f:
        f.write(json.dumps(characters, indent=4))
    with open('../files/JSON/comics.json', 'w') as f:
        f.write(json.dumps(comics, indent=4))