import csv
import numpy as np
import sys
import pandas as pd
import re
sys.path.append("./")
from evaluations.utils import *

token = os.getenv("githubToken")
custom_order = ["MICCAI", "MIDL", "Nature", "arXiv"]

for venue in custom_order:
    df = pd.read_excel("https://docs.google.com/spreadsheets/d/e/2PACX-1vQjpsSYcEcYUVB-88bCQ01UfQf0z9m16ax7p1ft03G68Nr-DdXHpPt-xOFSrXFj1N49AjK5nYhmKBfo/pub?output=xlsx", sheet_name=venue)
    df = df.replace('\t', ' ', regex=True)
    df.to_csv(f'data/{venue}.csv', sep="\t")

# Store all evaluations here
paper_dump = pd.DataFrame()
# Official color codes for conferences
zip_idx = 0

for venue in custom_order:
    with open(f'data/{venue}.csv') as file:
        tsv_file = csv.reader(file, delimiter="\t")
        for row in tsv_file:
            if (row[0] == ""):
                continue

            if (row[1] == ""):
                continue

            repo_url = row[4]
            username, repo_name = decompose_url(repo_url)
            repo_save_name = f"repo_{zip_idx}.zip"
            repository_zip_name = f"data/test/{repo_save_name}"
            log(0, "LOG", f"Fetching github repository: https://github.com/{username}/{repo_name}")
            fetch_repo(0, repo_url, repository_zip_name, token)

            if (os.path.exists(repository_zip_name)):
                paper_dump = pd.concat([paper_dump, pd.DataFrame({"venue": venue, "title": [row[1]], "year": [row[2]], "pdf": [row[3]], "url": [row[4]], "public": [row[5]], "dependencies": [row[6]], "training": [row[7]], "evaluation": [row[8]], "weights": [row[9]], "readme": [row[10]], "license": [row[11]], "zip_idx": [ repository_zip_name ]})], ignore_index=True)
                zip_idx += 1
            
paper_dump.to_csv(f'data/zipfiles.csv', sep="\t")