import pandas as pd
import os
from evaluations import documentation, requirements, training, validating, license, weights, pitfalls
from evaluations.utils import *
import zipfile
import os
import numpy as np
from huggingface_hub import InferenceClient

def evaluate(llm, verbose, repo_url, title=None, year=None, zip=None):
    try:
        if (not(llm)):
            log(verbose, "LOG", "No LLM will be used for the evaluation.")

        results = { "pred_live": "Yes", "pred_dependencies": None, "pred_training": None, "pred_evaluation": None, "pred_weights": None, "pred_readme": None, "pred_license": None, "pred_stars": None, "pred_citations": None, "pred_valid": False}
        
        if ((title != None) & (year != None) & (title != "") & (year != "")):
            res = fetch_openalex(verbose, title, year)
            if ((res != None)):
                res = res["results"]
                if (len(res) > 0):
                    res = res[0]
                    results["pred_citations"] = res["cited_by_count"]

        if (get_api_link(repo_url) != ""):
            results["pred_valid"] = True
        else:
            return results

        username, repo_name = decompose_url(repo_url)

        # If you don't provide a zip file, it will be fetched from github. For this, you need to provide a github token.
        if (zip is None):
            token = os.getenv("githubToken")
            repository_zip_name = "data/repo.zip"
            log(verbose, "LOG", f"Fetching github repository: https://github.com/{username}/{repo_name}")

            fetch_repo(verbose, repo_url, repository_zip_name, token)

            if (not(os.path.exists(repository_zip_name))):
                results["pred_live"] = "No"
                return results
            
            results["pred_stars"] = fetch_repo_stars(verbose, repo_url, token)

            zip = zipfile.ZipFile(repository_zip_name)

        readme = fetch_readme(zip)
        results["NA"] = documentation.is_applicable(verbose, llm, readme)

        results["pred_license"] = license.evaluate(verbose, llm, zip, readme)

        if (len(zip.namelist()) <= 2):
            log(verbose, "LOG", "The repository is empty.")
          
        results["pred_dependencies"] = requirements.evaluate(verbose, llm, zip, readme)
        results["pred_training"] = training.evaluate(verbose, llm, zip, readme)
        results["pred_evaluation"] = validating.evaluate(verbose, llm, zip, readme)
        results["pred_weights"] = weights.evaluate(verbose, llm, zip, readme)
        results["pred_readme"] = documentation.evaluate(verbose, llm, zip, readme)
        results["pred_codetocomment"] = documentation.get_code_to_comment_ratio(zip)
        pitfalls.evaluate(verbose, llm, zip, readme)

        return results
    except Exception as e:
        log(verbose, "ERROR", "Evaluating repository failed: " + str(e))
        results["pred_live"] = "No"
        return results

def full_evaluation():
  paper_dump = pd.read_csv("data/zipfiles.csv", sep="\t")
  full_results = []

  for idx, row in paper_dump.iterrows():

      if (pd.isna(row["url"]) | (row["url"] == "")):
          continue

      print(str(int(100 * idx / paper_dump["title"].count())) + "% done")
      result = evaluate(None, False, row["url"], row["title"], row["year"], zip=zipfile.ZipFile(row["zip_idx"]))
      for column in result.keys():
          row[column] = result[column]

      full_results.append(row)
  return pd.DataFrame(full_results)