import csv
from git import Repo
from perceval.backends.core.git import Git
import os
import datetime as dt
import time
import shutil 
import pandas as pd
import dateutil
from tqdm import tqdm
import math
import io 
import re

working_dir = "/data/users/mgaughan/kkex/time_specific_files/readme"
temp_dir = "/data/users/mgaughan/tmp3/"

# getting the specific readme or contributing file from a given commit 
# inputs: upstream vcs link, commit hash, yes/no is it a readme 
def get_file(vcs_link, commit_hash, is_readme):
    if "github" in vcs_link or "gitlab" in vcs_link:
        #making an evaluation that sub branches aren't being used and that people would fork if needed
        #this only looks at main
        vcs_link = "/".join(vcs_link.split("/")[0:5])
        full_temp_path = temp_dir + vcs_link.split('/')[4] + ".git"
        other_temp_path = temp_dir + vcs_link.split('/')[4] + ".git0"
    else:
        full_temp_path = temp_dir + vcs_link.split('/')[- 1] + ".git"
        other_temp_path = temp_dir + vcs_link.split('/')[- 1] + ".git0"
    repo0 = Repo.clone_from(vcs_link, full_temp_path)
    repo = Git(uri=vcs_link, gitpath=other_temp_path)
    commit0 = repo0.commit(commit_hash)
    commits = repo.fetch()
    target_filename = ""
    for commit in commits:
        files = commit['data']['files']
        for file in files:
            if is_readme:
                if "README" in file['file']:
                    #print(file['file'])
                    if "/" in file['file']:
                        target_filename = file['file'].split("/")[-1]
                    else:
                        target_filename = file['file']
            else:
                if "CONTRIBUTING" in file['file']:
                    '''
                    if "/" in file['file']:
                        target_filename = file['file'].split("/")[-1]
                    else:
                    '''
                    target_filename = str(file['file'])
    #print(commit.tree)
    #getting the name of the file from the root directory
    '''
    target_filename = ""
    for filename in os.listdir(full_temp_path):
        if is_readme:
            #target_filename = "README.md"
            if "README" in filename or "readme" in filename:
                target_filename = filename
        else:
            #target_filename = "CONTRIBUTING.md"
            if "CONTRIBUTING" in filename or "contributing" in filename:
                target_filename = filename
    '''
    if target_filename == "":
        shutil.rmtree(full_temp_path, ignore_errors=True)
        shutil.rmtree(other_temp_path, ignore_errors=True)
        return "NoFile"
    #target_filename = r"/README/"
    #issue with searching through the tree this way
    # need to match the tree w blobs 
    #print(commit0.tree.blobs)
    #file_id = commit0.tree[r'README.*'].hexsha
    #targetfile = repo0.blob(file_id)
    #targetfile = commit0.tree / target_filename
    '''
    try:
        targetfile = commit0.tree / target_filename
    except KeyError:
        target_filename = "README.rst"
        try:
            targetfile = commit0.tree / target_filename
        except KeyError:
            target_filename = "README"
            try:
                targetfile = commit0.tree / target_filename
            except KeyError:
                target_filename = "README.txt"
                try:
                    targetfile = commit0.tree / target_filename
                except KeyError:
                    shutil.rmtree(full_temp_path, ignore_errors=True)
                    shutil.rmtree(other_temp_path, ignore_errors=True)
                    return "KeyError -- the file is not in the commit tree"
        '''
    print(target_filename)
    for blob in commit0.tree.blobs:
        if "README" in blob.path:
            targetfile = blob
            print(blob.path)
        # why would a file not be in the commit tree? but would be in the directory?
        #shutil.rmtree(full_temp_path, ignore_errors=True)
    #    return "KeyError -- the file is not in the commit tree"
    if is_readme:
        last_path = "readme"
    else:
        last_path = "contributing"
    with open("/data/users/mgaughan/kkex/time_specific_files/" + last_path + "/" + full_temp_path[len(temp_dir):-4] + "_" + last_path + ".md", "w") as file:
        with io.BytesIO(targetfile.data_stream.read()) as f:
            file.write(f.read().decode('utf-8'))
        file.close()
    shutil.rmtree(full_temp_path, ignore_errors=True)
    shutil.rmtree(other_temp_path, ignore_errors=True)
    return "NoError"

def for_all_files():
    #toggle this based on readme or contributing files
    readme_is = True
    csv_path = "kk_031624_pr_did.csv"
    index = -1
    with open(csv_path, 'r') as file:
        with open('a_031824_spec_errors.csv', "w") as writing_file:
            csv_writer = csv.writer(writing_file)
            #csv_reader = csv.DictReader(file)
            lines = [line for line in file]
            for row in tqdm(csv.reader(lines), total=len(lines)):
                index += 1
                if index == 0:
                    continue
                if row[0] == "":
                    continue
                #print(row[0])
                return_value = get_file(row[0], row[2], readme_is)
                if return_value != "NoError":
                    csv_writer.writerow([row[0], row[2], readme_is, return_value])
                #get_file('https://github.com/tqdm/tqdm', 'fbe7952cce11e8073378b063bdae7ab277a96eb8', True)

if __name__ == "__main__":
    for_all_files()
    #print(get_file('https://github.com/the-tcpdump-group/tcpslice', 'ffac277bf41946a1d985afae7fe2535d7a28546f', True))
    #get_file('https://github.com/krahets/hello-algo/tree/dev1', 'f615ad42ef3c58cfc6f080b8fb0cd0eb741706a9', True )