import os
import pandas as pd
import sys


def crawl(dir_path, idx):
    for d in os.listdir(dir_path):
        if os.path.isfile(dir_path + "\\" + d) == False:
            crawl(dir_path + "\\" + d, idx)
        else:
            file_name = str(df['FileName'][idx][0:len(df['FileName'][idx]) - 9]) + ".java"
            # print(df['FileName'][idx])
            if d == file_name:
                actual_file_path = dir_path + "\\" + file_name
                df_out.append({'ProjectName': 'RxJava','TestFilePath': df['FilePath'][idx], 'FilePath': actual_file_path}, ignore_index=True)
                # print("Achei " + df['FileName'][i] + " e " + file_name + " at dir: " + actual_file_path)

csv_dir = r"C:\Users\guiga\EASY\TestSmells\csv"
project_path = r"C:\Users\guiga\EASY\TestSmells\repositories\RxJava"
files = []
test_files_list = list()
sys.setrecursionlimit(100000000)
df_out = pd.DataFrame(columns = ['ProjectName', 'TestFilePath', 'FilePath'])

for csv_file in os.listdir(csv_dir):
    # print(csv_file)
    df = pd.read_csv(csv_dir + "\\" + csv_file)
    df = df[['FileName', 'FilePath']]
    df = df.drop_duplicates()
    # print(df['FileName'][0])
    # test_files_list = list(set(df['FileName'].values))
    for i in df.index:
        # print(df['FileName'][i])
        if df['FileName'][i].endswith('Test.java'):
            crawl(project_path, i)
df_out.to_csv('out.csv', header=False)
# print(test_files_list)