main.py

#USER INPUT
from preprocessing import run_preprocessing
from ai_transcriber import transcribe_all
from reconciliate_and_upload import reconciliate_and_upload
import os
def run_main(
source_folder_with_reciepts = "https://drive.google.com/drive/folders/1skbgiXMnAe3z2r8E9oLAxXxkDBnrk8l4?usp=sharing",
link_to_csv = "https://drive.google.com/file/d/1cYoj8U5mttwQu5hNoupifHtjESCIHpsp/view?usp=sharing",
folder_to_save_processed_reciepts = "https://drive.google.com/drive/folders/1zADJlZ8pvXHNdAhbrxScPynSq1m5Jo1C?usp=sharing",
folder_to_save_reconciled_data =  "https://drive.google.com/drive/folders/1bmrHExKt0x5AJwJsMtwW1Yk6Hof4WbCF?usp=drive_link",
name_output_file = "[AI generated] June 2024.xlsx",
transaction_csv_path = 'downloaded_file.csv',
data_path = "trial2"
):
    os.system("apt update; yes | apt-get install poppler-utils; yes | ls")
    
    # breakpoint()
    source_folder_with_reciepts = source_folder_with_reciepts.split("?")[0].split("/")[-1]
    folder_to_save_processed_reciepts = folder_to_save_processed_reciepts.split("?")[0].split("/")[-1]
    folder_to_save_reconciled_data = folder_to_save_reconciled_data.split("?")[0].split("/")[-1]
    link_to_csv = link_to_csv.split("/view?")[0].split("/")[-1]
    print("Extracted link csv id: ", link_to_csv)
    name_output_file = name_output_file + ".xlsx"
    name_output_file = name_output_file.replace(".xlsx.xlsx", ".xlsx")
    # breakpoint()
    run_preprocessing(data_path, source_folder_with_reciepts, link_to_csv)
    print("Done pre-processing!")
    transcribe_all(data_path)
    print("Done transcription!")
    id_output = reconciliate_and_upload(
                            data_path,
                            name_of_csv=transaction_csv_path,
                            folder_to_save_processed_reciepts=folder_to_save_processed_reciepts,
                            folder_to_save_reconciled_data = folder_to_save_reconciled_data,
                            name_of_output=name_output_file)
    
    
    url_output_file = "https://drive.google.com/file/d/" + str(id_output)
    print("Done all!")
    return url_output_file