csv_processor.py

import hashlib
import csv
import os


def hash_md5(filepath):
    md5_hash = hashlib.md5()
    try:
        with open(filepath, "rb") as file:
            for chunk in iter(lambda: file.read(128 * md5_hash.block_size), b''):
                md5_hash.update(chunk)
        return md5_hash.hexdigest()
    except Exception as e:
        return str(e)
CSV_FILE_PATH = "audio_plus_hash_uniq_07102024.csv"

def update_csv_with_files(csv_file_path, audio_old_path, audio_16000_path, new_transcription):
    hash_old = hash_md5(audio_old_path)
    hash_new = hash_md5(audio_16000_path)
    update_csv(csv_file_path, hash_old, hash_new, audio_old_path, new_transcription)

def update_csv(csv_file_path, search_hash, hash_16000, new_path, new_transcription):
    # Use read/write mode to modify the relevant line or append if not found
    with open(csv_file_path, mode='r+', newline='', encoding='utf-8') as file:
        reader = csv.DictReader(file)
        fieldnames = reader.fieldnames
        rows = list(reader)
        found = False
        
        # Locate the row with the matching hash
        for i, row in enumerate(rows):
            if row['hash'] == search_hash or row['hash_16000'] == search_hash:
                rows[i]['hash_16000'] = hash_16000
                rows[i]['transcription'] = new_transcription
                found = True
                break
        
        if found:
            # Move file pointer to the beginning and write only the updated row
            file.seek(0)  # Go to the beginning of the file
            writer = csv.DictWriter(file, fieldnames=fieldnames)
            writer.writeheader()  # Ensure the header is written
            writer.writerows(rows)  # Write all rows back, with the updated one
        return 
    # Append a new row if the hash is not found
    with open(csv_file_path, mode='a', newline='', encoding='utf-8') as append_file:
        writer = csv.DictWriter(append_file, fieldnames=fieldnames)
        writer.writerow({
            'hash': search_hash,
            'hash_16000': hash_16000,
            'filepath': new_path,
            'transcription': new_transcription
        })