from etl.utils.logger import Logger
import logging
import pymupdf


class pdfReaderToText():

    def __init__(self, file_path):
        self.source_path = file_path
        self.logger = Logger(name='pdfReader', level=logging.DEBUG).get_logger()
        self.all_text = ""
        self.text_list = []
        self.get_text_from_pdf_file()

    def get_text_from_pdf_file(self):
        self.logger.debug(f"Extrating text from {self.source_path}")
        pdf = pymupdf.open(self.source_path)

        for page in pdf:
            text = page.get_text()
            self.all_text += text

        self.text_list = self.all_text.split('\n')
        
    def get_list_of_test(self):
        return self.text_list