import os
from pdfReader.pdfReaderToText import pdfReaderToText
from etl.scraper.scraper import SharePointScraper, SharePointInstaller
from pprint import pprint, pformat
import logging
from etl.utils.logger import Logger
from etl.validator.validator import DomnaSharePointValidator

logger = Logger(name="main.py", level=logging.DEBUG).get_logger()
DATA_LOC_1 = "/tmp/sharepoint/Abdul Koddus/W.C. 03.03.2025/Southern Housing/10 Turnberry Close TN38 0WL/PRE SITE NOTES.pdf"
DATA_LOC_2 = "/tmp/sharepoint/Abdul Koddus/W.C. 03.03.2025/Southern Housing/16 Sunningdale Drive TN38 0WB/PRE SITE NOTES.pdf"

# Extract and trasform
pdfReader = pdfReaderToText(DATA_LOC_1)
doc2 = pdfReader.get_reader()
pdfReader2 = pdfReaderToText(DATA_LOC_2)
doc1 = pdfReader2.get_reader()
print(doc1.survey_information)

# Transform

def main():
    # south_coast_scraper = SharePointScraper(SharePointInstaller.SOUTH_COAST_INSULATION_SERVICE, development = True)
    # south_coast_scraper.download_file_for_each_address()
    pass


if __name__ == "__main__":
    main()


# Current todo list

# - [x] Finish off scraping for section that I need to finish
# - [] Pydantic format for deemed report
# - [] Generate deemed report
# - [] Docker compose to an sql database in docker compose (2 hours, then work on sql)
# - [] Deploy via terraform to aws (1 day)