functions/gradio.py

"""
gradio.py

Functions for handling Gradio UI interactions and processing user inputs.
"""

import logging
from pathlib import Path
from functions.helper import clean_text_whitespace
from functions.linkedin_resume import extract_text
from functions.github import get_github_repositories
from functions.job_call import summarize_job_call
from functions.writer_agent import write_resume

# pylint: disable=broad-exception-caught

# Set up logging
# Create logs directory if it doesn't exist
logs_dir = Path(__file__).parent.parent / "logs"
logs_dir.mkdir(exist_ok=True)

# Strip extraneous handlers
for handler in logging.root.handlers[:]:
    logging.root.removeHandler(handler)

# Configure logging to write to file and console
logging.basicConfig(
    level=logging.INFO,
    format='%(name)s - %(levelname)s - %(message)s',
    handlers=[
        logging.FileHandler(logs_dir / "gradio.log", mode='w'),  # Log to file
        logging.StreamHandler()  # Also log to console
    ]
)


def process_inputs(
        linkedin_pdf_path: str = None,
        github_username: str = None,
        job_post_text: str = None,
):
    """
    Process the input files and URLs from the Gradio interface.

    Args:
        linkedin_pdf: (str) Path to uploaded LinkedIn resume export PDF file
        github_username (str): GitHub profile URL
        job_post_text (str): Job post text content

    Returns:
        str: Formatted output with file and URL information
    """

    logger = logging.getLogger(f'{__name__}.process_inputs')
    logger.info("LinkedIn PDF: %s", linkedin_pdf_path)
    logger.info("GitHub username: %s", github_username)
    logger.info("Job post: %s", clean_text_whitespace(job_post_text[:100]).replace("\n", " "))

    # ==================================================================== #
    # Extract and structure text from the linkedin profile PDF
    logger.info("Extracting text from LinkedIn PDF: %s", linkedin_pdf_path)
    linkedin_resume = extract_text(linkedin_pdf_path)

    if linkedin_resume:
        logger.info("LinkedIn PDF text extraction successful")

    else:
        logger.error("LinkedIn PDF text extraction failed")

    # ==================================================================== #
    # Process GitHub profile
    logger.info("Processing GitHub profile: %s", github_username.strip())

    # Retrieve repositories from GitHub
    github_repositories = get_github_repositories(github_username.strip())

    if github_repositories:
        logger.info("GitHub repositories retrieved successfully")

    else:
        logger.error("GitHub repositories retrieval failed")

    # ==================================================================== #
    # Process job post text
    logger.info("Processing job post (%d characters)", len(job_post_text))

    # Parse the job post text
    job_post = summarize_job_call(job_post_text.strip())

    if job_post:
        logger.info("Job post parsed successfully")

    else:
        logger.error("Job post parsing failed")

    # ==================================================================== #
    # Generate resume only if we have valid extraction results
    result = ""

    if linkedin_resume and github_repositories and job_post:
        logger.info("Generating resume with provided data")

        try:
            result = write_resume(linkedin_resume, github_repositories, job_post)

        except Exception as e:
            logger.error("Resume generation failed: %s", str(e))
            result = ""
    else:
        logger.warning("Resume generation skipped - content missing")

    return result