parser/text_cleaner.py

import re

def clean_text(text: str) -> str:
    """
    Cleans extracted resume text by:
    - Removing non-ASCII characters
    - Normalizing newlines and whitespace
    - Removing stray bullet points or symbols
    
    Args:
        text (str): Raw text input
    
    Returns:
        str: Cleaned and normalized text
    """
    # Remove non-ASCII characters
    text = re.sub(r'[^\x00-\x7F]+', ' ', text)

    # Replace common bullets or symbols with newline
    text = re.sub(r'[\u2022•●▪■◆►▶✔➤➔➣➢➥]', '\n', text)

    # Collapse multiple newlines into one
    text = re.sub(r'\n+', '\n', text)

    # Collapse multiple spaces into one
    text = re.sub(r'[ \t]+', ' ', text)

    # Remove excessive blank lines
    text = "\n".join(line.strip() for line in text.splitlines() if line.strip())

    return text.strip()