utils/text_utils.py

import re
from typing import List


def extract_dates(text: str) -> List[str]:
    """Extract dates from text"""
    patterns = [
        r'\b\d{1,2}[/-]\d{1,2}[/-]\d{2,4}\b',  # MM/DD/YYYY or DD-MM-YYYY
        r'\b\d{4}[/-]\d{1,2}[/-]\d{1,2}\b',    # YYYY-MM-DD
        r'\b(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]* \d{1,2},? \d{4}\b'  # Month DD, YYYY
    ]
    
    dates = []
    for pattern in patterns:
        dates.extend(re.findall(pattern, text, re.IGNORECASE))
    
    return list(set(dates))


def extract_amounts(text: str) -> List[str]:
    """Extract monetary amounts from text"""
    pattern = r'\$\s?\d+(?:,\d{3})*(?:\.\d{2})?'
    return re.findall(pattern, text)


def extract_emails(text: str) -> List[str]:
    """Extract email addresses from text"""
    pattern = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
    return re.findall(pattern, text)


def extract_phone_numbers(text: str) -> List[str]:
    """Extract phone numbers from text"""
    patterns = [
        r'\b\d{3}[-.]?\d{3}[-.]?\d{4}\b',  # 123-456-7890
        r'\(\d{3}\)\s*\d{3}[-.]?\d{4}\b'   # (123) 456-7890
    ]
    
    numbers = []
    for pattern in patterns:
        numbers.extend(re.findall(pattern, text))
    
    return list(set(numbers))


def clean_text(text: str) -> str:
    """Clean and normalize text"""
    # Remove extra whitespace
    text = re.sub(r'\s+', ' ', text)
    # Remove special characters (keep punctuation)
    text = re.sub(r'[^\w\s.,!?;:()\-\'\"]', '', text)
    return text.strip()