tools/text_processing.py

from langchain_core.tools import tool
import re
from datetime import datetime, timedelta
import json

@tool
def extract_numbers(text: str) -> str:
    """
    Extracts all numbers from a text string and returns them as a comma-separated list.
    Useful for parsing numerical data from search results or documents.
    
    Args:
        text (str): The text to extract numbers from
        
    Returns:
        str: Comma-separated list of numbers found in the text
    """
    if not text:
        return ""
    
    # Find all numbers (integers and floats)
    numbers = re.findall(r'-?\d+\.?\d*', text)
    return ', '.join(numbers) if numbers else ""

@tool
def count_words(text: str) -> int:
    """
    Counts the number of words in a text string.
    
    Args:
        text (str): The text to count words in
        
    Returns:
        int: Number of words in the text
    """
    if not text:
        return 0
    
    # Split by whitespace and filter out empty strings
    words = [word for word in text.split() if word.strip()]
    return len(words)

@tool
def extract_dates(text: str) -> str:
    """
    Extracts date patterns from text and returns them in a standardized format.
    Supports various date formats including YYYY, YYYY-MM-DD, MM/DD/YYYY, etc.
    
    Args:
        text (str): The text to extract dates from
        
    Returns:
        str: Comma-separated list of dates found in the text
    """
    if not text:
        return ""
    
    date_patterns = [
        r'\b\d{4}-\d{2}-\d{2}\b',  # YYYY-MM-DD
        r'\b\d{2}/\d{2}/\d{4}\b',  # MM/DD/YYYY
        r'\b\d{1,2}/\d{1,2}/\d{2,4}\b',  # M/D/YY or MM/DD/YYYY
        r'\b\d{4}\b',  # Just years
        r'\b(January|February|March|April|May|June|July|August|September|October|November|December)\s+\d{1,2},?\s+\d{4}\b',  # Month DD, YYYY
    ]
    
    dates = []
    for pattern in date_patterns:
        matches = re.findall(pattern, text, re.IGNORECASE)
        dates.extend(matches)
    
    return ', '.join(dates) if dates else ""

@tool
def clean_text(text: str) -> str:
    """
    Cleans text by removing extra whitespace, special characters, and normalizing format.
    Useful for processing scraped or extracted text.
    
    Args:
        text (str): The text to clean
        
    Returns:
        str: Cleaned text
    """
    if not text:
        return ""
    
    # Remove extra whitespace
    cleaned = re.sub(r'\s+', ' ', text)
    # Remove leading/trailing whitespace
    cleaned = cleaned.strip()
    # Remove common unwanted characters but keep basic punctuation
    cleaned = re.sub(r'[^\w\s.,!?()-]', '', cleaned)
    
    return cleaned