tools/file_loader.py

import io
import os
import pandas as pd
from PyPDF2 import PdfReader

def read_pdf(file_bytes: bytes) -> str:
    """
    Extracts text from a PDF file provided as bytes.
    """
    try:
        reader = PdfReader(io.BytesIO(file_bytes))
        text = ""
        for page in reader.pages:
            text += page.extract_text() or ""
        return text.strip()
    except Exception as e:
        return f"[ERROR] Failed to read PDF: {e}"

def read_csv(file_bytes: bytes) -> str:
    """
    Reads the first few rows of a CSV file provided as bytes.
    """
    try:
        df = pd.read_csv(io.BytesIO(file_bytes))
        return df.head(10).to_string(index=False)
    except Exception as e:
        return f"[ERROR] Failed to read CSV: {e}"

def read_txt(file_bytes: bytes) -> str:
    """
    Reads a plain text file provided as bytes.
    """
    try:
        return file_bytes.decode('utf-8').strip()
    except UnicodeDecodeError:
        return file_bytes.decode('latin1', errors='ignore').strip()
    except Exception as e:
        return f"[ERROR] Failed to read TXT: {e}"

def load_file_if_any(file_path: str) -> str:
    """
    Loads and reads file content based on file extension.
    Supports .pdf, .csv, .txt files. Returns "" if no file.
    """
    if not file_path or not os.path.exists(file_path):
        return ""
    
    try:
        with open(file_path, "rb") as f:
            file_bytes = f.read()
        
        if file_path.endswith(".pdf"):
            return read_pdf(file_bytes)
        elif file_path.endswith(".csv"):
            return read_csv(file_bytes)
        elif file_path.endswith(".txt"):
            return read_txt(file_bytes)
        else:
            return "[WARNING] Unsupported file format."
    except Exception as e:
        return f"[ERROR] Failed to load file: {e}"