import fitz  # PyMuPDF
import docx
import os

def extract_text_from_file(file_path: str, original_filename: str) -> str:
    """
    Enterprise router that ingests a file, identifies its type, 
    and extracts raw text for the LLM pipeline.
    """
    # Get the file extension and convert to lowercase
    _, file_extension = os.path.splitext(original_filename)
    ext = file_extension.lower()

    try:
        # Route 1: PDF Extraction
        if ext == '.pdf':
            return _extract_from_pdf(file_path)
            
        # Route 2: Word Document Extraction
        elif ext in ['.docx', '.doc']:
            return _extract_from_docx(file_path)
            
        # Route 3: Plain Text / Markdown Extraction
        elif ext in ['.txt', '.md', '.csv']:
            with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
                return f.read()
                
        # The Bouncer: Reject unsupported files gracefully
        else:
            raise ValueError(f"Unsupported file type: {ext}. Please upload PDF, DOCX, or TXT.")

    except Exception as e:
        raise RuntimeError(f"Failed to parse document: {str(e)}")

# --- Private Helper Functions ---

def _extract_from_pdf(file_path: str) -> str:
    text_content = []
    # fitz opens the document securely
    with fitz.open(file_path) as doc:
        for page_num in range(len(doc)):
            page = doc.load_page(page_num)
            text_content.append(page.get_text("text"))
    
    # Clean up the output by joining pages and stripping excess whitespace
    return "\n".join(text_content).strip()

def _extract_from_docx(file_path: str) -> str:
    doc = docx.Document(file_path)
    text_content = [paragraph.text for paragraph in doc.paragraphs if paragraph.text.strip()]
    return "\n".join(text_content).strip()