import google.generativeai as genai
import os
import pandas as pd
import io
import tempfile
from PyPDF2 import PdfReader
import re
import csv

def configure_gemini(api_key: str):
    """Configure Gemini API with the provided key"""
    genai.configure(api_key=api_key)

def analyze_pdf_directly(pdf_bytes: bytes, prompt: str, model_name: str = "gemini-1.5-pro"):
    """Analyze a PDF directly using Gemini's PDF support"""
    model = genai.GenerativeModel(model_name)
    
    # Create a temporary PDF file
    with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as tmp_file:
        tmp_file.write(pdf_bytes)
        tmp_file_path = tmp_file.name
    
    try:
        # Use the file upload feature
        response = model.generate_content(
            [prompt, genai.upload_file(tmp_file_path)]
        )
        print(f"Response: {response}")
        return response.text
    finally:
        # Clean up temporary file
        if os.path.exists(tmp_file_path):
            os.unlink(tmp_file_path)

def extract_response_text(response) -> str:
    """Extract text content from Gemini response object"""
    try:
        if hasattr(response, 'text'):
            return response.text
        elif hasattr(response, 'result') and hasattr(response.result, 'candidates'):
            for candidate in response.result.candidates:
                if hasattr(candidate, 'content') and hasattr(candidate.content, 'parts'):
                    for part in candidate.content.parts:
                        if hasattr(part, 'text'):
                            return part.text
        return str(response)
    except Exception as e:
        print(f"Error extracting response text: {str(e)}")
        return str(response)
    
def extract_csv_from_response(response) -> str:
    """Extract CSV data from Gemini response"""
    try:
        # Get the text content from the response
        response_text = extract_response_text(response)
        
        # Extract CSV content between ```csv markers
        csv_match = re.search(r'```csv(.*?)```', response_text, re.DOTALL)
        if csv_match:
            return csv_match.group(1).strip()
        
        # Fallback: Try to find any CSV-like content
        lines = []
        in_csv = False
        for line in response_text.split('\n'):
            if ',' in line and ('Category,' in line or 'Location,' in line):
                in_csv = True
            if in_csv:
                lines.append(line)
        if lines:
            return '\n'.join(lines)
        
        return response_text  # Return full response if no CSV found
    except Exception as e:
        print(f"Error extracting CSV: {str(e)}")
        return response.text if hasattr(response, 'text') else str(response)

def csv_to_dataframe(csv_data: str) -> pd.DataFrame:
    """Convert CSV string to pandas DataFrame with error handling"""
    if not csv_data.strip():
        return pd.DataFrame()
    
    try:
        # Clean line breaks and extra spaces
        cleaned_data = "\n".join([line.strip() for line in csv_data.split('\n') if line.strip()])
        
        # Use CSV reader to handle irregular fields
        rows = []
        reader = csv.reader(io.StringIO(cleaned_data), 
                        delimiter=',', 
                        quotechar='"',
                        skipinitialspace=True)
        
        header = next(reader)
        for row in reader:
            if len(row) > len(header):
                # Combine extra fields into the last column
                row = row[:len(header)-1] + [','.join(row[len(header)-1:])]
            rows.append(row)
        
        return pd.DataFrame(rows, columns=header)
    
    except Exception as e:
        print(f"CSV conversion error: {str(e)}")
        try:
            # Fallback to pandas with flexible parsing
            return pd.read_csv(io.StringIO(cleaned_data), 
                on_bad_lines='warn',
                engine='python',
                quotechar='"',
                skipinitialspace=True)
        except Exception as fallback_error:
            print(f"Fallback conversion failed: {str(fallback_error)}")
            return pd.DataFrame()


def save_csv(csv_data: str, filename: str) -> str:
    """Save CSV data to file"""
    with open(filename, 'w', newline='', encoding='utf-8') as csvfile:
        csvfile.write(csv_data.strip())
    return filename

def get_pdf_metadata(pdf_bytes: bytes) -> dict:
    """Extract basic PDF metadata"""
    reader = PdfReader(io.BytesIO(pdf_bytes))
    return {
        'page_count': len(reader.pages),
        'author': reader.metadata.author if reader.metadata else None,
        'title': reader.metadata.title if reader.metadata else None
    }