import gradio as gr
from utils import SafeProgress
from embeddings import create_product_embeddings
from similarity import compute_similarities
from chicory_api import call_chicory_parser
from ui_core import embeddings, parse_input
from ui_formatters import format_categories_html, create_results_container
from openai_expansion import expand_product_descriptions

def categorize_products(product_input, is_file=False, use_expansion=False, top_n=10, confidence_threshold=0.5):
    """Categorize products from text input or file"""
    progress_tracker = SafeProgress(gr.Progress())
    progress_tracker(0, desc="Starting...")

    # Parse input
    product_names, error = parse_input(product_input, is_file)
    if error:
        return error

    # Validate embeddings are loaded
    if not embeddings:
        return "<div style='color: #d32f2f; font-weight: bold; padding: 20px;'>Error: No ingredient embeddings loaded. Please check that the embeddings file exists and is properly formatted.</div>"

    # Optional description expansion
    expanded_descriptions = {}
    if use_expansion:
        progress_tracker(0.2, desc="Expanding product descriptions...")
        expanded_descriptions = expand_product_descriptions(product_names, progress=gr.Progress())

    # Create embeddings
    progress_tracker(0.4, desc="Generating product embeddings...")
    if use_expansion and expanded_descriptions:
        # Use expanded descriptions for embedding creation when available
        products_for_embedding = [expanded_descriptions.get(name, name) for name in product_names]
        # Map expanded descriptions back to original product names for consistent keys
        products_embeddings = {}
        temp_embeddings = create_product_embeddings(products_for_embedding, progress=gr.Progress())
        
        # Ensure we use original product names as keys
        for i, product_name in enumerate(product_names):
            if i < len(products_for_embedding) and products_for_embedding[i] in temp_embeddings:
                products_embeddings[product_name] = temp_embeddings[products_for_embedding[i]]
    else:
        # Standard embedding creation with just product names
        products_embeddings = create_product_embeddings(product_names, progress=gr.Progress())
    
    if not products_embeddings:
        return "<div style='color: #d32f2f; font-weight: bold; padding: 20px;'>Error: Failed to generate product embeddings. Please try again with different product names.</div>"

    # Call Chicory Parser API
    progress_tracker(0.6, desc="Calling Chicory Parser API...")
    chicory_results = call_chicory_parser(product_names, progress=gr.Progress())

    # Compute similarities
    progress_tracker(0.8, desc="Computing similarities...")
    all_similarities = compute_similarities(embeddings, products_embeddings)

    # Format results
    progress_tracker(0.9, desc="Formatting results...")
    output_html = f"<p style='color: #555;'>Processing {len(product_names)} products.</p>"
    
    for product, similarities in all_similarities.items():
        filtered_similarities = [(ingredient, score) for ingredient, score in similarities if score >= confidence_threshold]
        top_similarities = filtered_similarities[:int(top_n)]
        
        # Add expansion explanation if available
        expansion_text = expanded_descriptions.get(product, "") if use_expansion else ""
        
        # Debug info for Chicory results
        chicory_data = chicory_results.get(product, [])
        output_html += format_categories_html(
            product, 
            top_similarities, 
            chicory_result=chicory_data,
            explanation=expansion_text,
            match_type="ingredients",
        )
        output_html += "<hr style='margin: 15px 0; border: 0; border-top: 1px solid #eee;'>"

    output_html += "</div>"
    if not all_similarities:
        output_html = "<div style='color: #d32f2f; font-weight: bold; padding: 20px;'>No results found. Please check your input or try different products.</div>"

    progress_tracker(1.0, desc="Done!")
    return create_results_container(output_html)