# database.py
import chromadb
from parser import parse_python_code, create_vector
import os
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np
from datasets import Dataset, load_dataset
from transformers import AutoTokenizer, AutoModel
import torch
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

# User-configurable variables (no HF_KEY hardcoded here)
DB_NAME = "python_programs"  # ChromaDB collection name
HF_DATASET_NAME = "python_program_vectors"  # Hugging Face Dataset name
PERSIST_DIR = "./chroma_data"  # Directory for persistent storage (optional)
USE_GPU = False  # Default to CPU, set to True for GPU if available

def init_chromadb(persist_dir=PERSIST_DIR):
    """Initialize ChromaDB client, optionally with persistent storage."""
    try:
        # Use persistent storage if directory exists, otherwise in-memory
        if os.path.exists(persist_dir):
            client = chromadb.PersistentClient(path=persist_dir)
        else:
            client = chromadb.Client()
        return client
    except Exception as e:
        print(f"Error initializing ChromaDB: {e}")
        return chromadb.Client()  # Fallback to in-memory

def create_collection(client, collection_name=DB_NAME):
    """Create or get a ChromaDB collection for Python programs."""
    try:
        collection = client.get_collection(name=collection_name)
    except:
        collection = client.create_collection(name=collection_name)
    return collection

def store_program(client, code, sequence, vectors, collection_name=DB_NAME):
    """Store a program in ChromaDB with its code, sequence, and vectors."""
    collection = create_collection(client, collection_name)
    
    # Flatten vectors to ensure they are a list of numbers (ChromaDB expects flat embeddings)
    flattened_vectors = [item for sublist in vectors for item in sublist]
    
    # Store program data (ID, code, sequence, vectors)
    program_id = str(hash(code))  # Use hash of code as ID for uniqueness
    collection.add(
        documents=[code],
        metadatas=[{"sequence": ",".join(sequence), "description_tokens": " ".join(generate_description_tokens(sequence, vectors))}],
        ids=[program_id],
        embeddings=[flattened_vectors]  # Pass as flat list
    )
    return program_id

def populate_sample_db(client):
    """Populate ChromaDB with sample Python programs."""
    samples = [
        """
        import os
        def add_one(x):
            y = x + 1
            return y
        """,
        """
        def multiply(a, b):
            c = a * b
            if c > 0:
                return c
        """
    ]
    
    for code in samples:
        parts, sequence = parse_python_code(code)
        vectors = [part['vector'] for part in parts]
        store_program(client, code, sequence, vectors)

def query_programs(client, operations, collection_name=DB_NAME, top_k=5, semantic_query=None):
    """Query ChromaDB for programs matching the operations sequence or semantic description."""
    collection = create_collection(client, collection_name)
    
    if semantic_query:
        # Semantic search using a 6D vector generated from the description
        query_vector = generate_semantic_vector(semantic_query)
        results = collection.query(
            query_embeddings=[query_vector],
            n_results=top_k,
            include=["documents", "metadatas"]
        )
    else:
        # Vector-based search for operations sequence
        query_vector = sum([create_vector(op, 0, (1, 1), 100, []) for op in operations], []) / len(operations) if operations else [0] * 6
        results = collection.query(
            query_embeddings=[query_vector],
            n_results=top_k,
            include=["documents", "metadatas"]
        )
    
    # Process results
    matching_programs = []
    for doc, meta in zip(results['documents'][0], results['metadatas'][0]):
        sequence = meta['sequence'].split(',')
        if not semantic_query or is_subsequence(operations, sequence):  # Ensure sequence match for operations
            try:
                # Reconstruct program vectors (flatten if needed)
                doc_vectors = eval(doc['vectors']) if isinstance(doc['vectors'], str) else doc['vectors']
                if isinstance(doc_vectors, (list, np.ndarray)) and len(doc_vectors) == 6:
                    program_vector = doc_vectors  # Single flat vector
                else:
                    program_vector = np.mean([v for v in doc_vectors if isinstance(v, (list, np.ndarray))], axis=0).tolist()
            except:
                program_vector = [0] * 6  # Fallback for malformed vectors
            similarity = cosine_similarity([query_vector], [program_vector])[0][0] if program_vector and query_vector else 0
            matching_programs.append({'id': meta['id'], 'code': doc, 'similarity': similarity, 'description': meta.get('description_tokens', '')})
    
    return sorted(matching_programs, key=lambda x: x['similarity'], reverse=True)

def create_vector(category, level, location, total_lines, parent_path):
    """Helper to create a vector for query (matches parser's create_vector)."""
    category_map = {
        'import': 1, 'function': 2, 'async_function': 3, 'class': 4,
        'if': 5, 'while': 6, 'for': 7, 'try': 8, 'expression': 9, 'spacer': 10,
        'other': 11, 'elif': 12, 'else': 13, 'except': 14, 'finally': 15, 'return': 16,
        'assigned_variable': 17, 'input_variable': 18, 'returned_variable': 19
    }
    category_id = category_map.get(category, 0)
    start_line, end_line = location
    span = (end_line - start_line + 1) / total_lines
    center_pos = ((start_line + end_line) / 2) / total_lines
    parent_depth = len(parent_path)
    parent_weight = sum(category_map.get(parent.split('[')[0].lower(), 0) * (1 / (i + 1)) 
                        for i, parent in enumerate(parent_path)) / max(1, len(category_map))
    return [category_id, level, center_pos, span, parent_depth, parent_weight]

def is_subsequence(subseq, seq):
    """Check if subseq is a subsequence of seq."""
    it = iter(seq)
    return all(item in it for item in subseq)

def generate_description_tokens(sequence, vectors):
    """Generate semantic description tokens for a program based on its sequence and vectors."""
    tokens = []
    category_descriptions = {
        'import': 'imports module',
        'function': 'defines function',
        'assigned_variable': 'assigns variable',
        'input_variable': 'input parameter',
        'returned_variable': 'returns value',
        'if': 'conditional statement',
        'return': 'returns result',
        'try': 'try block',
        'except': 'exception handler',
        'expression': 'expression statement',
        'spacer': 'empty line or comment'
    }
    
    for cat, vec in zip(sequence, vectors):
        if cat in category_descriptions:
            tokens.append(f"{category_descriptions[cat]}:{cat}")
            # Add vector-derived features (e.g., level, span) as tokens
            tokens.append(f"level:{vec[1]}")
            tokens.append(f"span:{vec[3]:.2f}")
    return tokens

def generate_semantic_vector(description, total_lines=100):
    """Generate a 6D semantic vector for a textual description, matching our vector format."""
    # Use a simplified heuristic to map description to our 6D vector format
    category_map = {
        'import': 1, 'function': 2, 'assign': 17, 'input': 18, 'return': 19, 'if': 5, 'try': 8, 'except': 14
    }
    
    # Parse description for key terms
    tokens = description.lower().split()
    vector = [0] * 6  # Initialize 6D vector
    
    # Map description tokens to categories and assign basic vector values
    for token in tokens:
        for cat, cat_id in category_map.items():
            if cat in token:
                vector[0] = cat_id  # category_id
                vector[1] = 1  # level (assume top-level for simplicity)
                vector[2] = 0.5  # center_pos (midpoint of code)
                vector[3] = 0.1  # span (small for simplicity)
                vector[4] = 1  # parent_depth (shallow)
                vector[5] = cat_id / len(category_map)  # parent_weight (normalized)
                break
    
    return vector

def save_chromadb_to_hf(dataset_name=HF_DATASET_NAME, token=os.getenv("HF_KEY")):
    """Save ChromaDB data to Hugging Face Dataset."""
    client = init_chromadb()
    collection = create_collection(client)
    
    # Fetch all data from ChromaDB
    results = collection.get(include=["documents", "metadatas", "embeddings"])
    data = {
        "code": results["documents"],
        "sequence": [meta["sequence"] for meta in results["metadatas"]],
        "vectors": results["embeddings"],  # ChromaDB already flattens embeddings
        "description_tokens": [meta.get('description_tokens', '') for meta in results["metadatas"]]
    }
    
    # Create a Hugging Face Dataset
    dataset = Dataset.from_dict(data)
    
    # Push to Hugging Face Hub
    dataset.push_to_hub(dataset_name, token=token)
    print(f"Dataset pushed to Hugging Face Hub as {dataset_name}")

def load_chromadb_from_hf(dataset_name=HF_DATASET_NAME, token=os.getenv("HF_KEY")):
    """Load ChromaDB data from Hugging Face Dataset, handle empty dataset."""
    try:
        dataset = load_dataset(dataset_name, split="train", token=token)
    except Exception as e:
        print(f"Error loading dataset from Hugging Face: {e}. Populating with samples...")
        client = init_chromadb()
        populate_sample_db(client)
        save_chromadb_to_hf()  # Create and push a new dataset
        return init_chromadb()
    
    client = init_chromadb()
    collection = create_collection(client)
    
    for item in dataset:
        collection.add(
            documents=[item["code"]],
            metadatas=[{"sequence": item["sequence"], "description_tokens": item["description_tokens"]}],
            ids=[str(hash(item["code"]))],
            embeddings=[item["vectors"]]
        )
    return client

if __name__ == '__main__':
    client = load_chromadb_from_hf()
    # Uncomment to save to Hugging Face
    # save_chromadb_to_hf()