"""
Utility helpers: document loading, env validation, stats.
Reconstructed to match the interface app.py imports.
"""

import os
from pathlib import Path
from typing import List

from langchain.schema import Document
from langchain_community.document_loaders import (
    PyPDFLoader,
    TextLoader,
    Docx2txtLoader,
)

REQUIRED_ENV_VARS = [
    "PINECONE_API_KEY",
    "PINECONE_INDEX_NAME",
    "OPENAI_API_KEY",
]

SUPPORTED_EXTENSIONS = {".pdf", ".txt", ".md", ".docx"}


def validate_env_variables() -> bool:
    """Return True only if every required environment variable is set and non-empty."""
    return all(os.getenv(var) for var in REQUIRED_ENV_VARS)


def _loader_for(file_path: str):
    """Pick the right LangChain loader for a file extension."""
    ext = Path(file_path).suffix.lower()
    if ext == ".pdf":
        return PyPDFLoader(file_path)
    if ext == ".docx":
        return Docx2txtLoader(file_path)
    if ext in {".txt", ".md"}:
        return TextLoader(file_path, encoding="utf-8")
    raise ValueError(f"Unsupported file type: {ext}")


def load_document(file_path: str) -> List[Document]:
    """Load a single document into a list of LangChain Document objects."""
    path = Path(file_path)
    if not path.exists():
        raise FileNotFoundError(f"File not found: {file_path}")

    docs = _loader_for(str(path)).load()
    for doc in docs:
        doc.metadata.setdefault("source", path.name)
    return docs


def load_documents_from_directory(directory_path: str) -> List[Document]:
    """Load every supported document in a directory (recursively)."""
    directory = Path(directory_path)
    if not directory.exists():
        raise FileNotFoundError(f"Directory not found: {directory_path}")

    documents: List[Document] = []
    for path in sorted(directory.rglob("*")):
        if path.is_file() and path.suffix.lower() in SUPPORTED_EXTENSIONS:
            try:
                documents.extend(load_document(str(path)))
            except Exception as exc:  # noqa: BLE001
                print(f"Skipped {path.name}: {exc}")
    return documents


def get_document_stats(documents: List[Document]) -> dict:
    """Summarize a batch of loaded documents."""
    total_characters = sum(len(doc.page_content) for doc in documents)
    sources = sorted(
        {doc.metadata.get("source", "Unknown") for doc in documents}
    )
    return {
        "total_documents": len(documents),
        "total_characters": total_characters,
        "sources": sources,
    }


def format_file_size(num_bytes: int) -> str:
    """Human-readable file size."""
    size = float(num_bytes)
    for unit in ["B", "KB", "MB", "GB", "TB"]:
        if size < 1024.0:
            return f"{size:.1f} {unit}"
        size /= 1024.0
    return f"{size:.1f} PB"