# Copyright 2026 The HuggingFace Team. All rights reserved.
# Licensed under the Apache License, Version 2.0.
"""Optional modular entry points for the separately installed RFD4 CIF preparation package."""

from pathlib import Path
from typing import ClassVar

import torch
from diffusers.modular_pipelines import (
    AutoPipelineBlocks,
    InputParam,
    ModularPipelineBlocks,
    OutputParam,
)


class RFD4PrepareCIFStep(ModularPipelineBlocks):
    """Prepare a single annotated input without loading generator weights."""

    _requirements: ClassVar = {"rfd4_proteina_prep": "==0.1.0", "atomworks": "==3.0.3"}

    @property
    def description(self):
        return "Prepare tensors and retain the atom mapping for annotated CIF export."

    @property
    def inputs(self):
        return [
            InputParam(
                "cif_path",
                required=True,
                type_hint=str,
                description="Local annotated CIF filename.",
            ),
            InputParam(
                "seed",
                default=42,
                type_hint=int,
                description="Seed for expandable segments.",
            ),
            InputParam(
                "device",
                default="cpu",
                type_hint=str,
                description="Device for returned tensors.",
            ),
            InputParam(
                "path_length_cutoff",
                default=64,
                type_hint=int,
                description="Topology path-length cutoff.",
            ),
        ]

    @property
    def intermediate_outputs(self):
        return [
            OutputParam(
                "features",
                type_hint=dict,
                description="Batched tensors, with coordinates in nanometers.",
            ),
            OutputParam(
                "atom_array", description="Original atom mapping; retain it for export."
            ),
        ]

    def __call__(self, components, state):
        block_state = self.get_block_state(state)
        path = Path(block_state.cif_path)
        if not path.is_file():
            raise FileNotFoundError(path)
        if type(block_state.seed) is not int:
            raise TypeError("seed must be an integer.")
        if (
            type(block_state.path_length_cutoff) is not int
            or block_state.path_length_cutoff < 1
        ):
            raise ValueError("path_length_cutoff must be a positive integer.")

        from rfd4_proteina_prep import prepare_cif

        features, atoms = prepare_cif(
            path,
            seed=block_state.seed,
            device=torch.device(block_state.device),
            path_length_cutoff=block_state.path_length_cutoff,
        )
        block_state.features = features
        block_state.atom_array = atoms
        self.set_block_state(state, block_state)
        return components, state


class RFD4ExportCIFStep(ModularPipelineBlocks):
    """Export one decoded design through the same package used for preparation."""

    _requirements: ClassVar = {"rfd4_proteina_prep": "==0.1.0", "atomworks": "==3.0.3"}

    @property
    def description(self):
        return "Write a new annotated CIF, preserving conditions and insertion mapping; never overwrite a file."

    @property
    def inputs(self):
        return [
            InputParam(
                "pipeline_output",
                required=True,
                description="RFD4ProteinaPipelineOutput with torch tensors.",
            ),
            InputParam(
                "features",
                required=True,
                type_hint=dict,
                description="The features used for this design batch.",
            ),
            InputParam(
                "atom_array",
                required=True,
                description="Atom mapping returned during preparation.",
            ),
            InputParam(
                "output_path",
                required=True,
                type_hint=str,
                description="New .cif filename; parent must exist.",
            ),
            InputParam(
                "row",
                default=0,
                type_hint=int,
                description="Batch row to export using this atom mapping.",
            ),
        ]

    @property
    def intermediate_outputs(self):
        return [
            OutputParam(
                "cif_path",
                type_hint=str,
                description="Written CIF path; coordinates are in angstroms.",
            )
        ]

    def __call__(self, components, state):
        block_state = self.get_block_state(state)
        path = Path(block_state.output_path)
        if path.suffix.lower() != ".cif":
            raise ValueError("output_path must end in .cif.")
        if path.exists() or path.is_symlink():
            raise FileExistsError(path)
        if not path.parent.is_dir():
            raise FileNotFoundError(path.parent)
        batch_size, tokens = block_state.features["padding_mask"].shape
        if type(block_state.row) is not int or not 0 <= block_state.row < batch_size:
            raise ValueError("row must select a batch row in features.")
        output = block_state.pipeline_output
        for name, shape in {
            "coords_nm": (batch_size, tokens, 37, 3),
            "residue_type": (batch_size, tokens),
            "atom_mask": (batch_size, tokens, 37),
            "insertion_logits": (batch_size, tokens, tokens),
        }.items():
            value = getattr(output, name)
            if not isinstance(value, torch.Tensor) or tuple(value.shape) != shape:
                raise ValueError(
                    f"pipeline_output.{name} must be a torch tensor with shape {shape}."
                )

        from rfd4_proteina_prep import write_cif

        block_state.cif_path = write_cif(
            output,
            block_state.features,
            block_state.atom_array,
            path,
            row=block_state.row,
        )
        self.set_block_state(state, block_state)
        return components, state


class RFD4CIFBlocks(AutoPipelineBlocks):
    """Prepare a CIF, or export when pipeline_output is provided; never perform model inference."""

    block_classes: ClassVar = [RFD4ExportCIFStep, RFD4PrepareCIFStep]
    block_names: ClassVar = ["export", "prepare"]
    block_trigger_inputs: ClassVar = ["pipeline_output", None]