Source code for arborist.distill.base

"""Distiller ABC.

A Distiller compresses a surface Document into a core Document. The runner
generates Merkle proofs for every contributing source chunk so the resulting
derivation row cryptographically binds the core back to its source.
"""

from __future__ import annotations

from abc import ABC, abstractmethod
from dataclasses import dataclass

from arborist.document import Document




@dataclass
class DistillationResult:
    """What a Distiller returns for one source.

    contributing_chunk_indices: 0-based indices into source_chunks that fed
    the core's content. The runner Merkle-proves each one against the
    source's document_root and stores those proofs in derivations.proof_blob.
    """

    core: Document
    contributing_chunk_indices: list[int]





class Distiller(ABC):
    """Pure function: surface Document + its chunks -> core DistillationResult.

    Distillers must be deterministic — same source bytes produce the same core
    bytes. Bumping a distiller's algorithm requires bumping its `name`.
    """

    name: str



    @abstractmethod
    def distill(
        self, source: Document, source_chunks: list[str]
    ) -> DistillationResult:
        ...