from __future__ import annotations
from dataclasses import dataclass, field


@dataclass
class ChunkerConfig:
    max_chars: int = 1200
    min_chars: int = 80
    target_chars: int = 800
    context_depth: int = 3
    skip_headings: set[str] = field(default_factory=lambda: {
        "indice",
        "sommario",
        "bibliografia",
        "ringraziamenti",
        "abbreviazioni",
    })
    skip_pre_heading: bool = True
    merge_short: bool = True
    atomic_types: set[str] = field(default_factory=lambda: {
        "table", "code", "list", "math", "html",
    })
    fail_on_broken_fence: bool = True
    fail_on_content_loss: bool = False