chemenu/tools/chemenu/search/registry.py

"""Backend selection.

One registry entry today. It exists so that adding a semantic/vector backend is
a new module plus one line here - not a change to the command, the filters, or
the output shape. Selecting several at once fuses them through RRF.
"""
from __future__ import annotations

import os
from pathlib import Path
from typing import Callable, Optional

from chemenu.errors import ValidationError
from chemenu.search.base import SearchBackend
from chemenu.search.ripgrep import RipgrepBackend

DEFAULT_BACKEND = "rg"
ENV_VAR = "WIKITOOL_SEARCH_BACKEND"

BACKENDS: dict[str, Callable[..., SearchBackend]] = {
    "rg": RipgrepBackend,
}


class UnknownBackend(ValidationError):
    pass


def resolve(
    spec: str | None = None,
    kb_dir: Optional[Path] = None,
    root: Optional[Path] = None,
) -> list[SearchBackend]:
    """Resolve a backend spec into instances.

    Precedence: explicit argument, then `WIKITOOL_SEARCH_BACKEND`, then the
    default. A comma-separated spec selects several and fuses their rankings.

    `kb_dir`/`root` are handed to the backend rather than left to its own
    defaults. Without them a caller could pass a corpus to `run_search` and
    still have the backend walk `config.KB_DIR` - the query answered from one
    tree and the pages read from another, with nothing saying so.
    """
    raw = spec or os.environ.get(ENV_VAR) or DEFAULT_BACKEND
    names = [n.strip() for n in raw.split(",") if n.strip()]
    unknown = [n for n in names if n not in BACKENDS]
    if unknown:
        raise UnknownBackend(
            f"unknown search backend(s): {', '.join(unknown)}. "
            f"Available: {', '.join(sorted(BACKENDS))}"
        )
    return [BACKENDS[name](kb_dir, root) for name in names]