Source code for arborist.source

"""Source ABC.

Adding a new corpus to arborist = one new Source subclass. The Source contract
is intentionally minimal: yield Document objects, one at a time.
"""

from __future__ import annotations

from abc import ABC, abstractmethod
from typing import Iterator

from arborist.document import Document



[docs]
class Source(ABC):
    """A corpus that yields documents into the ingest pipeline."""

    #: source_type tag stored on every Document this source produces.
    source_type: str


[docs]
    @abstractmethod
    def iter_documents(self) -> Iterator[Document]:
        """Yield Document objects. Must be deterministic & idempotent."""
        ...