ab19f78507
haiku.rag.ingester.sources was never ingester-only: one-shot client ingestion resolves adapters through it (create_document_from_source), and convert() now fetches through HTTPSource, so the core client imported into the ingester package to reach them. Move the package to haiku.rag.sources and update every import. No shims: haiku.rag.ingester.sources is gone. The haiku.rag.sources plugin entry-point group is unchanged, so third-party source packages need no edit — the group name now matches the module path it always implied. Source unit tests move to tests/sources/. test_source_plugins.py stays in tests/ingester/: it drives a PeriodicPoller against the job repo, so it is plugin wiring through ingester machinery rather than a source test.
74 lines
1.8 KiB
Python
74 lines
1.8 KiB
Python
from datetime import UTC, datetime
|
|
|
|
from haiku.rag.sources.base import (
|
|
FetchResult,
|
|
Source,
|
|
SourceEvent,
|
|
SourceEventKind,
|
|
)
|
|
|
|
|
|
def test_source_event_kind_values():
|
|
assert SourceEventKind.UPSERT.value == "upsert"
|
|
assert SourceEventKind.DELETE.value == "delete"
|
|
assert SourceEventKind.UNCHANGED.value == "unchanged"
|
|
|
|
|
|
def test_source_event_round_trip():
|
|
event = SourceEvent(
|
|
source_id="fs:/tmp/docs",
|
|
uri="file:///tmp/docs/a.md",
|
|
kind=SourceEventKind.UPSERT,
|
|
revision="123456",
|
|
discovered_at=datetime(2026, 5, 20, 12, 0, 0, tzinfo=UTC),
|
|
)
|
|
raw = event.model_dump_json()
|
|
again = SourceEvent.model_validate_json(raw)
|
|
assert again == event
|
|
|
|
|
|
def test_fetch_result_round_trip():
|
|
result = FetchResult(
|
|
uri="file:///tmp/docs/a.md",
|
|
body=b"hello",
|
|
content_type="text/markdown",
|
|
content_hash="abcd1234",
|
|
revision="123456",
|
|
extra_metadata={"source": "fs"},
|
|
)
|
|
raw = result.model_dump_json()
|
|
again = FetchResult.model_validate_json(raw)
|
|
assert again == result
|
|
|
|
|
|
def test_fetch_result_defaults_extra_metadata_to_empty():
|
|
result = FetchResult(
|
|
uri="file:///tmp/docs/a.md",
|
|
body=b"x",
|
|
content_type="text/markdown",
|
|
content_hash="x",
|
|
revision=None,
|
|
)
|
|
assert result.extra_metadata == {}
|
|
|
|
|
|
def test_source_protocol_runtime_checkable():
|
|
class Dummy:
|
|
source_id = "dummy"
|
|
|
|
def supports(self, uri: str) -> bool:
|
|
return True
|
|
|
|
async def aclose(self) -> None:
|
|
pass
|
|
|
|
async def head(self, uri: str):
|
|
return None
|
|
|
|
async def fetch(self, uri: str):
|
|
raise NotImplementedError
|
|
|
|
def discover(self, since=None):
|
|
raise NotImplementedError
|
|
|
|
assert isinstance(Dummy(), Source)
|