Dirk Riemann
118a9abd09
Adds the two Protocol-based client contracts the pipeline steps depend on, plus test-oriented fakes. Real engines (Surya, Ollama) land in Chunk 4. - ix.ocr.client.OCRClient — runtime_checkable Protocol with async ocr(). - ix.genai.client.GenAIClient — runtime_checkable Protocol with async invoke(); GenAIInvocationResult + GenAIUsage dataclasses carry the parsed model, token usage, and model name. - FakeOCRClient / FakeGenAIClient: return canned results; both expose a raise_on_call hook for error-path tests. 8 unit tests across tests/unit/test_ocr_fake.py + test_genai_fake.py confirm protocol conformance, canned-return behaviour, usage/model-name defaults, and raise_on_call propagation. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
"""FakeOCRClient — returns a canned :class:`OCRResult` for hermetic tests.
|
|
|
|
Used by every pipeline unit test to avoid booting Surya / CUDA. The
|
|
``raise_on_call`` hook lets error-path tests exercise ``IX_002_000``-style
|
|
code paths without needing to forge network errors.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from ix.contracts import OCRResult, Page
|
|
|
|
|
|
class FakeOCRClient:
|
|
"""Satisfies :class:`~ix.ocr.client.OCRClient` structurally.
|
|
|
|
Parameters
|
|
----------
|
|
canned:
|
|
The :class:`OCRResult` to return from every :meth:`ocr` call.
|
|
raise_on_call:
|
|
If set, :meth:`ocr` raises this exception instead of returning.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
canned: OCRResult,
|
|
*,
|
|
raise_on_call: BaseException | None = None,
|
|
) -> None:
|
|
self._canned = canned
|
|
self._raise_on_call = raise_on_call
|
|
|
|
async def ocr(self, pages: list[Page]) -> OCRResult:
|
|
"""Return the canned result or raise the configured error."""
|
|
if self._raise_on_call is not None:
|
|
raise self._raise_on_call
|
|
return self._canned
|
|
|
|
|
|
__all__ = ["FakeOCRClient"]
|