fegger
570c8585a0
- Replaces duplicated _load_prompt() helpers with shared load_prompt(). - Classifier raises cleanly when no renderable pages exist. - scanned_print, handwritten, and mixed_unknown branches now force response_format=OcrResponse and parse via client.parse_json(). - Adds branch tests for multi-page OCR and corrected invoice handling.
60 lines
2.2 KiB
Python
60 lines
2.2 KiB
Python
"""Tests for the scanned_print, handwritten, and mixed_unknown branches."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from PIL import Image
|
|
|
|
from odoo_ocr.config import Settings
|
|
from odoo_ocr.pipeline.handwritten import process_handwritten
|
|
from odoo_ocr.pipeline.mixed_unknown import process_mixed_unknown
|
|
from odoo_ocr.pipeline.scanned_print import process_scanned_print
|
|
from tests.conftest import FakeVLMClient
|
|
|
|
|
|
def _fake_ocr_client(text: str = "Hello invoice 123") -> FakeVLMClient:
|
|
return FakeVLMClient(responses={"OCR engine": {"text": text}})
|
|
|
|
|
|
def _pages(count: int = 2) -> list[Image.Image]:
|
|
return [Image.new("RGB", (20, 20)) for _ in range(count)]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_scanned_print_multi_page() -> None:
|
|
settings = Settings()
|
|
client = _fake_ocr_client()
|
|
text = await process_scanned_print(Path("scan.jpg"), _pages(2), client, settings)
|
|
assert "--- Page 1 ---" in text
|
|
assert "--- Page 2 ---" in text
|
|
assert text.count("Hello invoice 123") == 2
|
|
assert all(call["model"] == settings.models.ocr for call in client.calls)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_scanned_print_rejects_invalid_json() -> None:
|
|
"""Branches no longer silently fall back to raw content; invalid JSON fails."""
|
|
client = FakeVLMClient(responses={"OCR engine": "plain text without json"})
|
|
with pytest.raises(ValueError, match="Response does not match schema"):
|
|
await process_scanned_print(Path("scan.jpg"), _pages(1), client, Settings())
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_handwritten_extracts_text() -> None:
|
|
settings = Settings()
|
|
client = _fake_ocr_client("handwritten total 42")
|
|
text = await process_handwritten(Path("hand.jpg"), _pages(1), client, settings)
|
|
assert "handwritten total 42" in text
|
|
assert client.calls[0]["model"] == settings.models.ocr
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mixed_unknown_extracts_text() -> None:
|
|
settings = Settings()
|
|
client = _fake_ocr_client("mixed content text")
|
|
text = await process_mixed_unknown(Path("mixed.jpg"), _pages(1), client, settings)
|
|
assert "mixed content text" in text
|
|
assert client.calls[0]["model"] == settings.models.ocr
|