test(ocr): add failing tests for spell_check module

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-04-17 16:51:38 +02:00
parent 30a6cbeb7f
commit 47f9a0bf73

View File

@@ -0,0 +1,89 @@
"""Tests for OCR spell-check post-processing."""
import pytest
from spell_check import correct_text, load_spell_checker
@pytest.fixture(autouse=True)
def ensure_loaded():
load_spell_checker()
def test_known_german_word_passes_through():
assert correct_text("Haus") == "Haus"
def test_obvious_gibberish_replaced_with_marker():
assert correct_text("xqzwrpvmk") == "[unleserlich]"
def test_short_word_exempt_from_check():
assert correct_text("im") == "im"
assert correct_text("der") == "der"
assert correct_text("zu") == "zu"
def test_unleserlich_marker_preserved():
assert correct_text("[unleserlich]") == "[unleserlich]"
def test_mixed_text_correct_and_gibberish():
result = correct_text("Haus xqzwrpvmk Garten")
assert result == "Haus [unleserlich] Garten"
def test_adjacent_gibberish_words_collapsed_to_one_marker():
result = correct_text("[unleserlich] xqzwrpvmk Haus")
assert result == "[unleserlich] Haus"
def test_empty_string_returns_empty():
assert correct_text("") == ""
def test_whitespace_only_returns_unchanged():
assert correct_text(" ") == " "
def test_existing_marker_not_doubled():
result = correct_text("[unleserlich] Haus [unleserlich]")
assert result == "[unleserlich] Haus [unleserlich]"
def test_historical_word_passes_through():
assert correct_text("Thür") == "Thür"
def test_correctable_ocr_error_gets_corrected():
result = correct_text("Hauus")
assert result == "Haus[?]"
def test_sentence_with_multiple_corrections():
result = correct_text("Thür Hauus xqzwrpvmk Garten")
assert result == "Thür Haus[?] [unleserlich] Garten"
def test_capitalization_preserved_on_correction():
# "Freunnd" (doubled n) — OCR duplication error for "Freund"
result = correct_text("Freunnd")
assert result != "Freunnd"
assert result != "[unleserlich]"
assert result[0].isupper()
def test_raises_runtime_error_when_not_loaded(monkeypatch):
import spell_check as sc
monkeypatch.setattr(sc, "_spell", None)
with pytest.raises(RuntimeError, match="not loaded"):
correct_text("test")
def test_punctuation_attached_token_passes_through():
assert correct_text("Haus,") == "Haus,"
assert correct_text("Garten.") == "Garten."
def test_numeric_token_passes_through():
assert correct_text("1870er") == "1870er"
assert correct_text("18.") == "18."