feat: Add SpellBackwardDataset with word reversal and length filtering

This commit is contained in:
Andreas Koepf (aider) 2025-01-26 11:40:47 +01:00
parent f604c484b1
commit b18bede2bf
3 changed files with 97 additions and 1 deletions

View file

@ -54,6 +54,60 @@ def test_word_reversal_dataset_items():
assert answer_words == list(reversed(question_words))
def test_spell_backward_config_validation():
"""Test that invalid configs raise appropriate errors"""
with pytest.raises(AssertionError):
config = SpellBackwardConfig(min_word_len=0)
config.validate()
def test_spell_backward_dataset_deterministic():
"""Test that dataset generates same items with same seed"""
config = SpellBackwardConfig(seed=42, size=10)
dataset1 = SpellBackwardDataset(config)
dataset2 = SpellBackwardDataset(config)
for i in range(len(dataset1)):
assert dataset1[i] == dataset2[i]
def test_spell_backward_dataset_items():
"""Test basic properties of generated items"""
config = SpellBackwardConfig(min_word_len=3, size=10, seed=42)
dataset = SpellBackwardDataset(config)
for i in range(len(dataset)):
item = dataset[i]
# Check item structure
assert isinstance(item, dict)
assert "question" in item
assert "answer" in item
assert "metadata" in item
# Check metadata
assert "word" in item["metadata"]
assert "word_len" in item["metadata"]
# Verify word length constraint
word = item["metadata"]["word"]
assert len(word) >= config.min_word_len
# Verify answer is correct
assert item["answer"] == word[::-1]
def test_spell_backward_dataset_iteration():
"""Test that iteration respects dataset size"""
config = SpellBackwardConfig(size=5, seed=42)
dataset = SpellBackwardDataset(config)
items = list(dataset)
assert len(items) == config.size
# Test multiple iterations yield same items
assert items == list(dataset)
def test_word_reversal_dataset_iteration():
"""Test that iteration respects dataset size"""
config = WordReversalConfig(size=5, seed=42)