"""稀疏向量编码器单元测试"""

from app.core.sparse import SPARSE_DIM, SparseEncoder


class TestSparseEncoder:
    """SparseEncoder.encode / encode_batch 行为"""

    def setup_method(self):
        self.encoder = SparseEncoder()

    def test_deterministic(self):
        """同一文本多次编码结果完全一致"""
        text = "人工智能 artificial intelligence 2024"
        assert self.encoder.encode(text) == self.encoder.encode(text)

    def test_indices_sorted_unique(self):
        """indices 升序且无重复，与 values 等长，且都在 [0, SPARSE_DIM) 内"""
        indices, values = self.encoder.encode("向量检索与关键词检索相结合 hybrid search 123")
        assert indices == sorted(indices)
        assert len(indices) == len(set(indices))
        assert len(indices) == len(values)
        assert all(0 <= idx < SPARSE_DIM for idx in indices)
        assert all(v > 0 for v in values)

    def test_mixed_text_non_empty(self):
        """中英文混合文本产生非空向量"""
        indices, values = self.encoder.encode("使用 Qdrant 存储向量")
        assert len(indices) > 0
        assert len(values) > 0

    def test_empty_string(self):
        """空字符串返回空向量"""
        assert self.encoder.encode("") == ([], [])

    def test_different_texts_differ(self):
        """不同文本产生不同向量"""
        assert self.encoder.encode("机器学习") != self.encoder.encode("深度学习")

    def test_english_case_insensitive(self):
        """英文词小写化：大小写不同编码结果一致"""
        assert self.encoder.encode("Hello") == self.encoder.encode("hello")

    def test_tf_weighting(self):
        """词频越高权重越大（1 + log(tf)）"""
        once = dict(zip(*self.encoder.encode("apple"), strict=True))
        twice = dict(zip(*self.encoder.encode("apple apple"), strict=True))
        assert once.keys() == twice.keys()
        for idx in once:
            assert twice[idx] > once[idx]

    def test_batch_matches_single(self):
        """encode_batch 与逐条 encode 结果一致"""
        texts = ["人工智能", "vector search", ""]
        batch = self.encoder.encode_batch(texts)
        singles = [self.encoder.encode(t) for t in texts]
        assert batch == singles